Merge branches 'softirq-for-linus', 'x86-debug-for-linus', 'x86-numa-…

…for-linus', 'x86-quirks-for-linus', 'x86-setup-for-linus', 'x86-uv-for-linus' and 'x86-vm86-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'softirq-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  softirqs: Make wakeup_softirqd static

* 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, asm: Restore parentheses around one pushl_cfi argument
  x86, asm: Fix ancient-GAS workaround
  x86, asm: Fix CFI macro invocations to deal with shortcomings in gas

* 'x86-numa-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, numa: Assign CPUs to nodes in round-robin manner on fake NUMA

* 'x86-quirks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: HPET force enable for CX700 / VIA Epia LT

* 'x86-setup-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, setup: Use string copy operation to optimze copy in kernel compression

* 'x86-uv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, UV: Use allocated buffer in tlb_uv.c:tunables_read()

* 'x86-vm86-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, vm86: Fix preemption bug for int1 debug and int3 breakpoint handlers.

Kbuild

@@ -53,6 +53,7 @@ targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
 	"/^->/{s:->#\(.*\):/* \1 */:; \
+	s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 (\2) /* \3 */:; \
 	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
 	s:->::; p;}"
 endef

arch/x86/boot/compressed/misc.c

@@ -229,18 +229,35 @@ void *memset(void *s, int c, size_t n)
 		ss[i] = c;
 	return s;
 }
-
+#ifdef CONFIG_X86_32
 void *memcpy(void *dest, const void *src, size_t n)
 {
-	int i;
-	const char *s = src;
-	char *d = dest;
+	int d0, d1, d2;
+	asm volatile(
+		"rep ; movsl\n\t"
+		"movl %4,%%ecx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+		: "memory");
 
-	for (i = 0; i < n; i++)
-		d[i] = s[i];
 	return dest;
 }
+#else
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	long d0, d1, d2;
+	asm volatile(
+		"rep ; movsq\n\t"
+		"movq %4,%%rcx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
+		: "memory");
 
+	return dest;
+}
+#endif
 
 static void error(char *x)
 {

arch/x86/include/asm/calling.h

@@ -48,36 +48,38 @@ For 32-bit we have the following conventions - kernel is built with
 
 
 /*
- * 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
+ * 64-bit system call stack frame layout defines and helpers, for
+ * assembly code (note that the seemingly unnecessary parentheses
+ * are to prevent cpp from inserting spaces in expressions that get
+ * passed to macros):
  */
 
-#define R15		  0
-#define R14		  8
-#define R13		 16
-#define R12		 24
-#define RBP		 32
-#define RBX		 40
+#define R15		  (0)
+#define R14		  (8)
+#define R13		 (16)
+#define R12		 (24)
+#define RBP		 (32)
+#define RBX		 (40)
 
 /* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11		 48
-#define R10		 56
-#define R9		 64
-#define R8		 72
-#define RAX		 80
-#define RCX		 88
-#define RDX		 96
-#define RSI		104
-#define RDI		112
-#define ORIG_RAX	120       /* + error_code */
+#define R11		 (48)
+#define R10		 (56)
+#define R9		 (64)
+#define R8		 (72)
+#define RAX		 (80)
+#define RCX		 (88)
+#define RDX		 (96)
+#define RSI		(104)
+#define RDI		(112)
+#define ORIG_RAX	(120)       /* + error_code */
 /* end of arguments */
 
 /* cpu exception frame or undefined in case of fast syscall: */
-#define RIP		128
-#define CS		136
-#define EFLAGS		144
-#define RSP		152
-#define SS		160
+#define RIP		(128)
+#define CS		(136)
+#define EFLAGS		(144)
+#define RSP		(152)
+#define SS		(160)
 
 #define ARGOFFSET	R11
 #define SWFRAME		ORIG_RAX
@@ -111,7 +113,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define ARG_SKIP	9*8
+#define ARG_SKIP	(9*8)
 
