From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 9 Jan 2018 10:04:29 -0800
Subject: bpf: introduce BPF_JIT_ALWAYS_ON config
Patch-mainline: v4.15-rc8
Git-commit: 290af86629b25ffd1ed6232c4e9107da031705cb
References: bsc#1083647
The BPF interpreter has been used as part of the spectre 2 attack CVE-2017-5715.
A quote from goolge project zero blog:
"At this point, it would normally be necessary to locate gadgets in
the host kernel code that can be used to actually leak data by reading
from an attacker-controlled location, shifting and masking the result
appropriately and then using the result of that as offset to an
attacker-controlled address for a load. But piecing gadgets together
and figuring out which ones work in a speculation context seems annoying.
So instead, we decided to use the eBPF interpreter, which is built into
the host kernel - while there is no legitimate way to invoke it from inside
a VM, the presence of the code in the host kernel's text section is sufficient
to make it usable for the attack, just like with ordinary ROP gadgets."
To make attacker job harder introduce BPF_JIT_ALWAYS_ON config
option that removes interpreter from the kernel in favor of JIT-only mode.
So far eBPF JIT is supported by:
x64, arm64, arm32, sparc64, s390, powerpc64, mips64
The start of JITed program is randomized and code page is marked as read-only.
In addition "constant blinding" can be turned on with net.core.bpf_jit_harden
v2->v3:
- move __bpf_prog_ret0 under ifdef (Daniel)
v1->v2:
- fix init order, test_bpf and cBPF (Daniel's feedback)
- fix offloaded bpf (Jakub's feedback)
- add 'return 0' dummy in case something can invoke prog->bpf_func
- retarget bpf tree. For bpf-next the patch would need one extra hunk.
It will be sent when the trees are merged back to net-next
Considered doing:
int bpf_jit_enable __read_mostly = BPF_EBPF_JIT_DEFAULT;
but it seems better to land the patch as-is and in bpf-next remove
bpf_jit_enable global variable from all JITs, consolidate in one place
and remove this jit_init() function.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Gary Lin <glin@suse.com>
---
init/Kconfig | 7 +++++++
kernel/bpf/core.c | 19 +++++++++++++++++++
lib/test_bpf.c | 11 +++++++----
net/core/filter.c | 6 ++----
net/core/sysctl_net_core.c | 6 ++++++
net/socket.c | 9 +++++++++
6 files changed, 50 insertions(+), 8 deletions(-)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1701,6 +1701,13 @@ config ADVISE_SYSCALLS
applications use these syscalls, you can disable this option to save
space.
+config BPF_JIT_ALWAYS_ON
+ bool "Permanently enable BPF JIT and remove BPF interpreter"
+ depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT
+ help
+ Enables BPF JIT and removes BPF interpreter to avoid
+ speculative execution of BPF instructions by the interpreter
+
config USERFAULTFD
bool "Enable userfaultfd() system call"
select ANON_INODES
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -773,6 +773,7 @@ noinline u64 __bpf_call_base(u64 r1, u64
}
EXPORT_SYMBOL_GPL(__bpf_call_base);
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
/**
* __bpf_prog_run - run eBPF program on a given context
* @ctx: is the data we are operating on
@@ -1323,6 +1324,14 @@ EVAL6(PROG_NAME_LIST, 224, 256, 288, 320
EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
};
+#else
+static unsigned int __bpf_prog_ret0(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ return 0;
+}
+#endif
+
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
@@ -1370,9 +1379,13 @@ static int bpf_check_tail_call(const str
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0;
+#endif
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -1382,6 +1395,12 @@ struct bpf_prog *bpf_prog_select_runtime
*/
if (!bpf_prog_is_dev_bound(fp->aux)) {
fp = bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ if (!fp->jited) {
+ *err = -ENOTSUPP;
+ return fp;
+ }
+#endif
} else {
*err = bpf_prog_offload_compile(fp);
if (*err)
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -6175,9 +6175,8 @@ static struct bpf_prog *generate_filter(
return NULL;
}
}
- /* We don't expect to fail. */
if (*err) {
- pr_cont("FAIL to attach err=%d len=%d\n",
+ pr_cont("FAIL to prog_create err=%d len=%d\n",
*err, fprog.len);
return NULL;
}
@@ -6201,6 +6200,10 @@ static struct bpf_prog *generate_filter(
* checks.
*/
fp = bpf_prog_select_runtime(fp, err);
+ if (*err) {
+ pr_cont("FAIL to select_runtime err=%d\n", *err);
+ return NULL;
+ }
break;
}
@@ -6386,8 +6389,8 @@ static __init int test_bpf(void)
pass_cnt++;
continue;
}
-
- return err;
+ err_cnt++;
+ continue;
}
pr_cont("jited:%u ", fp->jited);
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1054,11 +1054,9 @@ static struct bpf_prog *bpf_migrate_filt
*/
goto out_err_free;
- /* We are guaranteed to never error here with cBPF to eBPF
- * transitions, since there's no issue with type compatibility
- * checks on program arrays.
- */
fp = bpf_prog_select_runtime(fp, &err);
+ if (err)
+ goto out_err_free;
kfree(old_prog);
return fp;
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -324,7 +324,13 @@ static struct ctl_table net_core_table[]
.data = &bpf_jit_enable,
.maxlen = sizeof(int),
.mode = 0644,
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
.proc_handler = proc_dointvec
+#else
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &one,
+#endif
},
# ifdef CONFIG_HAVE_EBPF_JIT
{
--- a/net/socket.c
+++ b/net/socket.c
@@ -2644,6 +2644,15 @@ out_fs:
core_initcall(sock_init); /* early initcall */
+static int __init jit_init(void)
+{
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ bpf_jit_enable = 1;
+#endif
+ return 0;
+}
+pure_initcall(jit_init);
+
#ifdef CONFIG_PROC_FS
void socket_seq_show(struct seq_file *seq)
{