summaryrefslogtreecommitdiff
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.c110
1 files changed, 78 insertions, 32 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 2b1e266ff95c..8fe35ed11fd6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -46,6 +46,12 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT4_off32(b1, b2, b3, b4, off) \
do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+#ifdef CONFIG_X86_KERNEL_IBT
+#define EMIT_ENDBR() EMIT(gen_endbr(), 4)
+#else
+#define EMIT_ENDBR()
+#endif
+
static bool is_imm8(int value)
{
return value <= 127 && value >= -128;
@@ -241,7 +247,7 @@ struct jit_context {
/* Number of bytes emit_patch() needs to generate instructions */
#define X86_PATCH_SIZE 5
/* Number of bytes that will be skipped on tailcall */
-#define X86_TAIL_CALL_OFFSET 11
+#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE)
static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
{
@@ -286,6 +292,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
/* 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) {
@@ -296,6 +303,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
}
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+
+ /* X86_TAIL_CALL_OFFSET is here */
+ EMIT_ENDBR();
+
/* sub rsp, rounded_stack_depth */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
@@ -330,8 +341,7 @@ static int emit_jump(u8 **pprog, void *func, void *ip)
}
static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
- void *old_addr, void *new_addr,
- const bool text_live)
+ void *old_addr, void *new_addr)
{
const u8 *nop_insn = x86_nops[5];
u8 old_insn[X86_PATCH_SIZE];
@@ -365,10 +375,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
- if (text_live)
- text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
- else
- memcpy(ip, new_insn, X86_PATCH_SIZE);
+ text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
ret = 0;
}
out:
@@ -384,7 +391,14 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
/* BPF poking in modules is not supported */
return -EINVAL;
- return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
+ /*
+ * See emit_prologue(), for IBT builds the trampoline hook is preceded
+ * with an ENDBR instruction.
+ */
+ if (is_endbr(*(u32 *)ip))
+ ip += ENDBR_INSN_SIZE;
+
+ return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
}
#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8)
@@ -394,7 +408,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
u8 *prog = *pprog;
#ifdef CONFIG_RETPOLINE
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -558,24 +572,15 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
mutex_lock(&array->aux->poke_mutex);
target = array->ptrs[poke->tail_call.key];
if (target) {
- /* Plain memcpy is used when image is not live yet
- * and still not locked as read-only. Once poke
- * location is active (poke->tailcall_target_stable),
- * any parallel bpf_arch_text_poke() might occur
- * still on the read-write image until we finally
- * locked it as read-only. Both modifications on
- * the given image are under text_mutex to avoid
- * interference.
- */
ret = __bpf_arch_text_poke(poke->tailcall_target,
BPF_MOD_JUMP, NULL,
(u8 *)target->bpf_func +
- poke->adj_off, false);
+ poke->adj_off);
BUG_ON(ret < 0);
ret = __bpf_arch_text_poke(poke->tailcall_bypass,
BPF_MOD_JUMP,
(u8 *)poke->tailcall_target +
- X86_PATCH_SIZE, NULL, false);
+ X86_PATCH_SIZE, NULL);
BUG_ON(ret < 0);
}
WRITE_ONCE(poke->tailcall_target_stable, true);
@@ -787,7 +792,6 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
/* emit opcode */
switch (atomic_op) {
case BPF_ADD:
- case BPF_SUB:
case BPF_AND:
case BPF_OR:
case BPF_XOR:
@@ -867,7 +871,7 @@ static void emit_nops(u8 **pprog, int len)
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
@@ -894,8 +898,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
push_callee_regs(&prog, callee_regs_used);
ilen = prog - temp;
- if (image)
- memcpy(image + proglen, temp, ilen);
+ if (rw_image)
+ memcpy(rw_image + proglen, temp, ilen);
proglen += ilen;
addrs[0] = proglen;
prog = temp;
@@ -1324,6 +1328,9 @@ st: if (is_imm8(insn->off))
pr_err("extable->insn doesn't fit into 32-bit\n");
return -EFAULT;
}
+ /* switch ex to rw buffer for writes */
+ ex = (void *)rw_image + ((void *)ex - (void *)image);
+
ex->insn = delta;
ex->data = EX_TYPE_BPF;
@@ -1706,7 +1713,7 @@ emit_jmp:
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
- memcpy(image + proglen, temp, ilen);
+ memcpy(rw_image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
@@ -2024,14 +2031,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
ip_off = stack_size;
- if (flags & BPF_TRAMP_F_SKIP_FRAME)
+ if (flags & BPF_TRAMP_F_SKIP_FRAME) {
/* skip patched call instruction and point orig_call to actual
* body of the kernel function.
*/
+ if (is_endbr(*(u32 *)orig_call))
+ orig_call += ENDBR_INSN_SIZE;
orig_call += X86_PATCH_SIZE;
+ }
prog = image;
+ EMIT_ENDBR();
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
@@ -2247,6 +2258,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs)
}
struct x64_jit_data {
+ struct bpf_binary_header *rw_header;
struct bpf_binary_header *header;
int *addrs;
u8 *image;
@@ -2259,6 +2271,7 @@ struct x64_jit_data {
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
+ struct bpf_binary_header *rw_header = NULL;
struct bpf_binary_header *header = NULL;
struct bpf_prog *tmp, *orig_prog = prog;
struct x64_jit_data *jit_data;
@@ -2267,6 +2280,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bool tmp_blinded = false;
bool extra_pass = false;
bool padding = false;
+ u8 *rw_image = NULL;
u8 *image = NULL;
int *addrs;
int pass;
@@ -2302,6 +2316,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
oldproglen = jit_data->proglen;
image = jit_data->image;
header = jit_data->header;
+ rw_header = jit_data->rw_header;
+ rw_image = (void *)rw_header + ((void *)image - (void *)header);
extra_pass = true;
padding = true;
goto skip_init_addrs;
@@ -2332,13 +2348,22 @@ skip_init_addrs:
for (pass = 0; pass < MAX_PASSES || image; pass++) {
if (!padding && pass >= PADDING_PASSES)
padding = true;
- proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding);
+ proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
if (proglen <= 0) {
out_image:
image = NULL;
- if (header)
- bpf_jit_binary_free(header);
+ if (header) {
+ bpf_arch_text_copy(&header->size, &rw_header->size,
+ sizeof(rw_header->size));
+ bpf_jit_binary_pack_free(header, rw_header);
+ }
+ /* Fall back to interpreter mode */
prog = orig_prog;
+ if (extra_pass) {
+ prog->bpf_func = NULL;
+ prog->jited = 0;
+ prog->jited_len = 0;
+ }
goto out_addrs;
}
if (image) {
@@ -2361,8 +2386,9 @@ out_image:
sizeof(struct exception_table_entry);
/* allocate module memory for x86 insns and extable */
- header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
- &image, align, jit_fill_hole);
+ header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size,
+ &image, align, &rw_header, &rw_image,
+ jit_fill_hole);
if (!header) {
prog = orig_prog;
goto out_addrs;
@@ -2378,14 +2404,27 @@ out_image:
if (image) {
if (!prog->is_func || extra_pass) {
+ /*
+ * bpf_jit_binary_pack_finalize fails in two scenarios:
+ * 1) header is not pointing to proper module memory;
+ * 2) the arch doesn't support bpf_arch_text_copy().
+ *
+ * Both cases are serious bugs and justify WARN_ON.
+ */
+ if (WARN_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header))) {
+ /* header has been freed */
+ header = NULL;
+ goto out_image;
+ }
+
bpf_tail_call_direct_fixup(prog);
- bpf_jit_binary_lock_ro(header);
} else {
jit_data->addrs = addrs;
jit_data->ctx = ctx;
jit_data->proglen = proglen;
jit_data->image = image;
jit_data->header = header;
+ jit_data->rw_header = rw_header;
}
prog->bpf_func = (void *)image;
prog->jited = 1;
@@ -2413,3 +2452,10 @@ bool bpf_jit_supports_kfunc_call(void)
{
return true;
}
+
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+ if (text_poke_copy(dst, src, len) == NULL)
+ return ERR_PTR(-EINVAL);
+ return dst;
+}
generated by cgit (git 2.34.1) at 2024-06-07 00:08:19 +0000