 	.macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
 			    skipr8910=0, skiprdx=0
@@ -169,7 +171,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define REST_SKIP	6*8
+#define REST_SKIP	(6*8)
 
 	.macro SAVE_REST
 	subq $REST_SKIP, %rsp

arch/x86/include/asm/entry_arch.h

@@ -16,22 +16,11 @@ BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
-BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+.irpc idx, "01234567"
+BUILD_INTERRUPT3(invalidate_interrupt\idx,
+		 (INVALIDATE_TLB_VECTOR_START)+\idx,
 		 smp_invalidate_interrupt)
+.endr
 #endif
 
 BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)

arch/x86/include/asm/segment.h

@@ -73,31 +73,31 @@
 
 #define GDT_ENTRY_DEFAULT_USER_DS	15
 
-#define GDT_ENTRY_KERNEL_BASE	12
+#define GDT_ENTRY_KERNEL_BASE		(12)
 
-#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE + 0)
+#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE+0)
 
-#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE + 1)
+#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE+1)
 
-#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE + 4)
-#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE + 5)
+#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE+4)
+#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE+5)
 
-#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 6)
-#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 11)
+#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE+6)
+#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE+11)
 
-#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE + 14)
-#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE+14)
+#define __ESPFIX_SS			(GDT_ENTRY_ESPFIX_SS*8)
 
-#define GDT_ENTRY_PERCPU			(GDT_ENTRY_KERNEL_BASE + 15)
+#define GDT_ENTRY_PERCPU		(GDT_ENTRY_KERNEL_BASE+15)
 #ifdef CONFIG_SMP
 #define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
 #else
 #define __KERNEL_PERCPU 0
 #endif
 
-#define GDT_ENTRY_STACK_CANARY		(GDT_ENTRY_KERNEL_BASE + 16)
+#define GDT_ENTRY_STACK_CANARY		(GDT_ENTRY_KERNEL_BASE+16)
 #ifdef CONFIG_CC_STACKPROTECTOR
-#define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY * 8)
+#define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY*8)
 #else
 #define __KERNEL_STACK_CANARY		0
 #endif
@@ -182,10 +182,10 @@
 
 #endif
 
-#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS * 8)
-#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS * 8)
-#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
-#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
+#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS*8)
+#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS*8)
+#define __USER_DS	(GDT_ENTRY_DEFAULT_USER_DS*8+3)
+#define __USER_CS	(GDT_ENTRY_DEFAULT_USER_CS*8+3)
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif

arch/x86/kernel/asm-offsets_32.c

@@ -99,9 +99,7 @@ void foo(void)
 
 	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
 	DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
-	DEFINE(PTRS_PER_PTE, PTRS_PER_PTE);
-	DEFINE(PTRS_PER_PMD, PTRS_PER_PMD);
-	DEFINE(PTRS_PER_PGD, PTRS_PER_PGD);
+	DEFINE(THREAD_SIZE_asm, THREAD_SIZE);
 
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
 

arch/x86/kernel/cpu/intel.c

@@ -284,9 +284,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE)
-		node = first_node(node_online_map);
-	else if (!node_online(node)) {
+	if (node == NUMA_NO_NODE || !node_online(node)) {
 		/* reuse the value from init_cpu_to_node() */
 		node = cpu_to_node(cpu);
 	}

arch/x86/kernel/entry_32.S

@@ -382,20 +382,20 @@ sysenter_past_esp:
 	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
 	 * we immediately enable interrupts at that point anyway.
 	 */
-	pushl_cfi $(__USER_DS)
+	pushl_cfi $__USER_DS
 	/*CFI_REL_OFFSET ss, 0*/
 	pushl_cfi %ebp
 	CFI_REL_OFFSET esp, 0
 	pushfl_cfi
 	orl $X86_EFLAGS_IF, (%esp)
-	pushl_cfi $(__USER_CS)
+	pushl_cfi $__USER_CS
 	/*CFI_REL_OFFSET cs, 0*/
 	/*
 	 * Push current_thread_info()->sysenter_return to the stack.
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
-	pushl_cfi (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
+	pushl_cfi (TI_sysenter_return-THREAD_SIZE_asm+8+4*4)(%esp)
 	CFI_REL_OFFSET eip, 0
 
 	pushl_cfi %eax

arch/x86/kernel/entry_64.S

@@ -963,22 +963,10 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
 	x86_platform_ipi smp_x86_platform_ipi
 
