Make sure we have all the dirty registers in user frames on the

backing store before we discard them. It is possible that we
enter the kernel (due to an execve in this case) with a lot of
dirty user registers and that the RSE has only partially spilled
them (to make room for new frames). We cannot move the backing
store pointer down (to discard user registers) when not all of
the user registers are on the backing store.
So, we flush the register stack IFF this happens. Unconditionally
doing the flush is too costly, because the condition in which we
need to flush is very rare.

This change appears to fix the SIGSEGV that sometimes happen for
newly executed processes and so far also appears to fix the last
of the corruption. It is possible, although not likely, that this
change prevents some other bug from happening, even though it is
itself not a fix. Hence the uncertainty. We'll know in a couple
of months I guess :-)

1 files changed, 12 insertions, 2 deletions

diff --git a/sys/ia64/ia64/machdep.c b/sys/ia64/ia64/machdep.c
index cc6f407..9ff50d4 100644
--- a/sys/ia64/ia64/machdep.c
+++ b/sys/ia64/ia64/machdep.c
@@ -1074,8 +1074,18 @@ exec_setregs(struct thread *td, u_long entry, u_long stack, u_long ps_strings)
 	if (ndirty > 0) {
 		__asm __volatile("mov	ar.rsc=0;;");
 		__asm __volatile("mov	%0=ar.bspstore" : "=r"(bspst));
-		rssz = bspst - kstack - ndirty;
-		bcopy((void*)(kstack + ndirty), (void*)kstack, rssz);
+		/*
+		 * Make sure we have all the user registers written out.
+		 * We're doing culculations with ndirty and ar.bspstore
+		 * and we better make sure ar.bspstore >= ndirty.
+		 */
+		rssz = bspst - kstack;
+		if (rssz < ndirty) {
+			__asm __volatile("flushrs;;");
+			__asm __volatile("mov   %0=ar.bspstore" : "=r"(bspst));
+			rssz = bspst - kstack;
+		}
+		bcopy((void*)(kstack + ndirty), (void*)kstack, rssz - ndirty);
 		bspst -= ndirty;
 		__asm __volatile("mov	ar.bspstore=%0;;" :: "r"(bspst));
 		__asm __volatile("mov	ar.rsc=3");