summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/Makefile3
-rw-r--r--kernel/bpf/arraymap.c6
-rw-r--r--kernel/bpf/cgroup.c570
-rw-r--r--kernel/bpf/core.c180
-rw-r--r--kernel/bpf/cpumap.c706
-rw-r--r--kernel/bpf/devmap.c5
-rw-r--r--kernel/bpf/disasm.c214
-rw-r--r--kernel/bpf/disasm.h32
-rw-r--r--kernel/bpf/hashtab.c5
-rw-r--r--kernel/bpf/inode.c15
-rw-r--r--kernel/bpf/lpm_trie.c98
-rw-r--r--kernel/bpf/offload.c194
-rw-r--r--kernel/bpf/percpu_freelist.c8
-rw-r--r--kernel/bpf/sockmap.c9
-rw-r--r--kernel/bpf/stackmap.c5
-rw-r--r--kernel/bpf/syscall.c325
-rw-r--r--kernel/bpf/verifier.c1480
-rw-r--r--kernel/cgroup/cgroup.c38
-rw-r--r--kernel/events/core.c31
-rw-r--r--kernel/trace/bpf_trace.c177
-rw-r--r--kernel/trace/trace_kprobe.c6
-rw-r--r--kernel/trace/trace_syscalls.c34
-rw-r--r--kernel/trace/trace_uprobe.c3
23 files changed, 3213 insertions, 931 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index af3ab6164ff5..e691da0b3bab 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -3,8 +3,11 @@ obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+obj-$(CONFIG_BPF_SYSCALL) += offload.o
ifeq ($(CONFIG_STREAM_PARSER),y)
obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c4b9ab01bba5..7c25426d3cf5 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -19,6 +19,9 @@
#include "map_in_map.h"
+#define ARRAY_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
@@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE ||
+ attr->value_size == 0 ||
+ attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
(percpu && numa_node != NUMA_NO_NODE))
return ERR_PTR(-EINVAL);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 546113430049..b789ab78d28f 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -27,129 +27,405 @@ void cgroup_bpf_put(struct cgroup *cgrp)
{
unsigned int type;
- for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) {
- struct bpf_prog *prog = cgrp->bpf.prog[type];
-
- if (prog) {
- bpf_prog_put(prog);
+ for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ struct bpf_prog_list *pl, *tmp;
+
+ list_for_each_entry_safe(pl, tmp, progs, node) {
+ list_del(&pl->node);
+ bpf_prog_put(pl->prog);
+ kfree(pl);
static_branch_dec(&cgroup_bpf_enabled_key);
}
+ bpf_prog_array_free(cgrp->bpf.effective[type]);
+ }
+}
+
+/* count number of elements in the list.
+ * it's slow but the list cannot be long
+ */
+static u32 prog_list_length(struct list_head *head)
+{
+ struct bpf_prog_list *pl;
+ u32 cnt = 0;
+
+ list_for_each_entry(pl, head, node) {
+ if (!pl->prog)
+ continue;
+ cnt++;
}
+ return cnt;
+}
+
+/* if parent has non-overridable prog attached,
+ * disallow attaching new programs to the descendent cgroup.
+ * if parent has overridable or multi-prog, allow attaching
+ */
+static bool hierarchy_allows_attach(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ u32 new_flags)
+{
+ struct cgroup *p;
+
+ p = cgroup_parent(cgrp);
+ if (!p)
+ return true;
+ do {
+ u32 flags = p->bpf.flags[type];
+ u32 cnt;
+
+ if (flags & BPF_F_ALLOW_MULTI)
+ return true;
+ cnt = prog_list_length(&p->bpf.progs[type]);
+ WARN_ON_ONCE(cnt > 1);
+ if (cnt == 1)
+ return !!(flags & BPF_F_ALLOW_OVERRIDE);
+ p = cgroup_parent(p);
+ } while (p);
+ return true;
+}
+
+/* compute a chain of effective programs for a given cgroup:
+ * start from the list of programs in this cgroup and add
+ * all parent programs.
+ * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
+ * to programs in this cgroup
+ */
+static int compute_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ struct bpf_prog_array __rcu **array)
+{
+ struct bpf_prog_array __rcu *progs;
+ struct bpf_prog_list *pl;
+ struct cgroup *p = cgrp;
+ int cnt = 0;
+
+ /* count number of effective programs by walking parents */
+ do {
+ if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ cnt += prog_list_length(&p->bpf.progs[type]);
+ p = cgroup_parent(p);
+ } while (p);
+
+ progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+ if (!progs)
+ return -ENOMEM;
+
+ /* populate the array with effective progs */
+ cnt = 0;
+ p = cgrp;
+ do {
+ if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ list_for_each_entry(pl,
+ &p->bpf.progs[type], node) {
+ if (!pl->prog)
+ continue;
+ rcu_dereference_protected(progs, 1)->
+ progs[cnt++] = pl->prog;
+ }
+ p = cgroup_parent(p);
+ } while (p);
+
+ *array = progs;
+ return 0;
+}
+
+static void activate_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ struct bpf_prog_array __rcu *array)
+{
+ struct bpf_prog_array __rcu *old_array;
+
+ old_array = xchg(&cgrp->bpf.effective[type], array);
+ /* free prog array after grace period, since __cgroup_bpf_run_*()
+ * might be still walking the array
+ */
+ bpf_prog_array_free(old_array);
}
/**
* cgroup_bpf_inherit() - inherit effective programs from parent
* @cgrp: the cgroup to modify
- * @parent: the parent to inherit from
*/
-void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
+int cgroup_bpf_inherit(struct cgroup *cgrp)
{
- unsigned int type;
+/* has to use marco instead of const int, since compiler thinks
+ * that array below is variable length
+ */
+#define NR ARRAY_SIZE(cgrp->bpf.effective)
+ struct bpf_prog_array __rcu *arrays[NR] = {};
+ int i;
- for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) {
- struct bpf_prog *e;
+ for (i = 0; i < NR; i++)
+ INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
- e = rcu_dereference_protected(parent->bpf.effective[type],
- lockdep_is_held(&cgroup_mutex));
- rcu_assign_pointer(cgrp->bpf.effective[type], e);
- cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
- }
+ for (i = 0; i < NR; i++)
+ if (compute_effective_progs(cgrp, i, &arrays[i]))
+ goto cleanup;
+
+ for (i = 0; i < NR; i++)
+ activate_effective_progs(cgrp, i, arrays[i]);
+
+ return 0;
+cleanup:
+ for (i = 0; i < NR; i++)
+ bpf_prog_array_free(arrays[i]);
+ return -ENOMEM;
}
+#define BPF_CGROUP_MAX_PROGS 64
+
/**
- * __cgroup_bpf_update() - Update the pinned program of a cgroup, and
+ * __cgroup_bpf_attach() - Attach the program to a cgroup, and
* propagate the change to descendants
* @cgrp: The cgroup which descendants to traverse
- * @parent: The parent of @cgrp, or %NULL if @cgrp is the root
- * @prog: A new program to pin
- * @type: Type of pinning operation (ingress/egress)
- *
- * Each cgroup has a set of two pointers for bpf programs; one for eBPF
- * programs it owns, and which is effective for execution.
- *
- * If @prog is not %NULL, this function attaches a new program to the cgroup
- * and releases the one that is currently attached, if any. @prog is then made
- * the effective program of type @type in that cgroup.
- *
- * If @prog is %NULL, the currently attached program of type @type is released,
- * and the effective program of the parent cgroup (if any) is inherited to
- * @cgrp.
- *
- * Then, the descendants of @cgrp are walked and the effective program for
- * each of them is set to the effective program of @cgrp unless the
- * descendant has its own program attached, in which case the subbranch is
- * skipped. This ensures that delegated subcgroups with own programs are left
- * untouched.
+ * @prog: A program to attach
+ * @type: Type of attach operation
*
* Must be called with cgroup_mutex held.
*/
-int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
- struct bpf_prog *prog, enum bpf_attach_type type,
- bool new_overridable)
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
{
- struct bpf_prog *old_prog, *effective = NULL;
- struct cgroup_subsys_state *pos;
- bool overridable = true;
-
- if (parent) {
- overridable = !parent->bpf.disallow_override[type];
- effective = rcu_dereference_protected(parent->bpf.effective[type],
- lockdep_is_held(&cgroup_mutex));
- }
-
- if (prog && effective && !overridable)
- /* if parent has non-overridable prog attached, disallow
- * attaching new programs to descendent cgroup
- */
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ struct bpf_prog *old_prog = NULL;
+ struct cgroup_subsys_state *css;
+ struct bpf_prog_list *pl;
+ bool pl_was_allocated;
+ int err;
+
+ if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+ /* invalid combination */
+ return -EINVAL;
+
+ if (!hierarchy_allows_attach(cgrp, type, flags))
return -EPERM;
- if (prog && effective && overridable != new_overridable)
- /* if parent has overridable prog attached, only
- * allow overridable programs in descendent cgroup
+ if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+ /* Disallow attaching non-overridable on top
+ * of existing overridable in this cgroup.
+ * Disallow attaching multi-prog if overridable or none
*/
return -EPERM;
- old_prog = cgrp->bpf.prog[type];
-
- if (prog) {
- overridable = new_overridable;
- effective = prog;
- if (old_prog &&
- cgrp->bpf.disallow_override[type] == new_overridable)
- /* disallow attaching non-overridable on top
- * of existing overridable in this cgroup
- * and vice versa
- */
- return -EPERM;
+ if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+ return -E2BIG;
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ list_for_each_entry(pl, progs, node)
+ if (pl->prog == prog)
+ /* disallow attaching the same prog twice */
+ return -EINVAL;
+
+ pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+ if (!pl)
+ return -ENOMEM;
+ pl_was_allocated = true;
+ pl->prog = prog;
+ list_add_tail(&pl->node, progs);
+ } else {
+ if (list_empty(progs)) {
+ pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+ if (!pl)
+ return -ENOMEM;
+ pl_was_allocated = true;
+ list_add_tail(&pl->node, progs);
+ } else {
+ pl = list_first_entry(progs, typeof(*pl), node);
+ old_prog = pl->prog;
+ pl_was_allocated = false;
+ }
+ pl->prog = prog;
}
- if (!prog && !old_prog)
- /* report error when trying to detach and nothing is attached */
- return -ENOENT;
+ cgrp->bpf.flags[type] = flags;
- cgrp->bpf.prog[type] = prog;
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
- css_for_each_descendant_pre(pos, &cgrp->self) {
- struct cgroup *desc = container_of(pos, struct cgroup, self);
-
- /* skip the subtree if the descendant has its own program */
- if (desc->bpf.prog[type] && desc != cgrp) {
- pos = css_rightmost_descendant(pos);
- } else {
- rcu_assign_pointer(desc->bpf.effective[type],
- effective);
- desc->bpf.disallow_override[type] = !overridable;
- }
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
}
- if (prog)
- static_branch_inc(&cgroup_bpf_enabled_key);
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ static_branch_inc(&cgroup_bpf_enabled_key);
if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* and cleanup the prog list */
+ pl->prog = old_prog;
+ if (pl_was_allocated) {
+ list_del(&pl->node);
+ kfree(pl);
+ }
+ return err;
+}
+
+/**
+ * __cgroup_bpf_detach() - Detach the program from a cgroup, and
+ * propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to detach or NULL
+ * @type: Type of detach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 unused_flags)
+{
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ u32 flags = cgrp->bpf.flags[type];
+ struct bpf_prog *old_prog = NULL;
+ struct cgroup_subsys_state *css;
+ struct bpf_prog_list *pl;
+ int err;
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ if (!prog)
+ /* to detach MULTI prog the user has to specify valid FD
+ * of the program to be detached
+ */
+ return -EINVAL;
+ } else {
+ if (list_empty(progs))
+ /* report error when trying to detach and nothing is attached */
+ return -ENOENT;
+ }
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ /* find the prog and detach it */
+ list_for_each_entry(pl, progs, node) {
+ if (pl->prog != prog)
+ continue;
+ old_prog = prog;
+ /* mark it deleted, so it's ignored while
+ * recomputing effective
+ */
+ pl->prog = NULL;
+ break;
+ }
+ if (!old_prog)
+ return -ENOENT;
+ } else {
+ /* to maintain backward compatibility NONE and OVERRIDE cgroups
+ * allow detaching with invalid FD (prog==NULL)
+ */
+ pl = list_first_entry(progs, typeof(*pl), node);
+ old_prog = pl->prog;
+ pl->prog = NULL;
+ }
+
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
+ }
+
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* now can actually delete it from this cgroup list */
+ list_del(&pl->node);
+ kfree(pl);
+ if (list_empty(progs))
+ /* last program was detached, reset flags to zero */
+ cgrp->bpf.flags[type] = 0;
+
+ bpf_prog_put(old_prog);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* and restore back old_prog */
+ pl->prog = old_prog;
+ return err;
+}
+
+/* Must be called with cgroup_mutex held to avoid races. */
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+ enum bpf_attach_type type = attr->query.attach_type;
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ u32 flags = cgrp->bpf.flags[type];
+ int cnt, ret = 0, i;
+
+ if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
+ cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
+ else
+ cnt = prog_list_length(progs);
+
+ if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+ return -EFAULT;
+ if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
+ return -EFAULT;
+ if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
+ /* return early if user requested only program count + flags */
+ return 0;
+ if (attr->query.prog_cnt < cnt) {
+ cnt = attr->query.prog_cnt;
+ ret = -ENOSPC;
+ }
+
+ if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+ return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
+ prog_ids, cnt);
+ } else {
+ struct bpf_prog_list *pl;
+ u32 id;
+
+ i = 0;
+ list_for_each_entry(pl, progs, node) {
+ id = pl->prog->aux->id;
+ if (copy_to_user(prog_ids + i, &id, sizeof(id)))
+ return -EFAULT;
+ if (++i == cnt)
+ break;
+ }
+ }
+ return ret;
}
/**
@@ -171,36 +447,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
struct sk_buff *skb,
enum bpf_attach_type type)
{
- struct bpf_prog *prog;
+ unsigned int offset = skb->data - skb_network_header(skb);
+ struct sock *save_sk;
struct cgroup *cgrp;
- int ret = 0;
+ int ret;
if (!sk || !sk_fullsock(sk))
return 0;
- if (sk->sk_family != AF_INET &&
- sk->sk_family != AF_INET6)
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
return 0;
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-
- rcu_read_lock();
-
- prog = rcu_dereference(cgrp->bpf.effective[type]);
- if (prog) {
- unsigned int offset = skb->data - skb_network_header(skb);
- struct sock *save_sk = skb->sk;
-
- skb->sk = sk;
- __skb_push(skb, offset);
- ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM;
- __skb_pull(skb, offset);
- skb->sk = save_sk;
- }
-
- rcu_read_unlock();
-
- return ret;
+ save_sk = skb->sk;
+ skb->sk = sk;
+ __skb_push(skb, offset);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
+ bpf_prog_run_save_cb);
+ __skb_pull(skb, offset);
+ skb->sk = save_sk;
+ return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
@@ -221,19 +487,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
enum bpf_attach_type type)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- struct bpf_prog *prog;
- int ret = 0;
+ int ret;
-
- rcu_read_lock();
-
- prog = rcu_dereference(cgrp->bpf.effective[type]);
- if (prog)
- ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
-
- rcu_read_unlock();
-
- return ret;
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN);
+ return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
@@ -258,18 +515,77 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
enum bpf_attach_type type)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- struct bpf_prog *prog;
- int ret = 0;
+ int ret;
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops,
+ BPF_PROG_RUN);
+ return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
+
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+ short access, enum bpf_attach_type type)
+{
+ struct cgroup *cgrp;
+ struct bpf_cgroup_dev_ctx ctx = {
+ .access_type = (access << 16) | dev_type,
+ .major = major,
+ .minor = minor,
+ };
+ int allow = 1;
rcu_read_lock();
+ cgrp = task_dfl_cgroup(current);
+ allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx,
+ BPF_PROG_RUN);
+ rcu_read_unlock();
- prog = rcu_dereference(cgrp->bpf.effective[type]);
- if (prog)
- ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM;
+ return !allow;
+}
+EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
- rcu_read_unlock();
+static const struct bpf_func_proto *
+cgroup_dev_func_proto(enum bpf_func_id func_id)
+{
+ 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_get_current_uid_gid:
+ return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_trace_printk:
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
+ default:
+ return NULL;
+ }
+}
- return ret;
+static bool cgroup_dev_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
+{
+ if (type == BPF_WRITE)
+ return false;
+
+ if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
+ return false;
+ /* The verifier guarantees that size > 0. */
+ if (off % size != 0)
+ return false;
+ if (size != sizeof(__u32))
+ return false;
+
+ return true;
}
-EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
+
+const struct bpf_prog_ops cg_dev_prog_ops = {
+};
+
+const struct bpf_verifier_ops cg_dev_verifier_ops = {
+ .get_func_proto = cgroup_dev_func_proto,
+ .is_valid_access = cgroup_dev_is_valid_access,
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7b62df86be1d..8a6c37762330 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -309,12 +309,25 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
{
+ const char *end = sym + KSYM_NAME_LEN;
+
BUILD_BUG_ON(sizeof("bpf_prog_") +
- sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN);
+ sizeof(prog->tag) * 2 +
+ /* name has been null terminated.
+ * We should need +1 for the '_' preceding
+ * the name. However, the null character
+ * is double counted between the name and the
+ * sizeof("bpf_prog_") above, so we omit
+ * the +1 here.
+ */
+ sizeof(prog->aux->name) > KSYM_NAME_LEN);
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
- *sym = 0;
+ if (prog->aux->name[0])
+ snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
+ else
+ *sym = 0;
}
static __always_inline unsigned long
@@ -1367,7 +1380,13 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
* valid program, which in this case would simply not
* be JITed, but falls back to the interpreter.
*/
- fp = bpf_int_jit_compile(fp);
+ if (!bpf_prog_is_dev_bound(fp->aux)) {
+ fp = bpf_int_jit_compile(fp);
+ } else {
+ *err = bpf_prog_offload_compile(fp);
+ if (*err)
+ return fp;
+ }
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
@@ -1381,11 +1400,163 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
+static unsigned int __bpf_prog_ret1(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ return 1;
+}
+
+static struct bpf_prog_dummy {
+ struct bpf_prog prog;
+} dummy_bpf_prog = {
+ .prog = {
+ .bpf_func = __bpf_prog_ret1,
+ },
+};
+
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+ struct bpf_prog_array hdr;
+ struct bpf_prog *null_prog;
+} empty_prog_array = {
+ .null_prog = NULL,
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+ if (prog_cnt)
+ return kzalloc(sizeof(struct bpf_prog_array) +
+ sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ flags);
+
+ return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+ if (!progs ||
+ progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+ return;
+ kfree_rcu(progs, rcu);
+}
+
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+{
+ struct bpf_prog **prog;
+ u32 cnt = 0;
+
+ rcu_read_lock();
+ prog = rcu_dereference(progs)->progs;
+ for (; *prog; prog++)
+ cnt++;
+ rcu_read_unlock();
+ return cnt;
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+ __u32 __user *prog_ids, u32 cnt)
+{
+ struct bpf_prog **prog;
+ u32 i = 0, id;
+
+ rcu_read_lock();
+ prog = rcu_dereference(progs)->progs;
+ for (; *prog; prog++) {
+ id = (*prog)->aux->id;
+ if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
+ rcu_read_unlock();
+ return -EFAULT;
+ }
+ if (++i == cnt) {
+ prog++;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (*prog)
+ return -ENOSPC;
+ return 0;
+}
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+ struct bpf_prog *old_prog)
+{
+ struct bpf_prog **prog = progs->progs;
+
+ for (; *prog; prog++)
+ if (*prog == old_prog) {
+ WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ break;
+ }
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array)
+{
+ int new_prog_cnt, carry_prog_cnt = 0;
+ struct bpf_prog **existing_prog;
+ struct bpf_prog_array *array;
+ int new_prog_idx = 0;
+
+ /* Figure out how many existing progs we need to carry over to
+ * the new array.
