* [PATCH] mm/vmalloc: fix data race in show_numa_info()
@ 2025-05-05 17:19 Jeongjun Park
2025-05-05 18:06 ` Eric Dumazet
0 siblings, 1 reply; 4+ messages in thread
From: Jeongjun Park @ 2025-05-05 17:19 UTC (permalink / raw)
To: akpm; +Cc: urezki, edumazet, linux-mm, linux-kernel, Jeongjun Park
The following data-race was found in show_numa_info():
==================================================================
BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show
read to 0xffff88800971fe30 of 4 bytes by task 8289 on cpu 0:
show_numa_info mm/vmalloc.c:4936 [inline]
vmalloc_info_show+0x5a8/0x7e0 mm/vmalloc.c:5016
seq_read_iter+0x373/0xb40 fs/seq_file.c:230
proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299
new_sync_read fs/read_write.c:489 [inline]
vfs_read+0x5b4/0x740 fs/read_write.c:570
ksys_read+0xbe/0x190 fs/read_write.c:713
__do_sys_read fs/read_write.c:722 [inline]
__se_sys_read fs/read_write.c:720 [inline]
__x64_sys_read+0x41/0x50 fs/read_write.c:720
x64_sys_call+0x1729/0x1fd0 arch/x86/include/generated/asm/syscalls_64.h:1
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xa6/0x1b0 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
write to 0xffff88800971fe30 of 4 bytes by task 8287 on cpu 1:
show_numa_info mm/vmalloc.c:4934 [inline]
vmalloc_info_show+0x38f/0x7e0 mm/vmalloc.c:5016
seq_read_iter+0x373/0xb40 fs/seq_file.c:230
proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299
new_sync_read fs/read_write.c:489 [inline]
vfs_read+0x5b4/0x740 fs/read_write.c:570
ksys_read+0xbe/0x190 fs/read_write.c:713
__do_sys_read fs/read_write.c:722 [inline]
__se_sys_read fs/read_write.c:720 [inline]
__x64_sys_read+0x41/0x50 fs/read_write.c:720
x64_sys_call+0x1729/0x1fd0 arch/x86/include/generated/asm/syscalls_64.h:1
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xa6/0x1b0 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
value changed: 0x0000008f -> 0x00000000
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 UID: 0 PID: 8287 Comm: syz.0.411 Not tainted 6.15.0-rc4-00256-g95d3481af6dc-dirty #1 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
==================================================================
There is a read/write data-race in counter[]. This seems to be happening
because only read memory barriers are currently applied, so we need to
modify the write operation to counters[] to be handled atomically.
Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information")
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
---
mm/vmalloc.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a787ec..d93fa535bc21 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -4917,7 +4917,8 @@ bool vmalloc_dump_obj(void *object)
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
{
if (IS_ENABLED(CONFIG_NUMA)) {
- unsigned int nr, *counters = m->private;
+ atomic_t *counters = m->private;
+ unsigned int nr;
unsigned int step = 1U << vm_area_page_order(v);
if (!counters)
@@ -4931,10 +4932,10 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr += step)
- counters[page_to_nid(v->pages[nr])] += step;
+ atomic_add(step, &counters[page_to_nid(v->pages[nr])]);
for_each_node_state(nr, N_HIGH_MEMORY)
- if (counters[nr])
- seq_printf(m, " N%u=%u", nr, counters[nr]);
+ if (atomic_read(&counters[nr]))
+ seq_printf(m, " N%u=%u", nr, atomic_read(&counters[nr]));
}
}
--
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] mm/vmalloc: fix data race in show_numa_info() 2025-05-05 17:19 [PATCH] mm/vmalloc: fix data race in show_numa_info() Jeongjun Park @ 2025-05-05 18:06 ` Eric Dumazet 2025-05-05 20:09 ` Eric Dumazet 0 siblings, 1 reply; 4+ messages in thread From: Eric Dumazet @ 2025-05-05 18:06 UTC (permalink / raw) To: Jeongjun Park; +Cc: akpm, urezki, linux-mm, linux-kernel On Mon, May 5, 2025 at 10:20 AM Jeongjun Park <aha310510@gmail.com> wrote: > > The following data-race was found in show_numa_info(): > > ================================================================== > BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show > > r > value changed: 0x0000008f -> 0x00000000 > > Reported by Kernel Concurrency Sanitizer on: > CPU: 1 UID: 0 PID: 8287 Comm: syz.0.411 Not tainted 6.15.0-rc4-00256-g95d3481af6dc-dirty #1 PREEMPT(voluntary) > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 > ================================================================== > > There is a read/write data-race in counter[]. This seems to be happening > because only read memory barriers are currently applied, so we need to > modify the write operation to counters[] to be handled atomically. > > Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information") > Signed-off-by: Jeongjun Park <aha310510@gmail.com> > --- > mm/vmalloc.c | 9 +++++---- > 1 file changed, 5 insertions(+), 4 deletions(-) > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > index 3ed720a787ec..d93fa535bc21 100644 > --- a/mm/vmalloc.c > +++ b/mm/vmalloc.c > @@ -4917,7 +4917,8 @@ bool vmalloc_dump_obj(void *object) > static void show_numa_info(struct seq_file *m, struct vm_struct *v) > { > if (IS_ENABLED(CONFIG_NUMA)) { > - unsigned int nr, *counters = m->private; > + atomic_t *counters = m->private; > + unsigned int nr; > unsigned int step = 1U << vm_area_page_order(v); > > if (!counters) > @@ -4931,10 +4932,10 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) > memset(counters, 0, nr_node_ids * sizeof(unsigned int)); > > for (nr = 0; nr < v->nr_pages; nr += step) > - counters[page_to_nid(v->pages[nr])] += step; > + atomic_add(step, &counters[page_to_nid(v->pages[nr])]); > for_each_node_state(nr, N_HIGH_MEMORY) > - if (counters[nr]) > - seq_printf(m, " N%u=%u", nr, counters[nr]); > + if (atomic_read(&counters[nr])) > + seq_printf(m, " N%u=%u", nr, atomic_read(&counters[nr])); > } > } > > -- This patch looks bogus to me. The race is about using m->private for storage, while the same file can be read from multiple threads. Using atomic_t is going to silence syzbot, but the bug is still there. ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] mm/vmalloc: fix data race in show_numa_info() 2025-05-05 18:06 ` Eric Dumazet @ 2025-05-05 20:09 ` Eric Dumazet 2025-05-06 5:44 ` Jeongjun Park 0 siblings, 1 reply; 4+ messages in thread From: Eric Dumazet @ 2025-05-05 20:09 UTC (permalink / raw) To: Jeongjun Park; +Cc: akpm, urezki, linux-mm, linux-kernel On Mon, May 5, 2025 at 11:06 AM Eric Dumazet <edumazet@google.com> wrote: > > On Mon, May 5, 2025 at 10:20 AM Jeongjun Park <aha310510@gmail.com> wrote: > > > > The following data-race was found in show_numa_info(): > > > > ================================================================== > > BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show > > > > r > > value changed: 0x0000008f -> 0x00000000 > > > > Reported by Kernel Concurrency Sanitizer on: > > CPU: 1 UID: 0 PID: 8287 Comm: syz.0.411 Not tainted 6.15.0-rc4-00256-g95d3481af6dc-dirty #1 PREEMPT(voluntary) > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 > > ================================================================== > > > > There is a read/write data-race in counter[]. This seems to be happening > > because only read memory barriers are currently applied, so we need to > > modify the write operation to counters[] to be handled atomically. > > > > Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information") > > Signed-off-by: Jeongjun Park <aha310510@gmail.com> > > --- > > mm/vmalloc.c | 9 +++++---- > > 1 file changed, 5 insertions(+), 4 deletions(-) > > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > > index 3ed720a787ec..d93fa535bc21 100644 > > --- a/mm/vmalloc.c > > +++ b/mm/vmalloc.c > > @@ -4917,7 +4917,8 @@ bool vmalloc_dump_obj(void *object) > > static void show_numa_info(struct seq_file *m, struct vm_struct *v) > > { > > if (IS_ENABLED(CONFIG_NUMA)) { > > - unsigned int nr, *counters = m->private; > > + atomic_t *counters = m->private; > > + unsigned int nr; > > unsigned int step = 1U << vm_area_page_order(v); > > > > if (!counters) > > @@ -4931,10 +4932,10 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) > > memset(counters, 0, nr_node_ids * sizeof(unsigned int)); > > > > for (nr = 0; nr < v->nr_pages; nr += step) > > - counters[page_to_nid(v->pages[nr])] += step; > > + atomic_add(step, &counters[page_to_nid(v->pages[nr])]); > > for_each_node_state(nr, N_HIGH_MEMORY) > > - if (counters[nr]) > > - seq_printf(m, " N%u=%u", nr, counters[nr]); > > + if (atomic_read(&counters[nr])) > > + seq_printf(m, " N%u=%u", nr, atomic_read(&counters[nr])); > > } > > } > > > > -- > > This patch looks bogus to me. > > The race is about using m->private for storage, while the same file > can be read from multiple threads. > > Using atomic_t is going to silence syzbot, but the bug is still there. A more correct fix would be : diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a6e7acebe9adf5e6c8abd52dcf7d02a6a1bc3030..cb69b44587d2032a6192f3ceb518490a05eff541 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4921,24 +4921,24 @@ bool vmalloc_dump_obj(void *object) static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; + unsigned int nr, *counters; unsigned int step = 1U << vm_area_page_order(v); + if (v->flags & VM_UNINITIALIZED) + return; + counters = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); if (!counters) return; - if (v->flags & VM_UNINITIALIZED) - return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); + kfree(counters); } } @@ -5032,13 +5032,7 @@ static int vmalloc_info_show(struct seq_file *m, void *p) static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] mm/vmalloc: fix data race in show_numa_info() 2025-05-05 20:09 ` Eric Dumazet @ 2025-05-06 5:44 ` Jeongjun Park 0 siblings, 0 replies; 4+ messages in thread From: Jeongjun Park @ 2025-05-06 5:44 UTC (permalink / raw) To: Eric Dumazet; +Cc: akpm, urezki, linux-mm, linux-kernel Eric Dumazet <edumazet@google.com> wrote: > > On Mon, May 5, 2025 at 11:06 AM Eric Dumazet <edumazet@google.com> wrote: > > > > On Mon, May 5, 2025 at 10:20 AM Jeongjun Park <aha310510@gmail.com> wrote: > > > > > > The following data-race was found in show_numa_info(): > > > > > > ================================================================== > > > BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show > > > > > > r > > > value changed: 0x0000008f -> 0x00000000 > > > > > > Reported by Kernel Concurrency Sanitizer on: > > > CPU: 1 UID: 0 PID: 8287 Comm: syz.0.411 Not tainted 6.15.0-rc4-00256-g95d3481af6dc-dirty #1 PREEMPT(voluntary) > > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 > > > ================================================================== > > > > > > There is a read/write data-race in counter[]. This seems to be happening > > > because only read memory barriers are currently applied, so we need to > > > modify the write operation to counters[] to be handled atomically. > > > > > > Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information") > > > Signed-off-by: Jeongjun Park <aha310510@gmail.com> > > > --- > > > mm/vmalloc.c | 9 +++++---- > > > 1 file changed, 5 insertions(+), 4 deletions(-) > > > > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > > > index 3ed720a787ec..d93fa535bc21 100644 > > > --- a/mm/vmalloc.c > > > +++ b/mm/vmalloc.c > > > @@ -4917,7 +4917,8 @@ bool vmalloc_dump_obj(void *object) > > > static void show_numa_info(struct seq_file *m, struct vm_struct *v) > > > { > > > if (IS_ENABLED(CONFIG_NUMA)) { > > > - unsigned int nr, *counters = m->private; > > > + atomic_t *counters = m->private; > > > + unsigned int nr; > > > unsigned int step = 1U << vm_area_page_order(v); > > > > > > if (!counters) > > > @@ -4931,10 +4932,10 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) > > > memset(counters, 0, nr_node_ids * sizeof(unsigned int)); > > > > > > for (nr = 0; nr < v->nr_pages; nr += step) > > > - counters[page_to_nid(v->pages[nr])] += step; > > > + atomic_add(step, &counters[page_to_nid(v->pages[nr])]); > > > for_each_node_state(nr, N_HIGH_MEMORY) > > > - if (counters[nr]) > > > - seq_printf(m, " N%u=%u", nr, counters[nr]); > > > + if (atomic_read(&counters[nr])) > > > + seq_printf(m, " N%u=%u", nr, atomic_read(&counters[nr])); > > > } > > > } > > > > > > -- > > > > This patch looks bogus to me. > > > > The race is about using m->private for storage, while the same file > > can be read from multiple threads. > > > > Using atomic_t is going to silence syzbot, but the bug is still there. > > A more correct fix would be : > Thanks for your suggestion! It definitely looks much better this way. I'll do some refactoring on show_numa_info() and send out a v2 patch. Regards, Jeongjun Park > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > index a6e7acebe9adf5e6c8abd52dcf7d02a6a1bc3030..cb69b44587d2032a6192f3ceb518490a05eff541 > 100644 > --- a/mm/vmalloc.c > +++ b/mm/vmalloc.c > @@ -4921,24 +4921,24 @@ bool vmalloc_dump_obj(void *object) > static void show_numa_info(struct seq_file *m, struct vm_struct *v) > { > if (IS_ENABLED(CONFIG_NUMA)) { > - unsigned int nr, *counters = m->private; > + unsigned int nr, *counters; > unsigned int step = 1U << vm_area_page_order(v); > > + if (v->flags & VM_UNINITIALIZED) > + return; > + counters = kcalloc(nr_node_ids, sizeof(unsigned int), > GFP_KERNEL); > if (!counters) > return; > > - if (v->flags & VM_UNINITIALIZED) > - return; > /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ > smp_rmb(); > > - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); > - > for (nr = 0; nr < v->nr_pages; nr += step) > counters[page_to_nid(v->pages[nr])] += step; > for_each_node_state(nr, N_HIGH_MEMORY) > if (counters[nr]) > seq_printf(m, " N%u=%u", nr, counters[nr]); > + kfree(counters); > } > } > > @@ -5032,13 +5032,7 @@ static int vmalloc_info_show(struct seq_file *m, void *p) > > static int __init proc_vmalloc_init(void) > { > - void *priv_data = NULL; > - > - if (IS_ENABLED(CONFIG_NUMA)) > - priv_data = kmalloc(nr_node_ids * sizeof(unsigned > int), GFP_KERNEL); > - > - proc_create_single_data("vmallocinfo", > - 0400, NULL, vmalloc_info_show, priv_data); > + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); > > return 0; > } ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2025-05-06 5:44 UTC | newest] Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2025-05-05 17:19 [PATCH] mm/vmalloc: fix data race in show_numa_info() Jeongjun Park 2025-05-05 18:06 ` Eric Dumazet 2025-05-05 20:09 ` Eric Dumazet 2025-05-06 5:44 ` Jeongjun Park
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox