Merge branch 'upstream'

18 files changed, 96 insertions, 55 deletions

diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index fffd6b0a2fa..70b9d21ed67 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -80,7 +80,7 @@ static int __init aperture_valid(char *name, u64 aper_base, u32 aper_size)
 		printk("Aperture from %s beyond 4GB. Ignoring.\n",name);
 		return 0; 
 	}
-	if (e820_mapped(aper_base, aper_base + aper_size, E820_RAM)) {  
+	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
 		printk("Aperture from %s pointing to e820 RAM. Ignoring.\n",name);
 		return 0; 
 	} 
diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c
index d54620147e8..100a30c4004 100644
--- a/arch/x86_64/kernel/apic.c
+++ b/arch/x86_64/kernel/apic.c
@@ -615,7 +615,7 @@ static int __init apic_set_verbosity(char *str)
 		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
 				" use apic=verbose or apic=debug", str);
 
-	return 0;
+	return 1;
 }
 
 __setup("apic=", apic_set_verbosity);
@@ -1137,35 +1137,35 @@ int __init APIC_init_uniprocessor (void)
 static __init int setup_disableapic(char *str) 
 { 
 	disable_apic = 1;
-	return 0;
+	return 1;
 } 
 
 static __init int setup_nolapic(char *str) 
 { 
 	disable_apic = 1;
-	return 0;
+	return 1;
 } 
 
 static __init int setup_noapictimer(char *str) 
 { 
 	if (str[0] != ' ' && str[0] != 0)
-		return -1;
+		return 0;
 	disable_apic_timer = 1;
-	return 0;
+	return 1;
 } 
 
 static __init int setup_apicmaintimer(char *str)
 {
 	apic_runs_main_timer = 1;
 	nohpet = 1;
-	return 0;
+	return 1;
 }
 __setup("apicmaintimer", setup_apicmaintimer);
 
 static __init int setup_noapicmaintimer(char *str)
 {
 	apic_runs_main_timer = -1;
-	return 0;
+	return 1;
 }
 __setup("noapicmaintimer", setup_noapicmaintimer);
 
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 293cd71a266..62776c07cff 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -80,7 +80,12 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size)
 	return 0;
 } 
 
-int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) 
+/*
+ * This function checks if any part of the range <start,end> is mapped
+ * with type.
+ */
+int __meminit
+e820_any_mapped(unsigned long start, unsigned long end, unsigned type)
 { 
 	int i;
 	for (i = 0; i < e820.nr_map; i++) { 
@@ -94,6 +99,35 @@ int __init e820_mapped(unsigned long start, unsigned long end, unsigned type)
 	return 0;
 }
 
+/*
+ * This function checks if the entire range <start,end> is mapped with type.
+ *
+ * Note: this function only works correct if the e820 table is sorted and
+ * not-overlapping, which is the case
+ */
+int __init e820_all_mapped(unsigned long start, unsigned long end, unsigned type)
+{
+	int i;
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		if (type && ei->type != type)
+			continue;
+		/* is the region (part) in overlap with the current region ?*/
+		if (ei->addr >= end || ei->addr + ei->size <= start)
+			continue;
+
+		/* if the region is at the beginning of <start,end> we move
+		 * start to the end of the region since it's ok until there
+		 */
+		if (ei->addr <= start)
+			start = ei->addr + ei->size;
+		/* if start is now at or beyond end, we're done, full coverage */
+		if (start >= end)
+			return 1; /* we're done */
+	}
+	return 0;
+}
+
 /* 
  * Find a free area in a specific range. 
  */ 
diff --git a/arch/x86_64/kernel/early_printk.c b/arch/x86_64/kernel/early_printk.c
index 13af920b659..b93ef5b5198 100644
--- a/arch/x86_64/kernel/early_printk.c
+++ b/arch/x86_64/kernel/early_printk.c
@@ -221,7 +221,7 @@ int __init setup_early_printk(char *opt)
 	char buf[256];
 
 	if (early_console_initialized)
-		return -1;
+		return 1;
 
 	strlcpy(buf,opt,sizeof(buf));
 	space = strchr(buf, ' ');
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index 8538bfea30e..c946e4fe67a 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -180,6 +180,10 @@ rff_trace:
  *
  * XXX	if we had a free scratch register we could save the RSP into the stack frame
  *      and report it properly in ps. Unfortunately we haven't.
+ *
+ * When user can change the frames always force IRET. That is because
+ * it deals with uncanonical addresses better. SYSRET has trouble
+ * with them due to bugs in both AMD and Intel CPUs.
  */ 			 		
 
