aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/net/bpf_jit_comp.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/net/bpf_jit_comp.c')
-rw-r--r--arch/x86/net/bpf_jit_comp.c134
1 files changed, 115 insertions, 19 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index af4a5de7d93a..c89a4abdd726 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -17,6 +17,7 @@
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
#include <asm/unwind.h>
+#include <asm/cfi.h>
static bool all_callee_regs_used[4] = {true, true, true, true};
@@ -51,9 +52,11 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
#ifdef CONFIG_X86_KERNEL_IBT
-#define EMIT_ENDBR() EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR() EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR_POISON() EMIT(gen_endbr_poison(), 4)
#else
#define EMIT_ENDBR()
+#define EMIT_ENDBR_POISON()
#endif
static bool is_imm8(int value)
@@ -305,6 +308,69 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
}
/*
+ * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
+ * in arch/x86/kernel/alternative.c
+ */
+
+static void emit_fineibt(u8 **pprog, u32 hash)
+{
+ u8 *prog = *pprog;
+
+ EMIT_ENDBR();
+ EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */
+ EMIT2(0x74, 0x07); /* jz.d8 +7 */
+ EMIT2(0x0f, 0x0b); /* ud2 */
+ EMIT1(0x90); /* nop */
+ EMIT_ENDBR_POISON();
+
+ *pprog = prog;
+}
+
+static void emit_kcfi(u8 **pprog, u32 hash)
+{
+ u8 *prog = *pprog;
+
+ EMIT1_off32(0xb8, hash); /* movl $hash, %eax */
+#ifdef CONFIG_CALL_PADDING
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+ EMIT1(0x90);
+#endif
+ EMIT_ENDBR();
+
+ *pprog = prog;
+}
+
+static void emit_cfi(u8 **pprog, u32 hash)
+{
+ u8 *prog = *pprog;
+
+ switch (cfi_mode) {
+ case CFI_FINEIBT:
+ emit_fineibt(&prog, hash);
+ break;
+
+ case CFI_KCFI:
+ emit_kcfi(&prog, hash);
+ break;
+
+ default:
+ EMIT_ENDBR();
+ break;
+ }
+
+ *pprog = prog;
+}
+
+/*
* Emit x86-64 prologue code for BPF program.
* bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
* while jumping to another program
@@ -315,10 +381,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
{
u8 *prog = *pprog;
+ emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
/* BPF trampoline can be made to work without these nops,
* but let's waste 5 bytes for now and optimize later
*/
- EMIT_ENDBR();
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
if (!ebpf_from_cbpf) {
@@ -2442,10 +2508,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
u8 *prog;
bool save_ret;
+ /*
+ * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is
+ * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG
+ * because @func_addr.
+ */
+ WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) &&
+ (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET)));
+
/* extra registers for struct arguments */
- for (i = 0; i < m->nr_args; i++)
+ for (i = 0; i < m->nr_args; i++) {
if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
nr_regs += (m->arg_size[i] + 7) / 8 - 1;
+ }
/* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6
* are passed through regs, the remains are through stack.
@@ -2528,20 +2603,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
prog = rw_image;
- EMIT_ENDBR();
- /*
- * This is the direct-call trampoline, as such it needs accounting
- * for the __fentry__ call.
- */
- x86_call_depth_emit_accounting(&prog, NULL);
+ if (flags & BPF_TRAMP_F_INDIRECT) {
+ /*
+ * Indirect call for bpf_struct_ops
+ */
+ emit_cfi(&prog, cfi_get_func_hash(func_addr));
+ } else {
+ /*
+ * Direct-call fentry stub, as such it needs accounting for the
+ * __fentry__ call.
+ */
+ x86_call_depth_emit_accounting(&prog, NULL);
+ }
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
- if (!is_imm8(stack_size))
+ if (!is_imm8(stack_size)) {
/* sub rsp, stack_size */
EMIT3_off32(0x48, 0x81, 0xEC, stack_size);
- else
+ } else {
/* sub rsp, stack_size */
EMIT4(0x48, 0x83, 0xEC, stack_size);
+ }
if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
EMIT1(0x50); /* push rax */
/* mov QWORD PTR [rbp - rbx_off], rbx */
@@ -2575,10 +2657,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
}
}
- if (fentry->nr_links)
+ if (fentry->nr_links) {
if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image))
return -EINVAL;
+ }
if (fmod_ret->nr_links) {
branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
@@ -2597,11 +2680,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
restore_regs(m, &prog, regs_off);
save_args(m, &prog, arg_stack_off, true);
- if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
/* Before calling the original function, restore the
* tail_call_cnt from stack to rax.
*/
RESTORE_TAIL_CALL_CNT(stack_size);
+ }
if (flags & BPF_TRAMP_F_ORIG_STACK) {
emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8);
@@ -2630,17 +2714,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/* Update the branches saved in invoke_bpf_mod_ret with the
* aligned address of do_fexit.
*/
- for (i = 0; i < fmod_ret->nr_links; i++)
+ for (i = 0; i < fmod_ret->nr_links; i++) {
emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image),
image + (branches[i] - (u8 *)rw_image), X86_JNE);
+ }
}
- if (fexit->nr_links)
+ if (fexit->nr_links) {
if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off,
false, image, rw_image)) {
ret = -EINVAL;
goto cleanup;
}
+ }
if (flags & BPF_TRAMP_F_RESTORE_REGS)
restore_regs(m, &prog, regs_off);
@@ -2657,11 +2743,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
ret = -EINVAL;
goto cleanup;
}
- } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
/* Before running the original function, restore the
* tail_call_cnt from stack to rax.
*/
RESTORE_TAIL_CALL_CNT(stack_size);
+ }
/* restore return value of orig_call or fentry prog back into RAX */
if (save_ret)
@@ -2669,9 +2756,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off);
EMIT1(0xC9); /* leave */
- if (flags & BPF_TRAMP_F_SKIP_FRAME)
+ if (flags & BPF_TRAMP_F_SKIP_FRAME) {
/* skip our return address and return to parent */
EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
+ }
emit_return(&prog, image + (prog - (u8 *)rw_image));
/* Make sure the trampoline generation logic doesn't overflow */
if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) {
@@ -3013,9 +3101,16 @@ out_image:
jit_data->header = header;
jit_data->rw_header = rw_header;
}
- prog->bpf_func = (void *)image;
+ /*
+ * ctx.prog_offset is used when CFI preambles put code *before*
+ * the function. See emit_cfi(). For FineIBT specifically this code
+ * can also be executed and bpf_prog_kallsyms_add() will
+ * generate an additional symbol to cover this, hence also
+ * decrement proglen.
+ */
+ prog->bpf_func = (void *)image + cfi_get_offset();
prog->jited = 1;
- prog->jited_len = proglen;
+ prog->jited_len = proglen - cfi_get_offset();
} else {
prog = orig_prog;
}
@@ -3070,6 +3165,7 @@ void bpf_jit_free(struct bpf_prog *prog)
kvfree(jit_data->addrs);
kfree(jit_data);
}
+ prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset();
hdr = bpf_jit_binary_pack_hdr(prog);
bpf_jit_binary_pack_free(hdr, NULL);
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
Powered by cgit, Gruvboxed by Blaster4385.