summaryrefslogtreecommitdiffstats
path: root/arch/arm64/net/bpf_jit_comp.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/net/bpf_jit_comp.c')
-rw-r--r--arch/arm64/net/bpf_jit_comp.c193
1 files changed, 158 insertions, 35 deletions
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 13eac43c63..1bf483ec97 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -29,6 +29,7 @@
#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
#define TMP_REG_3 (MAX_BPF_JIT_REG + 3)
#define FP_BOTTOM (MAX_BPF_JIT_REG + 4)
+#define ARENA_VM_START (MAX_BPF_JIT_REG + 5)
#define check_imm(bits, imm) do { \
if ((((imm) > 0) && ((imm) >> (bits))) || \
@@ -67,6 +68,8 @@ static const int bpf2a64[] = {
/* temporary register for blinding constants */
[BPF_REG_AX] = A64_R(9),
[FP_BOTTOM] = A64_R(27),
+ /* callee saved register for kern_vm_start address */
+ [ARENA_VM_START] = A64_R(28),
};
struct jit_ctx {
@@ -79,6 +82,7 @@ struct jit_ctx {
__le32 *ro_image;
u32 stack_size;
int fpb_offset;
+ u64 user_vm_start;
};
struct bpf_plt {
@@ -295,7 +299,7 @@ static bool is_lsi_offset(int offset, int scale)
#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 8)
static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
- bool is_exception_cb)
+ bool is_exception_cb, u64 arena_vm_start)
{
const struct bpf_prog *prog = ctx->prog;
const bool is_main_prog = !bpf_is_subprog(prog);
@@ -306,6 +310,7 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
const u8 fp = bpf2a64[BPF_REG_FP];
const u8 tcc = bpf2a64[TCALL_CNT];
const u8 fpb = bpf2a64[FP_BOTTOM];
+ const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
const int idx0 = ctx->idx;
int cur_offset;
@@ -411,6 +416,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
/* Set up function call stack */
emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
+
+ if (arena_vm_start)
+ emit_a64_mov_i64(arena_vm_base, arena_vm_start, ctx);
+
return 0;
}
@@ -485,20 +494,26 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
const u8 code = insn->code;
+ const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
const u8 dst = bpf2a64[insn->dst_reg];
const u8 src = bpf2a64[insn->src_reg];
const u8 tmp = bpf2a64[TMP_REG_1];
const u8 tmp2 = bpf2a64[TMP_REG_2];
const bool isdw = BPF_SIZE(code) == BPF_DW;
+ const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
const s16 off = insn->off;
- u8 reg;
+ u8 reg = dst;
- if (!off) {
- reg = dst;
- } else {
- emit_a64_mov_i(1, tmp, off, ctx);
- emit(A64_ADD(1, tmp, tmp, dst), ctx);
- reg = tmp;
+ if (off || arena) {
+ if (off) {
+ emit_a64_mov_i(1, tmp, off, ctx);
+ emit(A64_ADD(1, tmp, tmp, dst), ctx);
+ reg = tmp;
+ }
+ if (arena) {
+ emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+ reg = tmp;
+ }
}
switch (insn->imm) {
@@ -567,6 +582,12 @@ static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
u8 reg;
s32 jmp_offset;
+ if (BPF_MODE(code) == BPF_PROBE_ATOMIC) {
+ /* ll_sc based atomics don't support unsafe pointers yet. */
+ pr_err_once("unknown atomic opcode %02x\n", code);
+ return -EINVAL;
+ }
+
if (!off) {
reg = dst;
} else {
@@ -738,6 +759,7 @@ static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
#define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0)
#define BPF_FIXUP_REG_MASK GENMASK(31, 27)
+#define DONT_CLEAR 5 /* Unused ARM64 register from BPF's POV */
bool ex_handler_bpf(const struct exception_table_entry *ex,
struct pt_regs *regs)
@@ -745,7 +767,8 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
- regs->regs[dst_reg] = 0;
+ if (dst_reg != DONT_CLEAR)
+ regs->regs[dst_reg] = 0;
regs->pc = (unsigned long)&ex->fixup - offset;
return true;
}
@@ -765,7 +788,9 @@ static int add_exception_handler(const struct bpf_insn *insn,
return 0;
if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
- BPF_MODE(insn->code) != BPF_PROBE_MEMSX)
+ BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
+ BPF_MODE(insn->code) != BPF_PROBE_MEM32 &&
+ BPF_MODE(insn->code) != BPF_PROBE_ATOMIC)
