As soon as storage keys are enabled we need to stop working on zero page
mappings to prevent inconsistencies between storage keys and pgste.
Otherwise following data corruption could happen:
1) guest enables storage key
2) guest sets storage key for not mapped page X
-> change goes to PGSTE
3) guest reads from page X
-> as X was not dirty before, the page will be zero page backed,
storage key from PGSTE for X will go to storage key for zero page
4) guest sets storage key for not mapped page Y (same logic as above
5) guest reads from page Y
-> as Y was not dirty before, the page will be zero page backed,
storage key from PGSTE for Y will got to storage key for zero page
overwriting storage key for X
While holding the mmap sem, we are safe against changes on entries we
already fixed, as every fault would need to take the mmap_sem (read).
As sske and host large pages are also mutual exclusive we do not even
need to retry the fixup_user_fault.
As use_skey is already the condition on which we call s390_enable_skey
we need to introduce a new flag for the mm->context on which we decide
if zero page mapping is allowed.
Signed-off-by: Dominik Dingel <dingel@xxxxxxxxxxxxxxxxxx>
---
arch/s390/include/asm/mmu.h | 2 ++
arch/s390/include/asm/pgtable.h | 14 ++++++++++++++
arch/s390/mm/pgtable.c | 12 ++++++++++++
3 files changed, 28 insertions(+)
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index a5e6562..0f38469 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -18,6 +18,8 @@ typedef struct {
unsigned int has_pgste:1;
/* The mmu context uses storage keys. */
unsigned int use_skey:1;
+ /* The mmu context forbids zeropage mappings. */
+ unsigned int forbids_zeropage:1;
} mm_context_t;
#define INIT_MM_CONTEXT(name) \
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1e991f6a..fe3cfdf 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -481,6 +481,20 @@ static inline int mm_has_pgste(struct mm_struct *mm)
return 0;
}
+/*
+ * In the case that a guest uses storage keys
+ * faults should no longer be backed by zero pages
+ */
+#define mm_forbids_zeropage mm_forbids_zeropage
+static inline int mm_forbids_zeropage(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+ if (mm->context.forbids_zeropage)
+ return 1;
+#endif
+ return 0;
+}
+
static inline int mm_use_skey(struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ab55ba8..1e06fbc 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1309,6 +1309,15 @@ static int __s390_enable_skey(pte_t *pte, unsigned long addr,
pgste_t pgste;
pgste = pgste_get_lock(pte);
+ /*
+ * Remove all zero page mappings,
+ * after establishing a policy to forbid zero page mappings
+ * following faults for that page will get fresh anonymous pages
+ */
+ if (is_zero_pfn(pte_pfn(*pte))) {
+ ptep_flush_direct(walk->mm, addr, pte);
+ pte_val(*pte) = _PAGE_INVALID;
+ }
/* Clear storage key */
pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
PGSTE_GR_BIT | PGSTE_GC_BIT);
@@ -1327,6 +1336,9 @@ void s390_enable_skey(void)
down_write(&mm->mmap_sem);
if (mm_use_skey(mm))
goto out_up;
+
+ mm->context.forbids_zeropage = 1;
+
walk.mm = mm;
walk_page_range(0, TASK_SIZE, &walk);
mm->context.use_skey = 1;
--
1.8.5.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>