bpf-for-netdev

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCZUsiDAAKCRDbK58LschI
 g9xXAQCaFjj55sXDpr1qKG2D3PMSDURx7SzmpzIay/A/dqVDPgEAlgU6XsMW6w6S
 poMN8KniDLtBgj6nIKfJEAgIXeIYTAs=
 =qXjW
 -----END PGP SIGNATURE-----

Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-11-08

We've added 16 non-merge commits during the last 6 day(s) which contain
a total of 30 files changed, 341 insertions(+), 130 deletions(-).

The main changes are:

1) Fix a BPF verifier issue in precision tracking for BPF_ALU | BPF_TO_BE |
   BPF_END where the source register was incorrectly marked as precise,
   from Shung-Hsi Yu.

2) Fix a concurrency issue in bpf_timer where the former could still have
   been alive after an application releases or unpins the map, from Hou Tao.

3) Fix a BPF verifier issue where immediates are incorrectly cast to u32
   before being spilled and therefore losing sign information, from Hao Sun.

4) Fix a misplaced BPF_TRACE_ITER in check_css_task_iter_allowlist which
   incorrectly compared bpf_prog_type with bpf_attach_type, from Chuyi Zhou.

5) Add __bpf_hook_{start,end} as well as __bpf_kfunc_{start,end}_defs macros,
   migrate all BPF-related __diag callsites over to it, and add a new
   __diag_ignore_all for -Wmissing-declarations to the macros to address
   recent build warnings, from Dave Marchevsky.

6) Fix broken BPF selftest build of xdp_hw_metadata test on architectures
   where char is not signed, from Björn Töpel.

7) Fix test_maps selftest to properly use LIBBPF_OPTS() macro to initialize
   the bpf_map_create_opts, from Andrii Nakryiko.

8) Fix bpffs selftest to avoid unmounting /sys/kernel/debug as it may have
   been mounted and used by other applications already, from Manu Bretelle.

9) Fix a build issue without CONFIG_CGROUPS wrt css_task open-coded
   iterators, from Matthieu Baerts.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: get trusted cgrp from bpf_iter__cgroup directly
  bpf: Let verifier consider {task,cgroup} is trusted in bpf_iter_reg
  selftests/bpf: Fix broken build where char is unsigned
  selftests/bpf: precision tracking test for BPF_NEG and BPF_END
  bpf: Fix precision tracking for BPF_ALU | BPF_TO_BE | BPF_END
  selftests/bpf: Add test for using css_task iter in sleepable progs
  selftests/bpf: Add tests for css_task iter combining with cgroup iter
  bpf: Relax allowlist for css_task iter
  selftests/bpf: fix test_maps' use of bpf_map_create_opts
  bpf: Check map->usercnt after timer->timer is assigned
  bpf: Add __bpf_hook_{start,end} macros
  bpf: Add __bpf_kfunc_{start,end}_defs macros
  selftests/bpf: fix test_bpffs
  selftests/bpf: Add test for immediate spilled to stack
  bpf: Fix check_stack_write_fixed_off() to correctly spill imm
  bpf: fix compilation error without CGROUPS
====================

Link: https://lore.kernel.org/r/20231108132448.1970-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

@@ -39,9 +39,7 @@ struct bpf_testmod_struct_arg_4 {
 	int b;
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in bpf_testmod.ko BTF");
+__bpf_hook_start();
 
 noinline int
 bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
@@ -335,7 +333,7 @@ noinline int bpf_fentry_shadow_test(int a)
 }
 EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test);
 
-__diag_pop();
+__bpf_hook_end();
 
 static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.attr = { .name = "bpf_testmod", .mode = 0666, },

tools/testing/selftests/bpf/map_tests/map_percpu_stats.c

@@ -326,20 +326,14 @@ static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *
 
 static int create_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
 }
 
 static int create_percpu_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
 }
@@ -356,21 +350,17 @@ static int create_percpu_hash_prealloc(void)
 
 static int create_lru_hash(__u32 type, __u32 map_flags)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = map_flags,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = map_flags);
 
 	return map_create(type, "lru_hash", &map_opts);
 }
 
 static int create_hash_of_maps(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
 		.map_flags = BPF_F_NO_PREALLOC,
 		.inner_map_fd = create_small_hash(),
-	};
+	);
 	int ret;
 
 	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",

tools/testing/selftests/bpf/prog_tests/cgroup_iter.c

@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include "iters_css_task.skel.h"
 #include "cgroup_iter.skel.h"
 #include "cgroup_helpers.h"
 
