30 files changed, 228 insertions, 198 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f77dd6774bba..55ff016e9f69 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -13,7 +13,7 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_vsyscall_64.o    := $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o           := $(nostackp)
-CFLAGS_tsc_64.o         := $(nostackp)
+CFLAGS_tsc.o            := $(nostackp)
 
 obj-y                   := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
 obj-y                   += traps_$(BITS).o irq_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a31a579a47ca..9c981c4a3644 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -130,7 +130,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
         if (!phys || !size)
                 return NULL;
 
-        if (phys+size <= (max_pfn_mapped << PAGE_SHIFT))
+        if (phys+size <= (max_low_pfn_mapped << PAGE_SHIFT))
                 return __va(phys);
 
         offset = phys & (PAGE_SIZE - 1);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 958526d6a74a..bd182b7616ee 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -199,10 +199,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
                  * Don't do it for gbpages because there seems very little
                  * benefit in doing so.
                  */
-                if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
-                    (tseg >> PMD_SHIFT) <
-                        (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
+                if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+                    if ((tseg>>PMD_SHIFT) <
+                                (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
+                        ((tseg>>PMD_SHIFT) <
+                                (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
+                         (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
                         set_memory_4k((unsigned long)__va(tseg), 1);
+                }
         }
 }
 
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index 13526fd5cce1..2026d2119cdb 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -10,6 +10,8 @@ static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 {
         if (c->x86 == 0x6 && c->x86_model >= 0xf)
                 set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+        set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 }
 
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index 751850235291..36537ab9e56a 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -314,6 +314,9 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
         if (c->extended_cpuid_level >= 0x80000007)
                 c->x86_power = cpuid_edx(0x80000007);
 
+        /* Assume all 64-bit CPUs support 32-bit syscall */
+        set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+
         if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
             cpu_devs[c->x86_vendor]->c_early_init)
                 cpu_devs[c->x86_vendor]->c_early_init(c);
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
index fcb1cc9d75ca..02f773399e39 100644
--- a/arch/x86/kernel/cpu/intel_64.c
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -12,6 +12,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
         if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
             (c->x86 == 0x6 && c->x86_model >= 0x0e))
                 set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+        set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 }
 
 /*
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 269d367d2ace..a5383ae2cbe3 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1056,7 +1056,7 @@ unsigned long __initdata end_user_pfn = MAX_ARCH_PFN;
 /*
  * Find the highest page frame number we have available
  */
-unsigned long __init e820_end(void)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 {
         int i;
         unsigned long last_pfn = 0;
@@ -1064,12 +1064,21 @@ unsigned long __init e820_end(void)
 
         for (i = 0; i < e820.nr_map; i++) {
                 struct e820entry *ei = &e820.map[i];
+                unsigned long start_pfn;
                 unsigned long end_pfn;
 
-                if (ei->type != E820_RAM)
+                if (ei->type != type)
                         continue;
 
+                start_pfn = ei->addr >> PAGE_SHIFT;
                 end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+
+                if (start_pfn >= limit_pfn)
+                        continue;
+                if (end_pfn > limit_pfn) {
+                        last_pfn = limit_pfn;
+                        break;
+                }
                 if (end_pfn > last_pfn)
                         last_pfn = end_pfn;
         }
@@ -1083,7 +1092,15 @@ unsigned long __init e820_end(void)
                          last_pfn, max_arch_pfn);
         return last_pfn;
 }
+unsigned long __init e820_end_of_ram_pfn(void)
+{
+        return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+}
 
+unsigned long __init e820_end_of_low_ram_pfn(void)
+{
+        return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
+}
 /*
  * Finds an active region in the address range from start_pfn to last_pfn and
  * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
@@ -1165,6 +1182,8 @@ static void early_panic(char *msg)
         panic(msg);
 }
 
+static int userdef __initdata;
+
 /* "mem=nopentium" disables the 4MB page tables. */
 static int __init parse_memopt(char *p)
 {
@@ -1180,17 +1199,15 @@ static int __init parse_memopt(char *p)
         }
 #endif
 
