With virt_spin_lock() being a pvops function the bare metal case can be
optimized by patching the call away completely. In case a kernel running
as a guest it can decide whether to use paravitualized spinlocks, the
current fallback to the unfair test-and-set scheme, or to mimic the
bare metal behavior.
Juergen Gross (4):
paravirt: add generic _paravirt_false() function
paravirt: switch vcpu_is_preempted to use _paravirt_false() on bare
metal
paravirt: add virt_spin_lock pvops function
paravirt,xen: correct xen_nopvspin case
arch/x86/include/asm/paravirt.h | 5 ++++
arch/x86/include/asm/paravirt_types.h | 3 +++
arch/x86/include/asm/qspinlock.h | 48 ++++++++++++++++++++++++-----------
arch/x86/kernel/paravirt-spinlocks.c | 22 ++++++++--------
arch/x86/kernel/paravirt.c | 7 +++++
arch/x86/kernel/paravirt_patch_32.c | 18 ++++++-------
arch/x86/kernel/paravirt_patch_64.c | 17 +++++--------
arch/x86/kernel/smpboot.c | 2 ++
arch/x86/xen/spinlock.c | 2 ++
9 files changed, 79 insertions(+), 45 deletions(-)
--
2.12.3
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
