Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Flush TLB if PGD entry is changed in i386 PAE mode
  x86, dumpstack: Correct stack dump info when frame pointer is available
  x86: Clean up csum-copy_64.S a bit
  x86: Fix common misspellings
  x86: Fix misspelling and align params
  x86: Use PentiumPro-optimized partial_csum() on VIA C7

61 files changed, 231 insertions, 234 deletions

diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 7fbbaf85f5b7..48c13b8ab90c 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -189,13 +189,13 @@ ACPI
 
 PCI
 
-  pci=off       Don't use PCI
-  pci=conf1     Use conf1 access.
-  pci=conf2     Use conf2 access.
-  pci=rom       Assign ROMs.
-  pci=assign-busses    Assign busses
-  pci=irqmask=MASK             Set PCI interrupt mask to MASK
-  pci=lastbus=NUMBER           Scan upto NUMBER busses, no matter what the mptable says.
+  pci=off               Don't use PCI
+  pci=conf1             Use conf1 access.
+  pci=conf2             Use conf2 access.
+  pci=rom               Assign ROMs.
+  pci=assign-busses     Assign busses
+  pci=irqmask=MASK      Set PCI interrupt mask to MASK
+  pci=lastbus=NUMBER    Scan up to NUMBER busses, no matter what the mptable says.
   pci=noacpi            Don't use ACPI to set up PCI interrupt routing.
 
 IOMMU (input/output memory management unit)
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index ed47e6e1747f..d161e939df62 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -326,7 +326,7 @@ config X86_PPRO_FENCE
           Old PentiumPro multiprocessor systems had errata that could cause
           memory operations to violate the x86 ordering standard in rare cases.
           Enabling this option will attempt to work around some (but not all)
-          occurances of this problem, at the cost of much heavier spinlock and
+          occurrences of this problem, at the cost of much heavier spinlock and
           memory barrier operations.
 
           If unsure, say n here. Even distro kernels should think twice before
@@ -366,7 +366,7 @@ config X86_INTEL_USERCOPY
 
 config X86_USE_PPRO_CHECKSUM
         def_bool y
-        depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
+        depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
 
 config X86_USE_3DNOW
         def_bool y
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 8fe2a4966b7a..adcf794b22e2 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1346,7 +1346,7 @@ _zero_cipher_left_decrypt:
         and     $15, %r13                               # %r13 = arg4 (mod 16)
         je      _multiple_of_16_bytes_decrypt
 
-        # Handle the last <16 byte block seperately
+        # Handle the last <16 byte block separately
 
         paddd ONE(%rip), %xmm0         # increment CNT to get Yn
         movdqa SHUF_MASK(%rip), %xmm10
@@ -1355,7 +1355,7 @@ _zero_cipher_left_decrypt:
         ENCRYPT_SINGLE_BLOCK  %xmm0, %xmm1    # E(K, Yn)
         sub $16, %r11
         add %r13, %r11
-        movdqu (%arg3,%r11,1), %xmm1   # recieve the last <16 byte block
+        movdqu (%arg3,%r11,1), %xmm1   # receive the last <16 byte block
         lea SHIFT_MASK+16(%rip), %r12
         sub %r13, %r12
 # adjust the shuffle mask pointer to be able to shift 16-%r13 bytes
@@ -1607,7 +1607,7 @@ _zero_cipher_left_encrypt:
         and     $15, %r13                       # %r13 = arg4 (mod 16)
         je      _multiple_of_16_bytes_encrypt
 
-         # Handle the last <16 Byte block seperately
+         # Handle the last <16 Byte block separately
         paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
         movdqa SHUF_MASK(%rip), %xmm10
         PSHUFB_XMM %xmm10, %xmm0
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 62f084478f7e..4e12668711e5 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -71,7 +71,7 @@ static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
  * Read/Write    : ReadOnly, ReadWrite
  * Presence      : NotPresent
  *
- * Within a catagory, the attributes are mutually exclusive.
+ * Within a category, the attributes are mutually exclusive.
  *
  * The implementation of this API will take care of various aspects that
  * are associated with changing such attributes, such as:
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 518bbbb9ee59..fe2cc6e105fa 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,7 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_registers(struct pt_regs *regs);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-                       unsigned long *sp);
+                       unsigned long *sp, unsigned long bp);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern void show_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 07f46016d3ff..4886a68f267e 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -29,8 +29,8 @@ void arch_trigger_all_cpu_backtrace(void);
  * external nmis, because the local ones are more frequent.
  *
  * Also setup some default high/normal/low settings for
- * subsystems to registers with.  Using 4 bits to seperate
- * the priorities.  This can go alot higher if needed be.
+ * subsystems to registers with.  Using 4 bits to separate
+ * the priorities.  This can go a lot higher if needed be.
  */
 
 #define NMI_LOCAL_SHIFT         16      /* randomly picked */
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index 6d8723a766cc..af788496020b 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -38,7 +38,7 @@
 #define K8_NOP8 K8_NOP4 K8_NOP4
 
 /* K7 nops
-   uses eax dependencies (arbitary choice)
+   uses eax dependencies (arbitrary choice)
    1: nop
    2: movl %eax,%eax
    3: leal (,%eax,1),%eax
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index f482010350fb..5ca6801b75f3 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -20,7 +20,7 @@ extern struct olpc_platform_t olpc_platform_info;
 
