On Wed, Sep 21, 2022, Vitaly Kuznetsov wrote:
> Get rid of on-stack allocation of vcpu_mask and optimize kvm_hv_send_ipi()
> for a smaller number of vCPUs in the request. When Hyper-V TLB flush
> is in use, HvSendSyntheticClusterIpi{,Ex} calls are not commonly used to
> send IPIs to a large number of vCPUs (and are rarely used in general).
>
> Introduce hv_is_vp_in_sparse_set() to directly check if the specified
> VP_ID is present in sparse vCPU set.
>
> Reviewed-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
> Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
> ---
> arch/x86/kvm/hyperv.c | 37 ++++++++++++++++++++++++++-----------
> 1 file changed, 26 insertions(+), 11 deletions(-)
>
> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
> index 69891c48c12a..9764ebb7fd5f 100644
> --- a/arch/x86/kvm/hyperv.c
> +++ b/arch/x86/kvm/hyperv.c
> @@ -1741,6 +1741,25 @@ static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks,
> }
> }
>
> +static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[])
> +{
> + int bank, sbank = 0;
> +
> + if (!test_bit(vp_id / HV_VCPUS_PER_SPARSE_BANK,
> + (unsigned long *)&valid_bank_mask))
> + return false;
> +
> + for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
> + KVM_HV_MAX_SPARSE_VCPU_SET_BITS) {
> + if (bank == vp_id / HV_VCPUS_PER_SPARSE_BANK)
> + break;
> + sbank++;
At the risk of being too clever, this can be heavily optimized, which given what
this helper is used for is probably worth doing. The index into sparse_banks is
the number of bits preceding the target bit, and POPCNT can determine the number
of bits. So, to get the index, simply strip off the upper bits and do hweight64().
And to avoid bugs while also optimizing for "small" VMs, the math can be skipped
if vp_id < 64, i.e. if bank==0, because in that case there can't possibly be
preceding bits.
Compile tested only...
int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
unsigned long sbank;
if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
return false;
/*
* The index into the sparse bank is the number of preceding bits in
* the valid mask. Optimize for VMs with <64 vCPUs by skipping the
* fancy math if there can't possibly be preceding bits.
*/
if (valid_bit_nr)
sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0));
else
sbank = 0;
return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK,
(unsigned long *)&sparse_banks[sbank]);
yields this, where the "call __sw_hweight64" will be patched to POPCNT on 64-bit
hosts (POPCNT has been around for a long time).
call 0xffffffff810c3ea0 <__fentry__>
push %rbp
mov %edi,%eax
mov %rsp,%rbp
shr $0x6,%eax
sub $0x8,%rsp
mov %rsi,-0x8(%rbp)
mov %eax,%ecx
bt %rcx,-0x8(%rbp)
setb %cl
jae 0xffffffff81064784 <hv_is_vp_in_sparse_set+52>
test %eax,%eax
mov %edi,%r8d
jne 0xffffffff8106478c <hv_is_vp_in_sparse_set+60>
and $0x3f,%r8d
bt %r8,(%rdx)
setb %cl
leave
mov %ecx,%eax
jmp 0xffffffff81c02200 <__x86_return_thunk>
mov $0x40,%ecx
mov $0xffffffffffffffff,%rdi
sub %eax,%ecx
shr %cl,%rdi
and -0x8(%rbp),%rdi
call 0xffffffff815beea0 <__sw_hweight64>
lea (%rdx,%rax,8),%rdx
jmp 0xffffffff81064779 <hv_is_vp_in_sparse_set+41>
Alternatively, we could choose not to optimize bit==0 and just do:
sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr, 0)) - 1;
but there's enough prep work needed for hweight64() that I think it's worth
opimtizing because "small" VMs are probably very common.