+ */
+ if (old_array) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++) {
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ carry_prog_cnt++;
+ if (*existing_prog == include_prog)
+ return -EEXIST;
+ }
+ }
+
+ /* How many progs (not NULL) will be in the new array? */
+ new_prog_cnt = carry_prog_cnt;
+ if (include_prog)
+ new_prog_cnt += 1;
+
+ /* Do we have any prog (not NULL) in the new array? */
+ if (!new_prog_cnt) {
+ *new_array = NULL;
+ return 0;
+ }
+
+ /* +1 as the end of prog_array is marked with NULL */
+ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
+ if (!array)
+ return -ENOMEM;
+
+ /* Fill in the new prog array */
+ if (carry_prog_cnt) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++)
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ array->progs[new_prog_idx++] = *existing_prog;
+ }
+ if (include_prog)
+ array->progs[new_prog_idx++] = include_prog;
+ array->progs[new_prog_idx] = NULL;
+ *new_array = array;
+ return 0;
+}
+
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
aux = container_of(work, struct bpf_prog_aux, work);
+ if (bpf_prog_is_dev_bound(aux))
+ bpf_prog_offload_destroy(aux->prog);
bpf_jit_free(aux->prog);
}
@@ -1498,5 +1669,8 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
+/* These are only used within the BPF_SYSCALL code */
+#ifdef CONFIG_BPF_SYSCALL
EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type);
EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu);
+#endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000000..ce5b669003b2
--- /dev/null
+++ b/kernel/bpf/cpumap.c
@@ -0,0 +1,706 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2. See COPYING.
+ */
+
+/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirects XDP frames out another NIC device,
+ * this map type redirects raw XDP frames to another CPU. The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage. This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+#include <trace/events/xdp.h>
+
+#include <linux/netdevice.h> /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call. It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+ void *q[CPU_MAP_BULK_SIZE];
+ unsigned int count;
+};
+
+/* Struct for every remote "destination" CPU in map */
+struct bpf_cpu_map_entry {
+ u32 cpu; /* kthread CPU and map index */
+ int map_id; /* Back reference to map */
+ u32 qsize; /* Queue size placeholder for map lookup */
+
+ /* XDP can run multiple RX-ring queues, need __percpu enqueue store */
+ struct xdp_bulk_queue __percpu *bulkq;
+
+ /* Queue with potential multi-producers, and single-consumer kthread */
+ struct ptr_ring *queue;
+ struct task_struct *kthread;
+ struct work_struct kthread_stop_wq;
+
+ atomic_t refcnt; /* Control when this struct can be free'ed */
+ struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+ struct bpf_map map;
+ /* Below members specific for map type */
+ struct bpf_cpu_map_entry **cpu_map;
+ unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+ return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_cpu_map *cmap;
+ int err = -ENOMEM;
+ u64 cost;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ /* check sanity of attributes */
+ if (attr->max_entries == 0 || attr->key_size != 4 ||
+ attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ return ERR_PTR(-EINVAL);
+
+ cmap = kzalloc(sizeof(*cmap), GFP_USER);
+ if (!cmap)
+ return ERR_PTR(-ENOMEM);
+
+ /* mandatory map attributes */
+ cmap->map.map_type = attr->map_type;
+ cmap->map.key_size = attr->key_size;
+ cmap->map.value_size = attr->value_size;
+ cmap->map.max_entries = attr->max_entries;
+ cmap->map.map_flags = attr->map_flags;
+ cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+
+ /* Pre-limit array size based on NR_CPUS, not final CPU check */
+ if (cmap->map.max_entries > NR_CPUS) {
+ err = -E2BIG;
+ goto free_cmap;
+ }
+
+ /* make sure page count doesn't overflow */
+ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+ cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_cmap;
+ cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* Notice returns -EPERM on if map size is larger than memlock limit */
+ ret = bpf_map_precharge_memlock(cmap->map.pages);
+ if (ret) {
+ err = ret;
+ goto free_cmap;
+ }
+
+ /* A per cpu bitfield with a bit per possible CPU in map */
+ cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+ __alignof__(unsigned long));
+ if (!cmap->flush_needed)
+ goto free_cmap;
+
+ /* Alloc array for possible remote "destination" CPUs */
+ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+ sizeof(struct bpf_cpu_map_entry *),
+ cmap->map.numa_node);
+ if (!cmap->cpu_map)
+ goto free_percpu;
+
+ return &cmap->map;
+free_percpu:
+ free_percpu(cmap->flush_needed);
+free_cmap:
+ kfree(cmap);
+ return ERR_PTR(err);
+}
+
+void __cpu_map_queue_destructor(void *ptr)
+{
+ /* The tear-down procedure should have made sure that queue is
+ * empty. See __cpu_map_entry_replace() and work-queue
+ * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+ * gracefully and warn once.
+ */
+ if (WARN_ON_ONCE(ptr))
+ page_frag_free(ptr);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ if (atomic_dec_and_test(&rcpu->refcnt)) {
+ /* The queue should be empty at this point */
+ ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor);
+ kfree(rcpu->queue);
+ kfree(rcpu);
+ }
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+ /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+ * as it waits until all in-flight call_rcu() callbacks complete.
+ */
+ rcu_barrier();
+
+ /* kthread_stop will wake_up_process and wait for it to complete */
+ kthread_stop(rcpu->kthread);
+}
+
+/* For now, xdp_pkt is a cpumap internal data structure, with info
+ * carried between enqueue to dequeue. It is mapped into the top
+ * headroom of the packet, to avoid allocating separate mem.
+ */
+struct xdp_pkt {
+ void *data;
+ u16 len;
+ u16 headroom;
+ u16 metasize;
+ struct net_device *dev_rx;
+};
+
+/* Convert xdp_buff to xdp_pkt */
+static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
+{
+ struct xdp_pkt *xdp_pkt;
+ int metasize;
+ int headroom;
+
+ /* Assure headroom is available for storing info */
+ headroom = xdp->data - xdp->data_hard_start;
+ metasize = xdp->data - xdp->data_meta;
+ metasize = metasize > 0 ? metasize : 0;
+ if (unlikely((headroom - metasize) < sizeof(*xdp_pkt)))
+ return NULL;
+
+ /* Store info in top of packet */
+ xdp_pkt = xdp->data_hard_start;
+
+ xdp_pkt->data = xdp->data;
+ xdp_pkt->len = xdp->data_end - xdp->data;
+ xdp_pkt->headroom = headroom - sizeof(*xdp_pkt);
+ xdp_pkt->metasize = metasize;
+
+ return xdp_pkt;
+}
+
+struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_pkt *xdp_pkt)
+{
+ unsigned int frame_size;
+ void *pkt_data_start;
+ struct sk_buff *skb;
+
+ /* build_skb need to place skb_shared_info after SKB end, and
+ * also want to know the memory "truesize". Thus, need to
+ * know the memory frame size backing xdp_buff.
+ *
+ * XDP was designed to have PAGE_SIZE frames, but this
+ * assumption is not longer true with ixgbe and i40e. It
+ * would be preferred to set frame_size to 2048 or 4096
+ * depending on the driver.
+ * frame_size = 2048;
+ * frame_len = frame_size - sizeof(*xdp_pkt);
+ *
+ * Instead, with info avail, skb_shared_info in placed after
+ * packet len. This, unfortunately fakes the truesize.
+ * Another disadvantage of this approach, the skb_shared_info
+ * is not at a fixed memory location, with mixed length
+ * packets, which is bad for cache-line hotness.
+ */
+ frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ pkt_data_start = xdp_pkt->data - xdp_pkt->headroom;
+ skb = build_skb(pkt_data_start, frame_size);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, xdp_pkt->headroom);
+ __skb_put(skb, xdp_pkt->len);
+ if (xdp_pkt->metasize)
+ skb_metadata_set(skb, xdp_pkt->metasize);
+
+ /* Essential SKB info: protocol and skb->dev */
+ skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx);
+
+ /* Optional SKB info, currently missing:
+ * - HW checksum info (skb->ip_summed)
+ * - HW RX hash (skb_set_hash)
+ * - RX ring dev queue index (skb_record_rx_queue)
+ */
+
+ return skb;
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+ struct bpf_cpu_map_entry *rcpu = data;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* When kthread gives stop order, then rcpu have been disconnected
+ * from map, thus no new packets can enter. Remaining in-flight
+ * per CPU stored packets are flushed to this queue. Wait honoring
+ * kthread_stop signal until queue is empty.
+ */
+ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+ unsigned int processed = 0, drops = 0, sched = 0;
+ struct xdp_pkt *xdp_pkt;
+
+ /* Release CPU reschedule checks */
+ if (__ptr_ring_empty(rcpu->queue)) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* Recheck to avoid lost wake-up */
+ if (__ptr_ring_empty(rcpu->queue)) {
+ schedule();
+ sched = 1;
+ } else {
+ __set_current_state(TASK_RUNNING);
+ }
+ } else {
+ sched = cond_resched();
+ }
+
+ /* Process packets in rcpu->queue */
+ local_bh_disable();
+ /*
+ * The bpf_cpu_map_entry is single consumer, with this
+ * kthread CPU pinned. Lockless access to ptr_ring
+ * consume side valid as no-resize allowed of queue.
+ */
+ while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) {
+ struct sk_buff *skb;
+ int ret;
+
+ skb = cpu_map_build_skb(rcpu, xdp_pkt);
+ if (!skb) {
+ page_frag_free(xdp_pkt);
+ continue;
+ }
+
+ /* Inject into network stack */
+ ret = netif_receive_skb_core(skb);
+ if (ret == NET_RX_DROP)
+ drops++;
+
+ /* Limit BH-disable period */
+ if (++processed == 8)
+ break;
+ }
+ /* Feedback loop via tracepoint */
+ trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
+ local_bh_enable(); /* resched point, may call do_softirq() */
+ }
+ __set_current_state(TASK_RUNNING);
+
+ put_cpu_map_entry(rcpu);
+ return 0;
+}
+
+struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+{
+ gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+ struct bpf_cpu_map_entry *rcpu;
+ int numa, err;
+
+ /* Have map->numa_node, but choose node of redirect target CPU */
+ numa = cpu_to_node(cpu);
+
+ rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+ if (!rcpu)
+ return NULL;
+
+ /* Alloc percpu bulkq */
+ rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+ sizeof(void *), gfp);
+ if (!rcpu->bulkq)
+ goto free_rcu;
+
+ /* Alloc queue */
+ rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+ if (!rcpu->queue)
+ goto free_bulkq;
+
+ err = ptr_ring_init(rcpu->queue, qsize, gfp);
+ if (err)
+ goto free_queue;
+
+ rcpu->cpu = cpu;
+ rcpu->map_id = map_id;
+ rcpu->qsize = qsize;
+
+ /* Setup kthread */
+ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+ "cpumap/%d/map:%d", cpu, map_id);
+ if (IS_ERR(rcpu->kthread))
+ goto free_ptr_ring;
+
+ get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+ get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+ /* Make sure kthread runs on a single CPU */
+ kthread_bind(rcpu->kthread, cpu);
+ wake_up_process(rcpu->kthread);
+
+ return rcpu;
+
+free_ptr_ring:
+ ptr_ring_cleanup(rcpu->queue, NULL);
+free_queue:
+ kfree(rcpu->queue);
+free_bulkq:
+ free_percpu(rcpu->bulkq);
+free_rcu:
+ kfree(rcpu);
+ return NULL;
+}
+
+void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+ struct bpf_cpu_map_entry *rcpu;
+ int cpu;
+
+ /* This cpu_map_entry have been disconnected from map and one
+ * RCU graze-period have elapsed. Thus, XDP cannot queue any
+ * new packets and cannot change/set flush_needed that can
+ * find this entry.
+ */
+ rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+ /* Flush remaining packets in percpu bulkq */
+ for_each_online_cpu(cpu) {
+ struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+ /* No concurrent bq_enqueue can run at this point */
+ bq_flush_to_queue(rcpu, bq);
+ }
+ free_percpu(rcpu->bulkq);
+ /* Cannot kthread_stop() here, last put free rcpu resources */
+ put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver 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. The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq). A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue. Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+ u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+ struct bpf_cpu_map_entry *old_rcpu;
+
+ old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+ if (old_rcpu) {
+ call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+ INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+ schedule_work(&old_rcpu->kthread_stop_wq);
+ }
+}
+
+int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 key_cpu = *(u32 *)key;
+
+ if (key_cpu >= map->max_entries)
+ return -EINVAL;
+
+ /* notice caller map_delete_elem() use preempt_disable() */
+ __cpu_map_entry_replace(cmap, key_cpu, NULL);
+ return 0;
+}
+
+int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpu_map_entry *rcpu;
+
+ /* Array index key correspond to CPU number */
+ u32 key_cpu = *(u32 *)key;
+ /* Value is the queue size */
+ u32 qsize = *(u32 *)value;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(key_cpu >= cmap->map.max_entries))
+ return -E2BIG;
+ if (unlikely(map_flags == BPF_NOEXIST))
+ return -EEXIST;
+ if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+ return -EOVERFLOW;
+
+ /* Make sure CPU is a valid possible cpu */
+ if (!cpu_possible(key_cpu))
+ return -ENODEV;
+
+ if (qsize == 0) {
+ rcpu = NULL; /* Same as deleting */
+ } else {
+ /* Updating qsize cause re-allocation of bpf_cpu_map_entry */
+ rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+ if (!rcpu)
+ return -ENOMEM;
+ }
+ rcu_read_lock();
+ __cpu_map_entry_replace(cmap, key_cpu, rcpu);
+ rcu_read_unlock();
+ return 0;
+}
+
+void cpu_map_free(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ int cpu;
+ u32 i;
+
+ /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+ * so the bpf 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 "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+ * It does __not__ ensure pending flush operations (if any) are
+ * complete.
+ */
+ synchronize_rcu();
+
+ /* To ensure all pending flush operations have completed wait for flush
+ * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+ * Because the above synchronize_rcu() ensures the map is disconnected
+ * from the program we can assume no new bits will be set.
+ */
+ for_each_online_cpu(cpu) {
+ unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+ while (!bitmap_empty(bitmap, cmap->map.max_entries))
+ cond_resched();
+ }
+
+ /* For cpu_map the remote CPUs can still be using the entries
+ * (struct bpf_cpu_map_entry).
+ */
+ for (i = 0; i < cmap->map.max_entries; i++) {
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = READ_ONCE(cmap->cpu_map[i]);
+ if (!rcpu)
+ continue;
+
+ /* bq flush and cleanup happens after RCU graze-period */
+ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+ }
+ free_percpu(cmap->flush_needed);
+ bpf_map_area_free(cmap->cpu_map);
+ kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpu_map_entry *rcpu;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ rcpu = READ_ONCE(cmap->cpu_map[key]);
+ return rcpu;
+}
+
+static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_cpu_map_entry *rcpu =
+ __cpu_map_lookup_elem(map, *(u32 *)key);
+
+ return rcpu ? &rcpu->qsize : NULL;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = next_key;
+
+ if (index >= cmap->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == cmap->map.max_entries - 1)
+ return -ENOENT;
+ *next = index + 1;
+ return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+ .map_alloc = cpu_map_alloc,
+ .map_free = cpu_map_free,
+ .map_delete_elem = cpu_map_delete_elem,
+ .map_update_elem = cpu_map_update_elem,
+ .map_lookup_elem = cpu_map_lookup_elem,
+ .map_get_next_key = cpu_map_get_next_key,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq)
+{
+ unsigned int processed = 0, drops = 0;
+ const int to_cpu = rcpu->cpu;
+ struct ptr_ring *q;
+ int i;
+
+ if (unlikely(!bq->count))
+ return 0;
+
+ q = rcpu->queue;
+ spin_lock(&q->producer_lock);
+
+ for (i = 0; i < bq->count; i++) {
+ void *xdp_pkt = bq->q[i];
+ int err;
+
+ err = __ptr_ring_produce(q, xdp_pkt);
+ if (err) {
+ drops++;
+ page_frag_free(xdp_pkt); /* Free xdp_pkt */
+ }
+ processed++;
+ }
+ bq->count = 0;
+ spin_unlock(&q->producer_lock);
+
+ /* Feedback loop via tracepoints */
+ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
+ return 0;
+}
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+{
+ struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+ if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+ bq_flush_to_queue(rcpu, bq);
+
+ /* Notice, xdp_buff/page MUST be queued here, long enough for
+ * driver to code invoking us to finished, due to driver
+ * (e.g. ixgbe) recycle tricks based on page-refcnt.
+ *
+ * Thus, incoming xdp_pkt is always queued here (else we race
+ * with another CPU on page-refcnt and remaining driver code).
+ * Queue time is very short, as driver will invoke flush
+ * operation, when completing napi->poll call.
+ */
+ bq->q[bq->count++] = xdp_pkt;
+ return 0;
+}
+
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct xdp_pkt *xdp_pkt;
+
+ xdp_pkt = convert_to_xdp_pkt(xdp);
+ if (unlikely(!xdp_pkt))
+ return -EOVERFLOW;
+
+ /* Info needed when constructing SKB on remote CPU */
+ xdp_pkt->dev_rx = dev_rx;
+
+ bq_enqueue(rcpu, xdp_pkt);
+ return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+ __set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+ u32 bit;
+
+ /* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+ * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+ * bitmap indicate which percpu bulkq have packets.
+ */
+ for_each_set_bit(bit, bitmap, map->max_entries) {
+ struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+ struct xdp_bulk_queue *bq;
+
+ /* This is possible if entry is removed by user space
+ * between xdp redirect and flush op.