 /*
  * OLPC board IDs contain the major build number within the mask 0x0ff0,
- * and the minor build number withing 0x000f.  Pre-builds have a minor
+ * and the minor build number within 0x000f.  Pre-builds have a minor
  * number less than 8, and normal builds start at 8.  For example, 0x0B10
  * is a PreB1, and 0x0C18 is a C1.
  */
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index cc29086e30cd..56fd9e3abbda 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -1,5 +1,5 @@
 /*
- * Netburst Perfomance Events (P4, old Xeon)
+ * Netburst Performance Events (P4, old Xeon)
  */
 
 #ifndef PERF_EVENT_P4_H
@@ -9,7 +9,7 @@
 #include <linux/bitops.h>
 
 /*
- * NetBurst has perfomance MSRs shared between
+ * NetBurst has performance MSRs shared between
  * threads if HT is turned on, ie for both logical
  * processors (mem: in turn in Atom with HT support
  * perf-MSRs are not shared and every thread has its
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 94b979d1b58d..effff47a3c82 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -69,8 +69,6 @@ static inline void native_pmd_clear(pmd_t *pmd)
 
 static inline void pud_clear(pud_t *pudp)
 {
-        unsigned long pgd;
-
         set_pud(pudp, __pud(0));
 
         /*
@@ -79,13 +77,10 @@ static inline void pud_clear(pud_t *pudp)
          * section 8.1: in PAE mode we explicitly have to flush the
          * TLB via cr3 if the top-level pgd is changed...
          *
-         * Make sure the pud entry we're updating is within the
-         * current pgd to avoid unnecessary TLB flushes.
+         * Currently all places where pud_clear() is called either have
+         * flush_tlb_mm() followed or don't need TLB flush (x86_64 code or
+         * pud_clear_bad()), so we don't need TLB flush here.
          */
-        pgd = read_cr3();
-        if (__pa(pudp) >= pgd && __pa(pudp) <
-            (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
-                write_cr3(pgd);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 7a3e836eb2a9..a898a2b6e10c 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -7,7 +7,7 @@
  */
 #define X86_EFLAGS_CF   0x00000001 /* Carry Flag */
 #define X86_EFLAGS_PF   0x00000004 /* Parity Flag */
-#define X86_EFLAGS_AF   0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_AF   0x00000010 /* Auxiliary carry Flag */
 #define X86_EFLAGS_ZF   0x00000040 /* Zero Flag */
 #define X86_EFLAGS_SF   0x00000080 /* Sign Flag */
 #define X86_EFLAGS_TF   0x00000100 /* Trap Flag */
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 52b098a6eebb..7b0a55a88851 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -31,7 +31,7 @@
 #define R12 24
 #define RBP 32
 #define RBX 40
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here*/
 #define R11 48
 #define R10 56
 #define R9 64
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 78cd1ea94500..1babf8adecdf 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -73,7 +73,7 @@ struct pt_regs {
         unsigned long r12;
         unsigned long rbp;
         unsigned long rbx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
+/* arguments: non interrupts/non tracing syscalls only save up to here*/
         unsigned long r11;
         unsigned long r10;
         unsigned long r9;
@@ -103,7 +103,7 @@ struct pt_regs {
         unsigned long r12;
         unsigned long bp;
         unsigned long bx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
+/* arguments: non interrupts/non tracing syscalls only save up to here*/
         unsigned long r11;
         unsigned long r10;
         unsigned long r9;
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 52b5c7ed3608..d7e89c83645d 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -47,7 +47,7 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-                unsigned long *stack,
+                unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data);
 
 #ifdef CONFIG_X86_32
@@ -86,11 +86,11 @@ stack_frame(struct task_struct *task, struct pt_regs *regs)
 
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                   unsigned long *stack, char *log_lvl);
+                   unsigned long *stack, unsigned long bp, char *log_lvl);
 
 extern void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                   unsigned long *sp, char *log_lvl);
+                   unsigned long *sp, unsigned long bp, char *log_lvl);
 
 extern unsigned int code_bytes;
 
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 1ca132fc0d03..83e2efd181e2 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -35,7 +35,7 @@ static inline cycles_t get_cycles(void)
 static __always_inline cycles_t vget_cycles(void)
 {
         /*
-         * We only do VDSOs on TSC capable CPUs, so this shouldnt
+         * We only do VDSOs on TSC capable CPUs, so this shouldn't
          * access boot_cpu_data (which is not VDSO-safe):
          */
 #ifndef CONFIG_X86_TSC
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 1c10c88ee4e1..5d4922ad4b9b 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -86,7 +86,7 @@ DEFINE_GUEST_HANDLE(void);
  * The privilege level specifies which modes may enter a trap via a software
  * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
  * privilege levels as follows:
- *  Level == 0: Noone may enter
+ *  Level == 0: No one may enter
  *  Level == 1: Kernel may enter
  *  Level == 2: Kernel may enter
  *  Level == 3: Everyone may enter
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4db35544de73..4a234677e213 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -199,7 +199,7 @@ void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
-   self modifying code. This implies that assymetric systems where
+   self modifying code. This implies that asymmetric systems where
    APs have less capabilities than the boot processor are not handled.
    Tough. Make sure you disable such features by hand. */
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 7b1e8e10b89c..86d1ad4962a7 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -73,7 +73,7 @@ static u32 __init allocate_aperture(void)
         /*
          * using 512M as goal, in case kexec will load kernel_big
          * that will do the on position decompress, and  could overlap with
-         * that positon with gart that is used.
+         * that position with gart that is used.
          * sequende:
          * kernel_small
          * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 795ba310cb1d..180ca240e03c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1886,7 +1886,7 @@ void disable_IO_APIC(void)
          *
          * With interrupt-remapping, for now we will use virtual wire A mode,
          * as virtual wire B is little complex (need to configure both
-         * IOAPIC RTE aswell as interrupt-remapping table entry).
+         * IOAPIC RTE as well as interrupt-remapping table entry).
          * As this gets called during crash dump, keep this simple for now.
          */
         if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) {
@@ -2905,7 +2905,7 @@ void __init setup_IO_APIC(void)
 }
 