+        userdef = 1;
         mem_size = memparse(p, &p);
         end_user_pfn = mem_size>>PAGE_SHIFT;
-        e820_update_range(mem_size, ULLONG_MAX - mem_size,
-                E820_RAM, E820_RESERVED);
+        e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
         return 0;
 }
 early_param("mem", parse_memopt);
 
-static int userdef __initdata;
-
 static int __init parse_memmap_opt(char *p)
 {
         char *oldp;
@@ -1206,7 +1223,7 @@ static int __init parse_memmap_opt(char *p)
                  * the real mem size before original memory map is
                  * reset.
                  */
-                saved_max_pfn = e820_end();
+                saved_max_pfn = e820_end_of_ram_pfn();
 #endif
                 e820.nr_map = 0;
                 userdef = 1;
@@ -1230,8 +1247,7 @@ static int __init parse_memmap_opt(char *p)
                 e820_add_region(start_at, mem_size, E820_RESERVED);
         } else {
                 end_user_pfn = (mem_size >> PAGE_SHIFT);
-                e820_update_range(mem_size, ULLONG_MAX - mem_size,
-                        E820_RAM, E820_RESERVED);
+                e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
         }
         return *p == '\0' ? 0 : -EINVAL;
 }
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 94382faeadb6..06cc8d4254b1 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -473,7 +473,7 @@ void __init efi_enter_virtual_mode(void)
                 size = md->num_pages << EFI_PAGE_SHIFT;
                 end = md->phys_addr + size;
 
-                if (PFN_UP(end) <= max_pfn_mapped)
+                if (PFN_UP(end) <= max_low_pfn_mapped)
                         va = __va(md->phys_addr);
                 else
                         va = efi_ioremap(md->phys_addr, size);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 53393c306e11..cfe28a715434 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1024,6 +1024,7 @@ ENTRY(xen_sysenter_target)
         RING0_INT_FRAME
         addl $5*4, %esp         /* remove xen-provided frame */
         jmp sysenter_past_esp
+        CFI_ENDPROC
 
 ENTRY(xen_hypervisor_callback)
         CFI_STARTPROC
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 6b220b9dcbb3..c50adb84ea6f 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2027,7 +2027,7 @@ static inline void init_IO_APIC_traps(void)
  * The local APIC irq-chip implementation:
  */
 
-static void ack_apic(unsigned int irq)
+static void ack_lapic_irq(unsigned int irq)
 {
         ack_APIC_irq();
 }
@@ -2052,9 +2052,17 @@ static struct irq_chip lapic_chip __read_mostly = {
         .name           = "local-APIC",
         .mask           = mask_lapic_irq,
         .unmask         = unmask_lapic_irq,
-        .eoi            = ack_apic,
+        .ack            = ack_lapic_irq,
 };
 
+static void lapic_register_intr(int irq, int vector)
+{
+        irq_desc[irq].status &= ~IRQ_LEVEL;
+        set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+                                      "edge");
+        set_intr_gate(vector, interrupt[irq]);
+}
+
 static void __init setup_nmi(void)
 {
         /*
@@ -2257,8 +2265,7 @@ static inline void __init check_timer(void)
 
         printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
-        set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
-                                      "fasteoi");
+        lapic_register_intr(0, vector);
         apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);   /* Fixed mode */
         enable_8259A_irq(0);
 
@@ -2290,11 +2297,21 @@ out:
 }
 
 /*
- *
- * IRQ's that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- *   Linux doesn't really care, as it's not actually used
- *   for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices.  However there may be an I/O APIC pin available for
+ * this interrupt regardless.  The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A.  In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table.  With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default.  We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor.  Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now.  No actual device should request
+ * it anyway.  --macro
  */
 #define PIC_IRQS        (1 << PIC_CASCADE_IR)
 
@@ -2308,10 +2325,7 @@ void __init setup_IO_APIC(void)
 
         enable_IO_APIC();
 
