There is a faint risk that __pte_offset_map(), on a 32-bit architecture
with a 64-bit pmd_t e.g. x86-32 with CONFIG_X86_PAE=y, would succeed on
a pmdval assembled from a pmd_low and a pmd_high which never belonged
together: their combination not pointing to a page table at all, perhaps
not even a valid pfn. pmdp_get_lockless() is not enough to prevent that.
Guard against that (on such configs) by local_irq_save() blocking TLB
flush between present updates, as linux/pgtable.h suggests. It's only
needed around the pmdp_get_lockless() in __pte_offset_map(): a race when
__pte_offset_map_lock() repeats the pmdp_get_lockless() after getting the
lock, would just send it back to __pte_offset_map() again.
Complement this pmdp_get_lockless_start() and pmdp_get_lockless_end(),
used only locally in __pte_offset_map(), with a pmdp_get_lockless_sync()
synonym for tlb_remove_table_sync_one(): to send the necessary interrupt
at the right moment on those configs which do not already send it.
CONFIG_GUP_GET_PXX_LOW_HIGH is enabled when required by mips, sh and x86.
It is not enabled by arm-32 CONFIG_ARM_LPAE: my understanding is that
Will Deacon's 2020 enhancements to READ_ONCE() are sufficient for arm.
It is not enabled by arc, but its pmd_t is 32-bit even when pte_t 64-bit.
Limit the IRQ disablement to CONFIG_HIGHPTE? Perhaps, but would need a
little more work, to retry if pmd_low good for page table, but pmd_high
non-zero from THP (and that might be making x86-specific assumptions).
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
---
include/linux/pgtable.h | 4 ++++
mm/pgtable-generic.c | 29 +++++++++++++++++++++++++++++
2 files changed, 33 insertions(+)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 8b0fc7fdc46f..525f1782b466 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -390,6 +390,7 @@ static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
return pmd;
}
#define pmdp_get_lockless pmdp_get_lockless
+#define pmdp_get_lockless_sync() tlb_remove_table_sync_one()
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */
@@ -408,6 +409,9 @@ static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
{
return pmdp_get(pmdp);
}
+static inline void pmdp_get_lockless_sync(void)
+{
+}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 674671835631..5e85a625ab30 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -232,12 +232,41 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \
+ (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU))
+/*
+ * See the comment above ptep_get_lockless() in include/linux/pgtable.h:
+ * the barriers in pmdp_get_lockless() cannot guarantee that the value in
+ * pmd_high actually belongs with the value in pmd_low; but holding interrupts
+ * off blocks the TLB flush between present updates, which guarantees that a
+ * successful __pte_offset_map() points to a page from matched halves.
+ */
+static unsigned long pmdp_get_lockless_start(void)
+{
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
+ return irqflags;
+}
+static void pmdp_get_lockless_end(unsigned long irqflags)
+{
+ local_irq_restore(irqflags);
+}
+#else
+static unsigned long pmdp_get_lockless_start(void) { return 0; }
+static void pmdp_get_lockless_end(unsigned long irqflags) { }
+#endif
+
pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
{
+ unsigned long irqflags;
pmd_t pmdval;
rcu_read_lock();
+ irqflags = pmdp_get_lockless_start();
pmdval = pmdp_get_lockless(pmd);
+ pmdp_get_lockless_end(irqflags);
+
if (pmdvalp)
*pmdvalp = pmdval;
if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
--
2.35.3
