bpf: Support replacing cgroup-bpf program in MULTI mode

The common use-case in production is to have multiple cgroup-bpf
programs per attach type that cover multiple use-cases. Such programs
are attached with BPF_F_ALLOW_MULTI and can be maintained by different
people.

Order of programs usually matters, for example imagine two egress
programs: the first one drops packets and the second one counts packets.
If they're swapped the result of counting program will be different.

It brings operational challenges with updating cgroup-bpf program(s)
attached with BPF_F_ALLOW_MULTI since there is no way to replace a
program:

* One way to update is to detach all programs first and then attach the
  new version(s) again in the right order. This introduces an
  interruption in the work a program is doing and may not be acceptable
  (e.g. if it's egress firewall);

* Another way is attach the new version of a program first and only then
  detach the old version. This introduces the time interval when two
  versions of same program are working, what may not be acceptable if a
  program is not idempotent. It also imposes additional burden on
  program developers to make sure that two versions of their program can
  co-exist.

Solve the problem by introducing a "replace" mode in BPF_PROG_ATTACH
command for cgroup-bpf programs being attached with BPF_F_ALLOW_MULTI
flag. This mode is enabled by newly introduced BPF_F_REPLACE attach flag
and bpf_attr.replace_bpf_fd attribute to pass fd of the old program to
replace

That way user can replace any program among those attached with
BPF_F_ALLOW_MULTI flag without the problems described above.

Details of the new API:

* If BPF_F_REPLACE is set but replace_bpf_fd doesn't have valid
  descriptor of BPF program, BPF_PROG_ATTACH will return corresponding
  error (EINVAL or EBADF).

* If replace_bpf_fd has valid descriptor of BPF program but such a
  program is not attached to specified cgroup, BPF_PROG_ATTACH will
  return ENOENT.

BPF_F_REPLACE is introduced to make the user intent clear, since
replace_bpf_fd alone can't be used for this (its default value, 0, is a
valid fd). BPF_F_REPLACE also makes it possible to extend the API in the
future (e.g. add BPF_F_BEFORE and BPF_F_AFTER if needed).

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Narkyiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/30cd850044a0057bdfcaaf154b7d2f39850ba813.1576741281.git.rdna@fb.com

3 files changed, 31 insertions, 8 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 283efe3ce052..45346c79613a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -282,14 +282,17 @@ cleanup:
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to attach
+ * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
  * @type: Type of attach operation
  * @flags: Option flags
  *
  * Must be called with cgroup_mutex held.
  */
 int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			struct bpf_prog *replace_prog,
 			enum bpf_attach_type type, u32 flags)
 {
+	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
@@ -298,14 +301,15 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	enum bpf_cgroup_storage_type stype;
 	int err;
 
-	if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+	if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) ||
+	    ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
 		/* invalid combination */
 		return -EINVAL;
 
 	if (!hierarchy_allows_attach(cgrp, type))
 		return -EPERM;
 
-	if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+	if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags)
 		/* Disallow attaching non-overridable on top
 		 * of existing overridable in this cgroup.
 		 * Disallow attaching multi-prog if overridable or none
@@ -320,7 +324,12 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 			if (pl->prog == prog)
 				/* disallow attaching the same prog twice */
 				return -EINVAL;
+			if (pl->prog == replace_prog)
+				replace_pl = pl;
 		}
+		if ((flags & BPF_F_REPLACE) && !replace_pl)
+			/* prog to replace not found for cgroup */
+			return -ENOENT;
 	} else if (!list_empty(progs)) {
 		replace_pl = list_first_entry(progs, typeof(*pl), node);
 	}
@@ -356,7 +365,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	for_each_cgroup_storage_type(stype)
 		pl->storage[stype] = storage[stype];
 
-	cgrp->bpf.flags[type] = flags;
+	cgrp->bpf.flags[type] = saved_flags;
 
 	err = update_effective_progs(cgrp, type);
 	if (err)
@@ -522,6 +531,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog)
 {
+	struct bpf_prog *replace_prog = NULL;
 	struct cgroup *cgrp;
 	int ret;
 
@@ -529,8 +539,20 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 	if (IS_ERR(cgrp))
 		return PTR_ERR(cgrp);
 
-	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+	if ((attr->attach_flags & BPF_F_ALLOW_MULTI) &&
+	    (attr->attach_flags & BPF_F_REPLACE)) {
+		replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype);
+		if (IS_ERR(replace_prog)) {
+			cgroup_put(cgrp);
+			return PTR_ERR(replace_prog);
+		}
+	}
+
+	ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type,
 				attr->attach_flags);
+
+	if (replace_prog)
+		bpf_prog_put(replace_prog);
 	cgroup_put(cgrp);
 	return ret;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b08c362f4e02..81ee8595dfee 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2073,10 +2073,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	}
 }
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
+#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
 
 #define BPF_F_ATTACH_MASK \
-	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 735af8f15f95..725365df066d 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6288,12 +6288,13 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 
 #ifdef CONFIG_CGROUP_BPF
 int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, u32 flags)
+		      struct bpf_prog *replace_prog, enum bpf_attach_type type,
+		      u32 flags)
 {
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }