From: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
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.
Due to the locks being held, it was not possible to simply replace
uv_call with uv_call_sched. A more complex approach was
needed, in which uv_call is replaced with __uv_call, which does not
loop. When the UVC needs to be executed again, -EAGAIN is returned, and
the caller (or its caller) will try again.
When -EAGAIN is returned, the path is the same as when the page is in
writeback (and the writeback check is also performed, which is
harmless).
Fixes: 214d9bbcd3a672 ("s390/mm: provide memory management functions for protected KVM guests")
Signed-off-by: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
Reviewed-by: Janosch Frank <frankja@xxxxxxxxxxxxx>
Reviewed-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20210920132502.36111-5-imbrenda@xxxxxxxxxxxxx
Signed-off-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
---
arch/s390/kernel/uv.c | 29 +++++++++++++++++++++++------
arch/s390/kvm/intercept.c | 5 +++++
2 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index f95ccbd39692..09b80d371409 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -165,7 +165,7 @@ 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;
@@ -181,12 +181,25 @@ 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;
}
/*
@@ -239,6 +252,10 @@ 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/intercept.c b/arch/s390/kvm/intercept.c
index 2bd8f854f1b4..d07ff646d844 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -518,6 +518,11 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
*/
if (rc == -EINVAL)
return 0;
+ /*
+ * If we got -EAGAIN here, we simply return it. It will eventually
+ * get propagated all the way to userspace, which should then try
+ * again.
+ */
return rc;
}
--
2.31.1
