Merge tag 'bpf-next-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Support pulling non-linear xdp data with bpf_xdp_pull_data() kfunc
   (Amery Hung)

   Applied as a stable branch in bpf-next and net-next trees.

 - Support reading skb metadata via bpf_dynptr (Jakub Sitnicki)

   Also a stable branch in bpf-next and net-next trees.

 - Enforce expected_attach_type for tailcall compatibility (Daniel
   Borkmann)

 - Replace path-sensitive with path-insensitive live stack analysis in
   the verifier (Eduard Zingerman)

   This is a significant change in the verification logic. More details,
   motivation, long term plans are in the cover letter/merge commit.

 - Support signed BPF programs (KP Singh)

   This is another major feature that took years to materialize.

   Algorithm details are in the cover letter/marge commit

 - Add support for may_goto instruction to s390 JIT (Ilya Leoshkevich)

 - Add support for may_goto instruction to arm64 JIT (Puranjay Mohan)

 - Fix USDT SIB argument handling in libbpf (Jiawei Zhao)

 - Allow uprobe-bpf program to change context registers (Jiri Olsa)

 - Support signed loads from BPF arena (Kumar Kartikeya Dwivedi and
   Puranjay Mohan)

 - Allow access to union arguments in tracing programs (Leon Hwang)

 - Optimize rcu_read_lock() + migrate_disable() combination where it's
   used in BPF subsystem (Menglong Dong)

 - Introduce bpf_task_work_schedule*() kfuncs to schedule deferred
   execution of BPF callback in the context of a specific task using the
   kernel’s task_work infrastructure (Mykyta Yatsenko)

 - Enforce RCU protection for KF_RCU_PROTECTED kfuncs (Kumar Kartikeya
   Dwivedi)

 - Add stress test for rqspinlock in NMI (Kumar Kartikeya Dwivedi)

 - Improve the precision of tnum multiplier verifier operation
   (Nandakumar Edamana)

 - Use tnums to improve is_branch_taken() logic (Paul Chaignon)

 - Add support for atomic operations in arena in riscv JIT (Pu Lehui)

 - Report arena faults to BPF error stream (Puranjay Mohan)

 - Search for tracefs at /sys/kernel/tracing first in bpftool (Quentin
   Monnet)

 - Add bpf_strcasecmp() kfunc (Rong Tao)

 - Support lookup_and_delete_elem command in BPF_MAP_STACK_TRACE (Tao
   Chen)

* tag 'bpf-next-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (197 commits)
  libbpf: Replace AF_ALG with open coded SHA-256
  selftests/bpf: Add stress test for rqspinlock in NMI
  selftests/bpf: Add test case for different expected_attach_type
  bpf: Enforce expected_attach_type for tailcall compatibility
  bpftool: Remove duplicate string.h header
  bpf: Remove duplicate crypto/sha2.h header
  libbpf: Fix error when st-prefix_ops and ops from differ btf
  selftests/bpf: Test changing packet data from kfunc
  selftests/bpf: Add stacktrace map lookup_and_delete_elem test case
  selftests/bpf: Refactor stacktrace_map case with skeleton
  bpf: Add lookup_and_delete_elem for BPF_MAP_STACK_TRACE
  selftests/bpf: Fix flaky bpf_cookie selftest
  selftests/bpf: Test changing packet data from global functions with a kfunc
  bpf: Emit struct bpf_xdp_sock type in vmlinux BTF
  selftests/bpf: Task_work selftest cleanup fixes
  MAINTAINERS: Delete inactive maintainers from AF_XDP
  bpf: Mark kfuncs as __noclone
  selftests/bpf: Add kprobe multi write ctx attach test
  selftests/bpf: Add kprobe write ctx attach test
  selftests/bpf: Add uprobe context ip register change test
  ...

1 files changed, 16 insertions, 44 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e4568d44e827..d595fe512498 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -18,6 +18,7 @@
  */
 
 #include <uapi/linux/btf.h>
+#include <crypto/sha1.h>
 #include <linux/filter.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
@@ -38,6 +39,7 @@
 #include <linux/bpf_mem_alloc.h>
 #include <linux/memcontrol.h>
 #include <linux/execmem.h>
+#include <crypto/sha2.h>
 
 #include <asm/barrier.h>
 #include <linux/unaligned.h>
@@ -119,6 +121,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 
 	fp->pages = size / PAGE_SIZE;
 	fp->aux = aux;
+	fp->aux->main_prog_aux = aux;
 	fp->aux->prog = fp;
 	fp->jit_requested = ebpf_jit_enabled();
 	fp->blinding_requested = bpf_jit_blinding_enabled(fp);
@@ -293,28 +296,18 @@ void __bpf_prog_free(struct bpf_prog *fp)
 
 int bpf_prog_calc_tag(struct bpf_prog *fp)
 {
-	const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64);
-	u32 raw_size = bpf_prog_tag_scratch_size(fp);
-	u32 digest[SHA1_DIGEST_WORDS];
-	u32 ws[SHA1_WORKSPACE_WORDS];
-	u32 i, bsize, psize, blocks;
+	size_t size = bpf_prog_insn_size(fp);
 	struct bpf_insn *dst;
 	bool was_ld_map;
-	u8 *raw, *todo;
-	__be32 *result;
-	__be64 *bits;
+	u32 i;
 
-	raw = vmalloc(raw_size);
-	if (!raw)
+	dst = vmalloc(size);
+	if (!dst)
 		return -ENOMEM;
 
-	sha1_init_raw(digest);
-	memset(ws, 0, sizeof(ws));
-
 	/* We need to take out the map fd for the digest calculation
 	 * since they are unstable from user space side.
 	 */
-	dst = (void *)raw;
 	for (i = 0, was_ld_map = false; i < fp->len; i++) {
 		dst[i] = fp->insnsi[i];
 		if (!was_ld_map &&
@@ -334,33 +327,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 			was_ld_map = false;
 		}
 	}
-
-	psize = bpf_prog_insn_size(fp);
-	memset(&raw[psize], 0, raw_size - psize);
-	raw[psize++] = 0x80;
-
-	bsize  = round_up(psize, SHA1_BLOCK_SIZE);
-	blocks = bsize / SHA1_BLOCK_SIZE;
-	todo   = raw;
-	if (bsize - psize >= sizeof(__be64)) {
-		bits = (__be64 *)(todo + bsize - sizeof(__be64));
-	} else {
-		bits = (__be64 *)(todo + bsize + bits_offset);
-		blocks++;
-	}
-	*bits = cpu_to_be64((psize - 1) << 3);
-
-	while (blocks--) {
-		sha1_transform(digest, todo, ws);
-		todo += SHA1_BLOCK_SIZE;
-	}
-
-	result = (__force __be32 *)digest;
-	for (i = 0; i < SHA1_DIGEST_WORDS; i++)
-		result[i] = cpu_to_be32(digest[i]);
-	memcpy(fp->tag, result, sizeof(fp->tag));
-
-	vfree(raw);
+	sha256((u8 *)dst, size, fp->digest);
+	vfree(dst);
 	return 0;
 }
 
@@ -2393,6 +2361,7 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 		map->owner->type  = prog_type;
 		map->owner->jited = fp->jited;
 		map->owner->xdp_has_frags = aux->xdp_has_frags;
+		map->owner->expected_attach_type = fp->expected_attach_type;
 		map->owner->attach_func_proto = aux->attach_func_proto;
 		for_each_cgroup_storage_type(i) {
 			map->owner->storage_cookie[i] =
@@ -2404,6 +2373,10 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 		ret = map->owner->type  == prog_type &&
 		      map->owner->jited == fp->jited &&
 		      map->owner->xdp_has_frags == aux->xdp_has_frags;
+		if (ret &&
+		    map->map_type == BPF_MAP_TYPE_PROG_ARRAY &&
+		    map->owner->expected_attach_type != fp->expected_attach_type)
+			ret = false;
 		for_each_cgroup_storage_type(i) {
 			if (!ret)
 				break;
@@ -3329,9 +3302,8 @@ static bool find_from_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp)
 	rcu_read_unlock();
 	if (!prog)
 		return true;
-	if (bpf_is_subprog(prog))
-		return true;
-	ctxp->prog = prog;
+	/* Make sure we return the main prog if we found a subprog */
+	ctxp->prog = prog->aux->main_prog_aux->prog;
 	return false;
 }