Merge tag 'bpf-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Remove usermode driver (UMD) framework (Thomas Weißschuh)

 - Introduce Strongly Connected Component (SCC) in the verifier to
   detect loops and refine register liveness (Eduard Zingerman)

 - Allow 'void *' cast using bpf_rdonly_cast() and corresponding
   '__arg_untrusted' for global function parameters (Eduard Zingerman)

 - Improve precision for BPF_ADD and BPF_SUB operations in the verifier
   (Harishankar Vishwanathan)

 - Teach the verifier that constant pointer to a map cannot be NULL
   (Ihor Solodrai)

 - Introduce BPF streams for error reporting of various conditions
   detected by BPF runtime (Kumar Kartikeya Dwivedi)

 - Teach the verifier to insert runtime speculation barrier (lfence on
   x86) to mitigate speculative execution instead of rejecting the
   programs (Luis Gerhorst)

 - Various improvements for 'veristat' (Mykyta Yatsenko)

 - For CONFIG_DEBUG_KERNEL config warn on internal verifier errors to
   improve bug detection by syzbot (Paul Chaignon)

 - Support BPF private stack on arm64 (Puranjay Mohan)

 - Introduce bpf_cgroup_read_xattr() kfunc to read xattr of cgroup's
   node (Song Liu)

 - Introduce kfuncs for read-only string opreations (Viktor Malik)

 - Implement show_fdinfo() for bpf_links (Tao Chen)

 - Reduce verifier's stack consumption (Yonghong Song)

 - Implement mprog API for cgroup-bpf programs (Yonghong Song)

* tag 'bpf-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (192 commits)
  selftests/bpf: Migrate fexit_noreturns case into tracing_failure test suite
  selftests/bpf: Add selftest for attaching tracing programs to functions in deny list
  bpf: Add log for attaching tracing programs to functions in deny list
  bpf: Show precise rejected function when attaching fexit/fmod_ret to __noreturn functions
  bpf: Fix various typos in verifier.c comments
  bpf: Add third round of bounds deduction
  selftests/bpf: Test invariants on JSLT crossing sign
  selftests/bpf: Test cross-sign 64bits range refinement
  selftests/bpf: Update reg_bound range refinement logic
  bpf: Improve bounds when s64 crosses sign boundary
  bpf: Simplify bounds refinement from s32
  selftests/bpf: Enable private stack tests for arm64
  bpf, arm64: JIT support for private stack
  bpf: Move bpf_jit_get_prog_name() to core.c
  bpf, arm64: Fix fp initialization for exception boundary
  umd: Remove usermode driver framework
  bpf/preload: Don't select USERMODE_DRIVER
  selftests/bpf: Fix test dynptr/test_dynptr_memset_xdp_chunks failure
  selftests/bpf: Fix test dynptr/test_dynptr_copy_xdp failure
  selftests/bpf: Increase xdp data size for arm64 64K page size
  ...

1 files changed, 87 insertions, 29 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e8e63bd025c7..64739308902f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -858,26 +858,43 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 EXPORT_SYMBOL_GPL(btf_type_by_id);
 
 /*
- * Regular int is not a bit field and it must be either
- * u8/u16/u32/u64 or __int128.
+ * Check that the type @t is a regular int. This means that @t is not
+ * a bit field and it has the same size as either of u8/u16/u32/u64
+ * or __int128. If @expected_size is not zero, then size of @t should
+ * be the same. A caller should already have checked that the type @t
+ * is an integer.
  */
+static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size)
+{
+	u32 int_data = btf_type_int(t);
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+	return BITS_PER_BYTE_MASKED(nr_bits) == 0 &&
+	       BTF_INT_OFFSET(int_data) == 0 &&
+	       (nr_bytes <= 16 && is_power_of_2(nr_bytes)) &&
+	       (expected_size == 0 || nr_bytes == expected_size);
+}
+
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
-	u8 nr_bits, nr_bytes;
-	u32 int_data;
+	return __btf_type_int_is_regular(t, 0);
+}
 
-	int_data = btf_type_int(t);
-	nr_bits = BTF_INT_BITS(int_data);
-	nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
-	if (BITS_PER_BYTE_MASKED(nr_bits) ||
-	    BTF_INT_OFFSET(int_data) ||
-	    (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
-	     nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
-	     nr_bytes != (2 * sizeof(u64)))) {
-		return false;
-	}
+bool btf_type_is_i32(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4);
+}
 
-	return true;
+bool btf_type_is_i64(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8);
+}
+
+bool btf_type_is_primitive(const struct btf_type *t)
+{
+	return (btf_type_is_int(t) && btf_type_int_is_regular(t)) ||
+	       btf_is_any_enum(t);
 }
 
 /*
@@ -3443,7 +3460,8 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
 	node_field_name = strstr(value_type, ":");
 	if (!node_field_name)
 		return -EINVAL;
-	value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __GFP_NOWARN);
+	value_type = kstrndup(value_type, node_field_name - value_type,
+			      GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!value_type)
 		return -ENOMEM;
 	id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT);
@@ -3958,7 +3976,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 	/* This needs to be kzalloc to zero out padding and unused fields, see
 	 * comment in btf_record_equal.
 	 */
-	rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL | __GFP_NOWARN);
+	rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!rec)
 		return ERR_PTR(-ENOMEM);
 
@@ -6182,8 +6200,7 @@ int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_ty
 	return kctx_type_id;
 }
 
-BTF_ID_LIST(bpf_ctx_convert_btf_id)
-BTF_ID(struct, bpf_ctx_convert)
+BTF_ID_LIST_SINGLE(bpf_ctx_convert_btf_id, struct, bpf_ctx_convert)
 
 static struct btf *btf_parse_base(struct btf_verifier_env *env, const char *name,
 				  void *data, unsigned int data_size)
@@ -6903,6 +6920,7 @@ enum bpf_struct_walk_result {
 	/* < 0 error */
 	WALK_SCALAR = 0,
 	WALK_PTR,
+	WALK_PTR_UNTRUSTED,
 	WALK_STRUCT,
 };
 
@@ -7144,6 +7162,8 @@ error:
 					*field_name = mname;
 				return WALK_PTR;
 			}
+
+			return WALK_PTR_UNTRUSTED;
 		}
 
 		/* Allow more flexible access within an int as long as
@@ -7216,6 +7236,9 @@ int btf_struct_access(struct bpf_verifier_log *log,
 			*next_btf_id = id;
 			*flag = tmp_flag;
 			return PTR_TO_BTF_ID;
+		case WALK_PTR_UNTRUSTED:
+			*flag = MEM_RDONLY | PTR_UNTRUSTED;
+			return PTR_TO_MEM;
 		case WALK_SCALAR:
 			return SCALAR_VALUE;
 		case WALK_STRUCT:
@@ -7628,11 +7651,12 @@ cand_cache_unlock:
 }
 
 enum btf_arg_tag {
-	ARG_TAG_CTX	 = BIT_ULL(0),
-	ARG_TAG_NONNULL  = BIT_ULL(1),
-	ARG_TAG_TRUSTED  = BIT_ULL(2),
-	ARG_TAG_NULLABLE = BIT_ULL(3),
-	ARG_TAG_ARENA	 = BIT_ULL(4),
+	ARG_TAG_CTX	  = BIT_ULL(0),
+	ARG_TAG_NONNULL   = BIT_ULL(1),
+	ARG_TAG_TRUSTED   = BIT_ULL(2),
+	ARG_TAG_UNTRUSTED = BIT_ULL(3),
+	ARG_TAG_NULLABLE  = BIT_ULL(4),
+	ARG_TAG_ARENA	  = BIT_ULL(5),
 };
 
 /* Process BTF of a function to produce high-level expectation of function
@@ -7740,6 +7764,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 				tags |= ARG_TAG_CTX;
 			} else if (strcmp(tag, "trusted") == 0) {
 				tags |= ARG_TAG_TRUSTED;
+			} else if (strcmp(tag, "untrusted") == 0) {
+				tags |= ARG_TAG_UNTRUSTED;
 			} else if (strcmp(tag, "nonnull") == 0) {
 				tags |= ARG_TAG_NONNULL;
 			} else if (strcmp(tag, "nullable") == 0) {
@@ -7800,6 +7826,38 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 			sub->args[i].btf_id = kern_type_id;
 			continue;
 		}
+		if (tags & ARG_TAG_UNTRUSTED) {
+			struct btf *vmlinux_btf;
+			int kern_type_id;
+
+			if (tags & ~ARG_TAG_UNTRUSTED) {
+				bpf_log(log, "arg#%d untrusted cannot be combined with any other tags\n", i);
+				return -EINVAL;
+			}
+
+			ref_t = btf_type_skip_modifiers(btf, t->type, NULL);
+			if (btf_type_is_void(ref_t) || btf_type_is_primitive(ref_t)) {
+				sub->args[i].arg_type = ARG_PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED;
+				sub->args[i].mem_size = 0;
+				continue;
+			}
+
+			kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t);
+			if (kern_type_id < 0)
+				return kern_type_id;
+
+			vmlinux_btf = bpf_get_btf_vmlinux();
+			ref_t = btf_type_by_id(vmlinux_btf, kern_type_id);
+			if (!btf_type_is_struct(ref_t)) {
+				tname = __btf_name_by_offset(vmlinux_btf, t->name_off);
+				bpf_log(log, "arg#%d has type %s '%s', but only struct or primitive types are allowed\n",
+					i, btf_type_str(ref_t), tname);
+				return -EINVAL;
+			}
+			sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_UNTRUSTED;
+			sub->args[i].btf_id = kern_type_id;
+			continue;
+		}
 		if (tags & ARG_TAG_ARENA) {
 			if (tags & ~ARG_TAG_ARENA) {
 				bpf_log(log, "arg#%d arena cannot be combined with any other tags\n", i);
@@ -9019,7 +9077,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
 		bpf_free_cands_from_cache(*cc);
 		*cc = NULL;
 	}
-	new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
+	new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL_ACCOUNT);
 	if (!new_cands) {
 		bpf_free_cands(cands);
 		return ERR_PTR(-ENOMEM);
@@ -9027,7 +9085,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
 	/* strdup the name, since it will stay in cache.
 	 * the cands->name points to strings in prog's BTF and the prog can be unloaded.
 	 */
-	new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL);
+	new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL_ACCOUNT);
 	bpf_free_cands(cands);
 	if (!new_cands->name) {
 		kfree(new_cands);
@@ -9111,7 +9169,7 @@ bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf,
 			continue;
 
 		/* most of the time there is only one candidate for a given kind+name pair */
-		new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL);
+		new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL_ACCOUNT);
 		if (!new_cands) {
 			bpf_free_cands(cands);
 			return ERR_PTR(-ENOMEM);
@@ -9228,7 +9286,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
 	/* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
 	 * into arrays of btf_ids of struct fields and array indices.
 	 */
-	specs = kcalloc(3, sizeof(*specs), GFP_KERNEL);
+	specs = kcalloc(3, sizeof(*specs), GFP_KERNEL_ACCOUNT);
 	if (!specs)
 		return -ENOMEM;
 
@@ -9253,7 +9311,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
 			goto out;
 		}
 		if (cc->cnt) {
-			cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL);
+			cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL_ACCOUNT);
 			if (!cands.cands) {
 				err = -ENOMEM;
 				goto out;