18 files changed, 70 insertions, 77 deletions

diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index a33d53017997..8ea040124f7d 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -128,13 +128,11 @@ void foo(void)
 	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
 #endif
 
-#ifdef CONFIG_LGUEST_GUEST
+#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
 	BLANK();
 	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
 	OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir);
-#endif
 
-#ifdef CONFIG_LGUEST
 	BLANK();
 	OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc);
 	OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f86a3c4a2669..a38aafaefc23 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -504,7 +504,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	/* Clear all flags overriden by options */
 	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] ^= cleared_cpu_caps[i];
+		c->x86_capability[i] &= ~cleared_cpu_caps[i];
 
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index b6e136f23d3d..be83336fddba 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -43,6 +43,7 @@
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
+#include <asm/kvm_para.h>
 #include "mtrr.h"
 
 u32 num_var_ranges = 0;
@@ -649,6 +650,7 @@ static __init int amd_special_default_mtrr(void)
 
 /**
  * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
+ * @end_pfn: ending page frame number
  *
  * Some buggy BIOSes don't setup the MTRRs properly for systems with certain
  * memory configurations.  This routine checks that the highest MTRR matches
@@ -688,8 +690,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
 	if (!highest_pfn) {
-		printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n");
-		WARN_ON(1);
+		if (!kvm_para_available()) {
+			printk(KERN_WARNING
+				"WARNING: strange, CPU MTRRs all blank?\n");
+			WARN_ON(1);
+		}
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 200fb3f9ebfb..e8b422c1c512 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -76,13 +76,6 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 	/* All Transmeta CPUs have a constant TSC */
 	set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
 	
-	/* If we can run i686 user-space code, call us an i686 */
-#define USER686 ((1 << X86_FEATURE_TSC)|\
-		 (1 << X86_FEATURE_CX8)|\
-		 (1 << X86_FEATURE_CMOV))
-        if (c->x86 == 5 && (c->x86_capability[0] & USER686) == USER686)
-		c->x86 = 6;
-
 #ifdef CONFIG_SYSCTL
 	/* randomize_va_space slows us down enormously;
 	   it probably triggers retranslation of x86->native bytecode */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2ad9a1bc6a73..c20c9e7e08dd 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -453,6 +453,7 @@ ENTRY(stub_execve)
 	CFI_REGISTER rip, r11
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
+	movq %rsp, %rcx
 	call sys_execve
 	RESTORE_TOP_OF_STACK %r11
 	movq %rax,RAX(%rsp)
@@ -1036,15 +1037,16 @@ ENDPROC(child_rip)
  *	rdi: name, rsi: argv, rdx: envp
  *
  * We want to fallback into:
- *	extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs)
+ *	extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs)
  *
  * do_sys_execve asm fallback arguments:
- *	rdi: name, rsi: argv, rdx: envp, fake frame on the stack
+ *	rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack
  */
 ENTRY(kernel_execve)
 	CFI_STARTPROC
 	FAKE_STACK_FRAME $0
 	SAVE_ALL	
+	movq %rsp,%rcx
 	call sys_execve
 	movq %rax, RAX(%rsp)	
 	RESTORE_REST
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 25eb98540a41..fd8ca53943a8 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -606,7 +606,7 @@ ENTRY(_stext)
 .section ".bss.page_aligned","wa"
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-ENTRY(swapper_pg_pmd)
+swapper_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(swapper_pg_dir)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index eb415043a929..a007454133a3 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -379,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt)
 	/* Since I easily can, map the first 1G.
 	 * Don't set NX because code runs from these pages.
 	 */
-	PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
 
 NEXT_PAGE(level2_kernel_pgt)
-	/* 40MB kernel mapping. The kernel code cannot be bigger than that.
-	   When you change this change KERNEL_TEXT_SIZE in page.h too. */
-	/* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
-	PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE)
-	/* Module mapping starts here */
-	.fill	(PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0
+	/*
+	 * 128 MB kernel mapping. We spend a full page on this pagetable
+	 * anyway.
+	 *
+	 * The kernel code+data+bss must not be bigger than that.
+	 *
+	 * (NOTE: at +128MB starts the module area, see MODULES_VADDR.
+	 *  If you want to increase this then increase MODULES_VADDR
+	 *  too.)
+	 */
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL,
+		KERNEL_IMAGE_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_spare_pgt)
-	.fill   512,8,0
+	.fill   512, 8, 0
 