 /*
- *      Called after all the initialization is done. If we didnt find any
+ *      Called after all the initialization is done. If we didn't find any
  *      APIC bugs then we can allow the modify fast path
  */
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 9079926a5b18..0b4be431c620 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -66,7 +66,7 @@
  *    1.5: Fix segment register reloading (in case of bad segments saved
  *         across BIOS call).
  *         Stephen Rothwell
- *    1.6: Cope with complier/assembler differences.
+ *    1.6: Cope with compiler/assembler differences.
  *         Only try to turn off the first display device.
  *         Fix OOPS at power off with no APM BIOS by Jan Echternach
  *                   <echter@informatik.uni-rostock.de>
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index 03162dac6271..cf48cdd6907d 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -444,7 +444,7 @@ static int __cpuinit longhaul_get_ranges(void)
                 return -EINVAL;
         }
         /* Get max multiplier - as we always did.
-         * Longhaul MSR is usefull only when voltage scaling is enabled.
+         * Longhaul MSR is useful only when voltage scaling is enabled.
          * C3 is booting at max anyway. */
         maxmult = mult;
         /* Get min multiplier */
@@ -1011,7 +1011,7 @@ static void __exit longhaul_exit(void)
  * trigger frequency transition in some cases. */
 module_param(disable_acpi_c3, int, 0644);
 MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support");
-/* Change CPU voltage with frequency. Very usefull to save
+/* Change CPU voltage with frequency. Very useful to save
  * power, but most VIA C3 processors aren't supporting it. */
 module_param(scale_voltage, int, 0644);
 MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 1ae4133e6bd6..2368e38327b3 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1275,7 +1275,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 
         if (powernow_k8_cpu_init_acpi(data)) {
                 /*
-                 * Use the PSB BIOS structure. This is only availabe on
+                 * Use the PSB BIOS structure. This is only available on
                  * an UP version, and is deprecated by AMD.
                  */
                 if (num_online_cpus() != 1) {
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index 8abd869baabf..91bc25b67bc1 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
         result = speedstep_smi_ownership();
         if (result) {
-                dprintk("fails in aquiring ownership of a SMI interface.\n");
+                dprintk("fails in acquiring ownership of a SMI interface.\n");
                 return -EINVAL;
         }
 
@@ -360,7 +360,7 @@ static int speedstep_resume(struct cpufreq_policy *policy)
         int result = speedstep_smi_ownership();
 
         if (result)
-                dprintk("fails in re-aquiring ownership of a SMI interface.\n");
+                dprintk("fails in re-acquiring ownership of a SMI interface.\n");
 
         return result;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index a77971979564..0ed633c5048b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -32,7 +32,7 @@ static void inject_mce(struct mce *m)
 {
         struct mce *i = &per_cpu(injectm, m->extcpu);
 
-        /* Make sure noone reads partially written injectm */
+        /* Make sure no one reads partially written injectm */
         i->finished = 0;
         mb();
         m->finished = 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d916183b7f9c..ab1122998dba 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -881,7 +881,7 @@ reset:
  * Check if the address reported by the CPU is in a format we can parse.
  * It would be possible to add code for most other cases, but all would
  * be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses upto page granuality for now.
+ * parser). So only support physical addresses up to page granuality for now.
  */
 static int mce_usable_address(struct mce *m)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9f27228ceffd..a71efcdbb092 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -1,6 +1,6 @@
 /*
  * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong
- * because MTRRs can span upto 40 bits (36bits on most modern x86)
+ * because MTRRs can span up to 40 bits (36bits on most modern x86)
  */
 #define DEBUG
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e8dbe179587f..87eab4a27dfc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1109,7 +1109,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
 
         /*
          * If group events scheduling transaction was started,
-         * skip the schedulability test here, it will be peformed
+         * skip the schedulability test here, it will be performed
          * at commit time (->commit_txn) as a whole
          */
         if (cpuc->group_flag & PERF_EVENT_TXN)
@@ -1790,7 +1790,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
         perf_callchain_store(entry, regs->ip);
 
-        dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
+        dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3769ac822f96..0811f5ebfba6 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1,5 +1,5 @@
 /*
- * Netburst Perfomance Events (P4, old Xeon)
+ * Netburst Performance Events (P4, old Xeon)
  *
  *  Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org>
  *  Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com>
@@ -679,7 +679,7 @@ static int p4_validate_raw_event(struct perf_event *event)
          */
 
         /*
-         * if an event is shared accross the logical threads
+         * if an event is shared across the logical threads
          * the user needs special permissions to be able to use it
          */
         if (p4_ht_active() && p4_event_bind_map[v].shared) {
@@ -790,13 +790,13 @@ static void p4_pmu_disable_pebs(void)
          *
          * It's still allowed that two threads setup same cache
          * events so we can't simply clear metrics until we knew
-         * noone is depending on us, so we need kind of counter
+         * no one is depending on us, so we need kind of counter
          * for "ReplayEvent" users.
          *
          * What is more complex -- RAW events, if user (for some
          * reason) will pass some cache event metric with improper
          * event opcode -- it's fine from hardware point of view
-         * but completely nonsence from "meaning" of such action.
+         * but completely nonsense from "meaning" of such action.
          *
          * So at moment let leave metrics turned on forever -- it's
          * ok for now but need to be revisited!
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 227b0448960d..d22d0c4edcfd 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -86,7 +86,7 @@ static void __init vmware_platform_setup(void)
 }
 
