Merge branch 'percpu-cpumask-x86-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'percpu-cpumask-x86-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (682 commits)
  percpu: fix spurious alignment WARN in legacy SMP percpu allocator
  percpu: generalize embedding first chunk setup helper
  percpu: more flexibility for @dyn_size of pcpu_setup_first_chunk()
  percpu: make x86 addr <-> pcpu ptr conversion macros generic
  linker script: define __per_cpu_load on all SMP capable archs
  x86: UV: remove uv_flush_tlb_others() WARN_ON
  percpu: finer grained locking to break deadlock and allow atomic free
  percpu: move fully free chunk reclamation into a work
  percpu: move chunk area map extension out of area allocation
  percpu: replace pcpu_realloc() with pcpu_mem_alloc() and pcpu_mem_free()
  x86, percpu: setup reserved percpu area for x86_64
  percpu, module: implement reserved allocation and use it for module percpu variables
  percpu: add an indirection ptr for chunk page map access
  x86: make embedding percpu allocator return excessive free space
  percpu: use negative for auto for pcpu_setup_first_chunk() arguments
  percpu: improve first chunk initial area map handling
  percpu: cosmetic renames in pcpu_setup_first_chunk()
  percpu: clean up percpu constants
  x86: un-__init fill_pud/pmd/pte
  x86: remove vestigial fix_ioremap prototypes
  ...

Manually merge conflicts in arch/ia64/kernel/irq_ia64.c

1 files changed, 191 insertions, 2 deletions

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d12f7e37f8..6afa5232dbb 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1,8 +1,8 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <asm/idle.h>
 #include <linux/smp.h>
+#include <linux/prctl.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/module.h>
@@ -11,6 +11,9 @@
 #include <linux/ftrace.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/idle.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -56,6 +59,192 @@ void arch_task_cache_init(void)
 }
 
 /*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+	struct task_struct *me = current;
+	struct thread_struct *t = &me->thread;
+
+	if (me->thread.io_bitmap_ptr) {
+		struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
+
+		kfree(t->io_bitmap_ptr);
+		t->io_bitmap_ptr = NULL;
+		clear_thread_flag(TIF_IO_BITMAP);
+		/*
+		 * Careful, clear this in the TSS too:
+		 */
+		memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
+		t->io_bitmap_max = 0;
+		put_cpu();
+	}
+
+	ds_exit_thread(current);
+}
+
+void flush_thread(void)
+{
+	struct task_struct *tsk = current;
+
+#ifdef CONFIG_X86_64
+	if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
+		clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
+		if (test_tsk_thread_flag(tsk, TIF_IA32)) {
+			clear_tsk_thread_flag(tsk, TIF_IA32);
+		} else {
+			set_tsk_thread_flag(tsk, TIF_IA32);
+			current_thread_info()->status |= TS_COMPAT;
+		}
+	}
+#endif
+
+	clear_tsk_thread_flag(tsk, TIF_DEBUG);
+
+	tsk->thread.debugreg0 = 0;
+	tsk->thread.debugreg1 = 0;
+	tsk->thread.debugreg2 = 0;
+	tsk->thread.debugreg3 = 0;
+	tsk->thread.debugreg6 = 0;
+	tsk->thread.debugreg7 = 0;
+	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
+	/*
+	 * Forget coprocessor state..
+	 */
+	tsk->fpu_counter = 0;
+	clear_fpu(tsk);
+	clear_used_math();
+}
+
+static void hard_disable_TSC(void)
+{
+	write_cr4(read_cr4() | X86_CR4_TSD);
+}
+
+void disable_TSC(void)
+{
+	preempt_disable();
+	if (!test_and_set_thread_flag(TIF_NOTSC))
+		/*
+		 * Must flip the CPU state synchronously with
+		 * TIF_NOTSC in the current running context.
+		 */
+		hard_disable_TSC();
+	preempt_enable();
+}
+
+static void hard_enable_TSC(void)
+{
+	write_cr4(read_cr4() & ~X86_CR4_TSD);
+}
+
+static void enable_TSC(void)
+{
+	preempt_disable();
+	if (test_and_clear_thread_flag(TIF_NOTSC))
+		/*
+		 * Must flip the CPU state synchronously with
+		 * TIF_NOTSC in the current running context.
+		 */
+		hard_enable_TSC();
+	preempt_enable();
+}
+
+int get_tsc_mode(unsigned long adr)
+{
+	unsigned int val;
+
+	if (test_thread_flag(TIF_NOTSC))
+		val = PR_TSC_SIGSEGV;
+	else
+		val = PR_TSC_ENABLE;
+
+	return put_user(val, (unsigned int __user *)adr);
+}
+
+int set_tsc_mode(unsigned int val)
+{
+	if (val == PR_TSC_SIGSEGV)
+		disable_TSC();
+	else if (val == PR_TSC_ENABLE)
+		enable_TSC();
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+		      struct tss_struct *tss)
+{
+	struct thread_struct *prev, *next;
+
+	prev = &prev_p->thread;
+	next = &next_p->thread;
+
+	if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) ||
+	    test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR))
+		ds_switch_to(prev_p, next_p);
+	else if (next->debugctlmsr != prev->debugctlmsr)
+		update_debugctlmsr(next->debugctlmsr);
+
+	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
+		set_debugreg(next->debugreg0, 0);
+		set_debugreg(next->debugreg1, 1);
+		set_debugreg(next->debugreg2, 2);
+		set_debugreg(next->debugreg3, 3);
+		/* no 4 and 5 */
+		set_debugreg(next->debugreg6, 6);
+		set_debugreg(next->debugreg7, 7);
+	}
+
+	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
+	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
+		/* prev and next are different */
+		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
+			hard_disable_TSC();
+		else
+			hard_enable_TSC();
+	}
+
+	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
+		/*
+		 * Copy the relevant range of the IO bitmap.
+		 * Normally this is 128 bytes or less:
+		 */
+		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
+		       max(prev->io_bitmap_max, next->io_bitmap_max));
+	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
+		/*
+		 * Clear any possible leftover bits:
+		 */
+		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
+	}
+}
+
+int sys_fork(struct pt_regs *regs)
+{
+	return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+int sys_vfork(struct pt_regs *regs)
+{
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0,
+		       NULL, NULL);
+}
+
+
+/*
  * Idle related variables and functions
  */
 unsigned long boot_option_idle_override = 0;
@@ -350,7 +539,7 @@ static void c1e_idle(void)
 
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 	if (pm_idle == poll_idle && smp_num_siblings > 1) {
 		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
 			" performance may degrade.\n");