diff options
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/Makefile | 5 | ||||
-rw-r--r-- | kernel/bpf/arraymap.c | 10 | ||||
-rw-r--r-- | kernel/bpf/bpf_iter.c | 539 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 2 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 49 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 146 | ||||
-rw-r--r-- | kernel/bpf/core.c | 8 | ||||
-rw-r--r-- | kernel/bpf/cpumap.c | 23 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 1 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 4 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 91 | ||||
-rw-r--r-- | kernel/bpf/inode.c | 5 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 2 | ||||
-rw-r--r-- | kernel/bpf/map_in_map.c | 2 | ||||
-rw-r--r-- | kernel/bpf/map_iter.c | 102 | ||||
-rw-r--r-- | kernel/bpf/queue_stack_maps.c | 4 | ||||
-rw-r--r-- | kernel/bpf/reuseport_array.c | 2 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 2 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 570 | ||||
-rw-r--r-- | kernel/bpf/task_iter.c | 353 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 198 | ||||
-rw-r--r-- | kernel/bpf/xskmap.c | 265 |
22 files changed, 1889 insertions, 494 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f2d7be596966..375b933010dd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,7 +2,7 @@ obj-y := core.o CFLAGS_core.o += $(call cc-disable-warning, override-init) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o @@ -12,9 +12,6 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o -ifeq ($(CONFIG_XDP_SOCKETS),y) -obj-$(CONFIG_BPF_SYSCALL) += xskmap.o -endif obj-$(CONFIG_BPF_SYSCALL) += offload.o endif ifeq ($(CONFIG_PERF_EVENTS),y) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1d6120fd5ba6..11584618e861 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -77,7 +77,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int ret, numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool unpriv = !capable(CAP_SYS_ADMIN); + bool bypass_spec_v1 = bpf_bypass_spec_v1(); u64 cost, array_size, mask64; struct bpf_map_memory mem; struct bpf_array *array; @@ -95,7 +95,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) mask64 -= 1; index_mask = mask64; - if (unpriv) { + if (!bypass_spec_v1) { /* round up array size to nearest power of 2, * since cpu will speculate within index_mask limits */ @@ -149,7 +149,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); } array->index_mask = index_mask; - array->map.unpriv_array = unpriv; + array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); @@ -219,7 +219,7 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - if (map->unpriv_array) { + if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { @@ -1058,7 +1058,7 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map, *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - if (map->unpriv_array) { + if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c new file mode 100644 index 000000000000..dd612b80b9fe --- /dev/null +++ b/kernel/bpf/bpf_iter.c @@ -0,0 +1,539 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ + +#include <linux/fs.h> +#include <linux/anon_inodes.h> +#include <linux/filter.h> +#include <linux/bpf.h> + +struct bpf_iter_target_info { + struct list_head list; + const struct bpf_iter_reg *reg_info; + u32 btf_id; /* cached value */ +}; + +struct bpf_iter_link { + struct bpf_link link; + struct bpf_iter_target_info *tinfo; +}; + +struct bpf_iter_priv_data { + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u64 session_id; + u64 seq_num; + bool done_stop; + u8 target_private[] __aligned(8); +}; + +static struct list_head targets = LIST_HEAD_INIT(targets); +static DEFINE_MUTEX(targets_mutex); + +/* protect bpf_iter_link changes */ +static DEFINE_MUTEX(link_mutex); + +/* incremented on every opened seq_file */ +static atomic64_t session_id; + +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link); + +static void bpf_iter_inc_seq_num(struct seq_file *seq) +{ + struct bpf_iter_priv_data *iter_priv; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + iter_priv->seq_num++; +} + +static void bpf_iter_dec_seq_num(struct seq_file *seq) +{ + struct bpf_iter_priv_data *iter_priv; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + iter_priv->seq_num--; +} + +static void bpf_iter_done_stop(struct seq_file *seq) +{ + struct bpf_iter_priv_data *iter_priv; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + iter_priv->done_stop = true; +} + +/* bpf_seq_read, a customized and simpler version for bpf iterator. + * no_llseek is assumed for this file. + * The following are differences from seq_read(): + * . fixed buffer size (PAGE_SIZE) + * . assuming no_llseek + * . stop() may call bpf program, handling potential overflow there + */ +static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, + loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + size_t n, offs, copied = 0; + int err = 0; + void *p; + + mutex_lock(&seq->lock); + + if (!seq->buf) { + seq->size = PAGE_SIZE; + seq->buf = kmalloc(seq->size, GFP_KERNEL); + if (!seq->buf) { + err = -ENOMEM; + goto done; + } + } + + if (seq->count) { + n = min(seq->count, size); + err = copy_to_user(buf, seq->buf + seq->from, n); + if (err) { + err = -EFAULT; + goto done; + } + seq->count -= n; + seq->from += n; + copied = n; + goto done; + } + + seq->from = 0; + p = seq->op->start(seq, &seq->index); + if (!p) + goto stop; + if (IS_ERR(p)) { + err = PTR_ERR(p); + seq->op->stop(seq, p); + seq->count = 0; + goto done; + } + + err = seq->op->show(seq, p); + if (err > 0) { + /* object is skipped, decrease seq_num, so next + * valid object can reuse the same seq_num. + */ + bpf_iter_dec_seq_num(seq); + seq->count = 0; + } else if (err < 0 || seq_has_overflowed(seq)) { + if (!err) + err = -E2BIG; + seq->op->stop(seq, p); + seq->count = 0; + goto done; + } + + while (1) { + loff_t pos = seq->index; + + offs = seq->count; + p = seq->op->next(seq, p, &seq->index); + if (pos == seq->index) { + pr_info_ratelimited("buggy seq_file .next function %ps " + "did not updated position index\n", + seq->op->next); + seq->index++; + } + + if (IS_ERR_OR_NULL(p)) + break; + + /* got a valid next object, increase seq_num */ + bpf_iter_inc_seq_num(seq); + + if (seq->count >= size) + break; + + err = seq->op->show(seq, p); + if (err > 0) { + bpf_iter_dec_seq_num(seq); + seq->count = offs; + } else if (err < 0 || seq_has_overflowed(seq)) { + seq->count = offs; + if (offs == 0) { + if (!err) + err = -E2BIG; + seq->op->stop(seq, p); + goto done; + } + break; + } + } +stop: + offs = seq->count; + /* bpf program called if !p */ + seq->op->stop(seq, p); + if (!p) { + if (!seq_has_overflowed(seq)) { + bpf_iter_done_stop(seq); + } else { + seq->count = offs; + if (offs == 0) { + err = -E2BIG; + goto done; + } + } + } + + n = min(seq->count, size); + err = copy_to_user(buf, seq->buf, n); + if (err) { + err = -EFAULT; + goto done; + } + copied = n; + seq->count -= n; + seq->from = n; +done: + if (!copied) + copied = err; + else + *ppos += copied; + mutex_unlock(&seq->lock); + return copied; +} + +static int iter_open(struct inode *inode, struct file *file) +{ + struct bpf_iter_link *link = inode->i_private; + + return prepare_seq_file(file, link); +} + +static int iter_release(struct inode *inode, struct file *file) +{ + struct bpf_iter_priv_data *iter_priv; + struct seq_file *seq; + + seq = file->private_data; + if (!seq) + return 0; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + + if (iter_priv->tinfo->reg_info->fini_seq_private) + iter_priv->tinfo->reg_info->fini_seq_private(seq->private); + + bpf_prog_put(iter_priv->prog); + seq->private = iter_priv; + + return seq_release_private(inode, file); +} + +const struct file_operations bpf_iter_fops = { + .open = iter_open, + .llseek = no_llseek, + .read = bpf_seq_read, + .release = iter_release, +}; + +/* The argument reg_info will be cached in bpf_iter_target_info. + * The common practice is to declare target reg_info as + * a const static variable and passed as an argument to + * bpf_iter_reg_target(). + */ +int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info) +{ + struct bpf_iter_target_info *tinfo; + + tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); + if (!tinfo) + return -ENOMEM; + + tinfo->reg_info = reg_info; + INIT_LIST_HEAD(&tinfo->list); + + mutex_lock(&targets_mutex); + list_add(&tinfo->list, &targets); + mutex_unlock(&targets_mutex); + + return 0; +} + +void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info) +{ + struct bpf_iter_target_info *tinfo; + bool found = false; + + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (reg_info == tinfo->reg_info) { + list_del(&tinfo->list); + kfree(tinfo); + found = true; + break; + } + } + mutex_unlock(&targets_mutex); + + WARN_ON(found == false); +} + +static void cache_btf_id(struct bpf_iter_target_info *tinfo, + struct bpf_prog *prog) +{ + tinfo->btf_id = prog->aux->attach_btf_id; +} + +bool bpf_iter_prog_supported(struct bpf_prog *prog) +{ + const char *attach_fname = prog->aux->attach_func_name; + u32 prog_btf_id = prog->aux->attach_btf_id; + const char *prefix = BPF_ITER_FUNC_PREFIX; + struct bpf_iter_target_info *tinfo; + int prefix_len = strlen(prefix); + bool supported = false; + + if (strncmp(attach_fname, prefix, prefix_len)) + return false; + + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) { + supported = true; + break; + } + if (!strcmp(attach_fname + prefix_len, tinfo->reg_info->target)) { + cache_btf_id(tinfo, prog); + supported = true; + break; + } + } + mutex_unlock(&targets_mutex); + + if (supported) { + prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; + prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; + } + + return supported; +} + +static void bpf_iter_link_release(struct bpf_link *link) +{ +} + +static void bpf_iter_link_dealloc(struct bpf_link *link) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + + kfree(iter_link); +} + +static int bpf_iter_link_replace(struct bpf_link *link, + struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + int ret = 0; + + mutex_lock(&link_mutex); + if (old_prog && link->prog != old_prog) { + ret = -EPERM; + goto out_unlock; + } + + if (link->prog->type != new_prog->type || + link->prog->expected_attach_type != new_prog->expected_attach_type || + link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) { + ret = -EINVAL; + goto out_unlock; + } + + old_prog = xchg(&link->prog, new_prog); + bpf_prog_put(old_prog); + +out_unlock: + mutex_unlock(&link_mutex); + return ret; +} + +static const struct bpf_link_ops bpf_iter_link_lops = { + .release = bpf_iter_link_release, + .dealloc = bpf_iter_link_dealloc, + .update_prog = bpf_iter_link_replace, +}; + +bool bpf_link_is_iter(struct bpf_link *link) +{ + return link->ops == &bpf_iter_link_lops; +} + +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_iter_target_info *tinfo; + struct bpf_iter_link *link; + bool existed = false; + u32 prog_btf_id; + int err; + + if (attr->link_create.target_fd || attr->link_create.flags) + return -EINVAL; + + prog_btf_id = prog->aux->attach_btf_id; + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id == prog_btf_id) { + existed = true; + break; + } + } + mutex_unlock(&targets_mutex); + if (!existed) + return -ENOENT; + + link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); + if (!link) + return -ENOMEM; + + bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); + link->tinfo = tinfo; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + return err; + } + + return bpf_link_settle(&link_primer); +} + +static void init_seq_meta(struct bpf_iter_priv_data *priv_data, + struct bpf_iter_target_info *tinfo, + struct bpf_prog *prog) +{ + priv_data->tinfo = tinfo; + priv_data->prog = prog; + priv_data->session_id = atomic64_inc_return(&session_id); + priv_data->seq_num = 0; + priv_data->done_stop = false; +} + +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) +{ + struct bpf_iter_priv_data *priv_data; + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u32 total_priv_dsize; + struct seq_file *seq; + int err = 0; + + mutex_lock(&link_mutex); + prog = link->link.prog; + bpf_prog_inc(prog); + mutex_unlock(&link_mutex); + + tinfo = link->tinfo; + total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + + tinfo->reg_info->seq_priv_size; + priv_data = __seq_open_private(file, tinfo->reg_info->seq_ops, + total_priv_dsize); + if (!priv_data) { + err = -ENOMEM; + goto release_prog; + } + + if (tinfo->reg_info->init_seq_private) { + err = tinfo->reg_info->init_seq_private(priv_data->target_private); + if (err) + goto release_seq_file; + } + + init_seq_meta(priv_data, tinfo, prog); + seq = file->private_data; + seq->private = priv_data->target_private; + + return 0; + +release_seq_file: + seq_release_private(file->f_inode, file); + file->private_data = NULL; +release_prog: + bpf_prog_put(prog); + return err; +} + +int bpf_iter_new_fd(struct bpf_link *link) +{ + struct file *file; + unsigned int flags; + int err, fd; + + if (link->ops != &bpf_iter_link_lops) + return -EINVAL; + + flags = O_RDONLY | O_CLOEXEC; + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto free_fd; + } + + err = prepare_seq_file(file, + container_of(link, struct bpf_iter_link, link)); + if (err) + goto free_file; + + fd_install(fd, file); + return fd; + +free_file: + fput(file); +free_fd: + put_unused_fd(fd); + return err; +} + +struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop) +{ + struct bpf_iter_priv_data *iter_priv; + struct seq_file *seq; + void *seq_priv; + + seq = meta->seq; + if (seq->file->f_op != &bpf_iter_fops) + return NULL; + + seq_priv = seq->private; + iter_priv = container_of(seq_priv, struct bpf_iter_priv_data, + target_private); + + if (in_stop && iter_priv->done_stop) + return NULL; + + meta->session_id = iter_priv->session_id; + meta->seq_num = iter_priv->seq_num; + + return iter_priv->prog; +} + +int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) +{ + int ret; + + rcu_read_lock(); + migrate_disable(); + ret = BPF_PROG_RUN(prog, ctx); + migrate_enable(); + rcu_read_unlock(); + + /* bpf program can only return 0 or 1: + * 0 : okay + * 1 : retry the same object + * The bpf_iter_run_prog() return value + * will be seq_ops->show() return value. + */ + return ret == 0 ? 