Re: [PATCH bpf-next] bpf: introduce BPF_JIT_ALWAYS_ON config

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

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 init/Kconfig               | 7 +++++++
 kernel/bpf/core.c          | 9 +++++++++
 kernel/bpf/verifier.c      | 4 ++++
 net/core/sysctl_net_core.c | 9 +++++++++
 4 files changed, 29 insertions(+)

diff --git a/init/Kconfig b/init/Kconfig
index 2934249fba46..5e2a4a391ba9 100644
--- a/init/Kconfig
+++ b/init/Kconfig

@@ -1392,6 +1392,13 @@ config BPF_SYSCALL
 	  Enable the bpf() system call that allows to manipulate eBPF
 	  programs and maps via file descriptors.
 
+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

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 70a534549cd3..42756c434e0b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c

@@ -781,6 +781,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 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

@@ -1376,6 +1377,7 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 		__bpf_call_base_args;
 	insn->code = BPF_JMP | BPF_CALL_ARGS;
 }
+#endif
 
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)

@@ -1427,9 +1429,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
  */
 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];
+#endif
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during

@@ -1453,6 +1457,11 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 */
 	*err = bpf_check_tail_call(fp);
 
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+	if (!fp->jited)
+		*err = -ENOTSUPP;
+#endif

@@ -524,6 +530,9 @@ static __net_initdata struct pernet_operations sysctl_core_ops = {
 
 static __init int sysctl_core_init(void)
 {
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_JIT_ALWAYS_ON)
+	bpf_jit_enable = 1;
+#endif