Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into sh-fixes-for-linus

19 files changed, 159 insertions, 125 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 250806472a7e..f5abe3a245b8 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -8,7 +8,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
-CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
@@ -24,13 +23,16 @@ endif
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
-CFLAGS_tsc.o		:= $(nostackp)
+CFLAGS_vread_tsc_64.o	:= $(nostackp)
 CFLAGS_paravirt.o	:= $(nostackp)
 GCOV_PROFILE_vsyscall_64.o	:= n
 GCOV_PROFILE_hpet.o		:= n
 GCOV_PROFILE_tsc.o		:= n
 GCOV_PROFILE_paravirt.o		:= n
 
+# vread_tsc_64 is hot and should be fully optimized:
+CFLAGS_REMOVE_vread_tsc_64.o = -pg -fno-optimize-sibling-calls
+
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
@@ -39,7 +41,7 @@ obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
+obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o vread_tsc_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9488dcff7aec..e5293394b548 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -676,7 +676,7 @@ void mask_ioapic_entries(void)
 	int apic, pin;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (ioapics[apic].saved_registers)
+		if (!ioapics[apic].saved_registers)
 			continue;
 
 		for (pin = 0; pin < ioapics[apic].nr_registers; pin++) {
@@ -699,7 +699,7 @@ int restore_ioapic_entries(void)
 	int apic, pin;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (ioapics[apic].saved_registers)
+		if (!ioapics[apic].saved_registers)
 			continue;
 
 		for (pin = 0; pin < ioapics[apic].nr_registers; pin++)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f450b683dfcf..b511a011b7d0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -91,6 +91,10 @@ static int __init early_get_pnodeid(void)
 	m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
 	uv_min_hub_revision_id = node_id.s.revision;
 
+	if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
+		uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+
+	uv_hub_info->hub_revision = uv_min_hub_revision_id;
 	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
 	return pnode;
 }
@@ -112,17 +116,25 @@ static void __init early_get_apic_pnode_shift(void)
  */
 static void __init uv_set_apicid_hibit(void)
 {
-	union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
+	union uv1h_lb_target_physical_apic_id_mask_u apicid_mask;
 
-	apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
-	uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
+	if (is_uv1_hub()) {
+		apicid_mask.v =
+			uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+		uv_apicid_hibits =
+			apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
+	}
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	int pnodeid;
+	int pnodeid, is_uv1, is_uv2;
 
-	if (!strcmp(oem_id, "SGI")) {
+	is_uv1 = !strcmp(oem_id, "SGI");
+	is_uv2 = !strcmp(oem_id, "SGI2");
+	if (is_uv1 || is_uv2) {
+		uv_hub_info->hub_revision =
+			is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE;
 		pnodeid = early_get_pnodeid();
 		early_get_apic_pnode_shift();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
@@ -484,12 +496,19 @@ static __init void map_mmr_high(int max_pnode)
 static __init void map_mmioh_high(int max_pnode)
 {
 	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
-	int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+	int shift;
 
 	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-	if (mmioh.s.enable)
-		map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io,
+	if (is_uv1_hub() && mmioh.s1.enable) {
+		shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io,
+			max_pnode, map_uc);
+	}
+	if (is_uv2_hub() && mmioh.s2.enable) {
+		shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io,
 			max_pnode, map_uc);
+	}
 }
 
 static __init void map_low_mmrs(void)
@@ -736,13 +755,14 @@ void __init uv_system_init(void)
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask, pnode_io_mask;
 
+	printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2");
 	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
 	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-	n_io = mmioh.s.n_io;
+	n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
@@ -811,6 +831,8 @@ void __init uv_system_init(void)
 		 */
 		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
+		uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
+
 		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
 		lcpu = uv_blade_info[blade].nr_possible_cpus;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 3bfa02235965..965a7666c283 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -361,6 +361,7 @@ struct apm_user {
  * idle percentage above which bios idle calls are done
  */
 #ifdef CONFIG_APM_CPU_IDLE
+#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
 #define DEFAULT_IDLE_THRESHOLD	95
 #else
 #define DEFAULT_IDLE_THRESHOLD	100
@@ -904,6 +905,7 @@ static void apm_cpu_idle(void)
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
 	unsigned int bucket;
 
+	WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
 recalc:
 	if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
 		use_apm_idle = 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8f5cabb3c5b0..b13ed393dfce 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -612,8 +612,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	}
 #endif
 
-	/* As a rule processors have APIC timer running in deep C states */
-	if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+	/*
+	 * Family 0x12 and above processors have APIC timer
+	 * running in deep C states.
+	 */
+	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
 	/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c39576cb3018..525514cf33c3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,7 @@
 
 static int __init no_halt(char *s)
 {
+	WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n");
 	boot_cpu_data.hlt_works_ok = 0;
 	return 1;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c8b41623377f..22a073d7fbff 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -477,13 +477,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 	if (smp_num_siblings <= 1)
 		goto out;
 
-	if (smp_num_siblings > nr_cpu_ids) {
-		pr_warning("CPU: Unsupported number of siblings %d",
-			   smp_num_siblings);
-		smp_num_siblings = 1;
-		return;
-	}
-
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 
@@ -909,7 +902,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
-	init_c1e_mask();
+	init_amd_e400_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0ba15a6cc57e..c9a281f272fd 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;		/* holds return value of text write */
 static void *mod_code_ip;		/* holds the IP to write to */
-static void *mod_code_newcode;		/* holds the text to write to the IP */
+static const void *mod_code_newcode;	/* holds the text to write to the IP */
 
 static unsigned nmi_wait_count;
 static atomic_t nmi_update_count = ATOMIC_INIT(0);
@@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 }
 
 static int
-do_ftrace_mod_code(unsigned long ip, void *new_code)
+do_ftrace_mod_code(unsigned long ip, const void *new_code)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void)
 }
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-		   unsigned char *new_code)
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_call_replace(ip, addr);
@@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod,
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_nop_replace();
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 88a90a977f8e..426a5b66f7e4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,9 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(pm_idle);
+#endif
 
 #ifdef CONFIG_X86_32
 /*
@@ -397,7 +399,7 @@ void default_idle(void)
 		cpu_relax();
 	}
 }
-#ifdef CONFIG_APM_MODULE
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(default_idle);
 #endif
 
@@ -535,45 +537,45 @@ int mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
-bool c1e_detected;
-EXPORT_SYMBOL(c1e_detected);
+bool amd_e400_c1e_detected;
+EXPORT_SYMBOL(amd_e400_c1e_detected);
 
-static cpumask_var_t c1e_mask;
+static cpumask_var_t amd_e400_c1e_mask;
 
-void c1e_remove_cpu(int cpu)
+void amd_e400_remove_cpu(int cpu)
 {
-	if (c1e_mask != NULL)
-		cpumask_clear_cpu(cpu, c1e_mask);
+	if (amd_e400_c1e_mask != NULL)
+		cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
 }
 
 /*
- * C1E aware idle routine. We check for C1E active in the interrupt
+ * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
  * pending message MSR. If we detect C1E, then we handle it the same
  * way as C3 power states (local apic timer and TSC stop)
  */
-static void c1e_idle(void)
+static void amd_e400_idle(void)
 {
 	if (need_resched())
 		return;
 
-	if (!c1e_detected) {
+	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
 
 		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			c1e_detected = true;
+			amd_e400_c1e_detected = true;
 			if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 				mark_tsc_unstable("TSC halt in AMD C1E");
 			printk(KERN_INFO "System has AMD C1E enabled\n");
 		}
 	}
 
-	if (c1e_detected) {
+	if (amd_e400_c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpumask_test_cpu(cpu, c1e_mask)) {
-			cpumask_set_cpu(cpu, c1e_mask);
+		if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
+			cpumask_set_cpu(cpu, amd_e400_c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere.
 			 */
@@ -616,17 +618,17 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = mwait_idle;
 	} else if (cpu_has_amd_erratum(amd_erratum_400)) {
 		/* E400: APIC timer interrupt does not wake up CPU from C1e */
-		printk(KERN_INFO "using C1E aware idle routine\n");
-		pm_idle = c1e_idle;
+		printk(KERN_INFO "using AMD E400 aware idle routine\n");
+		pm_idle = amd_e400_idle;
 	} else
 		pm_idle = default_idle;
 }
 
-void __init init_c1e_mask(void)
+void __init init_amd_e400_c1e_mask(void)
 {
-	/* If we're using c1e_idle, we need to allocate c1e_mask. */
-	if (pm_idle == c1e_idle)
-		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+	/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
+	if (pm_idle == amd_e400_idle)
+		zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
@@ -640,6 +642,7 @@ static int __init idle_setup(char *str)
 		boot_option_idle_override = IDLE_POLL;
 	} else if (!strcmp(str, "mwait")) {
 		boot_option_idle_override = IDLE_FORCE_MWAIT;
+		WARN_ONCE(1, "\idle=mwait\" will be removed in 2012\"\n");
 	} else if (!strcmp(str, "halt")) {
 		/*
 		 * When the boot option of idle=halt is added, halt is
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index f65e5b521dbd..807c2a2b80f1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1363,7 +1363,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
  * We must return the syscall number to actually look up in the table.
  * This can be -1L to skip running any syscall at all.
  */
-asmregparm long syscall_trace_enter(struct pt_regs *regs)
+long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
@@ -1408,7 +1408,7 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	return ret ?: regs->orig_ax;
 }
 
