diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 8053b24afc395..55ca49d183196 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -571,6 +571,7 @@ (0x54000001 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) #define PPC_RAW_RLWIMI(d, a, i, mb, me) (0x50000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) #define PPC_RAW_RLDICL(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb)) +#define PPC_RAW_RLDICL_DOT(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb) | 0x1) #define PPC_RAW_RLDICR(d, a, i, me) (0x78000004 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_ME64(me)) /* slwi = rlwinm Rx, Ry, n, 0, 31-n */ diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 4c26912c2e3c3..748e30e8b5b49 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -161,9 +161,11 @@ struct codegen_context { unsigned int seen; unsigned int idx; unsigned int stack_size; - int b2p[MAX_BPF_JIT_REG + 2]; + int b2p[MAX_BPF_JIT_REG + 3]; unsigned int exentry_idx; unsigned int alt_exit_addr; + u64 arena_vm_start; + u64 user_vm_start; }; #define bpf_to_ppc(r) (ctx->b2p[r]) @@ -201,7 +203,7 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, struct codegen_context *ctx, int insn_idx, - int jmp_off, int dst_reg); + int jmp_off, int dst_reg, u32 code); #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index c0684733e9d6a..88ad5ba7b87fd 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -204,6 +204,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) /* Make sure that the stack is quadword aligned. */ cgctx.stack_size = round_up(fp->aux->stack_depth, 16); + cgctx.arena_vm_start = bpf_arena_get_kern_vm_start(fp->aux->arena); + cgctx.user_vm_start = bpf_arena_get_user_vm_start(fp->aux->arena); /* Scouting faux-generate pass 0 */ if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) { @@ -326,7 +328,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) */ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, struct codegen_context *ctx, int insn_idx, int jmp_off, - int dst_reg) + int dst_reg, u32 code) { off_t offset; unsigned long pc; @@ -355,6 +357,9 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass (ctx->exentry_idx * BPF_FIXUP_LEN * 4); fixup[0] = PPC_RAW_LI(dst_reg, 0); + if (BPF_CLASS(code) == BPF_ST || BPF_CLASS(code) == BPF_STX) + fixup[0] = PPC_RAW_NOP(); + if (IS_ENABLED(CONFIG_PPC32)) fixup[1] = PPC_RAW_LI(dst_reg - 1, 0); /* clear higher 32-bit register too */ @@ -435,11 +440,32 @@ bool bpf_jit_supports_kfunc_call(void) return true; } +bool bpf_jit_supports_arena(void) +{ + return IS_ENABLED(CONFIG_PPC64); +} + bool bpf_jit_supports_far_kfunc_call(void) { return IS_ENABLED(CONFIG_PPC64); } +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_H: + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + return false; + return IS_ENABLED(CONFIG_PPC64); + } + return true; +} + void *arch_alloc_bpf_trampoline(unsigned int size) { return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns); @@ -579,7 +605,7 @@ static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_contex { if (IS_ENABLED(CONFIG_PPC64)) { /* See bpf_jit_stack_tailcallcnt() */ - int tailcallcnt_offset = 6 * 8; + int tailcallcnt_offset = 7 * 8; EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset)); EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset)); @@ -594,7 +620,7 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont { if (IS_ENABLED(CONFIG_PPC64)) { /* See bpf_jit_stack_tailcallcnt() */ - int tailcallcnt_offset = 6 * 8; + int tailcallcnt_offset = 7 * 8; EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset)); EMIT(PPC_RAW_STL(_R3, _R1, func_frame_offset - tailcallcnt_offset)); diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 0aace304dfe19..3087e744fb250 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -1087,7 +1087,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code } ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, insn_idx, - jmp_off, dst_reg); + jmp_off, dst_reg, code); if (ret) return ret; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 025524378443e..1fe37128c8764 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -25,18 +25,18 @@ * with our redzone usage. * * [ prev sp ] <------------- - * [ nv gpr save area ] 5*8 | + * [ nv gpr save area ] 6*8 | * [ tail_call_cnt ] 8 | - * [ local_tmp_var ] 16 | + * [ local_tmp_var ] 24 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- */ /* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (5*8) +#define BPF_PPC_STACK_SAVE (6*8) /* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 24 +#define BPF_PPC_STACK_LOCALS 32 /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) @@ -44,6 +44,7 @@ /* BPF register usage */ #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) +#define ARENA_VM_START (MAX_BPF_JIT_REG + 2) /* BPF to ppc register mappings */ void bpf_jit_init_reg_mapping(struct codegen_context *ctx) @@ -67,10 +68,12 @@ void bpf_jit_init_reg_mapping(struct codegen_context *ctx) ctx->b2p[BPF_REG_AX] = _R12; ctx->b2p[TMP_REG_1] = _R9; ctx->b2p[TMP_REG_2] = _R10; + /* non volatile register for kern_vm_start address */ + ctx->b2p[ARENA_VM_START] = _R26; } -/* PPC NVR range -- update this if we ever use NVRs below r27 */ -#define BPF_PPC_NVR_MIN _R27 +/* PPC NVR range -- update this if we ever use NVRs below r26 */ +#define BPF_PPC_NVR_MIN _R26 static inline bool bpf_has_stack_frame(struct codegen_context *ctx) { @@ -89,9 +92,9 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ nv gpr save area ] 5*8 + * [ nv gpr save area ] 6*8 * [ tail_call_cnt ] 8 - * [ local_tmp_var ] 16 + * [ local_tmp_var ] 24 * [ unused red zone ] 224 */ static int bpf_jit_stack_local(struct codegen_context *ctx) @@ -99,12 +102,12 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) if (bpf_has_stack_frame(ctx)) return STACK_FRAME_MIN_SIZE + ctx->stack_size; else - return -(BPF_PPC_STACK_SAVE + 24); + return -(BPF_PPC_STACK_SAVE + 32); } static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) { - return bpf_jit_stack_local(ctx) + 16; + return bpf_jit_stack_local(ctx) + 24; } static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) @@ -170,10 +173,17 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) if (bpf_is_seen_register(ctx, bpf_to_ppc(i))) EMIT(PPC_RAW_STD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i)))); + if (ctx->arena_vm_start) + EMIT(PPC_RAW_STD(bpf_to_ppc(ARENA_VM_START), _R1, + bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START)))); + /* Setup frame pointer to point to the bpf stack area */ if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP))) EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1, STACK_FRAME_MIN_SIZE + ctx->stack_size)); + + if (ctx->arena_vm_start) + PPC_LI64(bpf_to_ppc(ARENA_VM_START), ctx->arena_vm_start); } static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx) @@ -185,6 +195,10 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx if (bpf_is_seen_register(ctx, bpf_to_ppc(i))) EMIT(PPC_RAW_LD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i)))); + if (ctx->arena_vm_start) + EMIT(PPC_RAW_LD(bpf_to_ppc(ARENA_VM_START), _R1, + bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START)))); + /* Tear down our stack frame */ if (bpf_has_stack_frame(ctx)) { EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME + ctx->stack_size)); @@ -396,11 +410,11 @@ void bpf_stf_barrier(void); asm ( " .global bpf_stf_barrier ;" " bpf_stf_barrier: ;" -" std 21,-64(1) ;" -" std 22,-56(1) ;" +" std 21,-80(1) ;" +" std 22,-72(1) ;" " sync ;" -" ld 21,-64(1) ;" -" ld 22,-56(1) ;" +" ld 21,-80(1) ;" +" ld 22,-72(1) ;" " ori 31,31,0 ;" " .rept 14 ;" " b 1f ;" @@ -409,6 +423,141 @@ asm ( " blr ;" ); +static int bpf_jit_emit_atomic_ops(u32 *image, struct codegen_context *ctx, + const struct bpf_insn *insn, u32 *jmp_off, + u32 *tmp_idx, u32 *addrp) +{ + u32 tmp1_reg = bpf_to_ppc(TMP_REG_1); + u32 tmp2_reg = bpf_to_ppc(TMP_REG_2); + u32 size = BPF_SIZE(insn->code); + u32 