16 files changed, 106 insertions, 63 deletions

diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index 857e492c571e..bbeb0c3fbd90 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -504,8 +504,11 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
                         if (sym->st_shndx == SHN_ABS) {
                                 continue;
                         }
-                        if (r_type == R_386_PC32) {
-                                /* PC relative relocations don't need to be adjusted */
+                        if (r_type == R_386_NONE || r_type == R_386_PC32) {
+                                /*
+                                 * NONE can be ignored and and PC relative
+                                 * relocations don't need to be adjusted.
+                                 */
                         }
                         else if (r_type == R_386_32) {
                                 /* Visit relocations that need to be adjusted */
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 5054c2ddd1a0..74b3d2ba84e9 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -17,11 +17,6 @@
 
 #define SMAP    0x534d4150      /* ASCII "SMAP" */
 
-struct e820_ext_entry {
-        struct e820entry std;
-        u32 ext_flags;
-} __attribute__((packed));
-
 static int detect_memory_e820(void)
 {
         int count = 0;
@@ -29,13 +24,21 @@ static int detect_memory_e820(void)
         u32 size, id, edi;
         u8 err;
         struct e820entry *desc = boot_params.e820_map;
-        static struct e820_ext_entry buf; /* static so it is zeroed */
+        static struct e820entry buf; /* static so it is zeroed */
 
         /*
-         * Set this here so that if the BIOS doesn't change this field
-         * but still doesn't change %ecx, we're still okay...
+         * Note: at least one BIOS is known which assumes that the
+         * buffer pointed to by one e820 call is the same one as
+         * the previous call, and only changes modified fields.  Therefore,
+         * we use a temporary buffer and copy the results entry by entry.
+         *
+         * This routine deliberately does not try to account for
+         * ACPI 3+ extended attributes.  This is because there are
+         * BIOSes in the field which report zero for the valid bit for
+         * all ranges, and we don't currently make any use of the
+         * other attribute bits.  Revisit this if we see the extended
+         * attribute bits deployed in a meaningful way in the future.
          */
-        buf.ext_flags = 1;
 
         do {
                 size = sizeof buf;
@@ -66,13 +69,7 @@ static int detect_memory_e820(void)
                         break;
                 }
 
-                /* ACPI 3.0 added the extended flags support.  If bit 0
-                   in the extended flags is zero, we're supposed to simply
-                   ignore the entry -- a backwards incompatible change! */
-                if (size > 20 && !(buf.ext_flags & 1))
-                        continue;
-
-                *desc++ = buf.std;
+                *desc++ = buf;
                 count++;
         } while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1caefc82e62..77848d9fca68 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
+static int __init x86_xsave_setup(char *s)
+{
+        setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+        return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 1;
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 208ecf6643df..54b6de2cd947 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -693,8 +693,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
         if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
             policy->cpuinfo.transition_latency > 20 * 1000) {
                 policy->cpuinfo.transition_latency = 20 * 1000;
-                        printk_once(KERN_INFO "Capping off P-state tranision"
-                                    " latency at 20 uS\n");
+                printk_once(KERN_INFO
+                            "P-state transition latency capped at 20 uS\n");
         }
 
         /* table init */
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 6ac55bd341ae..869615193720 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -168,6 +168,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
                 case 0x0E: /* Core */
                 case 0x0F: /* Core Duo */
                 case 0x16: /* Celeron Core */
+                case 0x1C: /* Atom */
                         p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
                         return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
                 case 0x0D: /* Pentium M (Dothan) */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index 3c28ccd49742..a8363e5be4ef 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -168,10 +168,12 @@ static int check_powernow(void)
         return 1;
 }
 
+#ifdef CONFIG_X86_POWERNOW_K7_ACPI
 static void invalidate_entry(unsigned int entry)
 {
         powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
 }
+#endif
 
 static int get_ranges(unsigned char *pst)
 {
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 4709ead2db52..35dc8fbe92bd 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -649,6 +649,20 @@ static void print_basics(struct powernow_k8_data *data)
                                 data->batps);
 }
 
+static u32 freq_from_fid_did(u32 fid, u32 did)
+{
+        u32 mhz = 0;
+
+        if (boot_cpu_data.x86 == 0x10)
+                mhz = (100 * (fid + 0x10)) >> did;
+        else if (boot_cpu_data.x86 == 0x11)
+                mhz = (100 * (fid + 8)) >> did;
+        else
+                BUG();
+
+        return mhz * 1000;
+}
+
 static int fill_powernow_table(struct powernow_k8_data *data,
                 struct pst_s *pst, u8 maxvid)
 {
@@ -821,7 +835,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
         struct cpufreq_frequency_table *powernow_table;
         int ret_val = -ENODEV;
-        acpi_integer space_id;
+        acpi_integer control, status;
 
         if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
                 dprintk("register performance failed: bad ACPI data\n");
@@ -834,12 +848,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
                 goto err_out;
         }
 
-        space_id = data->acpi_data.control_register.space_id;
-        if ((space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
-                (space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
+        control = data->acpi_data.control_register.space_id;
+        status = data->acpi_data.status_register.space_id;
+
+        if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
+            (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
                 dprintk("Invalid control/status registers (%x - %x)\n",
-                        data->acpi_data.control_register.space_id,
-                        space_id);
+                        control, status);
                 goto err_out;
         }
 
@@ -923,8 +938,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 
                 powernow_table[i].index = index;
 
-                powernow_table[i].frequency =
-                        data->acpi_data.states[i].core_frequency * 1000;
+                /* Frequency may be rounded for these */
+                if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+                        powernow_table[i].frequency =
+                                freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
+                } else
+                        powernow_table[i].frequency =
+                                data->acpi_data.states[i].core_frequency * 1000;
         }
         return 0;
 }
@@ -1215,13 +1235,16 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
         return cpufreq_frequency_table_verify(pol, data->powernow_table);
 }
 
+static const char ACPI_PSS_BIOS_BUG_MSG[] =
+        KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
+        KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+
 /* per CPU init entry point to the driver */
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
         struct powernow_k8_data *data;
         cpumask_t oldmask;
         int rc;
-        static int print_once;
 
         if (!cpu_online(pol->cpu))
                 return -ENODEV;
@@ -1244,19 +1267,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
                  * an UP version, and is deprecated by AMD.
                  */
                 if (num_online_cpus() != 1) {
-                        /*
-                         * Replace this one with print_once as soon as such a
-                         * thing gets introduced
-                         */
-                        if (!print_once) {
-                                WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS "
-                                        "does not provide ACPI _PSS objects "
-                                        "in a way that Linux understands. "
-                                        "Please report this to the Linux ACPI"
-                                        " maintainers and complain to your "
-                                        "BIOS vendor.\n");
-                                print_once++;
-                        }
+                        printk_once(ACPI_PSS_BIOS_BUG_MSG);
                         goto err_out;
                 }
                 if (pol->cpu != 0) {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1340dad417f4..667188e0b5a0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -232,6 +232,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
                 },
         },
+        {       /* Handle problems with rebooting on Sony VGN-Z540N */
+                .callback = set_bios_reboot,
+                .ident = "Sony VGN-Z540N",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
+                },
+        },
         { }
 };
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 3a97a4cf1872..8f0e13be36b3 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -160,8 +160,10 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
         /*
          * If large page isn't supported, there's no benefit in doing
          * this.  Also, on non-NUMA, embedding is better.
+         *
+         * NOTE: disabled for now.
          */
-        if (!cpu_has_pse || !pcpu_need_numa())
+        if (true || !cpu_has_pse || !pcpu_need_numa())
                 return -EINVAL;
 
         /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b6caf1329b1b..32cf11e5728a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2897,8 +2897,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
 
 static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
-        kvm_x86_ops->tlb_flush(vcpu);
-        set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+        kvm_set_cr3(vcpu, vcpu->arch.cr3);
         return 1;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 49079a46687b..3944e917e794 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -338,6 +338,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw);
 
 void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
+        unsigned long old_cr4 = vcpu->arch.cr4;
+        unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
+
         if (cr4 & CR4_RESERVED_BITS) {
                 printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
                 kvm_inject_gp(vcpu, 0);
@@ -351,7 +354,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
-        } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
+        } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
+                   && ((cr4 ^ old_cr4) & pdptr_bits)
                    && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
                 printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
                 kvm_inject_gp(vcpu, 0);
diff --git a/arch/x86/lguest/Makefile b/arch/x86/lguest/Makefile
index 27f0c9ed7f60..94e0e54056a9 100644
--- a/arch/x86/lguest/Makefile
+++ b/arch/x86/lguest/Makefile
@@ -1 +1,2 @@
 obj-y           := i386_head.o boot.o
+CFLAGS_boot.o   := $(call cc-option, -fno-stack-protector)
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index ca7ec44bafc3..33a93b417396 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -67,6 +67,7 @@
 #include <asm/mce.h>
 #include <asm/io.h>
 #include <asm/i387.h>
+#include <asm/stackprotector.h>
 #include <asm/reboot.h>         /* for struct machine_ops */
 
 /*G:010 Welcome to the Guest!
@@ -1088,13 +1089,21 @@ __init void lguest_init(void)
          * lguest_init() where the rest of the fairly chaotic boot setup
          * occurs. */
 
+        /* The stack protector is a weird thing where gcc places a canary
+         * value on the stack and then checks it on return.  This file is
+         * compiled with -fno-stack-protector it, so we got this far without
+         * problems.  The value of the canary is kept at offset 20 from the
+         * %gs register, so we need to set that up before calling C functions
+         * in other files. */
+        setup_stack_canary_segment(0);
+        /* We could just call load_stack_canary_segment(), but we might as
+         * call switch_to_new_gdt() which loads the whole table and sets up
+         * the per-cpu segment descriptor register %fs as well. */
+        switch_to_new_gdt(0);
+
         /* As described in head_32.S, we map the first 128M of memory. */
         max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
 
-        /* Load the %fs segment register (the per-cpu segment register) with
-         * the normal data segment to get through booting. */
-        asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory");
-
         /* The Host<->Guest Switcher lives at the top of our address space, and
          * the Host told us how big it is when we made LGUEST_INIT hypercall:
          * it put the answer in lguest_data.reserve_mem  */
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8f307d914c2e..f46c340727b8 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -26,12 +26,16 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
         unsigned long sbase = saddr & PUD_MASK;
         unsigned long s_end = sbase + PUD_SIZE;
 
+        /* Allow segments to share if only one is marked locked */
+        unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
+        unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+
         /*
          * match the virtual addresses, permission and the alignment of the
          * page table page.
          */
         if (pmd_index(addr) != pmd_index(saddr) ||
-            vma->vm_flags != svma->vm_flags ||
+            vm_flags != svm_flags ||
             sbase < svma->vm_start || svma->vm_end < s_end)
                 return 0;
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 797f9f107cb6..e17efed088c5 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -153,7 +153,7 @@ static void __cpa_flush_all(void *arg)
          */
         __flush_tlb_all();
 
-        if (cache && boot_cpu_data.x86_model >= 4)
+        if (cache && boot_cpu_data.x86 >= 4)
                 wbinvd();
 }
 
@@ -208,20 +208,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
                             int in_flags, struct page **pages)
 {
         unsigned int i, level;
+        unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
 
         BUG_ON(irqs_disabled());
 
-        on_each_cpu(__cpa_flush_range, NULL, 1);
+        on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
 
-        if (!cache)
+        if (!cache || do_wbinvd)
                 return;
 
-        /* 4M threshold */
-        if (numpages >= 1024) {
-                if (boot_cpu_data.x86_model >= 4)
-                        wbinvd();
-                return;
-        }
         /*
          * We only need to flush on one CPU,
          * clflush is a MESI-coherent instruction that
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 5fa10bb9604f..8766b0e216c5 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -375,7 +375,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
                 if (!fixmem32)
                         return AE_OK;
                 if ((mcfg_res->start >= fixmem32->address) &&
-                    (mcfg_res->end <= (fixmem32->address +
+                    (mcfg_res->end < (fixmem32->address +
                                       fixmem32->address_length))) {
                         mcfg_res->flags = 1;
                         return AE_CTRL_TERMINATE;
@@ -392,7 +392,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
                 return AE_OK;
 
         if ((mcfg_res->start >= address.minimum) &&
-            (mcfg_res->end <= (address.minimum + address.address_length))) {
+            (mcfg_res->end < (address.minimum + address.address_length))) {
                 mcfg_res->flags = 1;
                 return AE_CTRL_TERMINATE;
         }
@@ -418,7 +418,7 @@ static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used)
         struct resource mcfg_res;
 
         mcfg_res.start = start;
-        mcfg_res.end = end;
+        mcfg_res.end = end - 1;
         mcfg_res.flags = 0;
 
         acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL);