diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bpf/btf.c | 16 | ||||
| -rw-r--r-- | kernel/bpf/devmap.c | 29 | ||||
| -rw-r--r-- | kernel/bpf/dispatcher.c | 4 | ||||
| -rw-r--r-- | kernel/bpf/inode.c | 3 | ||||
| -rw-r--r-- | kernel/bpf/trampoline.c | 80 | ||||
| -rw-r--r-- | kernel/extable.c | 7 |
6 files changed, 112 insertions, 27 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 32963b6d5a9c..b7c1660fb594 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3669,6 +3669,19 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) } } +static bool is_string_ptr(struct btf *btf, const struct btf_type *t) +{ + /* t comes in already as a pointer */ + t = btf_type_by_id(btf, t->type); + + /* allow const */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) + t = btf_type_by_id(btf, t->type); + + /* char, signed char, unsigned char */ + return btf_type_is_int(t) && t->size == 1; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -3735,6 +3748,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, */ return true; + if (is_string_ptr(btf, t)) + return true; + /* this is a pointer to another type */ info->reg_type = PTR_TO_BTF_ID; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index de630f980282..58bdca5d978a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -190,10 +190,12 @@ static void dev_map_free(struct bpf_map *map) /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were - * disconnected from events. Wait for outstanding critical sections in - * these programs to complete. The rcu critical section only guarantees - * no further reads against netdev_map. It does __not__ ensure pending - * flush operations (if any) are complete. + * disconnected from events. The following synchronize_rcu() guarantees + * both rcu read critical sections complete and waits for + * preempt-disable regions (NAPI being the relevant context here) so we + * are certain there will be no further reads against the netdev_map and + * all flush operations are complete. Flush operations can only be done + * from NAPI context for this reason. */ spin_lock(&dev_map_lock); @@ -263,7 +265,8 @@ struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; - hlist_for_each_entry_rcu(dev, head, index_hlist) + hlist_for_each_entry_rcu(dev, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; @@ -363,16 +366,17 @@ error: * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the * net device can be torn down. On devmap tear down we ensure the flush list * is empty before completing to ensure all flush operations have completed. + * When drivers update the bpf program they may need to ensure any flush ops + * are also complete. Using synchronize_rcu or call_rcu will suffice for this + * because both wait for napi context to exit. */ void __dev_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; - rcu_read_lock(); list_for_each_entry_safe(bq, tmp, flush_list, flush_node) bq_xmit_all(bq, XDP_XMIT_FLUSH); - rcu_read_unlock(); } /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or @@ -502,12 +506,11 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; /* Use call_rcu() here to ensure any rcu critical sections have - * completed, but this does not guarantee a flush has happened - * yet. Because driver side rcu_read_lock/unlock only protects the - * running XDP program. However, for pending flush operations the - * dev and ctx are stored in another per cpu map. And additionally, - * the driver tear down ensures all soft irqs are complete before - * removing the net device in the case of dev_put equals zero. + * completed as well as any flush operations because call_rcu + * will wait for preempt-disable region to complete, NAPI in this + * context. And additionally, the driver tear down ensures all + * soft irqs are complete before removing the net device in the + * case of dev_put equals zero. */ old_dev = xchg(&dtab->netdev_map[k], NULL); if (old_dev) diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index 204ee61a3904..b3e5b214fed8 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -113,7 +113,7 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) noff = 0; } else { old = d->image + d->image_off; - noff = d->image_off ^ (PAGE_SIZE / 2); + noff = d->image_off ^ (BPF_IMAGE_SIZE / 2); } new = d->num_progs ? d->image + noff : NULL; @@ -140,7 +140,7 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, mutex_lock(&d->mutex); if (!d->image) { - d->image = bpf_jit_alloc_exec_page(); + d->image = bpf_image_alloc(); if (!d->image) goto out; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e11059b99f18..bd2fd8eab470 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -196,6 +196,7 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) void *key = map_iter(m)->key; void *prev_key; + (*pos)++; if (map_iter(m)->done) return NULL; @@ -208,8 +209,6 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) map_iter(m)->done = true; return NULL; } - - ++(*pos); return key; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index eb64c245052b..6b264a92064b 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -4,6 +4,7 @@ #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 = { @@ -16,11 +17,12 @@ const struct bpf_prog_ops bpf_extension_prog_ops = { #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); -void *bpf_jit_alloc_exec_page(void) +static void *bpf_jit_alloc_exec_page(void) { void *image; @@ -36,6 +38,64 @@ void *bpf_jit_alloc_exec_page(void) 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; @@ -56,7 +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(); + image = __bpf_image_alloc(false); if (!image) { kfree(tr); tr = NULL; @@ -131,14 +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]; @@ -174,7 +234,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) */ synchronize_rcu_tasks(); - err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, + err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, &tr->func.model, flags, fentry, fentry_cnt, fexit, fexit_cnt, @@ -284,6 +344,8 @@ out: void bpf_trampoline_put(struct bpf_trampoline *tr) { + struct bpf_image *image; + if (!tr) return; mutex_lock(&trampoline_mutex); @@ -294,9 +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; + 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(tr->image); + bpf_jit_free_exec(image); hlist_del(&tr->hlist); kfree(tr); out: diff --git a/kernel/extable.c b/kernel/extable.c index f6920a11e28a..a0024f27d3a1 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -131,8 +131,9 @@ int kernel_text_address(unsigned long addr) * triggers a stack trace, or a WARN() that happens during * coming back from idle, or cpu on or offlining. * - * is_module_text_address() as well as the kprobe slots - * and is_bpf_text_address() require RCU to be watching. + * is_module_text_address() as well as the kprobe slots, + * is_bpf_text_address() and is_bpf_image_address require + * RCU to be watching. */ no_rcu = !rcu_is_watching(); @@ -148,6 +149,8 @@ int kernel_text_address(unsigned long addr) goto out; if (is_bpf_text_address(addr)) goto out; + if (is_bpf_image_address(addr)) + goto out; ret = 0; out: if (no_rcu) |