Improve make_secure_pte to avoid stalls when the system is heavily
overcommitted. This was especially problematic in kvm_s390_pv_unpack,
because of the loop over all pages that needed unpacking.
Also fix kvm_s390_pv_init_vm to avoid stalls when the system is heavily
overcommitted.
Signed-off-by: Claudio Imbrenda <[email protected]>
Fixes: 214d9bbcd3a672 ("s390/mm: provide memory management functions for protected KVM guests")
---
arch/s390/kernel/uv.c | 29 +++++++++++++++++++++++------
arch/s390/kvm/pv.c | 2 +-
2 files changed, 24 insertions(+), 7 deletions(-)
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index aeb0a15bcbb7..68a8fbafcb9c 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -180,7 +180,7 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
{
pte_t entry = READ_ONCE(*ptep);
struct page *page;
- int expected, rc = 0;
+ int expected, cc = 0;
if (!pte_present(entry))
return -ENXIO;
@@ -196,12 +196,25 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
if (!page_ref_freeze(page, expected))
return -EBUSY;
set_bit(PG_arch_1, &page->flags);
- rc = uv_call(0, (u64)uvcb);
+ /*
+ * If the UVC does not succeed or fail immediately, we don't want to
+ * loop for long, or we might get stall notifications.
+ * On the other hand, this is a complex scenario and we are holding a lot of
+ * locks, so we can't easily sleep and reschedule. We try only once,
+ * and if the UVC returned busy or partial completion, we return
+ * -EAGAIN and we let the callers deal with it.
+ */
+ cc = __uv_call(0, (u64)uvcb);
page_ref_unfreeze(page, expected);
- /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
- if (rc)
- rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
- return rc;
+ /*
+ * Return -ENXIO if the page was not mapped, -EINVAL for other errors.
+ * If busy or partially completed, return -EAGAIN.
+ */
+ if (cc == UVC_CC_OK)
+ return 0;
+ else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL)
+ return -EAGAIN;
+ return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
}
/*
@@ -254,6 +267,10 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
mmap_read_unlock(gmap->mm);
if (rc == -EAGAIN) {
+ /*
+ * If we are here because the UVC returned busy or partial
+ * completion, this is just a useless check, but it is safe.
+ */
wait_on_page_writeback(page);
} else if (rc == -EBUSY) {
/*
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index c8841f476e91..e007df11a2fe 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -196,7 +196,7 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base;
uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
- cc = uv_call(0, (u64)&uvcb);
+ cc = uv_call_sched(0, (u64)&uvcb);
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",
--
2.31.1
On 04.08.21 17:40, Claudio Imbrenda wrote:
> Improve make_secure_pte to avoid stalls when the system is heavily
> overcommitted. This was especially problematic in kvm_s390_pv_unpack,
> because of the loop over all pages that needed unpacking.
>
> Also fix kvm_s390_pv_init_vm to avoid stalls when the system is heavily
> overcommitted.
I suggest splitting this change into a separate patch and adding a bit
more meat to the description why using the other variant is possible in
the called context. I was kind of surprise to find that change buried in
this patch.
Then, you can give both patches a more descriptive patch subject.
>
> Signed-off-by: Claudio Imbrenda <[email protected]>
> Fixes: 214d9bbcd3a672 ("s390/mm: provide memory management functions for protected KVM guests")
> ---
> arch/s390/kernel/uv.c | 29 +++++++++++++++++++++++------
> arch/s390/kvm/pv.c | 2 +-
> 2 files changed, 24 insertions(+), 7 deletions(-)
>
> diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
> index aeb0a15bcbb7..68a8fbafcb9c 100644
> --- a/arch/s390/kernel/uv.c
> +++ b/arch/s390/kernel/uv.c
> @@ -180,7 +180,7 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
> {
> pte_t entry = READ_ONCE(*ptep);
> struct page *page;
> - int expected, rc = 0;
> + int expected, cc = 0;
>
> if (!pte_present(entry))
> return -ENXIO;
> @@ -196,12 +196,25 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
> if (!page_ref_freeze(page, expected))
> return -EBUSY;
> set_bit(PG_arch_1, &page->flags);
> - rc = uv_call(0, (u64)uvcb);
> + /*
> + * If the UVC does not succeed or fail immediately, we don't want to
> + * loop for long, or we might get stall notifications.
