Re: [Patch v4 1/6] KVM: Support for guest page hinting

["Michael S. Tsirkin" <mst@redhat.com>]

On Fri, Nov 03, 2017 at 04:30:08PM -0400, nilal@redhat.com wrote:
> From: Nitesh Narayan Lal <nilal@redhat.com>
> 
> This patch includes the following:
> 1. Basic skeleton for the support
> 2. Enablement of x86 platform to use the same
> 
> Signed-off-by: Nitesh Narayan Lal <nilal@redhat.com>
> ---
>  arch/x86/Kbuild         |  2 +-
>  arch/x86/kvm/Makefile   |  2 ++
>  include/linux/gfp.h     |  7 +++++++
>  virt/kvm/Kconfig        |  4 ++++
>  virt/kvm/page_hinting.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
>  5 files changed, 60 insertions(+), 1 deletion(-)
>  create mode 100644 virt/kvm/page_hinting.c
> 
> diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
> index 0038a2d..7d39d7d 100644
> --- a/arch/x86/Kbuild
> +++ b/arch/x86/Kbuild
> @@ -2,7 +2,7 @@ obj-y += entry/
>  
>  obj-$(CONFIG_PERF_EVENTS) += events/
>  
> -obj-$(CONFIG_KVM) += kvm/
> +obj-$(subst m,y,$(CONFIG_KVM)) += kvm/
>  
>  # Xen paravirtualization support
>  obj-$(CONFIG_XEN) += xen/
> diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
> index 09d4b17..d8a3800 100644
> --- a/arch/x86/kvm/Makefile
> +++ b/arch/x86/kvm/Makefile
> @@ -15,6 +15,8 @@ kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
>  			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
>  			   hyperv.o page_track.o debugfs.o
>  
> +obj-$(CONFIG_KVM_FREE_PAGE_HINTING)	+= $(KVM)/page_hinting.o
> +
>  kvm-intel-y		+= vmx.o pmu_intel.o
>  kvm-amd-y		+= svm.o pmu_amd.o
>  
> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> index f780718..a74371f 100644
> --- a/include/linux/gfp.h
> +++ b/include/linux/gfp.h
> @@ -452,6 +452,13 @@ static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
>  	return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
>  }
>  
> +#ifdef	CONFIG_KVM_FREE_PAGE_HINTING
> +#define HAVE_ARCH_ALLOC_PAGE
> +#define HAVE_ARCH_FREE_PAGE
> +void arch_free_page(struct page *page, int order);
> +void arch_alloc_page(struct page *page, int order);
> +#endif
> +
>  #ifndef HAVE_ARCH_FREE_PAGE
>  static inline void arch_free_page(struct page *page, int order) { }
>  #endif


So the idea is to send pages to host in arch_free_page?

However, I notice:

        arch_free_page(page, order);
        kernel_poison_pages(page, 1 << order, 0);

Thus pages are immediately written to after they are freed.





> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index b0cc1a3..936c71d 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -50,3 +50,7 @@ config KVM_COMPAT
>  
>  config HAVE_KVM_IRQ_BYPASS
>         bool
> +
> +config KVM_FREE_PAGE_HINTING
> +       def_bool y
> +       depends on KVM
> diff --git a/virt/kvm/page_hinting.c b/virt/kvm/page_hinting.c
> new file mode 100644
> index 0000000..39d2b1d
> --- /dev/null
> +++ b/virt/kvm/page_hinting.c
> @@ -0,0 +1,46 @@
> +#include <linux/gfp.h>
> +#include <linux/mm.h>
> +#include <linux/page_ref.h>
> +#include <linux/kvm_host.h>
> +#include <linux/sort.h>
> +
> +#include <trace/events/kvm.h>
> +
> +#define MAX_FGPT_ENTRIES	1000
> +#define HYPERLIST_THRESHOLD	500
> +/*
> + * struct kvm_free_pages - Tracks the pages which are freed by the guest.
> + * @pfn	- page frame number for the page which is to be freed
> + * @pages - number of pages which are supposed to be freed.
> + * A global array object is used to hold the list of pfn and number of pages
> + * which are freed by the guest. This list may also have fragmentated pages so
> + * defragmentation is a must prior to the hypercall.
> + */
> +struct kvm_free_pages {
> +	unsigned long pfn;
> +	unsigned int pages;
> +};
> +
> +/*
> + * hypervisor_pages - It is a dummy structure passed with the hypercall.
> + * @pfn - page frame number for the page which is to be freed.
> + * @pages - number of pages which are supposed to be freed.
> + * A global array object is used to to hold the list of pfn and pages and is
> + * passed as part of the hypercall.
> + */
> +struct hypervisor_pages {
> +	unsigned long pfn;
> +	unsigned int pages;
> +};
> +
> +DEFINE_PER_CPU(struct kvm_free_pages [MAX_FGPT_ENTRIES], kvm_pt);
> +DEFINE_PER_CPU(int, kvm_pt_idx);
> +struct hypervisor_pages hypervisor_pagelist[MAX_FGPT_ENTRIES];
> +
> +void arch_alloc_page(struct page *page, int order)
> +{
> +}
> +
> +void arch_free_page(struct page *page, int order)
> +{
> +}
> -- 
> 2.9.4