 /*
- * While checking the dmi string infomation, just checking the product
+ * While checking the dmi string information, just checking the product
  * serial key should be enough, as this will always have a VMware
  * specific string when running under VMware hypervisor.
  */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 220a1c11cfde..999e2793590b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
 
 void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, char *log_lvl)
+                unsigned long *stack, unsigned long bp, char *log_lvl)
 {
         printk("%sCall Trace:\n", log_lvl);
-        dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
+        dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack)
+                unsigned long *stack, unsigned long bp)
 {
-        show_trace_log_lvl(task, regs, stack, "");
+        show_trace_log_lvl(task, regs, stack, bp, "");
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-        show_stack_log_lvl(task, NULL, sp, "");
+        show_stack_log_lvl(task, NULL, sp, 0, "");
 }
 
 /*
@@ -197,14 +197,16 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
+        unsigned long bp;
         unsigned long stack;
 
+        bp = stack_frame(current, NULL);
         printk("Pid: %d, comm: %.20s %s %s %.*s\n",
                 current->pid, current->comm, print_tainted(),
                 init_utsname()->release,
                 (int)strcspn(init_utsname()->version, " "),
                 init_utsname()->version);
-        show_trace(NULL, NULL, &stack);
+        show_trace(NULL, NULL, &stack, bp);
 }
 EXPORT_SYMBOL(dump_stack);
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 74cc1eda384b..3b97a80ce329 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,12 +17,11 @@
 #include <asm/stacktrace.h>
 
 
-void dump_trace(struct task_struct *task,
-                struct pt_regs *regs, unsigned long *stack,
+void dump_trace(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data)
 {
         int graph = 0;
-        unsigned long bp;
 
         if (!task)
                 task = current;
@@ -35,7 +34,9 @@ void dump_trace(struct task_struct *task,
                         stack = (unsigned long *)task->thread.sp;
         }
 
-        bp = stack_frame(task, regs);
+        if (!bp)
+                bp = stack_frame(task, regs);
+
         for (;;) {
                 struct thread_info *context;
 
@@ -55,7 +56,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                   unsigned long *sp, char *log_lvl)
+                   unsigned long *sp, unsigned long bp, char *log_lvl)
 {
         unsigned long *stack;
         int i;
@@ -77,7 +78,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
                 touch_nmi_watchdog();
         }
         printk(KERN_CONT "\n");
-        show_trace_log_lvl(task, regs, sp, log_lvl);
+        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
 
@@ -102,7 +103,7 @@ void show_registers(struct pt_regs *regs)
                 u8 *ip;
 
                 printk(KERN_EMERG "Stack:\n");
-                show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
+                show_stack_log_lvl(NULL, regs, &regs->sp, 0, KERN_EMERG);
 
                 printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index a6b6fcf7f0ae..e71c98d3c0d2 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-void dump_trace(struct task_struct *task,
-                struct pt_regs *regs, unsigned long *stack,
+void dump_trace(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data)
 {
         const unsigned cpu = get_cpu();
@@ -150,7 +150,6 @@ void dump_trace(struct task_struct *task,
         struct thread_info *tinfo;
         int graph = 0;
         unsigned long dummy;
-        unsigned long bp;
 
         if (!task)
                 task = current;
@@ -161,7 +160,8 @@ void dump_trace(struct task_struct *task,
                         stack = (unsigned long *)task->thread.sp;
         }
 
-        bp = stack_frame(task, regs);
+        if (!bp)
+                bp = stack_frame(task, regs);
         /*
          * Print function call entries in all stacks, starting at the
          * current stack address. If the stacks consist of nested
@@ -225,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                   unsigned long *sp, char *log_lvl)
+                   unsigned long *sp, unsigned long bp, char *log_lvl)
 {
         unsigned long *irq_stack_end;
         unsigned long *irq_stack;
@@ -269,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
         preempt_enable();
 
         printk(KERN_CONT "\n");
-        show_trace_log_lvl(task, regs, sp, log_lvl);
+        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
 void show_registers(struct pt_regs *regs)
@@ -298,7 +298,7 @@ void show_registers(struct pt_regs *regs)
 
                 printk(KERN_EMERG "Stack:\n");
                 show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-                                   KERN_EMERG);
+                                   0, KERN_EMERG);
 
                 printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b72b4a6466a9..8a445a0c989e 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -18,7 +18,7 @@
  * A note on terminology:
  * - top of stack: Architecture defined interrupt frame from SS to RIP
  * at the top of the kernel process stack.
- * - partial stack frame: partially saved registers upto R11.
+ * - partial stack frame: partially saved registers up to R11.
  * - full stack frame: Like partial stack frame, but all register saved.
  *
  * Some macro usage:
@@ -422,7 +422,7 @@ ENTRY(ret_from_fork)
 END(ret_from_fork)
 
