> On Feb 11, 2022, at 11:42 AM, Song Liu <songliubraving@xxxxxx> wrote:
>
>
>
>> On Feb 11, 2022, at 6:35 AM, Daniel Borkmann <daniel@xxxxxxxxxxxxx> wrote:
>>
>> On 2/10/22 5:51 PM, Song Liu wrote:
>>>> On Feb 10, 2022, at 12:25 AM, Daniel Borkmann <daniel@xxxxxxxxxxxxx> wrote:
>>>> On 2/10/22 7:41 AM, Song Liu wrote:
>>>>> bpf_prog_pack uses huge pages to reduce pressue on instruction TLB.
>>>>> To guarantee allocating huge pages for bpf_prog_pack, it is necessary to
>>>>> allocate memory of size PMD_SIZE * num_online_nodes().
>>>>> On the other hand, if the system doesn't support huge pages, it is more
>>>>> efficient to allocate PAGE_SIZE bpf_prog_pack.
>>>>> Address different scenarios with more flexible bpf_prog_pack_size().
>>>>> Signed-off-by: Song Liu <song@xxxxxxxxxx>
>>>>> ---
>>>>> kernel/bpf/core.c | 47 +++++++++++++++++++++++++++--------------------
>>>>> 1 file changed, 27 insertions(+), 20 deletions(-)
>>>>> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
>>>>> index 42d96549a804..d961a1f07a13 100644
>>>>> --- a/kernel/bpf/core.c
>>>>> +++ b/kernel/bpf/core.c
>>>>> @@ -814,46 +814,53 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
>>>>> * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86)
>>>>> * to host BPF programs.
>>>>> */
>>>>> -#ifdef CONFIG_TRANSPARENT_HUGEPAGE
>>>>> -#define BPF_PROG_PACK_SIZE HPAGE_PMD_SIZE
>>>>> -#else
>>>>> -#define BPF_PROG_PACK_SIZE PAGE_SIZE
>>>>> -#endif
>>>>> #define BPF_PROG_CHUNK_SHIFT 6
>>>>> #define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT)
>>>>> #define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1))
>>>>> -#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE)
>>>>> struct bpf_prog_pack {
>>>>> struct list_head list;
>>>>> void *ptr;
>>>>> - unsigned long bitmap[BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)];
>>>>> + unsigned long bitmap[];
>>>>> };
>>>>> -#define BPF_PROG_MAX_PACK_PROG_SIZE BPF_PROG_PACK_SIZE
>>>>> #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE)
>>>>> static DEFINE_MUTEX(pack_mutex);
>>>>> static LIST_HEAD(pack_list);
>>>>> +static inline int bpf_prog_pack_size(void)
>>>>> +{
>>>>> + /* If vmap_allow_huge == true, use pack size of the smallest
>>>>> + * possible vmalloc huge page: PMD_SIZE * num_online_nodes().
>>>>> + * Otherwise, use pack size of PAGE_SIZE.
>>>>> + */
>>>>> + return get_vmap_allow_huge() ? PMD_SIZE * num_online_nodes() : PAGE_SIZE;
>>>>> +}
>>>>
>>>> Imho, this is making too many assumptions about implementation details. Can't we
>>>> just add a new module_alloc*() API instead which internally guarantees allocating
>>>> huge pages when enabled/supported (e.g. with a __weak function as fallback)?
>>> I agree that this is making too many assumptions. But a new module_alloc_huge()
>>> may not work, because we need the caller to know the proper size to ask for.
>>> (Or maybe I misunderstood your suggestion?)
>>> How about we introduce something like
>>> /* minimal size to get huge pages from vmalloc. If not possible,
>>> * return 0 (or -1?)
>>> */
>>> int vmalloc_hpage_min_size(void)
>>> {
>>> return vmap_allow_huge ? PMD_SIZE * num_online_nodes() : 0;
>>> }
>>
>> And that would live inside mm/vmalloc.c and is exported to users ...
>
> Yeah, this will go to vmalloc.c.
>
>>
>>> /* minimal size to get huge pages from module_alloc */
>>> int module_alloc_hpage_min_size(void)
>>> {
>>> return vmalloc_hpage_min_size();
>>> }
>>
>> ... and this one as wrapper in module alloc infra with __weak attr?
>
> And this goes to some module.c file(s). I am not quite sure whether we
> need __weak attr or not.
>
>>
>>> static inline int bpf_prog_pack_size(void)
>>> {
>>> return module_alloc_hpage_min_size() ? : PAGE_SIZE;
>>> }
>>
>> Could probably work. It's not nice, but at least in the corresponding places so it's
>> not exposed / hard coded inside bpf and assuming implementation details which could
>> potentially break later on.
>
> I don't really like it either.
>
> Another way to do this is to test the required size for bpf_prog_pack
> in BPF code, something like the following. The pro of this version is
> that we don't need changes in vmalloc and module code.
