| 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: <20230414142341.354556-7-shiyn.lin@gmail.com>
Date: Fri, 14 Apr 2023 22:23:30 +0800
From: Chih-En Lin <shiyn.lin@...il.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Qi Zheng <zhengqi.arch@...edance.com>,
David Hildenbrand <david@...hat.com>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
Christophe Leroy <christophe.leroy@...roup.eu>,
John Hubbard <jhubbard@...dia.com>,
Nadav Amit <namit@...are.com>, Barry Song <baohua@...nel.org>,
Pasha Tatashin <pasha.tatashin@...een.com>
Cc: Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>,
"H. Peter Anvin" <hpa@...or.com>,
Steven Rostedt <rostedt@...dmis.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Yu Zhao <yuzhao@...gle.com>,
Steven Barrett <steven@...uorix.net>,
Juergen Gross <jgross@...e.com>, Peter Xu <peterx@...hat.com>,
Kefeng Wang <wangkefeng.wang@...wei.com>,
Tong Tiangen <tongtiangen@...wei.com>,
Christoph Hellwig <hch@...radead.org>,
"Liam R. Howlett" <Liam.Howlett@...cle.com>,
Yang Shi <shy828301@...il.com>,
Vlastimil Babka <vbabka@...e.cz>,
Alex Sierra <alex.sierra@....com>,
Vincent Whitchurch <vincent.whitchurch@...s.com>,
Anshuman Khandual <anshuman.khandual@....com>,
Li kunyu <kunyu@...china.com>,
Liu Shixin <liushixin2@...wei.com>,
Hugh Dickins <hughd@...gle.com>,
Minchan Kim <minchan@...nel.org>,
Joey Gouly <joey.gouly@....com>,
Chih-En Lin <shiyn.lin@...il.com>,
Michal Hocko <mhocko@...e.com>,
Suren Baghdasaryan <surenb@...gle.com>,
"Zach O'Keefe" <zokeefe@...gle.com>,
Gautam Menghani <gautammenghani201@...il.com>,
Catalin Marinas <catalin.marinas@....com>,
Mark Brown <broonie@...nel.org>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Andrei Vagin <avagin@...il.com>,
Shakeel Butt <shakeelb@...gle.com>,
Daniel Bristot de Oliveira <bristot@...nel.org>,
"Jason A. Donenfeld" <Jason@...c4.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Alexey Gladkov <legion@...nel.org>, x86@...nel.org,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
linux-mm@...ck.org, linux-trace-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org,
Dinglan Peng <peng301@...due.edu>,
Pedro Fonseca <pfonseca@...due.edu>,
Jim Huang <jserv@...s.ncku.edu.tw>,
Huichun Feng <foxhoundsk.tw@...il.com>
Subject: [PATCH v5 06/17] mm/rmap: Break COW PTE in rmap walking
Some of the features (unmap, migrate, device exclusive, mkclean, etc)
might modify the pte entry via rmap. Add a new page vma mapped walk
flag, PVMW_BREAK_COW_PTE, to indicate the rmap walking to break COW PTE.
Signed-off-by: Chih-En Lin <shiyn.lin@...il.com>
---
include/linux/rmap.h | 2 ++
mm/migrate.c | 3 ++-
mm/page_vma_mapped.c | 4 ++++
mm/rmap.c | 9 +++++----
mm/vmscan.c | 3 ++-
5 files changed, 15 insertions(+), 6 deletions(-)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b87d01660412..57e9b72dc63a 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -377,6 +377,8 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
#define PVMW_SYNC (1 << 0)
/* Look for migration entries rather than present PTEs */
#define PVMW_MIGRATION (1 << 1)
+/* Break COW-ed PTE during walking */
+#define PVMW_BREAK_COW_PTE (1 << 2)
struct page_vma_mapped_walk {
unsigned long pfn;
diff --git a/mm/migrate.c b/mm/migrate.c
index db3f154446af..38933993af14 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -184,7 +184,8 @@ void putback_movable_pages(struct list_head *l)
static bool remove_migration_pte(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr, void *old)
{
- DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
+ DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr,
+ PVMW_SYNC | PVMW_MIGRATION | PVMW_BREAK_COW_PTE);
while (page_vma_mapped_walk(&pvmw)) {
rmap_t rmap_flags = RMAP_NONE;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 4e448cfbc6ef..1750b3460828 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -254,6 +254,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
step_forward(pvmw, PMD_SIZE);
continue;
}
+ if (pvmw->flags & PVMW_BREAK_COW_PTE) {
+ if (break_cow_pte(vma, pvmw->pmd, pvmw->address))
+ return not_found(pvmw);
+ }
if (!map_pte(pvmw))
goto next_pte;
this_pte:
diff --git a/mm/rmap.c b/mm/rmap.c
index 8632e02661ac..5582da6d72fc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1006,7 +1006,8 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
- DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+ DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address,
+ PVMW_SYNC | PVMW_BREAK_COW_PTE);
int *cleaned = arg;
*cleaned += page_vma_mkclean_one(&pvmw);
@@ -1450,7 +1451,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
struct mm_struct *mm = vma->vm_mm;
- DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
+ DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_BREAK_COW_PTE);
pte_t pteval;
struct page *subpage;
bool anon_exclusive, ret = true;
@@ -1810,7 +1811,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
struct mm_struct *mm = vma->vm_mm;
- DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
+ DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_BREAK_COW_PTE);
pte_t pteval;
struct page *subpage;
bool anon_exclusive, ret = true;
@@ -2177,7 +2178,7 @@ static bool page_make_device_exclusive_one(struct folio *folio,
struct vm_area_struct *vma, unsigned long address, void *priv)
{
struct mm_struct *mm = vma->vm_mm;
- DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
+ DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_BREAK_COW_PTE);
struct make_exclusive_args *args = priv;
pte_t pteval;
struct page *subpage;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9c1c5e8b24b8..4abbd036f927 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1892,7 +1892,8 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
/*
* The folio is mapped into the page tables of one or more
- * processes. Try to unmap it here.
+ * processes. Try to unmap it here. Also, since it will write
+ * to the page tables, break COW PTE if they are.
*/
if (folio_mapped(folio)) {
enum ttu_flags flags = TTU_BATCH_FLUSH;
--
2.34.1
Powered by blists - more mailing lists