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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-04-22

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

The main changes are:

1) allow stack/queue helpers from more bpf program types, from Alban.

2) allow parallel verification of root bpf programs, from Alexei.

3) introduce bpf sysctl hook for trusted root cases, from Andrey.

4) recognize var/datasec in btf deduplication, from Andrii.

5) cpumap performance optimizations, from Jesper.

6) verifier prep for alu32 optimization, from Jiong.

7) libbpf xsk cleanup, from Magnus.

8) other various fixes and cleanups.
====================

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

6 files changed, 79 insertions, 10 deletions

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index bc30783d1403..ff2506fe6bd2 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -92,7 +92,7 @@ struct bpf_load_program_attr {
 #define MAPS_RELAX_COMPAT	0x01
 
 /* Recommend log buffer size */
-#define BPF_LOG_BUF_SIZE (16 * 1024 * 1024) /* verifier maximum in kernels <= 5.1 */
+#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
 LIBBPF_API int
 bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		       char *log_buf, size_t log_buf_sz);
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 701e7e28ada3..75eaf10b9e1a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1354,8 +1354,16 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	}
 	/* special BTF "void" type is made canonical immediately */
 	d->map[0] = 0;
-	for (i = 1; i <= btf->nr_types; i++)
-		d->map[i] = BTF_UNPROCESSED_ID;
+	for (i = 1; i <= btf->nr_types; i++) {
+		struct btf_type *t = d->btf->types[i];
+		__u16 kind = BTF_INFO_KIND(t->info);
+
+		/* VAR and DATASEC are never deduped and are self-canonical */
+		if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC)
+			d->map[i] = i;
+		else
+			d->map[i] = BTF_UNPROCESSED_ID;
+	}
 
 	d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
 	if (!d->hypot_map) {
@@ -1946,6 +1954,8 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_UNION:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FUNC_PROTO:
+	case BTF_KIND_VAR:
+	case BTF_KIND_DATASEC:
 		return 0;
 
 	case BTF_KIND_INT:
@@ -2699,6 +2709,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_VAR:
 		r = btf_dedup_remap_type_id(d, t->type);
 		if (r < 0)
 			return r;
@@ -2753,6 +2764,20 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 		break;
 	}
 
+	case BTF_KIND_DATASEC: {
+		struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1);
+		__u16 vlen = BTF_INFO_VLEN(t->info);
+
+		for (i = 0; i < vlen; i++) {
+			r = btf_dedup_remap_type_id(d, var->type);
+			if (r < 0)
+				return r;
+			var->type = r;
+			var++;
+		}
+		break;
+	}
+
 	default:
 		return -EINVAL;
 	}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 67484cf32b2e..d817bf20f3d6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -817,7 +817,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
 		memcpy(*data_buff, data->d_buf, data->d_size);
 	}
 
-	pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name);
+	pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
 	return 0;
 }
 
@@ -2064,6 +2064,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 		return false;
 	case BPF_PROG_TYPE_KPROBE:
 	default:
@@ -3004,6 +3005,8 @@ static const struct {
 						BPF_CGROUP_UDP4_SENDMSG),
 	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 						BPF_CGROUP_UDP6_SENDMSG),
+	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
+						BPF_CGROUP_SYSCTL),
 };
 
 #undef BPF_PROG_SEC_IMPL
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 8c3a1c04dcb2..0f25541632e3 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -97,6 +97,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	default:
 		break;
 	}
diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
index 81ecda0cb9c9..da94c4cb2e4d 100644
--- a/tools/lib/bpf/libbpf_util.h
+++ b/tools/lib/bpf/libbpf_util.h
@@ -23,6 +23,36 @@ do {				\
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
+/* Use these barrier functions instead of smp_[rw]mb() when they are
+ * used in a libbpf header file. That way they can be built into the
+ * application that uses libbpf.
+ */
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_rmb() asm volatile("" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("" : : : "memory")
+# define libbpf_smp_mb() \
+	asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
+/* Hinders stores to be observed before older loads. */
+# define libbpf_smp_rwmb() asm volatile("" : : : "memory")
+#elif defined(__aarch64__)
+# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#elif defined(__arm__)
+/* These are only valid for armv7 and above */
+# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#else
+/* Architecture missing native barrier functions. */
+# define libbpf_smp_rmb() __sync_synchronize()
+# define libbpf_smp_wmb() __sync_synchronize()
+# define libbpf_smp_mb() __sync_synchronize()
+# define libbpf_smp_rwmb() __sync_synchronize()
+#endif
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index a497f00e2962..82ea71a0f3ec 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -16,6 +16,7 @@
 #include <linux/if_xdp.h>
 
 #include "libbpf.h"
+#include "libbpf_util.h"
 
 #ifdef __cplusplus
 extern "C" {
@@ -36,6 +37,10 @@ struct name { \
 DEFINE_XSK_RING(xsk_ring_prod);
 DEFINE_XSK_RING(xsk_ring_cons);
 
+/* For a detailed explanation on the memory barriers associated with the
+ * ring, please take a look at net/xdp/xsk_queue.h.
+ */
+
 struct xsk_umem;
 struct xsk_socket;
 
@@ -105,7 +110,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
 static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
 					    size_t nb, __u32 *idx)
 {
-	if (unlikely(xsk_prod_nb_free(prod, nb) < nb))
+	if (xsk_prod_nb_free(prod, nb) < nb)
 		return 0;
 
 	*idx = prod->cached_prod;
@@ -116,10 +121,10 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
 
 static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
 {
-	/* Make sure everything has been written to the ring before signalling
-	 * this to the kernel.
+	/* Make sure everything has been written to the ring before indicating
+	 * this to the kernel by writing the producer pointer.
 	 */
-	smp_wmb();
+	libbpf_smp_wmb();
 
 	*prod->producer += nb;
 }
@@ -129,11 +134,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
 {
 	size_t entries = xsk_cons_nb_avail(cons, nb);
 
-	if (likely(entries > 0)) {
+	if (entries > 0) {
 		/* Make sure we do not speculatively read the data before
 		 * we have received the packet buffers from the ring.
 		 */
-		smp_rmb();
+		libbpf_smp_rmb();
 
 		*idx = cons->cached_cons;
 		cons->cached_cons += entries;
@@ -144,6 +149,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
 
 static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
 {
+	/* Make sure data has been read before indicating we are done
+	 * with the entries by updating the consumer pointer.
+	 */
+	libbpf_smp_rwmb();
+
 	*cons->consumer += nb;
 }