]> git.hungrycats.org Git - linux/commit
x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
authorPaolo Bonzini <pbonzini@redhat.com>
Wed, 26 Nov 2014 20:56:31 +0000 (14:56 -0600)
committerJiri Slaby <jslaby@suse.cz>
Wed, 3 Dec 2014 11:07:27 +0000 (12:07 +0100)
commita05916f8ff7280e8539dac505bc3100212a3a098
treeaca83a2fb909029adee22b2392c3f8b1f5baac61
parent7e3bea443c47e2f499d7547dbabafbaacfa2f8e6
x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only

commit c1118b3602c2329671ad5ec8bdf8e374323d6343 upstream.

On x86_64, kernel text mappings are mapped read-only with CONFIG_DEBUG_RODATA.
In that case, KVM will fail to patch VMCALL instructions to VMMCALL
as required on AMD processors.

The failure mode is currently a divide-by-zero exception, which obviously
is a KVM bug that has to be fixed.  However, picking the right instruction
between VMCALL and VMMCALL will be faster and will help if you cannot upgrade
the hypervisor.

Reported-by: Chris Webb <chris@arachsys.com>
Tested-by: Chris Webb <chris@arachsys.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Chris J Arges <chris.j.arges@canonical.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
arch/x86/include/asm/cpufeature.h
arch/x86/include/asm/kvm_para.h
arch/x86/kernel/cpu/amd.c