mm/memory_hotplug.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
We can't use kfree() to release the resource as it might come from bootmem.
Use release_mem_region() instead.
Fixes: ebff7d8f270d ("mem hotunplug: fix kfree() of bootmem memory")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
---
mm/memory_hotplug.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 7dc7e12302db..dc570772b4b1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -216,8 +216,7 @@ static void release_memory_resource(struct resource *res)
{
if (!res)
return;
- release_resource(res);
- kfree(res);
+ release_mem_region(res->start, resource_size(res));
}
static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
--
2.23.0
On 07.02.22 14:56, Miaohe Lin wrote: > We can't use kfree() to release the resource as it might come from bootmem. > Use release_mem_region() instead. How can this happen? release_mem_region() is called either from __add_memory() or from add_memory_driver_managed(), where we allocated the region via register_memory_resource(). Both functions shouldn't ever be called before the buddy is up an running. Do you have a backtrace of an actual instance of this issue? Or was this identified as possibly broken by code inspection? -- Thanks, David / dhildenb
Hi:
On 2022/2/7 22:33, David Hildenbrand wrote:
> On 07.02.22 14:56, Miaohe Lin wrote:
>> We can't use kfree() to release the resource as it might come from bootmem.
>> Use release_mem_region() instead.
>
> How can this happen? release_mem_region() is called either from
> __add_memory() or from add_memory_driver_managed(), where we allocated
> the region via register_memory_resource(). Both functions shouldn't ever
> be called before the buddy is up an running.
>
> Do you have a backtrace of an actual instance of this issue? Or was this
> identified as possibly broken by code inspection?
>
This is identified as possibly broken by code inspection. IIUC, alloc_resource
is always used to allocate the resource. It has the below logic:
if (bootmem_resource_free) {
res = bootmem_resource_free;
bootmem_resource_free = res->sibling;
}
where bootmem_resource_free is used to reusing the resource entries allocated by boot
mem after the system is up:
/*
* For memory hotplug, there is no way to free resource entries allocated
* by boot mem after the system is up. So for reusing the resource entry
* we need to remember the resource.
*/
static struct resource *bootmem_resource_free;
So I think register_memory_resource() can reuse the resource allocated by bootmem.
Or am I miss anything?
Thanks.
On 08.02.22 02:59, Miaohe Lin wrote:
> Hi:
> On 2022/2/7 22:33, David Hildenbrand wrote:
>> On 07.02.22 14:56, Miaohe Lin wrote:
>>> We can't use kfree() to release the resource as it might come from bootmem.
>>> Use release_mem_region() instead.
>>
>> How can this happen? release_mem_region() is called either from
>> __add_memory() or from add_memory_driver_managed(), where we allocated
>> the region via register_memory_resource(). Both functions shouldn't ever
>> be called before the buddy is up an running.
>>
>> Do you have a backtrace of an actual instance of this issue? Or was this
>> identified as possibly broken by code inspection?
>>
>
> This is identified as possibly broken by code inspection. IIUC, alloc_resource
> is always used to allocate the resource. It has the below logic:
>
> if (bootmem_resource_free) {
> res = bootmem_resource_free;
> bootmem_resource_free = res->sibling;
> }
>
> where bootmem_resource_free is used to reusing the resource entries allocated by boot
> mem after the system is up:
>
> /*
> * For memory hotplug, there is no way to free resource entries allocated
> * by boot mem after the system is up. So for reusing the resource entry
> * we need to remember the resource.
> */
> static struct resource *bootmem_resource_free;
>
> So I think register_memory_resource() can reuse the resource allocated by bootmem.
> Or am I miss anything?
I think you're right, if we did a previous free_resource() of a resource allocated
during boot we could end up reusing that here. My best guess is that this never
really happens.
Wow, that's ugly. It affects essentially anybody reserving+freeing a resource.
E.g., dax/kmem.c similarly does a release_resource(res)+kfree(res)
We could either
a) Expose free_resource() and replace all kfree(res) instances by it
b) Just simplify that. I don't think we care about saving a couple of
bytes in corner cases. I might be wrong (IIRC primarily ppc64 really
succeeds in unplugging boot memory)
diff --git a/kernel/resource.c b/kernel/resource.c
index 9c08d6e9eef2..fe91a72fd951 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -56,14 +56,6 @@ struct resource_constraint {
static DEFINE_RWLOCK(resource_lock);
-/*
- * For memory hotplug, there is no way to free resource entries allocated
- * by boot mem after the system is up. So for reusing the resource entry
- * we need to remember the resource.
- */
-static struct resource *bootmem_resource_free;
-static DEFINE_SPINLOCK(bootmem_resource_lock);
-
static struct resource *next_resource(struct resource *p)
{
if (p->child)
@@ -160,36 +152,19 @@ __initcall(ioresources_init);
static void free_resource(struct resource *res)
{
- if (!res)
- return;
-
- if (!PageSlab(virt_to_head_page(res))) {
- spin_lock(&bootmem_resource_lock);
- res->sibling = bootmem_resource_free;
- bootmem_resource_free = res;
- spin_unlock(&bootmem_resource_lock);
- } else {
+ /*
+ * If the resource was allocated using memblock early during boot
+ * we'll leak it here: we can only return full pages back to the
+ * buddy and trying to be smart and reusing them eventually in
+ * alloc_resource() overcomplicates resource handling.
+ */
+ if (res && PageSlab(virt_to_head_page(res)))
kfree(res);
- }
}
static struct resource *alloc_resource(gfp_t flags)
{
- struct resource *res = NULL;
-
- spin_lock(&bootmem_resource_lock);
- if (bootmem_resource_free) {
- res = bootmem_resource_free;
- bootmem_resource_free = res->sibling;
- }
- spin_unlock(&bootmem_resource_lock);
-
- if (res)
- memset(res, 0, sizeof(struct resource));
- else
- res = kzalloc(sizeof(struct resource), flags);
-
- return res;
+ return kzalloc(sizeof(struct resource), flags);
}
/* Return the conflict entry if you can't request it */
--
Thanks,
David / dhildenb
On 2022/2/8 17:19, David Hildenbrand wrote:
> On 08.02.22 02:59, Miaohe Lin wrote:
>> Hi:
>> On 2022/2/7 22:33, David Hildenbrand wrote:
>>> On 07.02.22 14:56, Miaohe Lin wrote:
>>>> We can't use kfree() to release the resource as it might come from bootmem.
>>>> Use release_mem_region() instead.
>>>
>>> How can this happen? release_mem_region() is called either from
>>> __add_memory() or from add_memory_driver_managed(), where we allocated
>>> the region via register_memory_resource(). Both functions shouldn't ever
>>> be called before the buddy is up an running.
>>>
>>> Do you have a backtrace of an actual instance of this issue? Or was this
>>> identified as possibly broken by code inspection?
>>>
>>
>> This is identified as possibly broken by code inspection. IIUC, alloc_resource
>> is always used to allocate the resource. It has the below logic:
>>
>> if (bootmem_resource_free) {
>> res = bootmem_resource_free;
>> bootmem_resource_free = res->sibling;
>> }
>>
>> where bootmem_resource_free is used to reusing the resource entries allocated by boot
>> mem after the system is up:
>>
>> /*
>> * For memory hotplug, there is no way to free resource entries allocated
>> * by boot mem after the system is up. So for reusing the resource entry
>> * we need to remember the resource.
>> */
>> static struct resource *bootmem_resource_free;
>>
>> So I think register_memory_resource() can reuse the resource allocated by bootmem.
>> Or am I miss anything?
>
> I think you're right, if we did a previous free_resource() of a resource allocated
> during boot we could end up reusing that here. My best guess is that this never
> really happens.
>
Agree with you. This reusing mechanism is introduced since 2013 and this possible
issue never happens.
> Wow, that's ugly. It affects essentially anybody reserving+freeing a resource.
>
> E.g., dax/kmem.c similarly does a release_resource(res)+kfree(res)
>
>
> We could either
>
> a) Expose free_resource() and replace all kfree(res) instances by it
>
> b) Just simplify that. I don't think we care about saving a couple of
> bytes in corner cases. I might be wrong (IIRC primarily ppc64 really
> succeeds in unplugging boot memory)
>
I prefer this one or there will be a huge change if we choose a.
I will drop my patch and below patch looks good to me.
Many thanks!
>
> diff --git a/kernel/resource.c b/kernel/resource.c
> index 9c08d6e9eef2..fe91a72fd951 100644
> --- a/kernel/resource.c
> +++ b/kernel/resource.c
> @@ -56,14 +56,6 @@ struct resource_constraint {
>
> static DEFINE_RWLOCK(resource_lock);
>
> -/*
> - * For memory hotplug, there is no way to free resource entries allocated
> - * by boot mem after the system is up. So for reusing the resource entry
> - * we need to remember the resource.
> - */
> -static struct resource *bootmem_resource_free;
> -static DEFINE_SPINLOCK(bootmem_resource_lock);
> -
> static struct resource *next_resource(struct resource *p)
> {
> if (p->child)
> @@ -160,36 +152,19 @@ __initcall(ioresources_init);
>
> static void free_resource(struct resource *res)
> {
> - if (!res)
> - return;
> -
> - if (!PageSlab(virt_to_head_page(res))) {
> - spin_lock(&bootmem_resource_lock);
> - res->sibling = bootmem_resource_free;
> - bootmem_resource_free = res;
> - spin_unlock(&bootmem_resource_lock);
> - } else {
> + /*
> + * If the resource was allocated using memblock early during boot
> + * we'll leak it here: we can only return full pages back to the
> + * buddy and trying to be smart and reusing them eventually in
> + * alloc_resource() overcomplicates resource handling.
> + */
> + if (res && PageSlab(virt_to_head_page(res)))
> kfree(res);
> - }
> }
>
> static struct resource *alloc_resource(gfp_t flags)
> {
> - struct resource *res = NULL;
> -
> - spin_lock(&bootmem_resource_lock);
> - if (bootmem_resource_free) {
> - res = bootmem_resource_free;
> - bootmem_resource_free = res->sibling;
> - }
> - spin_unlock(&bootmem_resource_lock);
> -
> - if (res)
> - memset(res, 0, sizeof(struct resource));
> - else
> - res = kzalloc(sizeof(struct resource), flags);
> -
> - return res;
> + return kzalloc(sizeof(struct resource), flags);
> }
>
> /* Return the conflict entry if you can't request it */
>
>
© 2016 - 2026 Red Hat, Inc.