Merge commit 'v2.6.27-rc1' into x86/core

Conflicts:

	include/asm-x86/dma-mapping.h
	include/asm-x86/namei.h
	include/asm-x86/uaccess.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

32 files changed, 962 insertions, 480 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 54f69837d35..4e1d7df7c3e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FTRACE) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 66ec9fd21e0..657f8f8d93a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -45,6 +45,7 @@
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
+#include <linux/namei.h>
 
 #include <asm/atomic.h>
 
@@ -1529,7 +1530,7 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
 	return cft->read_seq_string(state->cgroup, cft, m);
 }
 
-int cgroup_seqfile_release(struct inode *inode, struct file *file)
+static int cgroup_seqfile_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *seq = file->private_data;
 	kfree(seq->private);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 10ba5f1004a..e202a68d1cc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -216,7 +216,6 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
-	struct task_struct *p;
 	cpumask_t old_allowed, tmp;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
@@ -249,21 +248,18 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	cpus_setall(tmp);
 	cpu_clear(cpu, tmp);
 	set_cpus_allowed_ptr(current, &tmp);
+	tmp = cpumask_of_cpu(cpu);
 
-	p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
-
-	if (IS_ERR(p) || cpu_online(cpu)) {
+	err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 
-		if (IS_ERR(p)) {
-			err = PTR_ERR(p);
-			goto out_allowed;
-		}
-		goto out_thread;
+		goto out_allowed;
 	}
+	BUG_ON(cpu_online(cpu));
 
 	/* Wait for it to sleep (leaving idle task). */
 	while (!idle_cpu(cpu))
@@ -279,8 +275,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	check_for_tasks(cpu);
 
-out_thread:
-	err = kthread_stop(p);
 out_allowed:
 	set_cpus_allowed_ptr(current, &old_allowed);
 out_release:
@@ -461,3 +455,28 @@ out:
 #endif /* CONFIG_PM_SLEEP_SMP */
 
 #endif /* CONFIG_SMP */
+
+/*
+ * cpu_bit_bitmap[] is a special, "compressed" data structure that
+ * represents all NR_CPUS bits binary values of 1<<nr.
+ *
+ * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * mask value that has a single bit set only.
+ */
+
+/* cpu_bit_bitmap[0] is empty - so we can back into it */
+#define MASK_DECLARE_1(x)	[x+1][0] = 1UL << (x)
+#define MASK_DECLARE_2(x)	MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
+#define MASK_DECLARE_4(x)	MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
+#define MASK_DECLARE_8(x)	MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
+
+const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
+
+	MASK_DECLARE_8(0),	MASK_DECLARE_8(8),
+	MASK_DECLARE_8(16),	MASK_DECLARE_8(24),
+#if BITS_PER_LONG > 32
+	MASK_DECLARE_8(32),	MASK_DECLARE_8(40),
+	MASK_DECLARE_8(48),	MASK_DECLARE_8(56),
+#endif
+};
+EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
new file mode 100644
index 00000000000..7517115a8cc
--- /dev/null
+++ b/kernel/dma-coherent.c
@@ -0,0 +1,154 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+	void		*virt_base;
+	u32		device_base;
+	int		size;
+	int		flags;
+	unsigned long	*bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+				dma_addr_t device_addr, size_t size, int flags)
+{
+	void __iomem *mem_base = NULL;
+	int pages = size >> PAGE_SHIFT;
+	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+		goto out;
+	if (!size)
+		goto out;
+	if (dev->dma_mem)
+		goto out;
+
+	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+	mem_base = ioremap(bus_addr, size);
+	if (!mem_base)
+		goto out;
+
+	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+	if (!dev->dma_mem)
+		goto out;
+	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dev->dma_mem->bitmap)
+		goto free1_out;
+
+	dev->dma_mem->virt_base = mem_base;
+	dev->dma_mem->device_base = device_addr;
+	dev->dma_mem->size = pages;
+	dev->dma_mem->flags = flags;
+
+	if (flags & DMA_MEMORY_MAP)
+		return DMA_MEMORY_MAP;
+
+	return DMA_MEMORY_IO;
+
+ free1_out:
+	kfree(dev->dma_mem);
+ out:
+	if (mem_base)
+		iounmap(mem_base);
+	return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+
+	if (!mem)
+		return;
+	dev->dma_mem = NULL;
+	iounmap(mem->virt_base);
+	kfree(mem->bitmap);
+	kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+	int pos, err;
+	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1);
+
+	pages >>= PAGE_SHIFT;
+
+	if (!mem)
+		return ERR_PTR(-EINVAL);
+
+	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+	err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
+	if (err != 0)
+		return ERR_PTR(err);
+	return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * Try to allocate memory from the per-device coherent area.
+ *
+ * @dev:	device from which we allocate memory
+ * @size:	size of requested memory area
+ * @dma_handle:	This will be filled with the correct dma handle
+ * @ret:	This pointer will be filled with the virtual address
+ * 		to allocated area.
+ *
+ * This function should be only called from per-arch %dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return %ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	int order = get_order(size);
+
+	if (mem) {
+		int page = bitmap_find_free_region(mem->bitmap, mem->size,
+						     order);
+		if (page >= 0) {
+			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
+			*ret = mem->virt_base + (page << PAGE_SHIFT);
+			memset(*ret, 0, size);
+		} else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+			*ret = NULL;
+	}
+	return (mem != NULL);
+}
+
+/**
+ * Try to free the memory allocated from per-device coherent memory pool.
+ * @dev:	device from which the memory was allocated
+ * @order:	the order of pages allocated
+ * @vaddr:	virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * %dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+	if (mem && vaddr >= mem->virt_base && vaddr <
+		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+		bitmap_release_region(mem->bitmap, page, order);
+		return 1;
+	}
+	return 0;
+}
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index c1ef192aa65..0d407e88673 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -168,7 +168,6 @@ __set_personality(u_long personality)
 	current->personality = personality;
 	oep = current_thread_info()->exec_domain;
 	current_thread_info()->exec_domain = ep;
-	set_fs_altroot();
 
