With the introduction of protected KVM guests on s390 there is now a
concept of inaccessible pages. These pages need to be made accessible
before the host can access them.
While cpu accesses will trigger a fault that can be resolved, I/O
accesses will just fail. We need to add a callback into architecture
code for places that will do I/O, namely when writeback is started or
when a page reference is taken.
This is not only to enable paging, file backing etc, it is also
necessary to protect the host against a malicious user space. For
example a bad QEMU could simply start direct I/O on such protected
memory. We do not want userspace to be able to trigger I/O errors and
thus the logic is "whenever somebody accesses that page (gup) or does
I/O, make sure that this page can be accessed". When the guest tries
to access that page we will wait in the page fault handler for
writeback to have finished and for the page_ref to be the expected
value.
On s390x the function is not supposed to fail, so it is ok to use a
WARN_ON on failure. If we ever need some more finegrained handling
we can tackle this when we know the details.
Signed-off-by: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
Acked-by: Will Deacon <will@xxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
---
include/linux/gfp.h | 6 ++++++
mm/gup.c | 30 +++++++++++++++++++++++++++---
mm/page-writeback.c | 9 ++++++++-
3 files changed, 41 insertions(+), 4 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e5b817cb86e7..be2754841369 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -485,6 +485,12 @@ static inline void arch_free_page(struct page *page, int order) { }
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif
+#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
+static inline int arch_make_page_accessible(struct page *page)
+{
+ return 0;
+}
+#endif
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
diff --git a/mm/gup.c b/mm/gup.c
index 81a95fbe9901..d0c4c6f336bb 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -413,6 +413,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
+ int ret;
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
@@ -471,8 +472,6 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
- int ret;
-
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
@@ -480,7 +479,6 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
}
if (flags & FOLL_SPLIT && PageTransCompound(page)) {
- int ret;
get_page(page);
pte_unmap_unlock(ptep, ptl);
lock_page(page);
@@ -497,6 +495,19 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
page = ERR_PTR(-ENOMEM);
goto out;
}
+ /*
+ * We need to make the page accessible if and only if we are going
+ * to access its content (the FOLL_PIN case). Please see
+ * Documentation/core-api/pin_user_pages.rst for details.
+ */
+ if (flags & FOLL_PIN) {
+ ret = arch_make_page_accessible(page);
+ if (ret) {
+ unpin_user_page(page);
+ page = ERR_PTR(ret);
+ goto out;
+ }
+ }
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
@@ -2162,6 +2173,19 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
VM_BUG_ON_PAGE(compound_head(page) != head, page);
+ /*
+ * We need to make the page accessible if and only if we are
+ * going to access its content (the FOLL_PIN case). Please
+ * see Documentation/core-api/pin_user_pages.rst for
+ * details.
+ */
+ if (flags & FOLL_PIN) {
+ ret = arch_make_page_accessible(page);
+ if (ret) {
+ unpin_user_page(page);
+ goto pte_unmap;
+ }
+ }
SetPageReferenced(page);
pages[*nr] = page;
(*nr)++;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ab5a3cee8ad3..b7f3d0766a5f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2764,7 +2764,7 @@ int test_clear_page_writeback(struct page *page)
int __test_set_page_writeback(struct page *page, bool keep_write)
{
struct address_space *mapping = page_mapping(page);
- int ret;
+ int ret, access_ret;
lock_page_memcg(page);
if (mapping && mapping_use_writeback_tags(mapping)) {
@@ -2807,6 +2807,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
}
unlock_page_memcg(page);
+ access_ret = arch_make_page_accessible(page);
+ /*
+ * If writeback has been triggered on a page that cannot be made
+ * accessible, it is too late to recover here.
+ */
+ VM_BUG_ON_PAGE(access_ret != 0, page);
+
return ret;
}
--
2.24.1