 ENTRY(system_call)
@@ -254,7 +258,10 @@ sysret_signal:
 	xorl %esi,%esi # oldset -> arg2
 	call ptregscall_common
 1:	movl $_TIF_NEED_RESCHED,%edi
-	jmp sysret_check
+	/* Use IRET because user could have changed frame. This
+	   works because ptregscall_common has called FIXUP_TOP_OF_STACK. */
+	cli
+	jmp int_with_check
 	
 badsys:
 	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
@@ -280,7 +287,8 @@ tracesys:
 	call syscall_trace_leave
 	RESTORE_TOP_OF_STACK %rbx
 	RESTORE_REST
-	jmp ret_from_sys_call
+	/* Use IRET because user could have changed frame */
+	jmp int_ret_from_sys_call
 	CFI_ENDPROC
 		
 /* 
@@ -408,25 +416,9 @@ ENTRY(stub_execve)
 	CFI_ADJUST_CFA_OFFSET -8
 	CFI_REGISTER rip, r11
 	SAVE_REST
-	movq %r11, %r15
-	CFI_REGISTER rip, r15
 	FIXUP_TOP_OF_STACK %r11
 	call sys_execve
-	GET_THREAD_INFO(%rcx)
-	bt $TIF_IA32,threadinfo_flags(%rcx)
-	CFI_REMEMBER_STATE
-	jc exec_32bit
 	RESTORE_TOP_OF_STACK %r11
-	movq %r15, %r11
-	CFI_REGISTER rip, r11
-	RESTORE_REST
-	pushq %r11
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rip, 0
-	ret
-
-exec_32bit:
-	CFI_RESTORE_STATE
 	movq %rax,RAX(%rsp)
 	RESTORE_REST
 	jmp int_ret_from_sys_call
diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 04282ef9fbd..6f0790e8b6d 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -29,6 +29,8 @@
 #define MISC_MCELOG_MINOR 227
 #define NR_BANKS 6
 
+atomic_t mce_entry;
+
 static int mce_dont_init;
 
 /* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic,
@@ -172,10 +174,12 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 	int i;
 	int panicm_found = 0;
 
+	atomic_inc(&mce_entry);
+
 	if (regs)
 		notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL);
 	if (!banks)
-		return;
+		goto out2;
 
 	memset(&m, 0, sizeof(struct mce));
 	m.cpu = safe_smp_processor_id();
@@ -266,6 +270,8 @@ void do_machine_check(struct pt_regs * regs, long error_code)
  out:
 	/* Last thing done in the machine check exception to clear state. */
 	wrmsrl(MSR_IA32_MCG_STATUS, 0);
+ out2:
+	atomic_dec(&mce_entry);
 }
 
 /*
@@ -501,7 +507,7 @@ static struct miscdevice mce_log_device = {
 static int __init mcheck_disable(char *str)
 {
 	mce_dont_init = 1;
-	return 0;
+	return 1;
 }
 
 /* mce=off disables machine check. Note you can reenable it later
@@ -521,7 +527,7 @@ static int __init mcheck_enable(char *str)
 		get_option(&str, &tolerant);
 	else
 		printk("mce= argument %s ignored. Please use /sys", str); 
-	return 0;
+	return 1;
 }
 
 __setup("nomce", mcheck_disable);
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index d9e4067faf0..4e6357fe0ec 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -34,6 +34,7 @@
 #include <asm/proto.h>
 #include <asm/kdebug.h>
 #include <asm/local.h>
+#include <asm/mce.h>
 
