From patchwork Thu Jan 27 07:53:21 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hou Tao X-Patchwork-Id: 12728160 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id D6BCEC4332F for ; Fri, 28 Jan 2022 09:19:56 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1347575AbiA1JT4 (ORCPT ); Fri, 28 Jan 2022 04:19:56 -0500 Received: from szxga02-in.huawei.com ([45.249.212.188]:17827 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234750AbiA1JTz (ORCPT ); Fri, 28 Jan 2022 04:19:55 -0500 Received: from dggpeml500025.china.huawei.com (unknown [172.30.72.57]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4JlX1z33nWz9sc4; Fri, 28 Jan 2022 17:18:31 +0800 (CST) Received: from huawei.com (10.175.124.27) by dggpeml500025.china.huawei.com (7.185.36.35) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.21; Fri, 28 Jan 2022 17:19:38 +0800 From: Hou Tao To: Alexei Starovoitov CC: Martin KaFai Lau , Yonghong Song , Daniel Borkmann , Andrii Nakryiko , Song Liu , "David S . Miller" , John Fastabend , , , , Zi Shen Lim , Catalin Marinas , Will Deacon , Julien Thierry , Mark Rutland , Ard Biesheuvel , Subject: [PATCH bpf-next v2 1/2] selftests/bpf: use raw_tp program for atomic test Date: Thu, 27 Jan 2022 15:53:21 +0800 Message-ID: <20220127075322.675323-2-houtao1@huawei.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220127075322.675323-1-houtao1@huawei.com> References: <20220127075322.675323-1-houtao1@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.175.124.27] X-ClientProxiedBy: dggems702-chm.china.huawei.com (10.3.19.179) To dggpeml500025.china.huawei.com (7.185.36.35) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Now atomic tests will attach fentry program and run it through bpf_prog_test_run(), but attaching fentry program depends on bpf trampoline which is only available under x86-64. Considering many archs have atomic support, using raw_tp program instead. Signed-off-by: Hou Tao Acked-by: Andrii Nakryiko --- .../selftests/bpf/prog_tests/atomics.c | 121 ++++++------------ tools/testing/selftests/bpf/progs/atomics.c | 28 ++-- 2 files changed, 50 insertions(+), 99 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 86b7d5d84eec..8e05a703a62b 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -8,18 +8,14 @@ static void test_add(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__add__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(add)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.add.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run add") || + !ASSERT_OK(retval, "test_run add ret")) + return; ASSERT_EQ(skel->data->add64_value, 3, "add64_value"); ASSERT_EQ(skel->bss->add64_result, 1, "add64_result"); @@ -31,28 +27,20 @@ static void test_add(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->add_stack_result, 1, "add_stack_result"); ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value"); - -cleanup: - close(link_fd); } static void test_sub(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__sub__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(sub)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.sub.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run sub", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run sub") || + !ASSERT_OK(retval, "test_run sub ret")) + return; ASSERT_EQ(skel->data->sub64_value, -1, "sub64_value"); ASSERT_EQ(skel->bss->sub64_result, 1, "sub64_result"); @@ -64,27 +52,20 @@ static void test_sub(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->sub_stack_result, 1, "sub_stack_result"); ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value"); - -cleanup: - close(link_fd); } static void test_and(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__and__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(and)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.and.