On 2/5/19 11:27 AM, Michael S. Tsirkin wrote:
> On Tue, Feb 05, 2019 at 08:06:33AM -0500, Nitesh Narayan Lal wrote:
>> On 2/4/19 11:14 PM, Michael S. Tsirkin wrote:
>>> On Mon, Feb 04, 2019 at 03:18:48PM -0500, Nitesh Narayan Lal wrote:
>>>> 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 <nitesh@redhat.com>
>>>> ---
>>>>  arch/x86/Kbuild              |  2 +-
>>>>  arch/x86/kvm/Kconfig         |  8 ++++++++
>>>>  arch/x86/kvm/Makefile        |  2 ++
>>>>  include/linux/gfp.h          |  9 +++++++++
>>>>  include/linux/page_hinting.h | 17 +++++++++++++++++
>>>>  virt/kvm/page_hinting.c      | 36 ++++++++++++++++++++++++++++++++++++
>>>>  6 files changed, 73 insertions(+), 1 deletion(-)
>>>>  create mode 100644 include/linux/page_hinting.h
>>>>  create mode 100644 virt/kvm/page_hinting.c
>>>>
>>>> diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
>>>> index c625f57472f7..3244df4ee311 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-$(CONFIG_XEN) += xen/
>>>> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
>>>> index 72fa955f4a15..2fae31459706 100644
>>>> --- a/arch/x86/kvm/Kconfig
>>>> +++ b/arch/x86/kvm/Kconfig
>>>> @@ -96,6 +96,14 @@ config KVM_MMU_AUDIT
>>>>  	 This option adds a R/W kVM module parameter 'mmu_audit', which allows
>>>>  	 auditing of KVM MMU events at runtime.
>>>>  
>>>> +# KVM_FREE_PAGE_HINTING will allow the guest to report the free pages to the
>>>> +# host in regular interval of time.
>>>> +config KVM_FREE_PAGE_HINTING
>>>> +       def_bool y
>>>> +       depends on KVM
>>>> +       select VIRTIO
>>>> +       select VIRTIO_BALLOON
>>>> +
>>>>  # OK, it's a little counter-intuitive to do this, but it puts it neatly under
>>>>  # the virtualization menu.
>>>>  source "drivers/vhost/Kconfig"
>>>> diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
>>>> index 69b3a7c30013..78640a80501e 100644
>>>> --- a/arch/x86/kvm/Makefile
>>>> +++ b/arch/x86/kvm/Makefile
>>>> @@ -16,6 +16,8 @@ kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
>>>>  			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
>>>>  			   hyperv.o page_track.o debugfs.o
>>>>  
>>>> +obj-$(CONFIG_KVM_FREE_PAGE_HINTING)    += $(KVM)/page_hinting.o
>>>> +
>>>>  kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
>>>>  kvm-amd-y		+= svm.o pmu_amd.o
>>>>  
>>>> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
>>>> index 5f5e25fd6149..e596527284ba 100644
>>>> --- a/include/linux/gfp.h
>>>> +++ b/include/linux/gfp.h
>>>> @@ -7,6 +7,7 @@
>>>>  #include <linux/stddef.h>
>>>>  #include <linux/linkage.h>
>>>>  #include <linux/topology.h>
>>>> +#include <linux/page_hinting.h>
>>>>  
>>>>  struct vm_area_struct;
>>>>  
>>>> @@ -456,6 +457,14 @@ 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_FREE_PAGE
>>>> +static inline void arch_free_page(struct page *page, int order)
>>>> +{
>>>> +	guest_free_page(page, order);
>>>> +}
>>>> +#endif
>>>> +
>>>>  #ifndef HAVE_ARCH_FREE_PAGE
>>>>  static inline void arch_free_page(struct page *page, int order) { }
>>>>  #endif
>>> OK so arch_free_page hook is used to tie into mm code,
>>> with follow-up patches the pages get queued in a list
>>> and then sent to hypervisor so it can free them.
>>> Fair enough but how do we know the page is
>>> not reused by the time it's received by the hypervisor?
>>> If it's reused then isn't it a problem that
>>> hypervisor calls MADV_DONTNEED on them?
>> Hi Michael,
>>
>> In order to ensure that the page is not reused, we remove it from the
>> buddy free list by acquiring the zone lock. After the page is freed by
>> the hypervisor it is returned to the buddy free list again.
> Thanks that's good to know. Could you point me to code that does this?
In Patch 0006-KVM-Enables-the-kernel-to-isolate-and-report-free-page.
hinting_fn() is responsible for scanning the per-cpu-array, acquiring
the lock, isolating the page and invoking hyperlist_ready().
Under hyperlist_ready, the hypercall to report the free pages is made
and once it is done in this function only those pages are returned to
the buddy free list.
>
>>>
>>>> diff --git a/include/linux/page_hinting.h b/include/linux/page_hinting.h
>>>> new file mode 100644
>>>> index 000000000000..b54f7428f348
>>>> --- /dev/null
>>>> +++ b/include/linux/page_hinting.h
>>>> @@ -0,0 +1,17 @@
>>>> +/*
>>>> + * Size of the array which is used to store the freed pages is defined by
>>>> + * MAX_FGPT_ENTRIES. If possible, we have to find a better way using which
>>>> + * we can get rid of the hardcoded array size.
>>>> + */
>>>> +#define MAX_FGPT_ENTRIES	1000
>>>> +/*
>>>> + * hypervisor_pages - It is a dummy structure passed with the hypercall.
>>>> + * @pfn: page frame number for the page which needs to be sent to the host.
>>>> + * @order: order of the page needs to be reported to the host.
>>>> + */
>>>> +struct hypervisor_pages {
>>>> +	unsigned long pfn;
>>>> +	unsigned int order;
>>>> +};
>>>> +
>>>> +void guest_free_page(struct page *page, int order);
>>>> diff --git a/virt/kvm/page_hinting.c b/virt/kvm/page_hinting.c
>>>> new file mode 100644
>>>> index 000000000000..818bd6b84e0c
>>>> --- /dev/null
>>>> +++ b/virt/kvm/page_hinting.c
>>>> @@ -0,0 +1,36 @@
>>>> +#include <linux/gfp.h>
>>>> +#include <linux/mm.h>
>>>> +#include <linux/kernel.h>
>>>> +
>>>> +/*
>>>> + * struct kvm_free_pages - Tracks the pages which are freed by the guest.
>>>> + * @pfn: page frame number for the page which is freed.
>>>> + * @order: order corresponding to the page freed.
>>>> + * @zonenum: zone number to which the freed page belongs.
>>>> + */
>>>> +struct kvm_free_pages {
>>>> +	unsigned long pfn;
>>>> +	unsigned int order;
>>>> +	int zonenum;
>>>> +};
>>>> +
>>>> +/*
>>>> + * struct page_hinting - holds array objects for the structures used to track
>>>> + * guest free pages, along with an index variable for each of them.
>>>> + * @kvm_pt: array object for the structure kvm_free_pages.
>>>> + * @kvm_pt_idx: index for kvm_free_pages object.
>>>> + * @hypervisor_pagelist: array object for the structure hypervisor_pages.
>>>> + * @hyp_idx: index for hypervisor_pages object.
>>>> + */
>>>> +struct page_hinting {
>>>> +	struct kvm_free_pages kvm_pt[MAX_FGPT_ENTRIES];
>>>> +	int kvm_pt_idx;
>>>> +	struct hypervisor_pages hypervisor_pagelist[MAX_FGPT_ENTRIES];
>>>> +	int hyp_idx;
>>>> +};
>>>> +
>>>> +DEFINE_PER_CPU(struct page_hinting, hinting_obj);
>>>> +
>>>> +void guest_free_page(struct page *page, int order)
>>>> +{
>>>> +}
>>>> -- 
>>>> 2.17.2
>> -- 
>> Regards
>> Nitesh
>>
>
>
-- 
Regards
Nitesh