On Fri, Sep 03, 2021 at 03:08:04PM +0200, Juergen Gross wrote: > In order to support high vcpu numbers per guest don't use on stack > vcpu bitmasks. As all those currently used bitmasks are not used in > functions subject to recursion it is fairly easy to replace them with > percpu bitmasks. > > Disable preemption while such a bitmask is being used in order to > avoid double usage in case we'd switch cpus. > > Signed-off-by: Juergen Gross <jgross@xxxxxxxx> > --- > V2: > - use local_lock() instead of preempt_disable() (Paolo Bonzini) > --- > arch/x86/include/asm/kvm_host.h | 10 ++++++++++ > arch/x86/kvm/hyperv.c | 25 ++++++++++++++++++------- > arch/x86/kvm/irq_comm.c | 9 +++++++-- > arch/x86/kvm/x86.c | 22 +++++++++++++++++++++- > 4 files changed, 56 insertions(+), 10 deletions(-) > > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index 3513edee8e22..a809a9e4fa5c 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -15,6 +15,7 @@ > #include <linux/cpumask.h> > #include <linux/irq_work.h> > #include <linux/irq.h> > +#include <linux/local_lock.h> > > #include <linux/kvm.h> > #include <linux/kvm_para.h> > @@ -1591,6 +1592,15 @@ extern bool kvm_has_bus_lock_exit; > /* maximum vcpu-id */ > unsigned int kvm_max_vcpu_id(void); > > +/* per cpu vcpu bitmasks, protected by kvm_pcpu_mask_lock */ > +DECLARE_PER_CPU(local_lock_t, kvm_pcpu_mask_lock); > +extern unsigned long __percpu *kvm_pcpu_vcpu_mask; > +#define KVM_VCPU_MASK_SZ \ > + (sizeof(*kvm_pcpu_vcpu_mask) * BITS_TO_LONGS(KVM_MAX_VCPUS)) > +extern u64 __percpu *kvm_hv_vp_bitmap; > +#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) > +#define KVM_HV_VPMAP_SZ (sizeof(u64) * KVM_HV_MAX_SPARSE_VCPU_SET_BITS) I have just realized that the Hyper-V sparse bitmap format can support only up to 4096 CPUs, and the current implementation of sparse_set_to_vcpu_mask() won't even work correctly if KVM_MAX_VCPUS is larger than 4096. This means vp_bitmap can't and will never be larger than 512 bytes. Isn't a per-CPU variable for vp_bitmap overkill in this case? > [...] -- Eduardo