+ */
+ if (unlikely(!rcpu))
+ continue;
+
+ __clear_bit(bit, bitmap);
+
+ /* Flush all frames in bulkq to real queue */
+ bq = this_cpu_ptr(rcpu->bulkq);
+ bq_flush_to_queue(rcpu, bq);
+
+ /* If already running, costs spin_lock_irqsave + smb_mb */
+ wake_up_process(rcpu->kthread);
+ }
+}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index e745d6a88224..ebdef54bf7df 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -50,6 +50,9 @@
#include <linux/bpf.h>
#include <linux/filter.h>
+#define DEV_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
struct bpf_dtab_netdev {
struct net_device *dev;
struct bpf_dtab *dtab;
@@ -83,7 +86,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
dtab = kzalloc(sizeof(*dtab), GFP_USER);
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
new file mode 100644
index 000000000000..e682850c9715
--- /dev/null
+++ b/kernel/bpf/disasm.c
@@ -0,0 +1,214 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+
+#include "disasm.h"
+
+#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
+static const char * const func_id_str[] = {
+ __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
+};
+#undef __BPF_FUNC_STR_FN
+
+const char *func_id_name(int id)
+{
+ BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
+
+ if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
+ return func_id_str[id];
+ else
+ return "unknown";
+}
+
+const char *const bpf_class_string[8] = {
+ [BPF_LD] = "ld",
+ [BPF_LDX] = "ldx",
+ [BPF_ST] = "st",
+ [BPF_STX] = "stx",
+ [BPF_ALU] = "alu",
+ [BPF_JMP] = "jmp",
+ [BPF_RET] = "BUG",
+ [BPF_ALU64] = "alu64",
+};
+
+const char *const bpf_alu_string[16] = {
+ [BPF_ADD >> 4] = "+=",
+ [BPF_SUB >> 4] = "-=",
+ [BPF_MUL >> 4] = "*=",
+ [BPF_DIV >> 4] = "/=",
+ [BPF_OR >> 4] = "|=",
+ [BPF_AND >> 4] = "&=",
+ [BPF_LSH >> 4] = "<<=",
+ [BPF_RSH >> 4] = ">>=",
+ [BPF_NEG >> 4] = "neg",
+ [BPF_MOD >> 4] = "%=",
+ [BPF_XOR >> 4] = "^=",
+ [BPF_MOV >> 4] = "=",
+ [BPF_ARSH >> 4] = "s>>=",
+ [BPF_END >> 4] = "endian",
+};
+
+static const char *const bpf_ldst_string[] = {
+ [BPF_W >> 3] = "u32",
+ [BPF_H >> 3] = "u16",
+ [BPF_B >> 3] = "u8",
+ [BPF_DW >> 3] = "u64",
+};
+
+static const char *const bpf_jmp_string[16] = {
+ [BPF_JA >> 4] = "jmp",
+ [BPF_JEQ >> 4] = "==",
+ [BPF_JGT >> 4] = ">",
+ [BPF_JLT >> 4] = "<",
+ [BPF_JGE >> 4] = ">=",
+ [BPF_JLE >> 4] = "<=",
+ [BPF_JSET >> 4] = "&",
+ [BPF_JNE >> 4] = "!=",
+ [BPF_JSGT >> 4] = "s>",
+ [BPF_JSLT >> 4] = "s<",
+ [BPF_JSGE >> 4] = "s>=",
+ [BPF_JSLE >> 4] = "s<=",
+ [BPF_CALL >> 4] = "call",
+ [BPF_EXIT >> 4] = "exit",
+};
+
+static void print_bpf_end_insn(bpf_insn_print_cb verbose,
+ struct bpf_verifier_env *env,
+ const struct bpf_insn *insn)
+{
+ verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg,
+ BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le",
+ insn->imm, insn->dst_reg);
+}
+
+void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, bool allow_ptr_leaks)
+{
+ u8 class = BPF_CLASS(insn->code);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ if (BPF_OP(insn->code) == BPF_END) {
+ if (class == BPF_ALU64)
+ verbose(env, "BUG_alu64_%02x\n", insn->code);
+ else
+ print_bpf_end_insn(verbose, env, insn);
+ } else if (BPF_OP(insn->code) == BPF_NEG) {
+ verbose(env, "(%02x) r%d = %s-r%d\n",
+ insn->code, insn->dst_reg,
+ class == BPF_ALU ? "(u32) " : "",
+ insn->dst_reg);
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ verbose(env, "(%02x) %sr%d %s %sr%d\n",
+ insn->code, class == BPF_ALU ? "(u32) " : "",
+ insn->dst_reg,
+ bpf_alu_string[BPF_OP(insn->code) >> 4],
+ class == BPF_ALU ? "(u32) " : "",
+ insn->src_reg);
+ } else {
+ verbose(env, "(%02x) %sr%d %s %s%d\n",
+ insn->code, class == BPF_ALU ? "(u32) " : "",
+ insn->dst_reg,
+ bpf_alu_string[BPF_OP(insn->code) >> 4],
+ class == BPF_ALU ? "(u32) " : "",
+ insn->imm);
+ }
+ } else if (class == BPF_STX) {
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->src_reg);
+ else if (BPF_MODE(insn->code) == BPF_XADD)
+ verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg, insn->off,
+ insn->src_reg);
+ else
+ verbose(env, "BUG_%02x\n", insn->code);
+ } else if (class == BPF_ST) {
+ if (BPF_MODE(insn->code) != BPF_MEM) {
+ verbose(env, "BUG_st_%02x\n", insn->code);
+ return;
+ }
+ verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (class == BPF_LDX) {
+ if (BPF_MODE(insn->code) != BPF_MEM) {
+ verbose(env, "BUG_ldx_%02x\n", insn->code);
+ return;
+ }
+ verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n",
+ insn->code, insn->dst_reg,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->src_reg, insn->off);
+ } else if (class == BPF_LD) {
+ if (BPF_MODE(insn->code) == BPF_ABS) {
+ verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IND) {
+ verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->src_reg, insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IMM &&
+ BPF_SIZE(insn->code) == BPF_DW) {
+ /* At this point, we already made sure that the second
+ * part of the ldimm64 insn is accessible.
+ */
+ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+ bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+ if (map_ptr && !allow_ptr_leaks)
+ imm = 0;
+
+ verbose(env, "(%02x) r%d = 0x%llx\n", insn->code,
+ insn->dst_reg, (unsigned long long)imm);
+ } else {
+ verbose(env, "BUG_ld_%02x\n", insn->code);
+ return;
+ }
+ } else if (class == BPF_JMP) {
+ u8 opcode = BPF_OP(insn->code);
+
+ if (opcode == BPF_CALL) {
+ verbose(env, "(%02x) call %s#%d\n", insn->code,
+ func_id_name(insn->imm), insn->imm);
+ } else if (insn->code == (BPF_JMP | BPF_JA)) {
+ verbose(env, "(%02x) goto pc%+d\n",
+ insn->code, insn->off);
+ } else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+ verbose(env, "(%02x) exit\n", insn->code);
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n",
+ insn->code, insn->dst_reg,
+ bpf_jmp_string[BPF_OP(insn->code) >> 4],
+ insn->src_reg, insn->off);
+ } else {
+ verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n",
+ insn->code, insn->dst_reg,
+ bpf_jmp_string[BPF_OP(insn->code) >> 4],
+ insn->imm, insn->off);
+ }
+ } else {
+ verbose(env, "(%02x) %s\n",
+ insn->code, bpf_class_string[class]);
+ }
+}
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
new file mode 100644
index 000000000000..8de977e420b6
--- /dev/null
+++ b/kernel/bpf/disasm.h
@@ -0,0 +1,32 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef __BPF_DISASM_H__
+#define __BPF_DISASM_H__
+
+#include <linux/bpf.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+
+extern const char *const bpf_alu_string[16];
+extern const char *const bpf_class_string[8];
+
+const char *func_id_name(int id);
+
+struct bpf_verifier_env;
+typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env,
+ const char *, ...);
+void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, bool allow_ptr_leaks);
+
+#endif
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 6533f08d1238..e469e05c8e83 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -18,8 +18,9 @@
#include "bpf_lru_list.h"
#include "map_in_map.h"
-#define HTAB_CREATE_FLAG_MASK \
- (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE)
+#define HTAB_CREATE_FLAG_MASK \
+ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
+ BPF_F_RDONLY | BPF_F_WRONLY)
struct bucket {
struct hlist_nulls_head head;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index be1dde967208..01aaef1a77c5 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -295,7 +295,7 @@ out:
}
static void *bpf_obj_do_get(const struct filename *pathname,
- enum bpf_type *type)
+ enum bpf_type *type, int flags)
{
struct inode *inode;
struct path path;
@@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
return ERR_PTR(ret);
inode = d_backing_inode(path.dentry);
- ret = inode_permission(inode, MAY_WRITE);
+ ret = inode_permission(inode, ACC_MODE(flags));
if (ret)
goto out;
@@ -326,18 +326,23 @@ out:
return ERR_PTR(ret);
}
-int bpf_obj_get_user(const char __user *pathname)
+int bpf_obj_get_user(const char __user *pathname, int flags)
{
enum bpf_type type = BPF_TYPE_UNSPEC;
struct filename *pname;
int ret = -ENOENT;
+ int f_flags;
void *raw;
+ f_flags = bpf_get_file_flag(flags);
+ if (f_flags < 0)
+ return f_flags;
+
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
- raw = bpf_obj_do_get(pname, &type);
+ raw = bpf_obj_do_get(pname, &type, f_flags);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
@@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname)
if (type == BPF_TYPE_PROG)
ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
- ret = bpf_map_new_fd(raw);
+ ret = bpf_map_new_fd(raw, f_flags);
else
goto out;
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1b767844a76f..885e45479680 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -389,10 +389,99 @@ out:
return ret;
}
-static int trie_delete_elem(struct bpf_map *map, void *key)
+/* Called from syscall or from eBPF program */
+static int trie_delete_elem(struct bpf_map *map, void *_key)
{
- /* TODO */
- return -ENOSYS;
+ struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+ struct bpf_lpm_trie_key *key = _key;
+ struct lpm_trie_node __rcu **trim, **trim2;
+ struct lpm_trie_node *node, *parent;
+ unsigned long irq_flags;
+ unsigned int next_bit;
+ size_t matchlen = 0;
+ int ret = 0;
+
+ if (key->prefixlen > trie->max_prefixlen)
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&trie->lock, irq_flags);
+
+ /* Walk the tree looking for an exact key/length match and keeping
+ * track of the path we traverse. We will need to know the node
+ * we wish to delete, and the slot that points to the node we want
+ * to delete. We may also need to know the nodes parent and the
+ * slot that contains it.
+ */
+ trim = &trie->root;
+ trim2 = trim;
+ parent = NULL;
+ while ((node = rcu_dereference_protected(
+ *trim, lockdep_is_held(&trie->lock)))) {
+ matchlen = longest_prefix_match(trie, node, key);
+
+ if (node->prefixlen != matchlen ||
+ node->prefixlen == key->prefixlen)
+ break;
+
+ parent = node;
+ trim2 = trim;
+ next_bit = extract_bit(key->data, node->prefixlen);
+ trim = &node->child[next_bit];
+ }
+
+ if (!node || node->prefixlen != key->prefixlen ||
+ (node->flags & LPM_TREE_NODE_FLAG_IM)) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ trie->n_entries--;
+
+ /* If the node we are removing has two children, simply mark it
+ * as intermediate and we are done.
+ */
+ if (rcu_access_pointer(node->child[0]) &&
+ rcu_access_pointer(node->child[1])) {
+ node->flags |= LPM_TREE_NODE_FLAG_IM;
+ goto out;
+ }
+
+ /* If the parent of the node we are about to delete is an intermediate
+ * node, and the deleted node doesn't have any children, we can delete
+ * the intermediate parent as well and promote its other child
+ * up the tree. Doing this maintains the invariant that all
+ * intermediate nodes have exactly 2 children and that there are no
+ * unnecessary intermediate nodes in the tree.
+ */
+ if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) &&
+ !node->child[0] && !node->child[1]) {
+ if (node == rcu_access_pointer(parent->child[0]))
+ rcu_assign_pointer(
+ *trim2, rcu_access_pointer(parent->child[1]));
+ else
+ rcu_assign_pointer(
+ *trim2, rcu_access_pointer(parent->child[0]));
+ kfree_rcu(parent, rcu);
+ kfree_rcu(node, rcu);
+ goto out;
+ }
+
+ /* The node we are removing has either zero or one child. If there
+ * is a child, move it into the removed node's slot then delete
+ * the node. Otherwise just clear the slot and delete the node.
+ */
+ if (node->child[0])
+ rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0]));
+ else if (node->child[1])
+ rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1]));
+ else
+ RCU_INIT_POINTER(*trim, NULL);
+ kfree_rcu(node, rcu);
+
+out:
+ raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+
+ return ret;
}
#define LPM_DATA_SIZE_MAX 256
@@ -406,7 +495,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key)
#define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
#define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
-#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE)
+#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \
+ BPF_F_RDONLY | BPF_F_WRONLY)
static struct bpf_map *trie_alloc(union bpf_attr *attr)
{
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
new file mode 100644
index 000000000000..2816feb38be1
--- /dev/null
+++ b/kernel/bpf/offload.c
@@ -0,0 +1,194 @@
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bug.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rtnetlink.h>
+
+/* protected by RTNL */
+static LIST_HEAD(bpf_prog_offload_devs);
+
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_dev_offload *offload;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (attr->prog_flags)
+ return -EINVAL;
+
+ offload = kzalloc(sizeof(*offload), GFP_USER);
+ if (!offload)
+ return -ENOMEM;
+
+ offload->prog = prog;
+ init_waitqueue_head(&offload->verifier_done);
+
+ rtnl_lock();
+ offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex);
+ if (!offload->netdev) {
+ rtnl_unlock();
+ kfree(offload);
+ return -EINVAL;
+ }
+
+ prog->aux->offload = offload;
+ list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+ rtnl_unlock();
+
+ return 0;
+}
+
+static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
+ struct netdev_bpf *data)
+{
+ struct net_device *netdev = prog->aux->offload->netdev;
+
+ ASSERT_RTNL();
+
+ if (!netdev)
+ return -ENODEV;
+ if (!netdev->netdev_ops->ndo_bpf)
+ return -EOPNOTSUPP;
+
+ data->command = cmd;
+
+ return netdev->netdev_ops->ndo_bpf(netdev, data);
+}
+
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+{
+ struct netdev_bpf data = {};
+ int err;
+
+ data.verifier.prog = env->prog;
+
+ rtnl_lock();
+ err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
+ if (err)
+ goto exit_unlock;
+
+ env->dev_ops = data.verifier.ops;
+
+ env->prog->aux->offload->dev_state = true;
+ env->prog->aux->offload->verifier_running = true;
+exit_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+ struct bpf_dev_offload *offload = prog->aux->offload;
+ struct netdev_bpf data = {};
+
+ data.offload.prog = prog;
+
+ if (offload->verifier_running)
+ wait_event(offload->verifier_done, !offload->verifier_running);
+
+ if (offload->dev_state)
+ WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
+
+ offload->dev_state = false;
+ list_del_init(&offload->offloads);
+ offload->netdev = NULL;
+}
+
+void bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+ struct bpf_dev_offload *offload = prog->aux->offload;
+
+ offload->verifier_running = false;
+ wake_up(&offload->verifier_done);
+
+ rtnl_lock();
+ __bpf_prog_offload_destroy(prog);
+ rtnl_unlock();
+
+ kfree(offload);
+}
+
+static int bpf_prog_offload_translate(struct bpf_prog *prog)
+{
+ struct bpf_dev_offload *offload = prog->aux->offload;
+ struct netdev_bpf data = {};
+ int ret;
+
+ data.offload.prog = prog;
+
+ offload->verifier_running = false;
+ wake_up(&offload->verifier_done);
+
+ rtnl_lock();
+ ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
+ rtnl_unlock();
+
+ return ret;
+}
+
+static unsigned int bpf_prog_warn_on_exec(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ WARN(1, "attempt to execute device eBPF program on the host!");
+ return 0;
+}
+
+int bpf_prog_offload_compile(struct bpf_prog *prog)
+{
+ prog->bpf_func = bpf_prog_warn_on_exec;
+
+ return bpf_prog_offload_translate(prog);
+}
+
+u32 bpf_prog_offload_ifindex(struct bpf_prog *prog)
+{
+ struct bpf_dev_offload *offload = prog->aux->offload;
+ u32 ifindex;
+
+ rtnl_lock();
+ ifindex = offload->netdev ? offload->netdev->ifindex : 0;
+ rtnl_unlock();
+
+ return ifindex;
+}
+
+const struct bpf_prog_ops bpf_offload_prog_ops = {
+};
+
+static int bpf_offload_notification(struct notifier_block *notifier,
+ ulong event, void *ptr)
+{
+ struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+ struct bpf_dev_offload *offload, *tmp;
+
+ ASSERT_RTNL();
+
+ switch (event) {
+ case NETDEV_UNREGISTER:
+ list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs,
+ offloads) {
+ if (offload->netdev == netdev)
+ __bpf_prog_offload_destroy(offload->prog);
+ }
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block bpf_offload_notifier = {
+ .notifier_call = bpf_offload_notification,
+};
+
+static int __init bpf_offload_init(void)
+{
+ register_netdevice_notifier(&bpf_offload_notifier);
+ return 0;
+}
+
+subsys_initcall(bpf_offload_init);
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 5c51d1985b51..673fa6fe2d73 100644
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -78,8 +78,10 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
{
struct pcpu_freelist_head *head;
struct pcpu_freelist_node *node;
+ unsigned long flags;
int orig_cpu, cpu;
+ local_irq_save(flags);
orig_cpu = cpu = raw_smp_processor_id();
while (1) {
head = per_cpu_ptr(s->freelist, cpu);
@@ -87,14 +89,16 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
node = head->first;
if (node) {
head->first = node->next;
- raw_spin_unlock(&head->lock);
+ raw_spin_unlock_irqrestore(&head->lock, flags);
return node;
}
raw_spin_unlock(&head->lock);
cpu = cpumask_next(cpu, cpu_possible_mask);
if (cpu >= nr_cpu_ids)
cpu = 0;
- if (cpu == orig_cpu)
+ if (cpu == orig_cpu) {
+ local_irq_restore(flags);
return NULL;
+ }
}
}
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index dbd7b322a86b..5ee2e41893d9 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -41,6 +41,9 @@
#include <net/strparser.h>
#include <net/tcp.h>
+#define SOCK_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
struct bpf_stab {
struct bpf_map map;
struct sock **sock_map;
@@ -122,7 +125,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->bpf.map = NULL;
skb->sk = psock->sock;
- bpf_compute_data_end_sk_skb(skb);
+ bpf_compute_data_pointers(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
@@ -385,7 +388,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_end_sk_skb(skb);
+ bpf_compute_data_pointers(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -508,7 +511,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
if (attr->value_size > KMALLOC_MAX_SIZE)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 135be433e9a0..a15bc636cc98 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -11,6 +11,9 @@
#include <linux/perf_event.h>
#include "percpu_freelist.h"
+#define STACK_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
struct stack_map_bucket {
struct pcpu_freelist_node fnode;
u32 hash;
@@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
- if (attr->map_flags & ~BPF_F_NUMA_NODE)
+ if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
/* check sanity of attributes */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 25d074920a00..09badc37e864 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,6 +23,9 @@
#include <linux/version.h>
#include <linux/kernel.h>
#include <linux/idr.h>
+#include <linux/cred.h>
+#include <linux/timekeeping.h>
+#include <linux/ctype.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -31,6 +34,8 @@
#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
+#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY)
+
DEFINE_PER_CPU(int, bpf_prog_active);
static DEFINE_IDR(prog_idr);
static DEFINE_SPINLOCK(prog_idr_lock);
@@ -207,6 +212,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
struct bpf_map *map = container_of(work, struct bpf_map, work);
bpf_map_uncharge_memlock(map);
+ security_bpf_map_free(map);
/* implementation dependent freeing */
map->ops->map_free(map);
}
@@ -291,17 +297,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
}
#endif
-static const struct file_operations bpf_map_fops = {
+static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,
+ loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_READ.
+ */
+ return -EINVAL;
+}
+
+static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
+ size_t siz, loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_WRITE.
+ */
+ return -EINVAL;
+}
+
+const struct file_operations bpf_map_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = bpf_map_show_fdinfo,
#endif
.release = bpf_map_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
};
-int bpf_map_new_fd(struct bpf_map *map)
+int bpf_map_new_fd(struct bpf_map *map, int flags)
{
+ int ret;
+
+ ret = security_bpf_map(map, OPEN_FMODE(flags));
+ if (ret < 0)
+ return ret;
+
return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
- O_RDWR | O_CLOEXEC);
+ flags | O_CLOEXEC);
+}
+
+int bpf_get_file_flag(int flags)
+{
+ if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))
+ return -EINVAL;
+ if (flags & BPF_F_RDONLY)
+ return O_RDONLY;
+ if (flags & BPF_F_WRONLY)
+ return O_WRONLY;
+ return O_RDWR;
}
/* helper macro to check that unused fields 'union bpf_attr' are zero */
@@ -312,18 +355,46 @@ int bpf_map_new_fd(struct bpf_map *map)
offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
sizeof(attr->CMD##_LAST_FIELD)) != NULL
-#define BPF_MAP_CREATE_LAST_FIELD numa_node
+/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes.
+ * Return 0 on success and < 0 on error.
+ */
+static int bpf_obj_name_cpy(char *dst, const char *src)
+{
+ const char *end = src + BPF_OBJ_NAME_LEN;
+
+ memset(dst, 0, BPF_OBJ_NAME_LEN);
+
+ /* Copy all isalnum() and '_' char */
+ while (src < end && *src) {
+ if (!isalnum(*src) && *src != '_')
+ return -EINVAL;
+ *dst++ = *src++;
+ }
+
+ /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */
+ if (src == end)
+ return -EINVAL;
+
+ return 0;
+}
+
+#define BPF_MAP_CREATE_LAST_FIELD map_name
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
struct bpf_map *map;
+ int f_flags;
int err;
err = CHECK_ATTR(BPF_MAP_CREATE);
if (err)
return -EINVAL;
+ f_flags = bpf_get_file_flag(attr->map_flags);
+ if (f_flags < 0)
+ return f_flags;
+
if (numa_node != NUMA_NO_NODE &&
((unsigned int)numa_node >= nr_node_ids ||
!node_online(numa_node)))
@@ -334,18 +405,26 @@ static int map_create(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ err = bpf_obj_name_cpy(map->name, attr->map_name);
+ if (err)
+ goto free_map_nouncharge;
+
atomic_set(&map->refcnt, 1);
atomic_set(&map->usercnt, 1);
- err = bpf_map_charge_memlock(map);
+ err = security_bpf_map_alloc(map);
if (err)
goto free_map_nouncharge;
+ err = bpf_map_charge_memlock(map);
+ if (err)
+ goto free_map_sec;
+
err = bpf_map_alloc_id(map);
if (err)
goto free_map;
- err = bpf_map_new_fd(map);
+ err = bpf_map_new_fd(map, f_flags);
if (err < 0) {
/* failed to allocate fd.
