| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20240829165627.2256514-5-david@redhat.com>
Date: Thu, 29 Aug 2024 18:56:07 +0200
From: David Hildenbrand <david@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: linux-mm@...ck.org,
cgroups@...r.kernel.org,
x86@...nel.org,
linux-fsdevel@...r.kernel.org,
David Hildenbrand <david@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
Tejun Heo <tj@...nel.org>,
Zefan Li <lizefan.x@...edance.com>,
Johannes Weiner <hannes@...xchg.org>,
Michal Koutný <mkoutny@...e.com>,
Jonathan Corbet <corbet@....net>,
Andy Lutomirski <luto@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>
Subject: [PATCH v1 04/17] mm: let _folio_nr_pages overlay memcg_data in first tail page
Let's free up some more of the "unconditionally available on 64BIT"
space in order-1 folios by letting _folio_nr_pages overlay memcg_data in
the first tail page (second folio page). Consequently, we have the
optimization now whenever we have CONFIG_MEMCG, independent of 64BIT.
We have to make sure that page->memcg on tail pages does not return
"surprises". page_memcg_check() already properly refuses PageTail().
Let's do that earlier in print_page_owner_memcg() to avoid printing
wrong "Slab cache page" information. No other code should touch that
field on tail pages of compound pages.
Reset the "_nr_pages" to 0 when splitting folios, or when freeing them
back to the buddy (to avoid false page->memcg_data "bad page" reports).
Note that in __split_huge_page(), folio_nr_pages() would stop working
already as soon as we start messing with the subpages.
Most kernel configs should have at least CONFIG_MEMCG enabled, even if
disabled at runtime. 64byte "struct memmap" is what we usually have
on 64BIT.
While at it, rename "_folio_nr_pages" to "_nr_pages".
Signed-off-by: David Hildenbrand <david@...hat.com>
---
include/linux/mm.h | 4 ++--
include/linux/mm_types.h | 30 ++++++++++++++++++++++--------
mm/huge_memory.c | 8 ++++++++
mm/internal.h | 4 ++--
mm/page_alloc.c | 6 +++++-
mm/page_owner.c | 2 +-
6 files changed, 40 insertions(+), 14 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fa8b6ce54235c..98411e53da916 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1078,8 +1078,8 @@ static inline unsigned int folio_large_order(const struct folio *folio)
static inline long folio_large_nr_pages(const struct folio *folio)
{
-#ifdef CONFIG_64BIT
- return folio->_folio_nr_pages;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ return folio->_nr_pages;
#else
return 1L << folio_large_order(folio);
#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bca..480548552ea54 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -283,6 +283,11 @@ typedef struct {
unsigned long val;
} swp_entry_t;
+#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT)
+/* We have some extra room after the refcount in tail pages. */
+#define NR_PAGES_IN_LARGE_FOLIO
+#endif
+
/**
* struct folio - Represents a contiguous set of bytes.
* @flags: Identical to the page flags.
@@ -305,7 +310,7 @@ typedef struct {
* @_large_mapcount: Do not use directly, call folio_mapcount().
* @_nr_pages_mapped: Do not use outside of rmap and debug code.
* @_pincount: Do not use directly, call folio_maybe_dma_pinned().
- * @_folio_nr_pages: Do not use directly, call folio_nr_pages().
+ * @_nr_pages: Do not use directly, call folio_nr_pages().
* @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h.
* @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h.
* @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h.
@@ -366,13 +371,20 @@ struct folio {
unsigned long _flags_1;
unsigned long _head_1;
/* public: */
- atomic_t _large_mapcount;
- atomic_t _entire_mapcount;
- atomic_t _nr_pages_mapped;
- atomic_t _pincount;
-#ifdef CONFIG_64BIT
- unsigned int _folio_nr_pages;
-#endif
+ union {
+ struct {
+ atomic_t _large_mapcount;
+ atomic_t _entire_mapcount;
+ atomic_t _nr_pages_mapped;
+ atomic_t _pincount;
+ };
+ unsigned long _usable_1[4];
+ };
+ atomic_t _mapcount_1;
+ atomic_t _refcount_1;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ unsigned int _nr_pages;
+#endif /* NR_PAGES_IN_LARGE_FOLIO */
/* private: the union with struct page is transitional */
};
struct page __page_1;
@@ -424,6 +436,8 @@ FOLIO_MATCH(_last_cpupid, _last_cpupid);
offsetof(struct page, pg) + sizeof(struct page))
FOLIO_MATCH(flags, _flags_1);
FOLIO_MATCH(compound_head, _head_1);
+FOLIO_MATCH(_mapcount, _mapcount_1);
+FOLIO_MATCH(_refcount, _refcount_1);
#undef FOLIO_MATCH
#define FOLIO_MATCH(pg, fl) \
static_assert(offsetof(struct folio, fl) == \
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 15418ffdd3774..28d12573fcf8c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3171,6 +3171,14 @@ static void __split_huge_page(struct page *page, struct list_head *list,
int order = folio_order(folio);
unsigned int nr = 1 << order;
+ /*
+ * Reset any memcg data overlay in the tail pages. folio_nr_pages()
+ * is unreliable after this point.
+ */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ folio->_nr_pages = 0;
+#endif
+
/* complete memcg works before add pages to LRU */
split_page_memcg(head, order, new_order);
diff --git a/mm/internal.h b/mm/internal.h
index 97d6b94429ebd..f627fd2200464 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -625,8 +625,8 @@ static inline void folio_set_order(struct folio *folio, unsigned int order)
return;
folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
-#ifdef CONFIG_64BIT
- folio->_folio_nr_pages = 1U << order;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ folio->_nr_pages = 1U << order;
#endif
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c2ffccf9d2131..e276cbaf97054 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1077,8 +1077,12 @@ __always_inline bool free_pages_prepare(struct page *page,
if (unlikely(order)) {
int i;
- if (compound)
+ if (compound) {
page[1].flags &= ~PAGE_FLAGS_SECOND;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ ((struct folio *)page)->_nr_pages = 0;
+#endif
+ }
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_page_prepare(page, page + i);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 2d6360eaccbb6..a409e2561a8fd 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -507,7 +507,7 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
rcu_read_lock();
memcg_data = READ_ONCE(page->memcg_data);
- if (!memcg_data)
+ if (!memcg_data || PageTail(page))
goto out_unlock;
if (memcg_data & MEMCG_DATA_OBJEXTS)
--
2.46.0
Powered by blists - more mailing lists