[PATCH AUTOSEL 6.0 13/44] bpf: Convert BPF_DISPATCHER to use static_call() (not ftrace)

From: Sasha Levin
Date: Wed Nov 23 2022 - 07:42:53 EST


From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

[ Upstream commit c86df29d11dfba27c0a1f5039cd6fe387fbf4239 ]

The dispatcher function is currently abusing the ftrace __fentry__
call location for its own purposes -- this obviously gives trouble
when the dispatcher and ftrace are both in use.

A previous solution tried using __attribute__((patchable_function_entry()))
which works, except it is GCC-8+ only, breaking the build on the
earlier still supported compilers. Instead use static_call() -- which
has its own annotations and does not conflict with ftrace -- to
rewrite the dispatch function.

By using: return static_call()(ctx, insni, bpf_func) you get a perfect
forwarding tail call as function body (iow a single jmp instruction).
By having the default static_call() target be bpf_dispatcher_nop_func()
it retains the default behaviour (an indirect call to the argument
function). Only once a dispatcher program is attached is the target
rewritten to directly call the JIT'ed image.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Tested-by: Björn Töpel <bjorn@xxxxxxxxxx>
Tested-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Acked-by: Björn Töpel <bjorn@xxxxxxxxxx>
Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/Y1/oBlK0yFk5c/Im@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Link: https://lore.kernel.org/bpf/20221103120647.796772565@xxxxxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
include/linux/bpf.h | 39 ++++++++++++++++++++++++++++++++++++++-
kernel/bpf/dispatcher.c | 22 ++++++++--------------
2 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 80fc8a88c610..0466aa9cd46c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -27,6 +27,7 @@
#include <linux/bpfptr.h>
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
+#include <linux/static_call.h>

struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -894,6 +895,10 @@ struct bpf_dispatcher {
void *rw_image;
u32 image_off;
struct bpf_ksym ksym;
+#ifdef CONFIG_HAVE_STATIC_CALL
+ struct static_call_key *sc_key;
+ void *sc_tramp;
+#endif
};

static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
@@ -911,6 +916,34 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
void bpf_trampoline_put(struct bpf_trampoline *tr);
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
+
+/*
+ * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
+ * indirection with a direct call to the bpf program. If the architecture does
+ * not have STATIC_CALL, avoid a double-indirection.
+ */
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+#define __BPF_DISPATCHER_SC_INIT(_name) \
+ .sc_key = &STATIC_CALL_KEY(_name), \
+ .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name),
+
+#define __BPF_DISPATCHER_SC(name) \
+ DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func)
+
+#define __BPF_DISPATCHER_CALL(name) \
+ static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func)
+
+#define __BPF_DISPATCHER_UPDATE(_d, _new) \
+ __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new))
+
+#else
+#define __BPF_DISPATCHER_SC_INIT(name)
+#define __BPF_DISPATCHER_SC(name)
+#define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi)
+#define __BPF_DISPATCHER_UPDATE(_d, _new)
+#endif
+
#define BPF_DISPATCHER_INIT(_name) { \
.mutex = __MUTEX_INITIALIZER(_name.mutex), \
.func = &_name##_func, \
@@ -922,25 +955,29 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
.name = #_name, \
.lnode = LIST_HEAD_INIT(_name.ksym.lnode), \
}, \
+ __BPF_DISPATCHER_SC_INIT(_name##_call) \
}

#define DEFINE_BPF_DISPATCHER(name) \
+ __BPF_DISPATCHER_SC(name); \
noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
bpf_func_t bpf_func) \
{ \
- return bpf_func(ctx, insnsi); \
+ return __BPF_DISPATCHER_CALL(name); \
} \
EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \
struct bpf_dispatcher bpf_dispatcher_##name = \
BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
+
#define DECLARE_BPF_DISPATCHER(name) \
unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
bpf_func_t bpf_func); \
extern struct bpf_dispatcher bpf_dispatcher_##name;
+
#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa64b80b8bca..7dfb8d0d5202 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -4,6 +4,7 @@
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/static_call.h>

/* The BPF dispatcher is a multiway branch code generator. The
* dispatcher is a mechanism to avoid the performance penalty of an
@@ -104,17 +105,11 @@ static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *b

static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
{
- void *old, *new, *tmp;
- u32 noff;
- int err;
-
- if (!prev_num_progs) {
- old = NULL;
- noff = 0;
- } else {
- old = d->image + d->image_off;
+ void *new, *tmp;
+ u32 noff = 0;
+
+ if (prev_num_progs)
noff = d->image_off ^ (PAGE_SIZE / 2);
- }

new = d->num_progs ? d->image + noff : NULL;
tmp = d->num_progs ? d->rw_image + noff : NULL;
@@ -128,11 +123,10 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
return;
}

- err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new);
- if (err || !new)
- return;
+ __BPF_DISPATCHER_UPDATE(d, new ?: &bpf_dispatcher_nop_func);

- d->image_off = noff;
+ if (new)
+ d->image_off = noff;
}

void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
--
2.35.1