bpf: per-cgroup lsm flavor

Allow attaching to lsm hooks in the cgroup context.

Attaching to per-cgroup LSM works exactly like attaching
to other per-cgroup hooks. New BPF_LSM_CGROUP is added
to trigger new mode; the actual lsm hook we attach to is
signaled via existing attach_btf_id.

For the hooks that have 'struct socket' or 'struct sock' as its first
argument, we use the cgroup associated with that socket. For the rest,
we use 'current' cgroup (this is all on default hierarchy == v2 only).
Note that for some hooks that work on 'struct sock' we still
take the cgroup from 'current' because some of them work on the socket
that hasn't been properly initialized yet.

Behind the scenes, we allocate a shim program that is attached
to the trampoline and runs cgroup effective BPF programs array.
This shim has some rudimentary ref counting and can be shared
between several programs attaching to the same lsm hook from
different cgroups.

Note that this patch bloats cgroup size because we add 211
cgroup_bpf_attach_type(s) for simplicity sake. This will be
addressed in the subsequent patch.

Also note that we only add non-sleepable flavor for now. To enable
sleepable use-cases, bpf_prog_run_array_cg has to grab trace rcu,
shim programs have to be freed via trace rcu, cgroup_bpf.effective
should be also trace-rcu-managed + maybe some other changes that
I'm not aware of.

Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20220628174314.1216643-4-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 198 insertions, 0 deletions

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5466e15be61f..d7c251d7fbcd 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -11,6 +11,8 @@
 #include <linux/rcupdate_wait.h>
 #include <linux/module.h>
 #include <linux/static_call.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf_lsm.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -496,6 +498,177 @@ int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampolin
 	return err;
 }
 
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+static void bpf_shim_tramp_link_release(struct bpf_link *link)
+{
+	struct bpf_shim_tramp_link *shim_link =
+		container_of(link, struct bpf_shim_tramp_link, link.link);
+
+	/* paired with 'shim_link->trampoline = tr' in bpf_trampoline_link_cgroup_shim */
+	if (!shim_link->trampoline)
+		return;
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline));
+	bpf_trampoline_put(shim_link->trampoline);
+}
+
+static void bpf_shim_tramp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_shim_tramp_link *shim_link =
+		container_of(link, struct bpf_shim_tramp_link, link.link);
+
+	kfree(shim_link);
+}
+
+static const struct bpf_link_ops bpf_shim_tramp_link_lops = {
+	.release = bpf_shim_tramp_link_release,
+	.dealloc = bpf_shim_tramp_link_dealloc,
+};
+
+static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog,
+						     bpf_func_t bpf_func,
+						     int cgroup_atype)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_prog *p;
+
+	shim_link = kzalloc(sizeof(*shim_link), GFP_USER);
+	if (!shim_link)
+		return NULL;
+
+	p = bpf_prog_alloc(1, 0);
+	if (!p) {
+		kfree(shim_link);
+		return NULL;
+	}
+
+	p->jited = false;
+	p->bpf_func = bpf_func;
+
+	p->aux->cgroup_atype = cgroup_atype;
+	p->aux->attach_func_proto = prog->aux->attach_func_proto;
+	p->aux->attach_btf_id = prog->aux->attach_btf_id;
+	p->aux->attach_btf = prog->aux->attach_btf;
+	btf_get(p->aux->attach_btf);
+	p->type = BPF_PROG_TYPE_LSM;
+	p->expected_attach_type = BPF_LSM_MAC;
+	bpf_prog_inc(p);
+	bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
+		      &bpf_shim_tramp_link_lops, p);
+
+	return shim_link;
+}
+
+static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
+						    bpf_func_t bpf_func)
+{
+	struct bpf_tramp_link *link;
+	int kind;
+
+	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
+		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
+			struct bpf_prog *p = link->link.prog;
+
+			if (p->bpf_func == bpf_func)
+				return container_of(link, struct bpf_shim_tramp_link, link);
+		}
+	}
+
+	return NULL;
+}
+
+int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+				    int cgroup_atype)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_attach_target_info tgt_info = {};
+	struct bpf_trampoline *tr;
+	bpf_func_t bpf_func;
+	u64 key;
+	int err;
+
+	err = bpf_check_attach_target(NULL, prog, NULL,
+				      prog->aux->attach_btf_id,
+				      &tgt_info);
+	if (err)
+		return err;
+
+	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
+					 prog->aux->attach_btf_id);
+
+	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
+	tr = bpf_trampoline_get(key, &tgt_info);
+	if (!tr)
+		return  -ENOMEM;
+
+	mutex_lock(&tr->mutex);
+
+	shim_link = cgroup_shim_find(tr, bpf_func);
+	if (shim_link) {
+		/* Reusing existing shim attached by the other program. */
+		bpf_link_inc(&shim_link->link.link);
+
+		mutex_unlock(&tr->mutex);
+		bpf_trampoline_put(tr); /* bpf_trampoline_get above */
+		return 0;
+	}
+
+	/* Allocate and install new shim. */
+
+	shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype);
+	if (!shim_link) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	err = __bpf_trampoline_link_prog(&shim_link->link, tr);
+	if (err)
+		goto err;
+
+	shim_link->trampoline = tr;
+	/* note, we're still holding tr refcnt from above */
+
+	mutex_unlock(&tr->mutex);
+
+	return 0;
+err:
+	mutex_unlock(&tr->mutex);
+
+	if (shim_link)
+		bpf_link_put(&shim_link->link.link);
+
+	/* have to release tr while _not_ holding its mutex */
+	bpf_trampoline_put(tr); /* bpf_trampoline_get above */
+
+	return err;
+}
+
+void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_trampoline *tr;
+	bpf_func_t bpf_func;
+	u64 key;
+
+	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
+					 prog->aux->attach_btf_id);
+
+	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
+	tr = bpf_trampoline_lookup(key);
+	if (WARN_ON_ONCE(!tr))
+		return;
+
+	mutex_lock(&tr->mutex);
+	shim_link = cgroup_shim_find(tr, bpf_func);
+	mutex_unlock(&tr->mutex);
+
+	if (shim_link)
+		bpf_link_put(&shim_link->link.link);
+
+	bpf_trampoline_put(tr); /* bpf_trampoline_lookup above */
+}
+#endif
+
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info)
 {
@@ -628,6 +801,31 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_
 	rcu_read_unlock();
 }
 
+u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
+					struct bpf_tramp_run_ctx *run_ctx)
+	__acquires(RCU)
+{
+	/* Runtime stats are exported via actual BPF_LSM_CGROUP
+	 * programs, not the shims.
+	 */
+	rcu_read_lock();
+	migrate_disable();
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
+	return NO_START_TIME;
+}
+
+void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
+					struct bpf_tramp_run_ctx *run_ctx)
+	__releases(RCU)
+{
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
+	migrate_enable();
+	rcu_read_unlock();
+}
+
 u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 {
 	rcu_read_lock_trace();