* [PATCH v2] mm/vmalloc: fix data race in show_numa_info()
@ 2025-05-06 8:25 Jeongjun Park
2025-05-06 11:55 ` Uladzislau Rezki
0 siblings, 1 reply; 3+ messages in thread
From: Jeongjun Park @ 2025-05-06 8:25 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
==================================================================
According to this report, there is a read/write data-race because m->private
is accessible to multiple CPUs. To fix this, instead of allocating the heap
in proc_vmalloc_init() and passing the heap address to m->private,
show_numa_info() should allocate the heap.
One thing to note is that show_numa_info() is called in a critical section
of a spinlock, so it must be allocated on the heap with GFP_ATOMIC flag.
Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
---
v2: Refactoring some functions and fix patch as per Eric Dumazet suggestion
- Link to v1: https://lore.kernel.org/all/20250505171948.24410-1-aha310510@gmail.com/
---
mm/vmalloc.c | 50 +++++++++++++++++++++++++-------------------------
1 file changed, 25 insertions(+), 25 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a787ec..a5e795346141 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -4914,28 +4914,32 @@ bool vmalloc_dump_obj(void *object)
#endif
#ifdef CONFIG_PROC_FS
+
+/*
+ * Print number of pages allocated on each memory node.
+ *
+ * This function can only be called if CONFIG_NUMA is enabled
+ * and VM_UNINITIALIZED bit in v->flags is disabled.
+ */
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 step = 1U << vm_area_page_order(v);
+ unsigned int nr, *counters;
+ unsigned int step = 1U << vm_area_page_order(v);
- if (!counters)
- return;
+ counters = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_ATOMIC);
+ if (!counters)
+ return;
- if (v->flags & VM_UNINITIALIZED)
- return;
- /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
- smp_rmb();
+ /* 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]);
- 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);
}
static void show_purge_info(struct seq_file *m)
@@ -5013,7 +5017,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
if (is_vmalloc_addr(v->pages))
seq_puts(m, " vpages");
- show_numa_info(m, v);
+ if (!(v->flags & VM_UNINITIALIZED) &&
+ IS_ENABLED(CONFIG_NUMA))
+ show_numa_info(m, v);
+
seq_putc(m, '\n');
}
spin_unlock(&vn->busy.lock);
@@ -5028,14 +5035,7 @@ 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;
}
module_init(proc_vmalloc_init);
--
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] mm/vmalloc: fix data race in show_numa_info()
2025-05-06 8:25 [PATCH v2] mm/vmalloc: fix data race in show_numa_info() Jeongjun Park
@ 2025-05-06 11:55 ` Uladzislau Rezki
2025-05-07 13:07 ` Jeongjun Park
0 siblings, 1 reply; 3+ messages in thread
From: Uladzislau Rezki @ 2025-05-06 11:55 UTC (permalink / raw)
To: Jeongjun Park; +Cc: akpm, urezki, edumazet, linux-mm, linux-kernel
On Tue, May 06, 2025 at 05:25:19PM +0900, Jeongjun Park wrote:
> 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
> ==================================================================
>
> According to this report, there is a read/write data-race because m->private
> is accessible to multiple CPUs. To fix this, instead of allocating the heap
> in proc_vmalloc_init() and passing the heap address to m->private,
> show_numa_info() should allocate the heap.
>
> One thing to note is that show_numa_info() is called in a critical section
> of a spinlock, so it must be allocated on the heap with GFP_ATOMIC flag.
>
> Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information")
> Suggested-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Jeongjun Park <aha310510@gmail.com>
> ---
> v2: Refactoring some functions and fix patch as per Eric Dumazet suggestion
> - Link to v1: https://lore.kernel.org/all/20250505171948.24410-1-aha310510@gmail.com/
> ---
> mm/vmalloc.c | 50 +++++++++++++++++++++++++-------------------------
> 1 file changed, 25 insertions(+), 25 deletions(-)
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 3ed720a787ec..a5e795346141 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -4914,28 +4914,32 @@ bool vmalloc_dump_obj(void *object)
> #endif
>
> #ifdef CONFIG_PROC_FS
> +
> +/*
> + * Print number of pages allocated on each memory node.
> + *
> + * This function can only be called if CONFIG_NUMA is enabled
> + * and VM_UNINITIALIZED bit in v->flags is disabled.
> + */
> 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 step = 1U << vm_area_page_order(v);
> + unsigned int nr, *counters;
> + unsigned int step = 1U << vm_area_page_order(v);
>
> - if (!counters)
> - return;
> + counters = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_ATOMIC);
> + if (!counters)
> + return;
>
> - if (v->flags & VM_UNINITIALIZED)
> - return;
> - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
> - smp_rmb();
> + /* 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]);
>
> - 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);
> }
>
> static void show_purge_info(struct seq_file *m)
> @@ -5013,7 +5017,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
> if (is_vmalloc_addr(v->pages))
> seq_puts(m, " vpages");
>
> - show_numa_info(m, v);
> + if (!(v->flags & VM_UNINITIALIZED) &&
>
I think it makes sense to move the VM_UNINITIALIZED check before:
<snip>
v = va->vm;
seq_printf(m, "0x%pK-0x%pK %7ld",
v->addr, v->addr + v->size, v->size);
<snip>
because it can be still un-initialized, thus flags like "nr_pages", etc
will not be valid.
Any thoughts? It has nothing to do with a patch, because it fixes other
race issue and what i propose might well be a separate patch if we agree.
Thanks!
--
Uladzislau Rezki
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] mm/vmalloc: fix data race in show_numa_info()
2025-05-06 11:55 ` Uladzislau Rezki
@ 2025-05-07 13:07 ` Jeongjun Park
0 siblings, 0 replies; 3+ messages in thread
From: Jeongjun Park @ 2025-05-07 13:07 UTC (permalink / raw)
To: Uladzislau Rezki; +Cc: akpm, edumazet, linux-mm, linux-kernel
Uladzislau Rezki <urezki@gmail.com> wrote:
>
> On Tue, May 06, 2025 at 05:25:19PM +0900, Jeongjun Park wrote:
> > 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
> > ==================================================================
> >
> > According to this report, there is a read/write data-race because m->private
> > is accessible to multiple CPUs. To fix this, instead of allocating the heap
> > in proc_vmalloc_init() and passing the heap address to m->private,
> > show_numa_info() should allocate the heap.
> >
> > One thing to note is that show_numa_info() is called in a critical section
> > of a spinlock, so it must be allocated on the heap with GFP_ATOMIC flag.
> >
> > Fixes: a47a126ad5ea ("vmallocinfo: add NUMA information")
> > Suggested-by: Eric Dumazet <edumazet@google.com>
> > Signed-off-by: Jeongjun Park <aha310510@gmail.com>
> > ---
> > v2: Refactoring some functions and fix patch as per Eric Dumazet suggestion
> > - Link to v1: https://lore.kernel.org/all/20250505171948.24410-1-aha310510@gmail.com/
> > ---
> > mm/vmalloc.c | 50 +++++++++++++++++++++++++-------------------------
> > 1 file changed, 25 insertions(+), 25 deletions(-)
> >
> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > index 3ed720a787ec..a5e795346141 100644
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -4914,28 +4914,32 @@ bool vmalloc_dump_obj(void *object)
> > #endif
> >
> > #ifdef CONFIG_PROC_FS
> > +
> > +/*
> > + * Print number of pages allocated on each memory node.
> > + *
> > + * This function can only be called if CONFIG_NUMA is enabled
> > + * and VM_UNINITIALIZED bit in v->flags is disabled.
> > + */
> > 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 step = 1U << vm_area_page_order(v);
> > + unsigned int nr, *counters;
> > + unsigned int step = 1U << vm_area_page_order(v);
> >
> > - if (!counters)
> > - return;
> > + counters = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_ATOMIC);
> > + if (!counters)
> > + return;
> >
> > - if (v->flags & VM_UNINITIALIZED)
> > - return;
> > - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
> > - smp_rmb();
> > + /* 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]);
> >
> > - 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);
> > }
> >
> > static void show_purge_info(struct seq_file *m)
> > @@ -5013,7 +5017,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
> > if (is_vmalloc_addr(v->pages))
> > seq_puts(m, " vpages");
> >
> > - show_numa_info(m, v);
> > + if (!(v->flags & VM_UNINITIALIZED) &&
> >
> I think it makes sense to move the VM_UNINITIALIZED check before:
>
> <snip>
> v = va->vm;
>
> seq_printf(m, "0x%pK-0x%pK %7ld",
> v->addr, v->addr + v->size, v->size);
> <snip>
>
> because it can be still un-initialized, thus flags like "nr_pages", etc
> will not be valid.
>
> Any thoughts? It has nothing to do with a patch, because it fixes other
> race issue and what i propose might well be a separate patch if we agree.
>
> Thanks!
>
> --
> Uladzislau Rezki
That's absolutely correct. If the VM_UNINITIALIZED bit is enabled, it
means there are uninitialized member variables, so printing the vm_struct
information is not very appropriate.
I think it would be better to add the VM_UNINITIALIZED bit check code
right after `v = va->vm;`.
This change isn't that complicated, so I'll add it to the v3 patch and
send it.
Regards,
Jeongjun Park
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2025-05-07 13:07 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2025-05-06 8:25 [PATCH v2] mm/vmalloc: fix data race in show_numa_info() Jeongjun Park
2025-05-06 11:55 ` Uladzislau Rezki
2025-05-07 13:07 ` Jeongjun Park
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox