[PATCH 8/8] KVM: PPC: Add hugepage support for IOMMU in-kernel handling

[Alexander Graf]

On 11.07.2013, at 10:57, Alexey Kardashevskiy wrote:

> On 07/10/2013 03:32 AM, Alexander Graf wrote:
>> On 07/06/2013 05:07 PM, Alexey Kardashevskiy wrote:
>>> This adds special support for huge pages (16MB).  The reference
>>> counting cannot be easily done for such pages in real mode (when
>>> MMU is off) so we added a list of huge pages.  It is populated in
>>> virtual mode and get_page is called just once per a huge page.
>>> Real mode handlers check if the requested page is huge and in the list,
>>> then no reference counting is done, otherwise an exit to virtual mode
>>> happens.  The list is released at KVM exit.  At the moment the fastest
>>> card available for tests uses up to 9 huge pages so walking through this
>>> list is not very expensive.  However this can change and we may want
>>> to optimize this.
>>> 
>>> Signed-off-by: Paul Mackerras<paulus at samba.org>
>>> Signed-off-by: Alexey Kardashevskiy<aik at ozlabs.ru>
>>> 
>>> ---
>>> 
>>> Changes:
>>> 2013/06/27:
>>> * list of huge pages replaces with hashtable for better performance
>> 
>> So the only thing your patch description really talks about is not true
>> anymore?
>> 
>>> * spinlock removed from real mode and only protects insertion of new
>>> huge [ages descriptors into the hashtable
>>> 
>>> 2013/06/05:
>>> * fixed compile error when CONFIG_IOMMU_API=n
>>> 
>>> 2013/05/20:
>>> * the real mode handler now searches for a huge page by gpa (used to be pte)
>>> * the virtual mode handler prints warning if it is called twice for the same
>>> huge page as the real mode handler is expected to fail just once - when a
>>> huge
>>> page is not in the list yet.
>>> * the huge page is refcounted twice - when added to the hugepage list and
>>> when used in the virtual mode hcall handler (can be optimized but it will
>>> make the patch less nice).
>>> 
>>> Signed-off-by: Alexey Kardashevskiy<aik at ozlabs.ru>
>>> ---
>>>  arch/powerpc/include/asm/kvm_host.h |  25 +++++++++
>>>  arch/powerpc/kernel/iommu.c         |   6 ++-
>>>  arch/powerpc/kvm/book3s_64_vio.c    | 104
>>> +++++++++++++++++++++++++++++++++---
>>>  arch/powerpc/kvm/book3s_64_vio_hv.c |  21 ++++++--
>>>  4 files changed, 146 insertions(+), 10 deletions(-)
>>> 
>>> diff --git a/arch/powerpc/include/asm/kvm_host.h
>>> b/arch/powerpc/include/asm/kvm_host.h
>>> index 53e61b2..a7508cf 100644
>>> --- a/arch/powerpc/include/asm/kvm_host.h
>>> +++ b/arch/powerpc/include/asm/kvm_host.h
>>> @@ -30,6 +30,7 @@
>>>  #include<linux/kvm_para.h>
>>>  #include<linux/list.h>
>>>  #include<linux/atomic.h>
>>> +#include<linux/hashtable.h>
>>>  #include<asm/kvm_asm.h>
>>>  #include<asm/processor.h>
>>>  #include<asm/page.h>
>>> @@ -182,10 +183,34 @@ struct kvmppc_spapr_tce_table {
>>>      u32 window_size;
>>>      struct iommu_group *grp;        /* used for IOMMU groups */
>>>      struct vfio_group *vfio_grp;        /* used for IOMMU groups */
>>> +    DECLARE_HASHTABLE(hash_tab, ilog2(64));    /* used for IOMMU groups */
>>> +    spinlock_t hugepages_write_lock;    /* used for IOMMU groups */
>>>      struct { struct { unsigned long put, indir, stuff; } rm, vm; } stat;
>>>      struct page *pages[0];
>>>  };
>>> 
