Merge branch 'explicit-raw_tp-null-arguments'

Kumar Kartikeya Dwivedi says:

====================
Explicit raw_tp NULL arguments

This set reverts the raw_tp masking changes introduced in commit
cb4158ce8ec8 ("bpf: Mark raw_tp arguments with PTR_MAYBE_NULL") and
replaces it wwith an explicit list of tracepoints and their arguments
which need to be annotated as PTR_MAYBE_NULL. More context on the
fallout caused by the masking fix and subsequent discussions can be
found in [0].

To remedy this, we implement a solution of explicitly defined tracepoint
and define which args need to be marked NULL or scalar (for IS_ERR
case). The commit logs describes the details of this approach in detail.

We will follow up this solution an approach Eduard is working on to
perform automated analysis of NULL-ness of tracepoint arguments. The
current PoC is available here:

- LLVM branch with the analysis:
  https://github.com/eddyz87/llvm-project/tree/nullness-for-tracepoint-params
- Python script for merging of analysis results:
  https://gist.github.com/eddyz87/e47c164466a60e8d49e6911cff146f47

The idea is to infer a tri-state verdict for each tracepoint parameter:
definitely not null, can be null, unknown (in which case no assumptions
should be made).

Using this information, the verifier in most cases will be able to
precisely determine the state of the tracepoint parameter without any
human effort. At that point, the table maintained manually in this set
can be dropped and replace with this automated analysis tool's result.
This will be kept up to date with each kernel release.

  [0]: https://lore.kernel.org/bpf/20241206161053.809580-1-memxor@gmail.com

Changelog:
----------
v2 -> v3:
v2: https://lore.kernel.org/bpf/20241213175127.2084759-1-memxor@gmail.com

 * Address Eduard's nits, add Reviewed-by

v1 -> v2:
v1: https://lore.kernel.org/bpf/20241211020156.18966-1-memxor@gmail.com

 * Address comments from Jiri
   * Mark module tracepoints args NULL by default
   * Add more sunrpc tracepoints
   * Unify scalar or null handling
 * Address comments from Alexei
   * Use bitmask approach suggested in review
   * Unify scalar or null handling
   * Drop most tests that rely on CONFIG options
   * Drop scripts to generate tests
====================

Link: https://patch.msgid.link/20241213221929.3495062-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 146 insertions, 76 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a63a03582f02..e5a5f023cedd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6439,6 +6439,101 @@ int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto,
 	return off;
 }
 
+struct bpf_raw_tp_null_args {
+	const char *func;
+	u64 mask;
+};
+
+static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
+	/* sched */
+	{ "sched_pi_setprio", 0x10 },
+	/* ... from sched_numa_pair_template event class */
+	{ "sched_stick_numa", 0x100 },
+	{ "sched_swap_numa", 0x100 },
+	/* afs */
+	{ "afs_make_fs_call", 0x10 },
+	{ "afs_make_fs_calli", 0x10 },
+	{ "afs_make_fs_call1", 0x10 },
+	{ "afs_make_fs_call2", 0x10 },
+	{ "afs_protocol_error", 0x1 },
+	{ "afs_flock_ev", 0x10 },
+	/* cachefiles */
+	{ "cachefiles_lookup", 0x1 | 0x200 },
+	{ "cachefiles_unlink", 0x1 },
+	{ "cachefiles_rename", 0x1 },
+	{ "cachefiles_prep_read", 0x1 },
+	{ "cachefiles_mark_active", 0x1 },
+	{ "cachefiles_mark_failed", 0x1 },
+	{ "cachefiles_mark_inactive", 0x1 },
+	{ "cachefiles_vfs_error", 0x1 },
+	{ "cachefiles_io_error", 0x1 },
+	{ "cachefiles_ondemand_open", 0x1 },
+	{ "cachefiles_ondemand_copen", 0x1 },
+	{ "cachefiles_ondemand_close", 0x1 },
+	{ "cachefiles_ondemand_read", 0x1 },
+	{ "cachefiles_ondemand_cread", 0x1 },
+	{ "cachefiles_ondemand_fd_write", 0x1 },
+	{ "cachefiles_ondemand_fd_release", 0x1 },
+	/* ext4, from ext4__mballoc event class */
+	{ "ext4_mballoc_discard", 0x10 },
+	{ "ext4_mballoc_free", 0x10 },
+	/* fib */
+	{ "fib_table_lookup", 0x100 },
+	/* filelock */
+	/* ... from filelock_lock event class */
+	{ "posix_lock_inode", 0x10 },
+	{ "fcntl_setlk", 0x10 },
+	{ "locks_remove_posix", 0x10 },
+	{ "flock_lock_inode", 0x10 },
+	/* ... from filelock_lease event class */
+	{ "break_lease_noblock", 0x10 },
+	{ "break_lease_block", 0x10 },
+	{ "break_lease_unblock", 0x10 },
+	{ "generic_delete_lease", 0x10 },
+	{ "time_out_leases", 0x10 },
+	/* host1x */
+	{ "host1x_cdma_push_gather", 0x10000 },
+	/* huge_memory */
+	{ "mm_khugepaged_scan_pmd", 0x10 },
+	{ "mm_collapse_huge_page_isolate", 0x1 },
+	{ "mm_khugepaged_scan_file", 0x10 },
+	{ "mm_khugepaged_collapse_file", 0x10 },
+	/* kmem */
+	{ "mm_page_alloc", 0x1 },
+	{ "mm_page_pcpu_drain", 0x1 },
+	/* .. from mm_page event class */
+	{ "mm_page_alloc_zone_locked", 0x1 },
+	/* netfs */
+	{ "netfs_failure", 0x10 },
+	/* power */
+	{ "device_pm_callback_start", 0x10 },
+	/* qdisc */
+	{ "qdisc_dequeue", 0x1000 },
+	/* rxrpc */
+	{ "rxrpc_recvdata", 0x1 },
+	{ "rxrpc_resend", 0x10 },
+	/* sunrpc */
+	{ "xs_stream_read_data", 0x1 },
+	/* ... from xprt_cong_event event class */
+	{ "xprt_reserve_cong", 0x10 },
+	{ "xprt_release_cong", 0x10 },
+	{ "xprt_get_cong", 0x10 },
+	{ "xprt_put_cong", 0x10 },
+	/* tcp */
+	{ "tcp_send_reset", 0x11 },
+	/* tegra_apb_dma */
+	{ "tegra_dma_tx_status", 0x100 },
+	/* timer_migration */
+	{ "tmigr_update_events", 0x1 },
+	/* writeback, from writeback_folio_template event class */
+	{ "writeback_dirty_folio", 0x10 },
+	{ "folio_wait_writeback", 0x10 },
+	/* rdma */
+	{ "mr_integ_alloc", 0x2000 },
+	/* bpf_testmod */
+	{ "bpf_testmod_test_read", 0x0 },
+};
+
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
@@ -6449,6 +6544,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
 	const struct btf_param *args;
+	bool ptr_err_raw_tp = false;
 	const char *tag_value;
 	u32 nr_args, arg;
 	int i, ret;
@@ -6594,12 +6690,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	if (prog_args_trusted(prog))
 		info->reg_type |= PTR_TRUSTED;
 
-	/* Raw tracepoint arguments always get marked as maybe NULL */
-	if (bpf_prog_is_raw_tp(prog))
-		info->reg_type |= PTR_MAYBE_NULL;
-	else if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
+	if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
 		info->reg_type |= PTR_MAYBE_NULL;
 
+	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+		struct btf *btf = prog->aux->attach_btf;
+		const struct btf_type *t;
+		const char *tname;
+
+		/* BTF lookups cannot fail, return false on error */
+		t = btf_type_by_id(btf, prog->aux->attach_btf_id);
+		if (!t)
+			return false;
+		tname = btf_name_by_offset(btf, t->name_off);
+		if (!tname)
+			return false;
+		/* Checked by bpf_check_attach_target */
+		tname += sizeof("btf_trace_") - 1;
+		for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) {
+			/* Is this a func with potential NULL args? */
+			if (strcmp(tname, raw_tp_null_args[i].func))
+				continue;
+			if (raw_tp_null_args[i].mask & (0x1 << (arg * 4)))
+				info->reg_type |= PTR_MAYBE_NULL;
+			/* Is the current arg IS_ERR? */
+			if (raw_tp_null_args[i].mask & (0x2 << (arg * 4)))
+				ptr_err_raw_tp = true;
+			break;
+		}
+		/* If we don't know NULL-ness specification and the tracepoint
+		 * is coming from a loadable module, be conservative and mark
+		 * argument as PTR_MAYBE_NULL.
+		 */
+		if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf))
+			info->reg_type |= PTR_MAYBE_NULL;
+	}
+
 	if (tgt_prog) {
 		enum bpf_prog_type tgt_type;
 
@@ -6644,6 +6770,15 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n",
 		tname, arg, info->btf_id, btf_type_str(t),
 		__btf_name_by_offset(btf, t->name_off));
+
+	/* Perform all checks on the validity of type for this argument, but if
+	 * we know it can be IS_ERR at runtime, scrub pointer type and mark as
+	 * scalar.
+	 */
+	if (ptr_err_raw_tp) {
+		bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg);
+		info->reg_type = SCALAR_VALUE;
+	}
 	return true;
 }
 EXPORT_SYMBOL_GPL(btf_ctx_access);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5e541339b2f6..f7f892a52a37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -420,25 +420,6 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 	return rec;
 }
 
-static bool mask_raw_tp_reg_cond(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) {
-	return reg->type == (PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL) &&
-	       bpf_prog_is_raw_tp(env->prog) && !reg->ref_obj_id;
-}
-
-static bool mask_raw_tp_reg(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
-{
-	if (!mask_raw_tp_reg_cond(env, reg))
-		return false;
-	reg->type &= ~PTR_MAYBE_NULL;
-	return true;
-}
-
-static void unmask_raw_tp_reg(struct bpf_reg_state *reg, bool result)
-{
-	if (result)
-		reg->type |= PTR_MAYBE_NULL;
-}
-
 static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
 {
 	struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux;
@@ -6801,7 +6782,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	const char *field_name = NULL;
 	enum bpf_type_flag flag = 0;
 	u32 btf_id = 0;
-	bool mask;
 	int ret;
 
 	if (!env->allow_ptr_leaks) {
@@ -6873,21 +6853,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 
 	if (ret < 0)
 		return ret;
-	/* For raw_tp progs, we allow dereference of PTR_MAYBE_NULL
-	 * trusted PTR_TO_BTF_ID, these are the ones that are possibly
-	 * arguments to the raw_tp. Since internal checks in for trusted
-	 * reg in check_ptr_to_btf_access would consider PTR_MAYBE_NULL
-	 * modifier as problematic, mask it out temporarily for the
-	 * check. Don't apply this to pointers with ref_obj_id > 0, as
-	 * those won't be raw_tp args.
-	 *
-	 * We may end up applying this relaxation to other trusted
-	 * PTR_TO_BTF_ID with maybe null flag, since we cannot
-	 * distinguish PTR_MAYBE_NULL tagged for arguments vs normal
-	 * tagging, but that should expand allowed behavior, and not
-	 * cause regression for existing behavior.
-	 */
-	mask = mask_raw_tp_reg(env, reg);
+
 	if (ret != PTR_TO_BTF_ID) {
 		/* just mark; */
 
@@ -6948,13 +6914,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 		clear_trusted_flags(&flag);
 	}
 
-	if (atype == BPF_READ && value_regno >= 0) {
+	if (atype == BPF_READ && value_regno >= 0)
 		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
-		/* We've assigned a new type to regno, so don't undo masking. */
-		if (regno == value_regno)
-			mask = false;
-	}
-	unmask_raw_tp_reg(reg, mask);
 
 	return 0;
 }
@@ -7329,7 +7290,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (base_type(reg->type) == PTR_TO_BTF_ID &&
-		   (mask_raw_tp_reg_cond(env, reg) || !type_may_be_null(reg->type))) {
+		   !type_may_be_null(reg->type)) {
 		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
 					      value_regno);
 	} else if (reg->type == CONST_PTR_TO_MAP) {
@@ -9032,7 +8993,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	enum bpf_reg_type type = reg->type;
 	u32 *arg_btf_id = NULL;
 	int err = 0;
-	bool mask;
 
 	if (arg_type == ARG_DONTCARE)
 		return 0;
@@ -9073,11 +9033,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	    base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK)
 		arg_btf_id = fn->arg_btf_id[arg];
 
-	mask = mask_raw_tp_reg(env, reg);
 	err = check_reg_type(env, regno, arg_type, arg_btf_id, meta);
+	if (err)
+		return err;
 
-	err = err ?: check_func_arg_reg_off(env, reg, regno, arg_type);
-	unmask_raw_tp_reg(reg, mask);
+	err = check_func_arg_reg_off(env, reg, regno, arg_type);
 	if (err)
 		return err;
 