 #ifdef CONFIG_SMP
-apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \
-	invalidate_interrupt0 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+1 \
-	invalidate_interrupt1 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+2 \
-	invalidate_interrupt2 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+3 \
-	invalidate_interrupt3 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+4 \
-	invalidate_interrupt4 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+5 \
-	invalidate_interrupt5 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+6 \
-	invalidate_interrupt6 smp_invalidate_interrupt
-apicinterrupt INVALIDATE_TLB_VECTOR_START+7 \
-	invalidate_interrupt7 smp_invalidate_interrupt
+.irpc idx, "01234567"
+apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \
+	invalidate_interrupt\idx smp_invalidate_interrupt
+.endr
 #endif
 
 apicinterrupt THRESHOLD_APIC_VECTOR \

arch/x86/kernel/quirks.c

@@ -344,6 +344,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235,
 			 vt8237_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
 			 vt8237_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_CX700,
+			 vt8237_force_enable_hpet);
 
 static void ati_force_hpet_resume(void)
 {

arch/x86/kernel/tlb_uv.c

@@ -1001,18 +1001,23 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
 static ssize_t tunables_read(struct file *file, char __user *userbuf,
 						size_t count, loff_t *ppos)
 {
-	char buf[300];
+	char *buf;
 	int ret;
 
-	ret = snprintf(buf, 300, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
+	buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
 		"max_bau_concurrent plugged_delay plugsb4reset",
 		"timeoutsb4reset ipi_reset_limit complete_threshold",
 		"congested_response_us congested_reps congested_period",
 		max_bau_concurrent, plugged_delay, plugsb4reset,
 		timeoutsb4reset, ipi_reset_limit, complete_threshold,
 		congested_response_us, congested_reps, congested_period);
 
-	return simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf));
+	kfree(buf);
+	return ret;
 }
 
 /*

arch/x86/kernel/traps.c

@@ -575,6 +575,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	if (regs->flags & X86_VM_MASK) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs,
 				error_code, 1);
+		preempt_conditional_cli(regs);
 		return;
 	}
 

arch/x86/kernel/vm86_32.c

@@ -551,8 +551,14 @@ static void do_int(struct kernel_vm86_regs *regs, int i,
 int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 {
 	if (VMPI.is_vm86pus) {
-		if ((trapno == 3) || (trapno == 1))
-			return_to_32bit(regs, VM86_TRAP + (trapno << 8));
+		if ((trapno == 3) || (trapno == 1)) {
+			KVM86->regs32->ax = VM86_TRAP + (trapno << 8);
+			/* setting this flag forces the code in entry_32.S to
+			   call save_v86_state() and change the stack pointer
+			   to KVM86->regs32 */
+			set_thread_flag(TIF_IRET);
+			return 0;
+		}
 		do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs));
 		return 0;
 	}

include/linux/interrupt.h

@@ -416,7 +416,6 @@ static inline void __raise_softirq_irqoff(unsigned int nr)
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
-extern void wakeup_softirqd(void);
 
 /* This is the worklist that queues up per-cpu softirq work.
  *

kernel/softirq.c

@@ -67,7 +67,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
  * to the pending events, so lets the scheduler to balance
  * the softirq load for us.
  */
-void wakeup_softirqd(void)
+static void wakeup_softirqd(void)
 {
 	/* Interrupts are disabled: no need to stop preemption */
 	struct task_struct *tsk = __get_cpu_var(ksoftirqd);