8dcdb535d7
When emulating certain floating point instructions or vector instructions on PowerPC machines, QEMU did not properly generate the SPE/Embedded Floating- Point Unavailable interrupt. See the buglink further below for references to the relevant NXP documentation. This patch fixes the behavior of some evfs* instructions that were incorrectly emitting the interrupt. More importantly, this patch fixes the behavior of several efd* and ev* instructions that were not generating the interrupt. Triggering the interrupt for these instructions fixes lazy FPU/vector context switching on some operating systems like Linux. Without this patch, the result of some double-precision arithmetic could be corrupted due to the lack of proper saving and restoring of the upper 32-bit part of the general-purpose registers. Buglink: https://bugs.launchpad.net/qemu/+bug/1888918 Buglink: https://bugs.launchpad.net/qemu/+bug/1611394 Signed-off-by: Matthieu Bucchianeri <matthieu.bucchianeri@leostella.com> Message-Id: <20200727175553.32276-1-matthieu.bucchianeri@leostella.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> |
||
|---|---|---|
| .. | ||
| dfp-impl.inc.c | ||
| dfp-ops.inc.c | ||
| fp-impl.inc.c | ||
| fp-ops.inc.c | ||
| spe-impl.inc.c | ||
| spe-ops.inc.c | ||
| vmx-impl.inc.c | ||
| vmx-ops.inc.c | ||
| vsx-impl.inc.c | ||
| vsx-ops.inc.c | ||