linux/kernel/bpf/dispatcher.c
Mike Rapoport (Microsoft) 810a273919
bpf: dispatcher: Allocate bpf_dispatcher->rw_image with vzalloc()
bpf_dispatcher->rw_image is a temporary writable buffer that
arch_prepare_bpf_dispatcher() fills and then copies into
bpf_dispatcher->image using bpf_arch_text_copy().

The rel32 offsets emitted by emit_bpf_dispatcher() are calculated against
->image, so ->rw_image does not need to live in the module address range.

Allocate ->rw_image with vzalloc() to avoid permissions dance when
EXECMEM_BPF will be backed by ROX caches.

Using vzalloc() rather than vmalloc() ensures that the memory that
bpf_dispatcher_update() unconditionally copies into the executable buffer
is zeroed, which is not ideal but still better than random memory returned
by the existing bpf_jit_alloc_exec() or plain vmalloc().

Switching from bpf_jit_alloc_exec() to vzalloc() also saves a bit of
space in the more scarce module address space.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/bpf/20260716-execmem-x86-rox-bpf-v0-v3-1-4e76158c01c5@kernel.org
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
2026-07-22 17:26:39 +02:00

175 lines
4.3 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2019 Intel Corporation. */
#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
* indirect call, which is expensive when retpolines are enabled. A
* dispatch client registers a BPF program into the dispatcher, and if
* there is available room in the dispatcher a direct call to the BPF
* program will be generated. All calls to the BPF programs called via
* the dispatcher will then be a direct call, instead of an
* indirect. The dispatcher hijacks a trampoline function it via the
* __fentry__ of the trampoline. The trampoline function has the
* following signature:
*
* unsigned int trampoline(const void *ctx, const struct bpf_insn *insnsi,
* unsigned int (*bpf_func)(const void *,
* const struct bpf_insn *));
*/
static struct bpf_dispatcher_prog *bpf_dispatcher_find_prog(
struct bpf_dispatcher *d, struct bpf_prog *prog)
{
int i;
for (i = 0; i < BPF_DISPATCHER_MAX; i++) {
if (prog == d->progs[i].prog)
return &d->progs[i];
}
return NULL;
}
static struct bpf_dispatcher_prog *bpf_dispatcher_find_free(
struct bpf_dispatcher *d)
{
return bpf_dispatcher_find_prog(d, NULL);
}
static bool bpf_dispatcher_add_prog(struct bpf_dispatcher *d,
struct bpf_prog *prog)
{
struct bpf_dispatcher_prog *entry;
if (!prog)
return false;
entry = bpf_dispatcher_find_prog(d, prog);
if (entry) {
refcount_inc(&entry->users);
return false;
}
entry = bpf_dispatcher_find_free(d);
if (!entry)
return false;
bpf_prog_inc(prog);
entry->prog = prog;
refcount_set(&entry->users, 1);
d->num_progs++;
return true;
}
static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d,
struct bpf_prog *prog)
{
struct bpf_dispatcher_prog *entry;
if (!prog)
return false;
entry = bpf_dispatcher_find_prog(d, prog);
if (!entry)
return false;
if (refcount_dec_and_test(&entry->users)) {
entry->prog = NULL;
bpf_prog_put(prog);
d->num_progs--;
return true;
}
return false;
}
int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs)
{
return -ENOTSUPP;
}
static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
{
s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];
int i;
for (i = 0; i < BPF_DISPATCHER_MAX; i++) {
if (d->progs[i].prog)
*ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func;
}
return arch_prepare_bpf_dispatcher(image, buf, &ips[0], d->num_progs);
}
static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
{
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;
if (new) {
/* Prepare the dispatcher in d->rw_image. Then use
* bpf_arch_text_copy to update d->image, which is RO+X.
*/
if (bpf_dispatcher_prepare(d, new, tmp))
return;
if (IS_ERR(bpf_arch_text_copy(new, tmp, PAGE_SIZE / 2)))
return;
}
__BPF_DISPATCHER_UPDATE(d, new ?: (void *)&bpf_dispatcher_nop_func);
/* Make sure all the callers executing the previous/old half of the
* image leave it, so following update call can modify it safely.
*/
synchronize_rcu();
if (new)
d->image_off = noff;
}
void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
struct bpf_prog *to)
{
bool changed = false;
int prev_num_progs;
if (from == to)
return;
mutex_lock(&d->mutex);
if (!d->image) {
d->image = bpf_prog_pack_alloc(PAGE_SIZE, bpf_jit_fill_hole_with_zero, false);
if (!d->image)
goto out;
/* d->rw_image doesn't need to be in module memory range, so we
* can use vzalloc.
*/
d->rw_image = vzalloc(PAGE_SIZE);
if (!d->rw_image) {
bpf_prog_pack_free(d->image, PAGE_SIZE);
d->image = NULL;
goto out;
}
bpf_image_ksym_init(d->image, PAGE_SIZE, &d->ksym);
bpf_image_ksym_add(&d->ksym);
}
prev_num_progs = d->num_progs;
changed |= bpf_dispatcher_remove_prog(d, from);
changed |= bpf_dispatcher_add_prog(d, to);
if (!changed)
goto out;
bpf_dispatcher_update(d, prev_num_progs);
out:
mutex_unlock(&d->mutex);
}