[PATCH] KVM: ppc64: Enable ring-based dirty memory tracking

[Jordan Niethe]

On 8/6/23 10:34 pm, Kautuk Consul wrote:

Need at least a little context in the commit message itself:

"Enable ring-based dirty memory tracking on ppc64:"

> - Enable CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL as ppc64 is weakly
>    ordered.
> - Enable CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP because the
>    kvmppc_xive_native_set_attr is called in the context of an ioctl
>    syscall and will call kvmppc_xive_native_eq_sync for setting the
>    KVM_DEV_XIVE_EQ_SYNC attribute which will call mark_dirty_page()
>    when there isn't a running vcpu. Implemented the
>    kvm_arch_allow_write_without_running_vcpu to always return true
>    to allow mark_page_dirty_in_slot to mark the page dirty in the
>    memslot->dirty_bitmap in this case.

Should kvm_arch_allow_write_without_running_vcpu() only return true in 
the context of kvmppc_xive_native_eq_sync()?

> - Set KVM_DIRTY_LOG_PAGE_OFFSET for the ring buffer's physical page
>    offset.
> - Implement the kvm_arch_mmu_enable_log_dirty_pt_masked function required
>    for the generic KVM code to call.
> - Add a check to kvmppc_vcpu_run_hv for checking whether the dirty
>    ring is soft full.
> - Implement the kvm_arch_flush_remote_tlbs_memslot function to support
>    the CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT config option.
> 
> On testing with live migration it was found that there is around
> 150-180 ms improvment in overall migration time with this
> 
> Signed-off-by: Kautuk Consul <kconsul at linux.vnet.ibm.com>
> ---
>   Documentation/virt/kvm/api.rst      |  2 +-
>   arch/powerpc/include/uapi/asm/kvm.h |  2 ++
>   arch/powerpc/kvm/Kconfig            |  2 ++
>   arch/powerpc/kvm/book3s_64_mmu_hv.c | 42 +++++++++++++++++++++++++++++
>   arch/powerpc/kvm/book3s_hv.c        |  3 +++
>   include/linux/kvm_dirty_ring.h      |  5 ++++
>   6 files changed, 55 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index add067793b90..ce1ebc513bae 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -8114,7 +8114,7 @@ regardless of what has actually been exposed through the CPUID leaf.
>   8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
>   ----------------------------------------------------------
>   
> -:Architectures: x86, arm64
> +:Architectures: x86, arm64, ppc64
>   :Parameters: args[0] - size of the dirty log ring
>   
>   KVM is capable of tracking dirty memory using ring buffers that are
> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
> index 9f18fa090f1f..f722309ed7fb 100644
> --- a/arch/powerpc/include/uapi/asm/kvm.h
> +++ b/arch/powerpc/include/uapi/asm/kvm.h
> @@ -33,6 +33,8 @@
>   /* Not always available, but if it is, this is the correct offset.  */
>   #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
>   
> +#define KVM_DIRTY_LOG_PAGE_OFFSET 64
> +
>   struct kvm_regs {
>   	__u64 pc;
>   	__u64 cr;
> diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
> index 902611954200..c93354ec3bd5 100644
> --- a/arch/powerpc/kvm/Kconfig
> +++ b/arch/powerpc/kvm/Kconfig
> @@ -26,6 +26,8 @@ config KVM
>   	select IRQ_BYPASS_MANAGER
>   	select HAVE_KVM_IRQ_BYPASS
>   	select INTERVAL_TREE
> +	select HAVE_KVM_DIRTY_RING_ACQ_REL
> +	select NEED_KVM_DIRTY_RING_WITH_BITMAP
>   
>   config KVM_BOOK3S_HANDLER
>   	bool
> diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> index 7f765d5ad436..c92e8022e017 100644
> --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> @@ -2147,3 +2147,45 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
>   
>   	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
>   }
> +
> +/*
> + * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
> + * dirty pages.
> + *
> + * It write protects selected pages to enable dirty logging for them.
> + */
> +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
> +					     struct kvm_memory_slot *slot,
> +					     gfn_t gfn_offset,
> +					     unsigned long mask)
> +{
> +	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
> +	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
> +	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
> +
> +	while (start < end) {
> +		pte_t *ptep;
> +		unsigned int shift;
> +
> +		ptep = find_kvm_secondary_pte(kvm, start, &shift);
> +
> +		*ptep = __pte(pte_val(*ptep) & ~(_PAGE_WRITE));
On rpt I think you'd need to use kvmppc_radix_update_pte()?

> +
> +		start += PAGE_SIZE > +	}
> +}
> +
> +#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
> +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
> +{
> +	return true;
> +}
> +#endif
> +
> +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
> +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
> +					const struct kvm_memory_slot *memslot)
> +{
> +	kvm_flush_remote_tlbs(kvm);
> +}
> +#endif
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 130bafdb1430..1d1264ea72c4 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -4804,6 +4804,9 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
>   		return -EINTR;
>   	}
>   
> +	if (kvm_dirty_ring_check_request(vcpu))
> +		return 0;
> +
>   #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
>   	/*
>   	 * Don't allow entry with a suspended transaction, because
> diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
> index 4862c98d80d3..a00301059da5 100644
> --- a/include/linux/kvm_dirty_ring.h
> +++ b/include/linux/kvm_dirty_ring.h
> @@ -69,6 +69,11 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
>   {
>   }
>   
> +static inline bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu)
> +{
> +	return false;
> +}
> + >   #else /* CONFIG_HAVE_KVM_DIRTY_RING */
>   
>   int kvm_cpu_dirty_log_size(void);
>