 	module_put(oep->module);
 	return 0;
diff --git a/kernel/exit.c b/kernel/exit.c
index ad933bb29ec..eb4d6470d1d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,7 @@
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/tracehook.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -120,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->nivcsw += tsk->nivcsw;
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
-#ifdef CONFIG_TASK_XACCT
-		sig->rchar += tsk->rchar;
-		sig->wchar += tsk->wchar;
-		sig->syscr += tsk->syscr;
-		sig->syscw += tsk->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-		sig->ioac.read_bytes += tsk->ioac.read_bytes;
-		sig->ioac.write_bytes += tsk->ioac.write_bytes;
-		sig->ioac.cancelled_write_bytes +=
-					tsk->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+		task_io_accounting_add(&sig->ioac, &tsk->ioac);
 		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
@@ -162,27 +152,17 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 	put_task_struct(container_of(rhp, struct task_struct, rcu));
 }
 
-/*
- * Do final ptrace-related cleanup of a zombie being reaped.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_release_task(struct task_struct *p)
-{
-	BUG_ON(!list_empty(&p->ptraced));
-	ptrace_unlink(p);
-	BUG_ON(!list_empty(&p->ptrace_entry));
-}
 
 void release_task(struct task_struct * p)
 {
 	struct task_struct *leader;
 	int zap_leader;
 repeat:
+	tracehook_prepare_release_task(p);
 	atomic_dec(&p->user->processes);
 	proc_flush_task(p);
 	write_lock_irq(&tasklist_lock);
-	ptrace_release_task(p);
+	tracehook_finish_release_task(p);
 	__exit_signal(p);
 
 	/*
@@ -204,6 +184,13 @@ repeat:
 		 * that case.
 		 */
 		zap_leader = task_detached(leader);
+
+		/*
+		 * This maintains the invariant that release_task()
+		 * only runs on a task in EXIT_DEAD, just for sanity.
+		 */
+		if (zap_leader)
+			leader->exit_state = EXIT_DEAD;
 	}
 
 	write_unlock_irq(&tasklist_lock);
@@ -567,8 +554,6 @@ void put_fs_struct(struct fs_struct *fs)
 	if (atomic_dec_and_test(&fs->count)) {
 		path_put(&fs->root);
 		path_put(&fs->pwd);
-		if (fs->altroot.dentry)
-			path_put(&fs->altroot);
 		kmem_cache_free(fs_cachep, fs);
 	}
 }
@@ -887,7 +872,8 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-	int state;
+	int signal;
+	void *cookie;
 
