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

Daniel Borkmann says:

====================
bpf-next 2021-10-02

We've added 85 non-merge commits during the last 15 day(s) which contain
a total of 132 files changed, 13779 insertions(+), 6724 deletions(-).

The main changes are:

1) Massive update on test_bpf.ko coverage for JITs as preparatory work for
   an upcoming MIPS eBPF JIT, from Johan Almbladh.

2) Add a batched interface for RX buffer allocation in AF_XDP buffer pool,
   with driver support for i40e and ice from Magnus Karlsson.

3) Add legacy uprobe support to libbpf to complement recently merged legacy
   kprobe support, from Andrii Nakryiko.

4) Add bpf_trace_vprintk() as variadic printk helper, from Dave Marchevsky.

5) Support saving the register state in verifier when spilling <8byte bounded
   scalar to the stack, from Martin Lau.

6) Add libbpf opt-in for stricter BPF program section name handling as part
   of libbpf 1.0 effort, from Andrii Nakryiko.

7) Add a document to help clarifying BPF licensing, from Alexei Starovoitov.

8) Fix skel_internal.h to propagate errno if the loader indicates an internal
   error, from Kumar Kartikeya Dwivedi.

9) Fix build warnings with -Wcast-function-type so that the option can later
   be enabled by default for the kernel, from Kees Cook.

10) Fix libbpf to ignore STT_SECTION symbols in legacy map definitions as it
    otherwise errors out when encountering them, from Toke Høiland-Jørgensen.

11) Teach libbpf to recognize specialized maps (such as for perf RB) and
    internally remove BTF type IDs when creating them, from Hengqi Chen.

12) Various fixes and improvements to BPF selftests.
====================

Link: https://lore.kernel.org/r/20211002001327.15169-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 99 insertions, 60 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cebd4fb06d19..5e1ccfae916b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -645,7 +645,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_array_map_info),
 };
 
-static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				   void *callback_ctx, u64 flags)
 {
 	u32 i, key, num_elems = 0;
@@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
 			val = array->value + array->elem_size * i;
 		num_elems++;
 		key = i;
-		ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)&key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+		ret = callback_fn((u64)(long)map, (u64)(long)&key,
+				  (u64)(long)val, (u64)(long)callback_ctx, 0);
 		/* return value: 0 - continue, 1 - stop and return */
 		if (ret)
 			break;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6b7dfdd8066..ea8a468dbded 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
+{
+	return NULL;
+}
+
 u64 __weak
 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		 void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 32471ba02708..d29af9988f37 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
@@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
 	*insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
 			      offsetof(struct htab_elem, lru_node) +
@@ -2049,7 +2049,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_hash_map_info),
 };
 
-static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				  void *callback_ctx, u64 flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
@@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
 				val = elem->key + roundup_key_size;
 			}
 			num_elems++;
-			ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+			ret = callback_fn((u64)(long)map, (u64)(long)key,
+					  (u64)(long)val, (u64)(long)callback_ctx, 0);
 			/* return value: 0 - continue, 1 - stop and return */
 			if (ret) {
 				rcu_read_unlock();
@@ -2397,7 +2396,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9aabf84afd4b..1ffd469c217f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -979,15 +979,13 @@ out:
 	return err;
 }
 
-#define MAX_SNPRINTF_VARARGS		12
-
 BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
 	   const void *, data, u32, data_len)
 {
 	int err, num_args;
 	u32 *bin_args;
 
-	if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
+	if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 ||
 	    (data_len && !data))
 		return -EINVAL;
 	num_args = data_len / 8;
@@ -1058,7 +1056,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 	struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer);
 	struct bpf_map *map = t->map;
 	void *value = t->value;
-	void *callback_fn;
+	bpf_callback_t callback_fn;
 	void *key;
 	u32 idx;
 
@@ -1083,8 +1081,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 		key = value - round_up(map->key_size, 8);
 	}
 