-        if (acpi_ioapic)
-                io_apic_irqs = ~0;      /* all IRQs go through IOAPIC */
-        else
-                io_apic_irqs = ~PIC_IRQS;
+        io_apic_irqs = ~PIC_IRQS;
 
         printk("ENABLING IO-APIC IRQs\n");
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 848411753c7c..9e645cba11c4 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1561,7 +1561,7 @@ static inline void init_IO_APIC_traps(void)
         }
 }
 
-static void enable_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
 {
         unsigned long v;
 
@@ -1569,7 +1569,7 @@ static void enable_lapic_irq (unsigned int irq)
         apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void disable_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
 {
         unsigned long v;
 
@@ -1582,19 +1582,20 @@ static void ack_lapic_irq (unsigned int irq)
         ack_APIC_irq();
 }
 
-static void end_lapic_irq (unsigned int i) { /* nothing */ }
-
-static struct hw_interrupt_type lapic_irq_type __read_mostly = {
-        .name = "local-APIC",
-        .typename = "local-APIC-edge",
-        .startup = NULL, /* startup_irq() not used for IRQ0 */
-        .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
-        .enable = enable_lapic_irq,
-        .disable = disable_lapic_irq,
-        .ack = ack_lapic_irq,
-        .end = end_lapic_irq,
+static struct irq_chip lapic_chip __read_mostly = {
+        .name           = "local-APIC",
+        .mask           = mask_lapic_irq,
+        .unmask         = unmask_lapic_irq,
+        .ack            = ack_lapic_irq,
 };
 
+static void lapic_register_intr(int irq)
+{
+        irq_desc[irq].status &= ~IRQ_LEVEL;
+        set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+                                      "edge");
+}
+
 static void __init setup_nmi(void)
 {
         /*
@@ -1784,7 +1785,7 @@ static inline void __init check_timer(void)
 
         apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
-        irq_desc[0].chip = &lapic_irq_type;
+        lapic_register_intr(0);
         apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);     /* Fixed mode */
         enable_8259A_irq(0);
 
@@ -1822,11 +1823,21 @@ static int __init notimercheck(char *s)
 __setup("no_timer_check", notimercheck);
 
 /*
- *
- * IRQs that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- *   Linux doesn't really care, as it's not actually used
- *   for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices.  However there may be an I/O APIC pin available for
+ * this interrupt regardless.  The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A.  In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table.  With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default.  We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor.  Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now.  No actual device should request
+ * it anyway.  --macro
  */
 #define PIC_IRQS        (1<<2)
 
@@ -1837,10 +1848,7 @@ void __init setup_IO_APIC(void)
          * calling enable_IO_APIC() is moved to setup_local_APIC for BP
          */
 
-        if (acpi_ioapic)
-                io_apic_irqs = ~0;      /* all IRQs go through IOAPIC */
-        else
-                io_apic_irqs = ~PIC_IRQS;
+        io_apic_irqs = ~PIC_IRQS;
 
         apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 8dfe9db87a9e..716b89284be0 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -171,6 +171,9 @@ int __init check_nmi_watchdog(void)
 error:
         if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
                 disable_8259A_irq(0);
+#ifdef CONFIG_X86_32
+        timer_ack = 0;
+#endif
         return -1;
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb3db406247c..987b6fde3a99 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -714,14 +714,14 @@ void __init setup_arch(char **cmdline_p)
          * partially used pages are not usable - thus
          * we are rounding upwards:
          */
-        max_pfn = e820_end();
+        max_pfn = e820_end_of_ram_pfn();
 
         /* preallocate 4k for mptable mpc */
         early_reserve_e820_mpc_new();
         /* update e820 for memory not covered by WB MTRRs */
         mtrr_bp_init();
         if (mtrr_trim_uncached_memory(max_pfn))
-                max_pfn = e820_end();
+                max_pfn = e820_end_of_ram_pfn();
 
