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

Andrii Nakryiko says:

====================
bpf 2022-11-11

We've added 11 non-merge commits during the last 8 day(s) which contain
a total of 11 files changed, 83 insertions(+), 74 deletions(-).

The main changes are:

1) Fix strncpy_from_kernel_nofault() to prevent out-of-bounds writes,
   from Alban Crequy.

2) Fix for bpf_prog_test_run_skb() to prevent wrong alignment,
   from Baisong Zhong.

3) Switch BPF_DISPATCHER to static_call() instead of ftrace infra, with
   a small build fix on top, from Peter Zijlstra and Nathan Chancellor.

4) Fix memory leak in BPF verifier in some error cases, from Wang Yufen.

5) 32-bit compilation error fixes for BPF selftests, from Pu Lehui and
   Yang Jihong.

6) Ensure even distribution of per-CPU free list elements, from Xu Kuohai.

7) Fix copy_map_value() to track special zeroed out areas properly,
   from Xu Kuohai.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Fix offset calculation error in __copy_map_value and zero_map_value
  bpf: Initialize same number of free nodes for each pcpu_freelist
  selftests: bpf: Add a test when bpf_probe_read_kernel_str() returns EFAULT
  maccess: Fix writing offset in case of fault in strncpy_from_kernel_nofault()
  selftests/bpf: Fix test_progs compilation failure in 32-bit arch
  selftests/bpf: Fix casting error when cross-compiling test_verifier for 32-bit platforms
  bpf: Fix memory leaks in __check_func_call
  bpf: Add explicit cast to 'void *' for __BPF_DISPATCHER_UPDATE()
  bpf: Convert BPF_DISPATCHER to use static_call() (not ftrace)
  bpf: Revert ("Fix dispatcher patchable function entry to 5 bytes nop")
  bpf, test_run: Fix alignment problem in bpf_prog_test_run_skb()
====================

Link: https://lore.kernel.org/r/20221111231624.938829-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -11,7 +11,6 @@
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
-#include <linux/init.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
@@ -389,18 +388,6 @@ out:
 	return ret;
 }
 
-int __init bpf_arch_init_dispatcher_early(void *ip)
-{
-	const u8 *nop_insn = x86_nops[5];
-
-	if (is_endbr(*(u32 *)ip))
-		ip += ENDBR_INSN_SIZE;
-
-	if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
-		text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
-	return 0;
-}
-
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *old_addr, void *new_addr)
 {

include/linux/bpf.h

@@ -27,7 +27,7 @@
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
-#include <linux/init.h>
+#include <linux/static_call.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -315,7 +315,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b
 		u32 next_off = map->off_arr->field_off[i];
 
 		memcpy(dst + curr_off, src + curr_off, next_off - curr_off);
-		curr_off += map->off_arr->field_sz[i];
+		curr_off = next_off + map->off_arr->field_sz[i];
 	}
 	memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off);
 }
@@ -344,7 +344,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 		u32 next_off = map->off_arr->field_off[i];
 
 		memset(dst + curr_off, 0, next_off - curr_off);
-		curr_off += map->off_arr->field_sz[i];
+		curr_off = next_off + map->off_arr->field_sz[i];
 	}
 	memset(dst + curr_off, 0, map->value_size - curr_off);
 }
@@ -954,6 +954,10 @@ struct bpf_dispatcher {
 	void *rw_image;
 	u32 image_off;
 	struct bpf_ksym ksym;
+#ifdef CONFIG_HAVE_STATIC_CALL
+	struct static_call_key *sc_key;
+	void *sc_tramp;
+#endif
 };
 
 static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
@@ -971,7 +975,33 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
-int __init bpf_arch_init_dispatcher_early(void *ip);
+
+/*
+ * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
+ * indirection with a direct call to the bpf program. If the architecture does
+ * not have STATIC_CALL, avoid a double-indirection.
+ */
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+#define __BPF_DISPATCHER_SC_INIT(_name)				\
+	.sc_key = &STATIC_CALL_KEY(_name),			\
+	.sc_tramp = STATIC_CALL_TRAMP_ADDR(_name),
+
+#define __BPF_DISPATCHER_SC(name)				\
+	DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func)
+
+#define __BPF_DISPATCHER_CALL(name)				\
+	static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func)
+
+#define __BPF_DISPATCHER_UPDATE(_d, _new)			\
+	__static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new))
+
+#else
+#define __BPF_DISPATCHER_SC_INIT(name)
+#define __BPF_DISPATCHER_SC(name)
+#define __BPF_DISPATCHER_CALL(name)		bpf_func(ctx, insnsi)
+#define __BPF_DISPATCHER_UPDATE(_d, _new)
+#endif
 
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
@@ -984,34 +1014,21 @@ int __init bpf_arch_init_dispatcher_early(void *ip);
 		.name  = #_name,				\
 		.lnode = LIST_HEAD_INIT(_name.ksym.lnode),	\
 	},							\
+	__BPF_DISPATCHER_SC_INIT(_name##_call)			\
 }
 
-#define BPF_DISPATCHER_INIT_CALL(_name)					\
-	static int __init _name##_init(void)				\
-	{								\
-		return bpf_arch_init_dispatcher_early(_name##_func);	\
-	}								\
-	early_initcall(_name##_init)
-
-#ifdef CONFIG_X86_64
-#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5)))
-#else
-#define BPF_DISPATCHER_ATTRIBUTES
-#endif
-
 #define DEFINE_BPF_DISPATCHER(name)					\
-	notrace BPF_DISPATCHER_ATTRIBUTES				\
+	__BPF_DISPATCHER_SC(name);					\
 	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
 	{								\
-		return bpf_func(ctx, insnsi);				\
+		return __BPF_DISPATCHER_CALL(name);			\
 	}								\
 	EXPORT_SYMBOL(bpf_dispatcher_##name##_func);			\
 	struct bpf_dispatcher bpf_dispatcher_##name =			\
-		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);		\
+		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
-	BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name);
 
 #define DECLARE_BPF_DISPATCHER(name)					\
 	unsigned int bpf_dispatcher_##name##_func(			\
@@ -1019,6 +1036,7 @@ int __init bpf_arch_init_dispatcher_early(void *ip);
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func);					\
 	extern struct bpf_dispatcher bpf_dispatcher_##name;
+
 #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
 #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,

kernel/bpf/dispatcher.c

@@ -4,7 +4,7 @@
 #include <linux/hash.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
-#include <linux/init.h>
+#include <linux/static_call.h>
 
 /* The BPF dispatcher is a multiway branch code generator. The
  * dispatcher is a mechanism to avoid the performance penalty of an
@@ -91,11 +91,6 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n
 	return -ENOTSUPP;
 }
 
-int __weak __init bpf_arch_init_dispatcher_early(void *ip)
-{
-	return -ENOTSUPP;
-}
-
 static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
 {
 	s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];
@@ -110,17 +105,11 @@ static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *b
 
 static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 {
-	void *old, *new, *tmp;
+	void *new, *tmp;
-	u32 noff;
+	u32 noff = 0;
-	int err;
 
-	if (!prev_num_progs) {
+	if (prev_num_progs)
-		old = NULL;
-		noff = 0;
-	} else {
-		old = d->image + d->image_off;
 		noff = d->image_off ^ (PAGE_SIZE / 2);
-	}
 
 	new = d->num_progs ? d->image + noff : NULL;
 	tmp = d->num_progs ? d->rw_image + noff : NULL;
@@ -134,11 +123,10 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 			return;
 	}
 
-	err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new);
+	__BPF_DISPATCHER_UPDATE(d, new ?: (void *)&bpf_dispatcher_nop_func);
-	if (err || !new)
-		return;
 
-	d->image_off = noff;
+	if (new)
+		d->image_off = noff;
 }
 
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,

kernel/bpf/percpu_freelist.c

@@ -100,22 +100,21 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 			    u32 nr_elems)
 {
 	struct pcpu_freelist_head *head;
-	int i, cpu, pcpu_entries;
+	unsigned int cpu, cpu_idx, i, j, n, m;
 
-	pcpu_entries = nr_elems / num_possible_cpus() + 1;
+	n = nr_elems / num_possible_cpus();
-	i = 0;
+	m = nr_elems % num_possible_cpus();
 
+	cpu_idx = 0;
 	for_each_possible_cpu(cpu) {
-again:
 		head = per_cpu_ptr(s->freelist, cpu);
-		/* No locking required as this is not visible yet. */
+		j = n + (cpu_idx < m ? 1 : 0);
-		pcpu_freelist_push_node(head, buf);
+		for (i = 0; i < j; i++) {
-		i++;
+			/* No locking required as this is not visible yet. */
-		buf += elem_size;
+			pcpu_freelist_push_node(head, buf);
-		if (i == nr_elems)
+			buf += elem_size;
-			break;
+		}
-		if (i % pcpu_entries)
+		cpu_idx++;
-			goto again;
 	}
 }
 

kernel/bpf/verifier.c

@@ -6745,11 +6745,11 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	/* Transfer references to the callee */
 	err = copy_reference_state(callee, caller);
 	if (err)
-		return err;
+		goto err_out;
 
 	err = set_callee_state_cb(env, caller, callee, *insn_idx);
 	if (err)
-		return err;
+		goto err_out;
 
 	clear_caller_saved_regs(env, caller->regs);
 
@@ -6766,6 +6766,11 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		print_verifier_state(env, callee, true);
 	}
 	return 0;
+
+err_out:
+	free_func_state(callee);
+	state->frame[state->curframe + 1] = NULL;
+	return err;
 }
 
 int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -6979,8 +6984,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		return -EINVAL;
 	}
 
-	state->curframe--;
+	caller = state->frame[state->curframe - 1];
-	caller = state->frame[state->curframe];
 	if (callee->in_callback_fn) {
 		/* enforce R0 return value range [0, 1]. */
 		struct tnum range = callee->callback_ret_range;
@@ -7019,7 +7023,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	}
 	/* clear everything in the callee */
 	free_func_state(callee);
-	state->frame[state->curframe + 1] = NULL;
+	state->frame[state->curframe--] = NULL;
 	return 0;
 }
 

mm/maccess.c

@@ -97,7 +97,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 	return src - unsafe_addr;
 Efault:
 	pagefault_enable();
-	dst[-1] = '\0';
+	dst[0] = '\0';
 	return -EFAULT;
 }
 

net/bpf/test_run.c

@@ -774,6 +774,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
 	if (user_size > size)
 		return ERR_PTR(-EMSGSIZE);
 
+	size = SKB_DATA_ALIGN(size);
 	data = kzalloc(size + headroom + tailroom, GFP_USER);
 	if (!data)
 		return ERR_PTR(-ENOMEM);

tools/testing/selftests/bpf/prog_tests/varlen.c

@@ -63,6 +63,13 @@ void test_varlen(void)
 	CHECK_VAL(data->total4, size1 + size2);
 	CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check",
 	      "doesn't match!\n");
+
+	CHECK_VAL(bss->ret_bad_read, -EFAULT);
+	CHECK_VAL(data->payload_bad[0], 0x42);
+	CHECK_VAL(data->payload_bad[1], 0x42);
+	CHECK_VAL(data->payload_bad[2], 0);
+	CHECK_VAL(data->payload_bad[3], 0x42);
+	CHECK_VAL(data->payload_bad[4], 0x42);
 cleanup:
 	test_varlen__destroy(skel);
 }

tools/testing/selftests/bpf/progs/test_varlen.c

@@ -19,6 +19,7 @@ __u64 payload1_len1 = 0;
 __u64 payload1_len2 = 0;
 __u64 total1 = 0;
 char payload1[MAX_LEN + MAX_LEN] = {};
+__u64 ret_bad_read = 0;
 
 /* .data */
 int payload2_len1 = -1;
@@ -36,6 +37,8 @@ int payload4_len2 = -1;
 int total4= -1;
 char payload4[MAX_LEN + MAX_LEN] = { 1 };
 
+char payload_bad[5] = { 0x42, 0x42, 0x42, 0x42, 0x42 };
+
 SEC("raw_tp/sys_enter")
 int handler64_unsigned(void *regs)
 {
@@ -61,6 +64,8 @@ int handler64_unsigned(void *regs)
 
 	total1 = payload - (void *)payload1;
 
+	ret_bad_read = bpf_probe_read_kernel_str(payload_bad + 2, 1, (void *) -1);
+
 	return 0;
 }
 

tools/testing/selftests/bpf/test_progs.c

@@ -1010,7 +1010,7 @@ static inline const char *str_msg(const struct msg *msg, char *buf)
 			msg->subtest_done.have_log);
 		break;
 	case MSG_TEST_LOG:
-		sprintf(buf, "MSG_TEST_LOG (cnt: %ld, last: %d)",
+		sprintf(buf, "MSG_TEST_LOG (cnt: %zu, last: %d)",
 			strlen(msg->test_log.log_buf),
 			msg->test_log.is_last);
 		break;

tools/testing/selftests/bpf/test_verifier.c

@@ -1260,7 +1260,7 @@ static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt)
 
 	bzero(&info, sizeof(info));
 	info.xlated_prog_len = xlated_prog_len;
-	info.xlated_prog_insns = (__u64)*buf;
+	info.xlated_prog_insns = (__u64)(unsigned long)*buf;
 	if (bpf_obj_get_info_by_fd(fd_prog, &info, &info_len)) {
 		perror("second bpf_obj_get_info_by_fd failed");
 		goto out_free_buf;