 	/*
 	 * This does two things:
@@ -924,22 +910,11 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	    !capable(CAP_KILL))
 		tsk->exit_signal = SIGCHLD;
 
-	/* If something other than our normal parent is ptracing us, then
-	 * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
-	 * only has special meaning to our real parent.
-	 */
-	if (!task_detached(tsk) && thread_group_empty(tsk)) {
-		int signal = ptrace_reparented(tsk) ?
-				SIGCHLD : tsk->exit_signal;
-		do_notify_parent(tsk, signal);
-	} else if (tsk->ptrace) {
-		do_notify_parent(tsk, SIGCHLD);
-	}
+	signal = tracehook_notify_death(tsk, &cookie, group_dead);
+	if (signal > 0)
+		signal = do_notify_parent(tsk, signal);
 
-	state = EXIT_ZOMBIE;
-	if (task_detached(tsk) && likely(!tsk->ptrace))
-		state = EXIT_DEAD;
-	tsk->exit_state = state;
+	tsk->exit_state = signal < 0 ? EXIT_DEAD : EXIT_ZOMBIE;
 
 	/* mt-exec, de_thread() is waiting for us */
 	if (thread_group_leader(tsk) &&
@@ -949,8 +924,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 
 	write_unlock_irq(&tasklist_lock);
 
+	tracehook_report_death(tsk, signal, cookie, group_dead);
+
 	/* If the process is dead, release it - nobody will wait for it */
-	if (state == EXIT_DEAD)
+	if (signal < 0)
 		release_task(tsk);
 }
 
@@ -1029,10 +1006,7 @@ NORET_TYPE void do_exit(long code)
 	if (unlikely(!tsk->pid))
 		panic("Attempted to kill the idle task!");
 
-	if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
-		current->ptrace_message = code;
-		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
-	}
+	tracehook_report_exit(&code);
 
 	/*
 	 * We're taking recursive faults here in do_exit. Safest is to just
@@ -1378,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		psig->coublock +=
 			task_io_get_oublock(p) +
 			sig->oublock + sig->coublock;
-#ifdef CONFIG_TASK_XACCT
-		psig->rchar += p->rchar + sig->rchar;
-		psig->wchar += p->wchar + sig->wchar;
-		psig->syscr += p->syscr + sig->syscr;
-		psig->syscw += p->syscw + sig->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-		psig->ioac.read_bytes +=
-			p->ioac.read_bytes + sig->ioac.read_bytes;
-		psig->ioac.write_bytes +=
-			p->ioac.write_bytes + sig->ioac.write_bytes;
-		psig->ioac.cancelled_write_bytes +=
-				p->ioac.cancelled_write_bytes +
-				sig->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+		task_io_accounting_add(&psig->ioac, &p->ioac);
+		task_io_accounting_add(&psig->ioac, &sig->ioac);
 		spin_unlock_irq(&p->parent->sighand->siglock);
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index b99d73e971a..7ce2ebe8479 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -27,6 +27,7 @@
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
+#include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
@@ -37,6 +38,7 @@
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
@@ -413,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
+		mmu_notifier_mm_init(mm);
 		return mm;
 	}
 
@@ -445,6 +448,7 @@ void __mmdrop(struct mm_struct *mm)
 	BUG_ON(mm == &init_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
+	mmu_notifier_mm_destroy(mm);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -656,13 +660,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
 		path_get(&old->root);
 		fs->pwd = old->pwd;
 		path_get(&old->pwd);
-		if (old->altroot.dentry) {
-			fs->altroot = old->altroot;
-			path_get(&old->altroot);
-		} else {
-			fs->altroot.mnt = NULL;
-			fs->altroot.dentry = NULL;
-		}
 		read_unlock(&old->lock);
 	}
 	return fs;
@@ -812,12 +809,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
-#ifdef CONFIG_TASK_XACCT
-	sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0;
-#endif
-#ifdef CONFIG_TASK_IO_ACCOUNTING
-	memset(&sig->ioac, 0, sizeof(sig->ioac));
-#endif
+	task_io_accounting_init(&sig->ioac);
 	sig->sum_sched_runtime = 0;
 	INIT_LIST_HEAD(&sig->cpu_timers[0]);
 	INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -865,8 +857,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
 	new_flags &= ~PF_SUPERPRIV;
 	new_flags |= PF_FORKNOEXEC;
-	if (!(clone_flags & CLONE_PTRACE))
-		p->ptrace = 0;
+	new_flags |= PF_STARTING;
 	p->flags = new_flags;
 	clear_freeze_flag(p);
 }
@@ -907,7 +898,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					struct pt_regs *regs,
 					unsigned long stack_size,
 					int __user *child_tidptr,
-					struct pid *pid)
+					struct pid *pid,
+					int trace)
 {
 	int retval;
 	struct task_struct *p;
@@ -1000,13 +992,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->last_switch_timestamp = 0;
 #endif
 
