summaryrefslogtreecommitdiffstats
path: root/arch/x86/net
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/net')
-rw-r--r--arch/x86/net/bpf_jit_comp.c120
1 files changed, 108 insertions, 12 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 955133077c..e89e415aa7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -16,6 +16,9 @@
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
+#include <asm/unwind.h>
+
+static bool all_callee_regs_used[4] = {true, true, true, true};
static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
@@ -255,6 +258,14 @@ struct jit_context {
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE)
+static void push_r12(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x54); /* push r12 */
+ *pprog = prog;
+}
+
static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
@@ -270,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
*pprog = prog;
}
+static void pop_r12(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x5C); /* pop r12 */
+ *pprog = prog;
+}
+
static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
@@ -291,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
* while jumping to another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
- bool tail_call_reachable, bool is_subprog)
+ bool tail_call_reachable, bool is_subprog,
+ bool is_exception_cb)
{
u8 *prog = *pprog;
@@ -303,12 +323,30 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
prog += X86_PATCH_SIZE;
if (!ebpf_from_cbpf) {
if (tail_call_reachable && !is_subprog)
+ /* When it's the entry of the whole tailcall context,
+ * zeroing rax means initialising tail_call_cnt.
+ */
EMIT2(0x31, 0xC0); /* xor eax, eax */
else
+ /* Keep the same instruction layout. */
EMIT2(0x66, 0x90); /* nop2 */
}
- EMIT1(0x55); /* push rbp */
- EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+ /* Exception callback receives FP as third parameter */
+ if (is_exception_cb) {
+ EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */
+ EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */
+ /* The main frame must have exception_boundary as true, so we
+ * first restore those callee-saved regs from stack, before
+ * reusing the stack frame.
+ */
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ /* Reset the stack frame. */
+ EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */
+ } else {
+ EMIT1(0x55); /* push rbp */
+ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+ }
/* X86_TAIL_CALL_OFFSET is here */
EMIT_ENDBR();
@@ -467,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip)
* goto *(prog->bpf_func + prologue_size);
* out:
*/
-static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ u8 **pprog, bool *callee_regs_used,
u32 stack_depth, u8 *ip,
struct jit_context *ctx)
{
@@ -517,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
offset = ctx->tail_call_indirect_label - (prog + 2 - start);
EMIT2(X86_JE, offset); /* je out */
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
EMIT1(0x58); /* pop rax */
if (stack_depth)
@@ -541,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
*pprog = prog;
}
-static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
+static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+ struct bpf_jit_poke_descriptor *poke,
u8 **pprog, u8 *ip,
bool *callee_regs_used, u32 stack_depth,
struct jit_context *ctx)
@@ -570,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
poke->tailcall_bypass);
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
+
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
@@ -1045,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
- bpf_prog->aux->func_idx != 0);
- push_callee_regs(&prog, callee_regs_used);
+ bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
+ /* Exception callback will clobber callee regs for its own use, and
+ * restore the original callee regs from main prog's stack frame.
+ */
+ if (bpf_prog->aux->exception_boundary) {
+ /* We also need to save r12, which is not mapped to any BPF
+ * register, as we throw after entry into the kernel, which may
+ * overwrite r12.
+ */
+ push_r12(&prog);
+ push_callee_regs(&prog, all_callee_regs_used);
+ } else {
+ push_callee_regs(&prog, callee_regs_used);
+ }
ilen = prog - temp;
if (rw_image)
@@ -1643,13 +1706,15 @@ st: if (is_imm8(insn->off))
case BPF_JMP | BPF_TAIL_CALL:
if (imm32)
- emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
+ emit_bpf_tail_call_direct(bpf_prog,
+ &bpf_prog->aux->poke_tab[imm32 - 1],
&prog, image + addrs[i - 1],
callee_regs_used,
bpf_prog->aux->stack_depth,
ctx);
else
- emit_bpf_tail_call_indirect(&prog,
+ emit_bpf_tail_call_indirect(bpf_prog,
+ &prog,
callee_regs_used,
bpf_prog->aux->stack_depth,
image + addrs[i - 1],
@@ -1902,7 +1967,12 @@ emit_jmp:
seen_exit = true;
/* Update cleanup_addr */
ctx->cleanup_addr = proglen;
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
EMIT1(0xC9); /* leave */
emit_return(&prog, image + addrs[i - 1] + (prog - temp));
break;
@@ -2930,6 +3000,32 @@ void bpf_jit_free(struct bpf_prog *prog)
bpf_prog_unlock_free(prog);
}
+bool bpf_jit_supports_exceptions(void)
+{
+ /* We unwind through both kernel frames (starting from within bpf_throw
+ * call) and BPF frames. Therefore we require ORC unwinder to be enabled
+ * to walk kernel frames and reach BPF frames in the stack trace.
+ */
+ return IS_ENABLED(CONFIG_UNWINDER_ORC);
+}
+
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+#if defined(CONFIG_UNWINDER_ORC)
+ struct unwind_state state;
+ unsigned long addr;
+
+ for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp))
+ break;
+ }
+ return;
+#endif
+ WARN(1, "verification of programs using bpf_throw should have failed\n");
+}
+
void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
struct bpf_prog *new, struct bpf_prog *old)
{
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-21 06:46:05 +0000