From: Tejun Heo Passing an arena pointer to a kfunc takes two steps today. There is no arena pointer argument type, so the pointer crosses the boundary as a bare scalar, and the kfunc then offsets it by the arena base and casts it before it can touch the memory. Every such kfunc open-codes the same translation. Add the __arena and __arena__nullable argument suffixes to make this more convenient. The kfunc declares the parameter by its real pointer type and dereferences it directly, with the JIT rebasing the value at the call site, rN = kern_vm_start + (u32)rN. No bounds check is needed: the u32 offset stays within the guard-padded arena kernel mapping, and a fault on an unpopulated page recovers through the per-arena scratch page. A suffixed argument accepts a PTR_TO_ARENA or scalar register, matching global subprog arena arguments. __arena rebases unconditionally, so the kfunc never sees NULL and a value with zero in the low 32 bits arrives as the arena base. __arena__nullable preserves NULL for optional arguments by skipping the rebase when the truncated value, arena offset 0, is zero. Keeping the plain form NULL-free saves the NULL test on every call. The double separator makes the annotations composable: __arena__nullable also ends in __nullable. Match the composite suffix first when classifying kfunc arguments and function-model flags so it retains arena semantics while carrying the nullable flag. This patch adds the verifier side: the suffixes are recognized in check_kfunc_args() and distilled into argument flags in the function model stored in the kfunc descriptor. JITs retrieve the model while emitting the call, avoiding per-call state in insn_aux_data. JITs declare support with bpf_jit_supports_arena_args() and verification fails with -ENOTSUPP elsewhere. Signed-off-by: Tejun Heo Co-developed-by: Kumar Kartikeya Dwivedi Signed-off-by: Kumar Kartikeya Dwivedi --- Documentation/bpf/kfuncs.rst | 29 ++++++++++++++++++++ include/linux/bpf.h | 6 +++++ include/linux/filter.h | 1 + kernel/bpf/btf.c | 18 ++++++++++++- kernel/bpf/core.c | 5 ++++ kernel/bpf/verifier.c | 51 +++++++++++++++++++++++++++++++++--- 6 files changed, 105 insertions(+), 5 deletions(-) diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index cbde86d082cc..cd9b90d072cf 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -278,6 +278,33 @@ An example is given below:: ... } +2.3.8 __arena and __arena__nullable Annotations +----------------------------------------------- + +Both annotations indicate that the pointer argument points into the +calling program's arena. The JIT rebases the value at the call site so +the kfunc receives a directly dereferenceable kernel address, subject to +the access rules described in :ref:`BPF_kfunc_arena_access` (at most +``GUARD_SZ / 2``, 32 KiB, past the pointer in a single unchecked access). + +With ``__arena`` the rebase is unconditional and the argument is never +NULL: a value whose lower 32 bits are zero arrives as the arena base +address (arena offset 0). The kfunc must not check the argument for NULL. +With ``__arena__nullable`` such a value arrives as NULL instead and the +kfunc must check before dereferencing. + +An example is given below:: + + __bpf_kfunc int bpf_process_item(struct item *item__arena) + { + ... + } + +Calling such a kfunc requires the program to use an arena map and a JIT with +arena argument support (currently x86-64); verification fails otherwise. The +program can pass any value without compromising the kernel. A value that does +not point into the arena is a program bug. + .. _BPF_kfunc_nodef: 2.4 Using an existing kernel function @@ -515,6 +542,8 @@ In order to accommodate such requirements, the verifier will enforce strict PTR_TO_BTF_ID type matching if two types have the exact same name, with one being suffixed with ``___init``. +.. _BPF_kfunc_arena_access: + 2.8 Accessing arena memory through kfunc arguments -------------------------------------------------- diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 73bacfc6444d..f47556b56a48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1210,6 +1210,12 @@ struct bpf_prog_offload { /* The argument is signed. */ #define BTF_FMODEL_SIGNED_ARG BIT(1) +/* The argument is an arena pointer. */ +#define BTF_FMODEL_ARENA_ARG BIT(2) + +/* The argument is nullable. */ +#define BTF_FMODEL_NULLABLE_ARG BIT(3) + struct btf_func_model { u8 ret_size; u8 ret_flags; diff --git a/include/linux/filter.h b/include/linux/filter.h index 32d5297c557e..36ce3403fe59 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1183,6 +1183,7 @@ bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_stack_args(void); +bool bpf_jit_supports_arena_args(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 42414633cf26..4ff6148ae8e8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7539,6 +7539,22 @@ static u8 __get_type_fmodel_flags(const struct btf_type *t) return flags; } +static u8 __get_arg_fmodel_flags(const struct btf *btf, + const struct btf_param *arg, + const struct btf_type *t) +{ + u8 flags = __get_type_fmodel_flags(t); + + if (btf_param_match_suffix(btf, arg, "__arena__nullable")) + flags |= BTF_FMODEL_ARENA_ARG | BTF_FMODEL_NULLABLE_ARG; + else if (btf_param_match_suffix(btf, arg, "__arena")) + flags |= BTF_FMODEL_ARENA_ARG; + else if (btf_param_match_suffix(btf, arg, "__nullable")) + flags |= BTF_FMODEL_NULLABLE_ARG; + + return flags; +} + int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, @@ -7604,7 +7620,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->arg_size[i] = ret; - m->arg_flags[i] = __get_type_fmodel_flags(t); + m->arg_flags[i] = __get_arg_fmodel_flags(btf, &args[i], t); } m->nr_args = nargs; return 0; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index e2076667b245..a3e1fae32eac 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -3308,6 +3308,11 @@ bool __weak bpf_jit_supports_stack_args(void) return false; } +bool __weak bpf_jit_supports_arena_args(void) +{ + return false; +} + bool __weak bpf_jit_supports_far_kfunc_call(void) { return false; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b62e77949542..2b7f6f6bbe76 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10909,9 +10909,16 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } +static bool is_kfunc_arg_arena_nullable(const struct btf *btf, + const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__arena__nullable"); +} + static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { - return btf_param_match_suffix(btf, arg, "__nullable"); + return !is_kfunc_arg_arena_nullable(btf, arg) && + btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_nonown_allowed(const struct btf *btf, const struct btf_param *arg) @@ -10929,6 +10936,12 @@ static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param return btf_param_match_suffix(btf, arg, "__irq_flag"); } +static bool is_kfunc_arg_arena(const struct btf *btf, const struct btf_param *arg) +{ + return is_kfunc_arg_arena_nullable(btf, arg) || + btf_param_match_suffix(btf, arg, "__arena"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -11149,6 +11162,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_IRQ_FLAG, KF_ARG_PTR_TO_RES_SPIN_LOCK, KF_ARG_PTR_TO_TASK_WORK, + KF_ARG_PTR_TO_ARENA, }; enum special_kfunc_type { @@ -11434,7 +11448,6 @@ get_kfunc_arg_type(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, reg_arg_name(env, argno), btf_type_str(t)); return -EINVAL; } - ref_t = btf_type_skip_modifiers(meta->btf, t->type, NULL); ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off); @@ -11483,7 +11496,29 @@ get_kfunc_arg_type(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, arg_type = KF_ARG_PTR_TO_RES_SPIN_LOCK; else if (is_kfunc_arg_callback(env, meta->btf, &args[arg])) arg_type = KF_ARG_PTR_TO_CALLBACK; - else if (arg + 1 < nargs && + else if (is_kfunc_arg_arena(meta->btf, &args[arg])) { + if (!bpf_jit_supports_arena_args()) { + verbose(env, "JIT does not support kfunc %s() with arena pointer arguments\n", + meta->func_name); + return -ENOTSUPP; + } + if (!env->prog->aux->arena) { + verbose(env, + "%s arena pointer requires a program with an associated arena\n", + reg_arg_name(env, argno)); + return -EINVAL; + } + if (reg_from_argno(argno) < 0) { + verbose(env, "%s arena pointer cannot be a stack argument\n", + reg_arg_name(env, argno)); + return -EINVAL; + } + /* + * Both suffixes accept a constant zero. The function model determines + * whether the JIT rebases it to the arena base or preserves NULL. + */ + arg_type = KF_ARG_PTR_TO_ARENA | PTR_MAYBE_NULL; + } else if (arg + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[arg + 1]) || is_kfunc_arg_const_mem_size(meta->btf, &args[arg + 1]))) { if (!btf_type_is_void(ref_t) && !btf_type_is_scalar(ref_t) && @@ -12177,7 +12212,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_ptr(t) && (bpf_register_is_null(reg) || type_may_be_null(reg->type)) && - !is_kfunc_arg_nullable(meta->btf, &args[i])) { + !type_may_be_null(kf_arg_type)) { verbose(env, "Possibly NULL pointer passed to trusted %s\n", reg_arg_name(env, argno)); return -EACCES; @@ -12230,6 +12265,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me case KF_ARG_PTR_TO_TASK_WORK: case KF_ARG_PTR_TO_IRQ_FLAG: case KF_ARG_PTR_TO_RES_SPIN_LOCK: + case KF_ARG_PTR_TO_ARENA: break; case KF_ARG_PTR_TO_DYNPTR: arg_type = ARG_PTR_TO_DYNPTR; @@ -12296,6 +12332,13 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me meta->ret_btf_id = ret; } break; + case KF_ARG_PTR_TO_ARENA: + if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { + verbose(env, "%s is not a pointer to arena or scalar\n", + reg_arg_name(env, argno)); + return -EINVAL; + } + break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) { if (!is_bpf_obj_drop_kfunc(meta->func_id)) { -- 2.53.0