 #undef PMDS
 #undef NEXT_PAGE
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 429d084e014d..235fd6c77504 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -368,8 +368,8 @@ static int hpet_clocksource_register(void)
 	return 0;
 }
 
-/*
- * Try to setup the HPET timer
+/**
+ * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
 int __init hpet_enable(void)
 {
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 5b3ce7934363..3d01e47777db 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -15,6 +15,7 @@ static struct files_struct init_files = INIT_FILES;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
+EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */
 
 /*
  * Initial thread structure.
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a7d50a547dc2..be3c7a299f02 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -603,11 +603,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	}
 #endif
 
+#ifdef X86_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
+#endif
 
 
 	if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b0cc8f0136d8..3baf9b9f4c87 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -604,11 +604,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
 
+#ifdef X86_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
+#endif
 }
 
 /*
@@ -730,16 +732,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
  */
 asmlinkage
 long sys_execve(char __user *name, char __user * __user *argv,
-		char __user * __user *envp, struct pt_regs regs)
+		char __user * __user *envp, struct pt_regs *regs)
 {
 	long error;
 	char * filename;
 
 	filename = getname(name);
 	error = PTR_ERR(filename);
-	if (IS_ERR(filename)) 
+	if (IS_ERR(filename))
 		return error;
-	error = do_execve(filename, argv, envp, &regs); 
+	error = do_execve(filename, argv, envp, regs);
 	putname(filename);
 	return error;
 }
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index d862e396b099..f41fdc98efb1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -544,6 +544,8 @@ static int ptrace_set_debugreg(struct task_struct *child,
 	return 0;
 }
 
+#ifdef X86_BTS
+
 static int ptrace_bts_get_size(struct task_struct *child)
 {
 	if (!child->thread.ds_area_msr)
@@ -826,6 +828,7 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk,
 
 	ptrace_bts_write_record(tsk, &rec);
 }
+#endif /* X86_BTS */
 
 /*
  * Called by kernel/ptrace.c when detaching..
@@ -839,7 +842,9 @@ void ptrace_disable(struct task_struct *child)
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
 	if (child->thread.ds_area_msr) {
+#ifdef X86_BTS
 		ptrace_bts_realloc(child, 0, 0);
+#endif
 		child->thread.debugctlmsr &= ~ds_debugctl_mask();
 		if (!child->thread.debugctlmsr)
 			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
@@ -961,6 +966,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 #endif
 
+	/*
+	 * These bits need more cooking - not enabled yet:
+	 */
+#ifdef X86_BTS
 	case PTRACE_BTS_CONFIG:
 		ret = ptrace_bts_config
 			(child, data, (struct ptrace_bts_config __user *)addr);
@@ -988,6 +997,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		ret = ptrace_bts_drain
 			(child, data, (struct bts_struct __user *) addr);
 		break;
+#endif
 
 	default:
 		ret = ptrace_request(child, request, addr, data);
@@ -1226,12 +1236,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SETOPTIONS:
 	case PTRACE_SET_THREAD_AREA:
 	case PTRACE_GET_THREAD_AREA:
+#ifdef X86_BTS
 	case PTRACE_BTS_CONFIG:
 	case PTRACE_BTS_STATUS:
 	case PTRACE_BTS_SIZE:
 	case PTRACE_BTS_GET:
 	case PTRACE_BTS_CLEAR:
 	case PTRACE_BTS_DRAIN:
+#endif
 		return sys_ptrace(request, pid, addr, data);
 
 	default:
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6fd804f07821..7637dc91c79b 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -1021,7 +1021,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	/* Clear all flags overriden by options */
 	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] ^= cleared_cpu_caps[i];
+		c->x86_capability[i] &= ~cleared_cpu_caps[i];
 
 #ifdef CONFIG_X86_MCE
 	mcheck_init(c);
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index d53bd6fcb428..0880f2c388a9 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -554,10 +554,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 	int timeout;
 	unsigned long start_rip;
 	struct create_idle c_idle = {
-		.work = __WORK_INITIALIZER(c_idle.work, do_fork_idle),
 		.cpu = cpu,
 		.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
 	};
+	INIT_WORK(&c_idle.work, do_fork_idle);
 
 	/* allocate memory for gdts of secondary cpus. Hotplug is considered */
 	if (!cpu_gdt_descr[cpu].address &&
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 02f0f61f5b11..c28c342c162f 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -25,6 +25,8 @@ static int save_stack_stack(void *data, char *name)
 static void save_stack_address(void *data, unsigned long addr, int reliable)
 {
 	struct stack_trace *trace = data;
+	if (!reliable)
+		return;
 	if (trace->skip > 0) {
 		trace->skip--;
 		return;
@@ -37,6 +39,8 @@ static void
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
 	struct stack_trace *trace = (struct stack_trace *)data;
+	if (!reliable)
+		return;
 	if (in_sched_functions(addr))
 		return;
 	if (trace->skip > 0) {
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6dfd4e76661a..022bcaa3b42e 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -91,7 +91,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 
 asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
 {
-	return do_set_thread_area(current, -1, u_info, 1);
+	int ret = do_set_thread_area(current, -1, u_info, 1);
+	prevent_tail_call(ret);
+	return ret;
 }
 
 
@@ -139,7 +141,9 @@ int do_get_thread_area(struct task_struct *p, int idx,
 
 asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
 {
-	return do_get_thread_area(current, -1, u_info);
+	int ret = do_get_thread_area(current, -1, u_info);
+	prevent_tail_call(ret);
+	return ret;
 }
 
 int regset_tls_active(struct task_struct *target,
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 43517e324be8..f14cfd9d1f94 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -28,7 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz);
 static int __init tsc_setup(char *str)
 {
 	printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, "
-				"cannot disable TSC.\n");
+				"cannot disable TSC completely.\n");
+	mark_tsc_unstable("user disabled TSC");
 	return 1;
 }
 #else
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 3f8242774580..edff4c985485 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -44,11 +44,6 @@
 
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","cx","memory"
-#define __pa_vsymbol(x)			\
-	({unsigned long v;  		\
-	extern char __vsyscall_0; 	\
-	  asm("" : "=r" (v) : "0" (x)); \
-	  ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); })
 
 /*
  * vsyscall_gtod_data contains data that is :
@@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz)
 static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	int ret;
-	asm volatile("vsysc2: syscall"
+	asm volatile("syscall"
 		: "=a" (ret)
 		: "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
 		: __syscall_clobber );
@@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 static __always_inline long time_syscall(long *t)
 {
 	long secs;
-	asm volatile("vsysc1: syscall"
+	asm volatile("syscall"
 		: "=a" (secs)
 		: "0" (__NR_time),"D" (t) : __syscall_clobber);
 	return secs;
@@ -228,42 +223,11 @@ long __vsyscall(3) venosys_1(void)
 
 #ifdef CONFIG_SYSCTL
 
-#define SYSCALL 0x050f
-#define NOP2    0x9090
-
-/*
- * NOP out syscall in vsyscall page when not needed.
- */
-static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
-                        void __user *buffer, size_t *lenp, loff_t *ppos)
+static int
+vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
+		       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	extern u16 vsysc1, vsysc2;
-	u16 __iomem *map1;
-	u16 __iomem *map2;
-	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-	if (!write)
-		return ret;
-	/* gcc has some trouble with __va(__pa()), so just do it this
-	   way. */
-	map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
-	if (!map1)
-		return -ENOMEM;
-	map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
-	if (!map2) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	if (!vsyscall_gtod_data.sysctl_enabled) {
-		writew(SYSCALL, map1);
-		writew(SYSCALL, map2);
-	} else {
-		writew(NOP2, map1);
-		writew(NOP2, map2);
-	}
-	iounmap(map2);
-out:
-	iounmap(map1);
-	return ret;
+	return proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
 }
 
 static ctl_table kernel_table2[] = {
@@ -279,7 +243,6 @@ static ctl_table kernel_root_table2[] = {
 	  .child = kernel_table2 },
 	{}
 };
-
 #endif
 
 /* Assume __initcall executes before all user space. Hopefully kmod