 /*
- * System call entry. Upto 6 arguments in registers are supported.
+ * System call entry. Up to 6 arguments in registers are supported.
  *
  * SYSCALL does not save anything on the stack and does not change the
  * stack pointer.
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e60c38cc0eed..12aff2537682 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -145,7 +145,7 @@ EXPORT_SYMBOL_GPL(fpu_finit);
  * The _current_ task is using the FPU for the first time
  * so initialize it and set the mxcsr to its default
  * value at reset if we support XMM instructions and then
- * remeber the current task has used the FPU.
+ * remember the current task has used the FPU.
  */
 int init_fpu(struct task_struct *tsk)
 {
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 9974d21048fd..72090705a656 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -172,7 +172,7 @@ asmlinkage void do_softirq(void)
 
                 call_on_stack(__do_softirq, isp);
                 /*
-                 * Shouldnt happen, we returned above if in_interrupt():
+                 * Shouldn't happen, we returned above if in_interrupt():
                  */
                 WARN_ON_ONCE(softirq_count());
         }
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 7c64c420a9f6..dba0b36941a5 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -278,7 +278,7 @@ static int hw_break_release_slot(int breakno)
                 pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
                 if (dbg_release_bp_slot(*pevent))
                         /*
-                         * The debugger is responisble for handing the retry on
+                         * The debugger is responsible for handing the retry on
                          * remove failure.
                          */
                         return -1;
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 63eaf6596233..177183cbb6ae 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -259,7 +259,7 @@ static int __init mca_init(void)
         /*
          * WARNING: Be careful when making changes here. Putting an adapter
          * and the motherboard simultaneously into setup mode may result in
-         * damage to chips (according to The Indispensible PC Hardware Book
+         * damage to chips (according to The Indispensable PC Hardware Book
          * by Hans-Peter Messmer). Also, we disable system interrupts (so
          * that we are not disturbed in the middle of this).
          */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 01b0f6d06451..6f789a887c06 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -883,7 +883,7 @@ static int __init update_mp_table(void)
 
         if (!mpc_new_phys) {
                 unsigned char old, new;
-                /* check if we can change the postion */
+                /* check if we can change the position */
                 mpc->checksum = 0;
                 old = mpf_checksum((unsigned char *)mpc, mpc->length);
                 mpc->checksum = 0xff;
@@ -892,7 +892,7 @@ static int __init update_mp_table(void)
                         printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n");
                         return 0;
                 }
-                printk(KERN_INFO "use in-positon replacing\n");
+                printk(KERN_INFO "use in-position replacing\n");
         } else {
                 mpf->physptr = mpc_new_phys;
                 mpc_new = phys_to_virt(mpc_new_phys);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index f56a117cef68..e8c33a302006 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1279,7 +1279,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
 
         if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) {
                 /*
-                 * FIXME: properly scan for devices accross the
+                 * FIXME: properly scan for devices across the
                  * PCI-to-PCI bridge on every CalIOC2 port.
                  */
                 return 1;
@@ -1295,7 +1295,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
 
 /*
  * calgary_init_bitmap_from_tce_table():
- * Funtion for kdump case. In the second/kdump kernel initialize
+ * Function for kdump case. In the second/kdump kernel initialize
  * the bitmap based on the tce table entries obtained from first kernel
  */
 static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 99fa3adf0141..d46cbe46b7ab 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -87,7 +87,7 @@ void exit_thread(void)
 void show_regs(struct pt_regs *regs)
 {
         show_registers(regs);
-        show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
+        show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), 0);
 }
 
 void show_regs_common(void)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 938c8e10a19a..6515733a289d 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -73,7 +73,7 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-        dump_trace(current, NULL, NULL, &save_stack_ops, trace);
+        dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
@@ -81,14 +81,14 @@ EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
 {
-        dump_trace(current, regs, NULL, &save_stack_ops, trace);
+        dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-        dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
+        dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 58de45ee08b6..7977f0cfe339 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -166,7 +166,7 @@ static void enable_step(struct task_struct *child, bool block)
          * Make sure block stepping (BTF) is not enabled unless it should be.
          * Note that we don't try to worry about any is_setting_trap_flag()
          * instructions after the first when using block stepping.
-         * So noone should try to use debugger block stepping in a program
+         * So no one should try to use debugger block stepping in a program
          * that uses user-mode single stepping itself.
          */
         if (enable_single_step(child) && block) {
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 7e4515957a1c..8927486a4649 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -39,7 +39,7 @@ int __ref arch_register_cpu(int num)
         /*
          * CPU0 cannot be offlined due to several
          * restrictions and assumptions in kernel. This basically
-         * doesnt add a control file, one cannot attempt to offline
+         * doesn't add a control file, one cannot attempt to offline
          * BSP.
          *
          * Also certain PCI quirks require not to enable hotplug control
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ffe5755caa8b..9335bf7dd2e7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -427,7 +427,7 @@ unsigned long native_calibrate_tsc(void)
          * the delta to the previous read. We keep track of the min
          * and max values of that delta. The delta is mostly defined
          * by the IO time of the PIT access, so we can detect when a
-         * SMI/SMM disturbance happend between the two reads. If the
+         * SMI/SMM disturbance happened between the two reads. If the
          * maximum time is significantly larger than the minimum time,
          * then we discard the result and have another try.
          *
@@ -900,7 +900,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
  * timer based, instead of loop based, we don't block the boot
  * process while this longer calibration is done.
  *
- * If there are any calibration anomolies (too many SMIs, etc),
+ * If there are any calibration anomalies (too many SMIs, etc),
  * or the refined calibration is off by 1% of the fast early
  * calibration, we throw out the new calibration and use the
  * early calibration.
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 0edefc19a113..b9242bacbe59 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -18,7 +18,7 @@
  *      This file is expected to run in 32bit code.  Currently:
  *
  *      arch/x86/boot/compressed/head_64.S: Boot cpu verification
- *      arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ *      arch/x86/kernel/trampoline_64.S: secondary processor verification
  *      arch/x86/kernel/head_32.S: processor startup
  *
  *      verify_cpu, returns the status of longmode and SSE in register %eax.
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 547128546cc3..a3911343976b 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -53,7 +53,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
 
         /*
          * None of the feature bits are in init state. So nothing else
-         * to do for us, as the memory layout is upto date.
+         * to do for us, as the memory layout is up to date.
          */
         if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
                 return;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 751405097d8c..c6397795d865 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -346,7 +346,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                 return;
 
         /*
-         * we call mmu_set_spte() with host_writable = true beacuse that
+         * we call mmu_set_spte() with host_writable = true because that
          * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
          */
         mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
index fc7a101c4a35..abd86e865be3 100644
--- a/arch/x86/kvm/timer.c
+++ b/arch/x86/kvm/timer.c
@@ -25,7 +25,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 
         /*
          * There is a race window between reading and incrementing, but we do
-         * not care about potentially loosing timer events in the !reinject
+         * not care about potentially losing timer events in the !reinject
          * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
          * in vcpu_enter_guest.
          */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f1e4025f1ae2..58f517b59645 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1031,7 +1031,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
         /*
          * Special case: close write to TSC within 5 seconds of
          * another CPU is interpreted as an attempt to synchronize
-         * The 5 seconds is to accomodate host load / swapping as
+         * The 5 seconds is to accommodate host load / swapping as
          * well as any reset of TSC during the boot process.
          *
          * In that case, for a reliable TSC, we can match TSC offsets,
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index b9ec1c74943c..1cd608973ce5 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -397,7 +397,7 @@ static void lguest_load_tr_desc(void)
  * instead we just use the real "cpuid" instruction.  Then I pretty much turned
  * off feature bits until the Guest booted.  (Don't say that: you'll damage
  * lguest sales!)  Shut up, inner voice!  (Hey, just pointing out that this is
- * hardly future proof.)  Noone's listening!  They don't like you anyway,
+ * hardly future proof.)  No one's listening!  They don't like you anyway,
  * parenthetic weirdo!
  *
  * Replacing the cpuid so we can turn features off is great for the kernel, but
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index a460158b5ac5..99e482615195 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -117,7 +117,7 @@ ENDPROC(bad_from_user)
  * rdx count
  *
  * Output:
- * eax uncopied bytes or 0 if successfull.
+ * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_unrolled)
         CFI_STARTPROC
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index f0dba36578ea..fb903b758da8 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -1,6 +1,6 @@
 /*
- * Copyright 2002,2003 Andi Kleen, SuSE Labs.
- *      
+ * Copyright 2002, 2003 Andi Kleen, SuSE Labs.
+ *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file COPYING in the main directory of this archive
  * for more details. No warranty for anything given at all.
@@ -11,82 +11,82 @@
 
 /*
  * Checksum copy with exception handling.
- * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the 
+ * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the
  * destination is zeroed.
- * 
+ *
  * Input
  * rdi  source
  * rsi  destination
  * edx  len (32bit)
- * ecx  sum (32bit) 
+ * ecx  sum (32bit)
  * r8   src_err_ptr (int)
  * r9   dst_err_ptr (int)
  *
  * Output
  * eax  64bit sum. undefined in case of exception.
- * 
- * Wrappers need to take care of valid exception sum and zeroing.                
+ *
+ * Wrappers need to take care of valid exception sum and zeroing.
  * They also should align source or destination to 8 bytes.
  */
 
         .macro source
 10:
-        .section __ex_table,"a"
+        .section __ex_table, "a"
         .align 8
-        .quad 10b,.Lbad_source
+        .quad 10b, .Lbad_source
         .previous
         .endm
-                
+
         .macro dest
 20:
-        .section __ex_table,"a"
+        .section __ex_table, "a"
         .align 8
-        .quad 20b,.Lbad_dest
+        .quad 20b, .Lbad_dest
         .previous
         .endm
-                        
+
         .macro ignore L=.Lignore
 30:
-        .section __ex_table,"a"
+        .section __ex_table, "a"
         .align 8
-        .quad 30b,\L
+        .quad 30b, \L
         .previous
         .endm
-        
-                                
+
+
 ENTRY(csum_partial_copy_generic)
         CFI_STARTPROC
-        cmpl     $3*64,%edx
-        jle      .Lignore
+        cmpl    $3*64, %edx
+        jle     .Lignore
 
-.Lignore:               
-        subq  $7*8,%rsp
+.Lignore:
+        subq  $7*8, %rsp
         CFI_ADJUST_CFA_OFFSET 7*8
-        movq  %rbx,2*8(%rsp)
+        movq  %rbx, 2*8(%rsp)
         CFI_REL_OFFSET rbx, 2*8
-        movq  %r12,3*8(%rsp)
+        movq  %r12, 3*8(%rsp)
         CFI_REL_OFFSET r12, 3*8
-        movq  %r14,4*8(%rsp)
+        movq  %r14, 4*8(%rsp)
         CFI_REL_OFFSET r14, 4*8
-        movq  %r13,5*8(%rsp)
+        movq  %r13, 5*8(%rsp)
         CFI_REL_OFFSET r13, 5*8
-        movq  %rbp,6*8(%rsp)
+        movq  %rbp, 6*8(%rsp)
         CFI_REL_OFFSET rbp, 6*8
 
-        movq  %r8,(%rsp)
-        movq  %r9,1*8(%rsp)
-        
-        movl  %ecx,%eax
-        movl  %edx,%ecx
+        movq  %r8, (%rsp)
+        movq  %r9, 1*8(%rsp)
 
-        xorl  %r9d,%r9d
-        movq  %rcx,%r12
+        movl  %ecx, %eax
+        movl  %edx, %ecx
 