return 0;
if (!ctx->prog->aux->extable ||
@@ -810,6 +835,9 @@ static int add_exception_handler(const struct bpf_insn *insn,
ex->insn = ins_offset;
+ if (BPF_CLASS(insn->code) != BPF_LDX)
+ dst_reg = DONT_CLEAR;
+
ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
@@ -829,12 +857,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
bool extra_pass)
{
const u8 code = insn->code;
- const u8 dst = bpf2a64[insn->dst_reg];
- const u8 src = bpf2a64[insn->src_reg];
+ u8 dst = bpf2a64[insn->dst_reg];
+ u8 src = bpf2a64[insn->src_reg];
const u8 tmp = bpf2a64[TMP_REG_1];
const u8 tmp2 = bpf2a64[TMP_REG_2];
const u8 fp = bpf2a64[BPF_REG_FP];
const u8 fpb = bpf2a64[FP_BOTTOM];
+ const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
const s16 off = insn->off;
const s32 imm = insn->imm;
const int i = insn - ctx->prog->insnsi;
@@ -853,6 +882,24 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
/* dst = src */
case BPF_ALU | BPF_MOV | BPF_X:
case BPF_ALU64 | BPF_MOV | BPF_X:
+ if (insn_is_cast_user(insn)) {
+ emit(A64_MOV(0, tmp, src), ctx); // 32-bit mov clears the upper 32 bits
+ emit_a64_mov_i(0, dst, ctx->user_vm_start >> 32, ctx);
+ emit(A64_LSL(1, dst, dst, 32), ctx);
+ emit(A64_CBZ(1, tmp, 2), ctx);
+ emit(A64_ORR(1, tmp, dst, tmp), ctx);
+ emit(A64_MOV(1, dst, tmp), ctx);
+ break;
+ } else if (insn_is_mov_percpu_addr(insn)) {
+ if (dst != src)
+ emit(A64_MOV(1, dst, src), ctx);
+ if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+ emit(A64_MRS_TPIDR_EL2(tmp), ctx);
+ else
+ emit(A64_MRS_TPIDR_EL1(tmp), ctx);
+ emit(A64_ADD(1, dst, dst, tmp), ctx);
+ break;
+ }
switch (insn->off) {
case 0:
emit(A64_MOV(is64, dst, src), ctx);
@@ -1181,6 +1228,21 @@ emit_cond_jmp:
const u8 r0 = bpf2a64[BPF_REG_0];
bool func_addr_fixed;
u64 func_addr;
+ u32 cpu_offset;
+
+ /* Implement helper call to bpf_get_smp_processor_id() inline */
+ if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+ cpu_offset = offsetof(struct thread_info, cpu);
+
+ emit(A64_MRS_SP_EL0(tmp), ctx);
+ if (is_lsi_offset(cpu_offset, 2)) {
+ emit(A64_LDR32I(r0, tmp, cpu_offset), ctx);
+ } else {
+ emit_a64_mov_i(1, tmp2, cpu_offset, ctx);
+ emit(A64_LDR32(r0, tmp, tmp2), ctx);
+ }
+ break;
+ }
ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
&func_addr, &func_addr_fixed);
@@ -1237,7 +1299,15 @@ emit_cond_jmp:
case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
- if (ctx->fpb_offset > 0 && src == fp) {
+ case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+ case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+ case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+ case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+ emit(A64_ADD(1, tmp2, src, arena_vm_base), ctx);
+ src = tmp2;
+ }
+ if (ctx->fpb_offset > 0 && src == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) {
src_adj = fpb;
off_adj = off + ctx->fpb_offset;
} else {
@@ -1322,7 +1392,15 @@ emit_cond_jmp:
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
case BPF_ST | BPF_MEM | BPF_DW:
- if (ctx->fpb_offset > 0 && dst == fp) {
+ case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+ case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+ case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+ case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+ emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx);
+ dst = tmp2;
+ }
+ if (ctx->fpb_offset > 0 && dst == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) {
dst_adj = fpb;
off_adj = off + ctx->fpb_offset;
} else {
@@ -1365,6 +1443,10 @@ emit_cond_jmp:
}
break;
}
+
+ ret = add_exception_handler(insn, ctx, dst);
+ if (ret)
+ return ret;
break;
/* STX: *(size *)(dst + off) = src */
@@ -1372,7 +1454,15 @@ emit_cond_jmp:
case BPF_STX | BPF_MEM | BPF_H:
case BPF_STX | BPF_MEM | BPF_B:
case BPF_STX | BPF_MEM | BPF_DW:
- if (ctx->fpb_offset > 0 && dst == fp) {
+ case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
+ case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
+ case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
+ case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
+ if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+ emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx);
+ dst = tmp2;
+ }
+ if (ctx->fpb_offset > 0 && dst == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) {
dst_adj = fpb;
off_adj = off + ctx->fpb_offset;
} else {
@@ -1413,16 +1503,26 @@ emit_cond_jmp:
}
break;
}
+
+ ret = add_exception_handler(insn, ctx, dst);
+ if (ret)
+ return ret;
break;
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
ret = emit_lse_atomic(insn, ctx);
else
ret = emit_ll_sc_atomic(insn, ctx);
if (ret)
return ret;
+
+ ret = add_exception_handler(insn, ctx, dst);
+ if (ret)
+ return ret;
break;
default:
@@ -1594,6 +1694,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bool tmp_blinded = false;
bool extra_pass = false;
struct jit_ctx ctx;
+ u64 arena_vm_start;
u8 *image_ptr;
u8 *ro_image_ptr;
@@ -1611,6 +1712,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
prog = tmp;
}
+ arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena);
jit_data = prog->aux->jit_data;
if (!jit_data) {
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
@@ -1641,6 +1743,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
}
ctx.fpb_offset = find_fpb_offset(prog);
+ ctx.user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
/*
* 1. Initial fake pass to compute ctx->idx and ctx->offset.
@@ -1648,7 +1751,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
* BPF line info needs ctx->offset[i] to be the offset of
* instruction[i] in jited image, so build prologue first.
*/
- if (build_prologue(&ctx, was_classic, prog->aux->exception_cb)) {
+ if (build_prologue(&ctx, was_classic, prog->aux->exception_cb,
+ arena_vm_start)) {
prog = orig_prog;
goto out_off;
}
@@ -1696,7 +1800,7 @@ skip_init_ctx:
ctx.idx = 0;
ctx.exentry_idx = 0;
- build_prologue(&ctx, was_classic, prog->aux->exception_cb);
+ build_prologue(&ctx, was_classic, prog->aux->exception_cb, arena_vm_start);
if (build_body(&ctx, extra_pass)) {
prog = orig_prog;
@@ -1793,17 +1897,6 @@ u64 bpf_jit_alloc_exec_limit(void)
return VMALLOC_END - VMALLOC_START;
}
-void *bpf_jit_alloc_exec(unsigned long size)
-{
- /* Memory is intended to be executable, reset the pointer tag. */
- return kasan_reset_tag(vmalloc(size));
-}
-
-void bpf_jit_free_exec(void *addr)
-{
- return vfree(addr);
-}
-
/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
bool bpf_jit_supports_subprog_tailcalls(void)
{
@@ -2048,7 +2141,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_enter, ctx);
}
@@ -2092,7 +2185,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
if (flags & BPF_TRAMP_F_CALL_ORIG) {
im->ip_epilogue = ctx->ro_image + ctx->idx;
- emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_exit, ctx);
}
@@ -2176,12 +2269,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
bpf_prog_pack_free(image, size);
}
-void arch_protect_bpf_trampoline(void *image, unsigned int size)
-{
-}
-
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
{
+ return 0;
}
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
@@ -2464,6 +2554,39 @@ bool bpf_jit_supports_exceptions(void)
return true;
}
+bool bpf_jit_supports_arena(void)
+{
+ return true;
+}
+
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
+{
+ if (!in_arena)
+ return true;
+ switch (insn->code) {
+ case BPF_STX | BPF_ATOMIC | BPF_W:
+ case BPF_STX | BPF_ATOMIC | BPF_DW:
+ if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+ return false;
+ }
+ return true;
+}
+
+bool bpf_jit_supports_percpu_insn(void)
+{
+ return true;
+}
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+ switch (imm) {
+ case BPF_FUNC_get_smp_processor_id:
+ return true;
+ default:
+ return false;
+ }
+}
+
void bpf_jit_free(struct bpf_prog *prog)
{
if (prog->jited) {
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-29 03:35:32 +0000