From: Lior Ribak <liorribak(a)gmail.com>
Subject: binfmt_misc: fix possible deadlock in bm_register_write
There is a deadlock in bm_register_write:
First, in the begining of the function, a lock is taken on the binfmt_misc
root inode with inode_lock(d_inode(root)).
Then, if the user used the MISC_FMT_OPEN_FILE flag, the function will call
open_exec on the user-provided interpreter.
open_exec will call a path lookup, and if the path lookup process includes
the root of binfmt_misc, it will try to take a shared lock on its inode
again, but it is already locked, and the code will get stuck in a deadlock
To reproduce the bug:
$ echo ":iiiii:E::ii::/proc/sys/fs/binfmt_misc/bla:F" > /proc/sys/fs/binfmt_misc/register
backtrace of where the lock occurs (#5):
0 schedule () at ./arch/x86/include/asm/current.h:15
1 0xffffffff81b51237 in rwsem_down_read_slowpath (sem=0xffff888003b202e0, count=<optimized out>, state=state@entry=2) at kernel/locking/rwsem.c:992
2 0xffffffff81b5150a in __down_read_common (state=2, sem=<optimized out>) at kernel/locking/rwsem.c:1213
3 __down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1222
4 down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1355
5 0xffffffff811ee22a in inode_lock_shared (inode=<optimized out>) at ./include/linux/fs.h:783
6 open_last_lookups (op=0xffffc9000022fe34, file=0xffff888004098600, nd=0xffffc9000022fd10) at fs/namei.c:3177
7 path_openat (nd=nd@entry=0xffffc9000022fd10, op=op@entry=0xffffc9000022fe34, flags=flags@entry=65) at fs/namei.c:3366
8 0xffffffff811efe1c in do_filp_open (dfd=<optimized out>, pathname=pathname@entry=0xffff8880031b9000, op=op@entry=0xffffc9000022fe34) at fs/namei.c:3396
9 0xffffffff811e493f in do_open_execat (fd=fd@entry=-100, name=name@entry=0xffff8880031b9000, flags=<optimized out>, flags@entry=0) at fs/exec.c:913
10 0xffffffff811e4a92 in open_exec (name=<optimized out>) at fs/exec.c:948
11 0xffffffff8124aa84 in bm_register_write (file=<optimized out>, buffer=<optimized out>, count=19, ppos=<optimized out>) at fs/binfmt_misc.c:682
12 0xffffffff811decd2 in vfs_write (file=file@entry=0xffff888004098500, buf=buf@entry=0xa758d0 ":iiiii:E::ii::i:CF
", count=count@entry=19, pos=pos@entry=0xffffc9000022ff10) at fs/read_write.c:603
13 0xffffffff811defda in ksys_write (fd=<optimized out>, buf=0xa758d0 ":iiiii:E::ii::i:CF
", count=19) at fs/read_write.c:658
14 0xffffffff81b49813 in do_syscall_64 (nr=<optimized out>, regs=0xffffc9000022ff58) at arch/x86/entry/common.c:46
15 0xffffffff81c0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120
To solve the issue, the open_exec call is moved to before the write
lock is taken by bm_register_write
Link: https://lkml.kernel.org/r/20210228224414.95962-1-liorribak@gmail.com
Fixes: 948b701a607f1 ("binfmt_misc: add persistent opened binary handler for containers")
Signed-off-by: Lior Ribak <liorribak(a)gmail.com>
Acked-by: Helge Deller <deller(a)gmx.de>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/binfmt_misc.c | 29 ++++++++++++++---------------
1 file changed, 14 insertions(+), 15 deletions(-)
--- a/fs/binfmt_misc.c~binfmt_misc-fix-possible-deadlock-in-bm_register_write
+++ a/fs/binfmt_misc.c
@@ -649,12 +649,24 @@ static ssize_t bm_register_write(struct
struct super_block *sb = file_inode(file)->i_sb;
struct dentry *root = sb->s_root, *dentry;
int err = 0;
+ struct file *f = NULL;
e = create_entry(buffer, count);
if (IS_ERR(e))
return PTR_ERR(e);
+ if (e->flags & MISC_FMT_OPEN_FILE) {
+ f = open_exec(e->interpreter);
+ if (IS_ERR(f)) {
+ pr_notice("register: failed to install interpreter file %s\n",
+ e->interpreter);
+ kfree(e);
+ return PTR_ERR(f);
+ }
+ e->interp_file = f;
+ }
+
inode_lock(d_inode(root));
dentry = lookup_one_len(e->name, root, strlen(e->name));
err = PTR_ERR(dentry);
@@ -678,21 +690,6 @@ static ssize_t bm_register_write(struct
goto out2;
}
- if (e->flags & MISC_FMT_OPEN_FILE) {
- struct file *f;
-
- f = open_exec(e->interpreter);
- if (IS_ERR(f)) {
- err = PTR_ERR(f);
- pr_notice("register: failed to install interpreter file %s\n", e->interpreter);
- simple_release_fs(&bm_mnt, &entry_count);
- iput(inode);
- inode = NULL;
- goto out2;
- }
- e->interp_file = f;
- }
-
e->dentry = dget(dentry);
inode->i_private = e;
inode->i_fop = &bm_entry_operations;
@@ -709,6 +706,8 @@ out:
inode_unlock(d_inode(root));
if (err) {
+ if (f)
+ filp_close(f, NULL);
kfree(e);
return err;
}
_
From: Mike Rapoport <rppt(a)linux.ibm.com>
Subject: mm/page_alloc.c: refactor initialization of struct page for holes in memory layout
There could be struct pages that are not backed by actual physical memory.
This can happen when the actual memory bank is not a multiple of
SECTION_SIZE or when an architecture does not register memory holes
reserved by the firmware as memblock.memory.
Such pages are currently initialized using init_unavailable_mem() function
that iterates through PFNs in holes in memblock.memory and if there is a
struct page corresponding to a PFN, the fields of this page are set to
default values and it is marked as Reserved.
init_unavailable_mem() does not take into account zone and node the page
belongs to and sets both zone and node links in struct page to zero.
Before commit 73a6e474cb37 ("mm: memmap_init: iterate over memblock
regions rather that check each PFN") the holes inside a zone were
re-initialized during memmap_init() and got their zone/node links right.
However, after that commit nothing updates the struct pages representing
such holes.
On a system that has firmware reserved holes in a zone above ZONE_DMA, for
instance in a configuration below:
# grep -A1 E820 /proc/iomem
7a17b000-7a216fff : Unknown E820 type
7a217000-7bffffff : System RAM
unset zone link in struct page will trigger
VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
in set_pfnblock_flags_mask() when called with a struct page from a range
other than E820_TYPE_RAM because there are pages in the range of
ZONE_DMA32 but the unset zone link in struct page makes them appear as a
part of ZONE_DMA.
Interleave initialization of the unavailable pages with the normal
initialization of memory map, so that zone and node information will be
properly set on struct pages that are not backed by the actual memory.
With this change the pages for holes inside a zone will get proper
zone/node links and the pages that are not spanned by any node will get
links to the adjacent zone/node. The holes between nodes will be
prepended to the zone/node above the hole and the trailing pages in the
last section that will be appended to the zone/node below.
[akpm(a)linux-foundation.org: don't initialize static to zero, use %llu for u64]
Link: https://lkml.kernel.org/r/20210225224351.7356-2-rppt@kernel.org
Fixes: 73a6e474cb37 ("mm: memmap_init: iterate over memblock regions rather that check each PFN")
Signed-off-by: Mike Rapoport <rppt(a)linux.ibm.com>
Reported-by: Qian Cai <cai(a)lca.pw>
Reported-by: Andrea Arcangeli <aarcange(a)redhat.com>
Reviewed-by: Baoquan He <bhe(a)redhat.com>
Acked-by: Vlastimil Babka <vbabka(a)suse.cz>
Reviewed-by: David Hildenbrand <david(a)redhat.com>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: "H. Peter Anvin" <hpa(a)zytor.com>
Cc: Łukasz Majczak <lma(a)semihalf.com>
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Mel Gorman <mgorman(a)suse.de>
Cc: Michal Hocko <mhocko(a)kernel.org>
Cc: "Sarvela, Tomi P" <tomi.p.sarvela(a)intel.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/page_alloc.c | 158 +++++++++++++++++++++-------------------------
1 file changed, 75 insertions(+), 83 deletions(-)
--- a/mm/page_alloc.c~mm-page_allocc-refactor-initialization-of-struct-page-for-holes-in-memory-layout
+++ a/mm/page_alloc.c
@@ -6259,12 +6259,65 @@ static void __meminit zone_init_free_lis
}
}
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ * arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ * nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ * hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ * the zone boundary; the pages in such holes will be prepended to the
+ * zone/node above the hole except for the trailing pages in the last
+ * section that will be appended to the zone/node below.
+ */
+static u64 __meminit init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
+{
+ unsigned long pfn;
+ u64 pgcnt = 0;
+
+ for (pfn = spfn; pfn < epfn; pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+ pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+ + pageblock_nr_pages - 1;
+ continue;
+ }
+ __init_single_page(pfn_to_page(pfn), pfn, zone, node);
+ __SetPageReserved(pfn_to_page(pfn));
+ pgcnt++;
+ }
+
+ return pgcnt;
+}
+#else
+static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn,
+ int zone, int node)
+{
+ return 0;
+}
+#endif
+
void __meminit __weak memmap_init_zone(struct zone *zone)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+ static unsigned long hole_pfn;
unsigned long start_pfn, end_pfn;
+ u64 pgcnt = 0;
for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
@@ -6274,7 +6327,29 @@ void __meminit __weak memmap_init_zone(s
memmap_init_range(end_pfn - start_pfn, nid,
zone_id, start_pfn, zone_end_pfn,
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+ if (hole_pfn < start_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, start_pfn,
+ zone_id, nid);
+ hole_pfn = end_pfn;
}
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Initialize the hole in the range [zone_end_pfn, section_end].
+ * If zone boundary falls in the middle of a section, this hole
+ * will be re-initialized during the call to this function for the
+ * higher zone.
+ */
+ end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION);
+ if (hole_pfn < end_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, end_pfn,
+ zone_id, nid);
+#endif
+
+ if (pgcnt)
+ pr_info(" %s zone: %llu pages in unavailable ranges\n",
+ zone->name, pgcnt);
}
static int zone_batchsize(struct zone *zone)
@@ -7071,88 +7146,6 @@ void __init free_area_init_memoryless_no
free_area_init_node(nid);
}
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Initialize all valid struct pages in the range [spfn, epfn) and mark them
- * PageReserved(). Return the number of struct pages that were initialized.
- */
-static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
-{
- unsigned long pfn;
- u64 pgcnt = 0;
-
- for (pfn = spfn; pfn < epfn; pfn++) {
- if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
- pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
- + pageblock_nr_pages - 1;
- continue;
- }
- /*
- * Use a fake node/zone (0) for now. Some of these pages
- * (in memblock.reserved but not in memblock.memory) will
- * get re-initialized via reserve_bootmem_region() later.
- */
- __init_single_page(pfn_to_page(pfn), pfn, 0, 0);
- __SetPageReserved(pfn_to_page(pfn));
- pgcnt++;
- }
-
- return pgcnt;
-}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly initialize those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-static void __init init_unavailable_mem(void)
-{
- phys_addr_t start, end;
- u64 i, pgcnt;
- phys_addr_t next = 0;
-
- /*
- * Loop through unavailable ranges not covered by memblock.memory.
- */
- pgcnt = 0;
- for_each_mem_range(i, &start, &end) {
- if (next < start)
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- PFN_UP(start));
- next = end;
- }
-
- /*
- * Early sections always have a fully populated memmap for the whole
- * section - see pfn_valid(). If the last section has holes at the
- * end and that section is marked "online", the memmap will be
- * considered initialized. Make sure that memmap has a well defined
- * state.
- */
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- round_up(max_pfn, PAGES_PER_SECTION));
-
- /*
- * Struct pages that do not have backing memory. This could be because
- * firmware is using some of this memory, or for some other reasons.
- */
- if (pgcnt)
- pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#else
-static inline void __init init_unavailable_mem(void)
-{
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
#if MAX_NUMNODES > 1
/*
* Figure out the number of possible node ids.
@@ -7576,7 +7569,6 @@ void __init free_area_init(unsigned long
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- init_unavailable_mem();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
free_area_init_node(nid);
_