[PATCH arm64-next v3] net: bpf: arm64: address randomize and write protect JIT code

[Daniel Borkmann]

This is the ARM64 variant for 314beb9bcab ("x86: bpf_jit_comp: secure bpf
jit against spraying attacks").

Thanks to commit 11d91a770f1f ("arm64: Add CONFIG_DEBUG_SET_MODULE_RONX
support") which added necessary infrastructure, we can now implement
RO marking of eBPF generated JIT image pages and randomize start offset
for the JIT code, so that it does not reside directly on a page boundary
anymore. Likewise, the holes are filled with illegal instructions: here
we use BRK #0x100 (opcode 0xd4202000) to trigger a fault in the kernel
(unallocated BRKs would trigger a fault through do_debug_exception). This
seems more reliable as we don't have a guaranteed undefined instruction
space on ARM64.

This is basically the ARM64 variant of what we already have in ARM via
commit 55309dd3d4cd ("net: bpf: arm: address randomize and write protect
JIT code"). Moreover, this commit also presents a merge resolution due to
conflicts with commit 60a3b2253c41 ("net: bpf: make eBPF interpreter images
read-only") as we don't use kfree() in bpf_jit_free() anymore to release
the locked bpf_prog structure, but instead bpf_prog_unlock_free() through
a different allocator.

JIT tested on aarch64 with BPF test suite.

Reference: http://mainisusuallyafunction.blogspot.com/2012/11/attacking-hardened-linux-systems-with.html
Signed-off-by: Daniel Borkmann <dborkman at redhat.com>
Cc: Zi Shen Lim <zlim.lnx at gmail.com>
Cc: Will Deacon <will.deacon at arm.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Cc: David S. Miller <davem at davemloft.net>
Cc: Alexei Starovoitov <ast at plumgrid.com>
---
 v2->v3:
  - Use cpu_to_le32() as suggested by Zi/Will
 v1->v2:
  - Use brk insn as suggested by Catalin
 Note:
  - This patch depends on net-next being merged to mainline due
    to the mentioned merge conflict.

 arch/arm64/net/bpf_jit_comp.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 7ae3354..4b71779 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -19,7 +19,6 @@
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
 #include <linux/filter.h>
-#include <linux/moduleloader.h>
 #include <linux/printk.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
@@ -119,6 +118,15 @@ static inline int bpf2a64_offset(int bpf_to, int bpf_from,
 	return to - from;
 }
 
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	/* We use brk #0x100 to trigger a fault. */
+	u32 *ptr;
+	/* We are guaranteed to have aligned memory. */
+	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
+		*ptr++ = cpu_to_le32(0xd4202000);
+}
+
 static inline int epilogue_offset(const struct jit_ctx *ctx)
 {
 	int to = ctx->offset[ctx->prog->len - 1];
@@ -613,8 +621,10 @@ void bpf_jit_compile(struct bpf_prog *prog)
 
 void bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	struct bpf_binary_header *header;
 	struct jit_ctx ctx;
 	int image_size;
+	u8 *image_ptr;
 
 	if (!bpf_jit_enable)
 		return;
@@ -636,23 +646,25 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out;
 
 	build_prologue(&ctx);
-
 	build_epilogue(&ctx);
 
 	/* Now we know the actual image size. */
 	image_size = sizeof(u32) * ctx.idx;
-	ctx.image = module_alloc(image_size);
-	if (unlikely(ctx.image == NULL))
+	header = bpf_jit_binary_alloc(image_size, &image_ptr,
+				      sizeof(u32), jit_fill_hole);
+	if (header == NULL)
 		goto out;
 
 	/* 2. Now, the actual pass. */
 
+	ctx.image = (u32 *)image_ptr;
 	ctx.idx = 0;
+
 	build_prologue(&ctx);
 
 	ctx.body_offset = ctx.idx;
 	if (build_body(&ctx)) {
-		module_free(NULL, ctx.image);
+		bpf_jit_binary_free(header);
 		goto out;
 	}
 
@@ -663,17 +675,25 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
 
 	bpf_flush_icache(ctx.image, ctx.image + ctx.idx);
+
+	set_memory_ro((unsigned long)header, header->pages);
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
-
 out:
 	kfree(ctx.offset);
 }
 
 void bpf_jit_free(struct bpf_prog *prog)
 {
-	if (prog->jited)
-		module_free(NULL, prog->bpf_func);
+	unsigned long addr = (unsigned long)prog->bpf_func & PAGE_MASK;
+	struct bpf_binary_header *header = (void *)addr;
+
+	if (!prog->jited)
+		goto free_filter;
+
+	set_memory_rw(addr, header->pages);
+	bpf_jit_binary_free(header);
 
-	kfree(prog);
+free_filter:
+	bpf_prog_unlock_free(prog);
 }
-- 
1.9.3