0 : -EAGAIN; +} diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 26cb51f2db72..c6b0decaa46a 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -557,7 +557,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) struct bpf_map *map; int err; - if (!capable(CAP_SYS_ADMIN)) + if (!bpf_capable()) return ERR_PTR(-EPERM); st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d65c6912bdaf..58c9af1d4808 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3482,6 +3482,7 @@ extern char __weak __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) static union { struct bpf_ctx_convert { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ @@ -3508,6 +3509,7 @@ static u8 bpf_ctx_convert_map[] = { 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE static const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, @@ -3692,7 +3694,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, struct bpf_verifier_log *log = info->log; const struct btf_param *args; u32 nr_args, arg; - int ret; + int i, ret; if (off % 8) { bpf_log(log, "func '%s' offset %d is not multiple of 8\n", @@ -3789,6 +3791,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* this is a pointer to another type */ info->reg_type = PTR_TO_BTF_ID; + for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { + const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; + + if (ctx_arg_info->offset == off) { + info->reg_type = ctx_arg_info->reg_type; + break; + } + } if (tgt_prog) { ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg); @@ -3828,6 +3838,7 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; const char *tname, *mname; + u32 vlen; again: tname = __btf_name_by_offset(btf_vmlinux, t->name_off); @@ -3836,7 +3847,43 @@ again: return -EINVAL; } + vlen = btf_type_vlen(t); if (off + size > t->size) { + /* If the last element is a variable size array, we may + * need to relax the rule. + */ + struct btf_array *array_elem; + + if (vlen == 0) + goto error; + + member = btf_type_member(t) + vlen - 1; + mtype = btf_type_skip_modifiers(btf_vmlinux, member->type, + NULL); + if (!btf_type_is_array(mtype)) + goto error; + + array_elem = (struct btf_array *)(mtype + 1); + if (array_elem->nelems != 0) + goto error; + + moff = btf_member_bit_offset(t, member) / 8; + if (off < moff) + goto error; + + /* Only allow structure for now, can be relaxed for + * other types later. + */ + elem_type = btf_type_skip_modifiers(btf_vmlinux, + array_elem->type, NULL); + if (!btf_type_is_struct(elem_type)) + goto error; + + off = (off - moff) % elem_type->size; + return btf_struct_access(log, elem_type, off, size, atype, + next_btf_id); + +error: bpf_log(log, "access beyond struct %s at off %u size %u\n", tname, off, size); return -EACCES; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index cb305e71e7de..5c0e964105ac 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -557,8 +557,9 @@ found: * * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, - struct bpf_prog *new_prog) +static int __cgroup_bpf_replace(struct cgroup *cgrp, + struct bpf_cgroup_link *link, + struct bpf_prog *new_prog) { struct list_head *progs = &cgrp->bpf.progs[link->type]; struct bpf_prog *old_prog; @@ -583,6 +584,30 @@ int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, return 0; } +static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + struct bpf_cgroup_link *cg_link; + int ret; + + cg_link = container_of(link, struct bpf_cgroup_link, link); + + mutex_lock(&cgroup_mutex); + /* link might have been auto-released by dying cgroup, so fail */ + if (!cg_link->cgroup) { + ret = -EINVAL; + goto out_unlock; + } + if (old_prog && link->prog != old_prog) { + ret = -EPERM; + goto out_unlock; + } + ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); +out_unlock: + mutex_unlock(&cgroup_mutex); + return ret; +} + static struct bpf_prog_list *find_detach_entry(struct list_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, @@ -808,17 +833,56 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link) kfree(cg_link); } -const struct bpf_link_ops bpf_cgroup_link_lops = { +static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + u64 cg_id = 0; + + mutex_lock(&cgroup_mutex); + if (cg_link->cgroup) + cg_id = cgroup_id(cg_link->cgroup); + mutex_unlock(&cgroup_mutex); + + seq_printf(seq, + "cgroup_id:\t%llu\n" + "attach_type:\t%d\n", + cg_id, + cg_link->type); +} + +static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + u64 cg_id = 0; + + mutex_lock(&cgroup_mutex); + if (cg_link->cgroup) + cg_id = cgroup_id(cg_link->cgroup); + mutex_unlock(&cgroup_mutex); + + info->cgroup.cgroup_id = cg_id; + info->cgroup.attach_type = cg_link->type; + return 0; +} + +static const struct bpf_link_ops bpf_cgroup_link_lops = { .release = bpf_cgroup_link_release, .dealloc = bpf_cgroup_link_dealloc, + .update_prog = cgroup_bpf_replace, + .show_fdinfo = bpf_cgroup_link_show_fdinfo, + .fill_link_info = bpf_cgroup_link_fill_link_info, }; int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + struct bpf_link_primer link_primer; struct bpf_cgroup_link *link; - struct file *link_file; struct cgroup *cgrp; - int err, link_fd; + int err; if (attr->link_create.flags) return -EINVAL; @@ -832,26 +896,25 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = -ENOMEM; goto out_put_cgroup; } - bpf_link_init(&link->link, &bpf_cgroup_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops, + prog); link->cgroup = cgrp; link->type = attr->link_create.attach_type; - link_file = bpf_link_new_file(&link->link, &link_fd); - if (IS_ERR(link_file)) { + err = bpf_link_prime(&link->link, &link_primer); + if (err) { kfree(link); - err = PTR_ERR(link_file); goto out_put_cgroup; } err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, BPF_F_ALLOW_MULTI); if (err) { - bpf_link_cleanup(&link->link, link_file, link_fd); + bpf_link_cleanup(&link_primer); goto out_put_cgroup; } - fd_install(link_fd, link_file); - return link_fd; + return bpf_link_settle(&link_primer); out_put_cgroup: cgroup_put(cgrp); @@ -1054,36 +1117,21 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, return !allow; } -EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); static const struct bpf_func_proto * cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { - case BPF_FUNC_map_lookup_elem: - return &bpf_map_lookup_elem_proto; - case BPF_FUNC_map_update_elem: - return &bpf_map_update_elem_proto; - case BPF_FUNC_map_delete_elem: - return &bpf_map_delete_elem_proto; - case BPF_FUNC_map_push_elem: - return &bpf_map_push_elem_proto; - case BPF_FUNC_map_pop_elem: - return &bpf_map_pop_elem_proto; - case BPF_FUNC_map_peek_elem: - return &bpf_map_peek_elem_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_trace_printk: - if (capable(CAP_SYS_ADMIN)) - return bpf_get_trace_printk_proto(); - /* fall through */ + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; default: - return NULL; + return bpf_base_func_proto(func_id); } } @@ -1137,16 +1185,13 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * @head: sysctl table header * @table: sysctl table * @write: sysctl is being read (= 0) or written (= 1) - * @buf: pointer to buffer passed by user space + * @buf: pointer to buffer (in and out) * @pcount: value-result argument: value is size of buffer pointed to by @buf, * result is size of @new_buf if program set new value, initial value * otherwise * @ppos: value-result argument: value is position at which read from or write * to sysctl is happening, result is new position if program overrode it, * initial value otherwise - * @new_buf: pointer to pointer to new buffer that will be allocated if program - * overrides new value provided by user space on sysctl write - * NOTE: it's caller responsibility to free *new_buf if it was set * @type: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and @@ -1157,8 +1202,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { */ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - void __user *buf, size_t *pcount, - loff_t *ppos, void **new_buf, + void **buf, size_t *pcount, loff_t *ppos, enum bpf_attach_type type) { struct bpf_sysctl_kern ctx = { @@ -1173,36 +1217,28 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, .new_updated = 0, }; struct cgroup *cgrp; + loff_t pos = 0; int ret; ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL); - if (ctx.cur_val) { - mm_segment_t old_fs; - loff_t pos = 0; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - if (table->proc_handler(table, 0, (void __user *)ctx.cur_val, - &ctx.cur_len, &pos)) { - /* Let BPF program decide how to proceed. */ - ctx.cur_len = 0; - } - set_fs(old_fs); - } else { + if (!ctx.cur_val || + table->proc_handler(table, 0, ctx.cur_val, &ctx.cur_len, &pos)) { /* Let BPF program decide how to proceed. */ ctx.cur_len = 0; } - if (write && buf && *pcount) { + if (write && *buf && *pcount) { /* BPF program should be able to override new value with a * buffer bigger than provided by user. */ ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL); ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount); - if (!ctx.new_val || - copy_from_user(ctx.new_val, buf, ctx.new_len)) + if (ctx.new_val) { + memcpy(ctx.new_val, *buf, ctx.new_len); + } else { /* Let BPF program decide how to proceed. */< |