From 335ff4990cf3bfa42d8846f9b3d8c09456f51801 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:03 -0700 Subject: [PATCH 01/85] bpf: Merge printk and seq_printf VARARG max macros MAX_SNPRINTF_VARARGS and MAX_SEQ_PRINTF_VARARGS are used by bpf helpers bpf_snprintf and bpf_seq_printf to limit their varargs. Both call into bpf_bprintf_prepare for print formatting logic and have convenience macros in libbpf (BPF_SNPRINTF, BPF_SEQ_PRINTF) which use the same helper macros to convert varargs to a byte array. Changing shared functionality to support more varargs for either bpf helper would affect the other as well, so let's combine the _VARARGS macros to make this more obvious. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-2-davemarchevsky@fb.com --- include/linux/bpf.h | 2 ++ kernel/bpf/helpers.c | 4 +--- kernel/trace/bpf_trace.c | 4 +--- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f4c16f19f83e..be8d57e6e78a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2216,6 +2216,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); +#define MAX_BPRINTF_VARARGS 12 + int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 **bin_buf, u32 num_args); void bpf_bprintf_cleanup(void); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9aabf84afd4b..8f9f392c1322 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -979,15 +979,13 @@ out: return err; } -#define MAX_SNPRINTF_VARARGS 12 - BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, const void *, data, u32, data_len) { int err, num_args; u32 *bin_args; - if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 || + if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 067e88c3d2ee..4ec779fa0c1d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -414,15 +414,13 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -#define MAX_SEQ_PRINTF_VARARGS 12 - BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { int err, num_args; u32 *bin_args; - if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 || + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; From 84b4c52960bdccd86d6c3c42a730fd8d0ab75427 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:04 -0700 Subject: [PATCH 02/85] selftests/bpf: Stop using bpf_program__load bpf_program__load is not supposed to be used directly. Replace it with bpf_object__ APIs for the reference_tracking prog_test, which is the last offender in bpf selftests. Some additional complexity is added for this test, namely the use of one bpf_object to iterate through progs, while a second bpf_object is created and opened/closed to test actual loading of progs. This is because the test was doing bpf_program__load then __unload to test loading of individual progs and same semantics with bpf_object__load/__unload result in failure to load an __unload-ed obj. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-3-davemarchevsky@fb.com --- .../bpf/prog_tests/reference_tracking.c | 39 +++++++++++++++---- 1 file changed, 31 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 4e91f4d6466c..ded2dc8ddd79 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,6 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 #include +static void toggle_object_autoload_progs(const struct bpf_object *obj, + const char *title_load) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *title = bpf_program__section_name(prog); + + if (!strcmp(title_load, title)) + bpf_program__set_autoload(prog, true); + else + bpf_program__set_autoload(prog, false); + } +} + void test_reference_tracking(void) { const char *file = "test_sk_lookup_kern.o"; @@ -9,21 +24,21 @@ void test_reference_tracking(void) .object_name = obj_name, .relaxed_maps = true, ); - struct bpf_object *obj; + struct bpf_object *obj_iter, *obj = NULL; struct bpf_program *prog; __u32 duration = 0; int err = 0; - obj = bpf_object__open_file(file, &open_opts); - if (!ASSERT_OK_PTR(obj, "obj_open_file")) + obj_iter = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj_iter, "obj_iter_open_file")) return; - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", + if (CHECK(strcmp(bpf_object__name(obj_iter), obj_name), "obj_name", "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + bpf_object__name(obj_iter), obj_name)) goto cleanup; - bpf_object__for_each_program(prog, obj) { + bpf_object__for_each_program(prog, obj_iter) { const char *title; /* Ignore .text sections */ @@ -34,19 +49,27 @@ void test_reference_tracking(void) if (!test__start_subtest(title)) continue; + obj = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj, "obj_open_file")) + goto cleanup; + + toggle_object_autoload_progs(obj, title); /* Expect verifier failure if test name has 'err' */ if (strstr(title, "err_") != NULL) { libbpf_print_fn_t old_print_fn; old_print_fn = libbpf_set_print(NULL); - err = !bpf_program__load(prog, "GPL", 0); + err = !bpf_object__load(obj); libbpf_set_print(old_print_fn); } else { - err = bpf_program__load(prog, "GPL", 0); + err = bpf_object__load(obj); } CHECK(err, title, "\n"); + bpf_object__close(obj); + obj = NULL; } cleanup: bpf_object__close(obj); + bpf_object__close(obj_iter); } From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:05 -0700 Subject: [PATCH 03/85] bpf: Add bpf_trace_vprintk helper This helper is meant to be "bpf_trace_printk, but with proper vararg support". Follow bpf_snprintf's example and take a u64 pseudo-vararg array. Write to /sys/kernel/debug/tracing/trace_pipe using the same mechanism as bpf_trace_printk. The functionality of this helper was requested in the libbpf issue tracker [0]. [0] Closes: https://github.com/libbpf/libbpf/issues/315 Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++ kernel/bpf/core.c | 5 ++++ kernel/bpf/helpers.c | 2 ++ kernel/trace/bpf_trace.c | 52 +++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 11 +++++++ 6 files changed, 81 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be8d57e6e78a..b6c45a6cbbba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1088,6 +1088,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..6fddc13fe67f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8f9f392c1322..2c604ff8c7fb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1435,6 +1435,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return NULL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4ec779fa0c1d..6b3153841a33 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, @@ -410,10 +410,58 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); +} +const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +{ + __set_printk_clr_event(); return &bpf_trace_printk_proto; } +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, + u32, data_len) +{ + static char buf[BPF_TRACE_PRINTK_SIZE]; + unsigned long flags; + int ret, num_args; + u32 *bin_args; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !data)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + if (ret < 0) + return ret; + + raw_spin_lock_irqsave(&trace_printk_lock, flags); + ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + + trace_bpf_trace_printk(buf); + raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + + bpf_bprintf_cleanup(); + + return ret; +} + +static const struct bpf_func_proto bpf_trace_vprintk_proto = { + .func = bpf_trace_vprintk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) +{ + __set_printk_clr_event(); + return &bpf_trace_vprintk_proto; +} + BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { @@ -1160,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper From c2758baa9798bf75d79a9aad8792edb8b694373e Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:06 -0700 Subject: [PATCH 04/85] libbpf: Modify bpf_printk to choose helper based on arg count Instead of being a thin wrapper which calls into bpf_trace_printk, libbpf's bpf_printk convenience macro now chooses between bpf_trace_printk and bpf_trace_vprintk. If the arg count (excluding format string) is >3, use bpf_trace_vprintk, otherwise use the older helper. The motivation behind this added complexity - instead of migrating entirely to bpf_trace_vprintk - is to maintain good developer experience for users compiling against new libbpf but running on older kernels. Users who are passing <=3 args to bpf_printk will see no change in their bytecode. __bpf_vprintk functions similarly to BPF_SEQ_PRINTF and BPF_SNPRINTF macros elsewhere in the file - it allows use of bpf_trace_vprintk without manual conversion of varargs to u64 array. Previous implementation of bpf_printk macro is moved to __bpf_printk for use by the new implementation. This does change behavior of bpf_printk calls with >3 args in the "new libbpf, old kernels" scenario. Before this patch, attempting to use 4 args to bpf_printk results in a compile-time error. After this patch, using bpf_printk with 4 args results in a trace_vprintk helper call being emitted and a load-time failure on older kernels. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-5-davemarchevsky@fb.com --- tools/lib/bpf/bpf_helpers.h | 45 ++++++++++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index b9987c3efa3c..55a308796625 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -14,14 +14,6 @@ #define __type(name, val) typeof(val) *name #define __array(name, val) typeof(val) *name[] -/* Helper macro to print out debug messages */ -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names @@ -224,4 +216,41 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +#define __bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + #endif From 6c66b0e7c91a1320c1b85ad8150bdd534eb4ddae Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:07 -0700 Subject: [PATCH 05/85] libbpf: Use static const fmt string in __bpf_printk The __bpf_printk convenience macro was using a 'char' fmt string holder as it predates support for globals in libbpf. Move to more efficient 'static const char', but provide a fallback to the old way via BPF_NO_GLOBAL_DATA so users on old kernels can still use the macro. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-6-davemarchevsky@fb.com --- tools/lib/bpf/bpf_helpers.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 55a308796625..963b1060d944 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -216,9 +216,15 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + #define __bpf_printk(fmt, ...) \ ({ \ - char ____fmt[] = fmt; \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ bpf_trace_printk(____fmt, sizeof(____fmt), \ ##__VA_ARGS__); \ }) From 4190c299a49f323232221e73fe1846c53e3fc3f1 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:08 -0700 Subject: [PATCH 06/85] bpftool: Only probe trace_vprintk feature in 'full' mode Since commit 368cb0e7cdb5e ("bpftool: Make probes which emit dmesg warnings optional"), some helpers aren't probed by bpftool unless `full` arg is added to `bpftool feature probe`. bpf_trace_vprintk can emit dmesg warnings when probed, so include it. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-7-davemarchevsky@fb.com --- tools/bpf/bpftool/feature.c | 1 + tools/testing/selftests/bpf/test_bpftool.py | 22 +++++++++------------ 2 files changed, 10 insertions(+), 13 deletions(-) diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 7f36385aa9e2..ade44577688e 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ switch (id) { case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: case BPF_FUNC_probe_write_user: if (!full_mode) continue; diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py index 4fed2dc25c0a..1c2408ee1f5d 100644 --- a/tools/testing/selftests/bpf/test_bpftool.py +++ b/tools/testing/selftests/bpf/test_bpftool.py @@ -57,6 +57,11 @@ def default_iface(f): return f(*args, iface, **kwargs) return wrapper +DMESG_EMITTING_HELPERS = [ + "bpf_probe_write_user", + "bpf_trace_printk", + "bpf_trace_vprintk", + ] class TestBpftool(unittest.TestCase): @classmethod @@ -67,10 +72,7 @@ class TestBpftool(unittest.TestCase): @default_iface def test_feature_dev_json(self, iface): - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "program_types", @@ -94,10 +96,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe"]), bpftool_json(["feature"]), ] - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "system_config", @@ -121,10 +120,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe", "kernel", "full"]), bpftool_json(["feature", "probe", "full"]), ] - expected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + expected_helpers = DMESG_EMITTING_HELPERS for tc in test_cases: # Check if expected helpers are included at least once in any @@ -157,7 +153,7 @@ class TestBpftool(unittest.TestCase): not_full_set.add(helper) self.assertCountEqual(full_set - not_full_set, - {"bpf_probe_write_user", "bpf_trace_printk"}) + set(DMESG_EMITTING_HELPERS)) self.assertCountEqual(not_full_set - full_set, set()) def test_feature_macros(self): From d313d45a226fdc59739c3da05bbd065f71bae5a6 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:09 -0700 Subject: [PATCH 07/85] selftests/bpf: Migrate prog_tests/trace_printk CHECKs to ASSERTs Guidance for new tests is to use ASSERT macros instead of CHECK. Since trace_vprintk test will borrow heavily from trace_printk's, migrate its CHECKs so it remains obvious that the two are closely related. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-8-davemarchevsky@fb.com --- .../selftests/bpf/prog_tests/trace_printk.c | 24 +++++++------------ 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index d39bc00feb45..e47835f0a674 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -10,7 +10,7 @@ void test_trace_printk(void) { - int err, iter = 0, duration = 0, found = 0; + int err = 0, iter = 0, found = 0; struct trace_printk__bss *bss; struct trace_printk *skel; char *buf = NULL; @@ -18,25 +18,24 @@ void test_trace_printk(void) size_t buflen; skel = trace_printk__open(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "trace_printk__open")) return; - ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]"); skel->rodata->fmt[0] = 't'; err = trace_printk__load(skel); - if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__load")) goto cleanup; bss = skel->bss; err = trace_printk__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__attach")) goto cleanup; fp = fopen(TRACEBUF, "r"); - if (CHECK(fp == NULL, "could not open trace buffer", - "error %d opening %s", errno, TRACEBUF)) + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) goto cleanup; /* We do not want to wait forever if this test fails... */ @@ -46,14 +45,10 @@ void test_trace_printk(void) usleep(1); trace_printk__detach(skel); - if (CHECK(bss->trace_printk_ran == 0, - "bpf_trace_printk never ran", - "ran == %d", bss->trace_printk_ran)) + if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran")) goto cleanup; - if (CHECK(bss->trace_printk_ret <= 0, - "bpf_trace_printk returned <= 0 value", - "got %d", bss->trace_printk_ret)) + if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret")) goto cleanup; /* verify our search string is in the trace buffer */ @@ -66,8 +61,7 @@ void test_trace_printk(void) break; } - if (CHECK(!found, "message from bpf_trace_printk not found", - "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + if (!ASSERT_EQ(found, bss->trace_printk_ran, "found")) goto cleanup; cleanup: From 7606729fe24e163923430a5df9d50a246b22d287 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:10 -0700 Subject: [PATCH 08/85] selftests/bpf: Add trace_vprintk test prog This commit adds a test prog for vprintk which confirms that: * bpf_trace_vprintk is writing to /sys/kernel/debug/tracing/trace_pipe * __bpf_vprintk macro works as expected * >3 args are printed * bpf_printk w/ 0 format args compiles * bpf_trace_vprintk call w/ a fmt specifier but NULL fmt data fails Approach and code are borrowed from trace_printk test. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-9-davemarchevsky@fb.com --- tools/testing/selftests/bpf/Makefile | 3 +- .../selftests/bpf/prog_tests/trace_vprintk.c | 68 +++++++++++++++++++ .../selftests/bpf/progs/trace_vprintk.c | 33 +++++++++ 3 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/trace_vprintk.c create mode 100644 tools/testing/selftests/bpf/progs/trace_vprintk.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1a4d30ff3275..326ea75ce99e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -315,7 +315,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c + test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \ + trace_vprintk.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c new file mode 100644 index 000000000000..61a24e62e1a0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include + +#include "trace_vprintk.lskel.h" + +#define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" +#define SEARCHMSG "1,2,3,4,5,6,7,8,9,10" + +void test_trace_vprintk(void) +{ + int err = 0, iter = 0, found = 0; + struct trace_vprintk__bss *bss; + struct trace_vprintk *skel; + char *buf = NULL; + FILE *fp = NULL; + size_t buflen; + + skel = trace_vprintk__open_and_load(); + if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load")) + goto cleanup; + + bss = skel->bss; + + err = trace_vprintk__attach(skel); + if (!ASSERT_OK(err, "trace_vprintk__attach")) + goto cleanup; + + fp = fopen(TRACEBUF, "r"); + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) + goto cleanup; + + /* We do not want to wait forever if this test fails... */ + fcntl(fileno(fp), F_SETFL, O_NONBLOCK); + + /* wait for tracepoint to trigger */ + usleep(1); + trace_vprintk__detach(skel); + + if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran")) + goto cleanup; + + if (!ASSERT_GT(bss->trace_vprintk_ret, 0, "bss->trace_vprintk_ret")) + goto cleanup; + + /* verify our search string is in the trace buffer */ + while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) { + if (strstr(buf, SEARCHMSG) != NULL) + found++; + if (found == bss->trace_vprintk_ran) + break; + if (++iter > 1000) + break; + } + + if (!ASSERT_EQ(found, bss->trace_vprintk_ran, "found")) + goto cleanup; + + if (!ASSERT_LT(bss->null_data_vprintk_ret, 0, "bss->null_data_vprintk_ret")) + goto cleanup; + +cleanup: + trace_vprintk__destroy(skel); + free(buf); + if (fp) + fclose(fp); +} diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c new file mode 100644 index 000000000000..d327241ba047 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +int null_data_vprintk_ret = 0; +int trace_vprintk_ret = 0; +int trace_vprintk_ran = 0; + +SEC("fentry/__x64_sys_nanosleep") +int sys_enter(void *ctx) +{ + static const char one[] = "1"; + static const char three[] = "3"; + static const char five[] = "5"; + static const char seven[] = "7"; + static const char nine[] = "9"; + static const char f[] = "%pS\n"; + + /* runner doesn't search for \t, just ensure it compiles */ + bpf_printk("\t"); + + trace_vprintk_ret = __bpf_vprintk("%s,%d,%s,%d,%s,%d,%s,%d,%s,%d %d\n", + one, 2, three, 4, five, 6, seven, 8, nine, 10, ++trace_vprintk_ran); + + /* non-NULL fmt w/ NULL data should result in error */ + null_data_vprintk_ret = bpf_trace_vprintk(f, sizeof(f), NULL, 0); + return 0; +} From a42effb0b24fcaf49513c2d7d77ef6daa9e32a6f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:11 -0700 Subject: [PATCH 09/85] bpf: Clarify data_len param in bpf_snprintf and bpf_seq_printf comments Since the data_len in these two functions is a byte len of the preceding u64 *data array, it must always be a multiple of 8. If this isn't the case both helpers error out, so let's make the requirement explicit so users don't need to infer it. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-10-davemarchevsky@fb.com --- include/uapi/linux/bpf.h | 5 +++-- tools/include/uapi/linux/bpf.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid From 97c140d94e2e5f050d5f418317cc34f83da3d0f5 Mon Sep 17 00:00:00 2001 From: Grant Seltzer Date: Fri, 17 Sep 2021 23:14:58 -0400 Subject: [PATCH 10/85] libbpf: Add doc comments in libbpf.h This adds comments above functions in libbpf.h which document their uses. These comments are of a format that doxygen and sphinx can pick up and render. These are rendered by libbpf.readthedocs.org These doc comments are for: - bpf_object__find_map_by_name() - bpf_map__fd() - bpf_map__is_internal() - libbpf_get_error() - libbpf_num_possible_cpus() Signed-off-by: Grant Seltzer Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210918031457.36204-1-grantseltzer@gmail.com --- tools/lib/bpf/libbpf.h | 65 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 57 insertions(+), 8 deletions(-) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c90e3d79e72c..d0bedd673273 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -481,9 +481,13 @@ struct bpf_map_def { unsigned int map_flags; }; -/* - * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, - * so no need to worry about a name clash. +/** + * @brief **bpf_object__find_map_by_name()** returns BPF map of + * the given name, if it exists within the passed BPF object + * @param obj BPF object + * @param name name of the BPF map + * @return BPF map instance, if such map exists within the BPF object; + * or NULL otherwise. */ LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -509,7 +513,12 @@ bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -/* get/set map FD */ +/** + * @brief **bpf_map__fd()** gets the file descriptor of the passed + * BPF map + * @param map the BPF map instance + * @return the file descriptor; or -EINVAL in case of an error + */ LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ @@ -550,6 +559,14 @@ LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_internal()** tells the caller whether or not the + * passed map is a special map created by libbpf automatically for things like + * global variables, __ksym externs, Kconfig values, etc + * @param map the bpf_map + * @return true, if the map is an internal map; false, otherwise + */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); @@ -561,6 +578,38 @@ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Many libbpf API functions which return pointers have logic to encode error + * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** + * should be used on the return value from these functions immediately after + * calling the API function, with no intervening calls that could clobber the + * `errno` variable. Consult the individual functions documentation to verify + * if this logic applies should be used. + * + * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` + * is enabled, NULL is returned on error instead. + * + * If ptr is NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. + * + * Example usage: + * + * struct perf_buffer *pb; + * + * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); + * err = libbpf_get_error(pb); + * if (err) { + * pb = NULL; + * fprintf(stderr, "failed to open perf buffer: %d\n", err); + * goto cleanup; + * } + */ LIBBPF_API long libbpf_get_error(const void *ptr); struct bpf_prog_load_attr { @@ -825,9 +874,10 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); -/* - * A helper function to get the number of possible CPUs before looking up - * per-CPU maps. Negative errno is returned on failure. +/** + * @brief **libbpf_num_possible_cpus()** is a helper function to get the + * number of possible CPUs that the host kernel supports and expects. + * @return number of possible CPUs; or error code on failure * * Example usage: * @@ -837,7 +887,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); * } * long values[ncpus]; * bpf_map_lookup_elem(per_cpu_map_fd, key, values); - * */ LIBBPF_API int libbpf_num_possible_cpus(void); From f5c4e4191b542c8ceb4e945342fda8ea2e9a9193 Mon Sep 17 00:00:00 2001 From: Gokul Sivakumar Date: Sun, 19 Sep 2021 13:33:04 +0530 Subject: [PATCH 11/85] samples: bpf: Convert route table network order fields into readable format The route table that is dumped when the xdp_router_ipv4 process is launched has the "Gateway" field in non-readable network byte order format, also the alignment is off when printing the table. Destination Gateway Genmask Metric Iface 0.0.0.0 196a8c0 0 0 enp7s0 0.0.0.0 196a8c0 0 0 wlp6s0 169.254.0.0 196a8c0 16 0 enp7s0 172.17.0.0 0 16 0 docker0 192.168.150.0 0 24 0 enp7s0 192.168.150.0 0 24 0 wlp6s0 Fix this by converting the "Gateway" field from network byte order Hex into dotted decimal notation IPv4 format and "Genmask" from CIDR notation into dotted decimal notation IPv4 format. Also fix the aligntment of the fields in the route table. Destination Gateway Genmask Metric Iface 0.0.0.0 192.168.150.1 0.0.0.0 0 enp7s0 0.0.0.0 192.168.150.1 0.0.0.0 0 wlp6s0 169.254.0.0 192.168.150.1 255.255.0.0 0 enp7s0 172.17.0.0 0.0.0.0 255.255.0.0 0 docker0 192.168.150.0 0.0.0.0 255.255.255.0 0 enp7s0 192.168.150.0 0.0.0.0 255.255.255.0 0 wlp6s0 Signed-off-by: Gokul Sivakumar Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210919080305.173588-1-gokulkumar792@gmail.com --- samples/bpf/xdp_router_ipv4_user.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index b5f03cb17a3c..3e9db5a8c8c6 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -155,7 +155,7 @@ static void read_route(struct nlmsghdr *nh, int nll) printf("%d\n", nh->nlmsg_type); memset(&route, 0, sizeof(route)); - printf("Destination\t\tGateway\t\tGenmask\t\tMetric\t\tIface\n"); + printf("Destination Gateway Genmask Metric Iface\n"); for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) { rt_msg = (struct rtmsg *)NLMSG_DATA(nh); rtm_family = rt_msg->rtm_family; @@ -207,6 +207,7 @@ static void read_route(struct nlmsghdr *nh, int nll) int metric; __be32 gw; } *prefix_value; + struct in_addr dst_addr, gw_addr, mask_addr; prefix_key = alloca(sizeof(*prefix_key) + 3); prefix_value = alloca(sizeof(*prefix_value)); @@ -234,14 +235,17 @@ static void read_route(struct nlmsghdr *nh, int nll) for (i = 0; i < 4; i++) prefix_key->data[i] = (route.dst >> i * 8) & 0xff; - printf("%3d.%d.%d.%d\t\t%3x\t\t%d\t\t%d\t\t%s\n", - (int)prefix_key->data[0], - (int)prefix_key->data[1], - (int)prefix_key->data[2], - (int)prefix_key->data[3], - route.gw, route.dst_len, + dst_addr.s_addr = route.dst; + printf("%-16s", inet_ntoa(dst_addr)); + + gw_addr.s_addr = route.gw; + printf("%-16s", inet_ntoa(gw_addr)); + + mask_addr.s_addr = htonl(~(0xffffffffU >> route.dst_len)); + printf("%-16s%-7d%s\n", inet_ntoa(mask_addr), route.metric, route.iface_name); + if (bpf_map_lookup_elem(lpm_map_fd, prefix_key, prefix_value) < 0) { for (i = 0; i < 4; i++) @@ -672,7 +676,7 @@ int main(int ac, char **argv) if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return 1; - printf("\n**************loading bpf file*********************\n\n\n"); + printf("\n******************loading bpf file*********************\n"); if (!prog_fd) { printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; @@ -722,7 +726,7 @@ int main(int ac, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - printf("*******************ROUTE TABLE*************************\n\n\n"); + printf("\n*******************ROUTE TABLE*************************\n"); get_route_table(AF_INET); printf("*******************ARP TABLE***************************\n\n\n"); get_arp_table(AF_INET); From cf8980a362353c5ebb3efb9b09e9fda17e0abfa4 Mon Sep 17 00:00:00 2001 From: Gokul Sivakumar Date: Sun, 19 Sep 2021 13:33:05 +0530 Subject: [PATCH 12/85] samples: bpf: Convert ARP table network order fields into readable format The ARP table that is dumped when the xdp_router_ipv4 process is launched has the IP address & MAC address in non-readable network byte order format, also the alignment is off when printing the table. Address HwAddress 160000e0 1600005e0001 ff96a8c0 ffffffffffff faffffef faff7f5e0001 196a8c0 9607871293ea fb0000e0 fb00005e0001 0 0 196a8c0 9607871293ea ffff11ac ffffffffffff faffffef faff7f5e0001 fb0000e0 fb00005e0001 160000e0 1600005e0001 160000e0 1600005e0001 faffffef faff7f5e0001 fb0000e0 fb00005e0001 40011ac 40011ac4202 Fix this by converting the "Address" field from network byte order Hex into dotted decimal notation IPv4 format and "HwAddress" field from network byte order Hex into Colon separated Hex format. Also fix the aligntment of the fields in the ARP table. Address HwAddress 224.0.0.22 01:00:5e:00:00:16 192.168.150.255 ff:ff:ff:ff:ff:ff 239.255.255.250 01:00:5e:7f:ff:fa 192.168.150.1 ea:93:12:87:07:96 224.0.0.251 01:00:5e:00:00:fb 0.0.0.0 00:00:00:00:00:00 192.168.150.1 ea:93:12:87:07:96 172.17.255.255 ff:ff:ff:ff:ff:ff 239.255.255.250 01:00:5e:7f:ff:fa 224.0.0.251 01:00:5e:00:00:fb 224.0.0.22 01:00:5e:00:00:16 224.0.0.22 01:00:5e:00:00:16 239.255.255.250 01:00:5e:7f:ff:fa 224.0.0.251 01:00:5e:00:00:fb 172.17.0.4 02:42:ac:11:00:04 Signed-off-by: Gokul Sivakumar Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210919080305.173588-2-gokulkumar792@gmail.com --- samples/bpf/xdp_router_ipv4_user.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 3e9db5a8c8c6..cfaf7e50e431 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -397,8 +397,12 @@ static void read_arp(struct nlmsghdr *nh, int nll) if (nh->nlmsg_type == RTM_GETNEIGH) printf("READING arp entry\n"); - printf("Address\tHwAddress\n"); + printf("Address HwAddress\n"); for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) { + struct in_addr dst_addr; + char mac_str[18]; + int len = 0, i; + rt_msg = (struct ndmsg *)NLMSG_DATA(nh); rt_attr = (struct rtattr *)RTM_RTA(rt_msg); ndm_family = rt_msg->ndm_family; @@ -419,7 +423,14 @@ static void read_arp(struct nlmsghdr *nh, int nll) } arp_entry.dst = atoi(dsts); arp_entry.mac = atol(mac); - printf("%x\t\t%llx\n", arp_entry.dst, arp_entry.mac); + + dst_addr.s_addr = arp_entry.dst; + for (i = 0; i < 6; i++) + len += snprintf(mac_str + len, 18 - len, "%02llx%s", + ((arp_entry.mac >> i * 8) & 0xff), + i < 5 ? ":" : ""); + printf("%-16s%s\n", inet_ntoa(dst_addr), mac_str); + if (ndm_family == AF_INET) { if (bpf_map_lookup_elem(exact_match_map_fd, &arp_entry.dst, @@ -728,7 +739,7 @@ int main(int ac, char **argv) printf("\n*******************ROUTE TABLE*************************\n"); get_route_table(AF_INET); - printf("*******************ARP TABLE***************************\n\n\n"); + printf("\n*******************ARP TABLE***************************\n"); get_arp_table(AF_INET); if (monitor_route() < 0) { printf("Error in receiving route update"); From 303a257223a3bbd7cc6ccc2b7777179c8d9f3989 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Sep 2021 14:00:33 -0700 Subject: [PATCH 13/85] libbpf: Fix memory leak in legacy kprobe attach logic In some error scenarios legacy_probe string won't be free()'d. Fix this. This was reported by Coverity static analysis. Fixes: ca304b40c20d ("libbpf: Introduce legacy kprobe events support") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210921210036.1545557-2-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index da65a1666a5e..6d2f12db6034 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -9365,10 +9365,11 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, offset, -1 /* pid */); } if (pfd < 0) { + err = pfd; pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); @@ -9377,7 +9378,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, pr_warn("prog '%s': failed to attach to %s '%s': %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; } if (legacy) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9387,6 +9388,9 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); } struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, From d3b0e3b03cf75896de7b03ad1fca2bff98c59f15 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Sep 2021 14:00:34 -0700 Subject: [PATCH 14/85] selftests/bpf: Adopt attach_probe selftest to work on old kernels Make sure to not use ref_ctr_off feature when running on old kernels that don't support this feature. This allows to test libbpf's legacy kprobe and uprobe logic on old kernels. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210921210036.1545557-3-andrii@kernel.org --- .../selftests/bpf/prog_tests/attach_probe.c | 24 +++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index bf307bb9e446..6c511dcd1465 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -14,6 +14,20 @@ void test_attach_probe(void) struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr, ref_ctr_offset; + bool legacy; + + /* Check if new-style kprobe/uprobe API is supported. + * Kernels that support new FD-based kprobe and uprobe BPF attachment + * through perf_event_open() syscall expose + * /sys/bus/event_source/devices/kprobe/type and + * /sys/bus/event_source/devices/uprobe/type files, respectively. They + * contain magic numbers that are passed as "type" field of + * perf_event_attr. Lack of such file in the system indicates legacy + * kernel with old-style kprobe/uprobe attach interface through + * creating per-probe event through tracefs. For such cases + * ref_ctr_offset feature is not supported, so we don't test it. + */ + legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; base_addr = get_base_addr(); if (CHECK(base_addr < 0, "get_base_addr", @@ -45,10 +59,11 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_kretprobe = kretprobe_link; - ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); + if (!legacy) + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); uprobe_opts.retprobe = false; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, 0 /* self pid */, "/proc/self/exe", @@ -58,11 +73,12 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_uprobe = uprobe_link; - ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); + if (!legacy) + ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); /* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */ uprobe_opts.retprobe = true; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, -1 /* any pid */, "/proc/self/exe", From 46ed5fc33db966aa1a46e8ae9d96b08b756a2546 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Sep 2021 14:00:35 -0700 Subject: [PATCH 15/85] libbpf: Refactor and simplify legacy kprobe code Refactor legacy kprobe handling code to follow the same logic as uprobe legacy logic added in the next patchs: - add append_to_file() helper that makes it simpler to work with tracefs file-based interface for creating and deleting probes; - move out probe/event name generation outside of the code that adds/removes it, which simplifies bookkeeping significantly; - change the probe name format to start with "libbpf_" prefix and include offset within kernel function; - switch 'unsigned long' to 'size_t' for specifying kprobe offsets, which is consistent with how uprobes define that, simplifies printf()-ing internally, and also avoids unnecessary complications on architectures where sizeof(long) != sizeof(void *). This patch also implicitly fixes the problem with invalid open() error handling present in poke_kprobe_events(), which (the function) this patch removes. Fixes: ca304b40c20d ("libbpf: Introduce legacy kprobe events support") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210921210036.1545557-4-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 159 ++++++++++++++++++++++------------------- tools/lib/bpf/libbpf.h | 2 +- 2 files changed, 88 insertions(+), 73 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 6d2f12db6034..aa842f0721cb 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -9011,59 +9011,17 @@ int bpf_link__unpin(struct bpf_link *link) return 0; } -static int poke_kprobe_events(bool add, const char *name, bool retprobe, uint64_t offset) -{ - int fd, ret = 0; - pid_t p = getpid(); - char cmd[260], probename[128], probefunc[128]; - const char *file = "/sys/kernel/debug/tracing/kprobe_events"; - - if (retprobe) - snprintf(probename, sizeof(probename), "kretprobes/%s_libbpf_%u", name, p); - else - snprintf(probename, sizeof(probename), "kprobes/%s_libbpf_%u", name, p); - - if (offset) - snprintf(probefunc, sizeof(probefunc), "%s+%zu", name, (size_t)offset); - - if (add) { - snprintf(cmd, sizeof(cmd), "%c:%s %s", - retprobe ? 'r' : 'p', - probename, - offset ? probefunc : name); - } else { - snprintf(cmd, sizeof(cmd), "-:%s", probename); - } - - fd = open(file, O_WRONLY | O_APPEND, 0); - if (!fd) - return -errno; - ret = write(fd, cmd, strlen(cmd)); - if (ret < 0) - ret = -errno; - close(fd); - - return ret; -} - -static inline int add_kprobe_event_legacy(const char *name, bool retprobe, uint64_t offset) -{ - return poke_kprobe_events(true, name, retprobe, offset); -} - -static inline int remove_kprobe_event_legacy(const char *name, bool retprobe) -{ - return poke_kprobe_events(false, name, retprobe, 0); -} - struct bpf_link_perf { struct bpf_link link; int perf_event_fd; /* legacy kprobe support: keep track of probe identifier and type */ char *legacy_probe_name; + bool legacy_is_kprobe; bool legacy_is_retprobe; }; +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); + static int bpf_link_perf_detach(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9077,9 +9035,12 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(link->fd); /* legacy kprobe needs to be removed after perf event fd closure */ - if (perf_link->legacy_probe_name) - err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, - perf_link->legacy_is_retprobe); + if (perf_link->legacy_probe_name) { + if (perf_link->legacy_is_kprobe) { + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } + } return err; } @@ -9202,18 +9163,6 @@ static int parse_uint_from_file(const char *file, const char *fmt) return ret; } -static int determine_kprobe_perf_type_legacy(const char *func_name, bool is_retprobe) -{ - char file[192]; - - snprintf(file, sizeof(file), - "/sys/kernel/debug/tracing/events/%s/%s_libbpf_%d/id", - is_retprobe ? "kretprobes" : "kprobes", - func_name, getpid()); - - return parse_uint_from_file(file, "%d\n"); -} - static int determine_kprobe_perf_type(void) { const char *file = "/sys/bus/event_source/devices/kprobe/type"; @@ -9296,21 +9245,79 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, return pfd; } -static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64_t offset, int pid) +static int append_to_file(const char *file, const char *fmt, ...) +{ + int fd, n, err = 0; + va_list ap; + + fd = open(file, O_WRONLY | O_APPEND, 0); + if (fd < 0) + return -errno; + + va_start(ap, fmt); + n = vdprintf(fd, fmt, ap); + va_end(ap); + + if (n < 0) + err = -errno; + + close(fd); + return err; +} + +static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *kfunc_name, size_t offset) +{ + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset); +} + +static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "%c:%s/%s %s+0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "kretprobes" : "kprobes", + probe_name, kfunc_name, offset); +} + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name); +} + +static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[256]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "kretprobes" : "kprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset, int pid) { struct perf_event_attr attr = {}; char errmsg[STRERR_BUFSIZE]; int type, pfd, err; - err = add_kprobe_event_legacy(name, retprobe, offset); + err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); if (err < 0) { - pr_warn("failed to add legacy kprobe event: %s\n", + pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", + kfunc_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); return err; } - type = determine_kprobe_perf_type_legacy(name, retprobe); + type = determine_kprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { - pr_warn("failed to determine legacy kprobe event id: %s\n", + pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", + kfunc_name, offset, libbpf_strerror_r(type, errmsg, sizeof(errmsg))); return type; } @@ -9340,7 +9347,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, char errmsg[STRERR_BUFSIZE]; char *legacy_probe = NULL; struct bpf_link *link; - unsigned long offset; + size_t offset; bool retprobe, legacy; int pfd, err; @@ -9357,17 +9364,23 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, func_name, offset, -1 /* pid */, 0 /* ref_ctr_off */); } else { + char probe_name[256]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); + legacy_probe = strdup(func_name); if (!legacy_probe) return libbpf_err_ptr(-ENOMEM); - pfd = perf_event_kprobe_open_legacy(retprobe, func_name, + pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name, offset, -1 /* pid */); } if (pfd < 0) { - err = pfd; - pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, + err = -errno; + pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); goto err_out; } @@ -9375,8 +9388,9 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, err = libbpf_get_error(link); if (err) { close(pfd); - pr_warn("prog '%s': failed to attach to %s '%s': %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, + pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); goto err_out; } @@ -9384,6 +9398,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = true; perf_link->legacy_is_retprobe = retprobe; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index d0bedd673273..e35490c54eb3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -269,7 +269,7 @@ struct bpf_kprobe_opts { /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; /* function's offset to install kprobe to */ - unsigned long offset; + size_t offset; /* kprobe is return probe */ bool retprobe; size_t :0; From cc10623c681019c608c0cb30e2b38994e2c90b2a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Sep 2021 14:00:36 -0700 Subject: [PATCH 16/85] libbpf: Add legacy uprobe attaching support Similarly to recently added legacy kprobe attach interface support through tracefs, support attaching uprobes using the legacy interface if host kernel doesn't support newer FD-based interface. For uprobes event name consists of "libbpf_" prefix, PID, sanitized binary path and offset within that binary. Structuraly the code is aligned with kprobe logic refactoring in previous patch. struct bpf_link_perf is re-used and all the same legacy_probe_name and legacy_is_retprobe fields are used to ensure proper cleanup on bpf_link__destroy(). Users should be aware, though, that on old kernels which don't support FD-based interface for kprobe/uprobe attachment, if the application crashes before bpf_link__destroy() is called, uprobe legacy events will be left in tracefs. This is the same limitation as with legacy kprobe interfaces. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210921210036.1545557-5-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 130 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 122 insertions(+), 8 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index aa842f0721cb..ef5db34bf913 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -9021,6 +9021,7 @@ struct bpf_link_perf { }; static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); +static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe); static int bpf_link_perf_detach(struct bpf_link *link) { @@ -9034,11 +9035,14 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(perf_link->perf_event_fd); close(link->fd); - /* legacy kprobe needs to be removed after perf event fd closure */ + /* legacy uprobe/kprobe needs to be removed after perf event fd closure */ if (perf_link->legacy_probe_name) { if (perf_link->legacy_is_kprobe) { err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, perf_link->legacy_is_retprobe); + } else { + err = remove_uprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); } } @@ -9450,17 +9454,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog) return link; } +static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *binary_path, uint64_t offset) +{ + int i; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } +} + +static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "%c:%s/%s %s:0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "uretprobes" : "uprobes", + probe_name, binary_path, offset); +} + +static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name); +} + +static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[512]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "uretprobes" : "uprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset, int pid) +{ + struct perf_event_attr attr; + int type, pfd, err; + + err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); + if (err < 0) { + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", + binary_path, (size_t)offset, err); + return err; + } + type = determine_uprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", + binary_path, offset, err); + return type; + } + + memset(&attr, 0, sizeof(attr)); + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + return err; + } + return pfd; +} + LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; + char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; - bool retprobe; + bool retprobe, legacy; if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); @@ -9469,15 +9552,35 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, - func_offset, pid, ref_ctr_off); + legacy = determine_uprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, + func_offset, pid, ref_ctr_off); + } else { + char probe_name[512]; + + if (ref_ctr_off) + return libbpf_err_ptr(-EINVAL); + + gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), + binary_path, func_offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe, + binary_path, func_offset, pid); + } if (pfd < 0) { + err = -errno; pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { @@ -9486,9 +9589,20 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = false; + perf_link->legacy_is_retprobe = retprobe; } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); + } struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, From 17b52c226a9a170f1611f69d12a71be05748aefd Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 21 Sep 2021 16:59:11 +0200 Subject: [PATCH 17/85] seltests: bpf: test_tunnel: Use ip neigh The 'arp' command is deprecated and is another dependency of the selftest. Just use 'ip neigh', the test depends on iproute2 already. Signed-off-by: Jiri Benc Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/40f24b9d3f0f53b5c44471b452f9a11f4d13b7af.1632236133.git.jbenc@redhat.com --- tools/testing/selftests/bpf/test_tunnel.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 1ccbe804e8e1..ca1372924023 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -168,14 +168,15 @@ add_vxlan_tunnel() ip netns exec at_ns0 \ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 \ + ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF # root namespace ip link add dev $DEV type $TYPE external gbp dstport 4789 ip link set dev $DEV address 52:54:00:d9:02:00 up ip addr add dev $DEV 10.1.1.200/24 - arp -s 10.1.1.100 52:54:00:d9:01:00 + ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV } add_ip6vxlan_tunnel() From c86216bc96aa2a61ee5248d99d0bd15e69cf52d1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 17 Sep 2021 16:00:34 -0700 Subject: [PATCH 18/85] bpf: Document BPF licensing. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document and clarify BPF licensing. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Reviewed-by: Simon Horman Acked-by: Toke Høiland-Jørgensen Acked-by: Daniel Borkmann Acked-by: Joe Stringer Acked-by: Lorenz Bauer Acked-by: Dave Thaler Acked-by: Stephen Hemminger Acked-by: Jesper Dangaard Brouer Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210917230034.51080-1-alexei.starovoitov@gmail.com --- Documentation/bpf/bpf_licensing.rst | 92 +++++++++++++++++++++++++++++ Documentation/bpf/index.rst | 9 +++ 2 files changed, 101 insertions(+) create mode 100644 Documentation/bpf/bpf_licensing.rst diff --git a/Documentation/bpf/bpf_licensing.rst b/Documentation/bpf/bpf_licensing.rst new file mode 100644 index 000000000000..b19c433f41d2 --- /dev/null +++ b/Documentation/bpf/bpf_licensing.rst @@ -0,0 +1,92 @@ +============= +BPF licensing +============= + +Background +========== + +* Classic BPF was BSD licensed + +"BPF" was originally introduced as BSD Packet Filter in +http://www.tcpdump.org/papers/bpf-usenix93.pdf. The corresponding instruction +set and its implementation came from BSD with BSD license. That original +instruction set is now known as "classic BPF". + +However an instruction set is a specification for machine-language interaction, +similar to a programming language. It is not a code. Therefore, the +application of a BSD license may be misleading in a certain context, as the +instruction set may enjoy no copyright protection. + +* eBPF (extended BPF) instruction set continues to be BSD + +In 2014, the classic BPF instruction set was significantly extended. We +typically refer to this instruction set as eBPF to disambiguate it from cBPF. +The eBPF instruction set is still BSD licensed. + +Implementations of eBPF +======================= + +Using the eBPF instruction set requires implementing code in both kernel space +and user space. + +In Linux Kernel +--------------- + +The reference implementations of the eBPF interpreter and various just-in-time +compilers are part of Linux and are GPLv2 licensed. The implementation of +eBPF helper functions is also GPLv2 licensed. Interpreters, JITs, helpers, +and verifiers are called eBPF runtime. + +In User Space +------------- + +There are also implementations of eBPF runtime (interpreter, JITs, helper +functions) under +Apache2 (https://github.com/iovisor/ubpf), +MIT (https://github.com/qmonnet/rbpf), and +BSD (https://github.com/DPDK/dpdk/blob/main/lib/librte_bpf). + +In HW +----- + +The HW can choose to execute eBPF instruction natively and provide eBPF runtime +in HW or via the use of implementing firmware with a proprietary license. + +In other operating systems +-------------------------- + +Other kernels or user space implementations of eBPF instruction set and runtime +can have proprietary licenses. + +Using BPF programs in the Linux kernel +====================================== + +Linux Kernel (while being GPLv2) allows linking of proprietary kernel modules +under these rules: +Documentation/process/license-rules.rst + +When a kernel module is loaded, the linux kernel checks which functions it +intends to use. If any function is marked as "GPL only," the corresponding +module or program has to have GPL compatible license. + +Loading BPF program into the Linux kernel is similar to loading a kernel +module. BPF is loaded at run time and not statically linked to the Linux +kernel. BPF program loading follows the same license checking rules as kernel +modules. BPF programs can be proprietary if they don't use "GPL only" BPF +helper functions. + +Further, some BPF program types - Linux Security Modules (LSM) and TCP +Congestion Control (struct_ops), as of Aug 2021 - are required to be GPL +compatible even if they don't use "GPL only" helper functions directly. The +registration step of LSM and TCP congestion control modules of the Linux +kernel is done through EXPORT_SYMBOL_GPL kernel functions. In that sense LSM +and struct_ops BPF programs are implicitly calling "GPL only" functions. +The same restriction applies to BPF programs that call kernel functions +directly via unstable interface also known as "kfunc". + +Packaging BPF programs with user space applications +==================================================== + +Generally, proprietary-licensed applications and GPL licensed BPF programs +written for the Linux kernel in the same package can co-exist because they are +separate executable processes. This applies to both cBPF and eBPF programs. diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index 1ceb5d704a97..37f273a7e8b6 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -82,6 +82,15 @@ Testing and debugging BPF s390 +Licensing +========= + +.. toctree:: + :maxdepth: 1 + + bpf_licensing + + Other ===== From 091037fb770e1771a52246f9b68dc76082178a3c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Sep 2021 19:58:56 -0700 Subject: [PATCH 19/85] selftests/bpf: Fix btf_dump __int128 test failure with clang build kernel With clang build kernel (adding LLVM=1 to kernel and selftests/bpf build command line), I hit the following test failure: $ ./test_progs -t btf_dump ... btf_dump_data:PASS:ensure expected/actual match 0 nsec btf_dump_data:FAIL:find type id unexpected find type id: actual -2 < expected 0 btf_dump_data:FAIL:find type id unexpected find type id: actual -2 < expected 0 test_btf_dump_int_data:FAIL:dump __int128 unexpected error: -2 (errno 2) #15/9 btf_dump/btf_dump: int_data:FAIL Further analysis showed gcc build kernel has type "__int128" in dwarf/BTF and it doesn't exist in clang build kernel. Code searching for kernel code found the following: arch/s390/include/asm/types.h: unsigned __int128 pair; crypto/ecc.c: unsigned __int128 m = (unsigned __int128)left * right; include/linux/math64.h: return (u64)(((unsigned __int128)a * mul) >> shift); include/linux/math64.h: return (u64)(((unsigned __int128)a * mul) >> shift); lib/ubsan.h:typedef __int128 s_max; lib/ubsan.h:typedef unsigned __int128 u_max; In my case, CONFIG_UBSAN is not enabled. Even if we only have "unsigned __int128" in the code, somehow gcc still put "__int128" in dwarf while clang didn't. Hence current test works fine for gcc but not for clang. Enabling CONFIG_UBSAN is an option to provide __int128 type into dwarf reliably for both gcc and clang, but not everybody enables CONFIG_UBSAN in their kernel build. So the best choice is to use "unsigned __int128" type which is available in both clang and gcc build kernels. But clang and gcc dwarf encoded names for "unsigned __int128" are different: [$ ~] cat t.c unsigned __int128 a; [$ ~] gcc -g -c t.c && llvm-dwarfdump t.o | grep __int128 DW_AT_type (0x00000031 "__int128 unsigned") DW_AT_name ("__int128 unsigned") [$ ~] clang -g -c t.c && llvm-dwarfdump t.o | grep __int128 DW_AT_type (0x00000033 "unsigned __int128") DW_AT_name ("unsigned __int128") The test change in this patch tries to test type name before doing actual test. Signed-off-by: Yonghong Song Signed-off-by: Andrii Nakryiko Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/20210924025856.2192476-1-yhs@fb.com --- .../selftests/bpf/prog_tests/btf_dump.c | 27 ++++++++++++++----- 1 file changed, 21 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 52ccf0cf35e1..87f9df653e4e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -358,12 +358,27 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, TEST_BTF_DUMP_DATA_OVER(btf, d, NULL, str, int, sizeof(int)-1, "", 1); #ifdef __SIZEOF_INT128__ - TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128, BTF_F_COMPACT, - "(__int128)0xffffffffffffffff", - 0xffffffffffffffff); - ASSERT_OK(btf_dump_data(btf, d, "__int128", NULL, 0, &i, 16, str, - "(__int128)0xfffffffffffffffffffffffffffffffe"), - "dump __int128"); + /* gcc encode unsigned __int128 type with name "__int128 unsigned" in dwarf, + * and clang encode it with name "unsigned __int128" in dwarf. + * Do an availability test for either variant before doing actual test. + */ + if (btf__find_by_name(btf, "unsigned __int128") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, unsigned __int128, BTF_F_COMPACT, + "(unsigned __int128)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "unsigned __int128", NULL, 0, &i, 16, str, + "(unsigned __int128)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else if (btf__find_by_name(btf, "__int128 unsigned") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128 unsigned, BTF_F_COMPACT, + "(__int128 unsigned)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "__int128 unsigned", NULL, 0, &i, 16, str, + "(__int128 unsigned)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else { + ASSERT_TRUE(false, "unsigned_int128_not_found"); + } #endif } From 27113c59b6d0a587b29ae72d4ff3f832f58b0651 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:34 -0700 Subject: [PATCH 20/85] bpf: Check the other end of slot_type for STACK_SPILL Every 8 bytes of the stack is tracked by a bpf_stack_state. Within each bpf_stack_state, there is a 'u8 slot_type[8]' to track the type of each byte. Verifier tests slot_type[0] == STACK_SPILL to decide if the spilled reg state is saved. Verifier currently only saves the reg state if the whole 8 bytes are spilled to the stack, so checking the slot_type[7] is the same as checking slot_type[0]. The later patch will allow verifier to save the bounded scalar reg also for <8 bytes spill. There is a llvm patch [1] to ensure the <8 bytes spill will be 8-byte aligned, so checking slot_type[7] instead of slot_type[0] is required. While at it, this patch refactors the slot_type[0] == STACK_SPILL test into a new function is_spilled_reg() and change the slot_type[0] check to slot_type[7] check in there also. [1] https://reviews.llvm.org/D109073 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004934.624194-1-kafai@fb.com --- kernel/bpf/verifier.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e76b55917905..2ad2a12c5482 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -612,6 +612,14 @@ static const char *kernel_type_name(const struct btf* btf, u32 id) return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } +/* The reg state of a pointer or a bounded scalar was saved when + * it was spilled to the stack. + */ +static bool is_spilled_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -717,7 +725,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) { + if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", reg_type_str[t]); @@ -2373,7 +2381,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { - if (func->stack[j].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) @@ -2415,7 +2423,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, } while (spi >= 0) { - if (func->stack[spi].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[spi])) { stack_mask = 0; break; } @@ -2514,7 +2522,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, return 0; } - if (func->stack[i].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[i])) { stack_mask &= ~(1ull << i); continue; } @@ -2713,7 +2721,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ - if (state->stack[spi].slot_type[0] == STACK_SPILL) + if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_MISC; @@ -2923,7 +2931,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; - if (stype[0] == STACK_SPILL) { + if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); @@ -4514,11 +4522,11 @@ static int check_stack_range_initialized( goto mark; } - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) goto mark; - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { @@ -10356,9 +10364,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * return false to continue verification of this path */ return false; - if (i % BPF_REG_SIZE) + if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (old->stack[spi].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&old->stack[spi])) continue; if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) @@ -10565,7 +10573,7 @@ static int propagate_precision(struct bpf_verifier_env *env, } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || From 354e8f1970f821d4952458f77b1ab6c3eb24d530 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:41 -0700 Subject: [PATCH 21/85] bpf: Support <8-byte scalar spill and refill The verifier currently does not save the reg state when spilling <8byte bounded scalar to the stack. The bpf program will be incorrectly rejected when this scalar is refilled to the reg and then used to offset into a packet header. The later patch has a simplified bpf prog from a real use case to demonstrate this case. The current work around is to reparse the packet again such that this offset scalar is close to where the packet data will be accessed to avoid the spill. Thus, the header is parsed twice. The llvm patch [1] will align the <8bytes spill to the 8-byte stack address. This can simplify the verifier support by avoiding to store multiple reg states for each 8 byte stack slot. This patch changes the verifier to save the reg state when spilling <8bytes scalar to the stack. This reg state saving is limited to spill aligned to the 8-byte stack address. The current refill logic has already called coerce_reg_to_size(), so coerce_reg_to_size() is not called on state->stack[spi].spilled_ptr during spill. When refilling in check_stack_read_fixed_off(), it checks the refill size is the same as the number of bytes marked with STACK_SPILL before restoring the reg state. When restoring the reg state to state->regs[dst_regno], it needs to avoid the state->regs[dst_regno].subreg_def being over written because it has been marked by the check_reg_arg() earlier [check_mem_access() is called after check_reg_arg() in do_check()]. Reordering check_mem_access() and check_reg_arg() will need a lot of changes in test_verifier's tests because of the difference in verifier's error message. Thus, the patch here is to save the state->regs[dst_regno].subreg_def first in check_stack_read_fixed_off(). There are cases that the verifier needs to scrub the spilled slot from STACK_SPILL to STACK_MISC. After this patch the spill is not always in 8 bytes now, so it can no longer assume the other 7 bytes are always marked as STACK_SPILL. In particular, the scrub needs to avoid marking an uninitialized byte from STACK_INVALID to STACK_MISC. Otherwise, the verifier will incorrectly accept bpf program reading uninitialized bytes from the stack. A new helper scrub_spilled_slot() is created for this purpose. [1]: https://reviews.llvm.org/D109073 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004941.625398-1-kafai@fb.com --- kernel/bpf/verifier.c | 69 +++++++++++++++++++++++++++++++++---------- 1 file changed, 53 insertions(+), 16 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2ad2a12c5482..7a8351604f67 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -620,6 +620,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static void scrub_spilled_slot(u8 *stype) +{ + if (*stype != STACK_INVALID) + *stype = STACK_MISC; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -2634,15 +2640,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks, } static void save_register_state(struct bpf_func_state *state, - int spi, struct bpf_reg_state *reg) + int spi, struct bpf_reg_state *reg, + int size) { int i; state->stack[spi].spilled_ptr = *reg; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_SPILL; + for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) + state->stack[spi].slot_type[i - 1] = STACK_SPILL; + + /* size < 8 bytes spill */ + for (; i; i--) + scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, @@ -2689,7 +2701,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } - if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit @@ -2702,7 +2714,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -2714,7 +2726,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else { u8 type = STACK_MISC; @@ -2723,7 +2735,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -2926,23 +2938,50 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; - u8 *stype; + u8 *stype, type; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { + u8 scalar_size = 0; + if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } - if (dst_regno >= 0) { - mark_reg_unknown(env, state->regs, dst_regno); - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; - } + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + if (dst_regno < 0) + return 0; + + for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) + scalar_size++; + + if (!(off % BPF_REG_SIZE) && size == scalar_size) { + /* The earlier check_reg_arg() has decided the + * subreg_def for this insn. Save it first. + */ + s32 subreg_def = state->regs[dst_regno].subreg_def; + + state->regs[dst_regno] = *reg; + state->regs[dst_regno].subreg_def = subreg_def; + } else { + for (i = 0; i < size; i++) { + type = stype[(slot - i) % BPF_REG_SIZE]; + if (type == STACK_SPILL) + continue; + if (type == STACK_MISC) + continue; + verbose(env, "invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } + mark_reg_unknown(env, state->regs, dst_regno); + } + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } for (i = 1; i < BPF_REG_SIZE; i++) { @@ -2973,8 +3012,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { - u8 type; - for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) @@ -4532,7 +4569,7 @@ static int check_stack_range_initialized( if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) - state->stack[spi].slot_type[j] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } From 54ea6079b7d5fd5c6d2b98322a892188d6a1db78 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:47 -0700 Subject: [PATCH 22/85] bpf: selftest: A bpf prog that has a 32bit scalar spill It is a simplified example that can trigger a 32bit scalar spill. The const scalar is refilled and added to a skb->data later. Since the reg state of the 32bit scalar spill is not saved now, adding the refilled reg to skb->data and then comparing it with skb->data_end cannot verify the skb->data access. With the earlier verifier patch and the llvm patch [1]. The verifier can correctly verify the bpf prog. Here is the snippet of the verifier log that leads to verifier conclusion that the packet data is unsafe to read. The log is from the kerne without the previous verifier patch to save the <8-byte scalar spill. 67: R0=inv1 R1=inv17 R2=invP2 R3=inv1 R4=pkt(id=0,off=68,r=102,imm=0) R5=inv102 R6=pkt(id=0,off=62,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 67: (63) *(u32 *)(r10 -12) = r5 68: R0=inv1 R1=inv17 R2=invP2 R3=inv1 R4=pkt(id=0,off=68,r=102,imm=0) R5=inv102 R6=pkt(id=0,off=62,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmm???? ... 101: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm 101: (61) r1 = *(u32 *)(r10 -12) 102: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm 102: (bc) w1 = w1 103: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm 103: (0f) r7 += r1 last_idx 103 first_idx 67 regs=2 stack=0 before 102: (bc) w1 = w1 regs=2 stack=0 before 101: (61) r1 = *(u32 *)(r10 -12) 104: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7_w=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm ... 127: R0_w=inv1 R1=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm 127: (bf) r1 = r7 128: R0_w=inv1 R1_w=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm 128: (07) r1 += 8 129: R0_w=inv1 R1_w=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm 129: (b4) w0 = 1 130: R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm 130: (2d) if r1 > r8 goto pc-66 R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm 131: R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm 131: (69) r6 = *(u16 *)(r7 +0) invalid access to packet, off=0 size=2, R7(id=3,off=0,r=0) R7 offset is outside of the packet [1]: https://reviews.llvm.org/D109073 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004947.626286-1-kafai@fb.com --- tools/testing/selftests/bpf/README.rst | 13 + .../selftests/bpf/prog_tests/xdpwall.c | 15 + tools/testing/selftests/bpf/progs/xdpwall.c | 365 ++++++++++++++++++ 3 files changed, 393 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/xdpwall.c create mode 100644 tools/testing/selftests/bpf/progs/xdpwall.c diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 8200c0da2769..554553acc6d9 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -242,3 +242,16 @@ To fix this issue, user newer libbpf. .. Links .. _clang reloc patch: https://reviews.llvm.org/D102712 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst + +Clang dependencies for the u32 spill test (xdpwall) +=================================================== +The xdpwall selftest requires a change in `Clang 14`__. + +Without it, the xdpwall selftest will fail and the error message +from running test_progs will look like: + +.. code-block:: console + + test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007 + +__ https://reviews.llvm.org/D109073 diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c new file mode 100644 index 000000000000..f3927829a55a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "test_progs.h" +#include "xdpwall.skel.h" + +void test_xdpwall(void) +{ + struct xdpwall *skel; + + skel = xdpwall__open_and_load(); + ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?"); + + xdpwall__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c new file mode 100644 index 000000000000..7a891a0c3a39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdpwall.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum pkt_parse_err { + NO_ERR, + BAD_IP6_HDR, + BAD_IP4GUE_HDR, + BAD_IP6GUE_HDR, +}; + +enum pkt_flag { + TUNNEL = 0x1, + TCP_SYN = 0x2, + QUIC_INITIAL_FLAG = 0x4, + TCP_ACK = 0x8, + TCP_RST = 0x10 +}; + +struct v4_lpm_key { + __u32 prefixlen; + __u32 src; +}; + +struct v4_lpm_val { + struct v4_lpm_key key; + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, struct in6_addr); + __type(value, bool); +} v6_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, __u32); + __type(value, bool); +} v4_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(max_entries, 16); + __uint(key_size, sizeof(struct v4_lpm_key)); + __uint(value_size, sizeof(struct v4_lpm_val)); + __uint(map_flags, BPF_F_NO_PREALLOC); +} v4_lpm_val_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u8); +} tcp_port_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u16); +} udp_port_map SEC(".maps"); + +enum ip_type { V4 = 1, V6 = 2 }; + +struct fw_match_info { + __u8 v4_src_ip_match; + __u8 v6_src_ip_match; + __u8 v4_src_prefix_match; + __u8 v4_dst_prefix_match; + __u8 tcp_dp_match; + __u16 udp_sp_match; + __u16 udp_dp_match; + bool is_tcp; + bool is_tcp_syn; +}; + +struct pkt_info { + enum ip_type type; + union { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } ip; + int sport; + int dport; + __u16 trans_hdr_offset; + __u8 proto; + __u8 flags; +}; + +static __always_inline struct ethhdr *parse_ethhdr(void *data, void *data_end) +{ + struct ethhdr *eth = data; + + if (eth + 1 > data_end) + return NULL; + + return eth; +} + +static __always_inline __u8 filter_ipv6_addr(const struct in6_addr *ipv6addr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v6_addr_map, ipv6addr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_addr(const __u32 ipaddr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v4_addr_map, &ipaddr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_lpm(const __u32 ipaddr) +{ + struct v4_lpm_key v4_key = {}; + struct v4_lpm_val *lpm_val; + + v4_key.src = ipaddr; + v4_key.prefixlen = 32; + + lpm_val = bpf_map_lookup_elem(&v4_lpm_val_map, &v4_key); + + return lpm_val ? lpm_val->val : 0; +} + + +static __always_inline void +filter_src_dst_ip(struct pkt_info* info, struct fw_match_info* match_info) +{ + if (info->type == V6) { + match_info->v6_src_ip_match = + filter_ipv6_addr(&info->ip.ipv6->saddr); + } else if (info->type == V4) { + match_info->v4_src_ip_match = + filter_ipv4_addr(info->ip.ipv4->saddr); + match_info->v4_src_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->saddr); + match_info->v4_dst_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->daddr); + } +} + +static __always_inline void * +get_transport_hdr(__u16 offset, void *data, void *data_end) +{ + if (offset > 255 || data + offset > data_end) + return NULL; + + return data + offset; +} + +static __always_inline bool tcphdr_only_contains_flag(struct tcphdr *tcp, + __u32 FLAG) +{ + return (tcp_flag_word(tcp) & + (TCP_FLAG_ACK | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)) == FLAG; +} + +static __always_inline void set_tcp_flags(struct pkt_info *info, + struct tcphdr *tcp) { + if (tcphdr_only_contains_flag(tcp, TCP_FLAG_SYN)) + info->flags |= TCP_SYN; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_ACK)) + info->flags |= TCP_ACK; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_RST)) + info->flags |= TCP_RST; +} + +static __always_inline bool +parse_tcp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct tcphdr *tcp = transport_hdr; + + if (tcp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(tcp->source); + info->dport = bpf_ntohs(tcp->dest); + set_tcp_flags(info, tcp); + + return true; +} + +static __always_inline bool +parse_udp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct udphdr *udp = transport_hdr; + + if (udp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(udp->source); + info->dport = bpf_ntohs(udp->dest); + + return true; +} + +static __always_inline __u8 filter_tcp_port(int port) +{ + __u8 *leaf = bpf_map_lookup_elem(&tcp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline __u16 filter_udp_port(int port) +{ + __u16 *leaf = bpf_map_lookup_elem(&udp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline bool +filter_transport_hdr(void *transport_hdr, void *data_end, + struct pkt_info *info, struct fw_match_info *match_info) +{ + if (info->proto == IPPROTO_TCP) { + if (!parse_tcp(info, transport_hdr, data_end)) + return false; + + match_info->is_tcp = true; + match_info->is_tcp_syn = (info->flags & TCP_SYN) > 0; + + match_info->tcp_dp_match = filter_tcp_port(info->dport); + } else if (info->proto == IPPROTO_UDP) { + if (!parse_udp(info, transport_hdr, data_end)) + return false; + + match_info->udp_dp_match = filter_udp_port(info->dport); + match_info->udp_sp_match = filter_udp_port(info->sport); + } + + return true; +} + +static __always_inline __u8 +parse_gue_v6(struct pkt_info *info, struct ipv6hdr *ip6h, void *data_end) +{ + struct udphdr *udp = (struct udphdr *)(ip6h + 1); + void *encap_data = udp + 1; + + if (udp + 1 > data_end) + return BAD_IP6_HDR; + + if (udp->dest != bpf_htons(6666)) + return NO_ERR; + + info->flags |= TUNNEL; + + if (encap_data + 1 > data_end) + return BAD_IP6GUE_HDR; + + if (*(__u8 *)encap_data & 0x30) { + struct ipv6hdr *inner_ip6h = encap_data; + + if (inner_ip6h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V6; + info->proto = inner_ip6h->nexthdr; + info->ip.ipv6 = inner_ip6h; + info->trans_hdr_offset += sizeof(struct ipv6hdr) + sizeof(struct udphdr); + } else { + struct iphdr *inner_ip4h = encap_data; + + if (inner_ip4h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V4; + info->proto = inner_ip4h->protocol; + info->ip.ipv4 = inner_ip4h; + info->trans_hdr_offset += sizeof(struct iphdr) + sizeof(struct udphdr); + } + + return NO_ERR; +} + +static __always_inline __u8 parse_ipv6_gue(struct pkt_info *info, + void *data, void *data_end) +{ + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + + if (ip6h + 1 > data_end) + return BAD_IP6_HDR; + + info->proto = ip6h->nexthdr; + info->ip.ipv6 = ip6h; + info->type = V6; + info->trans_hdr_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + + if (info->proto == IPPROTO_UDP) + return parse_gue_v6(info, ip6h, data_end); + + return NO_ERR; +} + +SEC("xdp") +int edgewall(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)(ctx->data_end); + void *data = (void *)(long)(ctx->data); + struct fw_match_info match_info = {}; + struct pkt_info info = {}; + __u8 parse_err = NO_ERR; + void *transport_hdr; + struct ethhdr *eth; + bool filter_res; + __u32 proto; + + eth = parse_ethhdr(data, data_end); + if (!eth) + return XDP_DROP; + + proto = eth->h_proto; + if (proto != bpf_htons(ETH_P_IPV6)) + return XDP_DROP; + + if (parse_ipv6_gue(&info, data, data_end)) + return XDP_DROP; + + if (info.proto == IPPROTO_ICMPV6) + return XDP_PASS; + + if (info.proto != IPPROTO_TCP && info.proto != IPPROTO_UDP) + return XDP_DROP; + + filter_src_dst_ip(&info, &match_info); + + transport_hdr = get_transport_hdr(info.trans_hdr_offset, data, + data_end); + if (!transport_hdr) + return XDP_DROP; + + filter_res = filter_transport_hdr(transport_hdr, data_end, + &info, &match_info); + if (!filter_res) + return XDP_DROP; + + if (match_info.is_tcp && !match_info.is_tcp_syn) + return XDP_PASS; + + return XDP_DROP; +} + +char LICENSE[] SEC("license") = "GPL"; From ef979017b837031cbe3f2f7a4d78b00c48dc770b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:53 -0700 Subject: [PATCH 23/85] bpf: selftest: Add verifier tests for <8-byte scalar spill and refill This patch adds a few verifier tests for <8-byte spill and refill. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004953.627183-1-kafai@fb.com --- .../selftests/bpf/verifier/spill_fill.c | 161 ++++++++++++++++++ 1 file changed, 161 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 0b943897aaf6..c9991c3f3bd2 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -104,3 +104,164 @@ .result = ACCEPT, .retval = POINTER_VALUE, }, +{ + "Spill and refill a u32 const scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const, refill from another half of the uninit u32 from the stack", + .insns = { + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -4+0 size 4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -6) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a u32 const scalar at non 8byte aligned stack addr. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* r4 = *(u32 *)(r10 -4), */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a umax=40 bounded scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = (*u32 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r2 += r4 R2=pkt R4=inv,umax=40 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), + /* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20), + /* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1), + /* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, From 10a5e009b93a812956e232cee8804ed99f5b93bb Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:01 +0200 Subject: [PATCH 24/85] xsk: Get rid of unused entry in struct xdp_buff_xsk Get rid of the unused entry "unaligned" in struct xdp_buff_xsk. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-2-magnus.karlsson@gmail.com --- include/net/xsk_buff_pool.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 7a9a23e7a604..bcb29a10307f 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -23,7 +23,6 @@ struct xdp_buff_xsk { dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; - bool unaligned; u64 orig_addr; struct list_head free_list_node; }; From 47e4075df300050a920b99299c4db3dad9adaba9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:02 +0200 Subject: [PATCH 25/85] xsk: Batched buffer allocation for the pool Add a new driver interface xsk_buff_alloc_batch() offering batched buffer allocations to improve performance. The new interface takes three arguments: the buffer pool to allocated from, a pointer to an array of struct xdp_buff pointers which will contain pointers to the allocated xdp_buffs, and an unsigned integer specifying the max number of buffers to allocate. The return value is the actual number of buffers that the allocator managed to allocate and it will be in the range 0 <= N <= max, where max is the third parameter to the function. u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max); A second driver interface is also introduced that need to be used in conjunction with xsk_buff_alloc_batch(). It is a helper that sets the size of struct xdp_buff and is used by the NIC Rx irq routine when receiving a packet. This helper sets the three struct members data, data_meta, and data_end. The two first ones is in the xsk_buff_alloc() case set in the allocation routine and data_end is set when a packet is received in the receive irq function. This unfortunately leads to worse performance since the xdp_buff is touched twice with a long time period in between leading to an extra cache miss. Instead, we fill out the xdp_buff with all 3 fields at one single point in time in the driver, when the size of the packet is known. Hence this helper. Note that the driver has to use this helper (or set all three fields itself) when using xsk_buff_alloc_batch(). xsk_buff_alloc() works as before and does not require this. void xsk_buff_set_size(struct xdp_buff *xdp, u32 size); Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-3-magnus.karlsson@gmail.com --- include/net/xdp_sock_drv.h | 22 ++++++++++ include/net/xsk_buff_pool.h | 1 + net/xdp/xsk_buff_pool.c | 87 +++++++++++++++++++++++++++++++++++++ net/xdp/xsk_queue.h | 12 +++-- 4 files changed, 118 insertions(+), 4 deletions(-) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 4e295541e396..443d45951564 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -77,6 +77,12 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return xp_alloc(pool); } +/* Returns as many entries as possible up to max. 0 <= N <= max. */ +static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + return xp_alloc_batch(pool, xdp, max); +} + static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return xp_can_alloc(pool, count); @@ -89,6 +95,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } +static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) +{ + xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM; + xdp->data_meta = xdp->data; + xdp->data_end = xdp->data + size; +} + static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) { @@ -212,6 +225,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return NULL; } +static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + return 0; +} + static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; @@ -221,6 +239,10 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } +static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) +{ +} + static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index bcb29a10307f..b7068f97639f 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -104,6 +104,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool); +u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count); void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr); dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 8de01aaac4a0..884d95d70f5e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -507,6 +507,93 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) } EXPORT_SYMBOL(xp_alloc); +static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + u32 i, cached_cons, nb_entries; + + if (max > pool->free_heads_cnt) + max = pool->free_heads_cnt; + max = xskq_cons_nb_entries(pool->fq, max); + + cached_cons = pool->fq->cached_cons; + nb_entries = max; + i = max; + while (i--) { + struct xdp_buff_xsk *xskb; + u64 addr; + bool ok; + + __xskq_cons_read_addr_unchecked(pool->fq, cached_cons++, &addr); + + ok = pool->unaligned ? xp_check_unaligned(pool, &addr) : + xp_check_aligned(pool, &addr); + if (unlikely(!ok)) { + pool->fq->invalid_descs++; + nb_entries--; + continue; + } + + xskb = pool->free_heads[--pool->free_heads_cnt]; + *xdp = &xskb->xdp; + xskb->orig_addr = addr; + xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; + xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] & + ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK); + xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; + xdp++; + } + + xskq_cons_release_n(pool->fq, max); + return nb_entries; +} + +static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 nb_entries) +{ + struct xdp_buff_xsk *xskb; + u32 i; + + nb_entries = min_t(u32, nb_entries, pool->free_list_cnt); + + i = nb_entries; + while (i--) { + xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); + list_del(&xskb->free_list_node); + + *xdp = &xskb->xdp; + xdp++; + } + pool->free_list_cnt -= nb_entries; + + return nb_entries; +} + +u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + u32 nb_entries1 = 0, nb_entries2; + + if (unlikely(pool->dma_need_sync)) { + /* Slow path */ + *xdp = xp_alloc(pool); + return !!*xdp; + } + + if (unlikely(pool->free_list_cnt)) { + nb_entries1 = xp_alloc_reused(pool, xdp, max); + if (nb_entries1 == max) + return nb_entries1; + + max -= nb_entries1; + xdp += nb_entries1; + } + + nb_entries2 = xp_alloc_new_from_fq(pool, xdp, max); + if (!nb_entries2) + pool->fq->queue_empty_descs++; + + return nb_entries1 + nb_entries2; +} +EXPORT_SYMBOL(xp_alloc_batch); + bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count) { if (pool->free_list_cnt >= count) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 9ae13cccfb28..e9aa2c236356 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -111,14 +111,18 @@ struct xsk_queue { /* Functions that read and validate content from consumer rings. */ -static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) +static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + u32 idx = cached_cons & q->ring_mask; + *addr = ring->desc[idx]; +} + +static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) +{ if (q->cached_cons != q->cached_prod) { - u32 idx = q->cached_cons & q->ring_mask; - - *addr = ring->desc[idx]; + __xskq_cons_read_addr_unchecked(q, q->cached_cons, addr); return true; } From 57f7f8b6bc0bc80d94443f94fe5f21f266499a2b Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:03 +0200 Subject: [PATCH 26/85] ice: Use xdp_buf instead of rx_buf for xsk zero-copy In order to use the new xsk batched buffer allocation interface, a pointer to an array of struct xsk_buff pointers need to be provided so that the function can put the result of the allocation there. In the ice driver, we already have a ring that stores pointers to xdp_buffs. This is only used for the xsk zero-copy driver and is a union with the structure that is used for the regular non zero-copy path. Unfortunately, that structure is larger than the xdp_buffs pointers which mean that there will be a stride (of 20 bytes) between each xdp_buff pointer. And feeding this into the xsk_buff_alloc_batch interface will not work since it assumes a regular array of xdp_buff pointers (each 8 bytes with 0 bytes in-between them on a 64-bit system). To fix this, remove the xdp_buff pointer from the rx_buf union and move it one step higher to the union above which only has pointers to arrays in it. This solves the problem and we can directly feed the SW ring of xdp_buff pointers straight into the allocation function in the next patch when that interface is used. This will improve performance. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-4-magnus.karlsson@gmail.com --- drivers/net/ethernet/intel/ice/ice_txrx.h | 16 ++----- drivers/net/ethernet/intel/ice/ice_xsk.c | 56 +++++++++++------------ 2 files changed, 33 insertions(+), 39 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 1e46e80f3d6f..7c2328529ff8 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -164,17 +164,10 @@ struct ice_tx_offload_params { }; struct ice_rx_buf { - union { - struct { - dma_addr_t dma; - struct page *page; - unsigned int page_offset; - u16 pagecnt_bias; - }; - struct { - struct xdp_buff *xdp; - }; - }; + dma_addr_t dma; + struct page *page; + unsigned int page_offset; + u16 pagecnt_bias; }; struct ice_q_stats { @@ -270,6 +263,7 @@ struct ice_ring { union { struct ice_tx_buf *tx_buf; struct ice_rx_buf *rx_buf; + struct xdp_buff **xdp_buf; }; /* CL2 - 2nd cacheline starts here */ u16 q_index; /* Queue number of ring */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 5a9f61deeb38..f4ab5259a56c 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -364,7 +364,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; - struct ice_rx_buf *rx_buf; + struct xdp_buff **xdp; bool ok = true; dma_addr_t dma; @@ -372,26 +372,26 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) return true; rx_desc = ICE_RX_DESC(rx_ring, ntu); - rx_buf = &rx_ring->rx_buf[ntu]; + xdp = &rx_ring->xdp_buf[ntu]; do { - rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); - if (!rx_buf->xdp) { + *xdp = xsk_buff_alloc(rx_ring->xsk_pool); + if (!xdp) { ok = false; break; } - dma = xsk_buff_xdp_get_dma(rx_buf->xdp); + dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; rx_desc++; - rx_buf++; + xdp++; ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = ICE_RX_DESC(rx_ring, 0); - rx_buf = rx_ring->rx_buf; + xdp = rx_ring->xdp_buf; ntu = 0; } } while (--count); @@ -421,19 +421,19 @@ static void ice_bump_ntc(struct ice_ring *rx_ring) /** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring - * @rx_buf: zero-copy Rx buffer + * @xdp_arr: Pointer to the SW ring of xdp_buff pointers * * This function allocates a new skb from a zero-copy Rx buffer. * * Returns the skb on success, NULL on failure. */ static struct sk_buff * -ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) +ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr) { - unsigned int metasize = rx_buf->xdp->data - rx_buf->xdp->data_meta; - unsigned int datasize = rx_buf->xdp->data_end - rx_buf->xdp->data; - unsigned int datasize_hard = rx_buf->xdp->data_end - - rx_buf->xdp->data_hard_start; + struct xdp_buff *xdp = *xdp_arr; + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; struct sk_buff *skb; skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, @@ -441,13 +441,13 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) if (unlikely(!skb)) return NULL; - skb_reserve(skb, rx_buf->xdp->data - rx_buf->xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), rx_buf->xdp->data, datasize); + skb_reserve(skb, xdp->data - xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), xdp->data, datasize); if (metasize) skb_metadata_set(skb, metasize); - xsk_buff_free(rx_buf->xdp); - rx_buf->xdp = NULL; + xsk_buff_free(xdp); + *xdp_arr = NULL; return skb; } @@ -521,7 +521,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; - struct ice_rx_buf *rx_buf; + struct xdp_buff **xdp; struct sk_buff *skb; u16 stat_err_bits; u16 vlan_tag = 0; @@ -544,18 +544,18 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) if (!size) break; - rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; - rx_buf->xdp->data_end = rx_buf->xdp->data + size; - xsk_buff_dma_sync_for_cpu(rx_buf->xdp, rx_ring->xsk_pool); + xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean]; + (*xdp)->data_end = (*xdp)->data + size; + xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp); + xdp_res = ice_run_xdp_zc(rx_ring, *xdp); if (xdp_res) { if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) xdp_xmit |= xdp_res; else - xsk_buff_free(rx_buf->xdp); + xsk_buff_free(*xdp); - rx_buf->xdp = NULL; + *xdp = NULL; total_rx_bytes += size; total_rx_packets++; cleaned_count++; @@ -565,7 +565,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) } /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, rx_buf); + skb = ice_construct_skb_zc(rx_ring, xdp); if (!skb) { rx_ring->rx_stats.alloc_buf_failed++; break; @@ -813,12 +813,12 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) u16 i; for (i = 0; i < rx_ring->count; i++) { - struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i]; + struct xdp_buff **xdp = &rx_ring->xdp_buf[i]; - if (!rx_buf->xdp) + if (!xdp) continue; - rx_buf->xdp = NULL; + *xdp = NULL; } } From db804cfc21e969a5a4ada4b8142f711def5ed339 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:04 +0200 Subject: [PATCH 27/85] ice: Use the xsk batched rx allocation interface Use the new xsk batched rx allocation interface for the zero-copy data path. As the array of struct xdp_buff pointers kept by the driver is really a ring that wraps, the allocation routine is modified to detect a wrap and in that case call the allocation function twice. The allocation function cannot deal with wrapped rings, only arrays. As we now know exactly how many buffers we get and that there is no wrapping, the allocation function can be simplified even more as all if-statements in the allocation loop can be removed, improving performance. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-5-magnus.karlsson@gmail.com --- drivers/net/ethernet/intel/ice/ice_xsk.c | 46 +++++++++++------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index f4ab5259a56c..7682eaa9a9ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -365,44 +365,38 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; struct xdp_buff **xdp; - bool ok = true; + u32 nb_buffs, i; dma_addr_t dma; - if (!count) - return true; - rx_desc = ICE_RX_DESC(rx_ring, ntu); xdp = &rx_ring->xdp_buf[ntu]; - do { - *xdp = xsk_buff_alloc(rx_ring->xsk_pool); - if (!xdp) { - ok = false; - break; - } + nb_buffs = min_t(u16, count, rx_ring->count - ntu); + nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs); + if (!nb_buffs) + return false; + i = nb_buffs; + while (i--) { dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); - rx_desc->wb.status_error0 = 0; rx_desc++; xdp++; - ntu++; - - if (unlikely(ntu == rx_ring->count)) { - rx_desc = ICE_RX_DESC(rx_ring, 0); - xdp = rx_ring->xdp_buf; - ntu = 0; - } - } while (--count); - - if (rx_ring->next_to_use != ntu) { - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.status_error0 = 0; - ice_release_rx_desc(rx_ring, ntu); } - return ok; + ntu += nb_buffs; + if (ntu == rx_ring->count) { + rx_desc = ICE_RX_DESC(rx_ring, 0); + xdp = rx_ring->xdp_buf; + ntu = 0; + } + + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.status_error0 = 0; + ice_release_rx_desc(rx_ring, ntu); + + return count == nb_buffs ? true : false; } /** @@ -545,7 +539,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) break; xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean]; - (*xdp)->data_end = (*xdp)->data + size; + xsk_buff_set_size(*xdp, size); xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool); xdp_res = ice_run_xdp_zc(rx_ring, *xdp); From 6aab0bb0c5cdc02d6f182ada2d86afae0c22fc76 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:05 +0200 Subject: [PATCH 28/85] i40e: Use the xsk batched rx allocation interface Use the new xsk batched rx allocation interface for the zero-copy data path. As the array of struct xdp_buff pointers kept by the driver is really a ring that wraps, the allocation routine is modified to detect a wrap and in that case call the allocation function twice. The allocation function cannot deal with wrapped rings, only arrays. As we now know exactly how many buffers we get and that there is no wrapping, the allocation function can be simplified even more as all if-statements in the allocation loop can be removed, improving performance. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-6-magnus.karlsson@gmail.com --- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 54 +++++++++++----------- 1 file changed, 26 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index e7e778ca074c..6f85879ba993 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -193,42 +193,40 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) { u16 ntu = rx_ring->next_to_use; union i40e_rx_desc *rx_desc; - struct xdp_buff **bi, *xdp; + struct xdp_buff **xdp; + u32 nb_buffs, i; dma_addr_t dma; - bool ok = true; rx_desc = I40E_RX_DESC(rx_ring, ntu); - bi = i40e_rx_bi(rx_ring, ntu); - do { - xdp = xsk_buff_alloc(rx_ring->xsk_pool); - if (!xdp) { - ok = false; - goto no_buffers; - } - *bi = xdp; - dma = xsk_buff_xdp_get_dma(xdp); + xdp = i40e_rx_bi(rx_ring, ntu); + + nb_buffs = min_t(u16, count, rx_ring->count - ntu); + nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs); + if (!nb_buffs) + return false; + + i = nb_buffs; + while (i--) { + dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->read.hdr_addr = 0; rx_desc++; - bi++; - ntu++; - - if (unlikely(ntu == rx_ring->count)) { - rx_desc = I40E_RX_DESC(rx_ring, 0); - bi = i40e_rx_bi(rx_ring, 0); - ntu = 0; - } - } while (--count); - -no_buffers: - if (rx_ring->next_to_use != ntu) { - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.qword1.status_error_len = 0; - i40e_release_rx_desc(rx_ring, ntu); + xdp++; } - return ok; + ntu += nb_buffs; + if (ntu == rx_ring->count) { + rx_desc = I40E_RX_DESC(rx_ring, 0); + xdp = i40e_rx_bi(rx_ring, 0); + ntu = 0; + } + + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.qword1.status_error_len = 0; + i40e_release_rx_desc(rx_ring, ntu); + + return count == nb_buffs ? true : false; } /** @@ -365,7 +363,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) break; bi = *i40e_rx_bi(rx_ring, next_to_clean); - bi->data_end = bi->data + size; + xsk_buff_set_size(bi, size); xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool); xdp_res = i40e_run_xdp_zc(rx_ring, bi); From 94033cd8e73b8632bab7c8b7bb54caa4f5616db7 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:06 +0200 Subject: [PATCH 29/85] xsk: Optimize for aligned case Optimize for the aligned case by precomputing the parameter values of the xdp_buff_xsk and xdp_buff structures in the heads array. We can do this as the heads array size is equal to the number of chunks in the umem for the aligned case. Then every entry in this array will reflect a certain chunk/frame and can therefore be prepopulated with the correct values and we can drop the use of the free_heads stack. Note that it is not possible to allocate more buffers than what has been allocated in the aligned case since each chunk can only contain a single buffer. We can unfortunately not do this in the unaligned case as one chunk might contain multiple buffers. In this case, we keep the old scheme of populating a heads entry every time it is used and using the free_heads stack. Also move xp_release() and xp_get_handle() to xsk_buff_pool.h. They were for some reason in xsk.c even though they are buffer pool operations. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-7-magnus.karlsson@gmail.com --- include/net/xsk_buff_pool.h | 46 +++++++++++++++++++++++++++++- net/xdp/xsk.c | 15 ---------- net/xdp/xsk_buff_pool.c | 56 ++++++++++++++++++++++--------------- 3 files changed, 79 insertions(+), 38 deletions(-) diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index b7068f97639f..ddeefc4a1040 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -7,6 +7,7 @@ #include #include #include +#include #include struct xsk_buff_pool; @@ -66,6 +67,7 @@ struct xsk_buff_pool { u32 free_heads_cnt; u32 headroom; u32 chunk_size; + u32 chunk_shift; u32 frame_len; u8 cached_need_wakeup; bool uses_need_wakeup; @@ -80,6 +82,13 @@ struct xsk_buff_pool { struct xdp_buff_xsk *free_heads[]; }; +/* Masks for xdp_umem_page flags. + * The low 12-bits of the addr will be 0 since this is the page address, so we + * can use them for flags. + */ +#define XSK_NEXT_PG_CONTIG_SHIFT 0 +#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) + /* AF_XDP core. */ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); @@ -88,7 +97,6 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); -void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); @@ -98,6 +106,21 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); +static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, + u64 addr) +{ + xskb->orig_addr = addr; + xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; +} + +static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, + dma_addr_t *dma_pages, u64 addr) +{ + xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) + + (addr & ~PAGE_MASK); + xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; +} + /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, @@ -180,4 +203,25 @@ static inline u64 xp_unaligned_add_offset_to_addr(u64 addr) xp_unaligned_extract_offset(addr); } +static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr) +{ + return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift; +} + +static inline void xp_release(struct xdp_buff_xsk *xskb) +{ + if (xskb->pool->unaligned) + xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; +} + +static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) +{ + u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start; + + offset += xskb->pool->headroom; + if (!xskb->pool->unaligned) + return xskb->orig_addr + offset; + return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); +} + #endif /* XSK_BUFF_POOL_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index d6b500dc4208..f16074eb53c7 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -134,21 +134,6 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, return 0; } -void xp_release(struct xdp_buff_xsk *xskb) -{ - xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; -} - -static u64 xp_get_handle(struct xdp_buff_xsk *xskb) -{ - u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start; - - offset += xskb->pool->headroom; - if (!xskb->pool->unaligned) - return xskb->orig_addr + offset; - return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); -} - static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 884d95d70f5e..96b14e51ba7e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -44,12 +44,13 @@ void xp_destroy(struct xsk_buff_pool *pool) struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { + bool unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; - u32 i; + u32 i, entries; - pool = kvzalloc(struct_size(pool, free_heads, umem->chunks), - GFP_KERNEL); + entries = unaligned ? umem->chunks : 0; + pool = kvzalloc(struct_size(pool, free_heads, entries), GFP_KERNEL); if (!pool) goto out; @@ -63,7 +64,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, pool->free_heads_cnt = umem->chunks; pool->headroom = umem->headroom; pool->chunk_size = umem->chunk_size; - pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; + pool->chunk_shift = ffs(umem->chunk_size) - 1; + pool->unaligned = unaligned; pool->frame_len = umem->chunk_size - umem->headroom - XDP_PACKET_HEADROOM; pool->umem = umem; @@ -81,7 +83,10 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, xskb = &pool->heads[i]; xskb->pool = pool; xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; - pool->free_heads[i] = xskb; + if (pool->unaligned) + pool->free_heads[i] = xskb; + else + xp_init_xskb_addr(xskb, pool, i * pool->chunk_size); } return pool; @@ -406,6 +411,12 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, if (pool->unaligned) xp_check_dma_contiguity(dma_map); + else + for (i = 0; i < pool->heads_cnt; i++) { + struct xdp_buff_xsk *xskb = &pool->heads[i]; + + xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr); + } err = xp_init_dma_info(pool, dma_map); if (err) { @@ -448,8 +459,6 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool) if (pool->free_heads_cnt == 0) return NULL; - xskb = pool->free_heads[--pool->free_heads_cnt]; - for (;;) { if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) { pool->fq->queue_empty_descs++; @@ -466,17 +475,17 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool) } break; } - xskq_cons_release(pool->fq); - xskb->orig_addr = addr; - xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; - if (pool->dma_pages_cnt) { - xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] & - ~XSK_NEXT_PG_CONTIG_MASK) + - (addr & ~PAGE_MASK); - xskb->dma = xskb->frame_dma + pool->headroom + - XDP_PACKET_HEADROOM; + if (pool->unaligned) { + xskb = pool->free_heads[--pool->free_heads_cnt]; + xp_init_xskb_addr(xskb, pool, addr); + if (pool->dma_pages_cnt) + xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); + } else { + xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; } + + xskq_cons_release(pool->fq); return xskb; } @@ -533,13 +542,16 @@ static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xd continue; } - xskb = pool->free_heads[--pool->free_heads_cnt]; + if (pool->unaligned) { + xskb = pool->free_heads[--pool->free_heads_cnt]; + xp_init_xskb_addr(xskb, pool, addr); + if (pool->dma_pages_cnt) + xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); + } else { + xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; + } + *xdp = &xskb->xdp; - xskb->orig_addr = addr; - xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; - xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] & - ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK); - xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; xdp++; } From 5b132056123dfe25b0a8c96d1420e9c31cb8edf8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:07 +0200 Subject: [PATCH 30/85] selftests: xsk: Fix missing initialization Fix missing initialization of the member rx_pkt_nb in the packet stream. This leads to some tests declaring success too early as the test thought all packets had already been received. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-8-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 127bcde06c86..97591e2a69f7 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -445,6 +445,12 @@ static void test_spec_set_name(struct test_spec *test, const char *name) strncpy(test->name, name, MAX_TEST_NAME_SIZE); } +static void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) + pkt_stream->rx_pkt_nb = 0; +} + static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) { if (pkt_nb >= pkt_stream->nb_pkts) @@ -1032,6 +1038,7 @@ static void testapp_validate_traffic(struct test_spec *test) exit_with_error(errno); test->current_step++; + pkt_stream_reset(ifobj_rx->pkt_stream); /*Spawn RX thread */ pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); From 872a1184dbf2b6ed9f435d6a37ad8007126da982 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:08 +0200 Subject: [PATCH 31/85] selftests: xsk: Put the same buffer only once in the fill ring Fix a problem where the fill ring was populated with too many entries. If number of buffers in the umem was smaller than the fill ring size, the code used to loop over from the beginning of the umem and start putting the same buffers in again. This is racy indeed as a later packet can be received overwriting an earlier one before the Rx thread manages to validate it. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-9-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 97591e2a69f7..c5c68b860ae0 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -977,13 +977,18 @@ static void *worker_testapp_validate_tx(void *arg) static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) { - u32 idx = 0, i; + u32 idx = 0, i, buffers_to_fill; int ret; - ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) { + for (i = 0; i < buffers_to_fill; i++) { u64 addr; if (pkt_stream->use_addr_for_fill) { @@ -993,12 +998,12 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream break; addr = pkt->addr; } else { - addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET; + addr = i * umem->frame_size + DEFAULT_OFFSET; } *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + xsk_ring_prod__submit(&umem->fq, buffers_to_fill); } static void *worker_testapp_validate_rx(void *arg) From 89013b8a29281fa42e39406b8b25672cb6ce2341 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:09 +0200 Subject: [PATCH 32/85] selftests: xsk: Fix socket creation retry The socket creation retry unnecessarily registered the umem once for every retry. No reason to do this. It wastes memory and it might lead to too many pages being locked at some point and the failure of a test. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-10-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index c5c68b860ae0..aa5660dc0699 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -919,18 +919,17 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; u32 ctr = 0; void *bufs; + int ret; bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); if (bufs == MAP_FAILED) exit_with_error(errno); + ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); + if (ret) + exit_with_error(-ret); + while (ctr++ < SOCK_RECONF_CTR) { - int ret; - - ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); - if (ret) - exit_with_error(-ret); - ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], ifobject, i); if (!ret) From 1bf3649688c103f80690a7088a105924f9d5a6e4 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:10 +0200 Subject: [PATCH 33/85] selftests: xsk: Introduce pacing of traffic Introduce pacing of traffic so that the Tx thread can never send more packets than the receiver has processed plus the number of packets it can have in its umem. So at any point in time, the number of in flight packets (not processed by the Rx thread) are less than or equal to the number of packets that can be held in the Rx thread's umem. The batch size is also increased to improve running time. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-11-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 29 +++++++++++++++++++----- tools/testing/selftests/bpf/xdpxceiver.h | 7 +++++- 2 files changed, 29 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index aa5660dc0699..597fbe206026 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -384,6 +384,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, ifobj->umem = &ifobj->umem_arr[0]; ifobj->xsk = &ifobj->xsk_arr[0]; ifobj->use_poll = false; + ifobj->pacing_on = true; ifobj->pkt_stream = test->pkt_stream_default; if (i == 0) { @@ -724,6 +725,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * { struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); u32 idx_rx = 0, idx_fq = 0, rcvd, i; + u32 total = 0; int ret; while (pkt) { @@ -772,6 +774,13 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= rcvd; + total += rcvd; + if (pkts_in_flight < umem->num_frames) + pthread_cond_signal(&pacing_cond); + pthread_mutex_unlock(&pacing_mutex); } } @@ -797,10 +806,19 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) valid_pkts++; } + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + if (ifobject->pacing_on && pkts_in_flight >= ifobject->umem->num_frames - BATCH_SIZE) { + kick_tx(xsk); + pthread_cond_wait(&pacing_cond, &pacing_mutex); + } + pthread_mutex_unlock(&pacing_mutex); + xsk_ring_prod__submit(&xsk->tx, i); xsk->outstanding_tx += valid_pkts; - complete_pkts(xsk, BATCH_SIZE); + complete_pkts(xsk, i); + usleep(10); return i; } @@ -819,8 +837,6 @@ static void send_pkts(struct ifobject *ifobject) fds.events = POLLOUT; while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - u32 sent; - if (ifobject->use_poll) { int ret; @@ -832,9 +848,7 @@ static void send_pkts(struct ifobject *ifobject) continue; } - sent = __send_pkts(ifobject, pkt_cnt); - pkt_cnt += sent; - usleep(10); + pkt_cnt += __send_pkts(ifobject, pkt_cnt); } wait_for_tx_completion(ifobject->xsk); @@ -1043,6 +1057,7 @@ static void testapp_validate_traffic(struct test_spec *test) test->current_step++; pkt_stream_reset(ifobj_rx->pkt_stream); + pkts_in_flight = 0; /*Spawn RX thread */ pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); @@ -1126,6 +1141,8 @@ static void testapp_stats(struct test_spec *test) for (i = 0; i < STAT_TEST_TYPE_MAX; i++) { test_spec_reset(test); stat_test_type = i; + /* No or few packets will be received so cannot pace packets */ + test->ifobj_tx->pacing_on = false; switch (stat_test_type) { case STAT_TEST_RX_DROPPED: diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 5ac4a5e64744..00790c976f4f 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -35,7 +35,7 @@ #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define BATCH_SIZE 8 +#define BATCH_SIZE 64 #define POLL_TMOUT 1000 #define DEFAULT_PKT_CNT (4 * 1024) #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) @@ -136,6 +136,7 @@ struct ifobject { bool tx_on; bool rx_on; bool use_poll; + bool pacing_on; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -151,5 +152,9 @@ struct test_spec { }; pthread_barrier_t barr; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; +pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; + +u32 pkts_in_flight; #endif /* XDPXCEIVER_H */ From 96a40678ce5390cd8515ff32e55ad932fd1fa328 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:11 +0200 Subject: [PATCH 34/85] selftests: xsk: Add single packet test Add a test where a single packet is sent and received. This might sound like a silly test, but since many of the interfaces in xsk are batched, it is important to be able to validate that we did not break something as fundamental as just receiving single packets, instead of batches of packets at high speed. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-12-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 13 +++++++++++++ tools/testing/selftests/bpf/xdpxceiver.h | 1 + 2 files changed, 14 insertions(+) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 597fbe206026..3beea7531c8e 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -1217,6 +1217,15 @@ static bool testapp_unaligned(struct test_spec *test) return true; } +static void testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); +} + static void testapp_invalid_desc(struct test_spec *test) { struct pkt pkts[] = { @@ -1298,6 +1307,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ test_spec_set_name(test, "RUN_TO_COMPLETION"); testapp_validate_traffic(test); break; + case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: + test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); + testapp_single_pkt(test); + break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 00790c976f4f..d075192c95f8 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -55,6 +55,7 @@ enum test_mode { enum test_type { TEST_TYPE_RUN_TO_COMPLETION, TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME, + TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT, TEST_TYPE_POLL, TEST_TYPE_UNALIGNED, TEST_TYPE_ALIGNED_INV_DESC, From e4e9baf06a6ea6cfbf69db4c3766a0879329dda2 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:12 +0200 Subject: [PATCH 35/85] selftests: xsk: Change interleaving of packets in unaligned mode Change the interleaving of packets in unaligned mode. With the current buffer addresses in the packet stream, the last buffer in the umem could not be used as a large packet could potentially write over the end of the umem. The kernel correctly threw this buffer address away and refused to use it. This is perfectly fine for all regular packet streams, but the ones used for unaligned mode have every other packet being at some different offset. As we will add checks for correct offsets in the next patch, this needs to be fixed. Just start these page-boundary straddling buffers one page earlier so that the last one is not on the last page of the umem, making all buffers valid. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-13-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 3beea7531c8e..fd620f8accfd 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -543,14 +543,14 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) test->ifobj_rx->pkt_stream = pkt_stream; } -static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset) +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) { struct xsk_umem_info *umem = test->ifobj_tx->umem; struct pkt_stream *pkt_stream; u32 i; pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default); - for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) { + for (i = 1; i < test->pkt_stream_default->nb_pkts; i += 2) { pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset; pkt_stream->pkts[i].len = pkt_len; } @@ -1209,7 +1209,7 @@ static bool testapp_unaligned(struct test_spec *test) test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32); + pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); test->ifobj_rx->pkt_stream->use_addr_for_fill = true; testapp_validate_traffic(test); From e34087fc00f4f853886952711195984abdece7a3 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 22 Sep 2021 09:56:13 +0200 Subject: [PATCH 36/85] selftests: xsk: Add frame_headroom test Add a test for the frame_headroom feature that can be set on the umem. The logic added validates that all offsets in all tests and packets are valid, not just the ones that have a specifically configured frame_headroom. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922075613.12186-14-magnus.karlsson@gmail.com --- tools/testing/selftests/bpf/xdpxceiver.c | 52 +++++++++++++++++++----- tools/testing/selftests/bpf/xdpxceiver.h | 3 +- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index fd620f8accfd..6c7cf8aadc79 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -514,8 +514,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb pkt_stream->nb_pkts = nb_pkts; for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + - DEFAULT_OFFSET; + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size; pkt_stream->pkts[i].len = pkt_len; pkt_stream->pkts[i].payload = i; @@ -642,6 +641,25 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "---------------------------------------\n"); } +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, + u64 pkt_stream_addr) +{ + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset = 0; + + if (!pkt_stream->use_addr_for_fill) + pkt_stream_addr = 0; + + expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_test_result_fail("ERROR: [%s] expected [%u], got [%u]\n", __func__, expected_offset, + offset); + return false; +} + static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); @@ -724,6 +742,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * struct pollfd *fds) { struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); + struct xsk_umem_info *umem = xsk->umem; u32 idx_rx = 0, idx_fq = 0, rcvd, i; u32 total = 0; int ret; @@ -731,7 +750,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * while (pkt) { rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); @@ -739,16 +758,16 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * continue; } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } for (i = 0; i < rcvd; i++) { @@ -765,14 +784,17 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len)) + + if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len)) + return; + if (!is_offset_correct(umem, pkt_stream, addr, pkt->addr)) return; - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; pkt = pkt_stream_get_next_rx_pkt(pkt_stream); } - xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_prod__submit(&umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); pthread_mutex_lock(&pacing_mutex); @@ -1011,7 +1033,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream break; addr = pkt->addr; } else { - addr = i * umem->frame_size + DEFAULT_OFFSET; + addr = i * umem->frame_size; } *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; @@ -1134,6 +1156,13 @@ static void testapp_bpf_res(struct test_spec *test) testapp_validate_traffic(test); } +static void testapp_headroom(struct test_spec *test) +{ + test_spec_set_name(test, "UMEM_HEADROOM"); + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + testapp_validate_traffic(test); +} + static void testapp_stats(struct test_spec *test) { int i; @@ -1346,6 +1375,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ if (!testapp_unaligned(test)) return; break; + case TEST_TYPE_HEADROOM: + testapp_headroom(test); + break; default: break; } diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index d075192c95f8..2f705f44b748 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -41,7 +41,7 @@ #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) #define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE) #define RX_FULL_RXQSIZE 32 -#define DEFAULT_OFFSET 256 +#define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -61,6 +61,7 @@ enum test_type { TEST_TYPE_ALIGNED_INV_DESC, TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME, TEST_TYPE_UNALIGNED_INV_DESC, + TEST_TYPE_HEADROOM, TEST_TYPE_TEARDOWN, TEST_TYPE_BIDI, TEST_TYPE_STATS, From c3e8c44a90631d2479fec6ecc6ba37e3188f487d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 27 Sep 2021 22:58:10 +0200 Subject: [PATCH 37/85] libbpf: Ignore STT_SECTION symbols in 'maps' section MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When parsing legacy map definitions, libbpf would error out when encountering an STT_SECTION symbol. This becomes a problem because some versions of binutils will produce SECTION symbols for every section when processing an ELF file, so BPF files run through 'strip' will end up with such symbols, making libbpf refuse to load them. There's not really any reason why erroring out is strictly necessary, so change libbpf to just ignore SECTION symbols when parsing the ELF. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210927205810.715656-1-toke@redhat.com --- tools/lib/bpf/libbpf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ef5db34bf913..453148fe8b4b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1869,6 +1869,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -1881,8 +1883,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } - if (GELF_ST_TYPE(sym.st_info) == STT_SECTION - || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + if (GELF_ST_BIND(sym.st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; } From c2a228d69cef802cf6bfd773c84f8419d2e2acf9 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:29 +0200 Subject: [PATCH 38/85] bpf/tests: Allow different number of runs per test case This patch allows a test cast to specify the number of runs to use. For compatibility with existing test case definitions, the default value 0 is interpreted as MAX_TESTRUNS. A reduced number of runs is useful for complex test programs where 1000 runs may take a very long time. Instead of reducing what is tested, one can instead reduce the number of times the test is run. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-2-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 0018d51b93b0..a406cbb2e34d 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -80,6 +80,7 @@ struct bpf_test { int expected_errcode; /* used when FLAG_EXPECTED_FAIL is set in the aux */ __u8 frag_data[MAX_DATA]; int stack_depth; /* for eBPF only, since tests don't call verifier */ + int nr_testruns; /* Custom run count, defaults to MAX_TESTRUNS if 0 */ }; /* Large test cases need separate allocation and fill handler. */ @@ -8631,6 +8632,9 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test) { int err_cnt = 0, i, runs = MAX_TESTRUNS; + if (test->nr_testruns) + runs = min(test->nr_testruns, MAX_TESTRUNS); + for (i = 0; i < MAX_SUBTESTS; i++) { void *data; u64 duration; From 4bc354138d553bc48dc1fb1e184d50a524e6c20f Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:30 +0200 Subject: [PATCH 39/85] bpf/tests: Reduce memory footprint of test suite The test suite used to call any fill_helper callbacks to generate eBPF program data for all test cases at once. This caused ballooning memory requirements as more extensive test cases were added. Now the each fill_helper is called before the test is run and the allocated memory released afterwards, before the next test case is processed. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-3-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index a406cbb2e34d..c865fd584adb 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -8694,8 +8694,6 @@ static __init int find_test_index(const char *test_name) static __init int prepare_bpf_tests(void) { - int i; - if (test_id >= 0) { /* * if a test_id was specified, use test_range to @@ -8739,23 +8737,11 @@ static __init int prepare_bpf_tests(void) } } - for (i = 0; i < ARRAY_SIZE(tests); i++) { - if (tests[i].fill_helper && - tests[i].fill_helper(&tests[i]) < 0) - return -ENOMEM; - } - return 0; } static __init void destroy_bpf_tests(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(tests); i++) { - if (tests[i].fill_helper) - kfree(tests[i].u.ptr.insns); - } } static bool exclude_test(int test_id) @@ -8960,7 +8946,19 @@ static __init int test_bpf(void) pr_info("#%d %s ", i, tests[i].descr); + if (tests[i].fill_helper && + tests[i].fill_helper(&tests[i]) < 0) { + pr_cont("FAIL to prog_fill\n"); + continue; + } + fp = generate_filter(i, &err); + + if (tests[i].fill_helper) { + kfree(tests[i].u.ptr.insns); + tests[i].u.ptr.insns = NULL; + } + if (fp == NULL) { if (err == 0) { pass_cnt++; From 68c956fe741757b760aa00fca8725c5651f5f77a Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:31 +0200 Subject: [PATCH 40/85] bpf/tests: Add exhaustive tests of ALU shift values This patch adds a set of tests for ALU64 and ALU32 shift operations to verify correctness for all possible values of the shift value. Mainly intended for JIT testing. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-4-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 260 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 260 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index c865fd584adb..d599c2a8c860 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -497,6 +497,168 @@ static int bpf_fill_long_jmp(struct bpf_test *self) return 0; } +static int __bpf_ld_imm64(struct bpf_insn insns[2], u8 reg, s64 imm64) +{ + struct bpf_insn tmp[] = {BPF_LD_IMM64(reg, imm64)}; + + memcpy(insns, tmp, sizeof(tmp)); + return 2; +} + +/* Test an ALU shift operation for all valid shift values */ +static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op, + u8 mode, bool alu32) +{ + static const s64 regs[] = { + 0x0123456789abcdefLL, /* dword > 0, word < 0 */ + 0xfedcba9876543210LL, /* dowrd < 0, word > 0 */ + 0xfedcba0198765432LL, /* dowrd < 0, word < 0 */ + 0x0123458967abcdefLL, /* dword > 0, word > 0 */ + }; + int bits = alu32 ? 32 : 64; + int len = (2 + 7 * bits) * ARRAY_SIZE(regs) + 3; + struct bpf_insn *insn; + int imm, k; + int i = 0; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 0); + + for (k = 0; k < ARRAY_SIZE(regs); k++) { + s64 reg = regs[k]; + + i += __bpf_ld_imm64(&insn[i], R3, reg); + + for (imm = 0; imm < bits; imm++) { + u64 val; + + /* Perform operation */ + insn[i++] = BPF_ALU64_REG(BPF_MOV, R1, R3); + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R2, imm); + if (alu32) { + if (mode == BPF_K) + insn[i++] = BPF_ALU32_IMM(op, R1, imm); + else + insn[i++] = BPF_ALU32_REG(op, R1, R2); + switch (op) { + case BPF_LSH: + val = (u32)reg << imm; + break; + case BPF_RSH: + val = (u32)reg >> imm; + break; + case BPF_ARSH: + val = (u32)reg >> imm; + if (imm > 0 && (reg & 0x80000000)) + val |= ~(u32)0 << (32 - imm); + break; + } + } else { + if (mode == BPF_K) + insn[i++] = BPF_ALU64_IMM(op, R1, imm); + else + insn[i++] = BPF_ALU64_REG(op, R1, R2); + switch (op) { + case BPF_LSH: + val = (u64)reg << imm; + break; + case BPF_RSH: + val = (u64)reg >> imm; + break; + case BPF_ARSH: + val = (u64)reg >> imm; + if (imm > 0 && reg < 0) + val |= ~(u64)0 << (64 - imm); + break; + } + } + + /* + * When debugging a JIT that fails this test, one + * can write the immediate value to R0 here to find + * out which operand values that fail. + */ + + /* Load reference and check the result */ + i += __bpf_ld_imm64(&insn[i], R4, val); + insn[i++] = BPF_JMP_REG(BPF_JEQ, R1, R4, 1); + insn[i++] = BPF_EXIT_INSN(); + } + } + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 1); + insn[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + BUG_ON(i > len); + + return 0; +} + +static int bpf_fill_alu_lsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_LSH, BPF_K, false); +} + +static int bpf_fill_alu_rsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_RSH, BPF_K, false); +} + +static int bpf_fill_alu_arsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_K, false); +} + +static int bpf_fill_alu_lsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_LSH, BPF_X, false); +} + +static int bpf_fill_alu_rsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_RSH, BPF_X, false); +} + +static int bpf_fill_alu_arsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_X, false); +} + +static int bpf_fill_alu32_lsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_LSH, BPF_K, true); +} + +static int bpf_fill_alu32_rsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_RSH, BPF_K, true); +} + +static int bpf_fill_alu32_arsh_imm(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_K, true); +} + +static int bpf_fill_alu32_lsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_LSH, BPF_X, true); +} + +static int bpf_fill_alu32_rsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_RSH, BPF_X, true); +} + +static int bpf_fill_alu32_arsh_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_X, true); +} + static struct bpf_test tests[] = { { "TAX", @@ -8414,6 +8576,104 @@ static struct bpf_test tests[] = { {}, { { 0, 2 } }, }, + /* Exhaustive test of ALU64 shift operations */ + { + "ALU64_LSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_lsh_imm, + }, + { + "ALU64_RSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_rsh_imm, + }, + { + "ALU64_ARSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_arsh_imm, + }, + { + "ALU64_LSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_lsh_reg, + }, + { + "ALU64_RSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_rsh_reg, + }, + { + "ALU64_ARSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu_arsh_reg, + }, + /* Exhaustive test of ALU32 shift operations */ + { + "ALU32_LSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_lsh_imm, + }, + { + "ALU32_RSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_rsh_imm, + }, + { + "ALU32_ARSH_K: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_arsh_imm, + }, + { + "ALU32_LSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_lsh_reg, + }, + { + "ALU32_RSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_rsh_reg, + }, + { + "ALU32_ARSH_X: all shift values", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_arsh_reg, + }, }; static struct net_device dev; From 9298e63eafea1ebe235919dbbbfc20c1c25000f8 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:32 +0200 Subject: [PATCH 41/85] bpf/tests: Add exhaustive tests of ALU operand magnitudes This patch adds a set of tests for ALU64 and ALU32 arithmetic and bitwise logical operations to verify correctness for all possible magnitudes of the register and immediate operands. Mainly intended for JIT testing. The patch introduces a pattern generator that can be used to drive extensive tests of different kinds of operations. It is parameterized to allow tuning of the operand combinations to test. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-5-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 772 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 772 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index d599c2a8c860..228e681e84b7 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -659,6 +659,451 @@ static int bpf_fill_alu32_arsh_reg(struct bpf_test *self) return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_X, true); } +/* + * Common operand pattern generator for exhaustive power-of-two magnitudes + * tests. The block size parameters can be adjusted to increase/reduce the + * number of combinatons tested and thereby execution speed and memory + * footprint. + */ + +static inline s64 value(int msb, int delta, int sign) +{ + return sign * (1LL << msb) + delta; +} + +static int __bpf_fill_pattern(struct bpf_test *self, void *arg, + int dbits, int sbits, int block1, int block2, + int (*emit)(struct bpf_test*, void*, + struct bpf_insn*, s64, s64)) +{ + static const int sgn[][2] = {{1, 1}, {1, -1}, {-1, 1}, {-1, -1}}; + struct bpf_insn *insns; + int di, si, bt, db, sb; + int count, len, k; + int extra = 1 + 2; + int i = 0; + + /* Total number of iterations for the two pattern */ + count = (dbits - 1) * (sbits - 1) * block1 * block1 * ARRAY_SIZE(sgn); + count += (max(dbits, sbits) - 1) * block2 * block2 * ARRAY_SIZE(sgn); + + /* Compute the maximum number of insns and allocate the buffer */ + len = extra + count * (*emit)(self, arg, NULL, 0, 0); + insns = kmalloc_array(len, sizeof(*insns), GFP_KERNEL); + if (!insns) + return -ENOMEM; + + /* Add head instruction(s) */ + insns[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 0); + + /* + * Pattern 1: all combinations of power-of-two magnitudes and sign, + * and with a block of contiguous values around each magnitude. + */ + for (di = 0; di < dbits - 1; di++) /* Dst magnitudes */ + for (si = 0; si < sbits - 1; si++) /* Src magnitudes */ + for (k = 0; k < ARRAY_SIZE(sgn); k++) /* Sign combos */ + for (db = -(block1 / 2); + db < (block1 + 1) / 2; db++) + for (sb = -(block1 / 2); + sb < (block1 + 1) / 2; sb++) { + s64 dst, src; + + dst = value(di, db, sgn[k][0]); + src = value(si, sb, sgn[k][1]); + i += (*emit)(self, arg, + &insns[i], + dst, src); + } + /* + * Pattern 2: all combinations for a larger block of values + * for each power-of-two magnitude and sign, where the magnitude is + * the same for both operands. + */ + for (bt = 0; bt < max(dbits, sbits) - 1; bt++) /* Magnitude */ + for (k = 0; k < ARRAY_SIZE(sgn); k++) /* Sign combos */ + for (db = -(block2 / 2); db < (block2 + 1) / 2; db++) + for (sb = -(block2 / 2); + sb < (block2 + 1) / 2; sb++) { + s64 dst, src; + + dst = value(bt % dbits, db, sgn[k][0]); + src = value(bt % sbits, sb, sgn[k][1]); + i += (*emit)(self, arg, &insns[i], + dst, src); + } + + /* Append tail instructions */ + insns[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 1); + insns[i++] = BPF_EXIT_INSN(); + BUG_ON(i > len); + + self->u.ptr.insns = insns; + self->u.ptr.len = i; + + return 0; +} + +/* + * Block size parameters used in pattern tests below. une as needed to + * increase/reduce the number combinations tested, see following examples. + * block values per operand MSB + * ---------------------------------------- + * 0 none + * 1 (1 << MSB) + * 2 (1 << MSB) + [-1, 0] + * 3 (1 << MSB) + [-1, 0, 1] + */ +#define PATTERN_BLOCK1 1 +#define PATTERN_BLOCK2 5 + +/* Number of test runs for a pattern test */ +#define NR_PATTERN_RUNS 1 + +/* + * Exhaustive tests of ALU operations for all combinations of power-of-two + * magnitudes of the operands, both for positive and negative values. The + * test is designed to verify e.g. the JMP and JMP32 operations for JITs that + * emit different code depending on the magnitude of the immediate value. + */ + +static bool __bpf_alu_result(u64 *res, u64 v1, u64 v2, u8 op) +{ + *res = 0; + switch (op) { + case BPF_MOV: + *res = v2; + break; + case BPF_AND: + *res = v1 & v2; + break; + case BPF_OR: + *res = v1 | v2; + break; + case BPF_XOR: + *res = v1 ^ v2; + break; + case BPF_ADD: + *res = v1 + v2; + break; + case BPF_SUB: + *res = v1 - v2; + break; + case BPF_MUL: + *res = v1 * v2; + break; + case BPF_DIV: + if (v2 == 0) + return false; + *res = div64_u64(v1, v2); + break; + case BPF_MOD: + if (v2 == 0) + return false; + div64_u64_rem(v1, v2, res); + break; + } + return true; +} + +static int __bpf_emit_alu64_imm(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 imm) +{ + int op = *(int *)arg; + int i = 0; + u64 res; + + if (!insns) + return 7; + + if (__bpf_alu_result(&res, dst, (s32)imm, op)) { + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R3, res); + insns[i++] = BPF_ALU64_IMM(op, R1, imm); + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + } + + return i; +} + +static int __bpf_emit_alu32_imm(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 imm) +{ + int op = *(int *)arg; + int i = 0; + u64 res; + + if (!insns) + return 7; + + if (__bpf_alu_result(&res, (u32)dst, (u32)imm, op)) { + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R3, (u32)res); + insns[i++] = BPF_ALU32_IMM(op, R1, imm); + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + } + + return i; +} + +static int __bpf_emit_alu64_reg(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + int i = 0; + u64 res; + + if (!insns) + return 9; + + if (__bpf_alu_result(&res, dst, src, op)) { + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + i += __bpf_ld_imm64(&insns[i], R3, res); + insns[i++] = BPF_ALU64_REG(op, R1, R2); + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + } + + return i; +} + +static int __bpf_emit_alu32_reg(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + int i = 0; + u64 res; + + if (!insns) + return 9; + + if (__bpf_alu_result(&res, (u32)dst, (u32)src, op)) { + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + i += __bpf_ld_imm64(&insns[i], R3, (u32)res); + insns[i++] = BPF_ALU32_REG(op, R1, R2); + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + } + + return i; +} + +static int __bpf_fill_alu64_imm(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 32, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_alu64_imm); +} + +static int __bpf_fill_alu32_imm(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 32, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_alu32_imm); +} + +static int __bpf_fill_alu64_reg(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_alu64_reg); +} + +static int __bpf_fill_alu32_reg(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_alu32_reg); +} + +/* ALU64 immediate operations */ +static int bpf_fill_alu64_mov_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_MOV); +} + +static int bpf_fill_alu64_and_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_AND); +} + +static int bpf_fill_alu64_or_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_OR); +} + +static int bpf_fill_alu64_xor_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_XOR); +} + +static int bpf_fill_alu64_add_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_ADD); +} + +static int bpf_fill_alu64_sub_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_SUB); +} + +static int bpf_fill_alu64_mul_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_MUL); +} + +static int bpf_fill_alu64_div_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_DIV); +} + +static int bpf_fill_alu64_mod_imm(struct bpf_test *self) +{ + return __bpf_fill_alu64_imm(self, BPF_MOD); +} + +/* ALU32 immediate operations */ +static int bpf_fill_alu32_mov_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_MOV); +} + +static int bpf_fill_alu32_and_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_AND); +} + +static int bpf_fill_alu32_or_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_OR); +} + +static int bpf_fill_alu32_xor_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_XOR); +} + +static int bpf_fill_alu32_add_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_ADD); +} + +static int bpf_fill_alu32_sub_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_SUB); +} + +static int bpf_fill_alu32_mul_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_MUL); +} + +static int bpf_fill_alu32_div_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_DIV); +} + +static int bpf_fill_alu32_mod_imm(struct bpf_test *self) +{ + return __bpf_fill_alu32_imm(self, BPF_MOD); +} + +/* ALU64 register operations */ +static int bpf_fill_alu64_mov_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_MOV); +} + +static int bpf_fill_alu64_and_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_AND); +} + +static int bpf_fill_alu64_or_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_OR); +} + +static int bpf_fill_alu64_xor_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_XOR); +} + +static int bpf_fill_alu64_add_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_ADD); +} + +static int bpf_fill_alu64_sub_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_SUB); +} + +static int bpf_fill_alu64_mul_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_MUL); +} + +static int bpf_fill_alu64_div_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_DIV); +} + +static int bpf_fill_alu64_mod_reg(struct bpf_test *self) +{ + return __bpf_fill_alu64_reg(self, BPF_MOD); +} + +/* ALU32 register operations */ +static int bpf_fill_alu32_mov_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_MOV); +} + +static int bpf_fill_alu32_and_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_AND); +} + +static int bpf_fill_alu32_or_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_OR); +} + +static int bpf_fill_alu32_xor_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_XOR); +} + +static int bpf_fill_alu32_add_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_ADD); +} + +static int bpf_fill_alu32_sub_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_SUB); +} + +static int bpf_fill_alu32_mul_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_MUL); +} + +static int bpf_fill_alu32_div_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_DIV); +} + +static int bpf_fill_alu32_mod_reg(struct bpf_test *self) +{ + return __bpf_fill_alu32_reg(self, BPF_MOD); +} + static struct bpf_test tests[] = { { "TAX", @@ -8674,6 +9119,333 @@ static struct bpf_test tests[] = { { { 0, 1 } }, .fill_helper = bpf_fill_alu32_arsh_reg, }, + /* ALU64 immediate magnitudes */ + { + "ALU64_MOV_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mov_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_AND_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_and_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_OR_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_or_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_XOR_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_xor_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_ADD_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_add_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_SUB_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_sub_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_MUL_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mul_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_DIV_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_div_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_MOD_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mod_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* ALU32 immediate magnitudes */ + { + "ALU32_MOV_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mov_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_AND_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_and_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_OR_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_or_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_XOR_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_xor_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_ADD_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_add_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_SUB_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_sub_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_MUL_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mul_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_DIV_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_div_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_MOD_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mod_imm, + }, + /* ALU64 register magnitudes */ + { + "ALU64_MOV_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mov_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_AND_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_and_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_OR_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_or_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_XOR_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_xor_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_ADD_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_add_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_SUB_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_sub_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_MUL_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mul_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_DIV_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_div_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU64_MOD_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mod_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* ALU32 register magnitudes */ + { + "ALU32_MOV_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mov_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_AND_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_and_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_OR_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_or_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_XOR_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_xor_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_ADD_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_add_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_SUB_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_sub_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_MUL_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mul_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_DIV_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_div_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ALU32_MOD_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mod_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, }; static struct net_device dev; From a5a36544de38057b8e8de8fb6b2bcd9c102640f4 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:33 +0200 Subject: [PATCH 42/85] bpf/tests: Add exhaustive tests of JMP operand magnitudes This patch adds a set of tests for conditional JMP and JMP32 operations to verify correctness for all possible magnitudes of the immediate and register operands. Mainly intended for JIT testing. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-6-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 779 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 779 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 228e681e84b7..fb27a25e2c0c 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1104,6 +1104,384 @@ static int bpf_fill_alu32_mod_reg(struct bpf_test *self) return __bpf_fill_alu32_reg(self, BPF_MOD); } + +/* + * Exhaustive tests of JMP operations for all combinations of power-of-two + * magnitudes of the operands, both for positive and negative values. The + * test is designed to verify e.g. the JMP and JMP32 operations for JITs that + * emit different code depending on the magnitude of the immediate value. + */ + +static bool __bpf_match_jmp_cond(s64 v1, s64 v2, u8 op) +{ + switch (op) { + case BPF_JSET: + return !!(v1 & v2); + case BPF_JEQ: + return v1 == v2; + case BPF_JNE: + return v1 != v2; + case BPF_JGT: + return (u64)v1 > (u64)v2; + case BPF_JGE: + return (u64)v1 >= (u64)v2; + case BPF_JLT: + return (u64)v1 < (u64)v2; + case BPF_JLE: + return (u64)v1 <= (u64)v2; + case BPF_JSGT: + return v1 > v2; + case BPF_JSGE: + return v1 >= v2; + case BPF_JSLT: + return v1 < v2; + case BPF_JSLE: + return v1 <= v2; + } + return false; +} + +static int __bpf_emit_jmp_imm(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 imm) +{ + int op = *(int *)arg; + + if (insns) { + bool match = __bpf_match_jmp_cond(dst, (s32)imm, op); + int i = 0; + + insns[i++] = BPF_ALU32_IMM(BPF_MOV, R0, match); + + i += __bpf_ld_imm64(&insns[i], R1, dst); + insns[i++] = BPF_JMP_IMM(op, R1, imm, 1); + if (!match) + insns[i++] = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; + } + + return 5 + 1; +} + +static int __bpf_emit_jmp32_imm(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 imm) +{ + int op = *(int *)arg; + + if (insns) { + bool match = __bpf_match_jmp_cond((s32)dst, (s32)imm, op); + int i = 0; + + i += __bpf_ld_imm64(&insns[i], R1, dst); + insns[i++] = BPF_JMP32_IMM(op, R1, imm, 1); + if (!match) + insns[i++] = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; + } + + return 5; +} + +static int __bpf_emit_jmp_reg(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + + if (insns) { + bool match = __bpf_match_jmp_cond(dst, src, op); + int i = 0; + + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + insns[i++] = BPF_JMP_REG(op, R1, R2, 1); + if (!match) + insns[i++] = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; + } + + return 7; +} + +static int __bpf_emit_jmp32_reg(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + + if (insns) { + bool match = __bpf_match_jmp_cond((s32)dst, (s32)src, op); + int i = 0; + + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + insns[i++] = BPF_JMP32_REG(op, R1, R2, 1); + if (!match) + insns[i++] = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; + } + + return 7; +} + +static int __bpf_fill_jmp_imm(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 32, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_jmp_imm); +} + +static int __bpf_fill_jmp32_imm(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 32, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_jmp32_imm); +} + +static int __bpf_fill_jmp_reg(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_jmp_reg); +} + +static int __bpf_fill_jmp32_reg(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + PATTERN_BLOCK1, PATTERN_BLOCK2, + &__bpf_emit_jmp32_reg); +} + +/* JMP immediate tests */ +static int bpf_fill_jmp_jset_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JSET); +} + +static int bpf_fill_jmp_jeq_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JEQ); +} + +static int bpf_fill_jmp_jne_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JNE); +} + +static int bpf_fill_jmp_jgt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JGT); +} + +static int bpf_fill_jmp_jge_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JGE); +} + +static int bpf_fill_jmp_jlt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JLT); +} + +static int bpf_fill_jmp_jle_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JLE); +} + +static int bpf_fill_jmp_jsgt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JSGT); +} + +static int bpf_fill_jmp_jsge_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JSGE); +} + +static int bpf_fill_jmp_jslt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JSLT); +} + +static int bpf_fill_jmp_jsle_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp_imm(self, BPF_JSLE); +} + +/* JMP32 immediate tests */ +static int bpf_fill_jmp32_jset_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JSET); +} + +static int bpf_fill_jmp32_jeq_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JEQ); +} + +static int bpf_fill_jmp32_jne_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JNE); +} + +static int bpf_fill_jmp32_jgt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JGT); +} + +static int bpf_fill_jmp32_jge_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JGE); +} + +static int bpf_fill_jmp32_jlt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JLT); +} + +static int bpf_fill_jmp32_jle_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JLE); +} + +static int bpf_fill_jmp32_jsgt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JSGT); +} + +static int bpf_fill_jmp32_jsge_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JSGE); +} + +static int bpf_fill_jmp32_jslt_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JSLT); +} + +static int bpf_fill_jmp32_jsle_imm(struct bpf_test *self) +{ + return __bpf_fill_jmp32_imm(self, BPF_JSLE); +} + +/* JMP register tests */ +static int bpf_fill_jmp_jset_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JSET); +} + +static int bpf_fill_jmp_jeq_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JEQ); +} + +static int bpf_fill_jmp_jne_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JNE); +} + +static int bpf_fill_jmp_jgt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JGT); +} + +static int bpf_fill_jmp_jge_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JGE); +} + +static int bpf_fill_jmp_jlt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JLT); +} + +static int bpf_fill_jmp_jle_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JLE); +} + +static int bpf_fill_jmp_jsgt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JSGT); +} + +static int bpf_fill_jmp_jsge_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JSGE); +} + +static int bpf_fill_jmp_jslt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JSLT); +} + +static int bpf_fill_jmp_jsle_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp_reg(self, BPF_JSLE); +} + +/* JMP32 register tests */ +static int bpf_fill_jmp32_jset_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JSET); +} + +static int bpf_fill_jmp32_jeq_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JEQ); +} + +static int bpf_fill_jmp32_jne_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JNE); +} + +static int bpf_fill_jmp32_jgt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JGT); +} + +static int bpf_fill_jmp32_jge_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JGE); +} + +static int bpf_fill_jmp32_jlt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JLT); +} + +static int bpf_fill_jmp32_jle_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JLE); +} + +static int bpf_fill_jmp32_jsgt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JSGT); +} + +static int bpf_fill_jmp32_jsge_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JSGE); +} + +static int bpf_fill_jmp32_jslt_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JSLT); +} + +static int bpf_fill_jmp32_jsle_reg(struct bpf_test *self) +{ + return __bpf_fill_jmp32_reg(self, BPF_JSLE); +} + + static struct bpf_test tests[] = { { "TAX", @@ -9281,6 +9659,7 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, .fill_helper = bpf_fill_alu32_mod_imm, + .nr_testruns = NR_PATTERN_RUNS, }, /* ALU64 register magnitudes */ { @@ -9446,6 +9825,406 @@ static struct bpf_test tests[] = { .fill_helper = bpf_fill_alu32_mod_reg, .nr_testruns = NR_PATTERN_RUNS, }, + /* JMP immediate magnitudes */ + { + "JMP_JSET_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jset_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JEQ_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jeq_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JNE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jne_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JGT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jgt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JGE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jge_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JLT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jlt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JLE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jle_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSGT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsgt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSGE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsge_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSLT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jslt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSLE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsle_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* JMP register magnitudes */ + { + "JMP_JSET_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jset_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JEQ_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jeq_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JNE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jne_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JGT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jgt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JGE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jge_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JLT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jlt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JLE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jle_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSGT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsgt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSGE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsge_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSLT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jslt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP_JSLE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp_jsle_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* JMP32 immediate magnitudes */ + { + "JMP32_JSET_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jset_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JEQ_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jeq_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JNE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jne_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JGT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jgt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JGE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jge_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JLT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jlt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JLE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jle_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSGT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsgt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSGE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsge_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSLT_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jslt_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSLE_K: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsle_imm, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* JMP32 register magnitudes */ + { + "JMP32_JSET_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jset_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JEQ_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jeq_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JNE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jne_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JGT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jgt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JGE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jge_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JLT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jlt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JLE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jle_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSGT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsgt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSGE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsge_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSLT_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jslt_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "JMP32_JSLE_X: all register value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_jmp32_jsle_reg, + .nr_testruns = NR_PATTERN_RUNS, + }, }; static struct net_device dev; From a7d2e752e52050fcdf0c50cf343488891a8efd5b Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:34 +0200 Subject: [PATCH 43/85] bpf/tests: Add staggered JMP and JMP32 tests This patch adds a new type of jump test where the program jumps forwards and backwards with increasing offset. It mainly tests JITs where a relative jump may generate different JITed code depending on the offset size, read MIPS. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-7-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 829 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 829 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index fb27a25e2c0c..7b3d801275e8 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1481,6 +1481,426 @@ static int bpf_fill_jmp32_jsle_reg(struct bpf_test *self) return __bpf_fill_jmp32_reg(self, BPF_JSLE); } +/* + * Set up a sequence of staggered jumps, forwards and backwards with + * increasing offset. This tests the conversion of relative jumps to + * JITed native jumps. On some architectures, for example MIPS, a large + * PC-relative jump offset may overflow the immediate field of the native + * conditional branch instruction, triggering a conversion to use an + * absolute jump instead. Since this changes the jump offsets, another + * offset computation pass is necessary, and that may in turn trigger + * another branch conversion. This jump sequence is particularly nasty + * in that regard. + * + * The sequence generation is parameterized by size and jump type. + * The size must be even, and the expected result is always size + 1. + * Below is an example with size=8 and result=9. + * + * ________________________Start + * R0 = 0 + * R1 = r1 + * R2 = r2 + * ,------- JMP +4 * 3______________Preamble: 4 insns + * ,----------|-ind 0- if R0 != 7 JMP 8 * 3 + 1 <--------------------. + * | | R0 = 8 | + * | | JMP +7 * 3 ------------------------. + * | ,--------|-----1- if R0 != 5 JMP 7 * 3 + 1 <--------------. | | + * | | | R0 = 6 | | | + * | | | JMP +5 * 3 ------------------. | | + * | | ,------|-----2- if R0 != 3 JMP 6 * 3 + 1 <--------. | | | | + * | | | | R0 = 4 | | | | | + * | | | | JMP +3 * 3 ------------. | | | | + * | | | ,----|-----3- if R0 != 1 JMP 5 * 3 + 1 <--. | | | | | | + * | | | | | R0 = 2 | | | | | | | + * | | | | | JMP +1 * 3 ------. | | | | | | + * | | | | ,--t=====4> if R0 != 0 JMP 4 * 3 + 1 1 2 3 4 5 6 7 8 loc + * | | | | | R0 = 1 -1 +2 -3 +4 -5 +6 -7 +8 off + * | | | | | JMP -2 * 3 ---' | | | | | | | + * | | | | | ,------5- if R0 != 2 JMP 3 * 3 + 1 <-----' | | | | | | + * | | | | | | R0 = 3 | | | | | | + * | | | | | | JMP -4 * 3 ---------' | | | | | + * | | | | | | ,----6- if R0 != 4 JMP 2 * 3 + 1 <-----------' | | | | + * | | | | | | | R0 = 5 | | | | + * | | | | | | | JMP -6 * 3 ---------------' | | | + * | | | | | | | ,--7- if R0 != 6 JMP 1 * 3 + 1 <-----------------' | | + * | | | | | | | | R0 = 7 | | + * | | Error | | | JMP -8 * 3 ---------------------' | + * | | paths | | | ,8- if R0 != 8 JMP 0 * 3 + 1 <-----------------------' + * | | | | | | | | | R0 = 9__________________Sequence: 3 * size - 1 insns + * `-+-+-+-+-+-+-+-+-> EXIT____________________Return: 1 insn + * + */ + +/* The maximum size parameter */ +#define MAX_STAGGERED_JMP_SIZE ((0x7fff / 3) & ~1) + +/* We use a reduced number of iterations to get a reasonable execution time */ +#define NR_STAGGERED_JMP_RUNS 10 + +static int __bpf_fill_staggered_jumps(struct bpf_test *self, + const struct bpf_insn *jmp, + u64 r1, u64 r2) +{ + int size = self->test[0].result - 1; + int len = 4 + 3 * (size + 1); + struct bpf_insn *insns; + int off, ind; + + insns = kmalloc_array(len, sizeof(*insns), GFP_KERNEL); + if (!insns) + return -ENOMEM; + + /* Preamble */ + insns[0] = BPF_ALU64_IMM(BPF_MOV, R0, 0); + insns[1] = BPF_ALU64_IMM(BPF_MOV, R1, r1); + insns[2] = BPF_ALU64_IMM(BPF_MOV, R2, r2); + insns[3] = BPF_JMP_IMM(BPF_JA, 0, 0, 3 * size / 2); + + /* Sequence */ + for (ind = 0, off = size; ind <= size; ind++, off -= 2) { + struct bpf_insn *ins = &insns[4 + 3 * ind]; + int loc; + + if (off == 0) + off--; + + loc = abs(off); + ins[0] = BPF_JMP_IMM(BPF_JNE, R0, loc - 1, + 3 * (size - ind) + 1); + ins[1] = BPF_ALU64_IMM(BPF_MOV, R0, loc); + ins[2] = *jmp; + ins[2].off = 3 * (off - 1); + } + + /* Return */ + insns[len - 1] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insns; + self->u.ptr.len = len; + + return 0; +} + +/* 64-bit unconditional jump */ +static int bpf_fill_staggered_ja(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JA, 0, 0, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0, 0); +} + +/* 64-bit immediate jumps */ +static int bpf_fill_staggered_jeq_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JEQ, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jne_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JNE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 4321, 0); +} + +static int bpf_fill_staggered_jset_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JSET, R1, 0x82, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x86, 0); +} + +static int bpf_fill_staggered_jgt_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JGT, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x80000000, 0); +} + +static int bpf_fill_staggered_jge_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JGE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jlt_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JLT, R1, 0x80000000, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jle_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JLE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jsgt_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JSGT, R1, -2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, 0); +} + +static int bpf_fill_staggered_jsge_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JSGE, R1, -2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, 0); +} + +static int bpf_fill_staggered_jslt_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JSLT, R1, -1, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, 0); +} + +static int bpf_fill_staggered_jsle_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_IMM(BPF_JSLE, R1, -1, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, 0); +} + +/* 64-bit register jumps */ +static int bpf_fill_staggered_jeq_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JEQ, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jne_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JNE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 4321, 1234); +} + +static int bpf_fill_staggered_jset_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JSET, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x86, 0x82); +} + +static int bpf_fill_staggered_jgt_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JGT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x80000000, 1234); +} + +static int bpf_fill_staggered_jge_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JGE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jlt_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JLT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0x80000000); +} + +static int bpf_fill_staggered_jle_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JLE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jsgt_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JSGT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, -2); +} + +static int bpf_fill_staggered_jsge_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JSGE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, -2); +} + +static int bpf_fill_staggered_jslt_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JSLT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, -1); +} + +static int bpf_fill_staggered_jsle_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP_REG(BPF_JSLE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, -1); +} + +/* 32-bit immediate jumps */ +static int bpf_fill_staggered_jeq32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JEQ, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jne32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JNE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 4321, 0); +} + +static int bpf_fill_staggered_jset32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JSET, R1, 0x82, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x86, 0); +} + +static int bpf_fill_staggered_jgt32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JGT, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x80000000, 0); +} + +static int bpf_fill_staggered_jge32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JGE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jlt32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JLT, R1, 0x80000000, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jle32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JLE, R1, 1234, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0); +} + +static int bpf_fill_staggered_jsgt32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JSGT, R1, -2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, 0); +} + +static int bpf_fill_staggered_jsge32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JSGE, R1, -2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, 0); +} + +static int bpf_fill_staggered_jslt32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JSLT, R1, -1, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, 0); +} + +static int bpf_fill_staggered_jsle32_imm(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_IMM(BPF_JSLE, R1, -1, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, 0); +} + +/* 32-bit register jumps */ +static int bpf_fill_staggered_jeq32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JEQ, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jne32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JNE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 4321, 1234); +} + +static int bpf_fill_staggered_jset32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JSET, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x86, 0x82); +} + +static int bpf_fill_staggered_jgt32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JGT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 0x80000000, 1234); +} + +static int bpf_fill_staggered_jge32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JGE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jlt32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JLT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 0x80000000); +} + +static int bpf_fill_staggered_jle32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JLE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, 1234, 1234); +} + +static int bpf_fill_staggered_jsgt32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JSGT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, -2); +} + +static int bpf_fill_staggered_jsge32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JSGE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, -2); +} + +static int bpf_fill_staggered_jslt32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JSLT, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -2, -1); +} + +static int bpf_fill_staggered_jsle32_reg(struct bpf_test *self) +{ + struct bpf_insn jmp = BPF_JMP32_REG(BPF_JSLE, R1, R2, 0); + + return __bpf_fill_staggered_jumps(self, &jmp, -1, -1); +} + static struct bpf_test tests[] = { { @@ -10225,6 +10645,415 @@ static struct bpf_test tests[] = { .fill_helper = bpf_fill_jmp32_jsle_reg, .nr_testruns = NR_PATTERN_RUNS, }, + /* Staggered jump sequences, immediate */ + { + "Staggered jumps: JMP_JA", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_ja, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JEQ_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jeq_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JNE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jne_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSET_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jset_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JGT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jgt_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JGE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jge_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JLT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jlt_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JLE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jle_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSGT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsgt_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSGE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsge_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSLT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jslt_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSLE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsle_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + /* Staggered jump sequences, register */ + { + "Staggered jumps: JMP_JEQ_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jeq_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JNE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jne_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSET_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jset_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JGT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jgt_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JGE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jge_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JLT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jlt_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JLE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jle_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSGT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsgt_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSGE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsge_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSLT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jslt_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP_JSLE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsle_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + /* Staggered jump sequences, JMP32 immediate */ + { + "Staggered jumps: JMP32_JEQ_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jeq32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JNE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jne32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSET_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jset32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JGT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jgt32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JGE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jge32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JLT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jlt32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JLE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jle32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSGT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsgt32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSGE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsge32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSLT_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jslt32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSLE_K", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsle32_imm, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + /* Staggered jump sequences, JMP32 register */ + { + "Staggered jumps: JMP32_JEQ_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jeq32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JNE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jne32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSET_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jset32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JGT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jgt32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JGE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jge32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JLT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jlt32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JLE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jle32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSGT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsgt32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSGE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsge32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSLT_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jslt32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, + { + "Staggered jumps: JMP32_JSLE_X", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, MAX_STAGGERED_JMP_SIZE + 1 } }, + .fill_helper = bpf_fill_staggered_jsle32_reg, + .nr_testruns = NR_STAGGERED_JMP_RUNS, + }, }; static struct net_device dev; From 2e807611945c2d36e25d10bc6f932e5f9943deea Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:35 +0200 Subject: [PATCH 44/85] bpf/tests: Add exhaustive test of LD_IMM64 immediate magnitudes This patch adds a test for the 64-bit immediate load, a two-instruction operation, to verify correctness for all possible magnitudes of the immediate operand. Mainly intended for JIT testing. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-8-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 7b3d801275e8..8aef42cfb5fe 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1104,6 +1104,60 @@ static int bpf_fill_alu32_mod_reg(struct bpf_test *self) return __bpf_fill_alu32_reg(self, BPF_MOD); } +/* + * Test the two-instruction 64-bit immediate load operation for all + * power-of-two magnitudes of the immediate operand. For each MSB, a block + * of immediate values centered around the power-of-two MSB are tested, + * both for positive and negative values. The test is designed to verify + * the operation for JITs that emit different code depending on the magnitude + * of the immediate value. This is often the case if the native instruction + * immediate field width is narrower than 32 bits. + */ +static int bpf_fill_ld_imm64(struct bpf_test *self) +{ + int block = 64; /* Increase for more tests per MSB position */ + int len = 3 + 8 * 63 * block * 2; + struct bpf_insn *insn; + int bit, adj, sign; + int i = 0; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 0); + + for (bit = 0; bit <= 62; bit++) { + for (adj = -block / 2; adj < block / 2; adj++) { + for (sign = -1; sign <= 1; sign += 2) { + s64 imm = sign * ((1LL << bit) + adj); + + /* Perform operation */ + i += __bpf_ld_imm64(&insn[i], R1, imm); + + /* Load reference */ + insn[i++] = BPF_ALU32_IMM(BPF_MOV, R2, imm); + insn[i++] = BPF_ALU32_IMM(BPF_MOV, R3, + (u32)(imm >> 32)); + insn[i++] = BPF_ALU64_IMM(BPF_LSH, R3, 32); + insn[i++] = BPF_ALU64_REG(BPF_OR, R2, R3); + + /* Check result */ + insn[i++] = BPF_JMP_REG(BPF_JEQ, R1, R2, 1); + insn[i++] = BPF_EXIT_INSN(); + } + } + } + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 1); + insn[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + BUG_ON(i != len); + + return 0; +} /* * Exhaustive tests of JMP operations for all combinations of power-of-two @@ -10245,6 +10299,15 @@ static struct bpf_test tests[] = { .fill_helper = bpf_fill_alu32_mod_reg, .nr_testruns = NR_PATTERN_RUNS, }, + /* LD_IMM64 immediate magnitudes */ + { + "LD_IMM64: all immediate value magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_ld_imm64, + }, /* JMP immediate magnitudes */ { "JMP_JSET_K: all immediate value magnitudes", From 27cc6dac6ec816cc31be9031edbee3e519234471 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:36 +0200 Subject: [PATCH 45/85] bpf/tests: Add test case flag for verifier zero-extension This patch adds a new flag to indicate that the verified did insert zero-extensions, even though the verifier is not being run for any of the tests. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-9-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 8aef42cfb5fe..0c1c8cccf254 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -52,6 +52,7 @@ #define FLAG_NO_DATA BIT(0) #define FLAG_EXPECTED_FAIL BIT(1) #define FLAG_SKB_FRAG BIT(2) +#define FLAG_VERIFIER_ZEXT BIT(3) enum { CLASSIC = BIT(6), /* Old BPF instructions only. */ @@ -11280,6 +11281,8 @@ static struct bpf_prog *generate_filter(int which, int *err) fp->type = BPF_PROG_TYPE_SOCKET_FILTER; memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn)); fp->aux->stack_depth = tests[which].stack_depth; + fp->aux->verifier_zext = !!(tests[which].aux & + FLAG_VERIFIER_ZEXT); /* We cannot error here as we don't need type compatibility * checks. From d4ff9ee2dc0bbbdba204e215c8b6bf58f5773994 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:37 +0200 Subject: [PATCH 46/85] bpf/tests: Add JMP tests with small offsets This patch adds a set of tests for JMP to verify that the JITed jump offset is calculated correctly. We pretend that the verifier has inserted any zero extensions to make the jump-over operations JIT to one instruction each, in order to control the exact JITed jump offset. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-10-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 0c1c8cccf254..2eb1d0e4aff3 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -10709,6 +10709,77 @@ static struct bpf_test tests[] = { .fill_helper = bpf_fill_jmp32_jsle_reg, .nr_testruns = NR_PATTERN_RUNS, }, + /* Short relative jumps */ + { + "Short relative jump: offset=0", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JEQ, R0, 0, 0), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, -1), + }, + INTERNAL | FLAG_NO_DATA | FLAG_VERIFIER_ZEXT, + { }, + { { 0, 0 } }, + }, + { + "Short relative jump: offset=1", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JEQ, R0, 0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, -1), + }, + INTERNAL | FLAG_NO_DATA | FLAG_VERIFIER_ZEXT, + { }, + { { 0, 0 } }, + }, + { + "Short relative jump: offset=2", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JEQ, R0, 0, 2), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, -1), + }, + INTERNAL | FLAG_NO_DATA | FLAG_VERIFIER_ZEXT, + { }, + { { 0, 0 } }, + }, + { + "Short relative jump: offset=3", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JEQ, R0, 0, 3), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, -1), + }, + INTERNAL | FLAG_NO_DATA | FLAG_VERIFIER_ZEXT, + { }, + { { 0, 0 } }, + }, + { + "Short relative jump: offset=4", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JEQ, R0, 0, 4), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, -1), + }, + INTERNAL | FLAG_NO_DATA | FLAG_VERIFIER_ZEXT, + { }, + { { 0, 0 } }, + }, /* Staggered jump sequences, immediate */ { "Staggered jumps: JMP_JA", From c4df4559db8447cdae15254a713f7fd5d4cee3ab Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:38 +0200 Subject: [PATCH 47/85] bpf/tests: Add JMP tests with degenerate conditional This patch adds a set of tests for JMP and JMP32 operations where the branch decision is know at JIT time. Mainly testing JIT behaviour. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-11-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 229 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 229 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 2eb1d0e4aff3..2aa1d0d3c685 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -10709,6 +10709,235 @@ static struct bpf_test tests[] = { .fill_helper = bpf_fill_jmp32_jsle_reg, .nr_testruns = NR_PATTERN_RUNS, }, + /* Conditional jumps with constant decision */ + { + "JMP_JSET_K: imm = 0 -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_IMM(BPF_JSET, R1, 0, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JLT_K: imm = 0 -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_IMM(BPF_JLT, R1, 0, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JGE_K: imm = 0 -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_IMM(BPF_JGE, R1, 0, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JGT_K: imm = 0xffffffff -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_IMM(BPF_JGT, R1, U32_MAX, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JLE_K: imm = 0xffffffff -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_IMM(BPF_JLE, R1, U32_MAX, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP32_JSGT_K: imm = 0x7fffffff -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP32_IMM(BPF_JSGT, R1, S32_MAX, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP32_JSGE_K: imm = -0x80000000 -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP32_IMM(BPF_JSGE, R1, S32_MIN, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP32_JSLT_K: imm = -0x80000000 -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP32_IMM(BPF_JSLT, R1, S32_MIN, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP32_JSLE_K: imm = 0x7fffffff -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP32_IMM(BPF_JSLE, R1, S32_MAX, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JEQ_X: dst = src -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JEQ, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JGE_X: dst = src -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JGE, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JLE_X: dst = src -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JLE, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSGE_X: dst = src -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JSGE, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLE_X: dst = src -> always taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JSLE, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + }, + { + "JMP_JNE_X: dst = src -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JNE, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JGT_X: dst = src -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JGT, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JLT_X: dst = src -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JLT, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JSGT_X: dst = src -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JSGT, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, + { + "JMP_JSLT_X: dst = src -> never taken", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_JMP_REG(BPF_JSLT, R1, R1, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0 } }, + }, /* Short relative jumps */ { "Short relative jump: offset=0", From f1517eb790f97c1326016eb164a33a64d4d4fb7a Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:39 +0200 Subject: [PATCH 48/85] bpf/tests: Expand branch conversion JIT test This patch expands the branch conversion test introduced by 66e5eb84 ("bpf, tests: Add branch conversion JIT test"). The test now includes a JMP with maximum eBPF offset. This triggers branch conversion for the 64-bit MIPS JIT. Additional variants are also added for cases when the branch is taken or not taken. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-12-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 143 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 100 insertions(+), 43 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 2aa1d0d3c685..dd6bb0044097 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -463,41 +463,6 @@ static int bpf_fill_stxdw(struct bpf_test *self) return __bpf_fill_stxdw(self, BPF_DW); } -static int bpf_fill_long_jmp(struct bpf_test *self) -{ - unsigned int len = BPF_MAXINSNS; - struct bpf_insn *insn; - int i; - - insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); - if (!insn) - return -ENOMEM; - - insn[0] = BPF_ALU64_IMM(BPF_MOV, R0, 1); - insn[1] = BPF_JMP_IMM(BPF_JEQ, R0, 1, len - 2 - 1); - - /* - * Fill with a complex 64-bit operation that expands to a lot of - * instructions on 32-bit JITs. The large jump offset can then - * overflow the conditional branch field size, triggering a branch - * conversion mechanism in some JITs. - * - * Note: BPF_MAXINSNS of ALU64 MUL is enough to trigger such branch - * conversion on the 32-bit MIPS JIT. For other JITs, the instruction - * count and/or operation may need to be modified to trigger the - * branch conversion. - */ - for (i = 2; i < len - 1; i++) - insn[i] = BPF_ALU64_IMM(BPF_MUL, R0, (i << 16) + i); - - insn[len - 1] = BPF_EXIT_INSN(); - - self->u.ptr.insns = insn; - self->u.ptr.len = len; - - return 0; -} - static int __bpf_ld_imm64(struct bpf_insn insns[2], u8 reg, s64 imm64) { struct bpf_insn tmp[] = {BPF_LD_IMM64(reg, imm64)}; @@ -506,6 +471,73 @@ static int __bpf_ld_imm64(struct bpf_insn insns[2], u8 reg, s64 imm64) return 2; } +/* + * Branch conversion tests. Complex operations can expand to a lot + * of instructions when JITed. This in turn may cause jump offsets + * to overflow the field size of the native instruction, triggering + * a branch conversion mechanism in some JITs. + */ +static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) +{ + struct bpf_insn *insns; + int len = S16_MAX + 5; + int i; + + insns = kmalloc_array(len, sizeof(*insns), GFP_KERNEL); + if (!insns) + return -ENOMEM; + + i = __bpf_ld_imm64(insns, R1, 0x0123456789abcdefULL); + insns[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 1); + insns[i++] = BPF_JMP_IMM(jmp, R0, imm, S16_MAX); + insns[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 2); + insns[i++] = BPF_EXIT_INSN(); + + while (i < len - 1) { + static const int ops[] = { + BPF_LSH, BPF_RSH, BPF_ARSH, BPF_ADD, + BPF_SUB, BPF_MUL, BPF_DIV, BPF_MOD, + }; + int op = ops[(i >> 1) % ARRAY_SIZE(ops)]; + + if (i & 1) + insns[i++] = BPF_ALU32_REG(op, R0, R1); + else + insns[i++] = BPF_ALU64_REG(op, R0, R1); + } + + insns[i++] = BPF_EXIT_INSN(); + self->u.ptr.insns = insns; + self->u.ptr.len = len; + BUG_ON(i != len); + + return 0; +} + +/* Branch taken by runtime decision */ +static int bpf_fill_max_jmp_taken(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 1); +} + +/* Branch not taken by runtime decision */ +static int bpf_fill_max_jmp_not_taken(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 0); +} + +/* Branch always taken, known at JIT time */ +static int bpf_fill_max_jmp_always_taken(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JGE, 0); +} + +/* Branch never taken, known at JIT time */ +static int bpf_fill_max_jmp_never_taken(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JLT, 0); +} + /* Test an ALU shift operation for all valid shift values */ static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op, u8 mode, bool alu32) @@ -8653,14 +8685,6 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, - { /* Mainly checking JIT here. */ - "BPF_MAXINSNS: Very long conditional jump", - { }, - INTERNAL | FLAG_NO_DATA, - { }, - { { 0, 1 } }, - .fill_helper = bpf_fill_long_jmp, - }, { "JMP_JA: Jump, gap, jump, ...", { }, @@ -11009,6 +11033,39 @@ static struct bpf_test tests[] = { { }, { { 0, 0 } }, }, + /* Conditional branch conversions */ + { + "Long conditional jump: taken at runtime", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_taken, + }, + { + "Long conditional jump: not taken at runtime", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_not_taken, + }, + { + "Long conditional jump: always taken, known at JIT time", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_always_taken, + }, + { + "Long conditional jump: never taken, known at JIT time", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_never_taken, + }, /* Staggered jump sequences, immediate */ { "Staggered jumps: JMP_JA", From f536a7c80675e4875e50df9182881d7678e27651 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:40 +0200 Subject: [PATCH 49/85] bpf/tests: Add more BPF_END byte order conversion tests This patch adds tests of the high 32 bits of 64-bit BPF_END conversions. It also adds a mirrored set of tests where the source bytes are reversed. The MSB of each byte is now set on the high word instead, possibly affecting sign-extension during conversion in a different way. Mainly for JIT testing. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-13-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 122 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 122 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index dd6bb0044097..7f8ad4fa4add 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -6748,6 +6748,67 @@ static struct bpf_test tests[] = { { }, { { 0, (u32) cpu_to_be64(0x0123456789abcdefLL) } }, }, + { + "ALU_END_FROM_BE 64: 0x0123456789abcdef >> 32 -> 0x01234567", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_BE, R0, 64), + BPF_ALU64_IMM(BPF_RSH, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) (cpu_to_be64(0x0123456789abcdefLL) >> 32) } }, + }, + /* BPF_ALU | BPF_END | BPF_FROM_BE, reversed */ + { + "ALU_END_FROM_BE 16: 0xfedcba9876543210 -> 0x3210", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_BE, R0, 16), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_be16(0x3210) } }, + }, + { + "ALU_END_FROM_BE 32: 0xfedcba9876543210 -> 0x76543210", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_BE, R0, 32), + BPF_ALU64_REG(BPF_MOV, R1, R0), + BPF_ALU64_IMM(BPF_RSH, R1, 32), + BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_be32(0x76543210) } }, + }, + { + "ALU_END_FROM_BE 64: 0xfedcba9876543210 -> 0x76543210", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_BE, R0, 64), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) cpu_to_be64(0xfedcba9876543210ULL) } }, + }, + { + "ALU_END_FROM_BE 64: 0xfedcba9876543210 >> 32 -> 0xfedcba98", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_BE, R0, 64), + BPF_ALU64_IMM(BPF_RSH, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) (cpu_to_be64(0xfedcba9876543210ULL) >> 32) } }, + }, /* BPF_ALU | BPF_END | BPF_FROM_LE */ { "ALU_END_FROM_LE 16: 0x0123456789abcdef -> 0xefcd", @@ -6785,6 +6846,67 @@ static struct bpf_test tests[] = { { }, { { 0, (u32) cpu_to_le64(0x0123456789abcdefLL) } }, }, + { + "ALU_END_FROM_LE 64: 0x0123456789abcdef >> 32 -> 0xefcdab89", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_LE, R0, 64), + BPF_ALU64_IMM(BPF_RSH, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) (cpu_to_le64(0x0123456789abcdefLL) >> 32) } }, + }, + /* BPF_ALU | BPF_END | BPF_FROM_LE, reversed */ + { + "ALU_END_FROM_LE 16: 0xfedcba9876543210 -> 0x1032", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_LE, R0, 16), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_le16(0x3210) } }, + }, + { + "ALU_END_FROM_LE 32: 0xfedcba9876543210 -> 0x10325476", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_LE, R0, 32), + BPF_ALU64_REG(BPF_MOV, R1, R0), + BPF_ALU64_IMM(BPF_RSH, R1, 32), + BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_le32(0x76543210) } }, + }, + { + "ALU_END_FROM_LE 64: 0xfedcba9876543210 -> 0x10325476", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_LE, R0, 64), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) cpu_to_le64(0xfedcba9876543210ULL) } }, + }, + { + "ALU_END_FROM_LE 64: 0xfedcba9876543210 >> 32 -> 0x98badcfe", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), + BPF_ENDIAN(BPF_FROM_LE, R0, 64), + BPF_ALU64_IMM(BPF_RSH, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) (cpu_to_le64(0xfedcba9876543210ULL) >> 32) } }, + }, /* BPF_ST(X) | BPF_MEM | BPF_B/H/W/DW */ { "ST_MEM_B: Store/Load byte: max negative", From 18935a72eb25525b655262579e1652362a3b29bb Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:41 +0200 Subject: [PATCH 50/85] bpf/tests: Fix error in tail call limit tests This patch fixes an error in the tail call limit test that caused the test to fail on for x86-64 JIT. Previously, the register R0 was used to report the total number of tail calls made. However, after a tail call fall-through, the value of the R0 register is undefined. Now, all tail call error path tests instead use context state to store the count. Fixes: 874be05f525e ("bpf, tests: Add tail call test suite") Reported-by: Paul Chaignon Reported-by: Tiezhu Yang Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Tested-by: Tiezhu Yang Link: https://lore.kernel.org/bpf/20210914091842.4186267-14-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 37 +++++++++++++++++++++++++++---------- 1 file changed, 27 insertions(+), 10 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 7f8ad4fa4add..a94ab634f947 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -12180,10 +12180,15 @@ static __init int test_bpf(void) struct tail_call_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; + int flags; int result; int stack_depth; }; +/* Flags that can be passed to tail call test cases */ +#define FLAG_NEED_STATE BIT(0) +#define FLAG_RESULT_IN_STATE BIT(1) + /* * Magic marker used in test snippets for tail calls below. * BPF_LD/MOV to R2 and R2 with this immediate value is replaced @@ -12253,32 +12258,38 @@ static struct tail_call_test tail_call_tests[] = { { "Tail call error path, max count reached", .insns = { - BPF_ALU64_IMM(BPF_ADD, R1, 1), - BPF_ALU64_REG(BPF_MOV, R0, R1), + BPF_LDX_MEM(BPF_W, R2, R1, 0), + BPF_ALU64_IMM(BPF_ADD, R2, 1), + BPF_STX_MEM(BPF_W, R1, R2, 0), TAIL_CALL(0), BPF_EXIT_INSN(), }, - .result = MAX_TAIL_CALL_CNT + 1, + .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, + .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, }, { "Tail call error path, NULL target", .insns = { - BPF_ALU64_IMM(BPF_MOV, R0, -1), + BPF_LDX_MEM(BPF_W, R2, R1, 0), + BPF_ALU64_IMM(BPF_ADD, R2, 1), + BPF_STX_MEM(BPF_W, R1, R2, 0), TAIL_CALL(TAIL_CALL_NULL), - BPF_ALU64_IMM(BPF_MOV, R0, 1), BPF_EXIT_INSN(), }, - .result = 1, + .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, + .result = MAX_TESTRUNS, }, { "Tail call error path, index out of range", .insns = { - BPF_ALU64_IMM(BPF_MOV, R0, -1), + BPF_LDX_MEM(BPF_W, R2, R1, 0), + BPF_ALU64_IMM(BPF_ADD, R2, 1), + BPF_STX_MEM(BPF_W, R1, R2, 0), TAIL_CALL(TAIL_CALL_INVALID), - BPF_ALU64_IMM(BPF_MOV, R0, 1), BPF_EXIT_INSN(), }, - .result = 1, + .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, + .result = MAX_TESTRUNS, }, }; @@ -12384,6 +12395,8 @@ static __init int test_tail_calls(struct bpf_array *progs) for (i = 0; i < ARRAY_SIZE(tail_call_tests); i++) { struct tail_call_test *test = &tail_call_tests[i]; struct bpf_prog *fp = progs->ptrs[i]; + int *data = NULL; + int state = 0; u64 duration; int ret; @@ -12400,7 +12413,11 @@ static __init int test_tail_calls(struct bpf_array *progs) if (fp->jited) jit_cnt++; - ret = __run_one(fp, NULL, MAX_TESTRUNS, &duration); + if (test->flags & FLAG_NEED_STATE) + data = &state; + ret = __run_one(fp, data, MAX_TESTRUNS, &duration); + if (test->flags & FLAG_RESULT_IN_STATE) + ret = state; if (ret == test->result) { pr_cont("%lld PASS", duration); pass_cnt++; From 29eef85be2f60b1027214b4bfc4b1a9d592830a7 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Tue, 14 Sep 2021 11:18:42 +0200 Subject: [PATCH 51/85] bpf/tests: Add tail call limit test with external function call This patch adds a tail call limit test where the program also emits a BPF_CALL to an external function prior to the tail call. Mainly testing that JITed programs preserve its internal register state, for example tail call count, across such external calls. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210914091842.4186267-15-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 83 insertions(+), 3 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index a94ab634f947..08f438e6fe9e 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -12208,6 +12208,30 @@ struct tail_call_test { offset, TAIL_CALL_MARKER), \ BPF_JMP_IMM(BPF_TAIL_CALL, 0, 0, 0) +/* + * A test function to be called from a BPF program, clobbering a lot of + * CPU registers in the process. A JITed BPF program calling this function + * must save and restore any caller-saved registers it uses for internal + * state, for example the current tail call count. + */ +BPF_CALL_1(bpf_test_func, u64, arg) +{ + char buf[64]; + long a = 0; + long b = 1; + long c = 2; + long d = 3; + long e = 4; + long f = 5; + long g = 6; + long h = 7; + + return snprintf(buf, sizeof(buf), + "%ld %lu %lx %ld %lu %lx %ld %lu %x", + a, b, c, d, e, f, g, h, (int)arg); +} +#define BPF_FUNC_test_func __BPF_FUNC_MAX_ID + /* * Tail call tests. Each test case may call any other test in the table, * including itself, specified as a relative index offset from the calling @@ -12267,6 +12291,28 @@ static struct tail_call_test tail_call_tests[] = { .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, }, + { + "Tail call count preserved across function calls", + .insns = { + BPF_LDX_MEM(BPF_W, R2, R1, 0), + BPF_ALU64_IMM(BPF_ADD, R2, 1), + BPF_STX_MEM(BPF_W, R1, R2, 0), + BPF_STX_MEM(BPF_DW, R10, R1, -8), + BPF_CALL_REL(BPF_FUNC_get_numa_node_id), + BPF_CALL_REL(BPF_FUNC_ktime_get_ns), + BPF_CALL_REL(BPF_FUNC_ktime_get_boot_ns), + BPF_CALL_REL(BPF_FUNC_ktime_get_coarse_ns), + BPF_CALL_REL(BPF_FUNC_jiffies64), + BPF_CALL_REL(BPF_FUNC_test_func), + BPF_LDX_MEM(BPF_DW, R1, R10, -8), + BPF_ALU32_REG(BPF_MOV, R0, R1), + TAIL_CALL(0), + BPF_EXIT_INSN(), + }, + .stack_depth = 8, + .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, + .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + }, { "Tail call error path, NULL target", .insns = { @@ -12345,17 +12391,19 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) /* Relocate runtime tail call offsets and addresses */ for (i = 0; i < len; i++) { struct bpf_insn *insn = &fp->insnsi[i]; - - if (insn->imm != TAIL_CALL_MARKER) - continue; + long addr = 0; switch (insn->code) { case BPF_LD | BPF_DW | BPF_IMM: + if (insn->imm != TAIL_CALL_MARKER) + break; insn[0].imm = (u32)(long)progs; insn[1].imm = ((u64)(long)progs) >> 32; break; case BPF_ALU | BPF_MOV | BPF_K: + if (insn->imm != TAIL_CALL_MARKER) + break; if (insn->off == TAIL_CALL_NULL) insn->imm = ntests; else if (insn->off == TAIL_CALL_INVALID) @@ -12363,6 +12411,38 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) else insn->imm = which + insn->off; insn->off = 0; + break; + + case BPF_JMP | BPF_CALL: + if (insn->src_reg != BPF_PSEUDO_CALL) + break; + switch (insn->imm) { + case BPF_FUNC_get_numa_node_id: + addr = (long)&numa_node_id; + break; + case BPF_FUNC_ktime_get_ns: + addr = (long)&ktime_get_ns; + break; + case BPF_FUNC_ktime_get_boot_ns: + addr = (long)&ktime_get_boot_fast_ns; + break; + case BPF_FUNC_ktime_get_coarse_ns: + addr = (long)&ktime_get_coarse_ns; + break; + case BPF_FUNC_jiffies64: + addr = (long)&get_jiffies_64; + break; + case BPF_FUNC_test_func: + addr = (long)&bpf_test_func; + break; + default: + err = -EFAULT; + goto out_err; + } + *insn = BPF_EMIT_CALL(BPF_CAST_CALL(addr)); + if ((long)__bpf_call_base + insn->imm != addr) + *insn = BPF_JMP_A(0); /* Skip: NOP */ + break; } } From 9673268f03ba72efcc00fa95f3fe3744fcae0dd0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:37 -0700 Subject: [PATCH 52/85] libbpf: Add "tc" SEC_DEF which is a better name for "classifier" As argued in [0], add "tc" ELF section definition for SCHED_CLS BPF program type. "classifier" is a misleading terminology and should be migrated away from. [0] https://lore.kernel.org/bpf/270e27b1-e5be-5b1c-b343-51bd644d0747@iogearbox.net/ Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210928161946.2512801-2-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 453148fe8b4b..0bcd0a4c867a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7968,6 +7968,7 @@ static const struct bpf_sec_def section_defs[] = { .attach_fn = attach_kprobe), BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), + BPF_PROG_SEC("tc", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), SEC_DEF("tracepoint/", TRACEPOINT, .attach_fn = attach_tp), From 8fffa0e3451abdd84e4b4e427f7e66040eb24f43 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:38 -0700 Subject: [PATCH 53/85] selftests/bpf: Normalize XDP section names in selftests Convert almost all SEC("xdp_blah") uses to strict SEC("xdp") to comply with strict libbpf 1.0 logic of exact section name match for XDP program types. There is only one exception, which is only tested through iproute2 and defines multiple XDP programs within the same BPF object. Given iproute2 still works in non-strict libbpf mode and it doesn't have means to specify XDP programs by its name (not section name/title), leave that single file alone for now until iproute2 gains lookup by function/program name. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-3-andrii@kernel.org --- tools/testing/selftests/bpf/progs/test_map_in_map.c | 2 +- .../selftests/bpf/progs/test_tcp_check_syncookie_kern.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp.c | 2 +- .../testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c | 2 +- .../selftests/bpf/progs/test_xdp_adjust_tail_shrink.c | 4 +--- tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_link.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_loop.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_noinline.c | 4 ++-- .../selftests/bpf/progs/test_xdp_with_cpumap_helpers.c | 4 ++-- .../selftests/bpf/progs/test_xdp_with_devmap_helpers.c | 4 ++-- tools/testing/selftests/bpf/progs/xdp_dummy.c | 2 +- tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c | 4 ++-- tools/testing/selftests/bpf/progs/xdping_kern.c | 4 ++-- tools/testing/selftests/bpf/test_tcp_check_syncookie.sh | 2 +- tools/testing/selftests/bpf/test_xdp_redirect.sh | 4 ++-- tools/testing/selftests/bpf/test_xdp_redirect_multi.sh | 2 +- tools/testing/selftests/bpf/test_xdp_veth.sh | 4 ++-- tools/testing/selftests/bpf/xdping.c | 5 ++--- 19 files changed, 27 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 1cfeb940cf9f..5f0e0bfc151e 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -23,7 +23,7 @@ struct { __uint(value_size, sizeof(__u32)); } mim_hash SEC(".maps"); -SEC("xdp_mimtest") +SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { int value = 123; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 47cbe2eeae43..fac7ef99f9a6 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -156,7 +156,7 @@ int check_syncookie_clsact(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("xdp/check_syncookie") +SEC("xdp") int check_syncookie_xdp(struct xdp_md *ctx) { check_syncookie(ctx, (void *)(long)ctx->data, diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 31f9bce37491..e6aa2fc6ce6b 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -210,7 +210,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 3d66599eee2e..199c61b7d062 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -2,7 +2,7 @@ #include #include -SEC("xdp_adjust_tail_grow") +SEC("xdp") int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index 22065a9cfb25..b7448253d135 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -9,9 +9,7 @@ #include #include -int _version SEC("version") = 1; - -SEC("xdp_adjust_tail_shrink") +SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c index b360ba2bd441..807bf895f42c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -5,7 +5,7 @@ #include #include -SEC("xdp_dm_log") +SEC("xdp") int xdpdm_devlog(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c index eb93ea95d1d8..ee7d6ac0f615 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_link.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -5,7 +5,7 @@ char LICENSE[] SEC("license") = "GPL"; -SEC("xdp/handler") +SEC("xdp") int xdp_handler(struct xdp_md *xdp) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index fcabcda30ba3..27eb52dda92c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -206,7 +206,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 3a67921f62b5..596c4e71bf3a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -797,7 +797,7 @@ out: return XDP_DROP; } -SEC("xdp-test-v4") +SEC("xdp") int balancer_ingress_v4(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; @@ -816,7 +816,7 @@ int balancer_ingress_v4(struct xdp_md *ctx) return XDP_DROP; } -SEC("xdp-test-v6") +SEC("xdp") int balancer_ingress_v6(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 59ee4f182ff8..532025057711 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -12,13 +12,13 @@ struct { __uint(max_entries, 4); } cpu_map SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&cpu_map, 1, 0); } -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 0ac086497722..1e6b9c38ea6d 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -9,7 +9,7 @@ struct { __uint(max_entries, 4); } dm_ports SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&dm_ports, 1, 0); @@ -18,7 +18,7 @@ int xdp_redir_prog(struct xdp_md *ctx) /* invalid program on DEVMAP entry; * SEC name means expected attach type not set */ -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index ea25e8881992..d988b2e0cee8 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -4,7 +4,7 @@ #include #include -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 880debcbcd65..8395782b6e0a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -34,7 +34,7 @@ struct { __uint(max_entries, 128); } mac_map SEC(".maps"); -SEC("xdp_redirect_map_multi") +SEC("xdp") int xdp_redirect_map_multi_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -63,7 +63,7 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx) } /* The following 2 progs are for 2nd devmap prog testing */ -SEC("xdp_redirect_map_ingress") +SEC("xdp") int xdp_redirect_map_all_prog(struct xdp_md *ctx) { return bpf_redirect_map(&map_egress, 0, diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 6b9ca40bd1f4..4ad73847b8a5 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -86,7 +86,7 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type) return XDP_TX; } -SEC("xdpclient") +SEC("xdp") int xdping_client(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -150,7 +150,7 @@ int xdping_client(struct xdp_md *ctx) return XDP_TX; } -SEC("xdpserver") +SEC("xdp") int xdping_server(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 9b3617d770a5..fed765157c53 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -77,7 +77,7 @@ TEST_IF=lo MAX_PING_TRIES=5 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o" CLSACT_SECTION="clsact/check_syncookie" -XDP_SECTION="xdp/check_syncookie" +XDP_SECTION="xdp" BPF_PROG_ID=0 PROG="${DIR}/test_tcp_check_syncookie_user" diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c033850886f4..57c8db9972a6 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -52,8 +52,8 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 1538373157e3..351955c2bdfd 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -88,7 +88,7 @@ setup_ns() # Add a neigh entry for IPv4 ping test ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 ip -n ns$i link set veth0 $mode obj \ - xdp_dummy.o sec xdp_dummy &> /dev/null || \ + xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}') diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index 995278e684b6..a3a1eaee26ea 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -107,9 +107,9 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 842d9155d36c..79a3453dab25 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -178,9 +178,8 @@ int main(int argc, char **argv) return 1; } - main_prog = bpf_object__find_program_by_title(obj, - server ? "xdpserver" : - "xdpclient"); + main_prog = bpf_object__find_program_by_name(obj, + server ? "xdping_server" : "xdping_client"); if (main_prog) prog_fd = bpf_program__fd(main_prog); if (!main_prog || prog_fd < 0) { From c22bdd28257f3532092746b31856932d84ca2e2b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:39 -0700 Subject: [PATCH 54/85] selftests/bpf: Switch SEC("classifier*") usage to a strict SEC("tc") Convert all SEC("classifier*") uses to a new and strict SEC("tc") section name. In reference_tracking selftests switch from ambiguous searching by program title (section name) to non-ambiguous searching by name in some selftests, getting closer to completely removing bpf_object__find_program_by_title(). Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210928161946.2512801-4-andrii@kernel.org --- .../bpf/prog_tests/reference_tracking.c | 23 ++++---- .../selftests/bpf/prog_tests/sk_assign.c | 2 +- .../selftests/bpf/prog_tests/tailcalls.c | 58 +++++++++---------- .../bpf/progs/for_each_array_map_elem.c | 2 +- .../bpf/progs/for_each_hash_map_elem.c | 2 +- .../selftests/bpf/progs/kfunc_call_test.c | 4 +- .../bpf/progs/kfunc_call_test_subprog.c | 2 +- .../testing/selftests/bpf/progs/skb_pkt_end.c | 2 +- tools/testing/selftests/bpf/progs/tailcall1.c | 7 +-- tools/testing/selftests/bpf/progs/tailcall2.c | 23 ++++---- tools/testing/selftests/bpf/progs/tailcall3.c | 7 +-- tools/testing/selftests/bpf/progs/tailcall4.c | 7 +-- tools/testing/selftests/bpf/progs/tailcall5.c | 7 +-- tools/testing/selftests/bpf/progs/tailcall6.c | 6 +- .../selftests/bpf/progs/tailcall_bpf2bpf1.c | 7 +-- .../selftests/bpf/progs/tailcall_bpf2bpf2.c | 7 +-- .../selftests/bpf/progs/tailcall_bpf2bpf3.c | 11 ++-- .../selftests/bpf/progs/tailcall_bpf2bpf4.c | 15 +++-- .../bpf/progs/test_btf_skc_cls_ingress.c | 2 +- .../selftests/bpf/progs/test_check_mtu.c | 12 ++-- .../selftests/bpf/progs/test_cls_redirect.c | 2 +- .../selftests/bpf/progs/test_global_data.c | 2 +- .../selftests/bpf/progs/test_global_func1.c | 2 +- .../selftests/bpf/progs/test_global_func3.c | 2 +- .../selftests/bpf/progs/test_global_func5.c | 2 +- .../selftests/bpf/progs/test_global_func6.c | 2 +- .../selftests/bpf/progs/test_global_func7.c | 2 +- .../selftests/bpf/progs/test_pkt_access.c | 2 +- .../selftests/bpf/progs/test_pkt_md_access.c | 4 +- .../selftests/bpf/progs/test_sk_assign.c | 3 +- .../selftests/bpf/progs/test_sk_lookup_kern.c | 37 ++++++------ .../selftests/bpf/progs/test_skb_helpers.c | 2 +- .../selftests/bpf/progs/test_sockmap_update.c | 2 +- .../testing/selftests/bpf/progs/test_tc_bpf.c | 2 +- .../selftests/bpf/progs/test_tc_neigh.c | 6 +- .../selftests/bpf/progs/test_tc_neigh_fib.c | 6 +- .../selftests/bpf/progs/test_tc_peer.c | 10 ++-- .../bpf/progs/test_tcp_check_syncookie_kern.c | 2 +- .../selftests/bpf/test_tcp_check_syncookie.sh | 2 +- 39 files changed, 141 insertions(+), 157 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index ded2dc8ddd79..873323fb18ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -2,14 +2,14 @@ #include static void toggle_object_autoload_progs(const struct bpf_object *obj, - const char *title_load) + const char *name_load) { struct bpf_program *prog; bpf_object__for_each_program(prog, obj) { - const char *title = bpf_program__section_name(prog); + const char *name = bpf_program__name(prog); - if (!strcmp(title_load, title)) + if (!strcmp(name_load, name)) bpf_program__set_autoload(prog, true); else bpf_program__set_autoload(prog, false); @@ -39,23 +39,19 @@ void test_reference_tracking(void) goto cleanup; bpf_object__for_each_program(prog, obj_iter) { - const char *title; + const char *name; - /* Ignore .text sections */ - title = bpf_program__section_name(prog); - if (strstr(title, ".text") != NULL) - continue; - - if (!test__start_subtest(title)) + name = bpf_program__name(prog); + if (!test__start_subtest(name)) continue; obj = bpf_object__open_file(file, &open_opts); if (!ASSERT_OK_PTR(obj, "obj_open_file")) goto cleanup; - toggle_object_autoload_progs(obj, title); + toggle_object_autoload_progs(obj, name); /* Expect verifier failure if test name has 'err' */ - if (strstr(title, "err_") != NULL) { + if (strncmp(name, "err_", sizeof("err_") - 1) == 0) { libbpf_print_fn_t old_print_fn; old_print_fn = libbpf_set_print(NULL); @@ -64,7 +60,8 @@ void test_reference_tracking(void) } else { err = bpf_object__load(obj); } - CHECK(err, title, "\n"); + ASSERT_OK(err, name); + bpf_object__close(obj); obj = NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3a469099f30d..1d272e05188e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -48,7 +48,7 @@ configure_stack(void) return false; sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", "direct-action object-file ./test_sk_assign.o", - "section classifier/sk_assign_test", + "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", "run with -vv for more info\n")) diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 7bf3a7a97d7b..9825f1f7bfcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -21,7 +21,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -38,9 +38,9 @@ static void test_tailcall_1(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -70,9 +70,9 @@ static void test_tailcall_1(void) err, errno, retval); for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -92,9 +92,9 @@ static void test_tailcall_1(void) for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { j = bpf_map__def(prog_array)->max_entries - 1 - i; - snprintf(prog_name, sizeof(prog_name), "classifier/%i", j); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -159,7 +159,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -176,9 +176,9 @@ static void test_tailcall_2(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -233,7 +233,7 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -249,7 +249,7 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -329,7 +329,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -354,9 +354,9 @@ static void test_tailcall_4(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -417,7 +417,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -442,9 +442,9 @@ static void test_tailcall_5(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -503,7 +503,7 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -521,9 +521,9 @@ static void test_tailcall_bpf2bpf_1(void) /* nop -> jmp */ for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -587,7 +587,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -603,7 +603,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -665,7 +665,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -682,9 +682,9 @@ static void test_tailcall_bpf2bpf_3(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -762,7 +762,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -779,9 +779,9 @@ static void test_tailcall_bpf2bpf_4(bool noise) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c index 75e8e1069fe7..df918b2469da 100644 --- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -47,7 +47,7 @@ check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, u32 arraymap_output = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c index 913dd91aafff..276994d5c0c7 100644 --- a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c @@ -78,7 +78,7 @@ int hashmap_output = 0; int hashmap_elems = 0; int percpu_map_elems = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 470f8723e463..8a8cf59017aa 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -8,7 +8,7 @@ extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; -SEC("classifier") +SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; @@ -23,7 +23,7 @@ int kfunc_call_test2(struct __sk_buff *skb) return bpf_kfunc_call_test2((struct sock *)sk, 1, 2); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 5fbd9e232d44..c1fdecabeabf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -33,7 +33,7 @@ int __noinline f1(struct __sk_buff *skb) return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { return f1(skb); diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c index 7f2eaa2f89f8..992b7861003a 100644 --- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -25,7 +25,7 @@ out: return ip; } -SEC("classifier/cls") +SEC("tc") int main_prog(struct __sk_buff *skb) { struct iphdr *ip = NULL; diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 7115bcefbe8a..8159a0b4a69a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -11,8 +11,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -20,7 +20,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { /* Multiple locations to make sure we patch @@ -45,4 +45,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 0431e4fe7efd..a5ff53e61702 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -10,41 +10,41 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); return 0; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 2); return 1; } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { return 2; } -SEC("classifier/3") -int bpf_func_3(struct __sk_buff *skb) +SEC("tc") +int classifier_3(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 4); return 3; } -SEC("classifier/4") -int bpf_func_4(struct __sk_buff *skb) +SEC("tc") +int classifier_4(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 3); return 4; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -56,4 +56,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 910858fe078a..f60bcd7b8d4b 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -12,15 +12,15 @@ struct { int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; bpf_tail_call_static(skb, &jmp_table, 0); return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -28,4 +28,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index bd4be135c39d..a56bbc2313ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call(skb, &jmp_table, selector); @@ -30,4 +30,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index adf30a33064e..8d03496eb6ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { int idx = 0; @@ -37,4 +37,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c index 0f4a811cc028..d77b8abd62f3 100644 --- a/tools/testing/selftests/bpf/progs/tailcall6.c +++ b/tools/testing/selftests/bpf/progs/tailcall6.c @@ -12,8 +12,8 @@ struct { int count, which; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; if (__builtin_constant_p(which)) @@ -22,7 +22,7 @@ int bpf_func_0(struct __sk_buff *skb) return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { if (__builtin_constant_p(which)) diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c index 0103f3dd9f02..8c91428deb90 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c @@ -10,8 +10,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -26,7 +26,7 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); @@ -35,4 +35,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 3cc4c12817b5..ce97d141daee 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -22,14 +22,14 @@ int subprog_tail(struct __sk_buff *skb) int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; return subprog_tail(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -38,4 +38,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c index 0d5482bea6c9..7fab39a3bb12 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c @@ -33,23 +33,23 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { volatile char arr[128] = {}; return subprog_tail2(skb); } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { volatile char arr[128] = {}; return skb->len * 3; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { volatile char arr[128] = {}; @@ -58,4 +58,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index e89368a50b97..b67e8022d500 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -50,30 +50,29 @@ int subprog_tail(struct __sk_buff *skb) return skb->len; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { return subprog_tail_2(skb); } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { count++; return subprog_tail_2(skb); } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { return subprog_tail_1(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { return subprog_tail(skb); } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index 9a6b85dd52d2..e2bea4da194b 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -145,7 +145,7 @@ release: return TC_ACT_OK; } -SEC("classifier/ingress") +SEC("tc") int cls_ingress(struct __sk_buff *skb) { struct ipv6hdr *ip6h; diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 71184af57749..2ec1de11a3ae 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -153,7 +153,7 @@ int xdp_input_len_exceed(struct xdp_md *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_use_helper(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -172,7 +172,7 @@ out: return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu(struct __sk_buff *ctx) { __u32 ifindex = GLOBAL_USER_IFINDEX; @@ -196,7 +196,7 @@ int tc_exceed_mtu(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu_da(struct __sk_buff *ctx) { /* SKB Direct-Access variant */ @@ -223,7 +223,7 @@ int tc_exceed_mtu_da(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_minus_delta(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -245,7 +245,7 @@ int tc_minus_delta(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -265,7 +265,7 @@ int tc_input_len(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len_exceed(struct __sk_buff *ctx) { int retval = BPF_DROP; /* Fail */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index e2a5acc4785c..2833ad722cb7 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -928,7 +928,7 @@ static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) } } -SEC("classifier/cls_redirect") +SEC("tc") int cls_redirect(struct __sk_buff *skb) { metrics_t *metrics = get_global_metrics(); diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 1319be1c54ba..719e314ef3e4 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -68,7 +68,7 @@ static struct foo struct3 = { bpf_map_update_elem(&result_##map, &key, var, 0); \ } while (0) -SEC("classifier/static_data_load") +SEC("tc") int load_static_data(struct __sk_buff *skb) { static const __u64 bar = ~0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index 880260f6d536..7b42dad187b8 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -38,7 +38,7 @@ int f3(int val, struct __sk_buff *skb, int var) return skb->ifindex * val * var; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c index 86f0ecb304fc..01bf8275dfd6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func3.c +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -54,7 +54,7 @@ int f8(struct __sk_buff *skb) } #endif -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { #ifndef NO_FN8 diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index 260c25b827ef..9248d03e0d06 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c index 69e19c64e10b..af8c78bdfb25 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func6.c +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c index 309b3f6136bd..6cb8e2f5254c 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func7.c +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -10,7 +10,7 @@ void foo(struct __sk_buff *skb) skb->tc_index = 0; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { foo(skb); diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 852051064507..3cfd88141ddc 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -97,7 +97,7 @@ int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) return 0; } -SEC("classifier/test_pkt_access") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 610c74ea9f64..d1839366f3e1 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -7,8 +7,6 @@ #include #include -int _version SEC("version") = 1; - #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define TEST_FIELD(TYPE, FIELD, MASK) \ { \ @@ -27,7 +25,7 @@ int _version SEC("version") = 1; } #endif -SEC("classifier/test_pkt_md_access") +SEC("tc") int test_pkt_md_access(struct __sk_buff *skb) { TEST_FIELD(__u8, len, 0xFF); diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 1ecd987005d2..02f79356d5eb 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -36,7 +36,6 @@ struct { .pinning = PIN_GLOBAL_NS, }; -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -159,7 +158,7 @@ assign: return ret; } -SEC("classifier/sk_assign_test") +SEC("tc") int bpf_sk_assign_test(struct __sk_buff *skb) { struct bpf_sock_tuple *tuple, ln = {0}; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index 8249075f088f..40f161480a2f 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -15,7 +15,6 @@ #include #include -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -53,8 +52,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, return result; } -SEC("classifier/sk_lookup_success") -int bpf_sk_lookup_test0(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; void *data = (void *)(long)skb->data; @@ -79,8 +78,8 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb) return sk ? TC_ACT_OK : TC_ACT_UNSPEC; } -SEC("classifier/sk_lookup_success_simple") -int bpf_sk_lookup_test1(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success_simple(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -91,8 +90,8 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb) return 0; } -SEC("classifier/err_use_after_free") -int bpf_sk_lookup_uaf(struct __sk_buff *skb) +SEC("tc") +int err_use_after_free(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -106,8 +105,8 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb) return family; } -SEC("classifier/err_modify_sk_pointer") -int bpf_sk_lookup_modptr(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -121,8 +120,8 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb) return 0; } -SEC("classifier/err_modify_sk_or_null_pointer") -int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_or_null_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -135,8 +134,8 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) return 0; } -SEC("classifier/err_no_release") -int bpf_sk_lookup_test2(struct __sk_buff *skb) +SEC("tc") +int err_no_release(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; @@ -144,8 +143,8 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_twice") -int bpf_sk_lookup_test3(struct __sk_buff *skb) +SEC("tc") +int err_release_twice(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -156,8 +155,8 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_unchecked") -int bpf_sk_lookup_test4(struct __sk_buff *skb) +SEC("tc") +int err_release_unchecked(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -173,8 +172,8 @@ void lookup_no_release(struct __sk_buff *skb) bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); } -SEC("classifier/err_no_release_subcall") -int bpf_sk_lookup_test5(struct __sk_buff *skb) +SEC("tc") +int err_no_release_subcall(struct __sk_buff *skb) { lookup_no_release(skb); return 0; diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c index bb3fbf1a29e3..507215791c5b 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -14,7 +14,7 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("classifier/test_skb_helpers") +SEC("tc") int test_skb_helpers(struct __sk_buff *skb) { struct task_struct *task; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c index 9d0c9f28cab2..6d64ea536e3d 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_update.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -24,7 +24,7 @@ struct { __type(value, __u64); } dst_sock_hash SEC(".maps"); -SEC("classifier/copy_sock_map") +SEC("tc") int copy_sock_map(void *ctx) { struct bpf_sock *sk; diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index 18a3a7ed924a..d28ca8d1f3d0 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -5,7 +5,7 @@ /* Dummy prog to test TC-BPF API */ -SEC("classifier") +SEC("tc") int cls(struct __sk_buff *skb) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index 0c93d326a663..3e32ea375ab4 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -70,7 +70,7 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -83,7 +83,7 @@ int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; @@ -108,7 +108,7 @@ int tc_dst(struct __sk_buff *skb) return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index f7ab69cf018e..ec4cce19362d 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,7 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -143,13 +143,13 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return tc_redir(skb); diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fe818cd5f010..365eacb5dc34 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -16,31 +16,31 @@ volatile const __u32 IFINDEX_DST; static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { return TC_ACT_SHOT; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("classifier/dst_ingress_l3") +SEC("tc") int tc_dst_l3(struct __sk_buff *skb) { return bpf_redirect(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress_l3") +SEC("tc") int tc_src_l3(struct __sk_buff *skb) { __u16 proto = skb->protocol; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index fac7ef99f9a6..cd747cd93dbe 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -148,7 +148,7 @@ release: bpf_sk_release(sk); } -SEC("clsact/check_syncookie") +SEC("tc") int check_syncookie_clsact(struct __sk_buff *skb) { check_syncookie(skb, (void *)(long)skb->data, diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index fed765157c53..6413c1472554 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -76,7 +76,7 @@ DIR=$(dirname $0) TEST_IF=lo MAX_PING_TRIES=5 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o" -CLSACT_SECTION="clsact/check_syncookie" +CLSACT_SECTION="tc" XDP_SECTION="xdp" BPF_PROG_ID=0 PROG="${DIR}/test_tcp_check_syncookie_user" From 15669e1dcd75fe6d51e495f8479222b5884665b6 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:40 -0700 Subject: [PATCH 55/85] selftests/bpf: Normalize all the rest SEC() uses Normalize all the other non-conforming SEC() usages across all selftests. This is in preparation for libbpf to start to enforce stricter SEC() rules in libbpf 1.0 mode. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-5-andrii@kernel.org --- .../selftests/bpf/prog_tests/flow_dissector.c | 4 +-- .../selftests/bpf/prog_tests/sockopt_multi.c | 30 +++++++++---------- tools/testing/selftests/bpf/progs/bpf_flow.c | 3 +- .../bpf/progs/cg_storage_multi_isolated.c | 4 +-- .../bpf/progs/cg_storage_multi_shared.c | 4 +-- .../selftests/bpf/progs/sockopt_multi.c | 5 ++-- .../selftests/bpf/progs/test_cgroup_link.c | 4 +-- .../bpf/progs/test_misc_tcp_hdr_options.c | 2 +- .../selftests/bpf/progs/test_sk_lookup.c | 6 ++-- .../selftests/bpf/progs/test_sockmap_listen.c | 2 +- .../progs/test_sockmap_skb_verdict_attach.c | 2 +- .../bpf/progs/test_tcp_hdr_options.c | 2 +- 12 files changed, 33 insertions(+), 35 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 225714f71ac6..ac54e3f91d42 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -458,9 +458,9 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return -1; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i); + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (!prog) return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 51fac975b316..bc34f7773444 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,7 +2,7 @@ #include #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -15,23 +15,23 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) return -1; } - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) { - log_err("Failed to find %s BPF program", title); + log_err("Failed to find %s BPF program", name); return -1; } err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, attach_type, BPF_F_ALLOW_MULTI); if (err) { - log_err("Failed to attach %s BPF program", title); + log_err("Failed to attach %s BPF program", name); return -1; } return 0; } -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -42,7 +42,7 @@ static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) if (err) return -1; - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) return -1; @@ -89,7 +89,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) goto detach; @@ -113,7 +113,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent"); + err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); if (err) goto detach; @@ -157,7 +157,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) { log_err("Failed to detach child program"); goto detach; @@ -198,8 +198,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt/child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt/parent"); + prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); + prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); return err; } @@ -236,7 +236,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt"); + err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -263,7 +263,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt"); + err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -289,8 +289,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt"); + prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); + prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); return err; } diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 95a5a0778ed7..f266c757b3df 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -19,9 +19,8 @@ #include #include -int _version SEC("version") = 1; #define PROG(F) PROG_(F, _##F) -#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME +#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c index a25373002055..3f81ff92184c 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c index a149f33bc533..d662db27fe4a 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 9d8c212dde9f..177a59069dae 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -4,9 +4,8 @@ #include char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; -SEC("cgroup/getsockopt/child") +SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; @@ -29,7 +28,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) return 1; } -SEC("cgroup/getsockopt/parent") +SEC("cgroup/getsockopt") int _getsockopt_parent(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c index 77e47b9e4446..4faba88e45a5 100644 --- a/tools/testing/selftests/bpf/progs/test_cgroup_link.c +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -6,14 +6,14 @@ int calls = 0; int alt_calls = 0; -SEC("cgroup_skb/egress1") +SEC("cgroup_skb/egress") int egress(struct __sk_buff *skb) { __sync_fetch_and_add(&calls, 1); return 1; } -SEC("cgroup_skb/egress2") +SEC("cgroup_skb/egress") int egress_alt(struct __sk_buff *skb) { __sync_fetch_and_add(&alt_calls, 1); diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index 6077a025092c..2c121c5d66a7 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -293,7 +293,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) return check_active_hdr_in(skops); } -SEC("sockops/misc_estab") +SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index ac6f7f205e25..6c4d32c56765 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -84,13 +84,13 @@ int lookup_drop(struct bpf_sk_lookup *ctx) return SK_DROP; } -SEC("sk_reuseport/reuse_pass") +SEC("sk_reuseport") int reuseport_pass(struct sk_reuseport_md *ctx) { return SK_PASS; } -SEC("sk_reuseport/reuse_drop") +SEC("sk_reuseport") int reuseport_drop(struct sk_reuseport_md *ctx) { return SK_DROP; @@ -194,7 +194,7 @@ int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_reuseport/select_sock_b") +SEC("sk_reuseport") int select_sock_b(struct sk_reuseport_md *ctx) { __u32 key = KEY_SERVER_B; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a1cc58b10c7c..00f1456aaeda 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -56,7 +56,7 @@ int prog_stream_verdict(struct __sk_buff *skb) return verdict; } -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { unsigned int *count; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c index 2d31f66e4f23..3c69aa971738 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c @@ -9,7 +9,7 @@ struct { __type(value, __u64); } sock_map SEC(".maps"); -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { return SK_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c index 678bd0fad29e..5f4e87ee949a 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -594,7 +594,7 @@ static int handle_parse_hdr(struct bpf_sock_ops *skops) return CG_OK; } -SEC("sockops/estab") +SEC("sockops") int estab(struct bpf_sock_ops *skops) { int true_val = 1; From 12d9466d8bf3d1d4b4fd0f5733b6fa0cc5ee1013 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:41 -0700 Subject: [PATCH 56/85] libbpf: Refactor internal sec_def handling to enable pluggability Refactor internals of libbpf to allow adding custom SEC() handling logic easily from outside of libbpf. To that effect, each SEC()-handling registration sets mandatory program type/expected attach type for a given prefix and can provide three callbacks called at different points of BPF program lifetime: - init callback for right after bpf_program is initialized and prog_type/expected_attach_type is set. This happens during bpf_object__open() step, close to the very end of constructing bpf_object, so all the libbpf APIs for querying and updating bpf_program properties should be available; - pre-load callback is called right before BPF_PROG_LOAD command is called in the kernel. This callbacks has ability to set both bpf_program properties, as well as program load attributes, overriding and augmenting the standard libbpf handling of them; - optional auto-attach callback, which makes a given SEC() handler support auto-attachment of a BPF program through bpf_program__attach() API and/or BPF skeletons __attach() method. Each callbacks gets a `long cookie` parameter passed in, which is specified during SEC() handling. This can be used by callbacks to lookup whatever additional information is necessary. This is not yet completely ready to be exposed to the outside world, mainly due to non-public nature of struct bpf_prog_load_params. Instead of making it part of public API, we'll wait until the planned low-level libbpf API improvements for BPF_PROG_LOAD and other typical bpf() syscall APIs, at which point we'll have a public, probably OPTS-based, way to fully specify BPF program load parameters, which will be used as an interface for custom pre-load callbacks. But this change itself is already a good first step to unify the BPF program hanling logic even within the libbpf itself. As one example, all the extra per-program type handling (sleepable bit, attach_btf_id resolution, unsetting optional expected attach type) is now more obvious and is gathered in one place. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-6-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 129 +++++++++++++++++++++++++++-------------- 1 file changed, 87 insertions(+), 42 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0bcd0a4c867a..d4d56536dc4b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -220,7 +220,9 @@ struct reloc_desc { struct bpf_sec_def; -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog); +typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); +typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie); +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); struct bpf_sec_def { const char *sec; @@ -231,7 +233,11 @@ struct bpf_sec_def { bool is_attachable; bool is_attach_btf; bool is_sleepable; + + init_fn_t init_fn; + preload_fn_t preload_fn; attach_fn_t attach_fn; + long cookie; }; /* @@ -6095,6 +6101,44 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program return 0; } +static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); + +/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ +static int libbpf_preload_prog(struct bpf_program *prog, + struct bpf_prog_load_params *attr, long cookie) +{ + /* old kernels might not support specifying expected_attach_type */ + if (prog->sec_def->is_exp_attach_type_optional && + !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + attr->expected_attach_type = 0; + + if (prog->sec_def->is_sleepable) + attr->prog_flags |= BPF_F_SLEEPABLE; + + if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { + int btf_obj_fd = 0, btf_type_id = 0, err; + + err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + /* cache resolved BTF FD and BTF type ID in the prog */ + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; + + /* but by now libbpf common logic is not utilizing + * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because + * this callback is called after attrs were populated by + * libbpf, so this callback has to update attr explicitly here + */ + attr->attach_btf_obj_fd = btf_obj_fd; + attr->attach_btf_id = btf_type_id; + } + return 0; +} + static int load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *license, __u32 kern_version, int *pfd) @@ -6103,7 +6147,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL; - int btf_fd, ret; + int btf_fd, ret, err; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6119,22 +6163,15 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, return -EINVAL; load_attr.prog_type = prog->type; - /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && - prog->sec_def->is_exp_attach_type_optional) - load_attr.expected_attach_type = 0; - else - load_attr.expected_attach_type = prog->expected_attach_type; + load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(prog->obj, FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insn_cnt = insns_cnt; load_attr.license = license; load_attr.attach_btf_id = prog->attach_btf_id; - if (prog->attach_prog_fd) - load_attr.attach_prog_fd = prog->attach_prog_fd; - else - load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; @@ -6153,6 +6190,16 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; + /* adjust load_attr if sec_def provides custom preload callback */ + if (prog->sec_def && prog->sec_def->preload_fn) { + err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to prepare load attributes: %d\n", + prog->name, err); + return err; + } + } + if (prog->obj->gen_loader) { bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, prog - prog->obj->programs); @@ -6268,8 +6315,6 @@ static int bpf_program__record_externs(struct bpf_program *prog) return 0; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); - int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { int err = 0, fd, i; @@ -6279,19 +6324,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) return libbpf_err(-EINVAL); } - if ((prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { - int btf_obj_fd = 0, btf_type_id = 0; - - err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); - if (err) - return libbpf_err(err); - - prog->attach_btf_obj_fd = btf_obj_fd; - prog->attach_btf_id = btf_type_id; - } - if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { pr_warn("Internal error: can't load program '%s'\n", @@ -6401,6 +6433,7 @@ static const struct bpf_sec_def *find_sec_def(const char *sec_name); static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) { struct bpf_program *prog; + int err; bpf_object__for_each_program(prog, obj) { prog->sec_def = find_sec_def(prog->sec_name); @@ -6411,8 +6444,6 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object continue; } - if (prog->sec_def->is_sleepable) - prog->prog_flags |= BPF_F_SLEEPABLE; bpf_program__set_type(prog, prog->sec_def->prog_type); bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); @@ -6422,6 +6453,18 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); #pragma GCC diagnostic pop + + /* sec_def can have custom callback which should be called + * after bpf_program is initialized to adjust its properties + */ + if (prog->sec_def->init_fn) { + err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to initialize: %d\n", + prog->name, err); + return err; + } + } } return 0; @@ -7919,6 +7962,7 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, .is_exp_attach_type_optional = eatype_optional, \ .is_attachable = attachable, \ .is_attach_btf = attach_btf, \ + .preload_fn = libbpf_preload_prog, \ } /* Programs that can NOT be attached. */ @@ -7945,15 +7989,16 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, .sec = sec_pfx, \ .len = sizeof(sec_pfx) - 1, \ .prog_type = BPF_PROG_TYPE_##ptype, \ + .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog); -static struct bpf_link *attach_tp(const struct bpf_program *prog); -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog); -static struct bpf_link *attach_trace(const struct bpf_program *prog); -static struct bpf_link *attach_lsm(const struct bpf_program *prog); -static struct bpf_link *attach_iter(const struct bpf_program *prog); +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), @@ -9425,7 +9470,7 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog) +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; @@ -9708,7 +9753,7 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_program *prog) +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) { char *sec_name, *tp_cat, *tp_name; struct bpf_link *link; @@ -9762,7 +9807,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog) +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) { const char *tp_name = prog->sec_name + prog->sec_def->len; @@ -9809,12 +9854,12 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_program *prog) +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) { return bpf_program__attach_trace(prog); } -static struct bpf_link *attach_lsm(const struct bpf_program *prog) +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) { return bpf_program__attach_lsm(prog); } @@ -9945,7 +9990,7 @@ bpf_program__attach_iter(const struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_program *prog) +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) { return bpf_program__attach_iter(prog, NULL); } @@ -9955,7 +10000,7 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) if (!prog->sec_def || !prog->sec_def->attach_fn) return libbpf_err_ptr(-ESRCH); - return prog->sec_def->attach_fn(prog); + return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); } static int bpf_link__detach_struct_ops(struct bpf_link *link) From 13d35a0cf1741431333ba4aa9bce9c5bbc88f63b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:42 -0700 Subject: [PATCH 57/85] libbpf: Reduce reliance of attach_fns on sec_def internals Move closer to not relying on bpf_sec_def internals that won't be part of public API, when pluggable SEC() handlers will be allowed. Drop pre-calculated prefix length, and in various helpers don't rely on this prefix length availability. Also minimize reliance on knowing bpf_sec_def's prefix for few places where section prefix shortcuts are supported (e.g., tp vs tracepoint, raw_tp vs raw_tracepoint). Given checking some string for having a given string-constant prefix is such a common operation and so annoying to be done with pure C code, add a small macro helper, str_has_pfx(), and reuse it throughout libbpf.c where prefix comparison is performed. With __builtin_constant_p() it's possible to have a convenient helper that checks some string for having a given prefix, where prefix is either string literal (or compile-time known string due to compiler optimization) or just a runtime string pointer, which is quite convenient and saves a lot of typing and string literal duplication. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-7-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 41 ++++++++++++++++++--------------- tools/lib/bpf/libbpf_internal.h | 7 ++++++ 2 files changed, 30 insertions(+), 18 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d4d56536dc4b..f87ffd4d7eab 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -226,7 +226,6 @@ typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long coo struct bpf_sec_def { const char *sec; - size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; bool is_exp_attach_type_optional; @@ -1671,7 +1670,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, void *ext_val; __u64 num; - if (strncmp(buf, "CONFIG_", 7)) + if (!str_has_pfx(buf, "CONFIG_")) return 0; sep = strchr(buf, '='); @@ -2920,7 +2919,7 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) static bool is_sec_name_dwarf(const char *name) { /* approximation, but the actual list is too long */ - return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; + return str_has_pfx(name, ".debug_"); } static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) @@ -2942,7 +2941,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) if (is_sec_name_dwarf(name)) return true; - if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + if (str_has_pfx(name, ".rel")) { name += sizeof(".rel") - 1; /* DWARF section relocations */ if (is_sec_name_dwarf(name)) @@ -6891,8 +6890,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, if (err) return err; pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); - } else if (ext->type == EXT_KCFG && - strncmp(ext->name, "CONFIG_", 7) == 0) { + } else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) { need_config = true; } else if (ext->type == EXT_KSYM) { if (ext->ksym.type_id) @@ -7956,7 +7954,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, attachable, attach_btf) \ { \ .sec = string, \ - .len = sizeof(string) - 1, \ .prog_type = ptype, \ .expected_attach_type = eatype, \ .is_exp_attach_type_optional = eatype_optional, \ @@ -7987,7 +7984,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, #define SEC_DEF(sec_pfx, ptype, ...) { \ .sec = sec_pfx, \ - .len = sizeof(sec_pfx) - 1, \ .prog_type = BPF_PROG_TYPE_##ptype, \ .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ @@ -8162,10 +8158,8 @@ static const struct bpf_sec_def *find_sec_def(const char *sec_name) int i, n = ARRAY_SIZE(section_defs); for (i = 0; i < n; i++) { - if (strncmp(sec_name, - section_defs[i].sec, section_defs[i].len)) - continue; - return §ion_defs[i]; + if (str_has_pfx(sec_name, section_defs[i].sec)) + return §ion_defs[i]; } return NULL; } @@ -8519,7 +8513,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, prog->sec_name); return -ESRCH; } - attach_name = prog->sec_name + prog->sec_def->len; + attach_name = prog->sec_name + strlen(prog->sec_def->sec); /* BPF program's BTF ID */ if (attach_prog_fd) { @@ -9479,8 +9473,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cooki char *func; int n, err; - func_name = prog->sec_name + prog->sec_def->len; - opts.retprobe = strcmp(prog->sec_def->sec, "kretprobe/") == 0; + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); + if (opts.retprobe) + func_name = prog->sec_name + sizeof("kretprobe/") - 1; + else + func_name = prog->sec_name + sizeof("kprobe/") - 1; n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { @@ -9762,8 +9759,11 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) if (!sec_name) return libbpf_err_ptr(-ENOMEM); - /* extract "tp//" */ - tp_cat = sec_name + prog->sec_def->len; + /* extract "tp//" or "tracepoint//" */ + if (str_has_pfx(prog->sec_name, "tp/")) + tp_cat = sec_name + sizeof("tp/") - 1; + else + tp_cat = sec_name + sizeof("tracepoint/") - 1; tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); @@ -9809,7 +9809,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) { - const char *tp_name = prog->sec_name + prog->sec_def->len; + const char *tp_name; + + if (str_has_pfx(prog->sec_name, "raw_tp/")) + tp_name = prog->sec_name + sizeof("raw_tp/") - 1; + else + tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1; return bpf_program__attach_raw_tracepoint(prog, tp_name); } diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ceb0c98979bc..ec79400517d4 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -89,6 +89,13 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is + * a string literal known at compilation time or char * pointer known only at + * runtime. + */ +#define str_has_pfx(str, pfx) \ + (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) + /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. From 15ea31fadd7f5b1076b4f91f75562bc319799c24 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:43 -0700 Subject: [PATCH 58/85] libbpf: Refactor ELF section handler definitions Refactor ELF section handler definitions table to use a set of flags and unified SEC_DEF() macro. This allows for more succinct and table-like set of definitions, and allows to more easily extend the logic without adding more verbosity (this is utilized in later patches in the series). This approach is also making libbpf-internal program pre-load callback not rely on bpf_sec_def definition, which demonstrates that future pluggable ELF section handlers will be able to achieve similar level of integration without libbpf having to expose extra types and APIs. For starters, update SEC_DEF() definitions and make them more succinct. Also convert BPF_PROG_SEC() and BPF_APROG_COMPAT() definitions to a common SEC_DEF() use. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-8-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 195 ++++++++++++++++++----------------------- 1 file changed, 84 insertions(+), 111 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index f87ffd4d7eab..954c135a8adf 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -224,19 +224,35 @@ typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie); typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); +/* stored as sec_def->cookie for all libbpf-supported SEC()s */ +enum sec_def_flags { + SEC_NONE = 0, + /* expected_attach_type is optional, if kernel doesn't support that */ + SEC_EXP_ATTACH_OPT = 1, + /* legacy, only used by libbpf_get_type_names() and + * libbpf_attach_type_by_name(), not used by libbpf itself at all. + * This used to be associated with cgroup (and few other) BPF programs + * that were attachable through BPF_PROG_ATTACH command. Pretty + * meaningless nowadays, though. + */ + SEC_ATTACHABLE = 2, + SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT, + /* attachment target is specified through BTF ID in either kernel or + * other BPF program's BTF object */ + SEC_ATTACH_BTF = 4, + /* BPF program type allows sleeping/blocking in kernel */ + SEC_SLEEPABLE = 8, +}; + struct bpf_sec_def { const char *sec; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - bool is_exp_attach_type_optional; - bool is_attachable; - bool is_attach_btf; - bool is_sleepable; + long cookie; init_fn_t init_fn; preload_fn_t preload_fn; attach_fn_t attach_fn; - long cookie; }; /* @@ -6100,26 +6116,30 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program return 0; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id); /* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ static int libbpf_preload_prog(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie) { + enum sec_def_flags def = cookie; + /* old kernels might not support specifying expected_attach_type */ - if (prog->sec_def->is_exp_attach_type_optional && - !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) attr->expected_attach_type = 0; - if (prog->sec_def->is_sleepable) + if (def & SEC_SLEEPABLE) attr->prog_flags |= BPF_F_SLEEPABLE; if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; + const char *attach_name; - err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); + attach_name = strchr(prog->sec_name, '/') + 1; + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); if (err) return err; @@ -7956,15 +7976,14 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, .sec = string, \ .prog_type = ptype, \ .expected_attach_type = eatype, \ - .is_exp_attach_type_optional = eatype_optional, \ - .is_attachable = attachable, \ - .is_attach_btf = attach_btf, \ + .cookie = (long) ( \ + (eatype_optional ? SEC_EXP_ATTACH_OPT : 0) | \ + (attachable ? SEC_ATTACHABLE : 0) | \ + (attach_btf ? SEC_ATTACH_BTF : 0) \ + ), \ .preload_fn = libbpf_preload_prog, \ } -/* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) - /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) @@ -7977,14 +7996,11 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, #define BPF_PROG_BTF(string, ptype, eatype) \ BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) -/* Programs that can be attached but attach type can't be identified by section - * name. Kept for backward compatibility. - */ -#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) - -#define SEC_DEF(sec_pfx, ptype, ...) { \ +#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ + .expected_attach_type = atype, \ + .cookie = (long)(flags), \ .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ } @@ -7997,93 +8013,50 @@ static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); static const struct bpf_sec_def section_defs[] = { - BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE), BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT), - SEC_DEF("kprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - SEC_DEF("kretprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), - BPF_PROG_SEC("tc", BPF_PROG_TYPE_SCHED_CLS), - BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - SEC_DEF("tracepoint/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("tp/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("raw_tp/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("tp_btf/", TRACING, - .expected_attach_type = BPF_TRACE_RAW_TP, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fexit/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry.s/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret.s/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fexit.s/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("freplace/", EXT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("lsm/", LSM, - .is_attach_btf = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("lsm.s/", LSM, - .is_attach_btf = true, - .is_sleepable = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("iter/", TRACING, - .expected_attach_type = BPF_TRACE_ITER, - .is_attach_btf = true, - .attach_fn = attach_iter), - SEC_DEF("syscall", SYSCALL, - .is_sleepable = true), + SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace/", EXT, 0, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), + SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), + SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, BPF_XDP_CPUMAP), BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, BPF_XDP), - BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), - BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), - BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), - BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), - BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE), BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_INGRESS), BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS), - BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE), BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE), BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, @@ -8102,7 +8075,7 @@ static const struct bpf_sec_def section_defs[] = { BPF_SK_SKB_STREAM_PARSER), BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_VERDICT), - BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT), BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, @@ -8139,16 +8112,14 @@ static const struct bpf_sec_def section_defs[] = { BPF_CGROUP_GETSOCKOPT), BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT), - BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), + SEC_DEF("struct_ops", STRUCT_OPS, 0, SEC_NONE), BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, BPF_SK_LOOKUP), }; #undef BPF_PROG_SEC_IMPL -#undef BPF_PROG_SEC #undef BPF_APROG_SEC #undef BPF_EAPROG_SEC -#undef BPF_APROG_COMPAT #undef SEC_DEF #define MAX_TYPE_NAME_SIZE 32 @@ -8176,8 +8147,15 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (attach_type && !section_defs[i].is_attachable) - continue; + const struct bpf_sec_def *sec_def = §ion_defs[i]; + + if (attach_type) { + if (sec_def->preload_fn != libbpf_preload_prog) + continue; + + if (!(sec_def->cookie & SEC_ATTACHABLE)) + continue; + } if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); @@ -8501,20 +8479,13 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, return -ESRCH; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id) +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id) { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *attach_name; int err = 0; - if (!prog->sec_def || !prog->sec_def->is_attach_btf) { - pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", - prog->sec_name); - return -ESRCH; - } - attach_name = prog->sec_name + strlen(prog->sec_def->sec); - /* BPF program's BTF ID */ if (attach_prog_fd) { err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); @@ -8564,7 +8535,9 @@ int libbpf_attach_type_by_name(const char *name, return libbpf_err(-EINVAL); } - if (!sec_def->is_attachable) + if (sec_def->preload_fn != libbpf_preload_prog) + return libbpf_err(-EINVAL); + if (!(sec_def->cookie & SEC_ATTACHABLE)) return libbpf_err(-EINVAL); *attach_type = sec_def->expected_attach_type; From d41ea045a6e461673d1b2fad106b8cd04c3ba863 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:44 -0700 Subject: [PATCH 59/85] libbpf: Complete SEC() table unification for BPF_APROG_SEC/BPF_EAPROG_SEC Complete SEC() table refactoring towards unified form by rewriting BPF_APROG_SEC and BPF_EAPROG_SEC definitions with SEC_DEF(SEC_ATTACHABLE_OPT) (for optional expected_attach_type) and SEC_DEF(SEC_ATTACHABLE) (mandatory expected_attach_type), respectively. Drop BPF_APROG_SEC, BPF_EAPROG_SEC, and BPF_PROG_SEC_IMPL macros after that, leaving SEC_DEF() macro as the only one used. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-9-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 136 +++++++++++------------------------------ 1 file changed, 35 insertions(+), 101 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 954c135a8adf..4ba67dff6b0d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7970,32 +7970,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ - attachable, attach_btf) \ - { \ - .sec = string, \ - .prog_type = ptype, \ - .expected_attach_type = eatype, \ - .cookie = (long) ( \ - (eatype_optional ? SEC_EXP_ATTACH_OPT : 0) | \ - (attachable ? SEC_ATTACHABLE : 0) | \ - (attach_btf ? SEC_ATTACH_BTF : 0) \ - ), \ - .preload_fn = libbpf_preload_prog, \ - } - -/* Programs that can be attached. */ -#define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) - -/* Programs that must specify expected attach type at load time. */ -#define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) - -/* Programs that use BTF to identify attach point */ -#define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) - #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ @@ -8014,10 +7988,8 @@ static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) static const struct bpf_sec_def section_defs[] = { SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE), - BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), - BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE), SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), @@ -8041,87 +8013,49 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), - BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, - BPF_XDP_DEVMAP), - BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, - BPF_XDP_CPUMAP), - BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, - BPF_XDP), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT), SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE), SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE), SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE), SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE), SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE), - BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_INGRESS), - BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_EGRESS), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT), SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE), - BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_RELEASE), - BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET4_POST_BIND), - BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET6_POST_BIND), - BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, - BPF_CGROUP_DEVICE), - BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, - BPF_CGROUP_SOCK_OPS), - BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_PARSER), - BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_VERDICT), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), - BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, - BPF_SK_MSG_VERDICT), - BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, - BPF_LIRC_MODE2), - BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, - BPF_FLOW_DISSECTOR), - BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_BIND), - BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_BIND), - BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_CONNECT), - BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_CONNECT), - BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_SENDMSG), - BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_SENDMSG), - BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_RECVMSG), - BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_RECVMSG), - BPF_EAPROG_SEC("cgroup/getpeername4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getpeername6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getsockname4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/getsockname6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, - BPF_CGROUP_SYSCTL), - BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_GETSOCKOPT), - BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_SETSOCKOPT), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), SEC_DEF("struct_ops", STRUCT_OPS, 0, SEC_NONE), - BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, - BPF_SK_LOOKUP), + SEC_DEF("sk_lookup/", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), }; -#undef BPF_PROG_SEC_IMPL -#undef BPF_APROG_SEC -#undef BPF_EAPROG_SEC -#undef SEC_DEF - #define MAX_TYPE_NAME_SIZE 32 static const struct bpf_sec_def *find_sec_def(const char *sec_name) From dd94d45cf0acb1d82748b17e1106b2c8b487b28b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:45 -0700 Subject: [PATCH 60/85] libbpf: Add opt-in strict BPF program section name handling logic Implement strict ELF section name handling for BPF programs. It utilizes `libbpf_set_strict_mode()` framework and adds new flag: LIBBPF_STRICT_SEC_NAME. If this flag is set, libbpf will enforce exact section name matching for a lot of program types that previously allowed just partial prefix match. E.g., if previously SEC("xdp_whatever_i_want") was allowed, now in strict mode only SEC("xdp") will be accepted, which makes SEC("") definitions cleaner and more structured. SEC() now won't be used as yet another way to uniquely encode BPF program identifier (for that C function name is better and is guaranteed to be unique within bpf_object). Now SEC() is strictly BPF program type and, depending on program type, extra load/attach parameter specification. Libbpf completely supports multiple BPF programs in the same ELF section, so multiple BPF programs of the same type/specification easily co-exist together within the same bpf_object scope. Additionally, a new (for now internal) convention is introduced: section name that can be a stand-alone exact BPF program type specificator, but also could have extra parameters after '/' delimiter. An example of such section is "struct_ops", which can be specified by itself, but also allows to specify the intended operation to be attached to, e.g., "struct_ops/dctcp_init". Note, that "struct_ops_some_op" is not allowed. Such section definition is specified as "struct_ops+". This change is part of libbpf 1.0 effort ([0], [1]). [0] Closes: https://github.com/libbpf/libbpf/issues/271 [1] https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#stricter-and-more-uniform-bpf-program-section-name-sec-handling Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-10-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 136 ++++++++++++++++++++++------------ tools/lib/bpf/libbpf_legacy.h | 9 +++ 2 files changed, 99 insertions(+), 46 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4ba67dff6b0d..3e1f6211b9b9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -242,6 +242,8 @@ enum sec_def_flags { SEC_ATTACH_BTF = 4, /* BPF program type allows sleeping/blocking in kernel */ SEC_SLEEPABLE = 8, + /* allow non-strict prefix matching */ + SEC_SLOPPY_PFX = 16, }; struct bpf_sec_def { @@ -7987,16 +7989,16 @@ static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); static const struct bpf_sec_def section_defs[] = { - SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE), - SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE), - SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), @@ -8015,44 +8017,44 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), - SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT), - SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE), - SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE), - SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE), - SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE), - SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE), - SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE), - SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE), - SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE), - SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), - SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), - SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), - SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), - SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), - SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), - SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), - SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), - SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), - SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), - SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), - SEC_DEF("struct_ops", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("sk_lookup/", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), }; @@ -8060,11 +8062,53 @@ static const struct bpf_sec_def section_defs[] = { static const struct bpf_sec_def *find_sec_def(const char *sec_name) { - int i, n = ARRAY_SIZE(section_defs); + const struct bpf_sec_def *sec_def; + enum sec_def_flags sec_flags; + int i, n = ARRAY_SIZE(section_defs), len; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; for (i = 0; i < n; i++) { - if (str_has_pfx(sec_name, section_defs[i].sec)) - return §ion_defs[i]; + sec_def = §ion_defs[i]; + sec_flags = sec_def->cookie; + len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; + continue; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + continue; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return sec_def; + continue; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; + continue; + } + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + if (strcmp(sec_name, sec_def->sec) == 0) + return sec_def; } return NULL; } diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index df0d03dcffab..74e6f860f703 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -46,6 +46,15 @@ enum libbpf_strict_mode { */ LIBBPF_STRICT_DIRECT_ERRS = 0x02, + /* + * Enforce strict BPF program section (SEC()) names. + * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were + * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become + * unrecognized by libbpf and would have to be just SEC("xdp") and + * SEC("xdp") and SEC("perf_event"). + */ + LIBBPF_STRICT_SEC_NAME = 0x04, + __LIBBPF_STRICT_LAST, }; From 7c80c87ad56a05ec56069c3f5d7e60b5b1eb19b4 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Sep 2021 09:19:46 -0700 Subject: [PATCH 61/85] selftests/bpf: Switch sk_lookup selftests to strict SEC("sk_lookup") use Update "sk_lookup/" definition to be a stand-alone type specifier, with backwards-compatible prefix match logic in non-libbpf-1.0 mode. Currently in selftests all the "sk_lookup/" uses just use for duplicated unique name encoding, which is redundant as BPF program's name (C function name) uniquely and descriptively identifies the intended use for such BPF programs. With libbpf's SEC_DEF("sk_lookup") definition updated, switch existing sk_lookup programs to use "unqualified" SEC("sk_lookup") section names, with no random text after it. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Dave Marchevsky Link: https://lore.kernel.org/bpf/20210928161946.2512801-11-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 2 +- .../selftests/bpf/progs/test_sk_lookup.c | 38 +++++++++---------- 2 files changed, 20 insertions(+), 20 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 3e1f6211b9b9..1c859b32968d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -8055,7 +8055,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), - SEC_DEF("sk_lookup/", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; #define MAX_TYPE_NAME_SIZE 32 diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index 6c4d32c56765..48534d810391 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -72,13 +72,13 @@ static const __u16 DST_PORT = 7007; /* Host byte order */ static const __u32 DST_IP4 = IP4(127, 0, 0, 1); static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); -SEC("sk_lookup/lookup_pass") +SEC("sk_lookup") int lookup_pass(struct bpf_sk_lookup *ctx) { return SK_PASS; } -SEC("sk_lookup/lookup_drop") +SEC("sk_lookup") int lookup_drop(struct bpf_sk_lookup *ctx) { return SK_DROP; @@ -97,7 +97,7 @@ int reuseport_drop(struct sk_reuseport_md *ctx) } /* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ -SEC("sk_lookup/redir_port") +SEC("sk_lookup") int redir_port(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -116,7 +116,7 @@ int redir_port(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip4") +SEC("sk_lookup") int redir_ip4(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -139,7 +139,7 @@ int redir_ip4(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip6") +SEC("sk_lookup") int redir_ip6(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -164,7 +164,7 @@ int redir_ip6(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a") +SEC("sk_lookup") int select_sock_a(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -179,7 +179,7 @@ int select_sock_a(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a_no_reuseport") +SEC("sk_lookup") int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -205,7 +205,7 @@ int select_sock_b(struct sk_reuseport_md *ctx) } /* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ -SEC("sk_lookup/sk_assign_eexist") +SEC("sk_lookup") int sk_assign_eexist(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -238,7 +238,7 @@ out: } /* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ -SEC("sk_lookup/sk_assign_replace_flag") +SEC("sk_lookup") int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -270,7 +270,7 @@ out: } /* Check that bpf_sk_assign(sk=NULL) is accepted. */ -SEC("sk_lookup/sk_assign_null") +SEC("sk_lookup") int sk_assign_null(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk = NULL; @@ -313,7 +313,7 @@ out: } /* Check that selected sk is accessible through context. */ -SEC("sk_lookup/access_ctx_sk") +SEC("sk_lookup") int access_ctx_sk(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk1 = NULL, *sk2 = NULL; @@ -379,7 +379,7 @@ out: * are not covered because they give bogus results, that is the * verifier ignores the offset. */ -SEC("sk_lookup/ctx_narrow_access") +SEC("sk_lookup") int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -553,7 +553,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) } /* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ -SEC("sk_lookup/sk_assign_esocknosupport") +SEC("sk_lookup") int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -578,28 +578,28 @@ out: return ret; } -SEC("sk_lookup/multi_prog_pass1") +SEC("sk_lookup") int multi_prog_pass1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_pass2") +SEC("sk_lookup") int multi_prog_pass2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_drop1") +SEC("sk_lookup") int multi_prog_drop1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_DROP; } -SEC("sk_lookup/multi_prog_drop2") +SEC("sk_lookup") int multi_prog_drop2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); @@ -623,7 +623,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir1") +SEC("sk_lookup") int multi_prog_redir1(struct bpf_sk_lookup *ctx) { int ret; @@ -633,7 +633,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir2") +SEC("sk_lookup") int multi_prog_redir2(struct bpf_sk_lookup *ctx) { int ret; From 09710d82c0a3469eadc32781721ac2336fdf915d Mon Sep 17 00:00:00 2001 From: Yucong Sun Date: Tue, 28 Sep 2021 11:42:21 -0700 Subject: [PATCH 62/85] bpftool: Avoid using "?: " in generated code "?:" is a GNU C extension, some environment has warning flags for its use, or even prohibit it directly. This patch avoid triggering these problems by simply expand it to its full form, no functionality change. Signed-off-by: Yucong Sun Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210928184221.1545079-1-fallentree@fb.com --- tools/bpf/bpftool/gen.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index e3ec47a6a612..cc835859465b 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -803,7 +803,10 @@ static int do_skeleton(int argc, char **argv) } \n\ \n\ err = %1$s__create_skeleton(obj); \n\ - err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ if (err) \n\ goto err_out; \n\ \n\ From 3d717fad5081b8e3bda76d86907fad95398cbde8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 28 Sep 2021 16:09:45 -0700 Subject: [PATCH 63/85] bpf: Replace "want address" users of BPF_CAST_CALL with BPF_CALL_IMM In order to keep ahead of cases in the kernel where Control Flow Integrity (CFI) may trip over function call casts, enabling -Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes various warnings and is one of the last places in the kernel triggering this warning. Most places using BPF_CAST_CALL actually just want a void * to perform math on. It's not actually performing a call, so just use a different helper to get the void *, by way of the new BPF_CALL_IMM() helper, which can clean up a common copy/paste idiom as well. This change results in no object code difference. Signed-off-by: Kees Cook Signed-off-by: Alexei Starovoitov Reviewed-by: Gustavo A. R. Silva Acked-by: Andrii Nakryiko Link: https://github.com/KSPP/linux/issues/20 Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com Link: https://lore.kernel.org/bpf/20210928230946.4062144-2-keescook@chromium.org --- include/linux/filter.h | 6 +++++- kernel/bpf/hashtab.c | 6 +++--- kernel/bpf/verifier.c | 26 +++++++++----------------- lib/test_bpf.c | 2 +- 4 files changed, 18 insertions(+), 22 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a93c12543ee..6c247663d4ce 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -365,13 +365,17 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CAST_CALL(x) \ ((u64 (*)(u64, u64, u64, u64, u64))(x)) +/* Convert function address to BPF immediate */ + +#define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) + #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ - .imm = ((FUNC) - __bpf_call_base) }) + .imm = BPF_CALL_IMM(FUNC) }) /* Raw code statement block */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 32471ba02708..3d8f9d6997d5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -2397,7 +2397,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7a8351604f67..1433752db740 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1744,7 +1744,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; - desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base; + desc->imm = BPF_CALL_IMM(addr); err = btf_distill_func_proto(&env->log, btf_vmlinux, func_proto, func_name, &desc->func_model); @@ -12514,8 +12514,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; - insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses @@ -12995,32 +12994,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env) patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: - insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); continue; case BPF_FUNC_map_update_elem: - insn->imm = BPF_CAST_CALL(ops->map_update_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_update_elem); continue; case BPF_FUNC_map_delete_elem: - insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_delete_elem); continue; case BPF_FUNC_map_push_elem: - insn->imm = BPF_CAST_CALL(ops->map_push_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_push_elem); continue; case BPF_FUNC_map_pop_elem: - insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_pop_elem); continue; case BPF_FUNC_map_peek_elem: - insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_peek_elem); continue; case BPF_FUNC_redirect_map: - insn->imm = BPF_CAST_CALL(ops->map_redirect) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_redirect); continue; } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 08f438e6fe9e..21ea1ab253a1 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -12439,7 +12439,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) err = -EFAULT; goto out_err; } - *insn = BPF_EMIT_CALL(BPF_CAST_CALL(addr)); + *insn = BPF_EMIT_CALL(addr); if ((long)__bpf_call_base + insn->imm != addr) *insn = BPF_JMP_A(0); /* Skip: NOP */ break; From 102acbacfd9a96d101abd96d1a7a5bf92b7c3e8e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 28 Sep 2021 16:09:46 -0700 Subject: [PATCH 64/85] bpf: Replace callers of BPF_CAST_CALL with proper function typedef In order to keep ahead of cases in the kernel where Control Flow Integrity (CFI) may trip over function call casts, enabling -Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes various warnings and is one of the last places in the kernel triggering this warning. For actual function calls, replace BPF_CAST_CALL() with a typedef, which captures the same details about the given function pointers. This change results in no object code difference. Signed-off-by: Kees Cook Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Gustavo A. R. Silva Link: https://github.com/KSPP/linux/issues/20 Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com Link: https://lore.kernel.org/bpf/20210928230946.4062144-3-keescook@chromium.org --- include/linux/bpf.h | 4 +++- include/linux/filter.h | 5 ----- kernel/bpf/arraymap.c | 7 +++---- kernel/bpf/hashtab.c | 7 +++---- kernel/bpf/helpers.c | 5 ++--- 5 files changed, 11 insertions(+), 17 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b6c45a6cbbba..19735d59230a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -48,6 +48,7 @@ extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; +typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -142,7 +143,8 @@ struct bpf_map_ops { int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); - int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn, + int (*map_for_each_callback)(struct bpf_map *map, + bpf_callback_t callback_fn, void *callback_ctx, u64 flags); /* BTF name and id of struct allocated by map_alloc */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 6c247663d4ce..47f80adbe744 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -360,11 +360,6 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = TGT }) -/* Function call */ - -#define BPF_CAST_CALL(x) \ - ((u64 (*)(u64, u64, u64, u64, u64))(x)) - /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index cebd4fb06d19..5e1ccfae916b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -645,7 +645,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_array_map_info), }; -static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn, +static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags) { u32 i, key, num_elems = 0; @@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn, val = array->value + array->elem_size * i; num_elems++; key = i; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)&key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)&key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) break; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3d8f9d6997d5..d29af9988f37 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -2049,7 +2049,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_hash_map_info), }; -static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn, +static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); @@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn, val = elem->key + roundup_key_size; } num_elems++; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) { rcu_read_unlock(); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 2c604ff8c7fb..1ffd469c217f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1056,7 +1056,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); struct bpf_map *map = t->map; void *value = t->value; - void *callback_fn; + bpf_callback_t callback_fn; void *key; u32 idx; @@ -1081,8 +1081,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) key = value - round_up(map->key_size, 8); } - BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, - (u64)(long)value, 0, 0); + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); /* The verifier checked that return value is zero. */ this_cpu_write(hrtimer_running, NULL); From 38261f369fb905552ebdd3feb9699c0788fd3371 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 28 Sep 2021 20:30:00 -0700 Subject: [PATCH 65/85] selftests/bpf: Fix probe_user test failure with clang build kernel clang build kernel failed the selftest probe_user. $ ./test_progs -t probe_user $ ... $ test_probe_user:PASS:get_kprobe_res 0 nsec $ test_probe_user:FAIL:check_kprobe_res wrong kprobe res from probe read: 0.0.0.0:0 $ #94 probe_user:FAIL The test attached to kernel function __sys_connect(). In net/socket.c, we have int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { ...... } ... SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { return __sys_connect(fd, uservaddr, addrlen); } The gcc compiler (8.5.0) does not inline __sys_connect() in syscall entry function. But latest clang trunk did the inlining. So the bpf program is not triggered. To make the test more reliable, let us kprobe the syscall entry function instead. Note that x86_64, arm64 and s390 have syscall wrappers and they have to be handled specially. Signed-off-by: Yonghong Song Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210929033000.3711921-1-yhs@fb.com --- .../selftests/bpf/prog_tests/probe_user.c | 4 +-- .../selftests/bpf/progs/test_probe_user.c | 28 +++++++++++++++++-- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 95bd12097358..52fe157e2a90 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,7 +3,7 @@ void test_probe_user(void) { - const char *prog_name = "kprobe/__sys_connect"; + const char *prog_name = "handle_sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -18,7 +18,7 @@ void test_probe_user(void) if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; - kprobe_prog = bpf_object__find_program_by_title(obj, prog_name); + kprobe_prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!kprobe_prog, "find_probe", "prog '%s' not found\n", prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 89b3532ccc75..8812a90da4eb 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -8,13 +8,37 @@ #include #include +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "" +#endif + static struct sockaddr_in old; -SEC("kprobe/__sys_connect") +SEC("kprobe/" SYS_PREFIX "sys_connect") int BPF_KPROBE(handle_sys_connect) { - void *ptr = (void *)PT_REGS_PARM2(ctx); +#if SYSCALL_WRAPPER == 1 + struct pt_regs *real_regs; +#endif struct sockaddr_in new; + void *ptr; + +#if SYSCALL_WRAPPER == 0 + ptr = (void *)PT_REGS_PARM2(ctx); +#else + real_regs = (struct pt_regs *)PT_REGS_PARM1(ctx); + bpf_probe_read_kernel(&ptr, sizeof(ptr), &PT_REGS_PARM2(real_regs)); +#endif bpf_probe_read_user(&old, sizeof(old), ptr); __builtin_memset(&new, 0xab, sizeof(new)); From 3103836496e75095ac208cc180a9fe8f7ff33fd8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 29 Sep 2021 08:14:03 +0200 Subject: [PATCH 66/85] xsk: Fix clang build error in __xp_alloc Fix a build error with clang in __xp_alloc(): [...] net/xdp/xsk_buff_pool.c:465:15: error: variable 'xskb' is uninitialized when used here [-Werror,-Wuninitialized] xp_release(xskb); ^~~~ This is correctly detected by clang, but not gcc. In fact, the xp_release() statement should not be there at all in the refactored code, just remove it. Fixes: 94033cd8e73b ("xsk: Optimize for aligned case") Reported-by: Nathan Chancellor Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20210929061403.8587-1-magnus.karlsson@gmail.com --- net/xdp/xsk_buff_pool.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 96b14e51ba7e..90c4e1e819d3 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -462,7 +462,6 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool) for (;;) { if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) { pool->fq->queue_empty_descs++; - xp_release(xskb); return NULL; } From e31eec77e4ab90dcec7d2da93415f839098dc287 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 27 Sep 2021 20:29:40 +0530 Subject: [PATCH 67/85] bpf: selftests: Fix fd cleanup in get_branch_snapshot Cleanup code uses while (cpu++ < cpu_cnt) for closing fds, which means it starts iterating from 1 for closing fds. If the first fd is -1, it skips over it and closes garbage fds (typically zero) in the remaining array. This leads to test failures for future tests when they end up storing fd 0 (as the slot becomes free due to close(0)) in ldimm64's BTF fd, ending up trying to match module BTF id with vmlinux. This was observed as spurious CI failure for the ksym_module_libbpf and module_attach tests. The test ends up closing fd 0 and breaking libbpf's assumption that module BTF fd will always be > 0, which leads to the kernel thinking that we are pointing to a BTF ID in vmlinux BTF. Fixes: 025bd7c753aa (selftests/bpf: Add test for bpf_get_branch_snapshot) Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210927145941.1383001-12-memxor@gmail.com --- tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c index f81db9135ae4..67e86f8d8677 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c +++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c @@ -38,10 +38,9 @@ static int create_perf_events(void) static void close_perf_events(void) { - int cpu = 0; - int fd; + int cpu, fd; - while (cpu++ < cpu_cnt) { + for (cpu = 0; cpu < cpu_cnt; cpu++) { fd = pfd_array[cpu]; if (fd < 0) break; From 66fe33241726d1f872e55d95a35c063d58602ae1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 27 Sep 2021 20:29:37 +0530 Subject: [PATCH 68/85] libbpf: Make gen_loader data aligned. Align gen_loader data to 8 byte boundary to make sure union bpf_attr, bpf_insns and other structs are aligned. Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210927145941.1383001-9-memxor@gmail.com --- tools/lib/bpf/gen_loader.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 8df718a6b142..80087b13877f 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "btf.h" #include "bpf.h" #include "libbpf.h" @@ -135,13 +136,17 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) static int add_data(struct bpf_gen *gen, const void *data, __u32 size) { + __u32 size8 = roundup(size, 8); + __u64 zero = 0; void *prev; - if (realloc_data_buf(gen, size)) + if (realloc_data_buf(gen, size8)) return 0; prev = gen->data_cur; memcpy(gen->data_cur, data, size); gen->data_cur += size; + memcpy(gen->data_cur, &zero, size8 - size); + gen->data_cur += size8 - size; return prev - gen->data_start; } From de21d8bf777240c6d6dfefa39b4925729e32c0fd Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Tue, 28 Sep 2021 10:30:59 +0100 Subject: [PATCH 69/85] bpf: Do not invoke the XDP dispatcher for PROG_RUN with single repeat We have a unit test that invokes an XDP program with 1m different inputs, aka 1m BPF_PROG_RUN syscalls. We run this test concurrently with slight variations in how we generated the input. Since commit f23c4b3924d2 ("bpf: Start using the BPF dispatcher in BPF_TEST_RUN") the unit test has slowed down significantly. Digging deeper reveals that the concurrent tests are serialised in the kernel on the XDP dispatcher. This is a global resource that is protected by a mutex, on which we contend. Fix this by not calling into the XDP dispatcher if we only want to perform a single run of the BPF program. See: https://lore.kernel.org/bpf/CACAyw9_y4QumOW35qpgTbLsJ532uGq-kVW-VESJzGyiZkypnvw@mail.gmail.com/ Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210928093100.27124-1-lmb@cloudflare.com --- net/bpf/test_run.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fcb2f493f710..6593a71dba5f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -803,7 +803,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (ret) goto free_data; - bpf_prog_change_xdp(NULL, prog); + if (repeat > 1) + bpf_prog_change_xdp(NULL, prog); ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented @@ -824,7 +825,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, sizeof(struct xdp_md)); out: - bpf_prog_change_xdp(prog, NULL); + if (repeat > 1) + bpf_prog_change_xdp(prog, NULL); free_data: kfree(data); free_ctx: From 161ecd537948a7003129889b04a3a0858687bc70 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Wed, 29 Sep 2021 23:38:37 +0200 Subject: [PATCH 70/85] libbpf: Properly ignore STT_SECTION symbols in legacy map definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The previous patch to ignore STT_SECTION symbols only added the ignore condition in one of them. This fails if there's more than one map definition in the 'maps' section, because the subsequent modulus check will fail, resulting in error messages like: libbpf: elf: unable to determine legacy map definition size in ./xdpdump_xdp.o Fix this by also ignoring STT_SECTION in the first loop. Fixes: c3e8c44a9063 ("libbpf: Ignore STT_SECTION symbols in 'maps' section") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210929213837.832449-1-toke@redhat.com --- tools/lib/bpf/libbpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1c859b32968d..7544d7d09160 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1868,6 +1868,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; nr_maps++; } /* Assume equally sized map definitions */ From e68ac0082787f4e8ee6ae5b19076ec7709ce715b Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 27 Sep 2021 20:29:39 +0530 Subject: [PATCH 71/85] libbpf: Fix skel_internal.h to set errno on loader retval < 0 When the loader indicates an internal error (result of a checked bpf system call), it returns the result in attr.test.retval. However, tests that rely on ASSERT_OK_PTR on NULL (returned from light skeleton) may miss that NULL denotes an error if errno is set to 0. This would result in skel pointer being NULL, while ASSERT_OK_PTR returning 1, leading to a SEGV on dereference of skel, because libbpf_get_error relies on the assumption that errno is always set in case of error for ptr == NULL. In particular, this was observed for the ksyms_module test. When executed using `./test_progs -t ksyms`, prior tests manipulated errno and the test didn't crash when it failed at ksyms_module load, while using `./test_progs -t ksyms_module` crashed due to errno being untouched. Fixes: 67234743736a (libbpf: Generate loader program out of BPF ELF file.) Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210927145941.1383001-11-memxor@gmail.com --- tools/lib/bpf/skel_internal.