diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-10 11:26:21 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-10 11:26:21 -0800 |
| commit | f17b474e36647c23801ef8fdaf2255ab66dd2973 (patch) | |
| tree | 7fbaa4d93d71d72eb1cf8f61201eb42881daaeb0 /kernel/trace | |
| parent | a7423e6ea2f8f6f453de79213c26f7a36c86d9a2 (diff) | |
| parent | db975debcb8c4cd367a78811bc1ba84c83f854bd (diff) | |
Merge tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Pull bpf updates from Alexei Starovoitov:
- Support associating BPF program with struct_ops (Amery Hung)
- Switch BPF local storage to rqspinlock and remove recursion detection
counters which were causing false positives (Amery Hung)
- Fix live registers marking for indirect jumps (Anton Protopopov)
- Introduce execution context detection BPF helpers (Changwoo Min)
- Improve verifier precision for 32bit sign extension pattern
(Cupertino Miranda)
- Optimize BTF type lookup by sorting vmlinux BTF and doing binary
search (Donglin Peng)
- Allow states pruning for misc/invalid slots in iterator loops (Eduard
Zingerman)
- In preparation for ASAN support in BPF arenas teach libbpf to move
global BPF variables to the end of the region and enable arena kfuncs
while holding locks (Emil Tsalapatis)
- Introduce support for implicit arguments in kfuncs and migrate a
number of them to new API. This is a prerequisite for cgroup
sub-schedulers in sched-ext (Ihor Solodrai)
- Fix incorrect copied_seq calculation in sockmap (Jiayuan Chen)
- Fix ORC stack unwind from kprobe_multi (Jiri Olsa)
- Speed up fentry attach by using single ftrace direct ops in BPF
trampolines (Jiri Olsa)
- Require frozen map for calculating map hash (KP Singh)
- Fix lock entry creation in TAS fallback in rqspinlock (Kumar
Kartikeya Dwivedi)
- Allow user space to select cpu in lookup/update operations on per-cpu
array and hash maps (Leon Hwang)
- Make kfuncs return trusted pointers by default (Matt Bobrowski)
- Introduce "fsession" support where single BPF program is executed
upon entry and exit from traced kernel function (Menglong Dong)
- Allow bpf_timer and bpf_wq use in all programs types (Mykyta
Yatsenko, Andrii Nakryiko, Kumar Kartikeya Dwivedi, Alexei
Starovoitov)
- Make KF_TRUSTED_ARGS the default for all kfuncs and clean up their
definition across the tree (Puranjay Mohan)
- Allow BPF arena calls from non-sleepable context (Puranjay Mohan)
- Improve register id comparison logic in the verifier and extend
linked registers with negative offsets (Puranjay Mohan)
- In preparation for BPF-OOM introduce kfuncs to access memcg events
(Roman Gushchin)
- Use CFI compatible destructor kfunc type (Sami Tolvanen)
- Add bitwise tracking for BPF_END in the verifier (Tianci Cao)
- Add range tracking for BPF_DIV and BPF_MOD in the verifier (Yazhou
Tang)
- Make BPF selftests work with 64k page size (Yonghong Song)
* tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (268 commits)
selftests/bpf: Fix outdated test on storage->smap
selftests/bpf: Choose another percpu variable in bpf for btf_dump test
selftests/bpf: Remove test_task_storage_map_stress_lookup
selftests/bpf: Update task_local_storage/task_storage_nodeadlock test
selftests/bpf: Update task_local_storage/recursion test
selftests/bpf: Update sk_storage_omem_uncharge test
bpf: Switch to bpf_selem_unlink_nofail in bpf_local_storage_{map_free, destroy}
bpf: Support lockless unlink when freeing map or local storage
bpf: Prepare for bpf_selem_unlink_nofail()
bpf: Remove unused percpu counter from bpf_local_storage_map_free
bpf: Remove cgroup local storage percpu counter
bpf: Remove task local storage percpu counter
bpf: Change local_storage->lock and b->lock to rqspinlock
bpf: Convert bpf_selem_unlink to failable
bpf: Convert bpf_selem_link_map to failable
bpf: Convert bpf_selem_unlink_map to failable
bpf: Select bpf_local_storage_map_bucket based on bpf_local_storage
selftests/xsk: fix number of Tx frags in invalid packet
selftests/xsk: properly handle batch ending in the middle of a packet
bpf: Prevent reentrance into call_rcu_tasks_trace()
...
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/Kconfig | 3 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 84 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 407 |
3 files changed, 438 insertions, 56 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index bfa2ec46e075..d7042a09fe46 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -50,6 +50,9 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS bool +config HAVE_SINGLE_FTRACE_DIRECT_OPS + bool + config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS bool diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fe28d86f7c35..f7baeb8278ca 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -830,7 +830,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struc info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; - info.si_value.sival_ptr = (void *)(unsigned long)value; + info.si_value.sival_ptr = (void __user __force *)(unsigned long)value; siginfo = &info; } @@ -1022,7 +1022,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .func = bpf_snprintf_btf, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, @@ -1194,7 +1194,7 @@ const struct bpf_func_proto bpf_get_branch_snapshot_proto = { BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) { /* This helper call is inlined by verifier. */ - u64 nr_args = ((u64 *)ctx)[-1]; + u64 nr_args = ((u64 *)ctx)[-1] & 0xFF; if ((u64) n >= nr_args) return -EINVAL; @@ -1214,7 +1214,7 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = { BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) { /* This helper call is inlined by verifier. */ - u64 nr_args = ((u64 *)ctx)[-1]; + u64 nr_args = ((u64 *)ctx)[-1] & 0xFF; *value = ((u64 *)ctx)[nr_args]; return 0; @@ -1231,7 +1231,7 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = { BPF_CALL_1(get_func_arg_cnt, void *, ctx) { /* This helper call is inlined by verifier. */ - return ((u64 *)ctx)[-1]; + return ((u64 *)ctx)[-1] & 0xFF; } static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { @@ -1286,7 +1286,8 @@ static bool is_kprobe_multi(const struct bpf_prog *prog) static inline bool is_kprobe_session(const struct bpf_prog *prog) { - return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; + return prog->type == BPF_PROG_TYPE_KPROBE && + prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; } static inline bool is_uprobe_multi(const struct bpf_prog *prog) @@ -1297,7 +1298,14 @@ static inline bool is_uprobe_multi(const struct bpf_prog *prog) static inline bool is_uprobe_session(const struct bpf_prog *prog) { - return prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; + return prog->type == BPF_PROG_TYPE_KPROBE && + prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; +} + +static inline bool is_trace_fsession(const struct bpf_prog *prog) +{ + return prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_FSESSION; } static const struct bpf_func_proto * @@ -1526,7 +1534,7 @@ static const struct bpf_func_proto bpf_read_branch_records_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg2_type = ARG_PTR_TO_MEM_OR_NULL | MEM_WRITE, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -1661,7 +1669,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -1734,11 +1742,17 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_d_path: return &bpf_d_path_proto; case BPF_FUNC_get_func_arg: - return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; + if (bpf_prog_has_trampoline(prog) || + prog->expected_attach_type == BPF_TRACE_RAW_TP) + return &bpf_get_func_arg_proto; + return NULL; case BPF_FUNC_get_func_ret: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; case BPF_FUNC_get_func_arg_cnt: - return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; + if (bpf_prog_has_trampoline(prog) || + prog->expected_attach_type == BPF_TRACE_RAW_TP) + return &bpf_get_func_arg_cnt_proto; + return NULL; case BPF_FUNC_get_attach_cookie: if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) @@ -2063,7 +2077,7 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) struct bpf_trace_run_ctx run_ctx; cant_sleep(); - if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { + if (unlikely(!bpf_prog_get_recursion_context(prog))) { bpf_prog_inc_misses_counter(prog); goto out; } @@ -2077,7 +2091,7 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) bpf_reset_run_ctx(old_run_ctx); out: - this_cpu_dec(*(prog->active)); + bpf_prog_put_recursion_context(prog); } #define UNPACK(...) __VA_ARGS__ @@ -2564,6 +2578,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); + ftrace_partial_regs_update(fregs, bpf_kprobe_multi_pt_regs_ptr()); rcu_read_unlock(); out: @@ -3316,7 +3331,7 @@ static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx) __bpf_kfunc_start_defs(); -__bpf_kfunc bool bpf_session_is_return(void) +__bpf_kfunc bool bpf_session_is_return(void *ctx) { struct bpf_session_run_ctx *session_ctx; @@ -3324,7 +3339,7 @@ __bpf_kfunc bool bpf_session_is_return(void) return session_ctx->is_return; } -__bpf_kfunc __u64 *bpf_session_cookie(void) +__bpf_kfunc __u64 *bpf_session_cookie(void *ctx) { struct bpf_session_run_ctx *session_ctx; @@ -3334,34 +3349,39 @@ __bpf_kfunc __u64 *bpf_session_cookie(void) __bpf_kfunc_end_defs(); -BTF_KFUNCS_START(kprobe_multi_kfunc_set_ids) +BTF_KFUNCS_START(session_kfunc_set_ids) BTF_ID_FLAGS(func, bpf_session_is_return) BTF_ID_FLAGS(func, bpf_session_cookie) -BTF_KFUNCS_END(kprobe_multi_kfunc_set_ids) +BTF_KFUNCS_END(session_kfunc_set_ids) -static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id) +static int bpf_session_filter(const struct bpf_prog *prog, u32 kfunc_id) { - if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id)) + if (!btf_id_set8_contains(&session_kfunc_set_ids, kfunc_id)) return 0; - if (!is_kprobe_session(prog) && !is_uprobe_session(prog)) + if (!is_kprobe_session(prog) && !is_uprobe_session(prog) && !is_trace_fsession(prog)) return -EACCES; return 0; } -static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { +static const struct btf_kfunc_id_set bpf_session_kfunc_set = { .owner = THIS_MODULE, - .set = &kprobe_multi_kfunc_set_ids, - .filter = bpf_kprobe_multi_filter, + .set = &session_kfunc_set_ids, + .filter = bpf_session_filter, }; -static int __init bpf_kprobe_multi_kfuncs_init(void) +static int __init bpf_trace_kfuncs_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); + int err = 0; + + err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_session_kfunc_set); + err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_session_kfunc_set); + + return err; } -late_initcall(bpf_kprobe_multi_kfuncs_init); +late_initcall(bpf_trace_kfuncs_init); typedef int (*copy_fn_t)(void *dst, const void *src, u32 size, struct task_struct *tsk); @@ -3517,7 +3537,7 @@ __bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid __bpf_kfunc int bpf_probe_read_user_dynptr(struct bpf_dynptr *dptr, u64 off, u64 size, const void __user *unsafe_ptr__ign) { - return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_data_nofault, NULL); } @@ -3531,7 +3551,7 @@ __bpf_kfunc int bpf_probe_read_kernel_dynptr(struct bpf_dynptr *dptr, u64 off, __bpf_kfunc int bpf_probe_read_user_str_dynptr(struct bpf_dynptr *dptr, u64 off, u64 size, const void __user *unsafe_ptr__ign) { - return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy_str(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_str_nofault, NULL); } @@ -3545,14 +3565,14 @@ __bpf_kfunc int bpf_probe_read_kernel_str_dynptr(struct bpf_dynptr *dptr, u64 of __bpf_kfunc int bpf_copy_from_user_dynptr(struct bpf_dynptr *dptr, u64 off, u64 size, const void __user *unsafe_ptr__ign) { - return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_data_sleepable, NULL); } __bpf_kfunc int bpf_copy_from_user_str_dynptr(struct bpf_dynptr *dptr, u64 off, u64 size, const void __user *unsafe_ptr__ign) { - return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy_str(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_str_sleepable, NULL); } @@ -3560,7 +3580,7 @@ __bpf_kfunc int bpf_copy_from_user_task_dynptr(struct bpf_dynptr *dptr, u64 off, u64 size, const void __user *unsafe_ptr__ign, struct task_struct *tsk) { - return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_data_sleepable, tsk); } @@ -3568,7 +3588,7 @@ __bpf_kfunc int bpf_copy_from_user_task_str_dynptr(struct bpf_dynptr *dptr, u64 u64 size, const void __user *unsafe_ptr__ign, struct task_struct *tsk) { - return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, + return __bpf_dynptr_copy_str(dptr, off, size, (const void __force *)unsafe_ptr__ign, copy_user_str_sleepable, tsk); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index aa758efc3731..f9b10c633bdd 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -68,7 +68,6 @@ }) /* hash bits for specific function selection */ -#define FTRACE_HASH_DEFAULT_BITS 10 #define FTRACE_HASH_MAX_BITS 12 #ifdef CONFIG_DYNAMIC_FTRACE @@ -1210,8 +1209,8 @@ static void __add_hash_entry(struct ftrace_hash *hash, hash->count++; } -static struct ftrace_func_entry * -add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +struct ftrace_func_entry * +add_ftrace_hash_entry_direct(struct ftrace_hash *hash, unsigned long ip, unsigned long direct) { struct ftrace_func_entry *entry; @@ -1220,11 +1219,18 @@ add_hash_entry(struct ftrace_hash *hash, unsigned long ip) return NULL; entry->ip = ip; + entry->direct = direct; __add_hash_entry(hash, entry); return entry; } +static struct ftrace_func_entry * +add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + return add_ftrace_hash_entry_direct(hash, ip, 0); +} + static void free_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) @@ -1283,7 +1289,7 @@ static void clear_ftrace_mod_list(struct list_head *head) mutex_unlock(&ftrace_lock); } -static void free_ftrace_hash(struct ftrace_hash *hash) +void free_ftrace_hash(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) return; @@ -1323,7 +1329,7 @@ void ftrace_free_filter(struct ftrace_ops *ops) } EXPORT_SYMBOL_GPL(ftrace_free_filter); -static struct ftrace_hash *alloc_ftrace_hash(int size_bits) +struct ftrace_hash *alloc_ftrace_hash(int size_bits) { struct ftrace_hash *hash; int size; @@ -1397,7 +1403,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - if (add_hash_entry(new_hash, entry->ip) == NULL) + if (add_ftrace_hash_entry_direct(new_hash, entry->ip, entry->direct) == NULL) goto free_hash; } } @@ -2068,7 +2074,7 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, */ if (!ops->ops_func) return -EBUSY; - ret = ops->ops_func(ops, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF); + ret = ops->ops_func(ops, rec->ip, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF); if (ret) return ret; } else if (is_ipmodify) { @@ -2624,8 +2630,13 @@ unsigned long ftrace_find_rec_direct(unsigned long ip) static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - unsigned long addr = READ_ONCE(ops->direct_call); + unsigned long addr; +#ifdef CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS + addr = ftrace_find_rec_direct(ip); +#else + addr = READ_ONCE(ops->direct_call); +#endif if (!addr) return; @@ -6049,15 +6060,8 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) if (ftrace_hash_empty(hash)) return -EINVAL; - /* This is a "raw" address, and this should never happen. */ - if (WARN_ON_ONCE(ftrace_is_jmp(addr))) - return -EINVAL; - mutex_lock(&direct_mutex); - if (ops->flags & FTRACE_OPS_FL_JMP) - addr = ftrace_jmp_set(addr); - /* Make sure requested entries are not already registered.. */ size = 1 << hash->size_bits; for (i = 0; i < size; i++) { @@ -6178,13 +6182,6 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) lockdep_assert_held_once(&direct_mutex); - /* This is a "raw" address, and this should never happen. */ - if (WARN_ON_ONCE(ftrace_is_jmp(addr))) - return -EINVAL; - - if (ops->flags & FTRACE_OPS_FL_JMP) - addr = ftrace_jmp_set(addr); - /* Enable the tmp_ops to have the same functions as the direct ops */ ftrace_ops_init(&tmp_ops); tmp_ops.func_hash = ops->func_hash; @@ -6289,6 +6286,368 @@ int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) return err; } EXPORT_SYMBOL_GPL(modify_ftrace_direct); + +static unsigned long hash_count(struct ftrace_hash *hash) +{ + return hash ? hash->count : 0; +} + +/** + * hash_add - adds two struct ftrace_hash and returns the result + * @a: struct ftrace_hash object + * @b: struct ftrace_hash object + * + * Returns struct ftrace_hash object on success, NULL on error. + */ +static struct ftrace_hash *hash_add(struct ftrace_hash *a, struct ftrace_hash *b) +{ + struct ftrace_func_entry *entry; + struct ftrace_hash *add; + int size; + + size = hash_count(a) + hash_count(b); + if (size > 32) + size = 32; + + add = alloc_and_copy_ftrace_hash(fls(size), a); + if (!add) + return NULL; + + size = 1 << b->size_bits; + for (int i = 0; i < size; i++) { + hlist_for_each_entry(entry, &b->buckets[i], hlist) { + if (add_ftrace_hash_entry_direct(add, entry->ip, entry->direct) == NULL) { + free_ftrace_hash(add); + return NULL; + } + } + } + return add; +} + +/** + * update_ftrace_direct_add - Updates @ops by adding direct + * callers provided in @hash + * @ops: The address of the struct ftrace_ops object + * @hash: The address of the struct ftrace_hash object + * + * This is used to add custom direct callers (ip -> addr) to @ops, + * specified in @hash. The @ops will be either registered or updated. + * + * Returns: zero on success. Non zero on error, which includes: + * -EINVAL - The @hash is empty + */ +int update_ftrace_direct_add(struct ftrace_ops *ops, struct ftrace_hash *hash) +{ + struct ftrace_hash *old_direct_functions = NULL; + struct ftrace_hash *new_direct_functions; + struct ftrace_hash *old_filter_hash; + struct ftrace_hash *new_filter_hash = NULL; + struct ftrace_func_entry *entry; + int err = -EINVAL; + int size; + bool reg; + + if (!hash_count(hash)) + return -EINVAL; + + mutex_lock(&direct_mutex); + + /* Make sure requested entries are not already registered. */ + size = 1 << hash->size_bits; + for (int i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + if (__ftrace_lookup_ip(direct_functions, entry->ip)) + goto out_unlock; + } + } + + old_filter_hash = ops->func_hash ? ops->func_hash->filter_hash : NULL; + + /* If there's nothing in filter_hash we need to register the ops. */ + reg = hash_count(old_filter_hash) == 0; + if (reg) { + if (ops->func || ops->trampoline) + goto out_unlock; + if (ops->flags & FTRACE_OPS_FL_ENABLED) + goto out_unlock; + } + + err = -ENOMEM; + new_filter_hash = hash_add(old_filter_hash, hash); + if (!new_filter_hash) + goto out_unlock; + + new_direct_functions = hash_add(direct_functions, hash); + if (!new_direct_functions) + goto out_unlock; + + old_direct_functions = direct_functions; + rcu_assign_pointer(direct_functions, new_direct_functions); + + if (reg) { + ops->func = call_direct_funcs; + ops->flags |= MULTI_FLAGS; + ops->trampoline = FTRACE_REGS_ADDR; + ops->local_hash.filter_hash = new_filter_hash; + + err = register_ftrace_function_nolock(ops); + if (err) { + /* restore old filter on error */ + ops->local_hash.filter_hash = old_filter_hash; + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; + } else { + new_filter_hash = old_filter_hash; + } + } else { + err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); + /* + * new_filter_hash is dup-ed, so we need to release it anyway, + * old_filter_hash either stays on error or is already released + */ + } + + if (err) { + /* reset direct_functions and free the new one */ + rcu_assign_pointer(direct_functions, old_direct_functions); + old_direct_functions = new_direct_functions; + } + + out_unlock: + mutex_unlock(&direct_mutex); + + if (old_direct_functions && old_direct_functions != EMPTY_HASH) + call_rcu_tasks(&old_direct_functions->rcu, register_ftrace_direct_cb); + free_ftrace_hash(new_filter_hash); + + return err; +} + +/** + * hash_sub - substracts @b from @a and returns the result + * @a: struct ftrace_hash object + * @b: struct ftrace_hash object + * + * Returns struct ftrace_hash object on success, NULL on error. + */ +static struct ftrace_hash *hash_sub(struct ftrace_hash *a, struct ftrace_hash *b) +{ + struct ftrace_func_entry *entry, *del; + struct ftrace_hash *sub; + int size; + + sub = alloc_and_copy_ftrace_hash(a->size_bits, a); + if (!sub) + return NULL; + + size = 1 << b->size_bits; + for (int i = 0; i < size; i++) { + hlist_for_each_entry(entry, &b->buckets[i], hlist) { + del = __ftrace_lookup_ip(sub, entry->ip); + if (WARN_ON_ONCE(!del)) { + free_ftrace_hash(sub); + return NULL; + } + remove_hash_entry(sub, del); + kfree(del); + } + } + return sub; +} + +/** + * update_ftrace_direct_del - Updates @ops by removing its direct + * callers provided in @hash + * @ops: The address of the struct ftrace_ops object + * @hash: The address of the struct ftrace_hash object + * + * This is used to delete custom direct callers (ip -> addr) in + * @ops specified via @hash. The @ops will be either unregistered + * updated. + * + * Returns: zero on success. Non zero on error, which includes: + * -EINVAL - The @hash is empty + * -EINVAL - The @ops is not registered + */ +int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash) +{ + struct ftrace_hash *old_direct_functions = NULL; + struct ftrace_hash *new_direct_functions; + struct ftrace_hash *new_filter_hash = NULL; + struct ftrace_hash *old_filter_hash; + struct ftrace_func_entry *entry; + struct ftrace_func_entry *del; + unsigned long size; + int err = -EINVAL; + + if (!hash_count(hash)) + return -EINVAL; + if (check_direct_multi(ops)) + return -EINVAL; + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EINVAL; + if (direct_functions == EMPTY_HASH) + return -EINVAL; + + mutex_lock(&direct_mutex); + + old_filter_hash = ops->func_hash ? ops->func_hash->filter_hash : NULL; + + if (!hash_count(old_filter_hash)) + goto out_unlock; + + /* Make sure requested entries are already registered. */ + size = 1 << hash->size_bits; + for (int i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + del = __ftrace_lookup_ip(direct_functions, entry->ip); + if (!del || del->direct != entry->direct) + goto out_unlock; + } + } + + err = -ENOMEM; + new_filter_hash = hash_sub(old_filter_hash, hash); + if (!new_filter_hash) + goto out_unlock; + + new_direct_functions = hash_sub(direct_functions, hash); + if (!new_direct_functions) + goto out_unlock; + + /* If there's nothing left, we need to unregister the ops. */ + if (ftrace_hash_empty(new_filter_hash)) { + err = unregister_ftrace_function(ops); + if (!err) { + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; + ftrace_free_filter(ops); + ops->func_hash->filter_hash = NULL; + } + } else { + err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); + /* + * new_filter_hash is dup-ed, so we need to release it anyway, + * old_filter_hash either stays on error or is already released + */ + } + + if (err) { + /* free the new_direct_functions */ + old_direct_functions = new_direct_functions; + } else { + old_direct_functions = direct_functions; + rcu_assign_pointer(direct_functions, new_direct_functions); + } + + out_unlock: + mutex_unlock(&direct_mutex); + + if (old_direct_functions && old_direct_functions != EMPTY_HASH) + call_rcu_tasks(&old_direct_functions->rcu, register_ftrace_direct_cb); + free_ftrace_hash(new_filter_hash); + + return err; +} + +/** + * update_ftrace_direct_mod - Updates @ops by modifing its direct + * callers provided in @hash + * @ops: The address of the struct ftrace_ops object + * @hash: The address of the struct ftrace_hash object + * @do_direct_lock: If true lock the direct_mutex + * + * This is used to modify custom direct callers (ip -> addr) in + * @ops specified via @hash. + * + * This can be called from within ftrace ops_func callback with + * direct_mutex already locked, in which case @do_direct_lock + * needs to be false. + * + * Returns: zero on success. Non zero on error, which includes: + * -EINVAL - The @hash is empty + * -EINVAL - The @ops is not registered + */ +int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, bool do_direct_lock) +{ + struct ftrace_func_entry *entry, *tmp; + static struct ftrace_ops tmp_ops = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_STUB, + }; + struct ftrace_hash *orig_hash; + unsigned long size, i; + int err = -EINVAL; + + if (!hash_count(hash)) + return -EINVAL; + if (check_direct_multi(ops)) + return -EINVAL; + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EINVAL; + if (direct_functions == EMPTY_HASH) + return -EINVAL; + + /* + * We can be called from within ops_func callback with direct_mutex + * already taken. + */ + if (do_direct_lock) + mutex_lock(&direct_mutex); + + orig_hash = ops->func_hash ? ops->func_hash->filter_hash : NULL; + if (!orig_hash) + goto unlock; + + /* Enable the tmp_ops to have the same functions as the direct ops */ + ftrace_ops_init(&tmp_ops); + tmp_ops.func_hash = ops->func_hash; + + err = register_ftrace_function_nolock(&tmp_ops); + if (err) + goto unlock; + + /* + * Call __ftrace_hash_update_ipmodify() here, so that we can call + * ops->ops_func for the ops. This is needed because the above + * register_ftrace_function_nolock() worked on tmp_ops. + */ + err = __ftrace_hash_update_ipmodify(ops, orig_hash, orig_hash, true); + if (err) + goto out; + + /* + * Now the ftrace_ops_list_func() is called to do the direct callers. + * We can safely change the direct functions attached to each entry. + */ + mutex_lock(&ftrace_lock); + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + tmp = __ftrace_lookup_ip(direct_functions, entry->ip); + if (!tmp) + continue; + tmp->direct = entry->direct; + } + } + + mutex_unlock(&ftrace_lock); + +out: + /* Removing the tmp_ops will add the updated direct callers to the functions */ + unregister_ftrace_function(&tmp_ops); + +unlock: + if (do_direct_lock) + mutex_unlock(&direct_mutex); + return err; +} + #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** @@ -8709,7 +9068,7 @@ static int prepare_direct_functions_for_ipmodify(struct ftrace_ops *ops) if (!op->ops_func) return -EBUSY; - ret = op->ops_func(op, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER); + ret = op->ops_func(op, ip, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER); if (ret) return ret; } @@ -8756,7 +9115,7 @@ static void cleanup_direct_functions_after_ipmodify(struct ftrace_ops *ops) /* The cleanup is optional, ignore any errors */ if (found_op && op->ops_func) - op->ops_func(op, FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER); + op->ops_func(op, ip, FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER); } } mutex_unlock(&direct_mutex); |