@@ -263,6 +264,35 @@ close_cgrp:
 	close(cgrp_fd);
 }
 
+static void test_walk_self_only_css_task(void)
+{
+	struct iters_css_task *skel;
+	int err;
+
+	skel = iters_css_task__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);
+
+	err = iters_css_task__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = join_cgroup(cg_path[CHILD2]);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	snprintf(expected_output, sizeof(expected_output),
+		PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
+		BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+cleanup:
+	iters_css_task__destroy(skel);
+}
+
 void test_cgroup_iter(void)
 {
 	struct cgroup_iter *skel = NULL;
@@ -293,6 +323,9 @@ void test_cgroup_iter(void)
 		test_walk_self_only(skel);
 	if (test__start_subtest("cgroup_iter__dead_self_only"))
 		test_walk_dead_self_only(skel);
+	if (test__start_subtest("cgroup_iter__self_only_css_task"))
+		test_walk_self_only_css_task();
+
 out:
 	cgroup_iter__destroy(skel);
 	cleanup_cgroups();

tools/testing/selftests/bpf/prog_tests/iters.c

@@ -294,6 +294,7 @@ void test_iters(void)
 	RUN_TESTS(iters_state_safety);
 	RUN_TESTS(iters_looping);
 	RUN_TESTS(iters);
+	RUN_TESTS(iters_css_task);
 
 	if (env.has_testmod)
 		RUN_TESTS(iters_testmod_seq);

tools/testing/selftests/bpf/prog_tests/test_bpffs.c

@@ -8,7 +8,8 @@
 #include <sys/types.h>
 #include <test_progs.h>
 
-#define TDIR "/sys/kernel/debug"
+/* TDIR must be in a location we can create a directory in. */
+#define TDIR "/tmp/test_bpffs_testdir"
 
 static int read_iter(char *file)
 {
@@ -43,8 +44,11 @@ static int fn(void)
 	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
-	err = umount(TDIR);
-	if (!ASSERT_OK(err, "umount " TDIR))
+	err =  mkdir(TDIR, 0777);
+	/* If the directory already exists we can carry on. It may be left over
+	 * from a previous run.
+	 */
+	if ((err && errno != EEXIST) && !ASSERT_OK(err, "mkdir " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
@@ -138,6 +142,7 @@ out:
 	rmdir(TDIR "/fs1");
 	rmdir(TDIR "/fs2");
 	umount(TDIR);
+	rmdir(TDIR);
 	exit(err);
 }
 

tools/testing/selftests/bpf/prog_tests/verifier.c

@@ -46,6 +46,7 @@
 #include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
+#include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
 #include "verifier_raw_stack.skel.h"
 #include "verifier_raw_tp_writable.skel.h"
@@ -153,6 +154,7 @@ void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
 void test_verifier_raw_stack(void)            { RUN(verifier_raw_stack); }
 void test_verifier_raw_tp_writable(void)      { RUN(verifier_raw_tp_writable); }

tools/testing/selftests/bpf/progs/iters_css_task.c

@@ -10,6 +10,7 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
 struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
 void bpf_cgroup_release(struct cgroup *p) __ksym;
 
@@ -45,3 +46,57 @@ int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
 
 	return -EPERM;
 }
+
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+	return cgrp->kn->id;
+}
+
+SEC("?iter/cgroup")
+int cgroup_id_printer(struct bpf_iter__cgroup *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct cgroup *cgrp = ctx->cgroup;
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	/* epilogue */
+	if (cgrp == NULL) {
+		BPF_SEQ_PRINTF(seq, "epilogue\n");
+		return 0;
+	}
+
+	/* prologue */
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "prologue\n");
+
+	BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp));
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+		if (task->pid == target_pid)
+			css_task_cnt++;
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int BPF_PROG(iter_css_task_for_each_sleep)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}

tools/testing/selftests/bpf/progs/iters_task_failure.c

@@ -84,8 +84,8 @@ int BPF_PROG(iter_css_lock_and_unlock)
 	return 0;
 }
 
-SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs")
 int BPF_PROG(iter_css_task_for_each)
 {
 	u64 cg_id = bpf_get_current_cgroup_id();

tools/testing/selftests/bpf/progs/verifier_precision.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 SUSE LLC */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0xfffffff8 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (87) r2 = -r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 8")
+__naked int bpf_neg(void)
+{
+	asm volatile (
+		"r2 = 8;"
+		"r2 = -r2;"
+		"if r2 != -8 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d4) r2 = le16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_le(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = le16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (dc) r2 = be16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_be(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = be16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	__clang_major__ >= 18
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d7) r2 = bswap16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_bswap(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = bswap16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#endif /* v4 instruction */

tools/testing/selftests/bpf/verifier/bpf_st_mem.c

@@ -65,3 +65,35 @@
 	.expected_attach_type = BPF_SK_LOOKUP,
 	.runs = -1,
 },
+{
+	"BPF_ST_MEM stack imm sign",
+	/* Check if verifier correctly reasons about sign of an
+	 * immediate spilled to stack by BPF_ST instruction.
+	 *
+	 *   fp[-8] = -44;
+	 *   r0 = fp[-8];
+	 *   if r0 s< 0 goto ret0;
+	 *   r0 = -1;
+	 *   exit;
+	 * ret0:
+	 *   r0 = 0;
+	 *   exit;
+	 */
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, -44),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, -1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.result = VERBOSE_ACCEPT,
+	.runs = -1,
+	.errstr = "0: (7a) *(u64 *)(r10 -8) = -44        ; R10=fp0 fp-8_w=-44\
+	2: (c5) if r0 s< 0x0 goto pc+2\
+	R0_w=-44",
+},

tools/testing/selftests/bpf/xdp_hw_metadata.c

@@ -430,7 +430,7 @@ static void print_usage(void)
 
 static void read_args(int argc, char *argv[])
 {
-	char opt;
+	int opt;
 
 	while ((opt = getopt(argc, argv, "mh")) != -1) {
 		switch (opt) {