Merge branch 'x86-cfi-bpf-fix-cfi-vs-ebpf'

Peter Zijlstra says:

====================
x86/cfi,bpf: Fix CFI vs eBPF

Hi!

What started with the simple observation that bpf_dispatcher_*_func() was
broken for calling CFI functions with a __nocfi calling context for FineIBT
ended up with a complete BPF wide CFI fixup.

With these changes on the BPF selftest suite passes without crashing -- there's
still a few failures, but Alexei has graciously offered to look into those.

(Alexei, I have presumed your SoB on the very last patch, please update
as you see fit)

Changes since v2 are numerous but include:
 - cfi_get_offset() -- as a means to communicate the offset (ast)
 - 5 new patches fixing various BPF internals to be CFI clean

Note: it *might* be possible to merge the
bpf_bpf_tcp_ca.c:unsupported_ops[] thing into the CFI stubs, as is
get_info will have a NULL stub, unlike the others.
---
 arch/riscv/include/asm/cfi.h   |   3 +-
 arch/riscv/kernel/cfi.c        |   2 +-
 arch/x86/include/asm/cfi.h     | 126 +++++++++++++++++++++++++++++++++++++-
 arch/x86/kernel/alternative.c  |  87 +++++++++++++++++++++++---
 arch/x86/kernel/cfi.c          |   4 +-
 arch/x86/net/bpf_jit_comp.c    | 134 +++++++++++++++++++++++++++++++++++------
 include/asm-generic/Kbuild     |   1 +
 include/linux/bpf.h            |  27 ++++++++-
 include/linux/cfi.h            |  12 ++++
 kernel/bpf/bpf_struct_ops.c    |  16 ++---
 kernel/bpf/core.c              |  25 ++++++++
 kernel/bpf/cpumask.c           |   8 ++-
 kernel/bpf/helpers.c           |  18 +++++-
 net/bpf/bpf_dummy_struct_ops.c |  31 +++++++++-
 net/bpf/test_run.c             |  15 ++++-
 net/ipv4/bpf_tcp_ca.c          |  69 +++++++++++++++++++++
 16 files changed, 528 insertions(+), 50 deletions(-)
====================

Link: https://lore.kernel.org/r/20231215091216.135791411@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 55 insertions, 12 deletions

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 4d53c53fc5aa..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,17 +352,16 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
-				      void *image, void *image_end)
+				      void *stub_func, void *image, void *image_end)
 {
-	u32 flags;
+	u32 flags = BPF_TRAMP_F_INDIRECT;
 	int size;
 
 	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
 	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
-	/* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
-	 * and it must be used alone.
-	 */
-	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+	if (model->ret_size > 0)
+		flags |= BPF_TRAMP_F_RET_FENTRY_RET;
 
 	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
 	if (size < 0)
@@ -370,7 +369,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 	if (size > (unsigned long)image_end - (unsigned long)image)
 		return -E2BIG;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tlinks, NULL);
+					   model, flags, tlinks, stub_func);
 }
 
 static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -504,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
+							*(void **)(st_ops->cfi_stubs + moff),
 							image, image_end);
 		if (err < 0)
 			goto reset_unlock;
 
-		*(void **)(kdata + moff) = image;
+		*(void **)(kdata + moff) = image + cfi_get_offset();
 		image += err;
 
 		/* put prog_id to udata */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c34513d645c4..5aa6863ac33b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 #endif
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+#ifdef CONFIG_FINEIBT
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode);
+#endif
 	mutex_init(&fp->aux->used_maps_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
@@ -683,6 +686,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 	fp->aux->ksym.prog = true;
 
 	bpf_ksym_add(&fp->aux->ksym);
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * When FineIBT, code in the __cfi_foo() symbols can get executed
+	 * and hence unwinder needs help.
+	 */
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+
+	snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN,
+		 "__cfi_%s", fp->aux->ksym.name);
+
+	fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16;
+	fp->aux->ksym_prefix.end   = (unsigned long) fp->bpf_func;
+
+	bpf_ksym_add(&fp->aux->ksym_prefix);
+#endif
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -691,6 +711,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 		return;
 
 	bpf_ksym_del(&fp->aux->ksym);
+#ifdef CONFIG_FINEIBT
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+	bpf_ksym_del(&fp->aux->ksym_prefix);
+#endif
 }
 
 static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 7499b7d8c06f..2e73533a3811 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
 	migrate_enable();
 }
 
+__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask)
+{
+	bpf_cpumask_release(cpumask);
+}
+CFI_NOSEAL(bpf_cpumask_release_dtor);
+
 /**
  * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask.
  * @cpumask: The cpumask being queried.
@@ -453,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = {
 
 BTF_ID_LIST(cpumask_dtor_ids)
 BTF_ID(struct, bpf_cpumask)
-BTF_ID(func, bpf_cpumask_release)
+BTF_ID(func, bpf_cpumask_release_dtor)
 
 static int __init cpumask_kfunc_init(void)
 {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b0b485126a76..07fd4b5704f3 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2150,6 +2150,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p)
 	put_task_struct_rcu_user(p);
 }
 
+__bpf_kfunc void bpf_task_release_dtor(void *p)
+{
+	put_task_struct_rcu_user(p);
+}
+CFI_NOSEAL(bpf_task_release_dtor);
+
 #ifdef CONFIG_CGROUPS
 /**
  * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by
@@ -2174,6 +2180,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp)
 	cgroup_put(cgrp);
 }
 
+__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp)
+{
+	cgroup_put(cgrp);
+}
+CFI_NOSEAL(bpf_cgroup_release_dtor);
+
 /**
  * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor
  * array. A cgroup returned by this kfunc which is not subsequently stored in a
@@ -2525,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	 * which skips compiler generated instrumentation to do the same.
 	 */
 	kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
-	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
@@ -2570,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
 
 BTF_ID_LIST(generic_dtor_ids)
 BTF_ID(struct, task_struct)
-BTF_ID(func, bpf_task_release)
+BTF_ID(func, bpf_task_release_dtor)
 #ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
-BTF_ID(func, bpf_cgroup_release)
+BTF_ID(func, bpf_cgroup_release_dtor)
 #endif
 
 BTF_SET8_START(common_btf_ids)