src_reg = bpf_to_ppc(insn->src_reg); + u32 dst_reg = bpf_to_ppc(insn->dst_reg); + s32 imm = insn->imm; + + u32 save_reg = tmp2_reg; + u32 ret_reg = src_reg; + u32 fixup_idx; + + /* Get offset into TMP_REG_1 */ + EMIT(PPC_RAW_LI(tmp1_reg, insn->off)); + /* + * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' + * before and after the operation. + * + * This is a requirement in the Linux Kernel Memory Model. + * See __cmpxchg_u64() in asm/cmpxchg.h as an example. + */ + if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); + + *tmp_idx = ctx->idx; + + /* load value from memory into TMP_REG_2 */ + if (size == BPF_DW) + EMIT(PPC_RAW_LDARX(tmp2_reg, tmp1_reg, dst_reg, 0)); + else + EMIT(PPC_RAW_LWARX(tmp2_reg, tmp1_reg, dst_reg, 0)); + /* Save old value in _R0 */ + if (imm & BPF_FETCH) + EMIT(PPC_RAW_MR(_R0, tmp2_reg)); + + switch (imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_AND: + case BPF_AND | BPF_FETCH: + EMIT(PPC_RAW_AND(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_OR: + case BPF_OR | BPF_FETCH: + EMIT(PPC_RAW_OR(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + EMIT(PPC_RAW_XOR(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_CMPXCHG: + /* + * Return old value in BPF_REG_0 for BPF_CMPXCHG & + * in src_reg for other cases. + */ + ret_reg = bpf_to_ppc(BPF_REG_0); + + /* Compare with old value in BPF_R0 */ + if (size == BPF_DW) + EMIT(PPC_RAW_CMPD(bpf_to_ppc(BPF_REG_0), tmp2_reg)); + else + EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), tmp2_reg)); + /* Don't set if different from old value */ + PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4); + fallthrough; + case BPF_XCHG: + save_reg = src_reg; + break; + default: + return -EOPNOTSUPP; + } + + /* store new value */ + if (size == BPF_DW) + EMIT(PPC_RAW_STDCX(save_reg, tmp1_reg, dst_reg)); + else + EMIT(PPC_RAW_STWCX(save_reg, tmp1_reg, dst_reg)); + /* we're done if this succeeded */ + PPC_BCC_SHORT(COND_NE, *tmp_idx * 4); + fixup_idx = ctx->idx; + + if (imm & BPF_FETCH) { + /* Emit 'sync' to enforce full ordering */ + if (IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); + EMIT(PPC_RAW_MR(ret_reg, _R0)); + /* + * Skip unnecessary zero-extension for 32-bit cmpxchg. + * For context, see commit 39491867ace5. + */ + if (size != BPF_DW && imm == BPF_CMPXCHG && + insn_is_zext(insn + 1)) + *addrp = ctx->idx * 4; + } + + *jmp_off = (fixup_idx - *tmp_idx) * 4; + + return 0; +} + +static int bpf_jit_emit_probe_mem_store(struct codegen_context *ctx, u32 src_reg, s16 off, + u32 code, u32 *image) +{ + u32 tmp1_reg = bpf_to_ppc(TMP_REG_1); + u32 tmp2_reg = bpf_to_ppc(TMP_REG_2); + + switch (BPF_SIZE(code)) { + case BPF_B: + EMIT(PPC_RAW_STB(src_reg, tmp1_reg, off)); + break; + case BPF_H: + EMIT(PPC_RAW_STH(src_reg, tmp1_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_STW(src_reg, tmp1_reg, off)); + break; + case BPF_DW: + if (off % 4) { + EMIT(PPC_RAW_LI(tmp2_reg, off)); + EMIT(PPC_RAW_STDX(src_reg, tmp1_reg, tmp2_reg)); + } else { + EMIT(PPC_RAW_STD(src_reg, tmp1_reg, off)); + } + break; + default: + return -EINVAL; + } + return 0; +} + static int emit_atomic_ld_st(const struct bpf_insn insn, struct codegen_context *ctx, u32 *image) { u32 code = insn.code; @@ -494,7 +643,6 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code u32 size = BPF_SIZE(code); u32 tmp1_reg = bpf_to_ppc(TMP_REG_1); u32 tmp2_reg = bpf_to_ppc(TMP_REG_2); - u32 save_reg, ret_reg; s16 off = insn[i].off; s32 imm = insn[i].imm; bool func_addr_fixed; @@ -502,6 +650,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code u64 imm64; u32 true_cond; u32 tmp_idx; + u32 jmp_off; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -768,6 +917,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code */ case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */ case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ + + if (insn_is_cast_user(&insn[i])) { + EMIT(PPC_RAW_RLDICL_DOT(tmp1_reg, src_reg, 0, 