-        shrq  $6,%r12
-        jz    .Lhandle_tail       /* < 64 */
+        xorl  %r9d, %r9d
+        movq  %rcx, %r12
+
+        shrq  $6, %r12
+        jz      .Lhandle_tail       /* < 64 */
 
         clc
-        
+
         /* main loop. clear in 64 byte blocks */
         /* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
         /* r11: temp3, rdx: temp4, r12 loopcnt */
@@ -94,156 +94,156 @@ ENTRY(csum_partial_copy_generic)
         .p2align 4
 .Lloop:
         source
-        movq  (%rdi),%rbx
+        movq  (%rdi), %rbx
         source
-        movq  8(%rdi),%r8
+        movq  8(%rdi), %r8
         source
-        movq  16(%rdi),%r11
+        movq  16(%rdi), %r11
         source
-        movq  24(%rdi),%rdx
+        movq  24(%rdi), %rdx
 
         source
-        movq  32(%rdi),%r10
+        movq  32(%rdi), %r10
         source
-        movq  40(%rdi),%rbp
+        movq  40(%rdi), %rbp
         source
-        movq  48(%rdi),%r14
+        movq  48(%rdi), %r14
         source
-        movq  56(%rdi),%r13
-                
+        movq  56(%rdi), %r13
+
         ignore 2f
         prefetcht0 5*64(%rdi)
-2:                                                      
-        adcq  %rbx,%rax
-        adcq  %r8,%rax
-        adcq  %r11,%rax
-        adcq  %rdx,%rax
-        adcq  %r10,%rax
-        adcq  %rbp,%rax
-        adcq  %r14,%rax
-        adcq  %r13,%rax
+2:
+        adcq  %rbx, %rax
+        adcq  %r8, %rax
+        adcq  %r11, %rax
+        adcq  %rdx, %rax
+        adcq  %r10, %rax
+        adcq  %rbp, %rax
+        adcq  %r14, %rax
+        adcq  %r13, %rax
 
         decl %r12d
-        
+
         dest
-        movq %rbx,(%rsi)
+        movq %rbx, (%rsi)
         dest
-        movq %r8,8(%rsi)
+        movq %r8, 8(%rsi)
         dest
-        movq %r11,16(%rsi)
+        movq %r11, 16(%rsi)
         dest
-        movq %rdx,24(%rsi)
+        movq %rdx, 24(%rsi)
 
         dest
-        movq %r10,32(%rsi)
+        movq %r10, 32(%rsi)
         dest
-        movq %rbp,40(%rsi)
+        movq %rbp, 40(%rsi)
         dest
-        movq %r14,48(%rsi)
+        movq %r14, 48(%rsi)
         dest
-        movq %r13,56(%rsi)
-        
+        movq %r13, 56(%rsi)
+
 3:
-        
-        leaq 64(%rdi),%rdi
-        leaq 64(%rsi),%rsi
 
-        jnz   .Lloop
+        leaq 64(%rdi), %rdi
+        leaq 64(%rsi), %rsi
 
-        adcq  %r9,%rax
+        jnz     .Lloop
 
-        /* do last upto 56 bytes */
+        adcq  %r9, %rax
+
+        /* do last up to 56 bytes */
 .Lhandle_tail:
         /* ecx: count */
-        movl %ecx,%r10d
-        andl $63,%ecx
-        shrl $3,%ecx
-        jz       .Lfold
+        movl %ecx, %r10d
+        andl $63, %ecx
+        shrl $3, %ecx
+        jz      .Lfold
         clc
         .p2align 4
-.Lloop_8:       
+.Lloop_8:
         source
-        movq (%rdi),%rbx
-        adcq %rbx,%rax
+        movq (%rdi), %rbx
+        adcq %rbx, %rax
         decl %ecx
         dest
-        movq %rbx,(%rsi)
-        leaq 8(%rsi),%rsi /* preserve carry */
-        leaq 8(%rdi),%rdi
+        movq %rbx, (%rsi)
+        leaq 8(%rsi), %rsi /* preserve carry */
+        leaq 8(%rdi), %rdi
         jnz     .Lloop_8
-        adcq %r9,%rax   /* add in carry */
+        adcq %r9, %rax  /* add in carry */
 
 .Lfold:
         /* reduce checksum to 32bits */
-        movl %eax,%ebx
-        shrq $32,%rax
-        addl %ebx,%eax
-        adcl %r9d,%eax
+        movl %eax, %ebx
+        shrq $32, %rax
+        addl %ebx, %eax
+        adcl %r9d, %eax
 
-        /* do last upto 6 bytes */      
+        /* do last up to 6 bytes */
 .Lhandle_7:
-        movl %r10d,%ecx
-        andl $7,%ecx
-        shrl $1,%ecx
+        movl %r10d, %ecx
+        andl $7, %ecx
+        shrl $1, %ecx
         jz   .Lhandle_1
-        movl $2,%edx
-        xorl %ebx,%ebx
-        clc  
+        movl $2, %edx
+        xorl %ebx, %ebx
+        clc
         .p2align 4
-.Lloop_1:       
+.Lloop_1:
         source
-        movw (%rdi),%bx
-        adcl %ebx,%eax
+        movw (%rdi), %bx
+        adcl %ebx, %eax
         decl %ecx
         dest
-        movw %bx,(%rsi)
-        leaq 2(%rdi),%rdi
-        leaq 2(%rsi),%rsi
+        movw %bx, (%rsi)
+        leaq 2(%rdi), %rdi
+        leaq 2(%rsi), %rsi
         jnz .Lloop_1
-        adcl %r9d,%eax  /* add in carry */
-        
+        adcl %r9d, %eax /* add in carry */
+
         /* handle last odd byte */
 .Lhandle_1:
-        testl $1,%r10d
+        testl $1, %r10d
         jz    .Lende
-        xorl  %ebx,%ebx
+        xorl  %ebx, %ebx
         source
-        movb (%rdi),%bl
+        movb (%rdi), %bl
         dest
-        movb %bl,(%rsi)
-        addl %ebx,%eax
-        adcl %r9d,%eax          /* carry */
-                        
+        movb %bl, (%rsi)
+        addl %ebx, %eax
+        adcl %r9d, %eax         /* carry */
+
         CFI_REMEMBER_STATE
 .Lende:
-        movq 2*8(%rsp),%rbx
+        movq 2*8(%rsp), %rbx
         CFI_RESTORE rbx
-        movq 3*8(%rsp),%r12
+        movq 3*8(%rsp), %r12
         CFI_RESTORE r12
-        movq 4*8(%rsp),%r14
+        movq 4*8(%rsp), %r14
         CFI_RESTORE r14
-        movq 5*8(%rsp),%r13
+        movq 5*8(%rsp), %r13
         CFI_RESTORE r13
-        movq 6*8(%rsp),%rbp
+        movq 6*8(%rsp), %rbp
         CFI_RESTORE rbp
-        addq $7*8,%rsp
+        addq $7*8, %rsp
         CFI_ADJUST_CFA_OFFSET -7*8
         ret
         CFI_RESTORE_STATE
 
