On Mon, Jan 23, 2023 at 05:03:23PM -0800, Ben Gardon wrote:
> On Thu, Jan 12, 2023 at 7:50 PM Ricardo Koller <ricarkol@xxxxxxxxxx> wrote:
> >
> > Add a new stage2 function, kvm_pgtable_stage2_split(), for splitting a
> > range of huge pages. This will be used for eager-splitting huge pages
> > into PAGE_SIZE pages. The goal is to avoid having to split huge pages
> > on write-protection faults, and instead use this function to do it
> > ahead of time for large ranges (e.g., all guest memory in 1G chunks at
> > a time).
> >
> > No functional change intended. This new function will be used in a
> > subsequent commit.
> >
> > Signed-off-by: Ricardo Koller <ricarkol@xxxxxxxxxx>
> > ---
> > arch/arm64/include/asm/kvm_pgtable.h | 29 ++++++++++++
> > arch/arm64/kvm/hyp/pgtable.c | 67 ++++++++++++++++++++++++++++
> > 2 files changed, 96 insertions(+)
> >
> > diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> > index 8ad78d61af7f..5fbdc1f259fd 100644
> > --- a/arch/arm64/include/asm/kvm_pgtable.h
> > +++ b/arch/arm64/include/asm/kvm_pgtable.h
> > @@ -644,6 +644,35 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
> > */
> > int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
> >
> > +/**
> > + * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing
> > + * to PAGE_SIZE guest pages.
> > + * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
> > + * @addr: Intermediate physical address from which to split.
> > + * @size: Size of the range.
> > + * @mc: Cache of pre-allocated and zeroed memory from which to allocate
> > + * page-table pages.
> > + *
> > + * @addr and the end (@addr + @size) are effectively aligned down and up to
> > + * the top level huge-page block size. This is an exampe using 1GB
>
> Nit: example
>
> > + * huge-pages and 4KB granules.
> > + *
> > + * [---input range---]
> > + * : :
> > + * [--1G block pte--][--1G block pte--][--1G block pte--][--1G block pte--]
> > + * : :
> > + * [--2MB--][--2MB--][--2MB--][--2MB--]
> > + * : :
> > + * [ ][ ][:][ ][ ][ ][ ][ ][:][ ][ ][ ]
> > + * : :
> > + *
> > + * Return: 0 on success, negative error code on failure. Note that
> > + * kvm_pgtable_stage2_split() is best effort: it tries to break as many
> > + * blocks in the input range as allowed by the size of the memcache. It
> > + * will fail it wasn't able to break any block.
> > + */
> > +int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc);
> > +
> > /**
> > * kvm_pgtable_walk() - Walk a page-table.
> > * @pgt: Page-table structure initialised by kvm_pgtable_*_init().
> > diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> > index 0dee13007776..db9d1a28769b 100644
> > --- a/arch/arm64/kvm/hyp/pgtable.c
> > +++ b/arch/arm64/kvm/hyp/pgtable.c
> > @@ -1229,6 +1229,73 @@ int kvm_pgtable_stage2_create_removed(struct kvm_pgtable *pgt,
> > return 0;
> > }
> >
> > +struct stage2_split_data {
> > + struct kvm_s2_mmu *mmu;
> > + void *memcache;
> > +};
> > +
> > +static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
> > + enum kvm_pgtable_walk_flags visit)
> > +{
> > + struct stage2_split_data *data = ctx->arg;
> > + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
> > + kvm_pte_t pte = ctx->old, new, *childp;
> > + enum kvm_pgtable_prot prot;
> > + void *mc = data->memcache;
> > + u32 level = ctx->level;
> > + u64 phys;
> > + int ret;
> > +
> > + /* Nothing to split at the last level */
>
> Would it be accurate to say:
> /* No huge pages can exist at the root level, so there's nothing to
> split here. */
>
> I think of "last level" as the lowest/leaf/4k level but
> KVM_PGTABLE_MAX_LEVELS - 1 is 3?
Right, this is the 4k level.
> Does ARM do the level numbering in
> reverse order to x86?
Yes, it does. Interesting, x86 does
iter->level--;
while arm does:
ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1);
I don't think this numbering scheme is encoded anywhere in the PTEs, so
either architecture could use the other.
>
> > + if (level == KVM_PGTABLE_MAX_LEVELS - 1)
> > + return 0;
> > +
> ...
