On Thu, 2015-04-02 at 17:01 +0100, Ian Campbell wrote:
> On Thu, 2015-04-02 at 16:50 +0100, Ian Campbell wrote:
>
> > Writing to the bottom half (e.g. w0) of a register implicitly clears the
> > top half, IIRC, so I think a kernel is unlikely to want to do this, even
> > if it could (which I'm not quite convinced of).
>
> That said, I'll see if I can make something work with the handle_*
> taking the reg number instead of a pointer and calling select_user_reg
> in each.
Actually don't even need that, I think the following does what is
needed. I'm not 100% convinced it is needed though, but it's simple
enough, and I can't find anything in the ARM ARM right now which rules
out what you are suggesting, even if it is unlikely.
Ian.
diff --git a/xen/arch/arm/traps.c b/xen/arch/arm/traps.c
index 71e349a..61a2106 100644
--- a/xen/arch/arm/traps.c
+++ b/xen/arch/arm/traps.c
@@ -1585,7 +1585,14 @@ static void handle_raz_wi(struct cpu_user_regs *regs,
return inject_undef_exception(regs, hsr);
if ( read )
- *reg = 0;
+ {
+#ifdef CONFIG_ARM_64
+ if ( psr_mode_is_32bit(regs->cpsr) )
+ *reg &= ~0xffffffffUL;
+ else
+#endif
+ *reg = 0;
+ }
/* else: write ignored */
advance_pc(regs, hsr);
@@ -1622,7 +1629,12 @@ static void handle_ro_raz(struct cpu_user_regs *regs,
return inject_undef_exception(regs, hsr);
/* else: raz */
- *reg = 0;
+#ifdef CONFIG_ARM_64
+ if ( psr_mode_is_32bit(regs->cpsr) )
+ *reg &= ~0xffffffffUL;
+ else
+#endif
+ *reg = 0;
advance_pc(regs, hsr);
}
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
