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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-02-26

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Various improvements for BPF kselftests: i) skip unprivileged tests
   when kernel.unprivileged_bpf_disabled sysctl knob is set, ii) count
   the number of skipped tests from unprivileged, iii) when a test case
   had an unexpected error then print the actual but also the unexpected
   one for better comparison, from Joe.

2) Add a sample program for collecting CPU state statistics with regards
   to how long the CPU resides in cstate and pstate levels. Based on
   cpu_idle and cpu_frequency trace points, from Leo.

3) Various x64 BPF JIT optimizations to further shrink the generated
   image size in order to make it more icache friendly. When tested on
   the Cilium generated programs, image size reduced by approx 4-5% in
   best case mainly due to how LLVM emits unsigned 32 bit constants,
   from Daniel.

4) Improvements and fixes on the BPF sockmap sample programs: i) fix
   the sockmap's Makefile to include nlattr.o for libbpf, ii) detach
   the sock ops programs from the cgroup before exit, from Prashant.

5) Avoid including xdp.h in filter.h by just forward declaring the
   struct xdp_rxq_info in filter.h, from Jesper.

6) Fix the BPF kselftests Makefile for cgroup_helpers.c by only declaring
   it a dependency for test_dev_cgroup.c but not every other test case
   where it is not needed, from Jesper.

7) Adjust rlimit RLIMIT_MEMLOCK for test_tcpbpf_user selftest since the
   default is insufficient for creating the 'global_map' used in the
   corresponding BPF program, from Yonghong.

8) Likewise, for the xdp_redirect sample, Tushar ran into the same when
   invoking xdp_redirect and xdp_monitor at the same time, therefore
   in order to have the sample generically work bump the limit here,
   too. Fix from Tushar.

9) Avoid an unnecessary NULL check in BPF_CGROUP_RUN_PROG_INET_SOCK()
   since sk is always guaranteed to be non-NULL, from Yafang.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 132 insertions, 6 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 5c43c187f27c..8567a858b789 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,12 +35,14 @@ TEST_GEN_PROGS_EXTENDED = test_libbpf_open
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c
+BPFOBJ := $(OUTPUT)/libbpf.a
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
 $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 
+$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+
 .PHONY: force
 
 # force a rebuild of BPFOBJ when its dependencies are updated
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 95a370f3d378..5d73db416460 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -11,6 +11,8 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -42,6 +44,7 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 
 int main(int argc, char **argv)
 {
+	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
 	const char *file = "test_tcpbpf_kern.o";
 	struct tcpbpf_globals g = {0};
 	int cg_fd, prog_fd, map_fd;
@@ -54,6 +57,9 @@ int main(int argc, char **argv)
 	int pid;
 	int rv;
 
+	if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+		perror("Unable to lift memlock rlimit");
+
 	if (argc > 1 && strcmp(argv[1], "-d") == 0)
 		debug_flag = true;
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c73592fa3d41..2164d218322e 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -57,6 +57,9 @@
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 #define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
 
+#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
+static bool unpriv_disabled = false;
+
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
@@ -11163,6 +11166,95 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"jit: lsh, rsh, arsh by 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_IMM(BPF_REG_1, 0xff),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 1),
+			BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x3fc, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 1),
+			BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0xff, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x7f, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: mov32 for ldimm64, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_LD_IMM64(BPF_REG_1, 0xfeffffffffffffffULL),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32),
+			BPF_LD_IMM64(BPF_REG_2, 0xfeffffffULL),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: mov32 for ldimm64, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_LD_IMM64(BPF_REG_1, 0x1ffffffffULL),
+			BPF_LD_IMM64(BPF_REG_2, 0xffffffffULL),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: various mul tests",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+			BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+			BPF_LD_IMM64(BPF_REG_1, 0xefefefULL),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_REG(BPF_REG_2, BPF_REG_2),
+			BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL),
+			BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL),
+			BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -11317,7 +11409,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			goto fail_log;
 		}
 		if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
-			printf("FAIL\nUnexpected error message!\n");
+			printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
+			      expected_err, bpf_vlog);
 			goto fail_log;
 		}
 	}
@@ -11401,9 +11494,20 @@ out:
 	return ret;
 }
 
+static void get_unpriv_disabled()
+{
+	char buf[2];
+	FILE *fd;
+
+	fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+	if (fgets(buf, 2, fd) == buf && atoi(buf))
+		unpriv_disabled = true;
+	fclose(fd);
+}
+
 static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
-	int i, passes = 0, errors = 0;
+	int i, passes = 0, errors = 0, skips = 0;
 
 	for (i = from; i < to; i++) {
 		struct bpf_test *test = &tests[i];
@@ -11411,7 +11515,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 		/* Program types that are not supported by non-root we
 		 * skip right away.
 		 */
-		if (!test->prog_type) {
+		if (!test->prog_type && unpriv_disabled) {
+			printf("#%d/u %s SKIP\n", i, test->descr);
+			skips++;
+		} else if (!test->prog_type) {
 			if (!unpriv)
 				set_admin(false);
 			printf("#%d/u %s ", i, test->descr);
@@ -11420,13 +11527,17 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 				set_admin(true);
 		}
 
-		if (!unpriv) {
+		if (unpriv) {
+			printf("#%d/p %s SKIP\n", i, test->descr);
+			skips++;
+		} else {
 			printf("#%d/p %s ", i, test->descr);
 			do_test_single(test, false, &passes, &errors);
 		}
 	}
 
-	printf("Summary: %d PASSED, %d FAILED\n", passes, errors);
+	printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes,
+	       skips, errors);
 	return errors ? EXIT_FAILURE : EXIT_SUCCESS;
 }
 
@@ -11454,6 +11565,13 @@ int main(int argc, char **argv)
 		}
 	}
 
+	get_unpriv_disabled();
+	if (unpriv && unpriv_disabled) {
+		printf("Cannot run as unprivileged user with sysctl %s.\n",
+		       UNPRIV_SYSCTL);
+		return EXIT_FAILURE;
+	}
+
 	setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf);
 	return do_test(unpriv, from, to);
 }