 /*
  * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
@@ -480,6 +481,12 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 		__get_cpu_var(nmi_touch) = 0;
 		touched = 1;
 	}
+#ifdef CONFIG_X86_MCE
+	/* Could check oops_in_progress here too, but it's safer
+	   not too */
+	if (atomic_read(&mce_entry) > 0)
+		touched = 1;
+#endif
 	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
 		/*
 		 * Ayiee, looks like this CPU is stuck ...
diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c
index 03c9eeedb0f..af035ede70c 100644
--- a/arch/x86_64/kernel/pci-dma.c
+++ b/arch/x86_64/kernel/pci-dma.c
@@ -48,9 +48,11 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
 {
 	struct page *page;
 	int node;
+#ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type)
 		node = pcibus_to_node(to_pci_dev(dev)->bus);
 	else
+#endif
 		node = numa_node_id();
 	page = alloc_pages_node(node, gfp, order);
 	return page ? page_address(page) : NULL;
diff --git a/arch/x86_64/kernel/pmtimer.c b/arch/x86_64/kernel/pmtimer.c
index ee5ee4891f3..b0444a415bd 100644
--- a/arch/x86_64/kernel/pmtimer.c
+++ b/arch/x86_64/kernel/pmtimer.c
@@ -121,7 +121,7 @@ unsigned int do_gettimeoffset_pm(void)
 static int __init nopmtimer_setup(char *s)
 {
 	pmtmr_ioport = 0;
-	return 0;
+	return 1;
 }
 
 __setup("nopmtimer", nopmtimer_setup);
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 70dd8e5c688..1c44b53cb15 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -781,10 +781,16 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 	}
 	case ARCH_GET_GS: { 
 		unsigned long base;
+		unsigned gsindex;
 		if (task->thread.gsindex == GS_TLS_SEL)
 			base = read_32bit_tls(task, GS_TLS);
-		else if (doit)
-			rdmsrl(MSR_KERNEL_GS_BASE, base);
+		else if (doit) {
+ 			asm("movl %%gs,%0" : "=r" (gsindex));
+			if (gsindex)
+				rdmsrl(MSR_KERNEL_GS_BASE, base);
+			else
+				base = task->thread.gs;
+		}
 		else
 			base = task->thread.gs;
 		ret = put_user(base, (unsigned long __user *)addr); 
diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
index d44b2c1e63a..da8e7903d81 100644
--- a/arch/x86_64/kernel/ptrace.c
+++ b/arch/x86_64/kernel/ptrace.c
@@ -274,11 +274,6 @@ static int putreg(struct task_struct *child,
 				return -EIO;
 			value &= 0xffff;
 			break;
-		case offsetof(struct user_regs_struct, rip):
-			/* Check if the new RIP address is canonical */
-			if (value >= TASK_SIZE_OF(child))
-				return -EIO;
-			break;
 	}
 	put_stack_long(child, regno - sizeof(struct pt_regs), value);
 	return 0;
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index d1f3e9272c0..c50b06765a8 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -353,8 +353,10 @@ static __init void parse_cmdline_early (char ** cmdline_p)
 		if (fullarg(from, "enable_timer_pin_1"))
 			disable_timer_pin_1 = -1;
 
-		if (fullarg(from, "nolapic") || fullarg(from, "disableapic"))
+		if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) {
+			clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
 			disable_apic = 1;
+		}
 
 		if (fullarg(from, "noapic"))
 			skip_ioapic_setup = 1;
@@ -540,7 +542,7 @@ void __init alternative_instructions(void)
 static int __init noreplacement_setup(char *s)
 { 
      no_replacement = 1; 
-     return 0; 
+     return 1;
 } 
 
 __setup("noreplacement", noreplacement_setup); 
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c
index eabdb63fec3..8a691fa6d39 100644
--- a/arch/x86_64/kernel/setup64.c
+++ b/arch/x86_64/kernel/setup64.c
@@ -55,7 +55,7 @@ int __init nonx_setup(char *str)
 		do_not_nx = 1;
 		__supported_pte_mask &= ~_PAGE_NX;
         }
-	return 0;
+	return 1;
 } 
 __setup("noexec=", nonx_setup);	/* parsed early actually */
 