32)); + PPC_LI64(dst_reg, (ctx->user_vm_start & 0xffffffff00000000UL)); + PPC_BCC_SHORT(COND_EQ, (ctx->idx + 2) * 4); + EMIT(PPC_RAW_OR(tmp1_reg, dst_reg, tmp1_reg)); + EMIT(PPC_RAW_MR(dst_reg, tmp1_reg)); + break; + } + if (imm == 1) { /* special mov32 for zext */ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31)); @@ -960,6 +1119,76 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code } break; + 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: + + EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START))); + + ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image); + if (ret) + return ret; + + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, + ctx->idx - 1, 4, -1, code); + if (ret) + return ret; + + break; + + 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: + + EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START))); + + if (BPF_SIZE(code) == BPF_W || BPF_SIZE(code) == BPF_DW) { + PPC_LI32(tmp2_reg, imm); + src_reg = tmp2_reg; + } else { + EMIT(PPC_RAW_LI(tmp2_reg, imm)); + src_reg = tmp2_reg; + } + + ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image); + if (ret) + return ret; + + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, + ctx->idx - 1, 4, -1, code); + if (ret) + return ret; + + break; + + /* + * BPF_STX PROBE_ATOMIC (arena atomic ops) + */ + case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, bpf_to_ppc(ARENA_VM_START))); + ret = bpf_jit_emit_atomic_ops(image, ctx, &insn[i], + &jmp_off, &tmp_idx, &addrs[i + 1]); + if (ret) { + if (ret == -EOPNOTSUPP) { + pr_err_ratelimited( + "eBPF filter atomic op code %02x (@%d) unsupported\n", + code, i); + } + return ret; + } + /* LDARX/LWARX should land here on exception. */ + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, + tmp_idx, jmp_off, dst_reg, code); + if (ret) + return ret; + + /* Retrieve the dst_reg */ + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, bpf_to_ppc(ARENA_VM_START))); + break; + /* * BPF_STX ATOMIC (atomic ops) */ @@ -982,93 +1211,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code return -EOPNOTSUPP; } - save_reg = tmp2_reg; - ret_reg = src_reg; - - /* Get offset into TMP_REG_1 */ - EMIT(PPC_RAW_LI(tmp1_reg, off)); - /* - * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' - * before and after the operation. - * - * This is a requirement in the Linux Kernel Memory Model. - * See __cmpxchg_u64() in asm/cmpxchg.h as an example. - */ - if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) - EMIT(PPC_RAW_SYNC()); - tmp_idx = ctx->idx * 4; - /* load value from memory into TMP_REG_2 */ - if (size == BPF_DW) - EMIT(PPC_RAW_LDARX(tmp2_reg, tmp1_reg, dst_reg, 0)); - else - EMIT(PPC_RAW_LWARX(tmp2_reg, tmp1_reg, dst_reg, 0)); - - /* Save old value in _R0 */ - if (imm & BPF_FETCH) - EMIT(PPC_RAW_MR(_R0, tmp2_reg)); - - switch (imm) { - case BPF_ADD: - case BPF_ADD | BPF_FETCH: - EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); - break; - case BPF_AND: - case BPF_AND | BPF_FETCH: - EMIT(PPC_RAW_AND(tmp2_reg, tmp2_reg, src_reg)); - break; - case BPF_OR: - case BPF_OR | BPF_FETCH: - EMIT(PPC_RAW_OR(tmp2_reg, tmp2_reg, src_reg)); - break; - case BPF_XOR: - case BPF_XOR | BPF_FETCH: - EMIT(PPC_RAW_XOR(tmp2_reg, tmp2_reg, src_reg)); - break; - case BPF_CMPXCHG: - /* - * Return old value in BPF_REG_0 for BPF_CMPXCHG & - * in src_reg for other cases. - */ - ret_reg = bpf_to_ppc(BPF_REG_0); - - /* Compare with old value in BPF_R0 */ - if (size == BPF_DW) - EMIT(PPC_RAW_CMPD(bpf_to_ppc(BPF_REG_0), tmp2_reg)); - else - EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), tmp2_reg)); - /* Don't set if different from old value */ - PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4); - fallthrough; - case BPF_XCHG: - save_reg = src_reg; - break; - default: - pr_err_ratelimited( - "eBPF filter atomic op code %02x (@%d) unsupported\n", - code, i); - return -EOPNOTSUPP; - } - - /* store new value */ - if (size == BPF_DW) - EMIT(PPC_RAW_STDCX(save_reg, tmp1_reg, dst_reg)); - else - EMIT(PPC_RAW_STWCX(save_reg, tmp1_reg, dst_reg)); - /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_NE, tmp_idx); - - if (imm & BPF_FETCH) { - /* Emit 'sync' to enforce full ordering */ - if (IS_ENABLED(CONFIG_SMP)) - EMIT(PPC_RAW_SYNC()); - EMIT(PPC_RAW_MR(ret_reg, _R0)); - /* - * Skip unnecessary zero-extension for 32-bit cmpxchg. - * For context, see commit 39491867ace5. - */ - if (size != BPF_DW && imm == BPF_CMPXCHG && - insn_is_zext(&insn[i + 1])) - addrs[++i] = ctx->idx * 4; + ret = bpf_jit_emit_atomic_ops(image, ctx, &insn[i], + &jmp_off, &tmp_idx, &addrs[i + 1]); + if (ret) { + if (ret == -EOPNOTSUPP) { + pr_err_ratelimited( + "eBPF filter atomic op code %02x (@%d) unsupported\n", + code, i); + } + return ret; } break; @@ -1112,9 +1263,10 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * Check if 'off' is word aligned for BPF_DW, because * we might generate two instructions. */ - if ((BPF_SIZE(code) == BPF_DW || - (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX)) && - (off & 3)) + if ((BPF_SIZE(code) == BPF_DW && (off & 3)) || + (BPF_SIZE(code) == BPF_B && + BPF_MODE(code) == BPF_PROBE_MEMSX) || + (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_MEMSX)) PPC_JMP((ctx->idx + 3) * 4); else PPC_JMP((ctx->idx + 2) * 4); @@ -1160,12 +1312,49 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (BPF_MODE(code) == BPF_PROBE_MEM) { ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, - ctx->idx - 1, 4, dst_reg); + ctx->idx - 1, 4, dst_reg, code); if (ret) return ret; } break; + /* dst = *(u64 *)(ul) (src + ARENA_VM_START + off) */ + 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: + + EMIT(PPC_RAW_ADD(tmp1_reg, src_reg, bpf_to_ppc(ARENA_VM_START))); + + switch (size) { + case BPF_B: + EMIT(PPC_RAW_LBZ(dst_reg, tmp1_reg, off)); + break; + case BPF_H: + EMIT(PPC_RAW_LHZ(dst_reg, tmp1_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_LWZ(dst_reg, tmp1_reg, off)); + break; + case BPF_DW: + if (off % 4) { + EMIT(PPC_RAW_LI(tmp2_reg, off)); + EMIT(PPC_RAW_LDX(dst_reg, tmp1_reg, tmp2_reg)); + } else { + EMIT(PPC_RAW_LD(dst_reg, tmp1_reg, off)); + } + break; + } + + if (size != BPF_DW && insn_is_zext(&insn[i + 1])) + addrs[++i] = ctx->idx * 4; + + ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, + ctx->idx - 1, 4, dst_reg, code); + if (ret) + return ret; + break; + /* * Doubleword load * 16 byte instruction that uses two 'struct bpf_insn' diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c index 0223fce4db2bc..1ec1ca9878930 100644 --- a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c @@ -40,8 +40,13 @@ static void *spin_lock_thread(void *arg) err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run err"); + + if (topts.retval == -EOPNOTSUPP) + goto end; + ASSERT_EQ((int)topts.retval, 0, "test_run retval"); +end: pthread_exit(arg); } @@ -63,6 +68,7 @@ static void test_arena_spin_lock_size(int size) skel = arena_spin_lock__open_and_load(); if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load")) return; + if (skel->data->test_skip == 2) { test__skip(); goto end; @@ -86,6 +92,13 @@ static void test_arena_spin_lock_size(int size) goto end_barrier; } + if (skel->data->test_skip == 2) { + printf("%s:SKIP: %d CPUs exceed the maximum supported by arena spinlock\n", + __func__, get_nprocs()); + test__skip(); + goto end_barrier; + } + ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value"); end_barrier: diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c index c4500c37f85e0..a475b974438ef 100644 --- a/tools/testing/selftests/bpf/progs/arena_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c @@ -37,8 +37,11 @@ int prog(void *ctx) #if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) unsigned long flags; - if ((ret = arena_spin_lock_irqsave(&lock, flags))) + if ((ret = arena_spin_lock_irqsave(&lock, flags))) { + if (ret == -EOPNOTSUPP) + test_skip = 2; return ret; + } if (counter != limit) counter++; bpf_repeat(cs_count);