8 files changed, 141 insertions, 27 deletions

diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index e36f92b463c..87a4e4427d8 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -97,6 +97,8 @@ SECTIONS
   .data           : {
     . = ALIGN(KERNEL_STACK_SIZE);		/* init_task */
     *(.data.init_task)
+    . = ALIGN(KERNEL_STACK_SIZE);
+    *(.data.init_irqstack)
     *(.data .data.* .gnu.linkonce.d.*)
     SORT(CONSTRUCTORS)
   }
diff --git a/arch/um/kernel/init_task.c b/arch/um/kernel/init_task.c
index cda91aa8e70..d4f1d1ab252 100644
--- a/arch/um/kernel/init_task.c
+++ b/arch/um/kernel/init_task.c
@@ -1,5 +1,5 @@
-/* 
- * Copyright (C) 2000 Jeff Dike (jdike@karaya.com)
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,intel.linux}.com)
  * Licensed under the GPL
  */
 
@@ -33,28 +33,20 @@ EXPORT_SYMBOL(init_task);
 /*
  * Initial thread structure.
  *
- * We need to make sure that this is 16384-byte aligned due to the
+ * We need to make sure that this is aligned due to the
  * way process stacks are handled. This is done by having a special
  * "init_task" linker map entry..
  */
 
-union thread_union init_thread_union 
-__attribute__((__section__(".data.init_task"))) = 
-{ INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union
+	__attribute__((__section__(".data.init_task"))) =
+		{ INIT_THREAD_INFO(init_task) };
+
+union thread_union cpu0_irqstack
+	__attribute__((__section__(".data.init_irqstack"))) =
+		{ INIT_THREAD_INFO(init_task) };
 
 void unprotect_stack(unsigned long stack)
 {
-	os_protect_memory((void *) stack, (1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE,
-		       1, 1, 0);
+	os_protect_memory((void *) stack, THREAD_SIZE, 1, 1, 0);
 }
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 8f2ed369031..dba04d88b43 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -1,4 +1,4 @@
-/* 
+/*
  * Copyright (C) 2000 Jeff Dike (jdike@karaya.com)
  * Licensed under the GPL
  * Derived (i.e. mostly copied) from arch/i386/kernel/irq.c:
@@ -32,6 +32,7 @@
 #include "sigio.h"
 #include "um_malloc.h"
 #include "misc_constants.h"
+#include "as-layout.h"
 
 /*
  * Generic, controller-independent functions:
@@ -53,7 +54,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (i < NR_IRQS) {
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
 		action = irq_desc[i].action;
-		if (!action) 
+		if (!action)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
 #ifndef CONFIG_SMP
@@ -468,3 +469,113 @@ int init_aio_irq(int irq, char *name, irq_handler_t handler)
  out:
 	return err;
 }
+
+/*
+ * IRQ stack entry and exit:
+ *
+ * Unlike i386, UML doesn't receive IRQs on the normal kernel stack
+ * and switch over to the IRQ stack after some preparation.  We use
+ * sigaltstack to receive signals on a separate stack from the start.
+ * These two functions make sure the rest of the kernel won't be too
+ * upset by being on a different stack.  The IRQ stack has a
+ * thread_info structure at the bottom so that current et al continue
+ * to work.
+ *
+ * to_irq_stack copies the current task's thread_info to the IRQ stack
+ * thread_info and sets the tasks's stack to point to the IRQ stack.
+ *
+ * from_irq_stack copies the thread_info struct back (flags may have
+ * been modified) and resets the task's stack pointer.
+ *
+ * Tricky bits -
+ *
+ * What happens when two signals race each other?  UML doesn't block
+ * signals with sigprocmask, SA_DEFER, or sa_mask, so a second signal
+ * could arrive while a previous one is still setting up the
+ * thread_info.
+ *
+ * There are three cases -
+ *     The first interrupt on the stack - sets up the thread_info and
+ * handles the interrupt
+ *     A nested interrupt interrupting the copying of the thread_info -
+ * can't handle the interrupt, as the stack is in an unknown state
+ *     A nested interrupt not interrupting the copying of the
+ * thread_info - doesn't do any setup, just handles the interrupt
+ *
+ * The first job is to figure out whether we interrupted stack setup.
+ * This is done by xchging the signal mask with thread_info->pending.
+ * If the value that comes back is zero, then there is no setup in
+ * progress, and the interrupt can be handled.  If the value is
+ * non-zero, then there is stack setup in progress.  In order to have
+ * the interrupt handled, we leave our signal in the mask, and it will
+ * be handled by the upper handler after it has set up the stack.
+ *
+ * Next is to figure out whether we are the outer handler or a nested
+ * one.  As part of setting up the stack, thread_info->real_thread is
+ * set to non-NULL (and is reset to NULL on exit).  This is the
+ * nesting indicator.  If it is non-NULL, then the stack is already
+ * set up and the handler can run.
+ */
+
+static unsigned long pending_mask;
+
+unsigned long to_irq_stack(int sig, unsigned long *mask_out)
+{
+	struct thread_info *ti;
+	unsigned long mask, old;
+	int nested;
+
+	mask = xchg(&pending_mask, 1 << sig);
+	if(mask != 0){
+		/* If any interrupts come in at this point, we want to
+		 * make sure that their bits aren't lost by our
+		 * putting our bit in.  So, this loop accumulates bits
+		 * until xchg returns the same value that we put in.
+		 * When that happens, there were no new interrupts,
+		 * and pending_mask contains a bit for each interrupt
+		 * that came in.
+		 */
+		old = 1 << sig;
+		do {
+			old |= mask;
+			mask = xchg(&pending_mask, old);
+		} while(mask != old);
+		return 1;
+	}
+
+	ti = current_thread_info();
+	nested = (ti->real_thread != NULL);
+	if(!nested){
+		struct task_struct *task;
+		struct thread_info *tti;
+
+		task = cpu_tasks[ti->cpu].task;
+		tti = task_thread_info(task);
+		*ti = *tti;
+		ti->real_thread = tti;
+		task->stack = ti;
+	}
+
+	mask = xchg(&pending_mask, 0);
+	*mask_out |= mask | nested;
+	return 0;
+}
+
+unsigned long from_irq_stack(int nested)
+{
+	struct thread_info *ti, *to;
+	unsigned long mask;
+
+	ti = current_thread_info();
+
+	pending_mask = 1;
+
+	to = ti->real_thread;
+	current->stack = to;
+	ti->real_thread = NULL;
+	*to = *ti;
+
+	mask = xchg(&pending_mask, 0);
+	return mask & ~1;
+}
+
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index ef36facd8fe..2a69a7ce579 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -163,8 +163,12 @@ static int start_kernel_proc(void *unused)
 
