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

Daniel Borkmann says:

====================
pull-request: bpf 2019-11-02

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

We've added 6 non-merge commits during the last 6 day(s) which contain
a total of 8 files changed, 35 insertions(+), 9 deletions(-).

The main changes are:

1) Fix ppc BPF JIT's tail call implementation by performing a second pass
to gather a stable JIT context before opcode emission, from Eric Dumazet.

2) Fix build of BPF samples sys_perf_event_open() usage to compiled out
unavailable test_attr__{enabled,open} checks. Also fix potential overflows
in bpf_map_{area_alloc,charge_init} on 32 bit archs, from Björn Töpel.

3) Fix narrow loads of bpf_sysctl context fields with offset > 0 on big endian
archs like s390x and also improve the test coverage, from Ilya Leoshkevich.
====================

Signed-off-by: David S. Miller <[e-mail]>

MAINTAINERS

···
 R:	Martin KaFai Lau <[e-mail]>
 R:	Song Liu <[e-mail]>
 R:	Yonghong Song <[e-mail]>
+R:	Andrii Nakryiko <[e-mail]>
 L:	[e-mail]
 L:	[e-mail]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git

arch/powerpc/net/bpf_jit_comp64.c

···
 	}
 
 	/*
+	 * If we have seen a tail call, we need a second pass.
+	 * This is because bpf_jit_emit_common_epilogue() is called
+	 * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
+	 */
+	if (cgctx.seen & SEEN_TAILCALL) {
+		cgctx.idx = 0;
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
+	}
+
+	/*
 	 * Pretend to build prologue, given the features we've seen.  This will
 	 * update ctgtx.idx as it pretends to output instructions, then we can
 	 * calculate total size from idx.

include/linux/bpf.h

···
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
 void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size);
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
 void bpf_map_charge_finish(struct bpf_map_memory *mem);
 void bpf_map_charge_move(struct bpf_map_memory *dst,
 			 struct bpf_map_memory *src);
-void *bpf_map_area_alloc(size_t size, int numa_node);
+void *bpf_map_area_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 

kernel/bpf/cgroup.c

···
 		return false;
 
 	switch (off) {
-	case offsetof(struct bpf_sysctl, write):
+	case bpf_ctx_range(struct bpf_sysctl, write):
 		if (type != BPF_READ)
 			return false;
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
-	case offsetof(struct bpf_sysctl, file_pos):
+	case bpf_ctx_range(struct bpf_sysctl, file_pos):
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
 			return bpf_ctx_narrow_access_ok(off, size, size_default);

kernel/bpf/syscall.c

···
 	return map;
 }
 
-void *bpf_map_area_alloc(size_t size, int numa_node)
+void *bpf_map_area_alloc(u64 size, int numa_node)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
···
 
 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
+
+	if (size >= SIZE_MAX)
+		return NULL;
 
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
···
 		atomic_long_sub(pages, &user->locked_vm);
 }
 
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size)
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
 {
 	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
 	struct user_struct *user;

samples/bpf/Makefile

···
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
+KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 

tools/perf/perf-sys.h

···
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 		     int fd, int group_fd, unsigned long flags);
 
-#define HAVE_ATTR_TEST
+#ifndef HAVE_ATTR_TEST
+#define HAVE_ATTR_TEST 1
+#endif
 
 static inline int
 sys_perf_event_open(struct perf_event_attr *attr,
···
 	fd = syscall(__NR_perf_event_open, attr, pid, cpu,
 		     group_fd, flags);
 
-#ifdef HAVE_ATTR_TEST
+#if HAVE_ATTR_TEST
 	if (unlikely(test_attr__enabled))
 		test_attr__open(attr, pid, cpu, fd, group_fd, flags);
 #endif

tools/testing/selftests/bpf/test_sysctl.c

···
 		.descr = "ctx:file_pos sysctl:read read ok narrow",
 		.insns = {
 			/* If (file_pos == X) */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
 			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
 				    offsetof(struct bpf_sysctl, file_pos)),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
+#else
+			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct bpf_sysctl, file_pos) + 3),
+#endif
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2),
 
 			/* return ALLOW; */
 			BPF_MOV64_IMM(BPF_REG_0, 1),
···
 		.attach_type = BPF_CGROUP_SYSCTL,
 		.sysctl = "kernel/ostype",
 		.open_flags = O_RDONLY,
+		.seek = 4,
 		.result = SUCCESS,
 	},
 	{