netdev - [PATCH bpf-next 2/2] bpf: flexible size for bpf_prog

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 9 Feb 2022 22:41:08 -0800
From:   Song Liu <song@...nel.org>
To:     <linux-mm@...ck.org>, <bpf@...r.kernel.org>,
        <netdev@...r.kernel.org>
CC:     <ast@...nel.org>, <daniel@...earbox.net>, <andrii@...nel.org>,
        <kernel-team@...com>, <akpm@...ux-foundation.org>,
        <eric.dumazet@...il.com>, Song Liu <song@...nel.org>
Subject: [PATCH bpf-next 2/2] bpf: flexible size for bpf_prog_pack

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@...nel.org>
---
 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;
+}
+
+static inline int bpf_prog_chunk_count(void)
+{
+	return bpf_prog_pack_size() / BPF_PROG_CHUNK_SIZE;
+}
+
 static struct bpf_prog_pack *alloc_new_pack(void)
 {
 	struct bpf_prog_pack *pack;
 
-	pack = kzalloc(sizeof(*pack), GFP_KERNEL);
+	pack = kzalloc(sizeof(*pack) + BITS_TO_BYTES(bpf_prog_chunk_count()), GFP_KERNEL);
 	if (!pack)
 		return NULL;
-	pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
+	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);
+	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 +871,7 @@ 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 +883,9 @@ 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 +911,12 @@ 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 +933,8 @@ 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);
-- 
2.30.2