Avi Kivity wrote:
> On 10/02/2009 10:19 PM, Gregory Haskins wrote:
>> This allows a scatter-gather approach to IO, which will be useful for
>> building high performance interfaces, like zero-copy and low-latency
>> copy (avoiding multiple calls to copy_to/from).
>>
>> The interface is based on the existing scatterlist infrastructure. The
>> caller is expected to pass in a scatterlist with its "dma" field
>> populated with valid GPAs. The xinterface will then populate each
>> entry by translating the GPA to a page*.
>>
>> The caller signifies completion by simply performing a put_page() on
>> each page returned in the list.
>>
>> Signed-off-by: Gregory Haskins<ghaskins@xxxxxxxxxx>
>> ---
>>
>> include/linux/kvm_xinterface.h | 4 ++
>> virt/kvm/xinterface.c | 72
>> ++++++++++++++++++++++++++++++++++++++++
>> 2 files changed, 76 insertions(+), 0 deletions(-)
>>
>> diff --git a/include/linux/kvm_xinterface.h
>> b/include/linux/kvm_xinterface.h
>> index 684b6f8..eefb575 100644
>> --- a/include/linux/kvm_xinterface.h
>> +++ b/include/linux/kvm_xinterface.h
>> @@ -9,6 +9,7 @@
>> #include<linux/kref.h>
>> #include<linux/module.h>
>> #include<linux/file.h>
>> +#include<linux/scatterlist.h>
>>
>> struct kvm_xinterface;
>> struct kvm_xvmap;
>> @@ -36,6 +37,9 @@ struct kvm_xinterface_ops {
>> u64 addr,
>> unsigned long len,
>> unsigned long flags);
>> + unsigned long (*sgmap)(struct kvm_xinterface *intf,
>> + struct scatterlist *sgl, int nents,
>> + unsigned long flags);
>> void (*release)(struct kvm_xinterface *);
>> };
>>
>> diff --git a/virt/kvm/xinterface.c b/virt/kvm/xinterface.c
>> index c356835..16729f6 100644
>> --- a/virt/kvm/xinterface.c
>> +++ b/virt/kvm/xinterface.c
>> @@ -467,6 +467,77 @@ fail:
>>
>> }
>>
>> +static unsigned long
>> +xinterface_sgmap(struct kvm_xinterface *intf,
>> + struct scatterlist *sgl, int nents,
>> + unsigned long flags)
>> +{
>> + struct _xinterface *_intf = to_intf(intf);
>> + struct task_struct *p = _intf->task;
>> + struct mm_struct *mm = _intf->mm;
>> + struct kvm *kvm = _intf->kvm;
>> + struct kvm_memory_slot *memslot = NULL;
>> + bool kthread = !current->mm;
>> + int ret;
>> + struct scatterlist *sg;
>> + int i;
>> +
>> + down_read(&kvm->slots_lock);
>> +
>> + if (kthread)
>> + use_mm(_intf->mm);
>> +
>> + for_each_sg(sgl, sg, nents, i) {
>> + unsigned long gpa = sg_dma_address(sg);
>> + unsigned long len = sg_dma_len(sg);
>> + unsigned long gfn = gpa>> PAGE_SHIFT;
>> + off_t offset = offset_in_page(gpa);
>> + unsigned long hva;
>> + struct page *pg;
>> +
>> + /* ensure that we do not have more than one page per entry */
>> + if ((PAGE_ALIGN(len + offset)>> PAGE_SHIFT) != 1) {
>> + ret = -EINVAL;
>> + break;
>> + }
>> +
>> + /* check for a memslot-cache miss */
>> + if (!memslot
>> + || gfn< memslot->base_gfn
>> + || gfn>= memslot->base_gfn + memslot->npages) {
>> + memslot = gfn_to_memslot(kvm, gfn);
>> + if (!memslot) {
>> + ret = -EFAULT;
>> + break;
>> + }
>> + }
>> +
>> + hva = (memslot->userspace_addr +
>> + (gfn - memslot->base_gfn) * PAGE_SIZE);
>> +
>> + if (kthread || current->mm == mm)
>> + ret = get_user_pages_fast(hva, 1, 1,&pg);
>> + else
>> + ret = get_user_pages(p, mm, hva, 1, 1, 0,&pg, NULL);
>>
>
> One of these needs the mm semaphore.
Indeed. Good catch.
>
>> +
>> + if (ret != 1) {
>> + if (ret>= 0)
>> + ret = -EFAULT;
>> + break;
>> + }
>> +
>> + sg_set_page(sg, pg, len, offset);
>> + ret = 0;
>> + }
>> +
>> + if (kthread)
>> + unuse_mm(_intf->mm);
>> +
>> + up_read(&kvm->slots_lock);
>> +
>> + return ret;
>> +}
>> +
>> static void
>> xinterface_release(struct kvm_xinterface *intf)
>> {
>> @@ -483,6 +554,7 @@ struct kvm_xinterface_ops _xinterface_ops = {
>> .copy_from = xinterface_copy_from,
>> .vmap = xinterface_vmap,
>> .ioevent = xinterface_ioevent,
>> + .sgmap = xinterface_sgmap,
>> .release = xinterface_release,
>> };
>>
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe kvm" in
>> the body of a message to majordomo@xxxxxxxxxxxxxxx
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>
>
>
Attachment:
signature.asc
Description: OpenPGP digital signature
