@@ -2004,6 +2004,13 @@ static inline struct folio *pfn_folio(unsigned long pfn)
return page_folio(pfn_to_page(pfn));
}
+static inline bool folio_has_pincount(const struct folio *folio)
+{
+ if (IS_ENABLED(CONFIG_64BIT))
+ return folio_test_large(folio);
+ return folio_order(folio) > 1;
+}
+
/**
* folio_maybe_dma_pinned - Report if a folio may be pinned for DMA.
* @folio: The folio.
@@ -2020,7 +2027,7 @@ static inline struct folio *pfn_folio(unsigned long pfn)
* get that many refcounts, and b) all the callers of this routine are
* expected to be able to deal gracefully with a false positive.
*
- * For large folios, the result will be exactly correct. That's because
+ * For most large folios, the result will be exactly correct. That's because
* we have more tracking data available: the _pincount field is used
* instead of the GUP_PIN_COUNTING_BIAS scheme.
*
@@ -2031,7 +2038,7 @@ static inline struct folio *pfn_folio(unsigned long pfn)
*/
static inline bool folio_maybe_dma_pinned(struct folio *folio)
{
- if (folio_test_large(folio))
+ if (folio_has_pincount(folio))
return atomic_read(&folio->_pincount) > 0;
/*
@@ -387,7 +387,9 @@ struct folio {
atomic_t _large_mapcount;
atomic_t _entire_mapcount;
atomic_t _nr_pages_mapped;
+#ifdef CONFIG_64BIT
atomic_t _pincount;
+#endif /* CONFIG_64BIT */
};
unsigned long _usable_1[4];
};
@@ -406,6 +408,9 @@ struct folio {
unsigned long _head_2;
/* public: */
struct list_head _deferred_list;
+#ifndef CONFIG_64BIT
+ atomic_t _pincount;
+#endif /* !CONFIG_64BIT */
/* private: the union with struct page is transitional */
};
struct page __page_2;
@@ -79,12 +79,17 @@ static void __dump_folio(struct folio *folio, struct page *page,
folio_ref_count(folio), mapcount, mapping,
folio->index + idx, pfn);
if (folio_test_large(folio)) {
+ int pincount = 0;
+
+ if (folio_has_pincount(folio))
+ pincount = atomic_read(&folio->_pincount);
+
pr_warn("head: order:%u mapcount:%d entire_mapcount:%d nr_pages_mapped:%d pincount:%d\n",
folio_order(folio),
folio_mapcount(folio),
folio_entire_mapcount(folio),
folio_nr_pages_mapped(folio),
- atomic_read(&folio->_pincount));
+ pincount);
}
#ifdef CONFIG_MEMCG
@@ -146,6 +151,9 @@ static void __dump_page(const struct page *page)
if (idx < MAX_FOLIO_NR_PAGES) {
memcpy(&folio, foliop, 2 * sizeof(struct page));
nr_pages = folio_nr_pages(&folio);
+ if (nr_pages > 1)
+ memcpy(&folio.__page_2, &foliop->__page_2,
+ sizeof(struct page));
foliop = &folio;
}
@@ -109,7 +109,7 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
if (is_zero_folio(folio))
return;
node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs);
- if (folio_test_large(folio))
+ if (folio_has_pincount(folio))
atomic_sub(refs, &folio->_pincount);
else
refs *= GUP_PIN_COUNTING_BIAS;
@@ -164,7 +164,7 @@ int __must_check try_grab_folio(struct folio *folio, int refs,
* Increment the normal page refcount field at least once,
* so that the page really is pinned.
*/
- if (folio_test_large(folio)) {
+ if (folio_has_pincount(folio)) {
folio_ref_add(folio, refs);
atomic_add(refs, &folio->_pincount);
} else {
@@ -223,7 +223,7 @@ void folio_add_pin(struct folio *folio)
* page refcount field at least once, so that the page really is
* pinned.
*/
- if (folio_test_large(folio)) {
+ if (folio_has_pincount(folio)) {
WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1);
folio_ref_inc(folio);
atomic_inc(&folio->_pincount);
@@ -575,7 +575,7 @@ static struct folio *try_grab_folio_fast(struct page *page, int refs,
* is pinned. That's why the refcount from the earlier
* try_get_folio() is left intact.
*/
- if (folio_test_large(folio))
+ if (folio_has_pincount(folio))
atomic_add(refs, &folio->_pincount);
else
folio_ref_add(folio,
@@ -723,7 +723,8 @@ static inline void prep_compound_head(struct page *page, unsigned int order)
atomic_set(&folio->_large_mapcount, -1);
atomic_set(&folio->_entire_mapcount, -1);
atomic_set(&folio->_nr_pages_mapped, 0);
- atomic_set(&folio->_pincount, 0);
+ if (IS_ENABLED(CONFIG_64BIT) || order > 1)
+ atomic_set(&folio->_pincount, 0);
if (order > 1)
INIT_LIST_HEAD(&folio->_deferred_list);
}
@@ -959,9 +959,11 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page)
bad_page(page, "nonzero nr_pages_mapped");
goto out;
}
- if (unlikely(atomic_read(&folio->_pincount))) {
- bad_page(page, "nonzero pincount");
- goto out;
+ if (IS_ENABLED(CONFIG_64BIT)) {
+ if (unlikely(atomic_read(&folio->_pincount))) {
+ bad_page(page, "nonzero pincount");
+ goto out;
+ }
}
break;
case 2:
@@ -970,6 +972,12 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page)
bad_page(page, "on deferred list");
goto out;
}
+ if (!IS_ENABLED(CONFIG_64BIT)) {
+ if (unlikely(atomic_read(&folio->_pincount))) {
+ bad_page(page, "nonzero pincount");
+ goto out;
+ }
+ }
break;
case 3:
/* the third tail page: hugetlb specifics overlap ->mappings */
Let's free up some space on 32bit in page[1] by moving the _pincount to page[2]. For order-1 folios (never anon folios!) on 32bit, we will now also use the GUP_PIN_COUNTING_BIAS approach. A fully-mapped order-1 folio requires 2 references. With GUP_PIN_COUNTING_BIAS being 1024, we'd detect such folios as "maybe pinned" with 512 full mappings, instead of 1024 for order-0. As anon folios are out of the picture (which are the most relevant users of checking for pinnings on *mapped* pages) and we are talking about 32bit, this is not expected to cause any trouble. In __dump_page(), copy one additional folio page if we detect a folio with an order > 1, so we can dump the pincount on order > 1 folios reliably. Note that THPs on 32bit are not particularly common (and we don't care too much about performance), but we want to keep it working reliably, because likely we want to use large folios there as well in the future, independent of PMD leaf support. Once we dynamically allocate "struct folio", fortunately the 32bit specifics will likely go away again; even small folios could then have a pincount and folio_has_pincount() would essentially always return "true". Signed-off-by: David Hildenbrand <david@redhat.com> --- include/linux/mm.h | 11 +++++++++-- include/linux/mm_types.h | 5 +++++ mm/debug.c | 10 +++++++++- mm/gup.c | 8 ++++---- mm/internal.h | 3 ++- mm/page_alloc.c | 14 +++++++++++--- 6 files changed, 40 insertions(+), 11 deletions(-)