>>> +/*
>>> + * The KVM guest can be backed with 16MB pages.
>>> + * In this case, we cannot do page counting from the real mode
>>> + * as the compound pages are used - they are linked in a list
>>> + * with pointers as virtual addresses which are inaccessible
>>> + * in real mode.
>>> + *
>>> + * The code below keeps a 16MB pages list and uses page struct
>>> + * in real mode if it is already locked in RAM and inserted into
>>> + * the list or switches to the virtual mode where it can be
>>> + * handled in a usual manner.
>>> + */
>>> +#define KVMPPC_SPAPR_HUGEPAGE_HASH(gpa)    hash_32(gpa>>  24, 32)
>>> +
>>> +struct kvmppc_spapr_iommu_hugepage {
>>> +    struct hlist_node hash_node;
>>> +    unsigned long gpa;    /* Guest physical address */
>>> +    unsigned long hpa;    /* Host physical address */
>>> +    struct page *page;    /* page struct of the very first subpage */
>>> +    unsigned long size;    /* Huge page size (always 16MB at the moment) */
>>> +};
>>> +
>>>  struct kvmppc_linear_info {
>>>      void        *base_virt;
>>>      unsigned long     base_pfn;
>>> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
>>> index 51678ec..e0b6eca 100644
>>> --- a/arch/powerpc/kernel/iommu.c
>>> +++ b/arch/powerpc/kernel/iommu.c
>>> @@ -999,7 +999,8 @@ int iommu_free_tces(struct iommu_table *tbl, unsigned
>>> long entry,
>>>              if (!pg) {
>>>                  ret = -EAGAIN;
>>>              } else if (PageCompound(pg)) {
>>> -                ret = -EAGAIN;
>>> +                /* Hugepages will be released at KVM exit */
>>> +                ret = 0;
>>>              } else {
>>>                  if (oldtce&  TCE_PCI_WRITE)
>>>                      SetPageDirty(pg);
>>> @@ -1009,6 +1010,9 @@ int iommu_free_tces(struct iommu_table *tbl,
>>> unsigned long entry,
>>>              struct page *pg = pfn_to_page(oldtce>>  PAGE_SHIFT);
>>>              if (!pg) {
>>>                  ret = -EAGAIN;
>>> +            } else if (PageCompound(pg)) {
>>> +                /* Hugepages will be released at KVM exit */
>>> +                ret = 0;
>>>              } else {
>>>                  if (oldtce&  TCE_PCI_WRITE)
>>>                      SetPageDirty(pg);
>>> diff --git a/arch/powerpc/kvm/book3s_64_vio.c
>>> b/arch/powerpc/kvm/book3s_64_vio.c
>>> index 2b51f4a..c037219 100644
>>> --- a/arch/powerpc/kvm/book3s_64_vio.c
>>> +++ b/arch/powerpc/kvm/book3s_64_vio.c
>>> @@ -46,6 +46,40 @@
>>> 
>>>  #define ERROR_ADDR      ((void *)~(unsigned long)0x0)
>>> 
>>> +#ifdef CONFIG_IOMMU_API
>> 
>> Can't you just make CONFIG_IOMMU_API mandatory in Kconfig?
> 
> 
> Where exactly (it is rather SPAPR_TCE_IOMMU but does not really matter)?
> Select it on KVM_BOOK3S_64? CONFIG_KVM_BOOK3S_64_HV?
> CONFIG_KVM_BOOK3S_64_PR? PPC_BOOK3S_64?

I'd say the most logical choice would be to check the Makefile and see when it gets compiled. For those cases we want it enabled.

> I am trying to imagine a configuration where we really do not want
> IOMMU_API. Ben mentioned PPC32 and embedded PPC64 and that's it so any of
> BOOK3S (KVM_BOOK3S_64 is the best) should be fine, no?

book3s_32 doesn't want this, but any book3s_64 implementation could potentially use it, yes. That's pretty much what the Makefile tells you too :).


Alex