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run and", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run and") || + !ASSERT_OK(retval, "test_run and ret")) + return; ASSERT_EQ(skel->data->and64_value, 0x010ull << 32, "and64_value"); ASSERT_EQ(skel->bss->and64_result, 0x110ull << 32, "and64_result"); @@ -93,27 +74,20 @@ static void test_and(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->and32_result, 0x110, "and32_result"); ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value"); -cleanup: - close(link_fd); } static void test_or(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__or__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(or)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.or.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run or", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run or") || + !ASSERT_OK(retval, "test_run or ret")) + return; ASSERT_EQ(skel->data->or64_value, 0x111ull << 32, "or64_value"); ASSERT_EQ(skel->bss->or64_result, 0x110ull << 32, "or64_result"); @@ -122,26 +96,20 @@ static void test_or(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->or32_result, 0x110, "or32_result"); ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value"); -cleanup: - close(link_fd); } static void test_xor(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xor__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xor)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xor.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xor", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run xor") || + !ASSERT_OK(retval, "test_run xor ret")) + return; ASSERT_EQ(skel->data->xor64_value, 0x101ull << 32, "xor64_value"); ASSERT_EQ(skel->bss->xor64_result, 0x110ull << 32, "xor64_result"); @@ -150,26 +118,20 @@ static void test_xor(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->xor32_result, 0x110, "xor32_result"); ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value"); -cleanup: - close(link_fd); } static void test_cmpxchg(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__cmpxchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.cmpxchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run cmpxchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run cmpxchg") || + !ASSERT_OK(retval, "test_run cmpxchg ret")) + return; ASSERT_EQ(skel->data->cmpxchg64_value, 2, "cmpxchg64_value"); ASSERT_EQ(skel->bss->cmpxchg64_result_fail, 1, "cmpxchg_result_fail"); @@ -178,45 +140,34 @@ static void test_cmpxchg(struct atomics_lskel *skel) ASSERT_EQ(skel->data->cmpxchg32_value, 2, "lcmpxchg32_value"); ASSERT_EQ(skel->bss->cmpxchg32_result_fail, 1, "cmpxchg_result_fail"); ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed"); - -cleanup: - close(link_fd); } static void test_xchg(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) - return; + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + err = bpf_prog_test_run(prog_fd, 0, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + if (!ASSERT_OK(err, "test_run xchg") || + !ASSERT_OK(retval, "test_run xchg ret")) + return; ASSERT_EQ(skel->data->xchg64_value, 2, "xchg64_value"); ASSERT_EQ(skel->bss->xchg64_result, 1, "xchg64_result"); ASSERT_EQ(skel->data->xchg32_value, 2, "xchg32_value"); ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result"); - -cleanup: - close(link_fd); } void test_atomics(void) { struct atomics_lskel *skel; - __u32 duration = 0; skel = atomics_lskel__open_and_load(); - if (CHECK(!skel, "skel_load", "atomics skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "atomics skeleton load")) return; if (skel->data->skip_tests) { diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c index 16e57313204a..f89c7f0cc53b 100644 --- a/tools/testing/selftests/bpf/progs/atomics.c +++ b/tools/testing/selftests/bpf/progs/atomics.c @@ -20,8 +20,8 @@ __u64 add_stack_value_copy = 0; __u64 add_stack_result = 0; __u64 add_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(add, int a) +SEC("raw_tp/sys_enter") +int add(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -46,8 +46,8 @@ __s64 sub_stack_value_copy = 0; __s64 sub_stack_result = 0; __s64 sub_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(sub, int a) +SEC("raw_tp/sys_enter") +int sub(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -70,8 +70,8 @@ __u32 and32_value = 0x110; __u32 and32_result = 0; __u64 and_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(and, int a) +SEC("raw_tp/sys_enter") +int and(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -91,8 +91,8 @@ __u32 or32_value = 0x110; __u32 or32_result = 0; __u64 or_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(or, int a) +SEC("raw_tp/sys_enter") +int or(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -111,8 +111,8 @@ __u32 xor32_value = 0x110; __u32 xor32_result = 0; __u64 xor_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xor, int a) +SEC("raw_tp/sys_enter") +int xor(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -132,8 +132,8 @@ __u32 cmpxchg32_value = 1; __u32 cmpxchg32_result_fail = 0; __u32 cmpxchg32_result_succeed = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(cmpxchg, int a) +SEC("raw_tp/sys_enter") +int cmpxchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -153,8 +153,8 @@ __u64 xchg64_result = 0; __u32 xchg32_value = 1; __u32 xchg32_result = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xchg, int a) +SEC("raw_tp/sys_enter") +int xchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; From patchwork Thu Jan 27 07:53:22 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hou Tao X-Patchwork-Id: 12728161 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4F0C3C43217 for ; Fri, 28 Jan 2022 09:19:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1347577AbiA1JT4 (ORCPT ); Fri, 28 Jan 2022 04:19:56 -0500 Received: from szxga02-in.huawei.com ([45.249.212.188]:17828 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1347444AbiA1JTz (ORCPT ); Fri, 28 Jan 2022 04:19:55 -0500 Received: from dggpeml500025.china.huawei.com (unknown [172.30.72.57]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4JlX1z3b5bz9sSm; Fri, 28 Jan 2022 17:18:31 +0800 (CST) Received: from huawei.com (10.175.124.27) by dggpeml500025.china.huawei.com (7.185.36.35) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.21; Fri, 28 Jan 2022 17:19:39 +0800 From: Hou Tao To: Alexei Starovoitov CC: Martin KaFai Lau , Yonghong Song , Daniel Borkmann , Andrii Nakryiko , Song Liu , "David S . Miller" , John Fastabend , , , , Zi Shen Lim , Catalin Marinas , Will Deacon , Julien Thierry , Mark Rutland , Ard Biesheuvel , Subject: [PATCH bpf-next v2 2/2] arm64, bpf: support more atomic operations Date: Thu, 27 Jan 2022 15:53:22 +0800 Message-ID: <20220127075322.675323-3-houtao1@huawei.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220127075322.675323-1-houtao1@huawei.com> References: <20220127075322.675323-1-houtao1@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.175.124.27] X-ClientProxiedBy: dggems702-chm.china.huawei.com (10.3.19.179) To dggpeml500025.china.huawei.com (7.185.36.35) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Atomics for eBPF patch series adds support for atomic[64]_fetch_add, atomic[64]_[fetch_]{and,or,xor} and atomic[64]_{xchg|cmpxchg}, but it only add support for x86-64, so support these atomic operations for arm64 as well. Basically the implementation procedure is almost mechanical translation of code snippets in atomic_ll_sc.h & atomic_lse.h & cmpxchg.h located under arch/arm64/include/asm. An extra temporary register is needed for (BPF_ADD | BPF_FETCH) to save the value of src register, instead of adding TMP_REG_4 just use BPF_REG_AX instead. For cpus_have_cap(ARM64_HAS_LSE_ATOMICS) case and no-LSE-ATOMICS case, both ./test_verifier and "./test_progs -t atomic" are exercised and passed correspondingly. Signed-off-by: Hou Tao Acked-by: John Fastabend --- arch/arm64/include/asm/insn.h | 45 +++++-- arch/arm64/lib/insn.c | 155 +++++++++++++++++++++--- arch/arm64/net/bpf_jit.h | 43 ++++++- arch/arm64/net/bpf_jit_comp.c | 216 +++++++++++++++++++++++++++------- 4 files changed, 394 insertions(+), 65 deletions(-) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 6b776c8667b2..1416d636f1af 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -280,6 +280,23 @@ enum aarch64_insn_adr_type { AARCH64_INSN_ADR_TYPE_ADR, }; +enum aarch64_insn_mem_atomic_op { + AARCH64_INSN_MEM_ATOMIC_ADD, + AARCH64_INSN_MEM_ATOMIC_BIC, + AARCH64_INSN_MEM_ATOMIC_EOR, + AARCH64_INSN_MEM_ATOMIC_ORR, + AARCH64_INSN_MEM_ATOMIC_SWP, +}; + +enum aarch64_insn_mem_order_type { + AARCH64_INSN_MEM_ORDER_NONE, + AARCH64_INSN_MEM_ORDER_LOAD_ACQ_STORE_REL, +}; + +enum aarch64_insn_mb_type { + AARCH64_INSN_MB_ISH, +}; + #define __AARCH64_INSN_FUNCS(abbr, mask, val) \ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ { \ @@ -303,6 +320,11 @@ __AARCH64_INSN_FUNCS(store_post, 0x3FE00C00, 0x38000400) __AARCH64_INSN_FUNCS(load_post, 0x3FE00C00, 0x38400400) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) __AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) +__AARCH64_INSN_FUNCS(ldclr, 0x3F20FC00, 0x38201000) +__AARCH64_INSN_FUNCS(ldeor, 0x3F20FC00, 0x38202000) +__AARCH64_INSN_FUNCS(ldset, 0x3F20FC00, 0x38203000) +__AARCH64_INSN_FUNCS(swp, 0x3F20FC00, 0x38208000) +__AARCH64_INSN_FUNCS(cas, 0x3FA07C00, 0x08A07C00) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) @@ -474,13 +496,21 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); -u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, - enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size); -u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size); +u32 aarch64_insn_gen_store_release_ex(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + enum aarch64_insn_register state, + enum aarch64_insn_size_type size); +u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_atomic_op op, + enum aarch64_insn_mem_order_type order); +u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_order_type order); u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, @@ -541,6 +571,7 @@ u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, enum aarch64_insn_prfm_policy policy); +u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); s32 aarch64_get_branch_offset(u32 insn); u32 aarch64_set_branch_offset(u32 insn, s32 offset); diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index fccfe363e567..2a7dde58c44b 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -328,6 +328,29 @@ static u32 aarch64_insn_encode_ldst_size(enum aarch64_insn_size_type type, return insn; } +static u32 aarch64_insn_encode_ldst_order(enum aarch64_insn_mem_order_type type, + u32 insn) +{ + u32 order; + + switch (type) { + case AARCH64_INSN_MEM_ORDER_NONE: + order = 0; + break; + case AARCH64_INSN_MEM_ORDER_LOAD_ACQ_STORE_REL: + order = 3; + break; + default: + pr_err("%s: unknown mem order %d\n", __func__, type); + return AARCH64_BREAK_FAULT; + } + + insn &= ~GENMASK(23, 22); + insn |= order << 22; + + return insn; +} + static inline long branch_imm_common(unsigned long pc, unsigned long addr, long range) { @@ -603,12 +626,49 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, state); } -u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, - enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size) +u32 aarch64_insn_gen_store_release_ex(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + enum aarch64_insn_register state, + enum aarch64_insn_size_type size) +{ + u32 insn = aarch64_insn_gen_load_store_ex(reg, base, state, size, + AARCH64_INSN_LDST_STORE_EX); + + if (insn == AARCH64_BREAK_FAULT) + return insn; + + return insn | BIT(15); +} + +u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_atomic_op op, + enum aarch64_insn_mem_order_type order) { - u32 insn = aarch64_insn_get_ldadd_value(); + u32 insn; + + switch (op) { + case AARCH64_INSN_MEM_ATOMIC_ADD: + insn = aarch64_insn_get_ldadd_value(); + break; + case AARCH64_INSN_MEM_ATOMIC_BIC: + insn = aarch64_insn_get_ldclr_value(); + break; + case