-#ifdef CONFIG_TASK_XACCT
-	p->rchar = 0;		/* I/O counter: bytes read */
-	p->wchar = 0;		/* I/O counter: bytes written */
-	p->syscr = 0;		/* I/O counter: read syscalls */
-	p->syscw = 0;		/* I/O counter: write syscalls */
-#endif
-	task_io_accounting_init(p);
+	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 
 	p->it_virt_expires = cputime_zero;
@@ -1163,8 +1149,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 */
 	p->group_leader = p;
 	INIT_LIST_HEAD(&p->thread_group);
-	INIT_LIST_HEAD(&p->ptrace_entry);
-	INIT_LIST_HEAD(&p->ptraced);
 
 	/* Now that the task is set up, run cgroup callbacks if
 	 * necessary. We need to run them before the task is visible
@@ -1195,7 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->real_parent = current->real_parent;
 	else
 		p->real_parent = current;
-	p->parent = p->real_parent;
 
 	spin_lock(&current->sighand->siglock);
 
@@ -1237,8 +1220,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (likely(p->pid)) {
 		list_add_tail(&p->sibling, &p->real_parent->children);
-		if (unlikely(p->ptrace & PT_PTRACED))
-			__ptrace_link(p, current->parent);
+		tracehook_finish_clone(p, clone_flags, trace);
 
 		if (thread_group_leader(p)) {
 			if (clone_flags & CLONE_NEWPID)
@@ -1323,29 +1305,13 @@ struct task_struct * __cpuinit fork_idle(int cpu)
 	struct pt_regs regs;
 
 	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-				&init_struct_pid);
+			    &init_struct_pid, 0);
 	if (!IS_ERR(task))
 		init_idle(task, cpu);
 
 	return task;
 }
 
-static int fork_traceflag(unsigned clone_flags)
-{
-	if (clone_flags & CLONE_UNTRACED)
-		return 0;
-	else if (clone_flags & CLONE_VFORK) {
-		if (current->ptrace & PT_TRACE_VFORK)
-			return PTRACE_EVENT_VFORK;
-	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-		if (current->ptrace & PT_TRACE_CLONE)
-			return PTRACE_EVENT_CLONE;
-	} else if (current->ptrace & PT_TRACE_FORK)
-		return PTRACE_EVENT_FORK;
-
-	return 0;
-}
-
 /*
  *  Ok, this is the main fork-routine.
  *
@@ -1380,14 +1346,14 @@ long do_fork(unsigned long clone_flags,
 		}
 	}
 
-	if (unlikely(current->ptrace)) {
-		trace = fork_traceflag (clone_flags);
-		if (trace)
-			clone_flags |= CLONE_PTRACE;
-	}
+	/*
+	 * When called from kernel_thread, don't do user tracing stuff.
+	 */
+	if (likely(user_mode(regs)))
+		trace = tracehook_prepare_clone(clone_flags);
 
 	p = copy_process(clone_flags, stack_start, regs, stack_size,
-			child_tidptr, NULL);
+			 child_tidptr, NULL, trace);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
@@ -1405,32 +1371,35 @@ long do_fork(unsigned long clone_flags,
 			init_completion(&vfork);
 		}
 
