Merge tag 'bpf-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Remove usermode driver (UMD) framework (Thomas Weißschuh)

 - Introduce Strongly Connected Component (SCC) in the verifier to
   detect loops and refine register liveness (Eduard Zingerman)

 - Allow 'void *' cast using bpf_rdonly_cast() and corresponding
   '__arg_untrusted' for global function parameters (Eduard Zingerman)

 - Improve precision for BPF_ADD and BPF_SUB operations in the verifier
   (Harishankar Vishwanathan)

 - Teach the verifier that constant pointer to a map cannot be NULL
   (Ihor Solodrai)

 - Introduce BPF streams for error reporting of various conditions
   detected by BPF runtime (Kumar Kartikeya Dwivedi)

 - Teach the verifier to insert runtime speculation barrier (lfence on
   x86) to mitigate speculative execution instead of rejecting the
   programs (Luis Gerhorst)

 - Various improvements for 'veristat' (Mykyta Yatsenko)

 - For CONFIG_DEBUG_KERNEL config warn on internal verifier errors to
   improve bug detection by syzbot (Paul Chaignon)

 - Support BPF private stack on arm64 (Puranjay Mohan)

 - Introduce bpf_cgroup_read_xattr() kfunc to read xattr of cgroup's
   node (Song Liu)

 - Introduce kfuncs for read-only string opreations (Viktor Malik)

 - Implement show_fdinfo() for bpf_links (Tao Chen)

 - Reduce verifier's stack consumption (Yonghong Song)

 - Implement mprog API for cgroup-bpf programs (Yonghong Song)

* tag 'bpf-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (192 commits)
  selftests/bpf: Migrate fexit_noreturns case into tracing_failure test suite
  selftests/bpf: Add selftest for attaching tracing programs to functions in deny list
  bpf: Add log for attaching tracing programs to functions in deny list
  bpf: Show precise rejected function when attaching fexit/fmod_ret to __noreturn functions
  bpf: Fix various typos in verifier.c comments
  bpf: Add third round of bounds deduction
  selftests/bpf: Test invariants on JSLT crossing sign
  selftests/bpf: Test cross-sign 64bits range refinement
  selftests/bpf: Update reg_bound range refinement logic
  bpf: Improve bounds when s64 crosses sign boundary
  bpf: Simplify bounds refinement from s32
  selftests/bpf: Enable private stack tests for arm64
  bpf, arm64: JIT support for private stack
  bpf: Move bpf_jit_get_prog_name() to core.c
  bpf, arm64: Fix fp initialization for exception boundary
  umd: Remove usermode driver framework
  bpf/preload: Don't select USERMODE_DRIVER
  selftests/bpf: Fix test dynptr/test_dynptr_memset_xdp_chunks failure
  selftests/bpf: Fix test dynptr/test_dynptr_copy_xdp failure
  selftests/bpf: Increase xdp data size for arm64 64K page size
  ...

1 files changed, 141 insertions, 10 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dae281a1286d..09dde5b00d0c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -134,6 +134,10 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	mutex_init(&fp->aux->ext_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
+#ifdef CONFIG_BPF_SYSCALL
+	bpf_prog_stream_init(fp);
+#endif
+
 	return fp;
 }
 
@@ -778,7 +782,10 @@ bool is_bpf_text_address(unsigned long addr)
 
 struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
 {
-	struct bpf_ksym *ksym = bpf_ksym_find(addr);
+	struct bpf_ksym *ksym;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	ksym = bpf_ksym_find(addr);
 
 	return ksym && ksym->prog ?
 	       container_of(ksym, struct bpf_prog_aux, ksym)->prog :
@@ -1290,6 +1297,13 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 	return 0;
 }
 
+const char *bpf_jit_get_prog_name(struct bpf_prog *prog)
+{
+	if (prog->aux->ksym.prog)
+		return prog->aux->ksym.name;
+	return prog->aux->name;
+}
+
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
 			      struct bpf_insn *to_buff,
@@ -2102,14 +2116,15 @@ out:
 #undef COND_JMP
 	/* ST, STX and LDX*/
 	ST_NOSPEC:
-		/* Speculation barrier for mitigating Speculative Store Bypass.
-		 * In case of arm64, we rely on the firmware mitigation as
-		 * controlled via the ssbd kernel parameter. Whenever the
-		 * mitigation is enabled, it works for all of the kernel code
-		 * with no need to provide any additional instructions here.
-		 * In case of x86, we use 'lfence' insn for mitigation. We
-		 * reuse preexisting logic from Spectre v1 mitigation that
-		 * happens to produce the required code on x86 for v4 as well.
+		/* Speculation barrier for mitigating Speculative Store Bypass,
+		 * Bounds-Check Bypass and Type Confusion. In case of arm64, we
+		 * rely on the firmware mitigation as controlled via the ssbd
+		 * kernel parameter. Whenever the mitigation is enabled, it
+		 * works for all of the kernel code with no need to provide any
+		 * additional instructions here. In case of x86, we use 'lfence'
+		 * insn for mitigation. We reuse preexisting logic from Spectre
+		 * v1 mitigation that happens to produce the required code on
+		 * x86 for v4 as well.
 		 */
 		barrier_nospec();
 		CONT;
@@ -2861,6 +2876,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	aux = container_of(work, struct bpf_prog_aux, work);
 #ifdef CONFIG_BPF_SYSCALL
 	bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab);
+	bpf_prog_stream_free(aux->prog);
 #endif
 #ifdef CONFIG_CGROUP_BPF
 	if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID)
@@ -3034,6 +3050,21 @@ bool __weak bpf_jit_needs_zext(void)
 	return false;
 }
 
+/* By default, enable the verifier's mitigations against Spectre v1 and v4 for
+ * all archs. The value returned must not change at runtime as there is
+ * currently no support for reloading programs that were loaded without
+ * mitigations.
+ */
+bool __weak bpf_jit_bypass_spec_v1(void)
+{
+	return false;
+}
+
+bool __weak bpf_jit_bypass_spec_v4(void)
+{
+	return false;
+}
+
 /* Return true if the JIT inlines the call to the helper corresponding to
  * the imm.
  *
@@ -3144,6 +3175,22 @@ u64 __weak arch_bpf_timed_may_goto(void)
 	return 0;
 }
 
+static noinline void bpf_prog_report_may_goto_violation(void)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	struct bpf_stream_stage ss;
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_find_from_stack();
+	if (!prog)
+		return;
+	bpf_stream_stage(ss, prog, BPF_STDERR, ({
+		bpf_stream_printk(ss, "ERROR: Timeout detected for may_goto instruction\n");
+		bpf_stream_dump_stack(ss);
+	}));
+#endif
+}
+
 u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *p)
 {
 	u64 time = ktime_get_mono_fast_ns();
@@ -3154,8 +3201,10 @@ u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *p)
 		return BPF_MAX_TIMED_LOOPS;
 	}
 	/* Check if we've exhausted our time slice, and zero count. */
-	if (time - p->timestamp >= (NSEC_PER_SEC / 4))
+	if (unlikely(time - p->timestamp >= (NSEC_PER_SEC / 4))) {
+		bpf_prog_report_may_goto_violation();
 		return 0;
+	}
 	/* Refresh the count for the stack frame. */
 	return BPF_MAX_TIMED_LOOPS;
 }
@@ -3192,3 +3241,85 @@ EXPORT_SYMBOL(bpf_stats_enabled_key);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);
+
+#ifdef CONFIG_BPF_SYSCALL
+
+int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep,
+			   const char **linep, int *nump)
+{
+	int idx = -1, insn_start, insn_end, len;
+	struct bpf_line_info *linfo;
+	void **jited_linfo;
+	struct btf *btf;
+	int nr_linfo;
+
+	btf = prog->aux->btf;
+	linfo = prog->aux->linfo;
+	jited_linfo = prog->aux->jited_linfo;
+
+	if (!btf || !linfo || !jited_linfo)
+		return -EINVAL;
+	len = prog->aux->func ? prog->aux->func[prog->aux->func_idx]->len : prog->len;
+
+	linfo = &prog->aux->linfo[prog->aux->linfo_idx];
+	jited_linfo = &prog->aux->jited_linfo[prog->aux->linfo_idx];
+
+	insn_start = linfo[0].insn_off;
+	insn_end = insn_start + len;
+	nr_linfo = prog->aux->nr_linfo - prog->aux->linfo_idx;
+
+	for (int i = 0; i < nr_linfo &&
+	     linfo[i].insn_off >= insn_start && linfo[i].insn_off < insn_end; i++) {
+		if (jited_linfo[i] >= (void *)ip)
+			break;
+		idx = i;
+	}
+
+	if (idx == -1)
+		return -ENOENT;
+
+	/* Get base component of the file path. */
+	*filep = btf_name_by_offset(btf, linfo[idx].file_name_off);
+	*filep = kbasename(*filep);
+	/* Obtain the source line, and strip whitespace in prefix. */
+	*linep = btf_name_by_offset(btf, linfo[idx].line_off);
+	while (isspace(**linep))
+		*linep += 1;
+	*nump = BPF_LINE_INFO_LINE_NUM(linfo[idx].line_col);
+	return 0;
+}
+
+struct walk_stack_ctx {
+	struct bpf_prog *prog;
+};
+
+static bool find_from_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+	struct walk_stack_ctx *ctxp = cookie;
+	struct bpf_prog *prog;
+
+	/*
+	 * The RCU read lock is held to safely traverse the latch tree, but we
+	 * don't need its protection when accessing the prog, since it has an
+	 * active stack frame on the current stack trace, and won't disappear.
+	 */
+	rcu_read_lock();
+	prog = bpf_prog_ksym_find(ip);
+	rcu_read_unlock();
+	if (!prog)
+		return true;
+	if (bpf_is_subprog(prog))
+		return true;
+	ctxp->prog = prog;
+	return false;
+}
+
+struct bpf_prog *bpf_prog_find_from_stack(void)
+{
+	struct walk_stack_ctx ctx = {};
+
+	arch_bpf_stack_walk(find_from_stack_cb, &ctx);
+	return ctx.prog;
+}
+
+#endif