@@ -74,7 +74,7 @@ static int __init nonx32_setup(char *str)
 		force_personality32 &= ~READ_IMPLIES_EXEC;
 	else if (!strcmp(str, "off"))
 		force_personality32 |= READ_IMPLIES_EXEC;
-	return 0;
+	return 1;
 }
 __setup("noexec32=", nonx32_setup);
 
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index ea48fa63807..71a7222cf9c 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -353,7 +353,7 @@ static void __cpuinit tsc_sync_wait(void)
 static __init int notscsync_setup(char *s)
 {
 	notscsync = 1;
-	return 0;
+	return 1;
 }
 __setup("notscsync", notscsync_setup);
 
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 473b514b66e..7392570f975 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -726,7 +726,7 @@ static __init int late_hpet_init(void)
 	unsigned int 		ntimer;
 
 	if (!vxtime.hpet_address)
-        	return -1;
+        	return 0;
 
 	memset(&hd, 0, sizeof (hd));
 
@@ -917,6 +917,8 @@ void __init time_init(void)
 		vxtime.hpet_address = 0;
 
 	if (hpet_use_timer) {
+		/* set tick_nsec to use the proper rate for HPET */
+	  	tick_nsec = TICK_NSEC_HPET;
 		cpu_khz = hpet_calibrate_tsc();
 		timename = "HPET";
 #ifdef CONFIG_X86_PM_TIMER
@@ -1306,7 +1308,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 static int __init nohpet_setup(char *s) 
 { 
 	nohpet = 1;
-	return 0;
+	return 1;
 } 
 
 __setup("nohpet", nohpet_setup);
@@ -1314,7 +1316,7 @@ __setup("nohpet", nohpet_setup);
 int __init notsc_setup(char *s)
 {
 	notsc = 1;
-	return 0;
+	return 1;
 }
 
 __setup("notsc", notsc_setup);
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index edaa9fe654d..6bda322d3ca 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -973,14 +973,14 @@ void __init trap_init(void)
 static int __init oops_dummy(char *s)
 { 
 	panic_on_oops = 1;
-	return -1; 
+	return 1;
 } 
 __setup("oops=", oops_dummy); 
 
 static int __init kstack_setup(char *s)
 {
 	kstack_depth_to_print = simple_strtoul(s,NULL,0);
-	return 0;
+	return 1;
 }
 __setup("kstack=", kstack_setup);
 
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 39ff0708f80..b81f473c4a1 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -65,7 +65,7 @@ SECTIONS
   .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
 	*(.data.cacheline_aligned)
   }
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+  . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
   .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
   	*(.data.read_mostly)
   }
diff --git a/arch/x86_64/kernel/x8664_ksyms.c b/arch/x86_64/kernel/x8664_ksyms.c
index d96a9348e5a..1def21c9f7c 100644
--- a/arch/x86_64/kernel/x8664_ksyms.c
+++ b/arch/x86_64/kernel/x8664_ksyms.c
@@ -102,8 +102,6 @@ EXPORT_SYMBOL(cpu_callout_map);
 EXPORT_SYMBOL(screen_info);
 #endif
 
-EXPORT_SYMBOL(get_wchan);
-
 EXPORT_SYMBOL(rtc_lock);
 
 EXPORT_SYMBOL_GPL(set_nmi_callback);
@@ -114,7 +112,6 @@ EXPORT_SYMBOL_GPL(unset_nmi_callback);
 #undef memcpy
 #undef memset
 #undef memmove
-#undef strlen
 
 extern void * memset(void *,int,__kernel_size_t);
 extern size_t strlen(const char *);
@@ -123,8 +120,6 @@ extern void * memcpy(void *,const void *,__kernel_size_t);
 extern void * __memcpy(void *,const void *,__kernel_size_t);
 
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strpbrk);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(__memcpy);