Hi Daniel,
Do you have further suggestions on this? I personally like the following
version best, as all the changes are limited to bpf/core.c.
Thanks,
Song
> diff --git i/kernel/bpf/core.c w/kernel/bpf/core.c
> index 44623c9b5bb1..3cfd0f0c93d2 100644
> --- i/kernel/bpf/core.c
> +++ w/kernel/bpf/core.c
> @@ -814,15 +814,9 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
> * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86)
> * to host BPF programs.
> */
> -#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -#define BPF_PROG_PACK_SIZE HPAGE_PMD_SIZE
> -#else
> -#define BPF_PROG_PACK_SIZE PAGE_SIZE
> -#endif
> #define BPF_PROG_CHUNK_SHIFT 6
> #define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT)
> #define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1))
> -#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE)
>
> struct bpf_prog_pack {
> struct list_head list;
> @@ -830,30 +824,56 @@ struct bpf_prog_pack {
> unsigned long bitmap[];
> };
>
> -#define BPF_PROG_MAX_PACK_PROG_SIZE BPF_PROG_PACK_SIZE
> #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE)
>
> +static int bpf_prog_pack_size = -1;
> +
> +static inline int bpf_prog_chunk_count(void)
> +{
> + WARN_ON_ONCE(bpf_prog_pack_size == -1);
> + return bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE;
> +}
> +
> static DEFINE_MUTEX(pack_mutex);
> static LIST_HEAD(pack_list);
>
> static struct bpf_prog_pack *alloc_new_pack(void)
> {
> struct bpf_prog_pack *pack;
> + void *ptr;
> + int size;
>
> - pack = kzalloc(sizeof(*pack) + BITS_TO_BYTES(BPF_PROG_CHUNK_COUNT), GFP_KERNEL);
> - if (!pack)
> + /* Test whether we can get huge pages. If not just use PAGE_SIZE
> + * packs.
> + */
> + if (bpf_prog_pack_size == -1) {
> + size = PMD_SIZE * num_online_nodes();
> + ptr = module_alloc(size);
> + if (is_vm_area_hugepages(ptr)) {
> + bpf_prog_pack_size = size;
> + goto got_ptr;
> + } else {
> + bpf_prog_pack_size = PAGE_SIZE;
> + vfree(ptr);
> + }
> + }
> +
> + ptr = module_alloc(bpf_prog_pack_size);
> + if (!ptr)
> return NULL;
> - pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
> - if (!pack->ptr) {
> - kfree(pack);
> +got_ptr:
> + pack = kzalloc(sizeof(*pack) + BITS_TO_BYTES(bpf_prog_chunk_count()), GFP_KERNEL);
> + if (!pack) {
> + vfree(ptr);
> return NULL;
> }
> - bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE);
> + pack->ptr = ptr;
> + bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE);
> list_add_tail(&pack->list, &pack_list);
>
> set_vm_flush_reset_perms(pack->ptr);
> - set_memory_ro((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
> - set_memory_x((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
> + set_memory_ro((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
> + set_memory_x((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
> return pack;
> }
>
> @@ -864,7 +884,7 @@ static void *bpf_prog_pack_alloc(u32 size)
> unsigned long pos;
> void *ptr = NULL;
>
> - if (size > BPF_PROG_MAX_PACK_PROG_SIZE) {
> + if (size > bpf_prog_pack_size) {
> size = round_up(size, PAGE_SIZE);
> ptr = module_alloc(size);
> if (ptr) {
> @@ -876,9 +896,9 @@ static void *bpf_prog_pack_alloc(u32 size)
> }
> mutex_lock(&pack_mutex);
> list_for_each_entry(pack, &pack_list, list) {
> - pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
> + pos = bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
> nbits, 0);
> - if (pos < BPF_PROG_CHUNK_COUNT)
> + if (pos < bpf_prog_chunk_count())
> goto found_free_area;
> }
>
> @@ -904,12 +924,12 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
> unsigned long pos;
> void *pack_ptr;
>
> - if (hdr->size > BPF_PROG_MAX_PACK_PROG_SIZE) {
> + if (hdr->size > bpf_prog_pack_size) {
> module_memfree(hdr);
> return;
> }
>
> - pack_ptr = (void *)((unsigned long)hdr & ~(BPF_PROG_PACK_SIZE - 1));
> + pack_ptr = (void *)((unsigned long)hdr & ~(bpf_prog_pack_size - 1));
> mutex_lock(&pack_mutex);
>
> list_for_each_entry(tmp, &pack_list, list) {
> @@ -926,8 +946,8 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
> pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT;
>
> bitmap_clear(pack->bitmap, pos, nbits);
> - if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
> - BPF_PROG_CHUNK_COUNT, 0) == 0) {
> + if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
> + bpf_prog_chunk_count(), 0) == 0) {
> list_del(&pack->list);
> module_memfree(pack->ptr);
> kfree(pack);
>
>