* bpf_map_put() is needed because the above
@@ -362,6 +441,8 @@ static int map_create(union bpf_attr *attr)
free_map:
bpf_map_uncharge_memlock(map);
+free_map_sec:
+ security_bpf_map_free(map);
free_map_nouncharge:
map->ops->map_free(map);
return err;
@@ -460,6 +541,11 @@ static int map_lookup_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -540,6 +626,11 @@ static int map_update_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -562,6 +653,12 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
+ /* Need to create a kthread, thus must support schedule */
+ if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ goto out;
+ }
+
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
@@ -592,7 +689,7 @@ static int map_update_elem(union bpf_attr *attr)
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
-
+out:
if (!err)
trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
@@ -623,6 +720,11 @@ static int map_delete_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -666,6 +768,11 @@ static int map_get_next_key(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
if (ukey) {
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
@@ -703,9 +810,9 @@ err_put:
return err;
}
-static const struct bpf_verifier_ops * const bpf_prog_types[] = {
-#define BPF_PROG_TYPE(_id, _ops) \
- [_id] = &_ops,
+static const struct bpf_prog_ops * const bpf_prog_types[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+ [_id] = & _name ## _prog_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
@@ -717,7 +824,10 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
return -EINVAL;
- prog->aux->ops = bpf_prog_types[type];
+ if (!bpf_prog_is_dev_bound(prog->aux))
+ prog->aux->ops = bpf_prog_types[type];
+ else
+ prog->aux->ops = &bpf_offload_prog_ops;
prog->type = type;
return 0;
}
@@ -820,6 +930,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
free_used_maps(aux);
bpf_prog_uncharge_memlock(aux->prog);
+ security_bpf_prog_free(aux);
bpf_prog_free(aux->prog);
}
@@ -867,15 +978,23 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
}
#endif
-static const struct file_operations bpf_prog_fops = {
+const struct file_operations bpf_prog_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = bpf_prog_show_fdinfo,
#endif
.release = bpf_prog_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
};
int bpf_prog_new_fd(struct bpf_prog *prog)
{
+ int ret;
+
+ ret = security_bpf_prog(prog);
+ if (ret < 0)
+ return ret;
+
return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
O_RDWR | O_CLOEXEC);
}
@@ -938,7 +1057,22 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
}
EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
-static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
+static bool bpf_prog_can_attach(struct bpf_prog *prog,
+ enum bpf_prog_type *attach_type,
+ struct net_device *netdev)
+{
+ struct bpf_dev_offload *offload = prog->aux->offload;
+
+ if (prog->type != *attach_type)
+ return false;
+ if (offload && offload->netdev != netdev)
+ return false;
+
+ return true;
+}
+
+static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
+ struct net_device *netdev)
{
struct fd f = fdget(ufd);
struct bpf_prog *prog;
@@ -946,7 +1080,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
prog = ____bpf_prog_get(f);
if (IS_ERR(prog))
return prog;
- if (type && prog->type != *type) {
+ if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) {
prog = ERR_PTR(-EINVAL);
goto out;
}
@@ -959,12 +1093,12 @@ out:
struct bpf_prog *bpf_prog_get(u32 ufd)
{
- return __bpf_prog_get(ufd, NULL);
+ return __bpf_prog_get(ufd, NULL, NULL);
}
struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
{
- struct bpf_prog *prog = __bpf_prog_get(ufd, &type);
+ struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL);
if (!IS_ERR(prog))
trace_bpf_prog_get_type(prog);
@@ -972,8 +1106,19 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type);
+struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
+ struct net_device *netdev)
+{
+ struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev);
+
+ if (!IS_ERR(prog))
+ trace_bpf_prog_get_type(prog);
+ return prog;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
+
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD prog_flags
+#define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex
static int bpf_prog_load(union bpf_attr *attr)
{
@@ -1015,10 +1160,14 @@ static int bpf_prog_load(union bpf_attr *attr)
if (!prog)
return -ENOMEM;
- err = bpf_prog_charge_memlock(prog);
+ err = security_bpf_prog_alloc(prog->aux);
if (err)
goto free_prog_nouncharge;
+ err = bpf_prog_charge_memlock(prog);
+ if (err)
+ goto free_prog_sec;
+
prog->len = attr->insn_cnt;
err = -EFAULT;
@@ -1032,11 +1181,22 @@ static int bpf_prog_load(union bpf_attr *attr)
atomic_set(&prog->aux->refcnt, 1);
prog->gpl_compatible = is_gpl ? 1 : 0;
+ if (attr->prog_target_ifindex) {
+ err = bpf_prog_offload_init(prog, attr);
+ if (err)
+ goto free_prog;
+ }
+
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
goto free_prog;
+ prog->aux->load_time = ktime_get_boot_ns();
+ err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
+ if (err)
+ goto free_prog;
+
/* run eBPF verifier */
err = bpf_check(&prog, attr);
if (err < 0)
@@ -1071,16 +1231,18 @@ free_used_maps:
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
+free_prog_sec:
+ security_bpf_prog_free(prog->aux);
free_prog_nouncharge:
bpf_prog_free(prog);
return err;
}
-#define BPF_OBJ_LAST_FIELD bpf_fd
+#define BPF_OBJ_LAST_FIELD file_flags
static int bpf_obj_pin(const union bpf_attr *attr)
{
- if (CHECK_ATTR(BPF_OBJ))
+ if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0)
return -EINVAL;
return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
@@ -1088,10 +1250,12 @@ static int bpf_obj_pin(const union bpf_attr *attr)
static int bpf_obj_get(const union bpf_attr *attr)
{
- if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
+ if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 ||
+ attr->file_flags & ~BPF_OBJ_FLAG_MASK)
return -EINVAL;
- return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
+ return bpf_obj_get_user(u64_to_user_ptr(attr->pathname),
+ attr->file_flags);
}
#ifdef CONFIG_CGROUP_BPF
@@ -1132,6 +1296,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach)
return 0;
}
+#define BPF_F_ATTACH_MASK \
+ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+
static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
@@ -1145,7 +1312,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
- if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
return -EINVAL;
switch (attr->attach_type) {
@@ -1159,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
+ case BPF_CGROUP_DEVICE:
+ ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
return sockmap_get_from_fd(attr, true);
@@ -1176,8 +1346,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return PTR_ERR(cgrp);
}
- ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
- attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
if (ret)
bpf_prog_put(prog);
cgroup_put(cgrp);
@@ -1189,6 +1359,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
+ enum bpf_prog_type ptype;
+ struct bpf_prog *prog;
struct cgroup *cgrp;
int ret;
@@ -1201,26 +1373,71 @@ static int bpf_prog_detach(const union bpf_attr *attr)
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
+ ptype = BPF_PROG_TYPE_CGROUP_SKB;
+ break;
case BPF_CGROUP_INET_SOCK_CREATE:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+ break;
case BPF_CGROUP_SOCK_OPS:
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
- cgroup_put(cgrp);
+ ptype = BPF_PROG_TYPE_SOCK_OPS;
+ break;
+ case BPF_CGROUP_DEVICE:
+ ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- ret = sockmap_get_from_fd(attr, false);
- break;
+ return sockmap_get_from_fd(attr, false);
default:
return -EINVAL;
}
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+ cgroup_put(cgrp);
return ret;
}
+#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
+
+static int bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ if (CHECK_ATTR(BPF_PROG_QUERY))
+ return -EINVAL;
+ if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE)
+ return -EINVAL;
+
+ switch (attr->query.attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_SOCK_OPS:
+ case BPF_CGROUP_DEVICE:
+ break;
+ default:
+ return -EINVAL;
+ }
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+ cgroup_put(cgrp);
+ return ret;
+}
#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -1305,20 +1522,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
return fd;
}
-#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags
static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
{
struct bpf_map *map;
u32 id = attr->map_id;
+ int f_flags;
int fd;
- if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
+ if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) ||
+ attr->open_flags & ~BPF_OBJ_FLAG_MASK)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ f_flags = bpf_get_file_flag(attr->open_flags);
+ if (f_flags < 0)
+ return f_flags;
+
spin_lock_bh(&map_idr_lock);
map = idr_find(&map_idr, id);
if (map)
@@ -1330,7 +1553,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
- fd = bpf_map_new_fd(map);
+ fd = bpf_map_new_fd(map, f_flags);
if (fd < 0)
bpf_map_put(map);
@@ -1358,8 +1581,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.type = prog->type;
info.id = prog->aux->id;
+ info.load_time = prog->aux->load_time;
+ info.created_by_uid = from_kuid_munged(current_user_ns(),
+ prog->aux->user->uid);
memcpy(info.tag, prog->tag, sizeof(prog->tag));
+ memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
+
+ ulen = info.nr_map_ids;
+ info.nr_map_ids = prog->aux->used_map_cnt;
+ ulen = min_t(u32, info.nr_map_ids, ulen);
+ if (ulen) {
+ u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids);
+ u32 i;
+
+ for (i = 0; i < ulen; i++)
+ if (put_user(prog->aux->used_maps[i]->id,
+ &user_map_ids[i]))
+ return -EFAULT;
+ }
if (!capable(CAP_SYS_ADMIN)) {
info.jited_prog_len = 0;
@@ -1385,6 +1625,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
return -EFAULT;
}
+ if (bpf_prog_is_dev_bound(prog->aux)) {
+ info.status |= BPF_PROG_STATUS_DEV_BOUND;
+ info.ifindex = bpf_prog_offload_ifindex(prog);
+ }
+
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
@@ -1413,6 +1658,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
info.value_size = map->value_size;
info.max_entries = map->max_entries;
info.map_flags = map->map_flags;
+ memcpy(info.name, map->name, sizeof(map->name));
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
@@ -1467,6 +1713,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
+ err = security_bpf(cmd, &attr, size);
+ if (err < 0)
+ return err;
+
switch (cmd) {
case BPF_MAP_CREATE:
err = map_create(&attr);
@@ -1499,6 +1749,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_DETACH:
err = bpf_prog_detach(&attr);
break;
+ case BPF_PROG_QUERY:
+ err = bpf_prog_query(&attr, uattr);
+ break;
#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c48ca2a34b5e..dd54d20ace2f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21,6 +21,17 @@
#include <linux/vmalloc.h>
#include <linux/stringify.h>
+#include "disasm.h"
+
+static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+ [_id] = & _name ## _verifier_ops,
+#define BPF_MAP_TYPE(_id, _ops)
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
+
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -153,28 +164,42 @@ struct bpf_call_arg_meta {
int access_size;
};
-/* verbose verifier prints what it's seeing
- * bpf_check() is called under lock, so no race to access these global vars
- */
-static u32 log_level, log_size, log_len;
-static char *log_buf;
-
static DEFINE_MUTEX(bpf_verifier_lock);
/* log_level controls verbosity level of eBPF verifier.
* verbose() is used to dump the verification trace to the log, so the user
* can figure out what's wrong with the program
*/
-static __printf(1, 2) void verbose(const char *fmt, ...)
+static __printf(2, 3) void verbose(struct bpf_verifier_env *env,
+ const char *fmt, ...)
{
+ struct bpf_verifer_log *log = &env->log;
+ unsigned int n;
va_list args;
- if (log_level == 0 || log_len >= log_size - 1)
+ if (!log->level || !log->ubuf || bpf_verifier_log_full(log))
return;
va_start(args, fmt);
- log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
+ n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
va_end(args);
+
+ WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
+ "verifier log line truncated - local buffer too short\n");
+
+ n = min(log->len_total - log->len_used - 1, n);
+ log->kbuf[n] = '\0';
+
+ if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
+ log->len_used += n;
+ else
+ log->ubuf = NULL;
+}
+
+static bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+ return type == PTR_TO_PACKET ||
+ type == PTR_TO_PACKET_META;
}
/* string representation of 'enum bpf_reg_type' */
@@ -187,26 +212,12 @@ static const char * const reg_type_str[] = {
[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
[PTR_TO_STACK] = "fp",
[PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_META] = "pkt_meta",
[PTR_TO_PACKET_END] = "pkt_end",
};
-#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
-static const char * const func_id_str[] = {
- __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
-};
-#undef __BPF_FUNC_STR_FN
-
-static const char *func_id_name(int id)
-{
- BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
-
- if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
- return func_id_str[id];
- else
- return "unknown";
-}
-
-static void print_verifier_state(struct bpf_verifier_state *state)
+static void print_verifier_state(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *state)
{
struct bpf_reg_state *reg;
enum bpf_reg_type t;
@@ -217,21 +228,21 @@ static void print_verifier_state(struct bpf_verifier_state *state)
t = reg->type;
if (t == NOT_INIT)
continue;
- verbose(" R%d=%s", i, reg_type_str[t]);
+ verbose(env, " R%d=%s", i, reg_type_str[t]);
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
tnum_is_const(reg->var_off)) {
/* reg->off should be 0 for SCALAR_VALUE */
- verbose("%lld", reg->var_off.value + reg->off);
+ verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
- verbose("(id=%d", reg->id);
+ verbose(env, "(id=%d", reg->id);
if (t != SCALAR_VALUE)
- verbose(",off=%d", reg->off);
- if (t == PTR_TO_PACKET)
- verbose(",r=%d", reg->range);
+ verbose(env, ",off=%d", reg->off);
+ if (type_is_pkt_pointer(t))
+ verbose(env, ",r=%d", reg->range);
else if (t == CONST_PTR_TO_MAP ||
t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
- verbose(",ks=%d,vs=%d",
+ verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
if (tnum_is_const(reg->var_off)) {
@@ -239,243 +250,174 @@ static void print_verifier_state(struct bpf_verifier_state *state)
* could be a pointer whose offset is too big
* for reg->off
*/
- verbose(",imm=%llx", reg->var_off.value);
+ verbose(env, ",imm=%llx", reg->var_off.value);
} else {
if (reg->smin_value != reg->umin_value &&
reg->smin_value != S64_MIN)
- verbose(",smin_value=%lld",
+ verbose(env, ",smin_value=%lld",
(long long)reg->smin_value);
if (reg->smax_value != reg->umax_value &&
reg->smax_value != S64_MAX)
- verbose(",smax_value=%lld",
+ verbose(env, ",smax_value=%lld",
(long long)reg->smax_value);
if (reg->umin_value != 0)
- verbose(",umin_value=%llu",
+ verbose(env, ",umin_value=%llu",
(unsigned long long)reg->umin_value);
if (reg->umax_value != U64_MAX)
- verbose(",umax_value=%llu",
+ verbose(env, ",umax_value=%llu",
(unsigned long long)reg->umax_value);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(",var_off=%s", tn_buf);
+ verbose(env, ",var_off=%s", tn_buf);
}
}
- verbose(")");
+ verbose(env, ")");
}
}
- for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
- if (state->stack_slot_type[i] == STACK_SPILL)
- verbose(" fp%d=%s", -MAX_BPF_STACK + i,
- reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] == STACK_SPILL)
+ verbose(env, " fp%d=%s",
+ -MAX_BPF_STACK + i * BPF_REG_SIZE,
+ reg_type_str[state->stack[i].spilled_ptr.type]);
}
- verbose("\n");
+ verbose(env, "\n");
}
-static const char *const bpf_class_string[] = {
- [BPF_LD] = "ld",
- [BPF_LDX] = "ldx",
- [BPF_ST] = "st",
- [BPF_STX] = "stx",
- [BPF_ALU] = "alu",
- [BPF_JMP] = "jmp",
- [BPF_RET] = "BUG",
- [BPF_ALU64] = "alu64",
-};
-
-static const char *const bpf_alu_string[16] = {
- [BPF_ADD >> 4] = "+=",
- [BPF_SUB >> 4] = "-=",
- [BPF_MUL >> 4] = "*=",
- [BPF_DIV >> 4] = "/=",
- [BPF_OR >> 4] = "|=",
- [BPF_AND >> 4] = "&=",
- [BPF_LSH >> 4] = "<<=",
- [BPF_RSH >> 4] = ">>=",
- [BPF_NEG >> 4] = "neg",
- [BPF_MOD >> 4] = "%=",
- [BPF_XOR >> 4] = "^=",
- [BPF_MOV >> 4] = "=",
- [BPF_ARSH >> 4] = "s>>=",
- [BPF_END >> 4] = "endian",
-};
-
-static const char *const bpf_ldst_string[] = {
- [BPF_W >> 3] = "u32",
- [BPF_H >> 3] = "u16",
- [BPF_B >> 3] = "u8",
- [BPF_DW >> 3] = "u64",
-};
-
-static const char *const bpf_jmp_string[16] = {
- [BPF_JA >> 4] = "jmp",
- [BPF_JEQ >> 4] = "==",
- [BPF_JGT >> 4] = ">",
- [BPF_JLT >> 4] = "<",
- [BPF_JGE >> 4] = ">=",
- [BPF_JLE >> 4] = "<=",
- [BPF_JSET >> 4] = "&",
- [BPF_JNE >> 4] = "!=",
- [BPF_JSGT >> 4] = "s>",
- [BPF_JSLT >> 4] = "s<",
- [BPF_JSGE >> 4] = "s>=",
- [BPF_JSLE >> 4] = "s<=",
- [BPF_CALL >> 4] = "call",
- [BPF_EXIT >> 4] = "exit",
-};
+static int copy_stack_state(struct bpf_verifier_state *dst,
+ const struct bpf_verifier_state *src)
+{
+ if (!src->stack)
+ return 0;
+ if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
+ /* internal bug, make state invalid to reject the program */
+ memset(dst, 0, sizeof(*dst));
+ return -EFAULT;
+ }
+ memcpy(dst->stack, src->stack,
+ sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
+ return 0;
+}
-static void print_bpf_insn(const struct bpf_verifier_env *env,
- const struct bpf_insn *insn)
+/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
+ * make it consume minimal amount of memory. check_stack_write() access from
+ * the program calls into realloc_verifier_state() to grow the stack size.
+ * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
+ * which this function copies over. It points to previous bpf_verifier_state
+ * which is never reallocated
+ */
+static int realloc_verifier_state(struct bpf_verifier_state *state, int size,
+ bool copy_old)
{
- u8 class = BPF_CLASS(insn->code);
-
- if (class == BPF_ALU || class == BPF_ALU64) {
- if (BPF_SRC(insn->code) == BPF_X)
- verbose("(%02x) %sr%d %s %sr%d\n",
- insn->code, class == BPF_ALU ? "(u32) " : "",
- insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
- class == BPF_ALU ? "(u32) " : "",
- insn->src_reg);
- else
- verbose("(%02x) %sr%d %s %s%d\n",
- insn->code, class == BPF_ALU ? "(u32) " : "",
- insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
- class == BPF_ALU ? "(u32) " : "",
- insn->imm);
- } else if (class == BPF_STX) {
- if (BPF_MODE(insn->code) == BPF_MEM)
- verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->src_reg);
- else if (BPF_MODE(insn->code) == BPF_XADD)
- verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg, insn->off,
- insn->src_reg);
- else
- verbose("BUG_%02x\n", insn->code);
- } else if (class == BPF_ST) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
- verbose("BUG_st_%02x\n", insn->code);
- return;
- }
- verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->imm);
- } else if (class == BPF_LDX) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
- verbose("BUG_ldx_%02x\n", insn->code);
- return;
+ u32 old_size = state->allocated_stack;
+ struct bpf_stack_state *new_stack;
+ int slot = size / BPF_REG_SIZE;
+
+ if (size <= old_size || !size) {
+ if (copy_old)
+ return 0;
+ state->allocated_stack = slot * BPF_REG_SIZE;
+ if (!size && old_size) {
+ kfree(state->stack);
+ state->stack = NULL;
}
- verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
- insn->code, insn->dst_reg,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->src_reg, insn->off);
- } else if (class == BPF_LD) {
- if (BPF_MODE(insn->code) == BPF_ABS) {
- verbose("(%02x) r0 = *(%s *)skb[%d]\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->imm);
- } else if (BPF_MODE(insn->code) == BPF_IND) {
- verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->src_reg, insn->imm);
- } else if (BPF_MODE(insn->code) == BPF_IMM &&
- BPF_SIZE(insn->code) == BPF_DW) {
- /* At this point, we already made sure that the second
- * part of the ldimm64 insn is accessible.
