Re: [linux-next:master] [mm] 0fa2857d23: WARNING:at_mm/page_alloc.c:#__alloc_pages_noprof

[Usama Arif <usamaarif642@gmail.com>]

On 24/06/2024 20:31, Yosry Ahmed wrote:
> On Mon, Jun 24, 2024 at 10:26 AM Usama Arif <usamaarif642@gmail.com> wrote:
>>
>> On 24/06/2024 19:56, Yosry Ahmed wrote:
>>> [..]
>>>>>> -       p->zeromap = bitmap_zalloc(maxpages, GFP_KERNEL);
>>>>>> +       p->zeromap = kvzalloc(DIV_ROUND_UP(maxpages, 8), GFP_KERNEL);
>>>>> No, 8 is not right for 32-bit kernels. I think you want
>>>>>         p->zeromap = kvzalloc(BITS_TO_LONGS(maxpages), GFP_KERNEL);
>>>>> but please check it carefully, I'm easily confused by such conversions.
>>>>>
>>>>> Hugh
>>>> Ah yes, didnt take into account 32-bit kernel. I think its supposed to be
>>>>
>>>>     p->zeromap = kvzalloc(BITS_TO_LONGS(maxpages) * sizeof(unsigned long),
>>>> GFP_KERNEL);
>>> You can do something similar to bitmap_zalloc() and use:
>>>
>>> kvmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), GFP_KERNEL
>>> | __GFP_ZERO)
>>>
>>> I don't see a kvzalloc_array() variant to use directly, but it should
>>> be trivial to add it. I can see other users of kvmalloc_array() that
>>> pass in __GFP_ZERO (e.g. fs/ntfs3/bitmap.c).
>>>
>>> , or you could take it a step further and add bitmap_kvzalloc(),
>>> assuming the maintainers are open to that.
>> Thanks! bitmap_kvzalloc makes most sense to me. It doesnt make sense
>> that bitmap should only be limited to MAX_PAGE_ORDER size. I can add
>> this patch below at the start of the series and use it in the patch for
>> zeropage swap optimization.
>>
>>
>>       bitmap: add support for virtually contiguous bitmap
>>
>>       The current bitmap_zalloc API limits the allocation to MAX_PAGE_ORDER,
>>       which prevents larger order bitmap allocations. Introduce
>>       bitmap_kvzalloc that will allow larger allocations of bitmap.
>>       kvmalloc_array still attempts to allocate physically contiguous memory,
>>       but upon failure, falls back to non-contiguous (vmalloc) allocation.
>>
>>       Suggested-by: Yosry Ahmed <yosryahmed@google.com>
>>       Signed-off-by: Usama Arif <usamaarif642@gmail.com>
>>
> LGTM with a small fix below.
>
>> diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
>> index 8c4768c44a01..881c2ff2e834 100644
>> --- a/include/linux/bitmap.h
>> +++ b/include/linux/bitmap.h
>> @@ -131,9 +131,11 @@ struct device;
>>     */
>>    unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags);
>>    unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags);
>> +unsigned long *bitmap_kvzalloc(unsigned int nbits, gfp_t flags);
>>    unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int
>> node);
>>    unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int
>> node);
>>    void bitmap_free(const unsigned long *bitmap);
>> +void bitmap_kvfree(const unsigned long *bitmap);
>>
>>    DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T))
>>
>> diff --git a/lib/bitmap.c b/lib/bitmap.c
>> index b97692854966..eabbfb85fb45 100644
>> --- a/lib/bitmap.c
>> +++ b/lib/bitmap.c
>> @@ -727,6 +727,13 @@ unsigned long *bitmap_zalloc(unsigned int nbits,
>> gfp_t flags)
>>    }
>>    EXPORT_SYMBOL(bitmap_zalloc);
>>
>> +unsigned long *bitmap_kvzalloc(unsigned int nbits, gfp_t flags)
>> +{
>> +       return kvmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long),
>> +                             flags | __GFP_ZERO);
>> +}
>> +EXPORT_SYMBOL(bitmap_zalloc);
> EXPORT_SYMBOL(bitmap_kvzalloc)*


Actually, does it make more sense to change the behaviour of the current 
APIs like below instead of above patch? Or is there an expectation that 
the current bitmap API is supposed to work only on physically contiguous 
bits?

I believe in the kernel if the allocation/free starts with 'k' its 
physically contiguous and with "kv" its physically contiguous if 
possible, otherwise virtually contiguous. The bitmap functions dont have 
either, so we could change the current implementation. I believe it 
would not impact the current users of the functions as the first attempt 
is physically contiguous which is how it works currently, and only upon 
failure it would be virtual and it would increase the use of current 
bitmap API to greater than MAX_PAGE_ORDER size allocations.

Yury Norov and Rasmus Villemoes, any views on this?

Thanks

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 7247e217e21b..ad771dc81afa 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -804,6 +804,7 @@ kvmalloc_array_node_noprof(size_t n, size_t size, 
gfp_t flags, int node)
  #define kvcalloc_node_noprof(_n,_s,_f,_node) 
kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node)
  #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, 
NUMA_NO_NODE)

+#define kvmalloc_array_node(...) 
alloc_hooks(kvmalloc_array_node_noprof(__VA_ARGS__))
  #define kvmalloc_array(...) 
alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__))
  #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__))
  #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__))
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b97692854966..272164dcbef1 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -716,7 +716,7 @@ void bitmap_fold(unsigned long *dst, const unsigned 
long *orig,

  unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags)
  {
-       return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long),
+       return kvmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long),
                              flags);
  }
  EXPORT_SYMBOL(bitmap_alloc);
@@ -729,7 +729,7 @@ EXPORT_SYMBOL(bitmap_zalloc);

  unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int 
node)
  {
-       return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned 
long),
+       return kvmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned 
long),
                                   flags, node);
  }
  EXPORT_SYMBOL(bitmap_alloc_node);
@@ -742,7 +742,7 @@ EXPORT_SYMBOL(bitmap_zalloc_node);

  void bitmap_free(const unsigned long *bitmap)
  {
-       kfree(bitmap);
+       kvfree(bitmap);
  }
  EXPORT_SYMBOL(bitmap_free);