-asmregparm void syscall_trace_leave(struct pt_regs *regs)
+void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 605e5ae19c7f..afaf38447ef5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -910,6 +910,13 @@ void __init setup_arch(char **cmdline_p)
 	memblock.current_limit = get_max_mapped();
 	memblock_x86_fill();
 
+	/*
+	 * The EFI specification says that boot service code won't be called
+	 * after ExitBootServices(). This is, in fact, a lie.
+	 */
+	if (efi_enabled)
+		efi_reserve_boot_services();
+
 	/* preallocate 4k for mptable mpc */
 	early_reserve_e820_mpc_new();
 
@@ -946,6 +953,8 @@ void __init setup_arch(char **cmdline_p)
 	if (init_ohci1394_dma_early)
 		init_ohci1394_dma_on_all_controllers();
 #endif
+	/* Allocate bigger log buffer */
+	setup_log_buf(1);
 
 	reserve_initrd();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a3c430bdfb60..eefd96765e79 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1307,7 +1307,7 @@ void play_dead_common(void)
 {
 	idle_task_exit();
 	reset_lazy_tlbstate();
-	c1e_remove_cpu(raw_smp_processor_id());
+	amd_e400_remove_cpu(raw_smp_processor_id());
 
 	mb();
 	/* Ack it */
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 32cbffb0c494..fbb0a045a1a2 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -345,3 +345,4 @@ ENTRY(sys_call_table)
 	.long sys_clock_adjtime
 	.long sys_syncfs
 	.long sys_sendmmsg		/* 345 */
+	.long sys_setns
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 998e972f3b1a..30ac65df7d4e 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -110,7 +110,6 @@ static struct mm_struct tboot_mm = {
 	.mmap_sem       = __RWSEM_INITIALIZER(init_mm.mmap_sem),
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
-	.cpu_vm_mask    = CPU_MASK_ALL,
 };
 
 static inline void switch_to_tboot_pt(void)
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 25a28a245937..00cbb272627f 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 9335bf7dd2e7..6cc6922262af 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -763,25 +763,6 @@ static cycle_t read_tsc(struct clocksource *cs)
 		ret : clocksource_tsc.cycle_last;
 }
 
-#ifdef CONFIG_X86_64
-static cycle_t __vsyscall_fn vread_tsc(void)
-{
-	cycle_t ret;
-
-	/*
-	 * Surround the RDTSC by barriers, to make sure it's not
-	 * speculated to outside the seqlock critical section and
-	 * does not cause time warps:
-	 */
-	rdtsc_barrier();
-	ret = (cycle_t)vget_cycles();
-	rdtsc_barrier();
-
-	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
-		ret : __vsyscall_gtod_data.clock.cycle_last;
-}
-#endif
-
 static void resume_tsc(struct clocksource *cs)
 {
 	clocksource_tsc.cycle_last = 0;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49927a863cc1..89aed99aafce 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -161,6 +161,12 @@ SECTIONS
 
 #define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
 #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+#define EMIT_VVAR(x, offset) .vsyscall_var_ ## x	\
+	ADDR(.vsyscall_0) + offset		 	\
+	: AT(VLOAD(.vsyscall_var_ ## x)) {     		\
+		*(.vsyscall_var_ ## x)			\
+	}						\
+	x = VVIRT(.vsyscall_var_ ## x);
 
 	. = ALIGN(4096);
 	__vsyscall_0 = .;
@@ -175,18 +181,6 @@ SECTIONS
 		*(.vsyscall_fn)
 	}
 
-	. = ALIGN(L1_CACHE_BYTES);
-	.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
-		*(.vsyscall_gtod_data)
-	}
-
-	vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
-	.vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
-		*(.vsyscall_clock)
-	}
-	vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
 	.vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
 		*(.vsyscall_1)
 	}
@@ -194,21 +188,14 @@ SECTIONS
 		*(.vsyscall_2)
 	}
 
-	.vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
-		*(.vgetcpu_mode)
-	}
-	vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
-	. = ALIGN(L1_CACHE_BYTES);
-	.jiffies : AT(VLOAD(.jiffies)) {
-		*(.jiffies)
-	}
-	jiffies = VVIRT(.jiffies);
-
 	.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
 		*(.vsyscall_3)
 	}
 
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+
 	. = __vsyscall_0 + PAGE_SIZE;
 
 #undef VSYSCALL_ADDR
@@ -216,6 +203,7 @@ SECTIONS
 #undef VLOAD
 #undef VVIRT_OFFSET
 #undef VVIRT
+#undef EMIT_VVAR
 
 #endif /* CONFIG_X86_64 */
 
@@ -326,7 +314,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kernel/vread_tsc_64.c b/arch/x86/kernel/vread_tsc_64.c
new file mode 100644
index 000000000000..a81aa9e9894c
--- /dev/null
+++ b/arch/x86/kernel/vread_tsc_64.c
@@ -0,0 +1,36 @@
+/* This code runs in userspace. */
+
+#define DISABLE_BRANCH_PROFILING
+#include <asm/vgtod.h>
+
+notrace cycle_t __vsyscall_fn vread_tsc(void)
+{
+	cycle_t ret;
+	u64 last;
+
+	/*
+	 * Empirically, a fence (of type that depends on the CPU)
+	 * before rdtsc is enough to ensure that rdtsc is ordered
+	 * with respect to loads.  The various CPU manuals are unclear
+	 * as to whether rdtsc can be reordered with later loads,
+	 * but no one has ever seen it happen.
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
+
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * GCC likes to generate cmov here, but this branch is extremely
+	 * predictable (it's just a funciton of time and the likely is
+	 * very likely) and there's a data dependence, so force GCC
+	 * to generate a branch instead.  I don't barrier() because
+	 * we don't actually need a barrier, and if this function
+	 * ever gets inlined it will generate worse code.
+	 */
+	asm volatile ("");
+	return last;
+}
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index dcbb28c4b694..3e682184d76c 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -49,17 +49,10 @@
 		__attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
 #define __syscall_clobber "r11","cx","memory"
 
-/*
- * vsyscall_gtod_data contains data that is :
- * - readonly from vsyscalls
- * - written by timer interrupt or systcl (/proc/sys/kernel/vsyscall64)
- * Try to keep this structure as small as possible to avoid cache line ping pongs
- */
-int __vgetcpu_mode __section_vgetcpu_mode;
-
-struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data =
+DEFINE_VVAR(int, vgetcpu_mode);
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
 {
-	.lock = SEQLOCK_UNLOCKED,
+	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
 	.sysctl_enabled = 1,
 };
 
@@ -97,7 +90,7 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
  */
 static __always_inline void do_get_tz(struct timezone * tz)
 {
-	*tz = __vsyscall_gtod_data.sys_tz;
+	*tz = VVAR(vsyscall_gtod_data).sys_tz;
 }
 
 static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
@@ -126,23 +119,24 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 	unsigned long mult, shift, nsec;
 	cycle_t (*vread)(void);
 	do {
-		seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+		seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
 
-		vread = __vsyscall_gtod_data.clock.vread;
-		if (unlikely(!__vsyscall_gtod_data.sysctl_enabled || !vread)) {
+		vread = VVAR(vsyscall_gtod_data).clock.vread;
+		if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled ||
+			     !vread)) {
 			gettimeofday(tv,NULL);
 			return;
 		}
 
 		now = vread();
-		base = __vsyscall_gtod_data.clock.cycle_last;
-		mask = __vsyscall_gtod_data.clock.mask;
-		mult = __vsyscall_gtod_data.clock.mult;
-		shift = __vsyscall_gtod_data.clock.shift;
+		base = VVAR(vsyscall_gtod_data).clock.cycle_last;
+		mask = VVAR(vsyscall_gtod_data).clock.mask;
+		mult = VVAR(vsyscall_gtod_data).clock.mult;
+		shift = VVAR(vsyscall_gtod_data).clock.shift;
 
-		tv->tv_sec = __vsyscall_gtod_data.wall_time_sec;
-		nsec = __vsyscall_gtod_data.wall_time_nsec;
-	} while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+		tv->tv_sec = VVAR(vsyscall_gtod_data).wall_time_sec;
+		nsec = VVAR(vsyscall_gtod_data).wall_time_nsec;
+	} while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
 
 	/* calculate interval: */
 	cycle_delta = (now - base) & mask;
@@ -171,15 +165,15 @@ time_t __vsyscall(1) vtime(time_t *t)
 {
 	unsigned seq;
 	time_t result;
-	if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
+	if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled))
 		return time_syscall(t);
 
 	do {
-		seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+		seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
 
-		result = __vsyscall_gtod_data.wall_time_sec;
+		result = VVAR(vsyscall_gtod_data).wall_time_sec;
 
-	} while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+	} while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
 
 	if (t)
 		*t = result;
@@ -208,9 +202,9 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 	   We do this here because otherwise user space would do it on
 	   its own in a likely inferior way (no access to jiffies).
 	   If you don't like it pass NULL. */
-	if (tcache && tcache->blob[0] == (j = __jiffies)) {
+	if (tcache && tcache->blob[0] == (j = VVAR(jiffies))) {
 		p = tcache->blob[1];
-	} else if (__vgetcpu_mode == VGETCPU_RDTSCP) {
+	} else if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
 		/* Load per CPU data from RDTSCP */
 		native_read_tscp(&p);
 	} else {