AARCH64_INSN_MEM_ATOMIC_EOR: + insn = aarch64_insn_get_ldeor_value(); + break; + case AARCH64_INSN_MEM_ATOMIC_ORR: + insn = aarch64_insn_get_ldset_value(); + break; + case AARCH64_INSN_MEM_ATOMIC_SWP: + insn = aarch64_insn_get_swp_value(); + break; + default: + pr_err("%s: unimplemented mem atomic op %d\n", __func__, op); + return AARCH64_BREAK_FAULT; + } switch (size) { case AARCH64_INSN_SIZE_32: @@ -621,6 +681,8 @@ u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, insn = aarch64_insn_encode_ldst_size(size, insn); + insn = aarch64_insn_encode_ldst_order(order, insn); + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, result); @@ -631,16 +693,60 @@ u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, value); } -u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size) +static u32 aarch64_insn_encode_cas_order(enum aarch64_insn_mem_order_type type, + u32 insn) { - /* - * STADD is simply encoded as an alias for LDADD with XZR as - * the destination register. - */ - return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address, - value, size); + u32 order; + + switch (type) { + case AARCH64_INSN_MEM_ORDER_NONE: + order = 0; + break; + case AARCH64_INSN_MEM_ORDER_LOAD_ACQ_STORE_REL: + order = BIT(15) | BIT(22); + break; + default: + pr_err("%s: unknown mem order %d\n", __func__, type); + return AARCH64_BREAK_FAULT; + } + + insn &= ~(BIT(15) | BIT(22)); + insn |= order; + + return insn; +} + +u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_order_type order) +{ + u32 insn; + + switch (size) { + case AARCH64_INSN_SIZE_32: + case AARCH64_INSN_SIZE_64: + break; + default: + pr_err("%s: unimplemented size encoding %d\n", __func__, size); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_get_cas_value(); + + insn = aarch64_insn_encode_ldst_size(size, insn); + + insn = aarch64_insn_encode_cas_order(order, insn); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, + result); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, + address); + + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, + value); } static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type, @@ -1456,3 +1562,24 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm); } + +u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) +{ + u32 opt; + u32 insn; + + switch (type) { + case AARCH64_INSN_MB_ISH: + opt = 0xb; + break; + default: + pr_err("%s: unknown dmb type %d\n", __func__, type); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_get_dmb_value(); + insn &= ~GENMASK(11, 8); + insn |= (opt << 8); + + return insn; +} diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index cc0cf0f5c7c3..308f96587861 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -88,10 +88,41 @@ /* [Rn] = Rt; (atomic) Rs = [state] */ #define A64_STXR(sf, Rt, Rn, Rs) \ A64_LSX(sf, Rt, Rn, Rs, STORE_EX) +/* smp_mb(); [Rn] = Rt; (atomic) Rs = [state] */ +#define A64_STLXR(sf, Rt, Rn, Rs) \ + aarch64_insn_gen_store_release_ex(Rt, Rn, Rs, A64_SIZE(sf)) -/* LSE atomics */ -#define A64_STADD(sf, Rn, Rs) \ - aarch64_insn_gen_stadd(Rn, Rs, A64_SIZE(sf)) +/* + * LSE atomics + * + * ST{ADD,CLR,SET,EOR} is simply encoded as an alias for + * LDD{ADD,CLR,SET,EOR} with XZR as the destination register. + */ +#define A64_ST_OP(sf, Rn, Rs, op) \ + aarch64_insn_gen_atomic_ld_op(A64_ZR, Rn, Rs, \ + A64_SIZE(sf), AARCH64_INSN_MEM_ATOMIC_##op, \ + AARCH64_INSN_MEM_ORDER_NONE) +/* [Rn] = Rs */ +#define A64_STADD(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, ADD) +#define A64_STCLR(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, BIC) +#define A64_STEOR(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, EOR) +#define A64_STSET(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, ORR) + +#define A64_LD_OP_AL(sf, Rt, Rn, Rs, op) \ + aarch64_insn_gen_atomic_ld_op(Rt, Rn, Rs, \ + A64_SIZE(sf), AARCH64_INSN_MEM_ATOMIC_##op, \ + AARCH64_INSN_MEM_ORDER_LOAD_ACQ_STORE_REL) +/* Rt = [Rn]; [Rn] = Rs */ +#define A64_LDADDAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, ADD) +#define A64_LDCLRAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, BIC) +#define A64_LDEORAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, EOR) +#define A64_LDSETAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, ORR) +/* Rt = [Rn]; [Rn] = Rs */ +#define A64_SWPAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, SWP) +/* Rs = CAS(Rn, Rs, Rt) */ +#define A64_CASAL(sf, Rt, Rn, Rs) \ + aarch64_insn_gen_cas(Rt, Rn, Rs, A64_SIZE(sf), \ + AARCH64_INSN_MEM_ORDER_LOAD_ACQ_STORE_REL) /* Add/subtract (immediate) */ #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \ @@ -196,6 +227,9 @@ #define A64_ANDS(sf, Rd, Rn, Rm) A64_LOGIC_SREG(sf, Rd, Rn, Rm, AND_SETFLAGS) /* Rn & Rm; set condition flags */ #define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm) +/* Rd = ~Rm (alias of ORN with A64_ZR as Rn) */ +#define A64_MVN(sf, Rd, Rm) \ + A64_LOGIC_SREG(sf, Rd, A64_ZR, Rm, ORN) /* Logical (immediate) */ #define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \ @@ -219,4 +253,7 @@ #define A64_BTI_J A64_HINT(AARCH64_INSN_HINT_BTIJ) #define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC) +/* DMB */ +#define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 3c2f91b8b00b..e60c464004c2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -29,6 +29,17 @@ #define TCALL_CNT (MAX_BPF_JIT_REG + 2) #define TMP_REG_3 (MAX_BPF_JIT_REG + 3) +#define check_imm(bits, imm) do { \ + if ((((imm) > 0) && ((imm) >> (bits))) || \ + (((imm) < 0) && (~(imm) >> (bits)))) { \ + pr_info("[%2d] imm=%d(0x%x) out of range\n", \ + i, imm, imm); \ + return -EINVAL; \ + } \ +} while (0) +#define check_imm19(imm) check_imm(19, imm) +#define check_imm26(imm) check_imm(26, imm) + /* Map BPF registers to A64 registers */ static const int bpf2a64[] = { /* return value from in-kernel function, and exit value from eBPF */ @@ -332,6 +343,163 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) #undef jmp_offset } +static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) +{ + const u8 code = insn->code; + 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 s16 off = insn->off; + u8 reg; + + if (!off) { + reg = dst; + } else { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + + switch (insn->imm) { + /* lock *(u32/u64 *)(dst_reg + off) = src_reg */ + case BPF_ADD: + emit(A64_STADD(isdw, reg, src), ctx); + break; + case BPF_AND: + emit(A64_MVN(isdw, tmp2, src), ctx); + emit(A64_STCLR(isdw, reg, tmp2), ctx); + break; + case BPF_OR: + emit(A64_STSET(isdw, reg, src), ctx); + break; + case BPF_XOR: + emit(A64_STEOR(isdw, reg, src), ctx); + break; + /* src_reg = atomic_fetch_add(dst_reg + off, src_reg) */ + case BPF_ADD | BPF_FETCH: + emit(A64_LDADDAL(isdw, src, reg, src), ctx); + break; + case BPF_AND | BPF_FETCH: + emit(A64_MVN(isdw, tmp2, src), ctx); + emit(A64_LDCLRAL(isdw, src, reg, tmp2), ctx); + break; + case BPF_OR | BPF_FETCH: + emit(A64_LDSETAL(isdw, src, reg, src), ctx); + break; + case BPF_XOR | BPF_FETCH: + emit(A64_LDEORAL(isdw, src, reg, src), ctx); + break; + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + case BPF_XCHG: + emit(A64_SWPAL(isdw, src, reg, src), ctx); + break; + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + case BPF_CMPXCHG: + emit(A64_CASAL(isdw, src, reg, bpf2a64[BPF_REG_0]), ctx); + break; + default: + pr_err_once("unknown atomic op code %02x\n", insn->imm); + return -EINVAL; + } + + return 0; +} + +static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) +{ + const u8 code = insn->code; + 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 u8 tmp3 = bpf2a64[TMP_REG_3]; + const int i = insn - ctx->prog->insnsi; + const s32 imm = insn->imm; + const s16 off = insn->off; + const bool isdw = BPF_SIZE(code) == BPF_DW; + u8 reg; + s32 jmp_offset; + + if (!off) { + reg = dst; + } else { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + + if (imm == BPF_ADD || imm == BPF_AND || + imm == BPF_OR || imm == BPF_XOR) { + /* lock *(u32/u64 *)(dst_reg + off) = src_reg */ + emit(A64_LDXR(isdw, tmp2, reg), ctx); + if (imm == BPF_ADD) + emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); + else if (imm == BPF_AND) + emit(A64_AND(isdw, tmp2, tmp2, src), ctx); + else if (imm == BPF_OR) + emit(A64_ORR(isdw, tmp2, tmp2, src), ctx); + else + emit(A64_EOR(isdw, tmp2, tmp2, src), ctx); + emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -3; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + } else if (imm == (BPF_ADD | BPF_FETCH) || + imm == (BPF_AND | BPF_FETCH) || + imm == (BPF_OR | BPF_FETCH) || + imm == (BPF_XOR | BPF_FETCH)) { + /* src_reg = atomic_fetch_add(dst_reg + off, src_reg) */ + const u8 ax = bpf2a64[BPF_REG_AX]; + + emit(A64_MOV(isdw, ax, src), ctx); + emit(A64_LDXR(isdw, src, reg), ctx); + if (imm == (BPF_ADD | BPF_FETCH)) + emit(A64_ADD(isdw, tmp2, src, ax), ctx); + else if (imm == (BPF_AND | BPF_FETCH)) + emit(A64_AND(isdw, tmp2, src, ax), ctx); + else if (imm == (BPF_OR | BPF_FETCH)) + emit(A64_ORR(isdw, tmp2, src, ax), ctx); + else + emit(A64_EOR(isdw, tmp2, src, ax), ctx); + emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -3; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + emit(A64_DMB_ISH, ctx); + } else if (imm == BPF_XCHG) { + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + emit(A64_MOV(isdw, tmp2, src), ctx); + emit(A64_LDXR(isdw, src, reg), ctx); + emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -2; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + emit(A64_DMB_ISH, ctx); + } else if (imm == BPF_CMPXCHG) { + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + const u8 r0 = bpf2a64[BPF_REG_0]; + + emit(A64_MOV(isdw, tmp2, r0), ctx); + emit(A64_LDXR(isdw, r0, reg), ctx); + emit(A64_EOR(isdw, tmp3, r0, tmp2), ctx); + jmp_offset = 4; + check_imm19(jmp_offset); + emit(A64_CBNZ(isdw, tmp3, jmp_offset), ctx); + emit(A64_STLXR(isdw, src, reg, tmp3), ctx); + jmp_offset = -4; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + emit(A64_DMB_ISH, ctx); + } else { + pr_err_once("unknown atomic op code %02x\n", imm); + return -EINVAL; + } + + return 0; +} + static void build_epilogue(struct jit_ctx *ctx) { const u8 r0 = bpf2a64[BPF_REG_0]; @@ -437,29 +605,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, const u8 src = bpf2a64[insn->src_reg]; const u8 tmp = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; - const u8 tmp3 = bpf2a64[TMP_REG_3]; const s16 off = insn->off; const s32 imm = insn->imm; const int i = insn - ctx->prog->insnsi; const bool is64 = BPF_CLASS(code) == BPF_ALU64 || BPF_CLASS(code) == BPF_JMP; - const bool isdw = BPF_SIZE(code) == BPF_DW; - u8 jmp_cond, reg; + u8 jmp_cond; s32 jmp_offset; u32 a64_insn; int ret; -#define check_imm(bits, imm) do { \ - if ((((imm) > 0) && ((imm) >> (bits))) || \ - (((imm) < 0) && (~(imm) >> (bits)))) { \ - pr_info("[%2d] imm=%d(0x%x) out of range\n", \ - i, imm, imm); \ - return -EINVAL; \ - } \ -} while (0) -#define check_imm19(imm) check_imm(19, imm) -#define check_imm26(imm) check_imm(26, imm) - switch (code) { /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: @@ -894,33 +1049,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: - if (insn->imm != BPF_ADD) { - pr_err_once("unknown atomic op code %02x\n", insn->imm); - return -EINVAL; - } - - /* STX XADD: lock *(u32 *)(dst + off) += src - * and - * STX XADD: lock *(u64 *)(dst + off) += src - */ - - if (!off) { - reg = dst; - } else { - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - reg = tmp; - } - if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) { - emit(A64_STADD(isdw, reg, src), ctx); - } else { - emit(A64_LDXR(isdw, tmp2, reg), ctx); - emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); - emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx); - jmp_offset = -3; - check_imm19(jmp_offset); - emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); - } + 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; break; default: