diff options
Diffstat (limited to 'kernel/bpf/trampoline.c')
| -rw-r--r-- | kernel/bpf/trampoline.c | 157 |
1 files changed, 139 insertions, 18 deletions
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 23b0d5cfd47e..6b264a92064b 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -4,16 +4,98 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ftrace.h> +#include <linux/rbtree_latch.h> + +/* dummy _ops. The verifier will operate on target program's ops. */ +const struct bpf_verifier_ops bpf_extension_verifier_ops = { +}; +const struct bpf_prog_ops bpf_extension_prog_ops = { +}; /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 #define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; +static struct latch_tree_root image_tree __cacheline_aligned; -/* serializes access to trampoline_table */ +/* serializes access to trampoline_table and image_tree */ static DEFINE_MUTEX(trampoline_mutex); +static void *bpf_jit_alloc_exec_page(void) +{ + void *image; + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return NULL; + + set_vm_flush_reset_perms(image); + /* Keep image as writeable. The alternative is to keep flipping ro/rw + * everytime new program is attached or detached. + */ + set_memory_x((long)image, 1); + return image; +} + +static __always_inline bool image_tree_less(struct latch_tree_node *a, + struct latch_tree_node *b) +{ + struct bpf_image *ia = container_of(a, struct bpf_image, tnode); + struct bpf_image *ib = container_of(b, struct bpf_image, tnode); + + return ia < ib; +} + +static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n) +{ + void *image = container_of(n, struct bpf_image, tnode); + + if (addr < image) + return -1; + if (addr >= image + PAGE_SIZE) + return 1; + + return 0; +} + +static const struct latch_tree_ops image_tree_ops = { + .less = image_tree_less, + .comp = image_tree_comp, +}; + +static void *__bpf_image_alloc(bool lock) +{ + struct bpf_image *image; + + image = bpf_jit_alloc_exec_page(); + if (!image) + return NULL; + + if (lock) + mutex_lock(&trampoline_mutex); + latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops); + if (lock) + mutex_unlock(&trampoline_mutex); + return image->data; +} + +void *bpf_image_alloc(void) +{ + return __bpf_image_alloc(true); +} + +bool is_bpf_image_address(unsigned long addr) +{ + bool ret; + + rcu_read_lock(); + ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL; + rcu_read_unlock(); + + return ret; +} + struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { struct bpf_trampoline *tr; @@ -34,7 +116,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) goto out; /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = bpf_jit_alloc_exec(PAGE_SIZE); + image = __bpf_image_alloc(false); if (!image) { kfree(tr); tr = NULL; @@ -48,12 +130,6 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) mutex_init(&tr->mutex); for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); - - set_vm_flush_reset_perms(image); - /* Keep image as writeable. The alternative is to keep flipping ro/rw - * everytime new program is attached or detached. - */ - set_memory_x((long)image, 1); tr->image = image; out: mutex_unlock(&trampoline_mutex); @@ -115,14 +191,14 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) } /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 + * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ #define BPF_MAX_TRAMP_PROGS 40 static int bpf_trampoline_update(struct bpf_trampoline *tr) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2; struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; @@ -150,11 +226,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (fexit_cnt) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; - err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags, + /* Though the second half of trampoline page is unused a task could be + * preempted in the middle of the first half of trampoline and two + * updates to trampoline would change the code from underneath the + * preempted task. Hence wait for tasks to voluntarily schedule or go + * to userspace. + */ + synchronize_rcu_tasks(); + + err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, + &tr->func.model, flags, fentry, fentry_cnt, fexit, fexit_cnt, tr->func.addr); - if (err) + if (err < 0) goto out; if (tr->selector) @@ -175,8 +260,10 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) switch (t) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; - default: + case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; + default: + return BPF_TRAMP_REPLACE; } } @@ -185,12 +272,31 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog) enum bpf_tramp_prog_type kind; struct bpf_trampoline *tr; int err = 0; + int cnt; tr = prog->aux->trampoline; kind = bpf_attach_type_to_tramp(prog->expected_attach_type); mutex_lock(&tr->mutex); - if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT] - >= BPF_MAX_TRAMP_PROGS) { + if (tr->extension_prog) { + /* cannot attach fentry/fexit if extension prog is attached. + * cannot overwrite extension prog either. + */ + err = -EBUSY; + goto out; + } + cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + if (kind == BPF_TRAMP_REPLACE) { + /* Cannot attach extension if fentry/fexit are in use. */ + if (cnt) { + err = -EBUSY; + goto out; + } + tr->extension_prog = prog; + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, + prog->bpf_func); + goto out; + } + if (cnt >= BPF_MAX_TRAMP_PROGS) { err = -E2BIG; goto out; } @@ -221,15 +327,25 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog) tr = prog->aux->trampoline; kind = bpf_attach_type_to_tramp(prog->expected_attach_type); mutex_lock(&tr->mutex); + if (kind == BPF_TRAMP_REPLACE) { + WARN_ON_ONCE(!tr->extension_prog); + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, + tr->extension_prog->bpf_func, NULL); + tr->extension_prog = NULL; + goto out; + } hlist_del(&prog->aux->tramp_hlist); tr->progs_cnt[kind]--; err = bpf_trampoline_update(prog->aux->trampoline); +out: mutex_unlock(&tr->mutex); return err; } void bpf_trampoline_put(struct bpf_trampoline *tr) { + struct bpf_image *image; + if (!tr) return; mutex_lock(&trampoline_mutex); @@ -240,7 +356,11 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) goto out; if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; - bpf_jit_free_exec(tr->image); + image = container_of(tr->image, struct bpf_image, data); + latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops); + /* wait for tasks to get out of trampoline before freeing it */ + synchronize_rcu_tasks(); + bpf_jit_free_exec(image); hlist_del(&tr->hlist); kfree(tr); out: @@ -286,7 +406,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) } int __weak -arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, +arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, struct bpf_prog **fentry_progs, int fentry_cnt, struct bpf_prog **fexit_progs, int fexit_cnt, void *orig_call) |