 #ifdef CONFIG_X86_32
         /* max_low_pfn get updated here */
@@ -733,12 +733,26 @@ void __init setup_arch(char **cmdline_p)
 
         /* How many end-of-memory variables you have, grandma! */
         /* need this before calling reserve_initrd */
-        max_low_pfn = max_pfn;
+        if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
+                max_low_pfn = e820_end_of_low_ram_pfn();
+        else
+                max_low_pfn = max_pfn;
+
         high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
         /* max_pfn_mapped is updated here */
-        max_pfn_mapped = init_memory_mapping(0, (max_low_pfn << PAGE_SHIFT));
+        max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
+        max_pfn_mapped = max_low_pfn_mapped;
+
+#ifdef CONFIG_X86_64
+        if (max_pfn > max_low_pfn) {
+                max_pfn_mapped = init_memory_mapping(1UL<<32,
+                                                     max_pfn<<PAGE_SHIFT);
+                /* can we preseve max_low_pfn ?*/
+                max_low_pfn = max_pfn;
+        }
+#endif
 
         /*
          * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4a775d001957..3c36f92160c9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -513,7 +513,6 @@ void __init tsc_init(void)
          */
         for_each_possible_cpu(cpu)
                 set_cyc2ns_scale(cpu_khz, cpu);
-        use_tsc_delay();
 
         if (tsc_disabled > 0)
                 return;
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index e5afb4ad3f1c..dfdf428975c0 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -185,7 +185,7 @@ ENTRY(copy_user_generic_unrolled)
 30:     shll $6,%ecx
         addl %ecx,%edx
         jmp 60f
-40:     leal (%edx,%ecx,8),%edx
+40:     lea (%rdx,%rcx,8),%rdx
         jmp 60f
 50:     movl %ecx,%edx
 60:     jmp copy_user_handle_tail /* ecx is zerorest also */
@@ -254,7 +254,7 @@ ENTRY(copy_user_generic_string)
         ret
 
         .section .fixup,"ax"
-11:     leal (%edx,%ecx,8),%ecx
+11:     lea (%rdx,%rcx,8),%rcx
 12:     movl %ecx,%edx          /* ecx is zerorest also */
         jmp copy_user_handle_tail
         .previous
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index 93353d6a5263..40e0e309d27e 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -104,7 +104,7 @@ ENTRY(__copy_user_nocache)
 30:     shll $6,%ecx
         addl %ecx,%edx
         jmp 60f
-40:     leal (%edx,%ecx,8),%edx
+40:     lea (%rdx,%rcx,8),%rdx
         jmp 60f
 50:     movl %ecx,%edx
 60:     sfence
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index b5a0fd5f4c5f..029e8cffca9e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -50,6 +50,7 @@
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
+unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 48548ef7ddf8..122bcef222fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -53,6 +53,7 @@
  * The direct mapping extends to max_pfn_mapped, so that we can directly access
  * apertures, ACPI and other tables without having to play with fixmaps.
  */
+unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
 static unsigned long dma_reserve __initdata;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index afd40054d157..0389cb8f6b1a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -536,8 +536,14 @@ static int split_large_page(pte_t *kpte, unsigned long address)
                 set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
 
         if (address >= (unsigned long)__va(0) &&
+                address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
+                split_page_count(level);
+
+#ifdef CONFIG_X86_64
+        if (address >= (unsigned long)__va(1UL<<32) &&
                 address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
                 split_page_count(level);
+#endif
 
         /*
          * Install the new, split up pagetable. Important details here:
@@ -655,12 +661,21 @@ static int cpa_process_alias(struct cpa_data *cpa)
         if (cpa->pfn > max_pfn_mapped)
                 return 0;
 
+#ifdef CONFIG_X86_64
+        if (cpa->pfn > max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
+                return 0;
+#endif
         /*
          * No need to redo, when the primary call touched the direct
          * mapping already:
          */
-        if (!within(cpa->vaddr, PAGE_OFFSET,
-                    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+        if (!(within(cpa->vaddr, PAGE_OFFSET,
+                    PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
+#ifdef CONFIG_X86_64
+                || within(cpa->vaddr, PAGE_OFFSET + (1UL<<32),
+                    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
+#endif
+        )) {
 
                 alias_cpa = *cpa;
                 alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index a885a1019b8a..749766c3c5cd 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -449,7 +449,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
         if (retval < 0)
                 return 0;
 
-        if (pfn <= max_pfn_mapped &&
+        if (((pfn <= max_low_pfn_mapped) ||
+             (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn <= max_pfn_mapped)) &&
             ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
                 free_memtype(offset, offset + size);
                 printk(KERN_INFO
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 0fd67b81a8b6..1b4763e26ea9 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -100,7 +100,19 @@ static __init inline int srat_disabled(void)
 /* Callback for SLIT parsing */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
-        acpi_slit = slit;
+        unsigned length;
+        unsigned long phys;
+
+        length = slit->header.length;
+        phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+                 PAGE_SIZE);
+
+        if (phys == -1L)
+                panic(" Can not save slit!\n");
+
+        acpi_slit = __va(phys);
+        memcpy(acpi_slit, slit, length);
+        reserve_early(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> LAPIC mapping */
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 6ccd7a108cd4..5281e343dd9f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -334,7 +334,9 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                 flags = new_flags;
         }
 
-        if (vma->vm_pgoff <= max_pfn_mapped &&
+        if (((vma->vm_pgoff <= max_low_pfn_mapped) ||
+             (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) &&
+              vma->vm_pgoff <= max_pfn_mapped)) &&
             ioremap_change_attr((unsigned long)__va(addr), len, flags)) {
                 free_memtype(addr, addr + len);
                 return -EINVAL;
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index cf058fecfcee..0bce5429a515 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -203,20 +203,11 @@ static struct page *vdso32_pages[1];
 
 #ifdef CONFIG_X86_64
 
-static int use_sysenter __read_mostly = -1;
-
-#define vdso32_sysenter()       (use_sysenter > 0)
+#define vdso32_sysenter()       (boot_cpu_has(X86_FEATURE_SYSENTER32))
 
 /* May not be __init: called during resume */
 void syscall32_cpu_init(void)
 {
-        if (use_sysenter < 0) {
-                if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-                        use_sysenter = 1;
-                if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR)
-                        use_sysenter = 1;
-        }
-
         /* Load these always in case some future AMD CPU supports
            SYSENTER from compat mode too. */
         checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 84a56da397b1..75ef959db329 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -74,8 +74,8 @@
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
 #define X86_FEATURE_PEBS        (3*32+12)  /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS         (3*32+13)  /* Branch Trace Store */
-/* 14 free */
-/* 15 free */
+#define X86_FEATURE_SYSCALL32   (3*32+14)  /* syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32  (3*32+15)  /* sysenter in ia32 userspace */
 #define X86_FEATURE_REP_GOOD    (3*32+16) /* rep microcode works well on this CPU */
 #define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
 #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
index b3cbb0ccae18..0bfe250894f7 100644
--- a/include/asm-x86/dwarf2.h
+++ b/include/asm-x86/dwarf2.h
@@ -1,5 +1,61 @@
-#ifdef CONFIG_X86_32
-# include "dwarf2_32.h"
+#ifndef _DWARF2_H
+#define _DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+   Macros for dwarf2 CFI unwind table entries.
+   See "as.info" for details on these pseudo ops. Unfortunately
+   they are only supported in very new binutils, so define them
+   away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC .cfi_startproc
+#define CFI_ENDPROC .cfi_endproc
+#define CFI_DEF_CFA .cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
+#define CFI_OFFSET .cfi_offset
+#define CFI_REL_OFFSET .cfi_rel_offset
+#define CFI_REGISTER .cfi_register
+#define CFI_RESTORE .cfi_restore
+#define CFI_REMEMBER_STATE .cfi_remember_state
+#define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
 #else
-# include "dwarf2_64.h"
+
+/* Due to the structure of pre-exisiting code, don't use assembler line
+   comment character # to ignore the arguments. Instead, use a dummy macro. */
+.macro ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC   ignore
+#define CFI_ENDPROC     ignore
+#define CFI_DEF_CFA     ignore
+#define CFI_DEF_CFA_REGISTER    ignore
+#define CFI_DEF_CFA_OFFSET      ignore
+#define CFI_ADJUST_CFA_OFFSET   ignore
+#define CFI_OFFSET      ignore
+#define CFI_REL_OFFSET  ignore
+#define CFI_REGISTER    ignore
+#define CFI_RESTORE     ignore
+#define CFI_REMEMBER_STATE ignore
+#define CFI_RESTORE_STATE ignore
+#define CFI_UNDEFINED ignore
+#define CFI_SIGNAL_FRAME ignore
+
+#endif
+
 #endif
diff --git a/include/asm-x86/dwarf2_32.h b/include/asm-x86/dwarf2_32.h
deleted file mode 100644
index 6d66398a307d..000000000000
--- a/include/asm-x86/dwarf2_32.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_UNWIND_INFO
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
-.macro ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC   ignore
-#define CFI_ENDPROC     ignore
-#define CFI_DEF_CFA     ignore
-#define CFI_DEF_CFA_REGISTER    ignore
-#define CFI_DEF_CFA_OFFSET      ignore
-#define CFI_ADJUST_CFA_OFFSET   ignore
-#define CFI_OFFSET      ignore
-#define CFI_REL_OFFSET  ignore
-#define CFI_REGISTER    ignore
-#define CFI_RESTORE     ignore
-#define CFI_REMEMBER_STATE ignore
-#define CFI_RESTORE_STATE ignore
-#define CFI_UNDEFINED ignore
-#define CFI_SIGNAL_FRAME ignore
-
-#endif
-
-#endif
diff --git a/include/asm-x86/dwarf2_64.h b/include/asm-x86/dwarf2_64.h
deleted file mode 100644
index c950519a264d..000000000000
--- a/include/asm-x86/dwarf2_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H 1
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* use assembler line comment character # to ignore the arguments. */
-#define CFI_STARTPROC   #
-#define CFI_ENDPROC     #
-#define CFI_DEF_CFA     #
-#define CFI_DEF_CFA_REGISTER    #
-#define CFI_DEF_CFA_OFFSET      #
-#define CFI_ADJUST_CFA_OFFSET   #
-#define CFI_OFFSET      #
-#define CFI_REL_OFFSET  #
-#define CFI_REGISTER    #
-#define CFI_RESTORE     #
-#define CFI_REMEMBER_STATE      #
-#define CFI_RESTORE_STATE       #
-#define CFI_UNDEFINED   #
-#define CFI_SIGNAL_FRAME        #
-
-#endif
-
-#endif
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 78c03d7bf441..33e793e991d0 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -99,7 +99,8 @@ extern void free_early(u64 start, u64 end);
 extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
-extern unsigned long e820_end(void);
+extern unsigned long e820_end_of_ram_pfn(void);
+extern unsigned long e820_end_of_low_ram_pfn(void);
 extern int e820_find_active_region(const struct e820entry *ei,
                                   unsigned long start_pfn,
                                   unsigned long last_pfn,
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index b52ed85f32f5..28d7b4533b1a 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -61,6 +61,7 @@ extern void map_devmem(unsigned long pfn, unsigned long size,
 extern void unmap_devmem(unsigned long pfn, unsigned long size,
                          pgprot_t vma_prot);
 
+extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
 struct page;
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index c4946c5964bf..983ce37c491f 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -160,7 +160,7 @@ extern void native_load_gs_index(unsigned);
  * Save a segment register away
  */
 #define savesegment(seg, value)                         \
-        asm("mov %%" #seg ",%0":"=rm" (value) : : "memory")
+        asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
 static inline unsigned long get_limit(unsigned long segment)
 {