         /* Exception handlers. Very simple, zeroing is done in the wrappers */
 .Lbad_source:
-        movq (%rsp),%rax
-        testq %rax,%rax
+        movq (%rsp), %rax
+        testq %rax, %rax
         jz   .Lende
-        movl $-EFAULT,(%rax)
+        movl $-EFAULT, (%rax)
         jmp  .Lende
-        
+
 .Lbad_dest:
-        movq 8(%rsp),%rax
-        testq %rax,%rax
-        jz   .Lende     
-        movl $-EFAULT,(%rax)
+        movq 8(%rsp), %rax
+        testq %rax, %rax
+        jz   .Lende
+        movl $-EFAULT, (%rax)
         jmp .Lende
         CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index bf51144d97e1..9845371c5c36 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -84,7 +84,7 @@ static unsigned do_csum(const unsigned char *buff, unsigned len)
                                 count64--;
                         }
 
-                        /* last upto 7 8byte blocks */
+                        /* last up to 7 8byte blocks */
                         count %= 8; 
                         while (count) { 
                                 asm("addq %1,%0\n\t"
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 069ce7c37c01..d4203988504a 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -326,7 +326,7 @@ try_again:
         if (mm->free_area_cache < len)
                 goto fail;
 
-        /* either no address requested or cant fit in requested address hole */
+        /* either no address requested or can't fit in requested address hole */
         addr = (mm->free_area_cache - len) & huge_page_mask(h);
         do {
                 /*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 73ad7ebd6e9c..80088f994193 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -917,7 +917,7 @@ static void mark_nxdata_nx(void)
 {
         /*
          * When this called, init has already been executed and released,
-         * so everything past _etext sould be NX.
+         * so everything past _etext should be NX.
          */
         unsigned long start = PFN_ALIGN(_etext);
         /*
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9ec0f209a6a4..e8c00cc72033 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -446,7 +446,7 @@ static int __init numa_alloc_distance(void)
  * @distance: NUMA distance
  *
  * Set the distance from node @from to @to to @distance.  If distance table
- * doesn't exist, one which is large enough to accomodate all the currently
+ * doesn't exist, one which is large enough to accommodate all the currently
  * known nodes will be created.
  *
  * If such table cannot be allocated, a warning is printed and further
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 90825f2eb0f4..f9e526742fa1 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -310,7 +310,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
                  * these shared mappings are made of small page mappings.
                  * Thus this don't enforce !RW mapping for small page kernel
                  * text mapping logic will help Linux Xen parvirt guest boot
-                 * aswell.
+                 * as well.
                  */
                 if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
                         pgprot_val(forbidden) |= _PAGE_RW;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0113d19c8aa6..8573b83a63d0 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -168,8 +168,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
          * section 8.1: in PAE mode we explicitly have to flush the
          * TLB via cr3 if the top-level pgd is changed...
          */
-        if (mm == current->active_mm)
-                write_cr3(read_cr3());
+        flush_tlb_mm(mm);
 }
 #else  /* !CONFIG_X86_PAE */
 
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 72cbec14d783..2d49d4e19a36 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
         if (!user_mode_vm(regs)) {
                 unsigned long stack = kernel_stack_pointer(regs);
                 if (depth)
-                        dump_trace(NULL, regs, (unsigned long *)stack,
+                        dump_trace(NULL, regs, (unsigned long *)stack, 0,
                                    &backtrace_ops, &depth);
                 return;
         }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index b1805b78842f..494f2e7ea2b4 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -241,7 +241,7 @@ void __init pcibios_resource_survey(void)
         e820_reserve_resources_late();
         /*
          * Insert the IO APIC resources after PCI initialization has
-         * occured to handle IO APICS that are mapped in on a BAR in
+         * occurred to handle IO APICS that are mapped in on a BAR in
          * PCI space, but before trying to assign unassigned pci res.
          */
         ioapic_insert_resources();
@@ -304,7 +304,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                 /*
                  * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
                  * To avoid attribute conflicts, request UC MINUS here
-                 * aswell.
+                 * as well.
                  */
                 prot |= _PAGE_CACHE_UC_MINUS;
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5695fa66d565..39ee7182fd18 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1744,7 +1744,7 @@ static void convert_pfn_mfn(void *v)
 }
 
 /*
- * Set up the inital kernel pagetable.
+ * Set up the initial kernel pagetable.
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into