> + * On the other hand, this is a complex scenario and we are holding a lot of
> + * locks, so we can't easily sleep and reschedule. We try only once,
> + * and if the UVC returned busy or partial completion, we return
> + * -EAGAIN and we let the callers deal with it.
> + */
> + cc = __uv_call(0, (u64)uvcb);
> page_ref_unfreeze(page, expected);
> - /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
> - if (rc)
> - rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
> - return rc;
> + /*
> + * Return -ENXIO if the page was not mapped, -EINVAL for other errors.
> + * If busy or partially completed, return -EAGAIN.
> + */
> + if (cc == UVC_CC_OK)
> + return 0;
> + else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL)
> + return -EAGAIN;
> + return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
> }
That looks conceptually like the right thing to me.
--
Thanks,
David / dhildenb
On Fri, 6 Aug 2021 09:30:04 +0200
David Hildenbrand <[email protected]> wrote:
> On 04.08.21 17:40, Claudio Imbrenda wrote:
> > Improve make_secure_pte to avoid stalls when the system is heavily
> > overcommitted. This was especially problematic in
> > kvm_s390_pv_unpack, because of the loop over all pages that needed
> > unpacking.
> >
> > Also fix kvm_s390_pv_init_vm to avoid stalls when the system is
> > heavily overcommitted.
>
> I suggest splitting this change into a separate patch and adding a
> bit more meat to the description why using the other variant is
> possible in the called context. I was kind of surprise to find that
> change buried in this patch.
>
> Then, you can give both patches a more descriptive patch subject.
fair enough, I'll split them
> >
> > Signed-off-by: Claudio Imbrenda <[email protected]>
> > Fixes: 214d9bbcd3a672 ("s390/mm: provide memory management
> > functions for protected KVM guests") ---
> > arch/s390/kernel/uv.c | 29 +++++++++++++++++++++++------
> > arch/s390/kvm/pv.c | 2 +-
> > 2 files changed, 24 insertions(+), 7 deletions(-)
> >
> > diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
> > index aeb0a15bcbb7..68a8fbafcb9c 100644
> > --- a/arch/s390/kernel/uv.c
> > +++ b/arch/s390/kernel/uv.c
> > @@ -180,7 +180,7 @@ static int make_secure_pte(pte_t *ptep,
> > unsigned long addr, {
> > pte_t entry = READ_ONCE(*ptep);
> > struct page *page;
> > - int expected, rc = 0;
> > + int expected, cc = 0;
> >
> > if (!pte_present(entry))
> > return -ENXIO;
> > @@ -196,12 +196,25 @@ static int make_secure_pte(pte_t *ptep,
> > unsigned long addr, if (!page_ref_freeze(page, expected))
> > return -EBUSY;
> > set_bit(PG_arch_1, &page->flags);
> > - rc = uv_call(0, (u64)uvcb);
> > + /*
> > + * If the UVC does not succeed or fail immediately, we
> > don't want to
> > + * loop for long, or we might get stall notifications.
> > + * On the other hand, this is a complex scenario and we
> > are holding a lot of
> > + * locks, so we can't easily sleep and reschedule. We try
> > only once,
> > + * and if the UVC returned busy or partial completion, we
> > return
> > + * -EAGAIN and we let the callers deal with it.
> > + */
> > + cc = __uv_call(0, (u64)uvcb);
> > page_ref_unfreeze(page, expected);
> > - /* Return -ENXIO if the page was not mapped, -EINVAL
> > otherwise */
> > - if (rc)
> > - rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
> > - return rc;
> > + /*
> > + * Return -ENXIO if the page was not mapped, -EINVAL for
> > other errors.
> > + * If busy or partially completed, return -EAGAIN.
> > + */
> > + if (cc == UVC_CC_OK)
> > + return 0;
> > + else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL)
> > + return -EAGAIN;
> > + return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
> > }
>
> That looks conceptually like the right thing to me.
>