Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-24 21:21:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

KVM: guest_memfd: abstract how prepared folios are recorded

Browse Source 
Right now, large folios are not supported in guest_memfd, and therefore the order
used by kvm_gmem_populate() is always 0.  In this scenario, using the up-to-date
bit to track prepared-ness is nice and easy because we have one bit available
per page.

In the future, however, we might have large pages that are partially populated;
for example, in the case of SEV-SNP, if a large page has both shared and private
areas inside, it is necessary to populate it at a granularity that is smaller
than that of the guest_memfd's backing store.  In that case we will have
to track preparedness at a 4K level, probably as a bitmap.

In preparation for that, do not use explicitly folio_test_uptodate() and
folio_mark_uptodate().  Return the state of the page directly from
__kvm_gmem_get_pfn(), so that it is expected to apply to 2^N pages
with N=*max_order.  The function to mark a range as prepared for now
takes just a folio, but is expected to take also an index and order
(or something like that) when large pages are introduced.

Thanks to Michael Roth for pointing out the issue with large pages.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini 2024-07-26 13:45:36 -04:00
parent e4ee544792
commit 66a644c09f
1 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
virt/kvm/guest_memfd.c
View File

@ -42,6 +42,11 @@ static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slo
return 0;
}
static inline void kvm_gmem_mark_prepared(struct folio *folio)
{
folio_mark_uptodate(folio);
}
/*
* Process @folio, which contains @gfn, so that the guest can use it.
* The folio must be locked and the gfn must be contained in @slot.
@ -55,9 +60,6 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
pgoff_t index;
int r;
if (folio_test_uptodate(folio))
return 0;
nr_pages = folio_nr_pages(folio);
for (i = 0; i < nr_pages; i++)
clear_highpage(folio_page(folio, i));
@ -80,7 +82,7 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
index = ALIGN_DOWN(index, 1 << folio_order(folio));
r = __kvm_gmem_prepare_folio(kvm, slot, index, folio);
if (!r)
folio_mark_uptodate(folio);
kvm_gmem_mark_prepared(folio);
return r;
}
@ -551,7 +553,8 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
/* Returns a locked folio on success. */
static struct folio *
__kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
gfn_t gfn, kvm_pfn_t *pfn, bool *is_prepared,
int *max_order)
{
pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
struct kvm_gmem *gmem = file->private_data;
@ -582,6 +585,7 @@ __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
if (max_order)
*max_order = 0;
*is_prepared = folio_test_uptodate(folio);
return folio;
}
@ -590,18 +594,21 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
{
struct file *file = kvm_gmem_get_file(slot);
struct folio *folio;
bool is_prepared = false;
int r = 0;
if (!file)
return -EFAULT;
folio = __kvm_gmem_get_pfn(file, slot, gfn, pfn, max_order);
folio = __kvm_gmem_get_pfn(file, slot, gfn, pfn, &is_prepared, max_order);
if (IS_ERR(folio)) {
r = PTR_ERR(folio);
goto out;
}
if (!is_prepared)
r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio);
folio_unlock(folio);
if (r < 0)
folio_put(folio);
@ -641,6 +648,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
for (i = 0; i < npages; i += (1 << max_order)) {
struct folio *folio;
gfn_t gfn = start_gfn + i;
bool is_prepared = false;
kvm_pfn_t pfn;
if (signal_pending(current)) {
@ -648,13 +656,13 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
break;
}
folio = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &max_order);
folio = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &is_prepared, &max_order);
if (IS_ERR(folio)) {
ret = PTR_ERR(folio);
break;
}
if (folio_test_uptodate(folio)) {
if (is_prepared) {
folio_unlock(folio);
folio_put(folio);
ret = -EEXIST;
@ -662,9 +670,8 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
}
folio_unlock(folio);
if (!IS_ALIGNED(gfn, (1 << max_order)) ||
(npages - i) < (1 << max_order))
max_order = 0;
WARN_ON(!IS_ALIGNED(gfn, 1 << max_order) ||
(npages - i) < (1 << max_order));
ret = -EINVAL;
while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order),
@ -678,7 +685,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
p = src ? src + i * PAGE_SIZE : NULL;
ret = post_populate(kvm, gfn, pfn, p, max_order, opaque);
if (!ret)
folio_mark_uptodate(folio);
kvm_gmem_mark_prepared(folio);
put_folio_and_exit:
folio_put(folio);