summaryrefslogtreecommitdiff
path: root/kernel/bpf/trampoline.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/trampoline.c')
-rw-r--r--kernel/bpf/trampoline.c217
1 files changed, 152 insertions, 65 deletions
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index f8302a5ca400..976d89011b15 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -115,10 +115,14 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
}
-void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym)
+void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym)
{
ksym->start = (unsigned long) data;
ksym->end = ksym->start + size;
+}
+
+void bpf_image_ksym_add(struct bpf_ksym *ksym)
+{
bpf_ksym_add(ksym);
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
PAGE_SIZE, false, ksym->name);
@@ -171,23 +175,42 @@ out:
return tr;
}
-static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+static int bpf_trampoline_update_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+ void *old_addr, void *new_addr)
{
+ enum bpf_text_poke_type new_t = BPF_MOD_CALL, old_t = BPF_MOD_CALL;
void *ip = tr->func.addr;
+
+ if (!new_addr)
+ new_t = BPF_MOD_NOP;
+ else if (bpf_trampoline_use_jmp(tr->flags))
+ new_t = BPF_MOD_JUMP;
+
+ if (!old_addr)
+ old_t = BPF_MOD_NOP;
+ else if (bpf_trampoline_use_jmp(orig_flags))
+ old_t = BPF_MOD_JUMP;
+
+ return bpf_arch_text_poke(ip, old_t, new_t, old_addr, new_addr);
+}
+
+static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+ void *old_addr)
+{
int ret;
if (tr->func.ftrace_managed)
ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
else
- ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+ ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr, NULL);
return ret;
}
-static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr,
+static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+ void *old_addr, void *new_addr,
bool lock_direct_mutex)
{
- void *ip = tr->func.addr;
int ret;
if (tr->func.ftrace_managed) {
@@ -196,7 +219,8 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
else
ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
} else {
- ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
+ ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr,
+ new_addr);
}
return ret;
}
@@ -216,10 +240,12 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
}
if (tr->func.ftrace_managed) {
- ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
+ ret = ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
+ if (ret)
+ return ret;
ret = register_ftrace_direct(tr->fops, (long)new_addr);
} else {
- ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+ ret = bpf_trampoline_update_fentry(tr, 0, NULL, new_addr);
}
return ret;
@@ -330,8 +356,9 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
* call_rcu_tasks() is not necessary.
*/
if (im->ip_after_call) {
- int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
- NULL, im->ip_epilogue);
+ int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_NOP,
+ BPF_MOD_JUMP, NULL,
+ im->ip_epilogue);
WARN_ON(err);
if (IS_ENABLED(CONFIG_TASKS_RCU))
call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
@@ -377,7 +404,8 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size)
ksym = &im->ksym;
INIT_LIST_HEAD_RCU(&ksym->lnode);
snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key);
- bpf_image_ksym_add(image, size, ksym);
+ bpf_image_ksym_init(image, size, ksym);
+ bpf_image_ksym_add(ksym);
return im;
out_free_image:
@@ -403,7 +431,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
return PTR_ERR(tlinks);
if (total == 0) {
- err = unregister_fentry(tr, tr->cur_image->image);
+ err = unregister_fentry(tr, orig_flags, tr->cur_image->image);
bpf_tramp_image_put(tr->cur_image);
tr->cur_image = NULL;
goto out;
@@ -427,9 +455,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
again:
- if ((tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) &&
- (tr->flags & BPF_TRAMP_F_CALL_ORIG))
- tr->flags |= BPF_TRAMP_F_ORIG_STACK;
+ if (tr->flags & BPF_TRAMP_F_CALL_ORIG) {
+ if (tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) {
+ /* The BPF_TRAMP_F_SKIP_FRAME can be cleared in the
+ * first try, reset it in the second try.
+ */
+ tr->flags |= BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SKIP_FRAME;
+ } else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_JMP)) {
+ /* Use "jmp" instead of "call" for the trampoline
+ * in the origin call case, and we don't need to
+ * skip the frame.
+ */
+ tr->flags &= ~BPF_TRAMP_F_SKIP_FRAME;
+ }
+ }
#endif
size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
@@ -460,10 +499,18 @@ again:
if (err)
goto out_free;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+ if (bpf_trampoline_use_jmp(tr->flags))
+ tr->fops->flags |= FTRACE_OPS_FL_JMP;
+ else
+ tr->fops->flags &= ~FTRACE_OPS_FL_JMP;
+#endif
+
WARN_ON(tr->cur_image && total == 0);
if (tr->cur_image)
/* progs already running at this address */
- err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex);
+ err = modify_fentry(tr, orig_flags, tr->cur_image->image,
+ im->image, lock_direct_mutex);
else
/* first time registering */
err = register_fentry(tr, im->image);
@@ -474,11 +521,6 @@ again:
* BPF_TRAMP_F_SHARE_IPMODIFY is set, we can generate the
* trampoline again, and retry register.
*/
- /* reset fops->func and fops->trampoline for re-register */
- tr->fops->func = NULL;
- tr->fops->trampoline = 0;
-
- /* free im memory and reallocate later */
bpf_tramp_image_free(im);
goto again;
}
@@ -491,8 +533,15 @@ again:
tr->cur_image = im;
out:
/* If any error happens, restore previous flags */
- if (err)
+ if (err) {
tr->flags = orig_flags;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+ if (bpf_trampoline_use_jmp(tr->flags))
+ tr->fops->flags |= FTRACE_OPS_FL_JMP;
+ else
+ tr->fops->flags &= ~FTRACE_OPS_FL_JMP;
+#endif
+ }
kfree(tlinks);
return err;
@@ -523,7 +572,27 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
}
}
-static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
+static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog)
+{
+ struct bpf_prog_aux *aux = tgt_prog->aux;
+
+ guard(mutex)(&aux->ext_mutex);
+ if (aux->prog_array_member_cnt)
+ /* Program extensions can not extend target prog when the target
+ * prog has been updated to any prog_array map as tail callee.
+ * It's to prevent a potential infinite loop like:
+ * tgt prog entry -> tgt prog subprog -> freplace prog entry
+ * --tailcall-> tgt prog entry.
+ */
+ return -EBUSY;
+
+ aux->is_extended = true;
+ return 0;
+}
+
+static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+ struct bpf_trampoline *tr,
+ struct bpf_prog *tgt_prog)
{
enum bpf_tramp_prog_type kind;
struct bpf_tramp_link *link_exiting;
@@ -544,8 +613,12 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr
/* Cannot attach extension if fentry/fexit are in use. */
if (cnt)
return -EBUSY;
+ err = bpf_freplace_check_tgt_prog(tgt_prog);
+ if (err)
+ return err;
tr->extension_prog = link->link.prog;
- return bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
+ return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP,
+ BPF_MOD_JUMP, NULL,
link->link.prog->bpf_func);
}
if (cnt >= BPF_MAX_TRAMP_LINKS)
@@ -570,17 +643,21 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr
return err;
}
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+ struct bpf_trampoline *tr,
+ struct bpf_prog *tgt_prog)
{
int err;
mutex_lock(&tr->mutex);
- err = __bpf_trampoline_link_prog(link, tr);
+ err = __bpf_trampoline_link_prog(link, tr, tgt_prog);
mutex_unlock(&tr->mutex);
return err;
}
-static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
+static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+ struct bpf_trampoline *tr,
+ struct bpf_prog *tgt_prog)
{
enum bpf_tramp_prog_type kind;
int err;
@@ -589,8 +666,11 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_
if (kind == BPF_TRAMP_REPLACE) {
WARN_ON_ONCE(!tr->extension_prog);
err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
+ BPF_MOD_NOP,
tr->extension_prog->bpf_func, NULL);
tr->extension_prog = NULL;
+ guard(mutex)(&tgt_prog->aux->ext_mutex);
+ tgt_prog->aux->is_extended = false;
return err;
}
hlist_del_init(&link->tramp_hlist);
@@ -599,12 +679,14 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_
}
/* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+ struct bpf_trampoline *tr,
+ struct bpf_prog *tgt_prog)
{
int err;
mutex_lock(&tr->mutex);
- err = __bpf_trampoline_unlink_prog(link, tr);
+ err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog);
mutex_unlock(&tr->mutex);
return err;
}
@@ -619,7 +701,7 @@ static void bpf_shim_tramp_link_release(struct bpf_link *link)
if (!shim_link->trampoline)
return;
- WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline));
+ WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL));
bpf_trampoline_put(shim_link->trampoline);
}
@@ -638,7 +720,8 @@ static const struct bpf_link_ops bpf_shim_tramp_link_lops = {
static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog,
bpf_func_t bpf_func,
- int cgroup_atype)
+ int cgroup_atype,
+ enum bpf_attach_type attach_type)
{
struct bpf_shim_tramp_link *shim_link = NULL;
struct bpf_prog *p;
@@ -665,7 +748,7 @@ static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog
p->expected_attach_type = BPF_LSM_MAC;
bpf_prog_inc(p);
bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
- &bpf_shim_tramp_link_lops, p);
+ &bpf_shim_tramp_link_lops, p, attach_type);
bpf_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype);
return shim_link;
@@ -690,7 +773,8 @@ static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
}
int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
- int cgroup_atype)
+ int cgroup_atype,
+ enum bpf_attach_type attach_type)
{
struct bpf_shim_tramp_link *shim_link = NULL;
struct bpf_attach_target_info tgt_info = {};
@@ -727,13 +811,13 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
/* Allocate and install new shim. */
- shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype);
+ shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype, attach_type);
if (!shim_link) {
err = -ENOMEM;
goto err;
}
- err = __bpf_trampoline_link_prog(&shim_link->link, tr);
+ err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL);
if (err)
goto err;
@@ -861,39 +945,45 @@ static __always_inline u64 notrace bpf_prog_start_time(void)
static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
__acquires(RCU)
{
- rcu_read_lock();
- migrate_disable();
+ rcu_read_lock_dont_migrate();
run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
bpf_prog_inc_misses_counter(prog);
+ if (prog->aux->recursion_detected)
+ prog->aux->recursion_detected(prog);
return 0;
}
return bpf_prog_start_time();
}
-static void notrace update_prog_stats(struct bpf_prog *prog,
- u64 start)
+static void notrace __update_prog_stats(struct bpf_prog *prog, u64 start)
{
struct bpf_prog_stats *stats;
+ unsigned long flags;
+ u64 duration;
- if (static_branch_unlikely(&bpf_stats_enabled_key) &&
- /* static_key could be enabled in __bpf_prog_enter*
- * and disabled in __bpf_prog_exit*.
- * And vice versa.
- * Hence check that 'start' is valid.
- */
- start > NO_START_TIME) {
- u64 duration = sched_clock() - start;
- unsigned long flags;
-
- stats = this_cpu_ptr(prog->stats);
- flags = u64_stats_update_begin_irqsave(&stats->syncp);
- u64_stats_inc(&stats->cnt);
- u64_stats_add(&stats->nsecs, duration);
- u64_stats_update_end_irqrestore(&stats->syncp, flags);
- }
+ /*
+ * static_key could be enabled in __bpf_prog_enter* and disabled in
+ * __bpf_prog_exit*. And vice versa. Check that 'start' is valid.
+ */
+ if (start <= NO_START_TIME)
+ return;
+
+ duration = sched_clock() - start;
+ stats = this_cpu_ptr(prog->stats);
+ flags = u64_stats_update_begin_irqsave(&stats->syncp);
+ u64_stats_inc(&stats->cnt);
+ u64_stats_add(&stats->nsecs, duration);
+ u64_stats_update_end_irqrestore(&stats->syncp, flags);
+}
+
+static __always_inline void notrace update_prog_stats(struct bpf_prog *prog,
+ u64 start)
+{
+ if (static_branch_unlikely(&bpf_stats_enabled_key))
+ __update_prog_stats(prog, start);
}
static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
@@ -904,8 +994,7 @@ static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
update_prog_stats(prog, start);
this_cpu_dec(*(prog->active));
- migrate_enable();
- rcu_read_unlock();
+ rcu_read_unlock_migrate();
}
static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
@@ -915,8 +1004,7 @@ static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
/* Runtime stats are exported via actual BPF_LSM_CGROUP
* programs, not the shims.
*/
- rcu_read_lock();
- migrate_disable();
+ rcu_read_lock_dont_migrate();
run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
@@ -929,8 +1017,7 @@ static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
{
bpf_reset_run_ctx(run_ctx->saved_run_ctx);
- migrate_enable();
- rcu_read_unlock();
+ rcu_read_unlock_migrate();
}
u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
@@ -944,6 +1031,8 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
bpf_prog_inc_misses_counter(prog);
+ if (prog->aux->recursion_detected)
+ prog->aux->recursion_detected(prog);
return 0;
}
return bpf_prog_start_time();
@@ -986,8 +1075,7 @@ static u64 notrace __bpf_prog_enter(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx)
__acquires(RCU)
{
- rcu_read_lock();
- migrate_disable();
+ rcu_read_lock_dont_migrate();
run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
@@ -1001,8 +1089,7 @@ static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start,
bpf_reset_run_ctx(run_ctx->saved_run_ctx);
update_prog_stats(prog, start);
- migrate_enable();
- rcu_read_unlock();
+ rcu_read_unlock_migrate();
}
void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr)
generated by cgit (git 2.34.1) at 2025-12-25 02:07:29 +0000