diff options
author | 2022-02-04 10:57:40 -0800 | |
---|---|---|
committer | 2022-02-07 18:13:01 -0800 | |
commit | 57631054fae6dcc9c892ae6310b58bbb6f6e5048 (patch) | |
tree | cbc2dd82f7767f68f07b404e2eb354a9002f1280 | |
parent | bpf: Introduce bpf_arch_text_copy (diff) | |
download | linux-57631054fae6dcc9c892ae6310b58bbb6f6e5048.tar.gz linux-57631054fae6dcc9c892ae6310b58bbb6f6e5048.tar.bz2 linux-57631054fae6dcc9c892ae6310b58bbb6f6e5048.zip |
bpf: Introduce bpf_prog_pack allocator
Most BPF programs are small, but they consume a page each. For systems
with busy traffic and many BPF programs, this could add significant
pressure to instruction TLB. High iTLB pressure usually causes slow down
for the whole system, which includes visible performance degradation for
production workloads.
Introduce bpf_prog_pack allocator to pack multiple BPF programs in a huge
page. The memory is then allocated in 64 byte chunks.
Memory allocated by bpf_prog_pack allocator is RO protected after initial
allocation. To write to it, the user (jit engine) need to use text poke
API.
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220204185742.271030-8-song@kernel.org
-rw-r--r-- | kernel/bpf/core.c | 127 |
1 files changed, 127 insertions, 0 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a5ec480f9862..7ae590897b73 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -805,6 +805,133 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, return slot; } +/* + * BPF program pack allocator. + * + * Most BPF programs are pretty small. Allocating a hole page for each + * program is sometime a waste. Many small bpf program also adds pressure + * to instruction TLB. To solve this issue, we introduce a BPF program pack + * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) + * to host BPF programs. + */ +#define BPF_PROG_PACK_SIZE HPAGE_PMD_SIZE +#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)]; +}; + +#define BPF_PROG_MAX_PACK_PROG_SIZE HPAGE_PMD_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 struct bpf_prog_pack *alloc_new_pack(void) +{ + struct bpf_prog_pack *pack; + + pack = kzalloc(sizeof(*pack), GFP_KERNEL); + if (!pack) + return NULL; + pack->ptr = module_alloc(BPF_PROG_PACK_SIZE); + if (!pack->ptr) { + kfree(pack); + return NULL; + } + 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); + return pack; +} + +static void *bpf_prog_pack_alloc(u32 size) +{ + unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); + struct bpf_prog_pack *pack; + unsigned long pos; + void *ptr = NULL; + + if (size > BPF_PROG_MAX_PACK_PROG_SIZE) { + size = round_up(size, PAGE_SIZE); + ptr = module_alloc(size); + if (ptr) { + set_vm_flush_reset_perms(ptr); + set_memory_ro((unsigned long)ptr, size / PAGE_SIZE); + set_memory_x((unsigned long)ptr, size / PAGE_SIZE); + } + return ptr; + } + 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, + nbits, 0); + if (pos < BPF_PROG_CHUNK_COUNT) + goto found_free_area; + } + + pack = alloc_new_pack(); + if (!pack) + goto out; + + pos = 0; + +found_free_area: + bitmap_set(pack->bitmap, pos, nbits); + ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); + +out: + mutex_unlock(&pack_mutex); + return ptr; +} + +static void bpf_prog_pack_free(struct bpf_binary_header *hdr) +{ + struct bpf_prog_pack *pack = NULL, *tmp; + unsigned int nbits; + unsigned long pos; + void *pack_ptr; + + if (hdr->size > BPF_PROG_MAX_PACK_PROG_SIZE) { + module_memfree(hdr); + return; + } + + pack_ptr = (void *)((unsigned long)hdr & ~(BPF_PROG_PACK_SIZE - 1)); + mutex_lock(&pack_mutex); + + list_for_each_entry(tmp, &pack_list, list) { + if (tmp->ptr == pack_ptr) { + pack = tmp; + break; + } + } + + if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) + goto out; + + nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); + 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) { + list_del(&pack->list); + module_memfree(pack->ptr); + kfree(pack); + } +out: + mutex_unlock(&pack_mutex); +} + static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, |