- */
- u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
- bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+ return 0;
+ }
+ new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
+ GFP_KERNEL);
+ if (!new_stack)
+ return -ENOMEM;
+ if (copy_old) {
+ if (state->stack)
+ memcpy(new_stack, state->stack,
+ sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
+ memset(new_stack + old_size / BPF_REG_SIZE, 0,
+ sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
+ }
+ state->allocated_stack = slot * BPF_REG_SIZE;
+ kfree(state->stack);
+ state->stack = new_stack;
+ return 0;
+}
- if (map_ptr && !env->allow_ptr_leaks)
- imm = 0;
+static void free_verifier_state(struct bpf_verifier_state *state,
+ bool free_self)
+{
+ kfree(state->stack);
+ if (free_self)
+ kfree(state);
+}
- verbose("(%02x) r%d = 0x%llx\n", insn->code,
- insn->dst_reg, (unsigned long long)imm);
- } else {
- verbose("BUG_ld_%02x\n", insn->code);
- return;
- }
- } else if (class == BPF_JMP) {
- u8 opcode = BPF_OP(insn->code);
+/* copy verifier state from src to dst growing dst stack space
+ * when necessary to accommodate larger src stack
+ */
+static int copy_verifier_state(struct bpf_verifier_state *dst,
+ const struct bpf_verifier_state *src)
+{
+ int err;
- if (opcode == BPF_CALL) {
- verbose("(%02x) call %s#%d\n", insn->code,
- func_id_name(insn->imm), insn->imm);
- } else if (insn->code == (BPF_JMP | BPF_JA)) {
- verbose("(%02x) goto pc%+d\n",
- insn->code, insn->off);
- } else if (insn->code == (BPF_JMP | BPF_EXIT)) {
- verbose("(%02x) exit\n", insn->code);
- } else if (BPF_SRC(insn->code) == BPF_X) {
- verbose("(%02x) if r%d %s r%d goto pc%+d\n",
- insn->code, insn->dst_reg,
- bpf_jmp_string[BPF_OP(insn->code) >> 4],
- insn->src_reg, insn->off);
- } else {
- verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
- insn->code, insn->dst_reg,
- bpf_jmp_string[BPF_OP(insn->code) >> 4],
- insn->imm, insn->off);
- }
- } else {
- verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
- }
+ err = realloc_verifier_state(dst, src->allocated_stack, false);
+ if (err)
+ return err;
+ memcpy(dst, src, offsetof(struct bpf_verifier_state, allocated_stack));
+ return copy_stack_state(dst, src);
}
-static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx)
+static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
+ int *insn_idx)
{
- struct bpf_verifier_stack_elem *elem;
- int insn_idx;
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_verifier_stack_elem *elem, *head = env->head;
+ int err;
if (env->head == NULL)
- return -1;
+ return -ENOENT;
- memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
- insn_idx = env->head->insn_idx;
+ if (cur) {
+ err = copy_verifier_state(cur, &head->st);
+ if (err)
+ return err;
+ }
+ if (insn_idx)
+ *insn_idx = head->insn_idx;
if (prev_insn_idx)
- *prev_insn_idx = env->head->prev_insn_idx;
- elem = env->head->next;
- kfree(env->head);
+ *prev_insn_idx = head->prev_insn_idx;
+ elem = head->next;
+ free_verifier_state(&head->st, false);
+ kfree(head);
env->head = elem;
env->stack_size--;
- return insn_idx;
+ return 0;
}
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx)
{
+ struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem;
+ int err;
- elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
if (!elem)
goto err;
- memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
elem->next = env->head;
env->head = elem;
env->stack_size++;
+ err = copy_verifier_state(&elem->st, cur);
+ if (err)
+ goto err;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
- verbose("BPF program is too complex\n");
+ verbose(env, "BPF program is too complex\n");
goto err;
}
return &elem->st;
err:
/* pop all elements and return */
- while (pop_stack(env, NULL) >= 0);
+ while (!pop_stack(env, NULL, NULL));
return NULL;
}
@@ -507,10 +449,11 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg)
__mark_reg_known(reg, 0);
}
-static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_known_zero(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
- verbose("mark_reg_known_zero(regs, %u)\n", regno);
+ verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(regs + regno);
@@ -519,6 +462,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno)
__mark_reg_known_zero(regs + regno);
}
+static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
+{
+ return type_is_pkt_pointer(reg->type);
+}
+
+static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
+{
+ return reg_is_pkt_pointer(reg) ||
+ reg->type == PTR_TO_PACKET_END;
+}
+
+/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
+static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
+ enum bpf_reg_type which)
+{
+ /* The register can already have a range from prior markings.
+ * This is fine as long as it hasn't been advanced from its
+ * origin.
+ */
+ return reg->type == which &&
+ reg->id == 0 &&
+ reg->off == 0 &&
+ tnum_equals_const(reg->var_off, 0);
+}
+
/* Attempts to improve min/max values based on var_off information */
static void __update_reg_bounds(struct bpf_reg_state *reg)
{
@@ -595,10 +563,11 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg)
__mark_reg_unbounded(reg);
}
-static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_unknown(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
- verbose("mark_reg_unknown(regs, %u)\n", regno);
+ verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(regs + regno);
@@ -613,10 +582,11 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg)
reg->type = NOT_INIT;
}
-static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_not_init(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
- verbose("mark_reg_not_init(regs, %u)\n", regno);
+ verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(regs + regno);
@@ -625,22 +595,23 @@ static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
__mark_reg_not_init(regs + regno);
}
-static void init_reg_state(struct bpf_reg_state *regs)
+static void init_reg_state(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs)
{
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
- mark_reg_not_init(regs, i);
+ mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
}
/* frame pointer */
regs[BPF_REG_FP].type = PTR_TO_STACK;
- mark_reg_known_zero(regs, BPF_REG_FP);
+ mark_reg_known_zero(env, regs, BPF_REG_FP);
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
- mark_reg_known_zero(regs, BPF_REG_1);
+ mark_reg_known_zero(env, regs, BPF_REG_1);
}
enum reg_arg_type {
@@ -671,29 +642,29 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno)
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
enum reg_arg_type t)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = env->cur_state->regs;
if (regno >= MAX_BPF_REG) {
- verbose("R%d is invalid\n", regno);
+ verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
if (regs[regno].type == NOT_INIT) {
- verbose("R%d !read_ok\n", regno);
+ verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
- mark_reg_read(&env->cur_state, regno);
+ mark_reg_read(env->cur_state, regno);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
- verbose("frame pointer is read only\n");
+ verbose(env, "frame pointer is read only\n");
return -EACCES;
}
regs[regno].live |= REG_LIVE_WRITTEN;
if (t == DST_OP)
- mark_reg_unknown(regs, regno);
+ mark_reg_unknown(env, regs, regno);
}
return 0;
}
@@ -706,6 +677,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_STACK:
case PTR_TO_CTX:
case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
case CONST_PTR_TO_MAP:
return true;
@@ -717,35 +689,48 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
-static int check_stack_write(struct bpf_verifier_state *state, int off,
+static int check_stack_write(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *state, int off,
int size, int value_regno)
{
- int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
+ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
+
+ err = realloc_verifier_state(state, round_up(slot + 1, BPF_REG_SIZE),
+ true);
+ if (err)
+ return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
+ if (!env->allow_ptr_leaks &&
+ state->stack[spi].slot_type[0] == STACK_SPILL &&
+ size != BPF_REG_SIZE) {
+ verbose(env, "attempt to corrupt spilled pointer on stack\n");
+ return -EACCES;
+ }
if (value_regno >= 0 &&
is_spillable_regtype(state->regs[value_regno].type)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
- verbose("invalid size of register spill\n");
+ verbose(env, "invalid size of register spill\n");
return -EACCES;
}
/* save register state */
- state->spilled_regs[spi] = state->regs[value_regno];
- state->spilled_regs[spi].live |= REG_LIVE_WRITTEN;
+ state->stack[spi].spilled_ptr = state->regs[value_regno];
+ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++)
- state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
+ state->stack[spi].slot_type[i] = STACK_SPILL;
} else {
/* regular write of data into stack */
- state->spilled_regs[spi] = (struct bpf_reg_state) {};
+ state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};
for (i = 0; i < size; i++)
- state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
+ state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
+ STACK_MISC;
}
return 0;
}
@@ -756,66 +741,72 @@ static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slo
while (parent) {
/* if read wasn't screened by an earlier write ... */
- if (state->spilled_regs[slot].live & REG_LIVE_WRITTEN)
+ if (state->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
break;
/* ... then we depend on parent's value */
- parent->spilled_regs[slot].live |= REG_LIVE_READ;
+ parent->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
}
}
-static int check_stack_read(struct bpf_verifier_state *state, int off, int size,
+static int check_stack_read(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *state, int off, int size,
int value_regno)
{
- u8 *slot_type;
- int i, spi;
+ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
+ u8 *stype;
- slot_type = &state->stack_slot_type[MAX_BPF_STACK + off];
+ if (state->allocated_stack <= slot) {
+ verbose(env, "invalid read from stack off %d+0 size %d\n",
+ off, size);
+ return -EACCES;
+ }
+ stype = state->stack[spi].slot_type;
- if (slot_type[0] == STACK_SPILL) {
+ if (stype[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
- verbose("invalid size of register spill\n");
+ verbose(env, "invalid size of register spill\n");
return -EACCES;
}
for (i = 1; i < BPF_REG_SIZE; i++) {
- if (slot_type[i] != STACK_SPILL) {
- verbose("corrupted spill memory\n");
+ if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
+ verbose(env, "corrupted spill memory\n");
return -EACCES;
}
}
- spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
-
if (value_regno >= 0) {
/* restore register state from stack */
- state->regs[value_regno] = state->spilled_regs[spi];
+ state->regs[value_regno] = state->stack[spi].spilled_ptr;
mark_stack_slot_read(state, spi);
}
return 0;
} else {
for (i = 0; i < size; i++) {
- if (slot_type[i] != STACK_MISC) {
- verbose("invalid read from stack off %d+%d size %d\n",
+ if (stype[(slot - i) % BPF_REG_SIZE] != STACK_MISC) {
+ verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
}
if (value_regno >= 0)
/* have read misc data from the stack */
- mark_reg_unknown(state->regs, value_regno);
+ mark_reg_unknown(env, state->regs, value_regno);
return 0;
}
}
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
- int size)
+ int size, bool zero_size_allowed)
{
- struct bpf_map *map = env->cur_state.regs[regno].map_ptr;
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map = regs[regno].map_ptr;
- if (off < 0 || size <= 0 || off + size > map->value_size) {
- verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
+ if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+ off + size > map->value_size) {
+ verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
@@ -824,9 +815,9 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, u32 regno,
- int off, int size)
+ int off, int size, bool zero_size_allowed)
{
- struct bpf_verifier_state *state = &env->cur_state;
+ struct bpf_verifier_state *state = env->cur_state;
struct bpf_reg_state *reg = &state->regs[regno];
int err;
@@ -834,8 +825,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
- if (log_level)
- print_verifier_state(state);
+ if (env->log.level)
+ print_verifier_state(env, state);
/* The minimum value is only important with signed
* comparisons where we can't assume the floor of a
* value is 0. If we are using signed variables for our
@@ -843,13 +834,15 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
* will have a set floor within our range.
*/
if (reg->smin_value < 0) {
- verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+ verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
- err = __check_map_access(env, regno, reg->smin_value + off, size);
+ err = __check_map_access(env, regno, reg->smin_value + off, size,
+ zero_size_allowed);
if (err) {
- verbose("R%d min value is outside of the array range\n", regno);
+ verbose(env, "R%d min value is outside of the array range\n",
+ regno);
return err;
}
@@ -858,13 +851,15 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
* If reg->umax_value + off could overflow, treat that as unbounded too.
*/
if (reg->umax_value >= BPF_MAX_VAR_OFF) {
- verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n",
+ verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
regno);
return -EACCES;
}
- err = __check_map_access(env, regno, reg->umax_value + off, size);
+ err = __check_map_access(env, regno, reg->umax_value + off, size,
+ zero_size_allowed);
if (err)
- verbose("R%d max value is outside of the array range\n", regno);
+ verbose(env, "R%d max value is outside of the array range\n",
+ regno);
return err;
}
@@ -897,13 +892,14 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
}
static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
- int off, int size)
+ int off, int size, bool zero_size_allowed)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
- if (off < 0 || size <= 0 || (u64)off + size > reg->range) {
- verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
+ if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+ (u64)off + size > reg->range) {
+ verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
off, size, regno, reg->id, reg->off, reg->range);
return -EACCES;
}
@@ -911,9 +907,9 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
}
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
- int size)
+ int size, bool zero_size_allowed)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
int err;
@@ -926,13 +922,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
* detail to prove they're safe.
*/
if (reg->smin_value < 0) {
- verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+ verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
- err = __check_packet_access(env, regno, off, size);
+ err = __check_packet_access(env, regno, off, size, zero_size_allowed);
if (err) {
- verbose("R%d offset is outside of the packet\n", regno);
+ verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
return err;
@@ -946,12 +942,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
.reg_type = *reg_type,
};
- /* for analyzer ctx accesses are already validated and converted */
- if (env->analyzer_ops)
- return 0;
-
- if (env->prog->aux->ops->is_valid_access &&
- env->prog->aux->ops->is_valid_access(off, size, t, &info)) {
+ if (env->ops->is_valid_access &&
+ env->ops->is_valid_access(off, size, t, &info)) {
/* A non zero info.ctx_field_size indicates that this field is a
* candidate for later verifier transformation to load the whole
* field and then apply a mask when accessed with a narrower
@@ -959,16 +951,16 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
* will only allow for whole field access and rejects any other
* type of narrower access.
*/
- env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
*reg_type = info.reg_type;
+ env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
return 0;
}
- verbose("invalid bpf_context access off=%d size=%d\n", off, size);
+ verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
return -EACCES;
}
@@ -983,10 +975,11 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
- return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
+ return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
}
-static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
int off, int size, bool strict)
{
struct tnum reg_off;
@@ -1011,7 +1004,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose("misaligned packet access off %d+%s+%d+%d size %d\n",
+ verbose(env,
+ "misaligned packet access off %d+%s+%d+%d size %d\n",
ip_align, tn_buf, reg->off, off, size);
return -EACCES;
}
@@ -1019,7 +1013,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
return 0;
}
-static int check_generic_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
const char *pointer_desc,
int off, int size, bool strict)
{
@@ -1034,7 +1029,7 @@ static int check_generic_ptr_alignment(const struct bpf_reg_state *reg,
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose("misaligned %saccess off %s+%d+%d size %d\n",
+ verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
pointer_desc, tn_buf, reg->off, off, size);
return -EACCES;
}
@@ -1051,8 +1046,11 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
switch (reg->type) {
case PTR_TO_PACKET:
- /* special case, because of NET_IP_ALIGN */
- return check_pkt_ptr_alignment(reg, off, size, strict);
+ case PTR_TO_PACKET_META:
+ /* Special case, because of NET_IP_ALIGN. Given metadata sits
+ * right in front, treat it the very same way.
+ */
+ return check_pkt_ptr_alignment(env, reg, off, size, strict);
case PTR_TO_MAP_VALUE:
pointer_desc = "value ";
break;
@@ -1065,7 +1063,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
default:
break;
}
- return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict);
+ return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
+ strict);
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -1078,8 +1077,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
int bpf_size, enum bpf_access_type t,
int value_regno)
{
- struct bpf_verifier_state *state = &env->cur_state;
- struct bpf_reg_state *reg = &state->regs[regno];
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = regs + regno;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
@@ -1097,27 +1097,28 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
- verbose("R%d leaks addr into map\n", value_regno);
+ verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
- err = check_map_access(env, regno, off, size);
+ err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
- mark_reg_unknown(state->regs, value_regno);
+ mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
- verbose("R%d leaks addr into ctx\n", value_regno);
+ verbose(env, "R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
/* ctx accesses must be at a fixed offset, so that we can
* determine what type of data were returned.
*/
if (reg->off) {
- verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+ verbose(env,
+ "dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
regno, reg->off, off - reg->off);
return -EACCES;
}
@@ -1125,24 +1126,26 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose("variable ctx access var_off=%s off=%d size=%d",
+ verbose(env,
+ "variable ctx access var_off=%s off=%d size=%d",
tn_buf, off, size);
return -EACCES;
}
err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
- * PTR_TO_PACKET[_END]. In the latter case, we know
- * the offset is zero.
+ * PTR_TO_PACKET[_META,_END]. In the latter
+ * case, we know the offset is zero.
*/
if (reg_type == SCALAR_VALUE)
- mark_reg_unknown(state->regs, value_regno);
+ mark_reg_unknown(env, regs, value_regno);
else
- mark_reg_known_zero(state->regs, value_regno);
- state->regs[value_regno].id = 0;
- state->regs[value_regno].off = 0;
- state->regs[value_regno].range = 0;
- state->regs[value_regno].type = reg_type;
+ mark_reg_known_zero(env, regs,
+ value_regno);
+ regs[value_regno].id = 0;
+ regs[value_regno].off = 0;
+ regs[value_regno].range = 0;
+ regs[value_regno].type = reg_type;
}
} else if (reg->type == PTR_TO_STACK) {
@@ -1154,55 +1157,52 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose("variable stack access var_off=%s off=%d size=%d",
+ verbose(env, "variable stack access var_off=%s off=%d size=%d",
tn_buf, off, size);
return -EACCES;
}
off += reg->var_off.value;
if (off >= 0 || off < -MAX_BPF_STACK) {
- verbose("invalid stack off=%d size=%d\n", off, size);
+ verbose(env, "invalid stack off=%d size=%d\n", off,
+ size);
return -EACCES;
}
if (env->prog->aux->stack_depth < -off)
env->prog->aux->stack_depth = -off;
- if (t == BPF_WRITE) {
- if (!env->allow_ptr_leaks &&
- state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL &&
- size != BPF_REG_SIZE) {
- verbose("attempt to corrupt spilled pointer on stack\n");
- return -EACCES;
- }
- err = check_stack_write(state, off, size, value_regno);
- } else {
- err = check_stack_read(state, off, size, value_regno);
- }
- } else if (reg->type == PTR_TO_PACKET) {
+ if (t == BPF_WRITE)
+ err = check_stack_write(env, state, off, size,
+ value_regno);
+ else
+ err = check_stack_read(env, state, off, size,
+ value_regno);
+ } else if (reg_is_pkt_pointer(reg)) {
if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
- verbose("cannot write into packet\n");
+ verbose(env, "cannot write into packet\n");
return -EACCES;
}
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
- verbose("R%d leaks addr into packet\n", value_regno);
+ verbose(env, "R%d leaks addr into packet\n",
+ value_regno);
return -EACCES;
}
- err = check_packet_access(env, regno, off, size);
+ err = check_packet_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
- mark_reg_unknown(state->regs, value_regno);
+ mark_reg_unknown(env, regs, value_regno);
} else {
- verbose("R%d invalid mem access '%s'\n",
- regno, reg_type_str[reg->type]);
+ verbose(env, "R%d invalid mem access '%s'\n", regno,
+ reg_type_str[reg->type]);
return -EACCES;
}
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
- state->regs[value_regno].type == SCALAR_VALUE) {
+ regs[value_regno].type == SCALAR_VALUE) {
/* b/h/w load zero-extends, mark upper bits as known 0 */
- state->regs[value_regno].var_off = tnum_cast(
- state->regs[value_regno].var_off, size);
- __update_reg_bounds(&state->regs[value_regno]);
+ regs[value_regno].var_off =
+ tnum_cast(regs[value_regno].var_off, size);
+ __update_reg_bounds(&regs[value_regno]);
}
return err;
}
@@ -1213,7 +1213,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
insn->imm != 0) {
- verbose("BPF_XADD uses reserved fields\n");
+ verbose(env, "BPF_XADD uses reserved fields\n");
return -EINVAL;
}
@@ -1228,7 +1228,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
return err;
if (is_pointer_value(env, insn->src_reg)) {
- verbose("R%d leaks addr into mem\n", insn->src_reg);
+ verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
return -EACCES;
}
@@ -1259,9 +1259,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
- struct bpf_verifier_state *state = &env->cur_state;
+ struct bpf_verifier_state *state = env->cur_state;
struct bpf_reg_state *regs = state->regs;
- int off, i;
+ int off, i, slot, spi;
if (regs[regno].type != PTR_TO_STACK) {
/* Allow zero-byte read from NULL, regardless of pointer type */
@@ -1269,7 +1269,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
register_is_null(regs[regno]))
return 0;
- verbose("R%d type=%s expected=%s\n", regno,
+ verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[regs[regno].type],
reg_type_str[PTR_TO_STACK]);
return -EACCES;
@@ -1280,13 +1280,13 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off);
- verbose("invalid variable stack read R%d var_off=%s\n",
+ verbose(env, "invalid variable stack read R%d var_off=%s\n",
regno, tn_buf);
}
off = regs[regno].off + regs[regno].var_off.value;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
- access_size <= 0) {
- verbose("invalid stack type R%d off=%d access_size=%d\n",
+ access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
+ verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
regno, off, access_size);
return -EACCES;
}
@@ -1301,8 +1301,12 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
}
for (i = 0; i < access_size; i++) {
- if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
- verbose("invalid indirect read from stack off %d+%d size %d\n",
+ slot = -(off + i) - 1;
+ spi = slot / BPF_REG_SIZE;
+ if (state->allocated_stack <= slot ||
+ state->stack[spi].slot_type[slot % BPF_REG_SIZE] !=
+ STACK_MISC) {
+ verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
off, i, access_size);
return -EACCES;
}
@@ -1314,13 +1318,16 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
- struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
+ struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
switch (reg->type) {
case PTR_TO_PACKET:
- return check_packet_access(env, regno, reg->off, access_size);
+ case PTR_TO_PACKET_META:
+ return check_packet_access(env, regno, reg->off, access_size,
+ zero_size_allowed);
case PTR_TO_MAP_VALUE:
- return check_map_access(env, regno, reg->off, access_size);
+ return check_map_access(env, regno, reg->off, access_size,
+ zero_size_allowed);
default: /* scalar_value|ptr_to_stack or invalid ptr */
return check_stack_boundary(env, regno, access_size,
zero_size_allowed, meta);
@@ -1331,7 +1338,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
struct bpf_call_arg_meta *meta)
{
- struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
+ struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
enum bpf_reg_type expected_type, type = reg->type;
int err = 0;
@@ -1344,22 +1351,24 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
if (arg_type == ARG_ANYTHING) {
if (is_pointer_value(env, regno)) {
- verbose("R%d leaks addr into helper function\n", regno);
+ verbose(env, "R%d leaks addr into helper function\n",
+ regno);
return -EACCES;
}
return 0;
}
- if (type == PTR_TO_PACKET &&
+ if (type_is_pkt_pointer(type) &&
!may_access_direct_pkt_data(env, meta, BPF_READ)) {
- verbose("helper access to the packet is not allowed\n");
+ verbose(env, "helper access to the packet is not allowed\n");
return -EACCES;
}
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
- if (type != PTR_TO_PACKET && type != expected_type)
+ if (!type_is_pkt_pointer(type) &&
+ type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
arg_type == ARG_CONST_SIZE_OR_ZERO) {
@@ -1383,12 +1392,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
*/
if (register_is_null(*reg))
/* final test in check_stack_boundary() */;
- else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE &&
+ else if (!type_is_pkt_pointer(type) &&
+ type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
} else {
- verbose("unsupported arg_type %d\n", arg_type);
+ verbose(env, "unsupported arg_type %d\n", arg_type);
return -EFAULT;
}
@@ -1406,12 +1416,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
* we have to check map_key here. Otherwise it means
* that kernel subsystem misconfigured verifier
*/
- verbose("invalid map_ptr to access map->key\n");
+ verbose(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
- if (type == PTR_TO_PACKET)
+ if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
- meta->map_ptr->key_size);
+ meta->map_ptr->key_size,
+ false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->key_size,
@@ -1422,12 +1433,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
*/
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
- verbose("invalid map_ptr to access map->value\n");
+ verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
- if (type == PTR_TO_PACKET)
+ if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
- meta->map_ptr->value_size);
+ meta->map_ptr->value_size,
+ false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->value_size,
@@ -1442,7 +1454,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
*/
if (regno == 0) {
/* kernel subsystem misconfigured verifier */
- verbose("ARG_CONST_SIZE cannot be first argument\n");
+ verbose(env,
+ "ARG_CONST_SIZE cannot be first argument\n");
return -EACCES;
}
@@ -1459,7 +1472,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
meta = NULL;
if (reg->smin_value < 0) {
- verbose("R%d min value is negative, either use unsigned or 'var &= const'\n",
+ verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
regno);
return -EACCES;
}
@@ -1473,7 +1486,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
}
if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
- verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
+ verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
regno);
return -EACCES;
}
@@ -1484,12 +1497,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
return err;
err_type:
- verbose("R%d type=%s expected=%s\n", regno,
+ verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[type], reg_type_str[expected_type]);
return -EACCES;
}
-static int check_map_func_compatibility(struct bpf_map *map, int func_id)
+static int check_map_func_compatibility(struct bpf_verifier_env *env,
+ struct bpf_map *map, int func_id)
{
if (!map)
return 0;
@@ -1502,7 +1516,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
break;
case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
if (func_id != BPF_FUNC_perf_event_read &&
- func_id != BPF_FUNC_perf_event_output)
+ func_id != BPF_FUNC_perf_event_output &&
+ func_id != BPF_FUNC_perf_event_read_value)
goto error;
break;
case BPF_MAP_TYPE_STACK_TRACE:
@@ -1522,6 +1537,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
+ /* Restrict bpf side of cpumap, open when use-cases appear */
+ case BPF_MAP_TYPE_CPUMAP:
+ if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
@@ -1545,6 +1565,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
break;
case BPF_FUNC_perf_event_read:
case BPF_FUNC_perf_event_output:
+ case BPF_FUNC_perf_event_read_value:
if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
goto error;
break;
@@ -1558,7 +1579,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
goto error;
break;
case BPF_FUNC_redirect_map:
- if (map->map_type != BPF_MAP_TYPE_DEVMAP)
+ if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+ map->map_type != BPF_MAP_TYPE_CPUMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
@@ -1575,7 +1597,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
return 0;
error:
- verbose("cannot pass map_type %d into func %s#%d\n",
+ verbose(env, "cannot pass map_type %d into func %s#%d\n",
map->map_type, func_id_name(func_id), func_id);
return -EINVAL;
}
@@ -1598,57 +1620,55 @@ static int check_raw_mode(const struct bpf_func_proto *fn)
return count > 1 ? -EINVAL : 0;
}
-/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid,
- * so turn them into unknown SCALAR_VALUE.
+/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
+ * are now invalid, so turn them into unknown SCALAR_VALUE.
*/
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
- struct bpf_verifier_state *state = &env->cur_state;
+ struct bpf_verifier_state *state = env->cur_state;
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
- if (regs[i].type == PTR_TO_PACKET ||
- regs[i].type == PTR_TO_PACKET_END)
- mark_reg_unknown(regs, i);
+ if (reg_is_pkt_pointer_any(&regs[i]))
+ mark_reg_unknown(env, regs, i);
- for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
- if (state->stack_slot_type[i] != STACK_SPILL)
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
- reg = &state->spilled_regs[i / BPF_REG_SIZE];
- if (reg->type != PTR_TO_PACKET &&
- reg->type != PTR_TO_PACKET_END)
- continue;
- __mark_reg_unknown(reg);
+ reg = &state->stack[i].spilled_ptr;
+ if (reg_is_pkt_pointer_any(reg))
+ __mark_reg_unknown(reg);
}
}
static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
- struct bpf_verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
- struct bpf_reg_state *regs = state->regs;
+ struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
bool changes_data;
int i, err;
/* find function prototype */
if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
- verbose("invalid func %s#%d\n", func_id_name(func_id), func_id);
+ verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
+ func_id);
return -EINVAL;
}
- if (env->prog->aux->ops->get_func_proto)
- fn = env->prog->aux->ops->get_func_proto(func_id);
+ if (env->ops->get_func_proto)
+ fn = env->ops->get_func_proto(func_id);
if (!fn) {
- verbose("unknown func %s#%d\n", func_id_name(func_id), func_id);
+ verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
+ func_id);
return -EINVAL;
}
/* eBPF programs must be GPL compatible to use GPL-ed functions */
if (!env->prog->gpl_compatible && fn->gpl_only) {
- verbose("cannot call GPL only function from proprietary program\n");
+ verbose(env, "cannot call GPL only function from proprietary program\n");
return -EINVAL;
}
@@ -1662,7 +1682,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
*/
err = check_raw_mode(fn);
if (err) {
- verbose("kernel subsystem misconfigured func %s#%d\n",
+ verbose(env, "kernel subsystem misconfigured func %s#%d\n",
func_id_name(func_id), func_id);
return err;
}
@@ -1693,16 +1713,17 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
return err;
}
+ regs = cur_regs(env);
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
- mark_reg_not_init(regs, caller_saved[i]);
+ mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* update return register (already marked as written above) */
if (fn->ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
- mark_reg_unknown(regs, BPF_REG_0);
+ mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
@@ -1710,14 +1731,15 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
- mark_reg_known_zero(regs, BPF_REG_0);
+ mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].off = 0;
/* remember map_ptr, so that check_map_access()
* can check 'value_size' boundary of memory access
* to map element returned from bpf_map_lookup_elem()
*/
if (meta.map_ptr == NULL) {
- verbose("kernel subsystem misconfigured verifier\n");
+ verbose(env,
+ "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
@@ -1728,12 +1750,12 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
else if (insn_aux->map_ptr != meta.map_ptr)
insn_aux->map_ptr = BPF_MAP_PTR_POISON;
} else {
- verbose("unknown return type %d of func %s#%d\n",
+ verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
return -EINVAL;
}
- err = check_map_func_compatibility(meta.map_ptr, func_id);
+ err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
return err;
@@ -1780,7 +1802,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
const struct bpf_reg_state *ptr_reg,
const struct bpf_reg_state *off_reg)
{
- struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
+ struct bpf_reg_state *regs = cur_regs(env), *dst_reg;
bool known = tnum_is_const(off_reg->var_off);
s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
@@ -1792,39 +1814,42 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg = &regs[dst];
if (WARN_ON_ONCE(known && (smin_val != smax_val))) {
- print_verifier_state(&env->cur_state);
- verbose("verifier internal error: known but bad sbounds\n");
+ print_verifier_state(env, env->cur_state);
+ verbose(env,
+ "verifier internal error: known but bad sbounds\n");
return -EINVAL;
}
if (WARN_ON_ONCE(known && (umin_val != umax_val))) {
- print_verifier_state(&env->cur_state);
- verbose("verifier internal error: known but bad ubounds\n");
+ print_verifier_state(env, env->cur_state);
+ verbose(env,
+ "verifier internal error: known but bad ubounds\n");
return -EINVAL;
}
if (BPF_CLASS(insn->code) != BPF_ALU64) {
/* 32-bit ALU ops on pointers produce (meaningless) scalars */
if (!env->allow_ptr_leaks)
- verbose("R%d 32-bit pointer arithmetic prohibited\n",
+ verbose(env,
+ "R%d 32-bit pointer arithmetic prohibited\n",
dst);
return -EACCES;
}
if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
if (!env->allow_ptr_leaks)
- verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
+ verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
dst);
return -EACCES;
}
if (ptr_reg->type == CONST_PTR_TO_MAP) {
if (!env->allow_ptr_leaks)
- verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
+ verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
dst);
return -EACCES;
}
if (ptr_reg->type == PTR_TO_PACKET_END) {
if (!env->allow_ptr_leaks)
- verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
+ verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
dst);
return -EACCES;
}
@@ -1879,7 +1904,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
- if (ptr_reg->type == PTR_TO_PACKET) {
+ if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
dst_reg->range = 0;
@@ -1889,7 +1914,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
if (!env->allow_ptr_leaks)
- verbose("R%d tried to subtract pointer from scalar\n",
+ verbose(env, "R%d tried to subtract pointer from scalar\n",
dst);
return -EACCES;
}
@@ -1899,7 +1924,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
*/
if (ptr_reg->type == PTR_TO_STACK) {
if (!env->allow_ptr_leaks)
- verbose("R%d subtraction from stack pointer prohibited\n",
+ verbose(env, "R%d subtraction from stack pointer prohibited\n",
dst);
return -EACCES;
}
@@ -1939,7 +1964,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
- if (ptr_reg->type == PTR_TO_PACKET) {
+ if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
@@ -1954,13 +1979,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
* ptr &= ~3 which would reduce min_value by 3.)
*/
if (!env->allow_ptr_leaks)
- verbose("R%d bitwise operator %s on pointer prohibited\n",
+ verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
default:
/* other operators (e.g. MUL,LSH) produce non-pointer results */
if (!env->allow_ptr_leaks)
- verbose("R%d pointer arithmetic with %s operator prohibited\n",
+ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
}
@@ -1976,7 +2001,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
struct bpf_reg_state *dst_reg,
struct bpf_reg_state src_reg)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
bool src_known, dst_known;
s64 smin_val, smax_val;
@@ -2126,7 +2151,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Shifts greater than 63 are undefined. This includes
* shifts by a negative number.
*/
- mark_reg_unknown(regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
/* We lose all sign bit information (except what we can pick
@@ -2154,7 +2179,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Shifts greater than 63 are undefined. This includes
* shifts by a negative number.
*/
- mark_reg_unknown(regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
/* BPF_RSH is an unsigned shift, so make the appropriate casts */
@@ -2182,7 +2207,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
__update_reg_bounds(dst_reg);
break;
default:
- mark_reg_unknown(regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
@@ -2197,7 +2222,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
- struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg, *src_reg;
+ struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg;
struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
u8 opcode = BPF_OP(insn->code);
int rc;
@@ -2214,12 +2239,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
* an arbitrary scalar.
*/
if (!env->allow_ptr_leaks) {
- verbose("R%d pointer %s pointer prohibited\n",
+ verbose(env, "R%d pointer %s pointer prohibited\n",
insn->dst_reg,
bpf_alu_string[opcode >> 4]);
return -EACCES;
}
- mark_reg_unknown(regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->dst_reg);
return 0;
} else {
/* scalar += pointer
@@ -2271,13 +2296,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* Got here implies adding two SCALAR_VALUEs */
if (WARN_ON_ONCE(ptr_reg)) {
- print_verifier_state(&env->cur_state);
- verbose("verifier internal error: unexpected ptr_reg\n");
+ print_verifier_state(env, env->cur_state);
+ verbose(env, "verifier internal error: unexpected ptr_reg\n");
return -EINVAL;
}
if (WARN_ON(!src_reg)) {
- print_verifier_state(&env->cur_state);
- verbose("verifier internal error: no src_reg\n");
+ print_verifier_state(env, env->cur_state);
+ verbose(env, "verifier internal error: no src_reg\n");
return -EINVAL;
}
return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
@@ -2286,7 +2311,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
int err;
@@ -2295,14 +2320,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (BPF_SRC(insn->code) != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->off != 0 || insn->imm != 0) {
- verbose("BPF_NEG uses reserved fields\n");
+ verbose(env, "BPF_NEG uses reserved fields\n");
return -EINVAL;
}
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
BPF_CLASS(insn->code) == BPF_ALU64) {
- verbose("BPF_END uses reserved fields\n");
+ verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
}
@@ -2313,7 +2338,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
if (is_pointer_value(env, insn->dst_reg)) {
- verbose("R%d pointer arithmetic prohibited\n",
+ verbose(env, "R%d pointer arithmetic prohibited\n",
insn->dst_reg);
return -EACCES;
}
@@ -2327,7 +2352,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
- verbose("BPF_MOV uses reserved fields\n");
+ verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
@@ -2337,7 +2362,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
- verbose("BPF_MOV uses reserved fields\n");
+ verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
}
@@ -2357,11 +2382,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
- verbose("R%d partial copy of pointer\n",
+ verbose(env,
+ "R%d partial copy of pointer\n",
insn->src_reg);
return -EACCES;
}
- mark_reg_unknown(regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->dst_reg);
/* high 32 bits are known zero. */
regs[insn->dst_reg].var_off = tnum_cast(
regs[insn->dst_reg].var_off, 4);
@@ -2376,14 +2402,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
} else if (opcode > BPF_END) {
- verbose("invalid BPF_ALU opcode %x\n", opcode);
+ verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
return -EINVAL;
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
- verbose("BPF_ALU uses reserved fields\n");
+ verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
@@ -2392,7 +2418,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
- verbose("BPF_ALU uses reserved fields\n");
+ verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
}
@@ -2404,7 +2430,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
- verbose("div by zero\n");
+ verbose(env, "div by zero\n");
return -EINVAL;
}
@@ -2413,7 +2439,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
if (insn->imm < 0 || insn->imm >= size) {
- verbose("invalid shift %d\n", insn->imm);
+ verbose(env, "invalid shift %d\n", insn->imm);
return -EINVAL;
}
}
@@ -2431,6 +2457,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
static void find_good_pkt_pointers(struct bpf_verifier_state *state,
struct bpf_reg_state *dst_reg,
+ enum bpf_reg_type type,
bool range_right_open)
{
struct bpf_reg_state *regs = state->regs, *reg;
@@ -2501,15 +2528,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
* dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
*/
for (i = 0; i < MAX_BPF_REG; i++)
- if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
+ if (regs[i].type == type && regs[i].id == dst_reg->id)
/* keep the maximum range already checked */
regs[i].range = max(regs[i].range, new_range);
- for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
- if (state->stack_slot_type[i] != STACK_SPILL)
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
- reg = &state->spilled_regs[i / BPF_REG_SIZE];
- if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
+ reg = &state->stack[i].spilled_ptr;
+ if (reg->type == type && reg->id == dst_reg->id)
reg->range = max(reg->range, new_range);
}
}
@@ -2758,29 +2785,122 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
for (i = 0; i < MAX_BPF_REG; i++)
mark_map_reg(regs, i, id, is_null);
- for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
- if (state->stack_slot_type[i] != STACK_SPILL)
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
- mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, is_null);
+ mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
}
}
+static bool try_match_pkt_pointers(const struct bpf_insn *insn,
+ struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg,
+ struct bpf_verifier_state *this_branch,
+ struct bpf_verifier_state *other_branch)
+{
+ if (BPF_SRC(insn->code) != BPF_X)
+ return false;
+
+ switch (BPF_OP(insn->code)) {
+ case BPF_JGT:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' > pkt_end, pkt_meta' > pkt_data */
+ find_good_pkt_pointers(this_branch, dst_reg,
+ dst_reg->type, false);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end > pkt_data', pkt_data > pkt_meta' */
+ find_good_pkt_pointers(other_branch, src_reg,
+ src_reg->type, true);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JLT:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' < pkt_end, pkt_meta' < pkt_data */
+ find_good_pkt_pointers(other_branch, dst_reg,
+ dst_reg->type, true);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end < pkt_data', pkt_data > pkt_meta' */
+ find_good_pkt_pointers(this_branch, src_reg,
+ src_reg->type, false);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JGE:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
+ find_good_pkt_pointers(this_branch, dst_reg,
+ dst_reg->type, true);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
+ find_good_pkt_pointers(other_branch, src_reg,
+ src_reg->type, false);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JLE:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
+ find_good_pkt_pointers(other_branch, dst_reg,
+ dst_reg->type, false);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
+ find_good_pkt_pointers(this_branch, src_reg,
+ src_reg->type, true);
+ } else {
+ return false;
+ }
+ break;
+ default:
+ return false;
+ }
+
+ return true;
+}
+
static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
- struct bpf_verifier_state *other_branch, *this_branch = &env->cur_state;
+ struct bpf_verifier_state *other_branch, *this_branch = env->cur_state;
struct bpf_reg_state *regs = this_branch->regs, *dst_reg;
u8 opcode = BPF_OP(insn->code);
int err;
if (opcode > BPF_JSLE) {
- verbose("invalid BPF_JMP opcode %x\n", opcode);
+ verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
return -EINVAL;
}
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
- verbose("BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP uses reserved fields\n");
return -EINVAL;
}
@@ -2790,13 +2910,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return err;
if (is_pointer_value(env, insn->src_reg)) {
- verbose("R%d pointer comparison prohibited\n",
+ verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
} else {
if (insn->src_reg != BPF_REG_0) {
- verbose("BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP uses reserved fields\n");
return -EINVAL;
}
}
@@ -2871,52 +2991,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*/
mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
- dst_reg->type == PTR_TO_PACKET &&
- regs[insn->src_reg].type == PTR_TO_PACKET_END) {
- /* pkt_data' > pkt_end */
- find_good_pkt_pointers(this_branch, dst_reg, false);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
- dst_reg->type == PTR_TO_PACKET_END &&
- regs[insn->src_reg].type == PTR_TO_PACKET) {
- /* pkt_end > pkt_data' */
- find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
- dst_reg->type == PTR_TO_PACKET &&
- regs[insn->src_reg].type == PTR_TO_PACKET_END) {
- /* pkt_data' < pkt_end */
- find_good_pkt_pointers(other_branch, dst_reg, true);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
- dst_reg->type == PTR_TO_PACKET_END &&
- regs[insn->src_reg].type == PTR_TO_PACKET) {
- /* pkt_end < pkt_data' */
- find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
- dst_reg->type == PTR_TO_PACKET &&
- regs[insn->src_reg].type == PTR_TO_PACKET_END) {
- /* pkt_data' >= pkt_end */
- find_good_pkt_pointers(this_branch, dst_reg, true);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
- dst_reg->type == PTR_TO_PACKET_END &&
- regs[insn->src_reg].type == PTR_TO_PACKET) {
- /* pkt_end >= pkt_data' */
- find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
- dst_reg->type == PTR_TO_PACKET &&
- regs[insn->src_reg].type == PTR_TO_PACKET_END) {
- /* pkt_data' <= pkt_end */
- find_good_pkt_pointers(other_branch, dst_reg, false);
- } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
- dst_reg->type == PTR_TO_PACKET_END &&
- regs[insn->src_reg].type == PTR_TO_PACKET) {
- /* pkt_end <= pkt_data' */
- find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
- } else if (is_pointer_value(env, insn->dst_reg)) {
- verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
+ } else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
+ this_branch, other_branch) &&
+ is_pointer_value(env, insn->dst_reg)) {
+ verbose(env, "R%d pointer comparison prohibited\n",
+ insn->dst_reg);
return -EACCES;
}
- if (log_level)
- print_verifier_state(this_branch);
+ if (env->log.level)
+ print_verifier_state(env, this_branch);
return 0;
}
@@ -2931,15 +3014,15 @@ static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
- verbose("invalid BPF_LD_IMM insn\n");
+ verbose(env, "invalid BPF_LD_IMM insn\n");
return -EINVAL;
}
if (insn->off != 0) {
- verbose("BPF_LD_IMM64 uses reserved fields\n");
+ verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
return -EINVAL;
}
@@ -2992,19 +3075,19 @@ static bool may_access_skb(enum bpf_prog_type type)
*/
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
- struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *regs = cur_regs(env);
u8 mode = BPF_MODE(insn->code);
int i, err;
if (!may_access_skb(env->prog->type)) {
- verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
+ verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
return -EINVAL;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
BPF_SIZE(insn->code) == BPF_DW ||
(mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
- verbose("BPF_LD_[ABS|IND] uses reserved fields\n");
+ verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
return -EINVAL;
}
@@ -3014,7 +3097,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
if (regs[BPF_REG_6].type != PTR_TO_CTX) {
- verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+ verbose(env,
+ "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
}
@@ -3027,7 +3111,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
- mark_reg_not_init(regs, caller_saved[i]);
+ mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
@@ -3035,7 +3119,45 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
* the value fetched from the packet.
* Already marked as written above.
*/
- mark_reg_unknown(regs, BPF_REG_0);
+ mark_reg_unknown(env, regs, BPF_REG_0);
+ return 0;
+}
+
+static int check_return_code(struct bpf_verifier_env *env)
+{
+ struct bpf_reg_state *reg;
+ struct tnum range = tnum_range(0, 1);
+
+ switch (env->prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ break;
+ default:
+ return 0;
+ }
+
+ reg = cur_regs(env) + BPF_REG_0;
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "At program exit the register R0 is not a known value (%s)\n",
+ reg_type_str[reg->type]);
+ return -EINVAL;
+ }
+
+ if (!tnum_in(range, reg->var_off)) {
+ verbose(env, "At program exit the register R0 ");
+ if (!tnum_is_unknown(reg->var_off)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "has value %s", tn_buf);
+ } else {
+ verbose(env, "has unknown scalar value");
+ }
+ verbose(env, " should have been 0 or 1\n");
+ return -EINVAL;
+ }
return 0;
}
@@ -3099,7 +3221,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
return 0;
if (w < 0 || w >= env->prog->len) {
- verbose("jump out of range from insn %d to %d\n", t, w);
+ verbose(env, "jump out of range from insn %d to %d\n", t, w);
return -EINVAL;
}
@@ -3116,13 +3238,13 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
insn_stack[cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
- verbose("back-edge from insn %d to %d\n", t, w);
+ verbose(env, "back-edge from insn %d to %d\n", t, w);
return -EINVAL;
} else if (insn_state[w] == EXPLORED) {
/* forward- or cross-edge */
insn_state[t] = DISCOVERED | e;
} else {
- verbose("insn state internal bug\n");
+ verbose(env, "insn state internal bug\n");
return -EFAULT;
}
return 0;
@@ -3216,7 +3338,7 @@ peek_stack:
mark_explored:
insn_state[t] = EXPLORED;
if (cur_stack-- <= 0) {
- verbose("pop stack internal bug\n");
+ verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
}
@@ -3225,7 +3347,7 @@ mark_explored:
check_state:
for (i = 0; i < insn_cnt; i++) {
if (insn_state[i] != EXPLORED) {
- verbose("unreachable insn %d\n", i);
+ verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
@@ -3340,8 +3462,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
/* Check our ids match any regs they're supposed to */
return check_ids(rold->id, rcur->id, idmap);
+ case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
- if (rcur->type != PTR_TO_PACKET)
+ if (rcur->type != rold->type)
return false;
/* We must have at least as much range as the old ptr
* did, so that any accesses which were safe before are
@@ -3379,6 +3502,57 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
}
+static bool stacksafe(struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur,
+ struct idpair *idmap)
+{
+ int i, spi;
+
+ /* if explored stack has more populated slots than current stack
+ * such stacks are not equivalent
+ */
+ if (old->allocated_stack > cur->allocated_stack)
+ return false;
+
+ /* walk slots of the explored stack and ignore any additional
+ * slots in the current stack, since explored(safe) state
+ * didn't use them
+ */
+ for (i = 0; i < old->allocated_stack; i++) {
+ spi = i / BPF_REG_SIZE;
+
+ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
+ continue;
+ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ /* Ex: old explored (safe) state has STACK_SPILL in
+ * this stack slot, but current has has STACK_MISC ->
+ * this verifier states are not equivalent,
+ * return false to continue verification of this path
+ */
+ return false;
+ if (i % BPF_REG_SIZE)
+ continue;
+ if (old->stack[spi].slot_type[0] != STACK_SPILL)
+ continue;
+ if (!regsafe(&old->stack[spi].spilled_ptr,
+ &cur->stack[spi].spilled_ptr,
+ idmap))
+ /* when explored and current stack slot are both storing
+ * spilled registers, check that stored pointers types
+ * are the same as well.
+ * Ex: explored safe path could have stored
+ * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
+ * but current path has stored:
+ * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
+ * such verifier states are not equivalent.
+ * return false to continue verification of this path
+ */
+ return false;
+ }
+ return true;
+}
+
/* compare two verifier states
*
* all states stored in state_list are known to be valid, since
@@ -3423,37 +3597,8 @@ static bool states_equal(struct bpf_verifier_env *env,
goto out_free;
}
- for (i = 0; i < MAX_BPF_STACK; i++) {
- if (old->stack_slot_type[i] == STACK_INVALID)
- continue;
- if (old->stack_slot_type[i] != cur->stack_slot_type[i])
- /* Ex: old explored (safe) state has STACK_SPILL in
- * this stack slot, but current has has STACK_MISC ->
- * this verifier states are not equivalent,
- * return false to continue verification of this path
- */
- goto out_free;
- if (i % BPF_REG_SIZE)
- continue;
- if (old->stack_slot_type[i] != STACK_SPILL)
- continue;
- if (!regsafe(&old->spilled_regs[i / BPF_REG_SIZE],
- &cur->spilled_regs[i / BPF_REG_SIZE],
- idmap))
- /* when explored and current stack slot are both storing
- * spilled registers, check that stored pointers types
- * are the same as well.
- * Ex: explored safe path could have stored
- * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
- * but current path has stored:
- * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
- * such verifier states are not equivalent.
- * return false to continue verification of this path
- */
- goto out_free;
- else
- continue;
- }
+ if (!stacksafe(old, cur, idmap))
+ goto out_free;
ret = true;
out_free:
kfree(idmap);
@@ -3489,17 +3634,19 @@ static bool do_propagate_liveness(const struct bpf_verifier_state *state,
}
}
/* ... and stack slots */
- for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) {
- if (parent->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL)
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
+ i < parent->allocated_stack / BPF_REG_SIZE; i++) {
+ if (parent->stack[i].slot_type[0] != STACK_SPILL)
continue;
- if (state->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL)
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
- if (parent->spilled_regs[i].live & REG_LIVE_READ)
+ if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
continue;
- if (writes && (state->spilled_regs[i].live & REG_LIVE_WRITTEN))
+ if (writes &&
+ (state->stack[i].spilled_ptr.live & REG_LIVE_WRITTEN))
continue;
- if (state->spilled_regs[i].live & REG_LIVE_READ) {
- parent->spilled_regs[i].live |= REG_LIVE_READ;
+ if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) {
+ parent->stack[i].spilled_ptr.live |= REG_LIVE_READ;
touched = true;
}
}
@@ -3529,7 +3676,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl;
- int i;
+ struct bpf_verifier_state *cur = env->cur_state;
+ int i, err;
sl = env->explored_states[insn_idx];
if (!sl)
@@ -3539,7 +3687,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return 0;
while (sl != STATE_LIST_MARK) {
- if (states_equal(env, &sl->state, &env->cur_state)) {
+ if (states_equal(env, &sl->state, cur)) {
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
@@ -3550,7 +3698,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* they'll be immediately forgotten as we're pruning
* this state and will pop a new one.
*/
- propagate_liveness(&sl->state, &env->cur_state);
+ propagate_liveness(&sl->state, cur);
return 1;
}
sl = sl->next;
@@ -3562,16 +3710,21 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* it will be rejected. Since there are no loops, we won't be
* seeing this 'insn_idx' instruction again on the way to bpf_exit
*/
- new_sl = kmalloc(sizeof(struct bpf_verifier_state_list), GFP_USER);
+ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
/* add new state to the head of linked list */
- memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state));
+ err = copy_verifier_state(&new_sl->state, cur);
+ if (err) {
+ free_verifier_state(&new_sl->state, false);
+ kfree(new_sl);
+ return err;
+ }
new_sl->next = env->explored_states[insn_idx];
env->explored_states[insn_idx] = new_sl;
/* connect new state to parentage chain */
- env->cur_state.parent = &new_sl->state;
+ cur->parent = &new_sl->state;
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
@@ -3579,33 +3732,37 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* explored_states can get read marks.)
*/
for (i = 0; i < BPF_REG_FP; i++)
- env->cur_state.regs[i].live = REG_LIVE_NONE;
- for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++)
- if (env->cur_state.stack_slot_type[i * BPF_REG_SIZE] == STACK_SPILL)
- env->cur_state.spilled_regs[i].live = REG_LIVE_NONE;
+ cur->regs[i].live = REG_LIVE_NONE;
+ for (i = 0; i < cur->allocated_stack / BPF_REG_SIZE; i++)
+ if (cur->stack[i].slot_type[0] == STACK_SPILL)
+ cur->stack[i].spilled_ptr.live = REG_LIVE_NONE;
return 0;
}
static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx)
{
- if (!env->analyzer_ops || !env->analyzer_ops->insn_hook)
- return 0;
+ if (env->dev_ops && env->dev_ops->insn_hook)
+ return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
- return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx);
+ return 0;
}
static int do_check(struct bpf_verifier_env *env)
{
- struct bpf_verifier_state *state = &env->cur_state;
+ struct bpf_verifier_state *state;
struct bpf_insn *insns = env->prog->insnsi;
- struct bpf_reg_state *regs = state->regs;
+ struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
int insn_idx, prev_insn_idx = 0;
int insn_processed = 0;
bool do_print_state = false;
- init_reg_state(regs);
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+ env->cur_state = state;
+ init_reg_state(env, state->regs);
state->parent = NULL;
insn_idx = 0;
for (;;) {
@@ -3614,7 +3771,7 @@ static int do_check(struct bpf_verifier_env *env)
int err;
if (insn_idx >= insn_cnt) {
- verbose("invalid insn idx %d insn_cnt %d\n",
+ verbose(env, "invalid insn idx %d insn_cnt %d\n",
insn_idx, insn_cnt);
return -EFAULT;
}
@@ -3623,7 +3780,8 @@ static int do_check(struct bpf_verifier_env *env)
class = BPF_CLASS(insn->code);
if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
- verbose("BPF program is too large. Processed %d insn\n",
+ verbose(env,
+ "BPF program is too large. Processed %d insn\n",
insn_processed);
return -E2BIG;
}
@@ -3633,12 +3791,12 @@ static int do_check(struct bpf_verifier_env *env)
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
- if (log_level) {
+ if (env->log.level) {
if (do_print_state)
- verbose("\nfrom %d to %d: safe\n",
+ verbose(env, "\nfrom %d to %d: safe\n",
prev_insn_idx, insn_idx);
else
- verbose("%d: safe\n", insn_idx);
+ verbose(env, "%d: safe\n", insn_idx);
}
goto process_bpf_exit;
}
@@ -3646,25 +3804,27 @@ static int do_check(struct bpf_verifier_env *env)
if (need_resched())
cond_resched();
- if (log_level > 1 || (log_level && do_print_state)) {
- if (log_level > 1)
- verbose("%d:", insn_idx);
+ if (env->log.level > 1 || (env->log.level && do_print_state)) {
+ if (env->log.level > 1)
+ verbose(env, "%d:", insn_idx);
else
- verbose("\nfrom %d to %d:",
+ verbose(env, "\nfrom %d to %d:",
prev_insn_idx, insn_idx);
- print_verifier_state(&env->cur_state);
+ print_verifier_state(env, state);
do_print_state = false;
}
- if (log_level) {
- verbose("%d: ", insn_idx);
- print_bpf_insn(env, insn);
+ if (env->log.level) {
+ verbose(env, "%d: ", insn_idx);
+ print_bpf_insn(verbose, env, insn,
+ env->allow_ptr_leaks);
}
err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
if (err)
return err;
+ regs = cur_regs(env);
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
if (err)
@@ -3714,7 +3874,7 @@ static int do_check(struct bpf_verifier_env *env)
* src_reg == stack|map in some other branch.
* Reject it.