@@ -9872,17 +9832,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 				return ret;
 		} else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) {
 			struct bpf_call_arg_meta meta;
-			bool mask;
 			int err;
 
 			if (register_is_null(reg) && type_may_be_null(arg->arg_type))
 				continue;
 
 			memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */
-			mask = mask_raw_tp_reg(env, reg);
 			err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta);
 			err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type);
-			unmask_raw_tp_reg(reg, mask);
 			if (err)
 				return err;
 		} else {
@@ -12205,7 +12162,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		enum bpf_arg_type arg_type = ARG_DONTCARE;
 		u32 regno = i + 1, ref_id, type_size;
 		bool is_ret_buf_sz = false;
-		bool mask = false;
 		int kf_arg_type;
 
 		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
@@ -12264,15 +12220,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			return -EINVAL;
 		}
 
-		mask = mask_raw_tp_reg(env, reg);
 		if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
 		    (register_is_null(reg) || type_may_be_null(reg->type)) &&
 			!is_kfunc_arg_nullable(meta->btf, &args[i])) {
 			verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
-			unmask_raw_tp_reg(reg, mask);
 			return -EACCES;
 		}
-		unmask_raw_tp_reg(reg, mask);
 
 		if (reg->ref_obj_id) {
 			if (is_kfunc_release(meta) && meta->ref_obj_id) {
@@ -12330,24 +12283,16 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))
 				break;
 
-			/* Allow passing maybe NULL raw_tp arguments to
-			 * kfuncs for compatibility. Don't apply this to
-			 * arguments with ref_obj_id > 0.
-			 */
-			mask = mask_raw_tp_reg(env, reg);
 			if (!is_trusted_reg(reg)) {
 				if (!is_kfunc_rcu(meta)) {
 					verbose(env, "R%d must be referenced or trusted\n", regno);
-					unmask_raw_tp_reg(reg, mask);
 					return -EINVAL;
 				}
 				if (!is_rcu_reg(reg)) {
 					verbose(env, "R%d must be a rcu pointer\n", regno);
-					unmask_raw_tp_reg(reg, mask);
 					return -EINVAL;
 				}
 			}
-			unmask_raw_tp_reg(reg, mask);
 			fallthrough;
 		case KF_ARG_PTR_TO_CTX:
 		case KF_ARG_PTR_TO_DYNPTR:
@@ -12370,9 +12315,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 
 		if (is_kfunc_release(meta) && reg->ref_obj_id)
 			arg_type |= OBJ_RELEASE;
-		mask = mask_raw_tp_reg(env, reg);
 		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
-		unmask_raw_tp_reg(reg, mask);
 		if (ret < 0)
 			return ret;
 
@@ -12549,7 +12492,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			ref_tname = btf_name_by_offset(btf, ref_t->name_off);
 			fallthrough;
 		case KF_ARG_PTR_TO_BTF_ID:
-			mask = mask_raw_tp_reg(env, reg);
 			/* Only base_type is checked, further checks are done here */
 			if ((base_type(reg->type) != PTR_TO_BTF_ID ||
 			     (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) &&
@@ -12558,11 +12500,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				verbose(env, "expected %s or socket\n",
 					reg_type_str(env, base_type(reg->type) |
 							  (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS)));
-				unmask_raw_tp_reg(reg, mask);
 				return -EINVAL;
 			}
 			ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i);
-			unmask_raw_tp_reg(reg, mask);
 			if (ret < 0)
 				return ret;
 			break;
@@ -13535,7 +13475,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
  */
 static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 				   struct bpf_insn *insn,
-				   struct bpf_reg_state *ptr_reg,
+				   const struct bpf_reg_state *ptr_reg,
 				   const struct bpf_reg_state *off_reg)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
@@ -13549,7 +13489,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_sanitize_info info = {};
 	u8 opcode = BPF_OP(insn->code);
 	u32 dst = insn->dst_reg;
-	bool mask;
 	int ret;
 
 	dst_reg = &regs[dst];
@@ -13576,14 +13515,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	mask = mask_raw_tp_reg(env, ptr_reg);
 	if (ptr_reg->type & PTR_MAYBE_NULL) {
 		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
 			dst, reg_type_str(env, ptr_reg->type));
-		unmask_raw_tp_reg(ptr_reg, mask);
 		return -EACCES;
 	}
-	unmask_raw_tp_reg(ptr_reg, mask);
 
 	switch (base_type(ptr_reg->type)) {
 	case PTR_TO_CTX:
@@ -20126,7 +20062,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		 * for this case.
 		 */
 		case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
-		case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL:
 			if (type == BPF_READ) {
 				if (BPF_MODE(insn->code) == BPF_MEM)
 					insn->code = BPF_LDX | BPF_PROBE_MEM |