Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2022-07-22

We've added 73 non-merge commits during the last 12 day(s) which contain
a total of 88 files changed, 3458 insertions(+), 860 deletions(-).

The main changes are:

1) Implement BPF trampoline for arm64 JIT, from Xu Kuohai.

2) Add ksyscall/kretsyscall section support to libbpf to simplify tracing kernel
   syscalls through kprobe mechanism, from Andrii Nakryiko.

3) Allow for livepatch (KLP) and BPF trampolines to attach to the same kernel
   function, from Song Liu & Jiri Olsa.

4) Add new kfunc infrastructure for netfilter's CT e.g. to insert and change
   entries, from Kumar Kartikeya Dwivedi & Lorenzo Bianconi.

5) Add a ksym BPF iterator to allow for more flexible and efficient interactions
   with kernel symbols, from Alan Maguire.

6) Bug fixes in libbpf e.g. for uprobe binary path resolution, from Dan Carpenter.

7) Fix BPF subprog function names in stack traces, from Alexei Starovoitov.

8) libbpf support for writing custom perf event readers, from Jon Doron.

9) Switch to use SPDX tag for BPF helper man page, from Alejandro Colomar.

10) Fix xsk send-only sockets when in busy poll mode, from Maciej Fijalkowski.

11) Reparent BPF maps and their charging on memcg offlining, from Roman Gushchin.

12) Multiple follow-up fixes around BPF lsm cgroup infra, from Stanislav Fomichev.

13) Use bootstrap version of bpftool where possible to speed up builds, from Pu Lehui.

14) Cleanup BPF verifier's check_func_arg() handling, from Joanne Koong.

15) Make non-prealloced BPF map allocations low priority to play better with
    memcg limits, from Yafang Shao.

16) Fix BPF test runner to reject zero-length data for skbs, from Zhengchao Shao.

17) Various smaller cleanups and improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (73 commits)
  bpf: Simplify bpf_prog_pack_[size|mask]
  bpf: Support bpf_trampoline on functions with IPMODIFY (e.g. livepatch)
  bpf, x64: Allow to use caller address from stack
  ftrace: Allow IPMODIFY and DIRECT ops on the same function
  ftrace: Add modify_ftrace_direct_multi_nolock
  bpf/selftests: Fix couldn't retrieve pinned program in xdp veth test
  bpf: Fix build error in case of !CONFIG_DEBUG_INFO_BTF
  selftests/bpf: Fix test_verifier failed test in unprivileged mode
  selftests/bpf: Add negative tests for new nf_conntrack kfuncs
  selftests/bpf: Add tests for new nf_conntrack kfuncs
  selftests/bpf: Add verifier tests for trusted kfunc args
  net: netfilter: Add kfuncs to set and change CT status
  net: netfilter: Add kfuncs to set and change CT timeout
  net: netfilter: Add kfuncs to allocate and insert CT
  net: netfilter: Deduplicate code in bpf_{xdp,skb}_ct_lookup
  bpf: Add documentation for kfuncs
  bpf: Add support for forcing kfunc args to be trusted
  bpf: Switch to new kfunc flags infrastructure
  tools/resolve_btfids: Add support for 8-byte BTF sets
  bpf: Introduce 8-byte BTF set
  ...
====================

Link: https://lore.kernel.org/r/20220722221218.29943-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 29 insertions, 71 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index bfeb9b937315..c1e10d088dbb 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -652,12 +652,6 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
 	return fp->jited && !bpf_prog_was_classic(fp);
 }
 
-static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
-{
-	return list_empty(&fp->aux->ksym.lnode) ||
-	       fp->aux->ksym.lnode.prev == LIST_POISON2;
-}
-
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
 	if (!bpf_prog_kallsyms_candidate(fp) ||
@@ -833,15 +827,6 @@ struct bpf_prog_pack {
 
 #define BPF_PROG_SIZE_TO_NBITS(size)	(round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE)
 
-static size_t bpf_prog_pack_size = -1;
-static size_t bpf_prog_pack_mask = -1;
-
-static 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);
 
@@ -849,55 +834,33 @@ static LIST_HEAD(pack_list);
  * CONFIG_MMU=n. Use PAGE_SIZE in these cases.
  */
 #ifdef PMD_SIZE
-#define BPF_HPAGE_SIZE PMD_SIZE
-#define BPF_HPAGE_MASK PMD_MASK
+#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes())
 #else
-#define BPF_HPAGE_SIZE PAGE_SIZE
-#define BPF_HPAGE_MASK PAGE_MASK
+#define BPF_PROG_PACK_SIZE PAGE_SIZE
 #endif
 
-static size_t select_bpf_prog_pack_size(void)
-{
-	size_t size;
-	void *ptr;
-
-	size = BPF_HPAGE_SIZE * num_online_nodes();
-	ptr = module_alloc(size);
-
-	/* Test whether we can get huge pages. If not just use PAGE_SIZE
-	 * packs.
-	 */
-	if (!ptr || !is_vm_area_hugepages(ptr)) {
-		size = PAGE_SIZE;
-		bpf_prog_pack_mask = PAGE_MASK;
-	} else {
-		bpf_prog_pack_mask = BPF_HPAGE_MASK;
-	}
-
-	vfree(ptr);
-	return size;
-}
+#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE)
 
 static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns)
 {
 	struct bpf_prog_pack *pack;
 
-	pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(bpf_prog_chunk_count())),
+	pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(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;
 	}
-	bpf_fill_ill_insns(pack->ptr, bpf_prog_pack_size);
-	bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE);
+	bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_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;
 }
 
@@ -909,10 +872,7 @@ static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insn
 	void *ptr = NULL;
 
 	mutex_lock(&pack_mutex);
-	if (bpf_prog_pack_size == -1)
-		bpf_prog_pack_size = select_bpf_prog_pack_size();
-
-	if (size > bpf_prog_pack_size) {
+	if (size > BPF_PROG_PACK_SIZE) {
 		size = round_up(size, PAGE_SIZE);
 		ptr = module_alloc(size);
 		if (ptr) {
@@ -924,9 +884,9 @@ static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insn
 		goto out;
 	}
 	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;
 	}
 
@@ -950,18 +910,15 @@ 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;
 
 	mutex_lock(&pack_mutex);
-	if (hdr->size > bpf_prog_pack_size) {
+	if (hdr->size > BPF_PROG_PACK_SIZE) {
 		module_memfree(hdr);
 		goto out;
 	}
 
-	pack_ptr = (void *)((unsigned long)hdr & bpf_prog_pack_mask);
-
 	list_for_each_entry(tmp, &pack_list, list) {
-		if (tmp->ptr == pack_ptr) {
+		if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) {
 			pack = tmp;
 			break;
 		}
@@ -971,14 +928,14 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 		goto out;
 
 	nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
-	pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT;
+	pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
 
 	WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
 		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
 
 	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);
@@ -1155,7 +1112,6 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
 		bpf_prog_pack_free(ro_header);
 		return PTR_ERR(ptr);
 	}
-	prog->aux->use_bpf_prog_pack = true;
 	return 0;
 }
 
@@ -1179,17 +1135,23 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 	bpf_jit_uncharge_modmem(size);
 }
 
+struct bpf_binary_header *
+bpf_jit_binary_pack_hdr(const struct bpf_prog *fp)
+{
+	unsigned long real_start = (unsigned long)fp->bpf_func;
+	unsigned long addr;
+
+	addr = real_start & BPF_PROG_CHUNK_MASK;
+	return (void *)addr;
+}
+
 static inline struct bpf_binary_header *
 bpf_jit_binary_hdr(const struct bpf_prog *fp)
 {
 	unsigned long real_start = (unsigned long)fp->bpf_func;
 	unsigned long addr;
 
-	if (fp->aux->use_bpf_prog_pack)
-		addr = real_start & BPF_PROG_CHUNK_MASK;
-	else
-		addr = real_start & PAGE_MASK;
-
+	addr = real_start & PAGE_MASK;
 	return (void *)addr;
 }
 
@@ -1202,11 +1164,7 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		if (fp->aux->use_bpf_prog_pack)
-			bpf_jit_binary_pack_free(hdr, NULL /* rw_buffer */);
-		else
-			bpf_jit_binary_free(hdr);
-
+		bpf_jit_binary_free(hdr);
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
 	}