 extern int userspace_pid[];
 
+extern char cpu0_irqstack[];
+
 int start_uml_skas(void)
 {
+	stack_protections((unsigned long) &cpu0_irqstack);
+	set_sigstack(cpu0_irqstack, THREAD_SIZE);
 	if(proc_mm)
 		userspace_pid[0] = start_userspace(0);
 
@@ -178,20 +182,23 @@ int start_uml_skas(void)
 
 int external_pid_skas(struct task_struct *task)
 {
-#warning Need to look up userspace_pid by cpu
+	/* FIXME: Need to look up userspace_pid by cpu */
 	return(userspace_pid[0]);
 }
 
 int thread_pid_skas(struct task_struct *task)
 {
-#warning Need to look up userspace_pid by cpu
+	/* FIXME: Need to look up userspace_pid by cpu */
 	return(userspace_pid[0]);
 }
 
 void kill_off_processes_skas(void)
 {
 	if(proc_mm)
-#warning need to loop over userspace_pids in kill_off_processes_skas
+		/*
+		 * FIXME: need to loop over userspace_pids in
+		 * kill_off_processes_skas
+		 */
 		os_kill_ptraced_process(userspace_pid[0], 1);
 	else {
 		struct task_struct *p;
diff --git a/arch/um/kernel/tt/exec_kern.c b/arch/um/kernel/tt/exec_kern.c
index 98e21743e60..40126cb5180 100644
--- a/arch/um/kernel/tt/exec_kern.c
+++ b/arch/um/kernel/tt/exec_kern.c
@@ -57,7 +57,7 @@ void flush_thread_tt(void)
 	enable_timer();
 	free_page(stack);
 	protect_memory(uml_reserved, high_physmem - uml_reserved, 1, 1, 0, 1);
-	task_protections((unsigned long) current_thread);
+	stack_protections((unsigned long) current_thread);
 	force_flush_all();
 	unblock_signals();
 }
diff --git a/arch/um/kernel/tt/process_kern.c b/arch/um/kernel/tt/process_kern.c
index c631303cb80..74347adf81b 100644
--- a/arch/um/kernel/tt/process_kern.c
+++ b/arch/um/kernel/tt/process_kern.c
@@ -209,7 +209,7 @@ void finish_fork_handler(int sig)
 	if(current->mm != current->parent->mm)
 		protect_memory(uml_reserved, high_physmem - uml_reserved, 1, 
 			       1, 0, 1);
-	task_protections((unsigned long) current_thread);
+	stack_protections((unsigned long) current_thread);
 
 	free_page(current->thread.temp_stack);
 	local_irq_disable();
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 1cf954a47fd..ecc458fe51b 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -459,7 +459,7 @@ int __init linux_main(int argc, char **argv)
 
 	uml_postsetup();
 
-	task_protections((unsigned long) &init_thread_info);
+	stack_protections((unsigned long) &init_thread_info);
 	os_flush_stdout();
 
 	return CHOOSE_MODE(start_uml_tt(), start_uml_skas());
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index f6301274cf3..bc59f97e34d 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -59,6 +59,8 @@ SECTIONS
   {
     . = ALIGN(KERNEL_STACK_SIZE);		/* init_task */
     *(.data.init_task)
+    . = ALIGN(KERNEL_STACK_SIZE);
+    *(.data.init_irqstack)
     *(.data)
     *(.gnu.linkonce.d*)
     CONSTRUCTORS