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

Alexei Starovoitov says:

====================
pull-request: bpf 2019-03-24

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

The main changes are:

1) libbpf verision fix up from Daniel.

2) fix liveness propagation from Jakub.

3) fix verbose print of refcounted regs from Martin.

4) fix for large map allocations from Martynas.

5) fix use after free in sanitize_ptr_alu from Xu.
====================

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

5 files changed, 92 insertions, 33 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 62f6bced3a3c..afca36f53c49 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -136,21 +136,29 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 
 void *bpf_map_area_alloc(size_t size, int numa_node)
 {
-	/* We definitely need __GFP_NORETRY, so OOM killer doesn't
-	 * trigger under memory pressure as we really just want to
-	 * fail instead.
+	/* We really just want to fail instead of triggering OOM killer
+	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
+	 * which is used for lower order allocation requests.
+	 *
+	 * It has been observed that higher order allocation requests done by
+	 * vmalloc with __GFP_NORETRY being set might fail due to not trying
+	 * to reclaim memory from the page cache, thus we set
+	 * __GFP_RETRY_MAYFAIL to avoid such situations.
 	 */
-	const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+
+	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		area = kmalloc_node(size, GFP_USER | flags, numa_node);
+		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
+				    numa_node);
 		if (area != NULL)
 			return area;
 	}
 
-	return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags,
-					   __builtin_return_address(0));
+	return __vmalloc_node_flags_caller(size, numa_node,
+					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
+					   flags, __builtin_return_address(0));
 }
 
 void bpf_map_area_free(void *area)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 86f9cd5d1c4e..fd502c1f71eb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -352,6 +352,14 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 		map_value_has_spin_lock(reg->map_ptr);
 }
 
+static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCKET_OR_NULL ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_TCP_SOCK_OR_NULL;
+}
+
 static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
 {
 	return type == ARG_PTR_TO_SOCK_COMMON;
@@ -451,8 +459,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			if (t == PTR_TO_STACK)
 				verbose(env, ",call_%d", func(env, reg)->callsite);
 		} else {
-			verbose(env, "(id=%d ref_obj_id=%d", reg->id,
-				reg->ref_obj_id);
+			verbose(env, "(id=%d", reg->id);
+			if (reg_type_may_be_refcounted_or_null(t))
+				verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
 			if (t != SCALAR_VALUE)
 				verbose(env, ",off=%d", reg->off);
 			if (type_is_pkt_pointer(t))
@@ -3372,7 +3381,7 @@ do_sim:
 		*dst_reg = *ptr_reg;
 	}
 	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
-	if (!ptr_is_dst_reg)
+	if (!ptr_is_dst_reg && ret)
 		*dst_reg = tmp;
 	return !ret ? -EFAULT : 0;
 }
@@ -6069,15 +6078,17 @@ static int propagate_liveness(struct bpf_verifier_env *env,
 	}
 	/* Propagate read liveness of registers... */
 	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
-	/* We don't need to worry about FP liveness because it's read-only */
-	for (i = 0; i < BPF_REG_FP; i++) {
-		if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
-			continue;
-		if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
-			err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i],
-					    &vparent->frame[vstate->curframe]->regs[i]);
-			if (err)
-				return err;
+	for (frame = 0; frame <= vstate->curframe; frame++) {
+		/* We don't need to worry about FP liveness, it's read-only */
+		for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) {
+			if (vparent->frame[frame]->regs[i].live & REG_LIVE_READ)
+				continue;
+			if (vstate->frame[frame]->regs[i].live & REG_LIVE_READ) {
+				err = mark_reg_read(env, &vstate->frame[frame]->regs[i],
+						    &vparent->frame[frame]->regs[i]);
+				if (err)
+					return err;
+			}
 		}
 	}
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 61aaacf0cfa1..5bf8e52c41fc 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
 
 BPF_VERSION = 0
 BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 1
+BPF_EXTRAVERSION = 2
 
 MAKEFLAGS += --no-print-directory
 
@@ -79,8 +79,6 @@ export prefix libdir src obj
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-LIB_FILE = libbpf.a libbpf.so
-
 VERSION		= $(BPF_VERSION)
 PATCHLEVEL	= $(BPF_PATCHLEVEL)
 EXTRAVERSION	= $(BPF_EXTRAVERSION)
@@ -88,7 +86,10 @@ EXTRAVERSION	= $(BPF_EXTRAVERSION)
 OBJ		= $@
 N		=
 
-LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+LIBBPF_VERSION	= $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+
+LIB_TARGET	= libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE	= libbpf.a libbpf.so*
 
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
@@ -128,16 +129,18 @@ all:
 export srctree OUTPUT CC LD CFLAGS V
 include $(srctree)/tools/build/Makefile.include
 
-BPF_IN    := $(OUTPUT)libbpf-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
-VERSION_SCRIPT := libbpf.map
+BPF_IN		:= $(OUTPUT)libbpf-in.o
+VERSION_SCRIPT	:= libbpf.map
+
+LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_TARGET)
 
 CXX_TEST_TARGET = $(OUTPUT)test_libbpf
 
@@ -170,9 +173,13 @@ $(BPF_IN): force elfdep bpfdep
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
-$(OUTPUT)libbpf.so: $(BPF_IN)
-	$(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \
-		$^ -o $@
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
+	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
+				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
+	@ln -sf $(@F) $(OUTPUT)libbpf.so
+	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -192,6 +199,12 @@ check_abi: $(OUTPUT)libbpf.so
 		exit 1;							 \
 	fi
 
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
+	fi
+endef
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
@@ -200,8 +213,9 @@ define do_install
 endef
 
 install_lib: all_cmd
-	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(call QUIET_INSTALL, $(LIB_TARGET)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
 install_headers:
 	$(call QUIET_INSTALL, headers) \
@@ -219,7 +233,7 @@ config-clean:
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
-		*.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
+		*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index 5788479384ca..cef7b77eab69 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -111,6 +111,7 @@ starting from ``0.0.1``.
 
 Every time ABI is being changed, e.g. because a new symbol is added or
 semantic of existing symbol is changed, ABI version should be bumped.
+This bump in ABI version is at most once per kernel development cycle.
 
 For example, if current state of ``libbpf.map`` is:
 
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 4004891afa9c..f2ccae39ee66 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -1940,3 +1940,28 @@
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
+{
+	"calls: cross frame pruning - liveness propagation",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_8, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_8, 1),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_9, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_9, 1),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr = "!read_ok",
+	.result = REJECT,
+},