From 339af577ec05c8fc0b96f23579614ae853d913ab Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Mon, 25 Mar 2024 15:07:15 +0000 Subject: [PATCH 1/2] bpf: Add arm64 JIT support for PROBE_MEM32 pseudo instructions. Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW] instructions. They are similar to PROBE_MEM instructions with the following differences: - PROBE_MEM32 supports store. - PROBE_MEM32 relies on the verifier to clear upper 32-bit of the src/dst register - PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in R28 in the prologue). Due to bpf_arena constructions such R28 + reg + off16 access is guaranteed to be within arena virtual range, so no address check at run-time. - PROBE_MEM32 allows STX and ST. If they fault the store is a nop. When LDX faults the destination register is zeroed. To support these on arm64, we do tmp2 = R28 + src/dst reg and then use tmp2 as the new src/dst register. This allows us to reuse most of the code for normal [LDX | STX | ST]. Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20240325150716.4387-2-puranjay12@gmail.com Signed-off-by: Alexei Starovoitov --- arch/arm64/net/bpf_jit_comp.c | 70 ++++++++++++++++++++++++++++++----- 1 file changed, 60 insertions(+), 10 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 82d6c562e8c7..c6210b150b6a 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 { @@ -295,7 +298,7 @@ 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 +309,7 @@ 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 +415,10 @@ 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; } @@ -738,6 +746,7 @@ 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 +754,8 @@ 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 +775,8 @@ 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) return 0; if (!ctx->prog->aux->extable || @@ -810,6 +821,9 @@ 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 +843,13 @@ 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; @@ -1237,7 +1252,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, 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 +1345,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, 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 +1396,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, } break; } + + ret = add_exception_handler(insn, ctx, dst); + if (ret) + return ret; break; /* STX: *(size *)(dst + off) = src */ @@ -1372,7 +1407,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, 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 { @@ -1413,6 +1456,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, } break; } + + ret = add_exception_handler(insn, ctx, dst); + if (ret) + return ret; break; case BPF_STX | BPF_ATOMIC | BPF_W: @@ -1594,6 +1641,7 @@ 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 +1659,7 @@ 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); @@ -1648,7 +1697,8 @@ 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 +1746,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) 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; From 4dd31243e30843d5f63bccfb0369146e4de1a130 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Mon, 25 Mar 2024 15:07:16 +0000 Subject: [PATCH 2/2] bpf: Add arm64 JIT support for bpf_addr_space_cast instruction. LLVM generates bpf_addr_space_cast instruction while translating pointers between native (zero) address space and __attribute__((address_space(N))). The addr_space=0 is reserved as bpf_arena address space. rY = addr_space_cast(rX, 0, 1) is processed by the verifier and converted to normal 32-bit move: wX = wY. rY = addr_space_cast(rX, 1, 0) : used to convert a bpf arena pointer to a pointer in the userspace vma. This has to be converted by the JIT. Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20240325150716.4387-3-puranjay12@gmail.com Signed-off-by: Alexei Starovoitov --- arch/arm64/net/bpf_jit_comp.c | 16 ++++++++++++++++ tools/testing/selftests/bpf/DENYLIST.aarch64 | 2 -- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c6210b150b6a..76b91f36c729 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -82,6 +82,7 @@ struct jit_ctx { __le32 *ro_image; u32 stack_size; int fpb_offset; + u64 user_vm_start; }; struct bpf_plt { @@ -868,6 +869,15 @@ 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; + } switch (insn->off) { case 0: emit(A64_MOV(is64, dst, src), ctx); @@ -1690,6 +1700,7 @@ 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. @@ -2511,6 +2522,11 @@ bool bpf_jit_supports_exceptions(void) return true; } +bool bpf_jit_supports_arena(void) +{ + return true; +} + void bpf_jit_free(struct bpf_prog *prog) { if (prog->jited) { diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index d8ade15e2789..0445ac38bc07 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -10,5 +10,3 @@ fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_mu fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 missed/kprobe_recursion # missed_kprobe_recursion__attach unexpected error: -95 (errno 95) -verifier_arena # JIT does not support arena -arena_htab # JIT does not support arena