-	BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key,
-				   (u64)(long)value, 0, 0);
+	callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0);
 	/* The verifier checked that return value is zero. */
 
 	this_cpu_write(hrtimer_running, NULL);
@@ -1437,6 +1434,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_task_pt_regs:
 		return &bpf_task_pt_regs_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return NULL;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e76b55917905..1433752db740 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -612,6 +612,20 @@ static const char *kernel_type_name(const struct btf* btf, u32 id)
 	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
+/* The reg state of a pointer or a bounded scalar was saved when
+ * it was spilled to the stack.
+ */
+static bool is_spilled_reg(const struct bpf_stack_state *stack)
+{
+	return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
+}
+
+static void scrub_spilled_slot(u8 *stype)
+{
+	if (*stype != STACK_INVALID)
+		*stype = STACK_MISC;
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
 				 const struct bpf_func_state *state)
 {
@@ -717,7 +731,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			continue;
 		verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 		print_liveness(env, state->stack[i].spilled_ptr.live);
-		if (state->stack[i].slot_type[0] == STACK_SPILL) {
+		if (is_spilled_reg(&state->stack[i])) {
 			reg = &state->stack[i].spilled_ptr;
 			t = reg->type;
 			verbose(env, "=%s", reg_type_str[t]);
@@ -1730,7 +1744,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 
 	desc = &tab->descs[tab->nr_descs++];
 	desc->func_id = func_id;
-	desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
+	desc->imm = BPF_CALL_IMM(addr);
 	err = btf_distill_func_proto(&env->log, btf_vmlinux,
 				     func_proto, func_name,
 				     &desc->func_model);
@@ -2373,7 +2387,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 				reg->precise = true;
 			}
 			for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
-				if (func->stack[j].slot_type[0] != STACK_SPILL)
+				if (!is_spilled_reg(&func->stack[j]))
 					continue;
 				reg = &func->stack[j].spilled_ptr;
 				if (reg->type != SCALAR_VALUE)
@@ -2415,7 +2429,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	}
 
 	while (spi >= 0) {
-		if (func->stack[spi].slot_type[0] != STACK_SPILL) {
+		if (!is_spilled_reg(&func->stack[spi])) {
 			stack_mask = 0;
 			break;
 		}
@@ -2514,7 +2528,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 				return 0;
 			}
 
-			if (func->stack[i].slot_type[0] != STACK_SPILL) {
+			if (!is_spilled_reg(&func->stack[i])) {
 				stack_mask &= ~(1ull << i);
 				continue;
 			}
@@ -2626,15 +2640,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 }
 
 static void save_register_state(struct bpf_func_state *state,
-				int spi, struct bpf_reg_state *reg)
+				int spi, struct bpf_reg_state *reg,
+				int size)
 {
 	int i;
 
 	state->stack[spi].spilled_ptr = *reg;
-	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+	if (size == BPF_REG_SIZE)
+		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
+	for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--)
+		state->stack[spi].slot_type[i - 1] = STACK_SPILL;
 
-	for (i = 0; i < BPF_REG_SIZE; i++)
-		state->stack[spi].slot_type[i] = STACK_SPILL;
+	/* size < 8 bytes spill */
+	for (; i; i--)
+		scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
 }
 
 /* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
@@ -2681,7 +2701,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
 	}
 
-	if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
+	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
 	    !register_is_null(reg) && env->bpf_capable) {
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
@@ -2694,7 +2714,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			if (err)
 				return err;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -2706,16 +2726,16 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
 			return -EINVAL;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else {
 		u8 type = STACK_MISC;
 
 		/* regular write of data into stack destroys any spilled ptr */
 		state->stack[spi].spilled_ptr.type = NOT_INIT;
 		/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
-		if (state->stack[spi].slot_type[0] == STACK_SPILL)
+		if (is_spilled_reg(&state->stack[spi]))
 			for (i = 0; i < BPF_REG_SIZE; i++)
-				state->stack[spi].slot_type[i] = STACK_MISC;
+				scrub_spilled_slot(&state->stack[spi].slot_type[i]);
 
 		/* only mark the slot as written if all 8 bytes were written
 		 * otherwise read propagation may incorrectly stop too soon
@@ -2918,23 +2938,50 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
-	u8 *stype;
+	u8 *stype, type;
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
 
-	if (stype[0] == STACK_SPILL) {
+	if (is_spilled_reg(&reg_state->stack[spi])) {
 		if (size != BPF_REG_SIZE) {
+			u8 scalar_size = 0;
+
 			if (reg->type != SCALAR_VALUE) {
 				verbose_linfo(env, env->insn_idx, "; ");
 				verbose(env, "invalid size of register fill\n");
 				return -EACCES;
 			}
-			if (dst_regno >= 0) {
+
+			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			if (dst_regno < 0)
+				return 0;
+
+			for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--)
+				scalar_size++;
+
+			if (!(off % BPF_REG_SIZE) && size == scalar_size) {
+				/* The earlier check_reg_arg() has decided the
+				 * subreg_def for this insn.  Save it first.
+				 */
+				s32 subreg_def = state->regs[dst_regno].subreg_def;
+
+				state->regs[dst_regno] = *reg;
+				state->regs[dst_regno].subreg_def = subreg_def;
+			} else {
+				for (i = 0; i < size; i++) {
+					type = stype[(slot - i) % BPF_REG_SIZE];
+					if (type == STACK_SPILL)
+						continue;
+					if (type == STACK_MISC)
+						continue;
+					verbose(env, "invalid read from stack off %d+%d size %d\n",
+						off, i, size);
+					return -EACCES;
+				}
 				mark_reg_unknown(env, state->regs, dst_regno);
-				state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			}
-			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			return 0;
 		}
 		for (i = 1; i < BPF_REG_SIZE; i++) {
@@ -2965,8 +3012,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
-		u8 type;
-
 		for (i = 0; i < size; i++) {
 			type = stype[(slot - i) % BPF_REG_SIZE];
 			if (type == STACK_MISC)
@@ -4514,17 +4559,17 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
 			goto mark;
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
 		     env->allow_ptr_leaks)) {
 			if (clobber) {
 				__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
 				for (j = 0; j < BPF_REG_SIZE; j++)
-					state->stack[spi].slot_type[j] = STACK_MISC;
+					scrub_spilled_slot(&state->stack[spi].slot_type[j]);
 			}
 			goto mark;
 		}
@@ -10356,9 +10401,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			 * return false to continue verification of this path
 			 */
 			return false;
-		if (i % BPF_REG_SIZE)
+		if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1)
 			continue;
-		if (old->stack[spi].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&old->stack[spi]))
 			continue;
 		if (!regsafe(env, &old->stack[spi].spilled_ptr,
 			     &cur->stack[spi].spilled_ptr, idmap))
@@ -10565,7 +10610,7 @@ static int propagate_precision(struct bpf_verifier_env *env,
 	}
 
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		if (state->stack[i].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&state->stack[i]))
 			continue;
 		state_reg = &state->stack[i].spilled_ptr;
 		if (state_reg->type != SCALAR_VALUE ||
@@ -12469,8 +12514,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			if (!bpf_pseudo_call(insn))
 				continue;
 			subprog = insn->off;
-			insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
-				    __bpf_call_base;
+			insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func);
 		}
 
 		/* we use the aux data to keep a list of the start addresses
@@ -12950,32 +12994,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_lookup_elem);
 				continue;
 			case BPF_FUNC_map_update_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_update_elem);
 				continue;
 			case BPF_FUNC_map_delete_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_delete_elem);
 				continue;
 			case BPF_FUNC_map_push_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_push_elem);
 				continue;
 			case BPF_FUNC_map_pop_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_pop_elem);
 				continue;
 			case BPF_FUNC_map_peek_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_peek_elem);
 				continue;
 			case BPF_FUNC_redirect_map:
-				insn->imm = BPF_CAST_CALL(ops->map_redirect) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_redirect);
 				continue;
 			}