-		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
+		tracehook_report_clone(trace, regs, clone_flags, nr, p);
+
+		/*
+		 * We set PF_STARTING at creation in case tracing wants to
+		 * use this to distinguish a fully live task from one that
+		 * hasn't gotten to tracehook_report_clone() yet.  Now we
+		 * clear it and set the child going.
+		 */
+		p->flags &= ~PF_STARTING;
+
+		if (unlikely(clone_flags & CLONE_STOPPED)) {
 			/*
 			 * We'll start up with an immediate SIGSTOP.
 			 */
 			sigaddset(&p->pending.signal, SIGSTOP);
 			set_tsk_thread_flag(p, TIF_SIGPENDING);
-		}
-
-		if (!(clone_flags & CLONE_STOPPED))
-			wake_up_new_task(p, clone_flags);
-		else
 			__set_task_state(p, TASK_STOPPED);
-
-		if (unlikely (trace)) {
-			current->ptrace_message = nr;
-			ptrace_notify ((trace << 8) | SIGTRAP);
+		} else {
+			wake_up_new_task(p, clone_flags);
 		}
 
+		tracehook_report_clone_complete(trace, regs,
+						clone_flags, nr, p);
+
 		if (clone_flags & CLONE_VFORK) {
 			freezer_do_not_count();
 			wait_for_completion(&vfork);
 			freezer_count();
-			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
-				current->ptrace_message = nr;
-				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
-			}
+			tracehook_report_vfork_done(p, nr);
 		}
 	} else {
 		nr = PTR_ERR(p);
@@ -1442,7 +1411,7 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(struct kmem_cache *cachep, void *data)
+static void sighand_ctor(void *data)
 {
 	struct sighand_struct *sighand = data;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 964964baefa..3cd441ebf5d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -28,8 +28,7 @@ void dynamic_irq_init(unsigned int irq)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
 	}
 
@@ -62,8 +61,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
 	}
 
@@ -71,9 +69,8 @@ void dynamic_irq_cleanup(unsigned int irq)
 	spin_lock_irqsave(&desc->lock, flags);
 	if (desc->action) {
 		spin_unlock_irqrestore(&desc->lock, flags);
-		printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n",
+		WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
 			irq);
-		WARN_ON(1);
 		return;
 	}
 	desc->msi_desc = NULL;
@@ -96,8 +93,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS) {
-		printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
 	}
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7d73e008fc3..22d10d3189f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -184,8 +184,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
 {
 	switch (desc->depth) {
 	case 0:
-		printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
-		WARN_ON(1);
+		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
 		unsigned int status = desc->status & ~IRQ_DISABLED;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 1c5fcacbcf3..c8a4370e2a3 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -24,6 +24,12 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -242,6 +248,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
 		goto out;
 	}
 
+	image->swap_page = kimage_alloc_control_pages(image, 0);
+	if (!image->swap_page) {
+		printk(KERN_ERR "Could not allocate swap buffer\n");
+		goto out;
+	}
+
 	result = 0;
  out:
 	if (result == 0)
@@ -589,14 +601,12 @@ static void kimage_free_extra_pages(struct kimage *image)
 	kimage_free_page_list(&image->unuseable_pages);
 
 }
-static int kimage_terminate(struct kimage *image)
+static void kimage_terminate(struct kimage *image)
 {
 	if (*image->entry != 0)
 		image->entry++;
 
 	*image->entry = IND_DONE;
-
-	return 0;
 }
 
 #define for_each_kimage_entry(image, ptr, entry) \
@@ -988,6 +998,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 		if (result)
 			goto out;
 
+		if (flags & KEXEC_PRESERVE_CONTEXT)
+			image->preserve_context = 1;
 		result = machine_kexec_prepare(image);
 		if (result)
 			goto out;
@@ -997,9 +1009,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 			if (result)
 				goto out;
 		}
-		result = kimage_terminate(image);
-		if (result)
-			goto out;
+		kimage_terminate(image);
 	}
 	/* Install the new kernel, and  Uninstall the old */
 	image = xchg(dest_image, image);
@@ -1415,3 +1425,85 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/**
+ *	kernel_kexec - reboot the system
+ *
+ *	Move into place and start executing a preloaded standalone
+ *	executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+	int error = 0;
+
+	if (xchg(&kexec_lock, 1))
+		return -EBUSY;
+	if (!kexec_image) {
+		error = -EINVAL;
+		goto Unlock;
+	}
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		mutex_lock(&pm_mutex);
+		pm_prepare_console();
+		error = freeze_processes();
+		if (error) {
+			error = -EBUSY;
+			goto Restore_console;
+		}
+		suspend_console();
+		error = device_suspend(PMSG_FREEZE);