*/
- verbose("same insn cannot be used with different pointers\n");
+ verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
@@ -3754,14 +3914,14 @@ static int do_check(struct bpf_verifier_env *env)
} else if (dst_reg_type != *prev_dst_type &&
(dst_reg_type == PTR_TO_CTX ||
*prev_dst_type == PTR_TO_CTX)) {
- verbose("same insn cannot be used with different pointers\n");
+ verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
} else if (class == BPF_ST) {
if (BPF_MODE(insn->code) != BPF_MEM ||
insn->src_reg != BPF_REG_0) {
- verbose("BPF_ST uses reserved fields\n");
+ verbose(env, "BPF_ST uses reserved fields\n");
return -EINVAL;
}
/* check src operand */
@@ -3784,7 +3944,7 @@ static int do_check(struct bpf_verifier_env *env)
insn->off != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0) {
- verbose("BPF_CALL uses reserved fields\n");
+ verbose(env, "BPF_CALL uses reserved fields\n");
return -EINVAL;
}
@@ -3797,7 +3957,7 @@ static int do_check(struct bpf_verifier_env *env)
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0) {
- verbose("BPF_JA uses reserved fields\n");
+ verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
@@ -3809,7 +3969,7 @@ static int do_check(struct bpf_verifier_env *env)
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0) {
- verbose("BPF_EXIT uses reserved fields\n");
+ verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
@@ -3824,13 +3984,18 @@ static int do_check(struct bpf_verifier_env *env)
return err;
if (is_pointer_value(env, BPF_REG_0)) {
- verbose("R0 leaks addr as return value\n");
+ verbose(env, "R0 leaks addr as return value\n");
return -EACCES;
}
+ err = check_return_code(env);
+ if (err)
+ return err;
process_bpf_exit:
- insn_idx = pop_stack(env, &prev_insn_idx);
- if (insn_idx < 0) {
+ err = pop_stack(env, &prev_insn_idx, &insn_idx);
+ if (err < 0) {
+ if (err != -ENOENT)
+ return err;
break;
} else {
do_print_state = true;
@@ -3856,19 +4021,19 @@ process_bpf_exit:
insn_idx++;
} else {
- verbose("invalid BPF_LD mode\n");
+ verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
}
} else {
- verbose("unknown insn class %d\n", class);
+ verbose(env, "unknown insn class %d\n", class);
return -EINVAL;
}
insn_idx++;
}
- verbose("processed %d insns, stack depth %d\n",
- insn_processed, env->prog->aux->stack_depth);
+ verbose(env, "processed %d insns, stack depth %d\n", insn_processed,
+ env->prog->aux->stack_depth);
return 0;
}
@@ -3880,7 +4045,8 @@ static int check_map_prealloc(struct bpf_map *map)
!(map->map_flags & BPF_F_NO_PREALLOC);
}
-static int check_map_prog_compatibility(struct bpf_map *map,
+static int check_map_prog_compatibility(struct bpf_verifier_env *env,
+ struct bpf_map *map,
struct bpf_prog *prog)
{
@@ -3891,12 +4057,12 @@ static int check_map_prog_compatibility(struct bpf_map *map,
*/
if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
if (!check_map_prealloc(map)) {
- verbose("perf_event programs can only use preallocated hash map\n");
+ verbose(env, "perf_event programs can only use preallocated hash map\n");
return -EINVAL;
}
if (map->inner_map_meta &&
!check_map_prealloc(map->inner_map_meta)) {
- verbose("perf_event programs can only use preallocated inner hash map\n");
+ verbose(env, "perf_event programs can only use preallocated inner hash map\n");
return -EINVAL;
}
}
@@ -3919,14 +4085,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
(BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
- verbose("BPF_LDX uses reserved fields\n");
+ verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
if (BPF_CLASS(insn->code) == BPF_STX &&
((BPF_MODE(insn->code) != BPF_MEM &&
BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
- verbose("BPF_STX uses reserved fields\n");
+ verbose(env, "BPF_STX uses reserved fields\n");
return -EINVAL;
}
@@ -3937,7 +4103,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
insn[1].off != 0) {
- verbose("invalid bpf_ld_imm64 insn\n");
+ verbose(env, "invalid bpf_ld_imm64 insn\n");
return -EINVAL;
}
@@ -3946,19 +4112,20 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
goto next_insn;
if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
- verbose("unrecognized bpf_ld_imm64 insn\n");
+ verbose(env,
+ "unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
f = fdget(insn->imm);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
- verbose("fd %d is not pointing to valid bpf_map\n",
+ verbose(env, "fd %d is not pointing to valid bpf_map\n",
insn->imm);
return PTR_ERR(map);
}
- err = check_map_prog_compatibility(map, env->prog);
+ err = check_map_prog_compatibility(env, map, env->prog);
if (err) {
fdput(f);
return err;
@@ -4067,7 +4234,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
*/
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
- const struct bpf_verifier_ops *ops = env->prog->aux->ops;
+ const struct bpf_verifier_ops *ops = env->ops;
int i, cnt, size, ctx_field_size, delta = 0;
const int insn_cnt = env->prog->len;
struct bpf_insn insn_buf[16], *insn;
@@ -4080,7 +4247,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
- verbose("bpf verifier is misconfigured\n");
+ verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
} else if (cnt) {
new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
@@ -4128,7 +4295,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
u8 size_code;
if (type == BPF_WRITE) {
- verbose("bpf verifier narrow ctx access misconfigured\n");
+ verbose(env, "bpf verifier narrow ctx access misconfigured\n");
return -EINVAL;
}
@@ -4147,7 +4314,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
&target_size);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
(ctx_field_size && !target_size)) {
- verbose("bpf verifier is misconfigured\n");
+ verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
@@ -4229,7 +4396,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
- verbose("bpf verifier is misconfigured\n");
+ verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
@@ -4268,12 +4435,13 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn = new_prog->insnsi + i + delta;
}
patch_call_imm:
- fn = prog->aux->ops->get_func_proto(insn->imm);
+ fn = env->ops->get_func_proto(insn->imm);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
if (!fn->func) {
- verbose("kernel subsystem misconfigured func %s#%d\n",
+ verbose(env,
+ "kernel subsystem misconfigured func %s#%d\n",
func_id_name(insn->imm), insn->imm);
return -EFAULT;
}
@@ -4297,6 +4465,7 @@ static void free_states(struct bpf_verifier_env *env)
if (sl)
while (sl != STATE_LIST_MARK) {
sln = sl->next;
+ free_verifier_state(&sl->state, false);
kfree(sl);
sl = sln;
}
@@ -4307,16 +4476,21 @@ static void free_states(struct bpf_verifier_env *env)
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
{
- char __user *log_ubuf = NULL;
struct bpf_verifier_env *env;
+ struct bpf_verifer_log *log;
int ret = -EINVAL;
+ /* no program is valid */
+ if (ARRAY_SIZE(bpf_verifier_ops) == 0)
+ return -EINVAL;
+
/* 'struct bpf_verifier_env' can be global, but since it's not small,
* allocate/free it every time bpf_check() is called
*/
env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
if (!env)
return -ENOMEM;
+ log = &env->log;
env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
(*prog)->len);
@@ -4324,6 +4498,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
if (!env->insn_aux_data)
goto err_free_env;
env->prog = *prog;
+ env->ops = bpf_verifier_ops[env->prog->type];
/* grab the mutex to protect few globals used by verifier */
mutex_lock(&bpf_verifier_lock);
@@ -4332,29 +4507,27 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
/* user requested verbose verifier output
* and supplied buffer to store the verification trace
*/
- log_level = attr->log_level;
- log_ubuf = (char __user *) (unsigned long) attr->log_buf;
- log_size = attr->log_size;
- log_len = 0;
+ log->level = attr->log_level;
+ log->ubuf = (char __user *) (unsigned long) attr->log_buf;
+ log->len_total = attr->log_size;
ret = -EINVAL;
- /* log_* values have to be sane */
- if (log_size < 128 || log_size > UINT_MAX >> 8 ||
- log_level == 0 || log_ubuf == NULL)
- goto err_unlock;
-
- ret = -ENOMEM;
- log_buf = vmalloc(log_size);
- if (!log_buf)
+ /* log attributes have to be sane */
+ if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+ !log->level || !log->ubuf)
goto err_unlock;
- } else {
- log_level = 0;
}
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
+ if (env->prog->aux->offload) {
+ ret = bpf_prog_offload_verifier_prep(env);
+ if (ret)
+ goto err_unlock;
+ }
+
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
goto skip_full_check;
@@ -4373,9 +4546,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
ret = do_check(env);
+ if (env->cur_state) {
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ }
skip_full_check:
- while (pop_stack(env, NULL) >= 0);
+ while (!pop_stack(env, NULL, NULL));
free_states(env);
if (ret == 0)
@@ -4385,17 +4562,11 @@ skip_full_check:
if (ret == 0)
ret = fixup_bpf_calls(env);
- if (log_level && log_len >= log_size - 1) {
- BUG_ON(log_len >= log_size);
- /* verifier log exceeded user supplied buffer */
+ if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
- /* fall through to return what was recorded */
- }
-
- /* copy verifier log back to user space including trailing zero */
- if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
+ if (log->level && !log->ubuf) {
ret = -EFAULT;
- goto free_log_buf;
+ goto err_release_maps;
}
if (ret == 0 && env->used_map_cnt) {
@@ -4406,7 +4577,7 @@ skip_full_check:
if (!env->prog->aux->used_maps) {
ret = -ENOMEM;
- goto free_log_buf;
+ goto err_release_maps;
}
memcpy(env->prog->aux->used_maps, env->used_maps,
@@ -4419,9 +4590,7 @@ skip_full_check:
convert_pseudo_ld_imm64(env);
}
-free_log_buf:
- if (log_level)
- vfree(log_buf);
+err_release_maps:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
* them now. Otherwise free_bpf_prog_info() will release them.
@@ -4435,58 +4604,3 @@ err_free_env:
kfree(env);
return ret;
}
-
-int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
- void *priv)
-{
- struct bpf_verifier_env *env;
- int ret;
-
- env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
- if (!env)
- return -ENOMEM;
-
- env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
- prog->len);
- ret = -ENOMEM;
- if (!env->insn_aux_data)
- goto err_free_env;
- env->prog = prog;
- env->analyzer_ops = ops;
- env->analyzer_priv = priv;
-
- /* grab the mutex to protect few globals used by verifier */
- mutex_lock(&bpf_verifier_lock);
-
- log_level = 0;
-
- env->strict_alignment = false;
- if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- env->strict_alignment = true;
-
- env->explored_states = kcalloc(env->prog->len,
- sizeof(struct bpf_verifier_state_list *),
- GFP_KERNEL);
- ret = -ENOMEM;
- if (!env->explored_states)
- goto skip_full_check;
-
- ret = check_cfg(env);
- if (ret < 0)
- goto skip_full_check;
-
- env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
-
- ret = do_check(env);
-
-skip_full_check:
- while (pop_stack(env, NULL) >= 0);
- free_states(env);
-
- mutex_unlock(&bpf_verifier_lock);
- vfree(env->insn_aux_data);
-err_free_env:
- kfree(env);
- return ret;
-}
-EXPORT_SYMBOL_GPL(bpf_analyzer);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 44857278eb8a..00f5b358aeac 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
if (ret)
goto destroy_root;
+ ret = cgroup_bpf_inherit(root_cgrp);
+ WARN_ON_ONCE(ret);
+
trace_cgroup_setup_root(root);
/*
@@ -4721,6 +4724,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
+ ret = cgroup_bpf_inherit(cgrp);
+ if (ret)
+ goto out_idr_free;
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -4755,13 +4761,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
if (!cgroup_on_dfl(cgrp))
cgrp->subtree_control = cgroup_control(cgrp);
- if (parent)
- cgroup_bpf_inherit(cgrp, parent);
-
cgroup_propagate_control(cgrp);
return cgrp;
+out_idr_free:
+ cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_cancel_ref:
percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
@@ -5744,14 +5749,33 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
#endif /* CONFIG_SOCK_CGROUP_DATA */
#ifdef CONFIG_CGROUP_BPF
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type, bool overridable)
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
{
- struct cgroup *parent = cgroup_parent(cgrp);
int ret;
mutex_lock(&cgroup_mutex);
- ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
+ ret = __cgroup_bpf_query(cgrp, attr, uattr);
mutex_unlock(&cgroup_mutex);
return ret;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c39c05e029a..3939a4674e0a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3601,7 +3601,6 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
goto out;
}
-
/*
* If the event is currently on this CPU, its either a per-task event,
* or local to this CPU. Furthermore it means its ACTIVE (otherwise
@@ -7867,11 +7866,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
struct pt_regs *regs, struct hlist_head *head,
struct task_struct *task)
{
- struct bpf_prog *prog = call->prog;
-
- if (prog) {
+ if (bpf_prog_array_valid(call)) {
*(struct pt_regs **)raw_data = regs;
- if (!trace_call_bpf(prog, raw_data) || hlist_empty(head)) {
+ if (!trace_call_bpf(call, raw_data) || hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
}
@@ -8060,13 +8057,11 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
{
bool is_kprobe, is_tracepoint, is_syscall_tp;
struct bpf_prog *prog;
+ int ret;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return perf_event_set_bpf_handler(event, prog_fd);
- if (event->tp_event->prog)
- return -EEXIST;
-
is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE;
is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT;
is_syscall_tp = is_syscall_trace_event(event->tp_event);
@@ -8094,26 +8089,20 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
return -EACCES;
}
}
- event->tp_event->prog = prog;
- event->tp_event->bpf_prog_owner = event;
- return 0;
+ ret = perf_event_attach_bpf_prog(event, prog);
+ if (ret)
+ bpf_prog_put(prog);
+ return ret;
}
static void perf_event_free_bpf_prog(struct perf_event *event)
{
- struct bpf_prog *prog;
-
- perf_event_free_bpf_handler(event);
-
- if (!event->tp_event)
+ if (event->attr.type != PERF_TYPE_TRACEPOINT) {
+ perf_event_free_bpf_handler(event);
return;
-
- prog = event->tp_event->prog;
- if (prog && event->tp_event->bpf_prog_owner == event) {
- event->tp_event->prog = NULL;
- bpf_prog_put(prog);
}
+ perf_event_detach_bpf_prog(event);
}
#else
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 95888ae6c263..a5580c670866 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -15,9 +15,11 @@
#include <linux/ctype.h>
#include "trace.h"
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+
/**
* trace_call_bpf - invoke BPF program
- * @prog: BPF program
+ * @call: tracepoint event
* @ctx: opaque context pointer
*
* kprobe handlers execute BPF programs via this helper.
@@ -29,7 +31,7 @@
* 1 - store kprobe event into ring buffer
* Other values are reserved and currently alias to 1
*/
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
unsigned int ret;
@@ -49,9 +51,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
goto out;
}
- rcu_read_lock();
- ret = BPF_PROG_RUN(prog, ctx);
- rcu_read_unlock();
+ /*
+ * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
+ * to all call sites, we did a bpf_prog_array_valid() there to check
+ * whether call->prog_array is empty or not, which is
+ * a heurisitc to speed up execution.
+ *
+ * If bpf_prog_array_valid() fetched prog_array was
+ * non-NULL, we go into trace_call_bpf() and do the actual
+ * proper rcu_dereference() under RCU lock.
+ * If it turns out that prog_array is NULL then, we bail out.
+ * For the opposite, if the bpf_prog_array_valid() fetched pointer
+ * was NULL, you'll skip the prog_array with the risk of missing
+ * out of events when it was updated in between this and the
+ * rcu_dereference() which is accepted risk.
+ */
+ ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
out:
__this_cpu_dec(bpf_prog_active);
@@ -63,12 +78,16 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
{
- int ret;
+ int ret = 0;
+
+ if (unlikely(size == 0))
+ goto out;
ret = probe_kernel_read(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
+ out:
return ret;
}
@@ -77,7 +96,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
- .arg2_type = ARG_CONST_SIZE,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_ANYTHING,
};
@@ -255,14 +274,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
return &bpf_trace_printk_proto;
}
-BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+static __always_inline int
+get_map_perf_counter(struct bpf_map *map, u64 flags,
+ u64 *value, u64 *enabled, u64 *running)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
unsigned int cpu = smp_processor_id();
u64 index = flags & BPF_F_INDEX_MASK;
struct bpf_event_entry *ee;
- u64 value = 0;
- int err;
if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
return -EINVAL;
@@ -275,7 +294,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
if (!ee)
return -ENOENT;
- err = perf_event_read_local(ee->event, &value, NULL, NULL);
+ return perf_event_read_local(ee->event, value, enabled, running);
+}
+
+BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+{
+ u64 value = 0;
+ int err;
+
+ err = get_map_perf_counter(map, flags, &value, NULL, NULL);
/*
* this api is ugly since we miss [-22..-2] range of valid
* counter values, but that's uapi
@@ -293,6 +320,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
.arg2_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
+ struct bpf_perf_event_value *, buf, u32, size)
+{
+ int err = -EINVAL;
+
+ if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+ goto clear;
+ err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
+ &buf->running);
+ if (unlikely(err))
+ goto clear;
+ return 0;
+clear:
+ memset(buf, 0, size);
+ return err;
+}
+
+static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
+ .func = bpf_perf_event_read_value,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+};
+
static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
static __always_inline u64
@@ -499,6 +553,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_perf_event_output_proto;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto;
+ case BPF_FUNC_perf_event_read_value:
+ return &bpf_perf_event_read_value_proto;
default:
return tracing_func_proto(func_id);
}
@@ -524,11 +580,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
return true;
}
-const struct bpf_verifier_ops kprobe_prog_ops = {
+const struct bpf_verifier_ops kprobe_verifier_ops = {
.get_func_proto = kprobe_prog_func_proto,
.is_valid_access = kprobe_prog_is_valid_access,
};
+const struct bpf_prog_ops kprobe_prog_ops = {
+};
+
BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
u64, flags, void *, data, u64, size)
{
@@ -576,6 +635,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+ struct bpf_perf_event_value *, buf, u32, size)
+{
+ int err = -EINVAL;
+
+ if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+ goto clear;
+ err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+ &buf->running);
+ if (unlikely(err))
+ goto clear;
+ return 0;
+clear:
+ memset(buf, 0, size);
+ return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
+ .func = bpf_perf_prog_read_value_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
@@ -583,6 +668,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
return &bpf_perf_event_output_proto_tp;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_tp;
+ case BPF_FUNC_perf_prog_read_value:
+ return &bpf_perf_prog_read_value_proto_tp;
default:
return tracing_func_proto(func_id);
}
@@ -602,11 +689,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
return true;
}
-const struct bpf_verifier_ops tracepoint_prog_ops = {
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
.get_func_proto = tp_prog_func_proto,
.is_valid_access = tp_prog_is_valid_access,
};
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
@@ -662,8 +752,67 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
}
-const struct bpf_verifier_ops perf_event_prog_ops = {
+const struct bpf_verifier_ops perf_event_verifier_ops = {
.get_func_proto = tp_prog_func_proto,
.is_valid_access = pe_prog_is_valid_access,
.convert_ctx_access = pe_prog_convert_ctx_access,
};
+
+const struct bpf_prog_ops perf_event_prog_ops = {
+};
+
+static DEFINE_MUTEX(bpf_event_mutex);
+
+int perf_event_attach_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ int ret = -EEXIST;
+
+ mutex_lock(&bpf_event_mutex);
+
+ if (event->prog)
+ goto unlock;
+
+ old_array = event->tp_event->prog_array;
+ ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+ if (ret < 0)
+ goto unlock;
+
+ /* set the new array to event->tp_event and set event->prog */
+ event->prog = prog;
+ rcu_assign_pointer(event->tp_event->prog_array, new_array);
+ bpf_prog_array_free(old_array);
+
+unlock:
+ mutex_unlock(&bpf_event_mutex);
+ return ret;
+}
+
+void perf_event_detach_bpf_prog(struct perf_event *event)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ int ret;
+
+ mutex_lock(&bpf_event_mutex);
+
+ if (!event->prog)
+ goto unlock;
+
+ old_array = event->tp_event->prog_array;
+ ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+ if (ret < 0) {
+ bpf_prog_array_delete_safe(old_array, event->prog);
+ } else {
+ rcu_assign_pointer(event->tp_event->prog_array, new_array);
+ bpf_prog_array_free(old_array);
+ }
+
+ bpf_prog_put(event->prog);
+ event->prog = NULL;
+
+unlock:
+ mutex_unlock(&bpf_event_mutex);
+}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8a907e12b6b9..abf92e478cfb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1174,13 +1174,12 @@ static void
kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct trace_event_call *call = &tk->tp.call;
- struct bpf_prog *prog = call->prog;
struct kprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
head = this_cpu_ptr(call->perf_events);
@@ -1210,13 +1209,12 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_event_call *call = &tk->tp.call;
- struct bpf_prog *prog = call->prog;
struct kretprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
head = this_cpu_ptr(call->perf_events);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a2a642f2c64f..19bcaaac884b 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -560,9 +560,10 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
static int sys_perf_refcount_enter;
static int sys_perf_refcount_exit;
-static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
- struct syscall_metadata *sys_data,
- struct syscall_trace_enter *rec) {
+static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *regs,
+ struct syscall_metadata *sys_data,
+ struct syscall_trace_enter *rec)
+{
struct syscall_tp_t {
unsigned long long regs;
unsigned long syscall_nr;
@@ -574,7 +575,7 @@ static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
param.syscall_nr = rec->nr;
for (i = 0; i < sys_data->nb_args; i++)
param.args[i] = rec->args[i];
- return trace_call_bpf(prog, &param);
+ return trace_call_bpf(call, &param);
}
static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
@@ -582,7 +583,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
struct hlist_head *head;
- struct bpf_prog *prog;
+ bool valid_prog_array;
int syscall_nr;
int rctx;
int size;
@@ -597,9 +598,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
if (!sys_data)
return;
- prog = READ_ONCE(sys_data->enter_event->prog);
head = this_cpu_ptr(sys_data->enter_event->perf_events);
- if (!prog && hlist_empty(head))
+ valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
+ if (!valid_prog_array && hlist_empty(head))
return;
/* get the size after alignment with the u32 buffer size field */
@@ -615,7 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+ if ((valid_prog_array &&
+ !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
@@ -660,8 +662,9 @@ static void perf_sysenter_disable(struct trace_event_call *call)
mutex_unlock(&syscall_trace_lock);
}
-static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
- struct syscall_trace_exit *rec) {
+static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *regs,
+ struct syscall_trace_exit *rec)
+{
struct syscall_tp_t {
unsigned long long regs;
unsigned long syscall_nr;
@@ -671,7 +674,7 @@ static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
param.ret = rec->ret;
- return trace_call_bpf(prog, &param);
+ return trace_call_bpf(call, &param);
}
static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
@@ -679,7 +682,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
struct hlist_head *head;
- struct bpf_prog *prog;
+ bool valid_prog_array;
int syscall_nr;
int rctx;
int size;
@@ -694,9 +697,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
if (!sys_data)
return;
- prog = READ_ONCE(sys_data->exit_event->prog);
head = this_cpu_ptr(sys_data->exit_event->perf_events);
- if (!prog && hlist_empty(head))
+ valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
+ if (!valid_prog_array && hlist_empty(head))
return;
/* We can probably do that at build time */
@@ -710,7 +713,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+ if ((valid_prog_array &&
+ !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 4525e0271a53..153c0e411461 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1113,13 +1113,12 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
{
struct trace_event_call *call = &tu->tp.call;
struct uprobe_trace_entry_head *entry;
- struct bpf_prog *prog = call->prog;
struct hlist_head *head;
void *data;
int size, esize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));