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index b22b50c1b173..9cf66702fa8d 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -105,10 +105,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; - if (err < 0) + if (err < 0) { err = -errno; - else + } else { err = (int)attr.test.retval; + errno = -err; + } goto out; } err = 0; From d4b6f87e8d3929d3d1594fca0256299113301fd7 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Wed, 29 Sep 2021 13:12:50 +0800 Subject: [PATCH 72/85] selftests/bpf: Use kselftest skip code for skipped tests There are several test cases in the bpf directory are still using exit 0 when they need to be skipped. Use kselftest framework skip code instead so it can help us to distinguish the return status. Criterion to filter out what should be fixed in bpf directory: grep -r "exit 0" -B1 | grep -i skip This change might cause some false-positives if people are running these test scripts directly and only checking their return codes, which will change from 0 to 4. However I think the impact should be small as most of our scripts here are already using this skip code. And there will be no such issue if running them with the kselftest framework. Signed-off-by: Po-Hsu Lin Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210929051250.13831-1-po-hsu.lin@canonical.com --- tools/testing/selftests/bpf/test_xdp_meta.sh | 5 ++++- tools/testing/selftests/bpf/test_xdp_vlan.sh | 7 +++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 637fcf4fe4e3..d10cefd6eb09 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -1,5 +1,8 @@ #!/bin/sh +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + cleanup() { if [ "$?" = "0" ]; then @@ -17,7 +20,7 @@ cleanup() ip link set dev lo xdp off 2>/dev/null > /dev/null if [ $? -ne 0 ];then echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit 0 + exit $KSFT_SKIP fi set -e diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index bb8b0da91686..0cbc7604a2f8 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then TESTNAME=xdp_vlan @@ -94,7 +97,7 @@ while true; do -h | --help ) usage; echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit 0 + exit $KSFT_SKIP ;; * ) shift @@ -117,7 +120,7 @@ fi ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit 0 + exit $KSFT_SKIP fi # Interactive mode likely require us to cleanup netns From 6bbc7103738f0e0871a9331351ee3cd4d462b431 Mon Sep 17 00:00:00 2001 From: Kev Jackson Date: Thu, 30 Sep 2021 07:34:02 +0100 Subject: [PATCH 73/85] bpf, xdp, docs: Correct some English grammar and spelling Header DOC on include/net/xdp.h contained a few English grammer and spelling errors. Signed-off-by: Kev Jackson Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/YVVaWmKqA8l9Tm4J@kev-VirtualBox --- include/net/xdp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index ad5b02dcb6f4..447f9b1578f3 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -15,13 +15,13 @@ * level RX-ring queues. It is information that is specific to how * the driver have configured a given RX-ring queue. * - * Each xdp_buff frame received in the driver carry a (pointer) + * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq - * context. Contents is read-mostly and must not be updated during + * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. @@ -30,8 +30,8 @@ * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally need to stop the RX-ring before purging and reallocating - * memory. In that process the driver MUST call unregistor (which - * also apply for driver shutdown and unload). The register API is + * memory. In that process the driver MUST call unregister (which + * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ From caaaa1667bf198c54cc3141ad92ca6ce853e99cd Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:39 +0200 Subject: [PATCH 74/85] bpf/tests: Add tests of BPF_LDX and BPF_STX with small sizes This patch adds a series of tests to verify the behavior of BPF_LDX and BPF_STX with BPF_B//W sizes in isolation. In particular, it checks that BPF_LDX zero-extendeds the result, and that BPF_STX does not overwrite adjacent bytes in memory. BPF_ST and operations on BPF_DW size are deemed to be sufficiently tested by existing tests. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-2-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 254 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 254 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 21ea1ab253a1..a838a6179ca4 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -6907,6 +6907,260 @@ static struct bpf_test tests[] = { { }, { { 0, (u32) (cpu_to_le64(0xfedcba9876543210ULL) >> 32) } }, }, + /* BPF_LDX_MEM B/H/W/DW */ + { + "BPF_LDX_MEM | BPF_B", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x0102030405060708ULL), + BPF_LD_IMM64(R2, 0x0000000000000008ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_B, R0, R10, -1), +#else + BPF_LDX_MEM(BPF_B, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_LDX_MEM | BPF_B, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8182838485868788ULL), + BPF_LD_IMM64(R2, 0x0000000000000088ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_B, R0, R10, -1), +#else + BPF_LDX_MEM(BPF_B, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_LDX_MEM | BPF_H", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x0102030405060708ULL), + BPF_LD_IMM64(R2, 0x0000000000000708ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_H, R0, R10, -2), +#else + BPF_LDX_MEM(BPF_H, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_LDX_MEM | BPF_H, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8182838485868788ULL), + BPF_LD_IMM64(R2, 0x0000000000008788ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_H, R0, R10, -2), +#else + BPF_LDX_MEM(BPF_H, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_LDX_MEM | BPF_W", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x0102030405060708ULL), + BPF_LD_IMM64(R2, 0x0000000005060708ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_W, R0, R10, -4), +#else + BPF_LDX_MEM(BPF_W, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_LDX_MEM | BPF_W, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8182838485868788ULL), + BPF_LD_IMM64(R2, 0x0000000085868788ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_LDX_MEM(BPF_W, R0, R10, -4), +#else + BPF_LDX_MEM(BPF_W, R0, R10, -8), +#endif + BPF_JMP_REG(BPF_JNE, R0, R2, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + /* BPF_STX_MEM B/H/W/DW */ + { + "BPF_STX_MEM | BPF_B", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x0102030405060708ULL), + BPF_LD_IMM64(R3, 0x8090a0b0c0d0e008ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_B, R10, R2, -1), +#else + BPF_STX_MEM(BPF_B, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_STX_MEM | BPF_B, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x8182838485868788ULL), + BPF_LD_IMM64(R3, 0x8090a0b0c0d0e088ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_B, R10, R2, -1), +#else + BPF_STX_MEM(BPF_B, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_STX_MEM | BPF_H", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x0102030405060708ULL), + BPF_LD_IMM64(R3, 0x8090a0b0c0d00708ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_H, R10, R2, -2), +#else + BPF_STX_MEM(BPF_H, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_STX_MEM | BPF_H, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x8182838485868788ULL), + BPF_LD_IMM64(R3, 0x8090a0b0c0d08788ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_H, R10, R2, -2), +#else + BPF_STX_MEM(BPF_H, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_STX_MEM | BPF_W", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x0102030405060708ULL), + BPF_LD_IMM64(R3, 0x8090a0b005060708ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_W, R10, R2, -4), +#else + BPF_STX_MEM(BPF_W, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + { + "BPF_STX_MEM | BPF_W, MSB set", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x8090a0b0c0d0e0f0ULL), + BPF_LD_IMM64(R2, 0x8182838485868788ULL), + BPF_LD_IMM64(R3, 0x8090a0b085868788ULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), +#ifdef __BIG_ENDIAN + BPF_STX_MEM(BPF_W, R10, R2, -4), +#else + BPF_STX_MEM(BPF_W, R10, R2, -8), +#endif + BPF_LDX_MEM(BPF_DW, R0, R10, -8), + BPF_JMP_REG(BPF_JNE, R0, R3, 1), + BPF_ALU64_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, /* BPF_ST(X) | BPF_MEM | BPF_B/H/W/DW */ { "ST_MEM_B: Store/Load byte: max negative", From 89b63462765cc0370f22ebec53d3e83cbbb17613 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:40 +0200 Subject: [PATCH 75/85] bpf/tests: Add zero-extension checks in BPF_ATOMIC tests This patch updates the existing tests of BPF_ATOMIC operations to verify that a 32-bit register operand is properly zero-extended. In particular, it checks the operation on archs that require 32-bit operands to be properly zero-/sign-extended or the result is undefined, e.g. MIPS64. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-3-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index a838a6179ca4..f6983ad7b981 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -7398,15 +7398,20 @@ static struct bpf_test tests[] = { * Individual tests are expanded from template macros for all * combinations of ALU operation, word size and fetching. */ +#define BPF_ATOMIC_POISON(width) ((width) == BPF_W ? (0xbaadf00dULL << 32) : 0) + #define BPF_ATOMIC_OP_TEST1(width, op, logic, old, update, result) \ { \ "BPF_ATOMIC | " #width ", " #op ": Test: " \ #old " " #logic " " #update " = " #result, \ .u.insns_int = { \ - BPF_ALU32_IMM(BPF_MOV, R5, update), \ + BPF_LD_IMM64(R5, (update) | BPF_ATOMIC_POISON(width)), \ BPF_ST_MEM(width, R10, -40, old), \ BPF_ATOMIC_OP(width, op, R10, R5, -40), \ BPF_LDX_MEM(width, R0, R10, -40), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ BPF_EXIT_INSN(), \ }, \ INTERNAL, \ @@ -7420,11 +7425,14 @@ static struct bpf_test tests[] = { #old " " #logic " " #update " = " #result, \ .u.insns_int = { \ BPF_ALU64_REG(BPF_MOV, R1, R10), \ - BPF_ALU32_IMM(BPF_MOV, R0, update), \ + BPF_LD_IMM64(R0, (update) | BPF_ATOMIC_POISON(width)), \ BPF_ST_MEM(BPF_W, R10, -40, old), \ BPF_ATOMIC_OP(width, op, R10, R0, -40), \ BPF_ALU64_REG(BPF_MOV, R0, R10), \ BPF_ALU64_REG(BPF_SUB, R0, R1), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ BPF_EXIT_INSN(), \ }, \ INTERNAL, \ @@ -7438,10 +7446,13 @@ static struct bpf_test tests[] = { #old " " #logic " " #update " = " #result, \ .u.insns_int = { \ BPF_ALU64_REG(BPF_MOV, R0, R10), \ - BPF_ALU32_IMM(BPF_MOV, R1, update), \ + BPF_LD_IMM64(R1, (update) | BPF_ATOMIC_POISON(width)), \ BPF_ST_MEM(width, R10, -40, old), \ BPF_ATOMIC_OP(width, op, R10, R1, -40), \ BPF_ALU64_REG(BPF_SUB, R0, R10), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ BPF_EXIT_INSN(), \ }, \ INTERNAL, \ @@ -7454,10 +7465,10 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | " #width ", " #op ": Test fetch: " \ #old " " #logic " " #update " = " #result, \ .u.insns_int = { \ - BPF_ALU32_IMM(BPF_MOV, R3, update), \ + BPF_LD_IMM64(R3, (update) | BPF_ATOMIC_POISON(width)), \ BPF_ST_MEM(width, R10, -40, old), \ BPF_ATOMIC_OP(width, op, R10, R3, -40), \ - BPF_ALU64_REG(BPF_MOV, R0, R3), \ + BPF_ALU32_REG(BPF_MOV, R0, R3), \ BPF_EXIT_INSN(), \ }, \ INTERNAL, \ @@ -7555,6 +7566,7 @@ static struct bpf_test tests[] = { BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab), BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab), BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab), +#undef BPF_ATOMIC_POISON #undef BPF_ATOMIC_OP_TEST1 #undef BPF_ATOMIC_OP_TEST2 #undef BPF_ATOMIC_OP_TEST3 From f68e8efd7fa506928432b8cd41b8c7d91d804e02 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:41 +0200 Subject: [PATCH 76/85] bpf/tests: Add exhaustive tests of BPF_ATOMIC magnitudes This patch adds a series of test to verify the operation of BPF_ATOMIC with BPF_DW and BPF_W sizes, for all power-of-two magnitudes of the register value operand. Also fixes a confusing typo in the comment for a related test. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-4-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 504 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 503 insertions(+), 1 deletion(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index f6983ad7b981..84efb23e09d0 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -796,7 +796,7 @@ static int __bpf_fill_pattern(struct bpf_test *self, void *arg, /* * Exhaustive tests of ALU operations for all combinations of power-of-two * magnitudes of the operands, both for positive and negative values. The - * test is designed to verify e.g. the JMP and JMP32 operations for JITs that + * test is designed to verify e.g. the ALU and ALU64 operations for JITs that * emit different code depending on the magnitude of the immediate value. */ @@ -1137,6 +1137,306 @@ static int bpf_fill_alu32_mod_reg(struct bpf_test *self) return __bpf_fill_alu32_reg(self, BPF_MOD); } +/* + * Exhaustive tests of atomic operations for all power-of-two operand + * magnitudes, both for positive and negative values. + */ + +static int __bpf_emit_atomic64(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + u64 keep, fetch, res; + int i = 0; + + if (!insns) + return 21; + + switch (op) { + case BPF_XCHG: + res = src; + break; + default: + __bpf_alu_result(&res, dst, src, BPF_OP(op)); + } + + keep = 0x0123456789abcdefULL; + if (op & BPF_FETCH) + fetch = dst; + else + fetch = src; + + i += __bpf_ld_imm64(&insns[i], R0, keep); + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + i += __bpf_ld_imm64(&insns[i], R3, res); + i += __bpf_ld_imm64(&insns[i], R4, fetch); + i += __bpf_ld_imm64(&insns[i], R5, keep); + + insns[i++] = BPF_STX_MEM(BPF_DW, R10, R1, -8); + insns[i++] = BPF_ATOMIC_OP(BPF_DW, op, R10, R2, -8); + insns[i++] = BPF_LDX_MEM(BPF_DW, R1, R10, -8); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R2, R4, 1); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R5, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; +} + +static int __bpf_emit_atomic32(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int op = *(int *)arg; + u64 keep, fetch, res; + int i = 0; + + if (!insns) + return 21; + + switch (op) { + case BPF_XCHG: + res = src; + break; + default: + __bpf_alu_result(&res, (u32)dst, (u32)src, BPF_OP(op)); + } + + keep = 0x0123456789abcdefULL; + if (op & BPF_FETCH) + fetch = (u32)dst; + else + fetch = src; + + i += __bpf_ld_imm64(&insns[i], R0, keep); + i += __bpf_ld_imm64(&insns[i], R1, (u32)dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + i += __bpf_ld_imm64(&insns[i], R3, (u32)res); + i += __bpf_ld_imm64(&insns[i], R4, fetch); + i += __bpf_ld_imm64(&insns[i], R5, keep); + + insns[i++] = BPF_STX_MEM(BPF_W, R10, R1, -4); + insns[i++] = BPF_ATOMIC_OP(BPF_W, op, R10, R2, -4); + insns[i++] = BPF_LDX_MEM(BPF_W, R1, R10, -4); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 1); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R2, R4, 1); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R5, 1); + insns[i++] = BPF_EXIT_INSN(); + + return i; +} + +static int __bpf_emit_cmpxchg64(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int i = 0; + + if (!insns) + return 23; + + i += __bpf_ld_imm64(&insns[i], R0, ~dst); + i += __bpf_ld_imm64(&insns[i], R1, dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + + /* Result unsuccessful */ + insns[i++] = BPF_STX_MEM(BPF_DW, R10, R1, -8); + insns[i++] = BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -8); + insns[i++] = BPF_LDX_MEM(BPF_DW, R3, R10, -8); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R1, R3, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R3, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + /* Result successful */ + insns[i++] = BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -8); + insns[i++] = BPF_LDX_MEM(BPF_DW, R3, R10, -8); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R2, R3, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R1, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + return i; +} + +static int __bpf_emit_cmpxchg32(struct bpf_test *self, void *arg, + struct bpf_insn *insns, s64 dst, s64 src) +{ + int i = 0; + + if (!insns) + return 27; + + i += __bpf_ld_imm64(&insns[i], R0, ~dst); + i += __bpf_ld_imm64(&insns[i], R1, (u32)dst); + i += __bpf_ld_imm64(&insns[i], R2, src); + + /* Result unsuccessful */ + insns[i++] = BPF_STX_MEM(BPF_W, R10, R1, -4); + insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); + insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); + + insns[i++] = BPF_JMP32_REG(BPF_JEQ, R1, R3, 2); + insns[i++] = BPF_MOV32_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R3, 2); + insns[i++] = BPF_MOV32_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + /* Result successful */ + i += __bpf_ld_imm64(&insns[i], R0, dst); + insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); + insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); + + insns[i++] = BPF_JMP32_REG(BPF_JEQ, R2, R3, 2); + insns[i++] = BPF_MOV32_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_JMP_REG(BPF_JEQ, R0, R1, 2); + insns[i++] = BPF_MOV32_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + return i; +} + +static int __bpf_fill_atomic64(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + 0, PATTERN_BLOCK2, + &__bpf_emit_atomic64); +} + +static int __bpf_fill_atomic32(struct bpf_test *self, int op) +{ + return __bpf_fill_pattern(self, &op, 64, 64, + 0, PATTERN_BLOCK2, + &__bpf_emit_atomic32); +} + +/* 64-bit atomic operations */ +static int bpf_fill_atomic64_add(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_ADD); +} + +static int bpf_fill_atomic64_and(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_AND); +} + +static int bpf_fill_atomic64_or(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_OR); +} + +static int bpf_fill_atomic64_xor(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_XOR); +} + +static int bpf_fill_atomic64_add_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_ADD | BPF_FETCH); +} + +static int bpf_fill_atomic64_and_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_AND | BPF_FETCH); +} + +static int bpf_fill_atomic64_or_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_OR | BPF_FETCH); +} + +static int bpf_fill_atomic64_xor_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_XOR | BPF_FETCH); +} + +static int bpf_fill_atomic64_xchg(struct bpf_test *self) +{ + return __bpf_fill_atomic64(self, BPF_XCHG); +} + +static int bpf_fill_cmpxchg64(struct bpf_test *self) +{ + return __bpf_fill_pattern(self, NULL, 64, 64, 0, PATTERN_BLOCK2, + &__bpf_emit_cmpxchg64); +} + +/* 32-bit atomic operations */ +static int bpf_fill_atomic32_add(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_ADD); +} + +static int bpf_fill_atomic32_and(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_AND); +} + +static int bpf_fill_atomic32_or(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_OR); +} + +static int bpf_fill_atomic32_xor(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_XOR); +} + +static int bpf_fill_atomic32_add_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_ADD | BPF_FETCH); +} + +static int bpf_fill_atomic32_and_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_AND | BPF_FETCH); +} + +static int bpf_fill_atomic32_or_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_OR | BPF_FETCH); +} + +static int bpf_fill_atomic32_xor_fetch(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_XOR | BPF_FETCH); +} + +static int bpf_fill_atomic32_xchg(struct bpf_test *self) +{ + return __bpf_fill_atomic32(self, BPF_XCHG); +} + +static int bpf_fill_cmpxchg32(struct bpf_test *self) +{ + return __bpf_fill_pattern(self, NULL, 64, 64, 0, PATTERN_BLOCK2, + &__bpf_emit_cmpxchg32); +} + /* * Test the two-instruction 64-bit immediate load operation for all * power-of-two magnitudes of the immediate operand. For each MSB, a block @@ -10721,6 +11021,208 @@ static struct bpf_test tests[] = { { { 0, 1 } }, .fill_helper = bpf_fill_ld_imm64, }, + /* 64-bit ATOMIC magnitudes */ + { + "ATOMIC_DW_ADD: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_add, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_AND: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_and, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_OR: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_or, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_XOR: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xor, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_ADD_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_add_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_AND_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_and_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_OR_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_or_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_XOR_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xor_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_XCHG: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xchg, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_DW_CMPXCHG: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_cmpxchg64, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + /* 64-bit atomic magnitudes */ + { + "ATOMIC_W_ADD: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_add, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_AND: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_and, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_OR: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_or, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_XOR: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xor, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_ADD_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_add_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_AND_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_and_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_OR_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_or_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_XOR_FETCH: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xor_fetch, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_XCHG: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xchg, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, + { + "ATOMIC_W_CMPXCHG: all operand magnitudes", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_cmpxchg32, + .stack_depth = 8, + .nr_testruns = NR_PATTERN_RUNS, + }, /* JMP immediate magnitudes */ { "JMP_JSET_K: all immediate value magnitudes", From 0bbaa02b481682004cf812dbeca68272752a5e8a Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:42 +0200 Subject: [PATCH 77/85] bpf/tests: Add tests to check source register zero-extension This patch adds tests to check that the source register is preserved when zero-extending a 32-bit value. In particular, it checks that the source operand is not zero-extended in-place. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-5-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 143 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 143 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 84efb23e09d0..c7db90112ef0 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -10586,6 +10586,149 @@ static struct bpf_test tests[] = { {}, { { 0, 2 } }, }, + /* Checking that ALU32 src is not zero extended in place */ +#define BPF_ALU32_SRC_ZEXT(op) \ + { \ + "ALU32_" #op "_X: src preserved in zext", \ + .u.insns_int = { \ + BPF_LD_IMM64(R1, 0x0123456789acbdefULL),\ + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL),\ + BPF_ALU64_REG(BPF_MOV, R0, R1), \ + BPF_ALU32_REG(BPF_##op, R2, R1), \ + BPF_ALU64_REG(BPF_SUB, R0, R1), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 0 } }, \ + } + BPF_ALU32_SRC_ZEXT(MOV), + BPF_ALU32_SRC_ZEXT(AND), + BPF_ALU32_SRC_ZEXT(OR), + BPF_ALU32_SRC_ZEXT(XOR), + BPF_ALU32_SRC_ZEXT(ADD), + BPF_ALU32_SRC_ZEXT(SUB), + BPF_ALU32_SRC_ZEXT(MUL), + BPF_ALU32_SRC_ZEXT(DIV), + BPF_ALU32_SRC_ZEXT(MOD), +#undef BPF_ALU32_SRC_ZEXT + /* Checking that ATOMIC32 src is not zero extended in place */ +#define BPF_ATOMIC32_SRC_ZEXT(op) \ + { \ + "ATOMIC_W_" #op ": src preserved in zext", \ + .u.insns_int = { \ + BPF_LD_IMM64(R0, 0x0123456789acbdefULL), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ST_MEM(BPF_W, R10, -4, 0), \ + BPF_ATOMIC_OP(BPF_W, BPF_##op, R10, R1, -4), \ + BPF_ALU64_REG(BPF_SUB, R0, R1), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 0 } }, \ + .stack_depth = 8, \ + } + BPF_ATOMIC32_SRC_ZEXT(ADD), + BPF_ATOMIC32_SRC_ZEXT(AND), + BPF_ATOMIC32_SRC_ZEXT(OR), + BPF_ATOMIC32_SRC_ZEXT(XOR), +#undef BPF_ATOMIC32_SRC_ZEXT + /* Checking that CMPXCHG32 src is not zero extended in place */ + { + "ATOMIC_W_CMPXCHG: src preserved in zext", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x0123456789acbdefULL), + BPF_ALU64_REG(BPF_MOV, R2, R1), + BPF_ALU64_REG(BPF_MOV, R0, 0), + BPF_ST_MEM(BPF_W, R10, -4, 0), + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R1, -4), + BPF_ALU64_REG(BPF_SUB, R1, R2), + BPF_ALU64_REG(BPF_MOV, R2, R1), + BPF_ALU64_IMM(BPF_RSH, R2, 32), + BPF_ALU64_REG(BPF_OR, R1, R2), + BPF_ALU64_REG(BPF_MOV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, + /* Checking that JMP32 immediate src is not zero extended in place */ +#define BPF_JMP32_IMM_ZEXT(op) \ + { \ + "JMP32_" #op "_K: operand preserved in zext", \ + .u.insns_int = { \ + BPF_LD_IMM64(R0, 0x0123456789acbdefULL),\ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_JMP32_IMM(BPF_##op, R0, 1234, 1), \ + BPF_JMP_A(0), /* Nop */ \ + BPF_ALU64_REG(BPF_SUB, R0, R1), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 0 } }, \ + } + BPF_JMP32_IMM_ZEXT(JEQ), + BPF_JMP32_IMM_ZEXT(JNE), + BPF_JMP32_IMM_ZEXT(JSET), + BPF_JMP32_IMM_ZEXT(JGT), + BPF_JMP32_IMM_ZEXT(JGE), + BPF_JMP32_IMM_ZEXT(JLT), + BPF_JMP32_IMM_ZEXT(JLE), + BPF_JMP32_IMM_ZEXT(JSGT), + BPF_JMP32_IMM_ZEXT(JSGE), + BPF_JMP32_IMM_ZEXT(JSGT), + BPF_JMP32_IMM_ZEXT(JSLT), + BPF_JMP32_IMM_ZEXT(JSLE), +#undef BPF_JMP2_IMM_ZEXT + /* Checking that JMP32 dst & src are not zero extended in place */ +#define BPF_JMP32_REG_ZEXT(op) \ + { \ + "JMP32_" #op "_X: operands preserved in zext", \ + .u.insns_int = { \ + BPF_LD_IMM64(R0, 0x0123456789acbdefULL),\ + BPF_LD_IMM64(R1, 0xfedcba9876543210ULL),\ + BPF_ALU64_REG(BPF_MOV, R2, R0), \ + BPF_ALU64_REG(BPF_MOV, R3, R1), \ + BPF_JMP32_IMM(BPF_##op, R0, R1, 1), \ + BPF_JMP_A(0), /* Nop */ \ + BPF_ALU64_REG(BPF_SUB, R0, R2), \ + BPF_ALU64_REG(BPF_SUB, R1, R3), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ + BPF_ALU64_REG(BPF_MOV, R1, R0), \ + BPF_ALU64_IMM(BPF_RSH, R1, 32), \ + BPF_ALU64_REG(BPF_OR, R0, R1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 0 } }, \ + } + BPF_JMP32_REG_ZEXT(JEQ), + BPF_JMP32_REG_ZEXT(JNE), + BPF_JMP32_REG_ZEXT(JSET), + BPF_JMP32_REG_ZEXT(JGT), + BPF_JMP32_REG_ZEXT(JGE), + BPF_JMP32_REG_ZEXT(JLT), + BPF_JMP32_REG_ZEXT(JLE), + BPF_JMP32_REG_ZEXT(JSGT), + BPF_JMP32_REG_ZEXT(JSGE), + BPF_JMP32_REG_ZEXT(JSGT), + BPF_JMP32_REG_ZEXT(JSLT), + BPF_JMP32_REG_ZEXT(JSLE), +#undef BPF_JMP2_REG_ZEXT /* Exhaustive test of ALU64 shift operations */ { "ALU64_LSH_K: all shift values", From e2f9797b3c7396065ca3bc9f223225ca63c1e2bd Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:43 +0200 Subject: [PATCH 78/85] bpf/tests: Add more tests for ALU and ATOMIC register clobbering This patch expands the register-clobbering-during-function-call tests to cover more all ALU32/64 MUL, DIV and MOD operations and all ATOMIC operations. In short, if a JIT implements a complex operation with a call to an external function, it must make sure to save and restore all its caller-saved registers that may be clobbered by the call. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-6-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 267 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 197 insertions(+), 70 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index c7db90112ef0..201f34060eef 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -3744,76 +3744,6 @@ static struct bpf_test tests[] = { { }, { { 0, -1 } } }, - { - /* - * Register (non-)clobbering test, in the case where a 32-bit - * JIT implements complex ALU64 operations via function calls. - * If so, the function call must be invisible in the eBPF - * registers. The JIT must then save and restore relevant - * registers during the call. The following tests check that - * the eBPF registers retain their values after such a call. - */ - "INT: Register clobbering, R1 updated", - .u.insns_int = { - BPF_ALU32_IMM(BPF_MOV, R0, 0), - BPF_ALU32_IMM(BPF_MOV, R1, 123456789), - BPF_ALU32_IMM(BPF_MOV, R2, 2), - BPF_ALU32_IMM(BPF_MOV, R3, 3), - BPF_ALU32_IMM(BPF_MOV, R4, 4), - BPF_ALU32_IMM(BPF_MOV, R5, 5), - BPF_ALU32_IMM(BPF_MOV, R6, 6), - BPF_ALU32_IMM(BPF_MOV, R7, 7), - BPF_ALU32_IMM(BPF_MOV, R8, 8), - BPF_ALU32_IMM(BPF_MOV, R9, 9), - BPF_ALU64_IMM(BPF_DIV, R1, 123456789), - BPF_JMP_IMM(BPF_JNE, R0, 0, 10), - BPF_JMP_IMM(BPF_JNE, R1, 1, 9), - BPF_JMP_IMM(BPF_JNE, R2, 2, 8), - BPF_JMP_IMM(BPF_JNE, R3, 3, 7), - BPF_JMP_IMM(BPF_JNE, R4, 4, 6), - BPF_JMP_IMM(BPF_JNE, R5, 5, 5), - BPF_JMP_IMM(BPF_JNE, R6, 6, 4), - BPF_JMP_IMM(BPF_JNE, R7, 7, 3), - BPF_JMP_IMM(BPF_JNE, R8, 8, 2), - BPF_JMP_IMM(BPF_JNE, R9, 9, 1), - BPF_ALU32_IMM(BPF_MOV, R0, 1), - BPF_EXIT_INSN(), - }, - INTERNAL, - { }, - { { 0, 1 } } - }, - { - "INT: Register clobbering, R2 updated", - .u.insns_int = { - BPF_ALU32_IMM(BPF_MOV, R0, 0), - BPF_ALU32_IMM(BPF_MOV, R1, 1), - BPF_ALU32_IMM(BPF_MOV, R2, 2 * 123456789), - BPF_ALU32_IMM(BPF_MOV, R3, 3), - BPF_ALU32_IMM(BPF_MOV, R4, 4), - BPF_ALU32_IMM(BPF_MOV, R5, 5), - BPF_ALU32_IMM(BPF_MOV, R6, 6), - BPF_ALU32_IMM(BPF_MOV, R7, 7), - BPF_ALU32_IMM(BPF_MOV, R8, 8), - BPF_ALU32_IMM(BPF_MOV, R9, 9), - BPF_ALU64_IMM(BPF_DIV, R2, 123456789), - BPF_JMP_IMM(BPF_JNE, R0, 0, 10), - BPF_JMP_IMM(BPF_JNE, R1, 1, 9), - BPF_JMP_IMM(BPF_JNE, R2, 2, 8), - BPF_JMP_IMM(BPF_JNE, R3, 3, 7), - BPF_JMP_IMM(BPF_JNE, R4, 4, 6), - BPF_JMP_IMM(BPF_JNE, R5, 5, 5), - BPF_JMP_IMM(BPF_JNE, R6, 6, 4), - BPF_JMP_IMM(BPF_JNE, R7, 7, 3), - BPF_JMP_IMM(BPF_JNE, R8, 8, 2), - BPF_JMP_IMM(BPF_JNE, R9, 9, 1), - BPF_ALU32_IMM(BPF_MOV, R0, 1), - BPF_EXIT_INSN(), - }, - INTERNAL, - { }, - { { 0, 1 } } - }, { /* * Test 32-bit JITs that implement complex ALU64 operations as @@ -10586,6 +10516,203 @@ static struct bpf_test tests[] = { {}, { { 0, 2 } }, }, + /* + * Register (non-)clobbering tests for the case where a JIT implements + * complex ALU or ATOMIC operations via function calls. If so, the + * function call must be transparent to the eBPF registers. The JIT + * must therefore save and restore relevant registers across the call. + * The following tests check that the eBPF registers retain their + * values after such an operation. Mainly intended for complex ALU + * and atomic operation, but we run it for all. You never know... + * + * Note that each operations should be tested twice with different + * destinations, to check preservation for all registers. + */ +#define BPF_TEST_CLOBBER_ALU(alu, op, dst, src) \ + { \ + #alu "_" #op " to " #dst ": no clobbering", \ + .u.insns_int = { \ + BPF_ALU64_IMM(BPF_MOV, R0, R0), \ + BPF_ALU64_IMM(BPF_MOV, R1, R1), \ + BPF_ALU64_IMM(BPF_MOV, R2, R2), \ + BPF_ALU64_IMM(BPF_MOV, R3, R3), \ + BPF_ALU64_IMM(BPF_MOV, R4, R4), \ + BPF_ALU64_IMM(BPF_MOV, R5, R5), \ + BPF_ALU64_IMM(BPF_MOV, R6, R6), \ + BPF_ALU64_IMM(BPF_MOV, R7, R7), \ + BPF_ALU64_IMM(BPF_MOV, R8, R8), \ + BPF_ALU64_IMM(BPF_MOV, R9, R9), \ + BPF_##alu(BPF_ ##op, dst, src), \ + BPF_ALU32_IMM(BPF_MOV, dst, dst), \ + BPF_JMP_IMM(BPF_JNE, R0, R0, 10), \ + BPF_JMP_IMM(BPF_JNE, R1, R1, 9), \ + BPF_JMP_IMM(BPF_JNE, R2, R2, 8), \ + BPF_JMP_IMM(BPF_JNE, R3, R3, 7), \ + BPF_JMP_IMM(BPF_JNE, R4, R4, 6), \ + BPF_JMP_IMM(BPF_JNE, R5, R5, 5), \ + BPF_JMP_IMM(BPF_JNE, R6, R6, 4), \ + BPF_JMP_IMM(BPF_JNE, R7, R7, 3), \ + BPF_JMP_IMM(BPF_JNE, R8, R8, 2), \ + BPF_JMP_IMM(BPF_JNE, R9, R9, 1), \ + BPF_ALU64_IMM(BPF_MOV, R0, 1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 1 } } \ + } + /* ALU64 operations, register clobbering */ + BPF_TEST_CLOBBER_ALU(ALU64_IMM, AND, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, AND, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, OR, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, OR, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, XOR, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, XOR, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, LSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, LSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, RSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, RSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, ARSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, ARSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, ADD, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, ADD, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, SUB, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, SUB, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, MUL, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, MUL, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, DIV, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, DIV, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, MOD, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU64_IMM, MOD, R9, 123456789), + /* ALU32 immediate operations, register clobbering */ + BPF_TEST_CLOBBER_ALU(ALU32_IMM, AND, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, AND, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, OR, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, OR, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, XOR, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, XOR, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, LSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, LSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, RSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, RSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, ARSH, R8, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, ARSH, R9, 12), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, ADD, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, ADD, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, SUB, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, SUB, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, MUL, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, MUL, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, DIV, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, DIV, R9, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, MOD, R8, 123456789), + BPF_TEST_CLOBBER_ALU(ALU32_IMM, MOD, R9, 123456789), + /* ALU64 register operations, register clobbering */ + BPF_TEST_CLOBBER_ALU(ALU64_REG, AND, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, AND, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, OR, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, OR, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, XOR, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, XOR, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, LSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, LSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, RSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, RSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, ARSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, ARSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, ADD, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, ADD, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, SUB, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, SUB, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, MUL, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, MUL, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, DIV, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, DIV, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, MOD, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU64_REG, MOD, R9, R1), + /* ALU32 register operations, register clobbering */ + BPF_TEST_CLOBBER_ALU(ALU32_REG, AND, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, AND, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, OR, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, OR, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, XOR, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, XOR, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, LSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, LSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, RSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, RSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, ARSH, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, ARSH, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, ADD, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, ADD, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, SUB, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, SUB, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, MUL, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, MUL, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, DIV, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, DIV, R9, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, MOD, R8, R1), + BPF_TEST_CLOBBER_ALU(ALU32_REG, MOD, R9, R1), +#undef BPF_TEST_CLOBBER_ALU +#define BPF_TEST_CLOBBER_ATOMIC(width, op) \ + { \ + "Atomic_" #width " " #op ": no clobbering", \ + .u.insns_int = { \ + BPF_ALU64_IMM(BPF_MOV, R0, 0), \ + BPF_ALU64_IMM(BPF_MOV, R1, 1), \ + BPF_ALU64_IMM(BPF_MOV, R2, 2), \ + BPF_ALU64_IMM(BPF_MOV, R3, 3), \ + BPF_ALU64_IMM(BPF_MOV, R4, 4), \ + BPF_ALU64_IMM(BPF_MOV, R5, 5), \ + BPF_ALU64_IMM(BPF_MOV, R6, 6), \ + BPF_ALU64_IMM(BPF_MOV, R7, 7), \ + BPF_ALU64_IMM(BPF_MOV, R8, 8), \ + BPF_ALU64_IMM(BPF_MOV, R9, 9), \ + BPF_ST_MEM(width, R10, -8, \ + (op) == BPF_CMPXCHG ? 0 : \ + (op) & BPF_FETCH ? 1 : 0), \ + BPF_ATOMIC_OP(width, op, R10, R1, -8), \ + BPF_JMP_IMM(BPF_JNE, R0, 0, 10), \ + BPF_JMP_IMM(BPF_JNE, R1, 1, 9), \ + BPF_JMP_IMM(BPF_JNE, R2, 2, 8), \ + BPF_JMP_IMM(BPF_JNE, R3, 3, 7), \ + BPF_JMP_IMM(BPF_JNE, R4, 4, 6), \ + BPF_JMP_IMM(BPF_JNE, R5, 5, 5), \ + BPF_JMP_IMM(BPF_JNE, R6, 6, 4), \ + BPF_JMP_IMM(BPF_JNE, R7, 7, 3), \ + BPF_JMP_IMM(BPF_JNE, R8, 8, 2), \ + BPF_JMP_IMM(BPF_JNE, R9, 9, 1), \ + BPF_ALU64_IMM(BPF_MOV, R0, 1), \ + BPF_EXIT_INSN(), \ + }, \ + INTERNAL, \ + { }, \ + { { 0, 1 } }, \ + .stack_depth = 8, \ + } + /* 64-bit atomic operations, register clobbering */ + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_ADD), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_AND), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_OR), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_XOR), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_ADD | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_AND | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_OR | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_XOR | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_XCHG), + BPF_TEST_CLOBBER_ATOMIC(BPF_DW, BPF_CMPXCHG), + /* 32-bit atomic operations, register clobbering */ + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_ADD), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_AND), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_OR), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_XOR), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_ADD | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_AND | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_OR | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_XOR | BPF_FETCH), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_XCHG), + BPF_TEST_CLOBBER_ATOMIC(BPF_W, BPF_CMPXCHG), +#undef BPF_TEST_CLOBBER_ATOMIC /* Checking that ALU32 src is not zero extended in place */ #define BPF_ALU32_SRC_ZEXT(op) \ { \ From e42fc3c2c40e0fb9d371c146dc8c0a70bee88a3c Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:44 +0200 Subject: [PATCH 79/85] bpf/tests: Minor restructuring of ALU tests This patch moves the ALU LSH/RSH/ARSH reference computations into the common reference value function. Also fix typo in constants so they now have the intended values. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-7-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 137 +++++++++++++++++++++++-------------------------- 1 file changed, 65 insertions(+), 72 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 201f34060eef..919323a3b69f 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -538,6 +538,57 @@ static int bpf_fill_max_jmp_never_taken(struct bpf_test *self) return __bpf_fill_max_jmp(self, BPF_JLT, 0); } +/* ALU result computation used in tests */ +static bool __bpf_alu_result(u64 *res, u64 v1, u64 v2, u8 op) +{ + *res = 0; + switch (op) { + case BPF_MOV: + *res = v2; + break; + case BPF_AND: + *res = v1 & v2; + break; + case BPF_OR: + *res = v1 | v2; + break; + case BPF_XOR: + *res = v1 ^ v2; + break; + case BPF_LSH: + *res = v1 << v2; + break; + case BPF_RSH: + *res = v1 >> v2; + break; + case BPF_ARSH: + *res = v1 >> v2; + if (v2 > 0 && v1 > S64_MAX) + *res |= ~0ULL << (64 - v2); + break; + case BPF_ADD: + *res = v1 + v2; + break; + case BPF_SUB: + *res = v1 - v2; + break; + case BPF_MUL: + *res = v1 * v2; + break; + case BPF_DIV: + if (v2 == 0) + return false; + *res = div64_u64(v1, v2); + break; + case BPF_MOD: + if (v2 == 0) + return false; + div64_u64_rem(v1, v2, res); + break; + } + return true; +} + /* Test an ALU shift operation for all valid shift values */ static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op, u8 mode, bool alu32) @@ -576,37 +627,19 @@ static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op, insn[i++] = BPF_ALU32_IMM(op, R1, imm); else insn[i++] = BPF_ALU32_REG(op, R1, R2); - switch (op) { - case BPF_LSH: - val = (u32)reg << imm; - break; - case BPF_RSH: - val = (u32)reg >> imm; - break; - case BPF_ARSH: - val = (u32)reg >> imm; - if (imm > 0 && (reg & 0x80000000)) - val |= ~(u32)0 << (32 - imm); - break; - } + + if (op == BPF_ARSH) + reg = (s32)reg; + else + reg = (u32)reg; + __bpf_alu_result(&val, reg, imm, op); + val = (u32)val; } else { if (mode == BPF_K) insn[i++] = BPF_ALU64_IMM(op, R1, imm); else insn[i++] = BPF_ALU64_REG(op, R1, R2); - switch (op) { - case BPF_LSH: - val = (u64)reg << imm; - break; - case BPF_RSH: - val = (u64)reg >> imm; - break; - case BPF_ARSH: - val = (u64)reg >> imm; - if (imm > 0 && reg < 0) - val |= ~(u64)0 << (64 - imm); - break; - } + __bpf_alu_result(&val, reg, imm, op); } /* @@ -799,46 +832,6 @@ static int __bpf_fill_pattern(struct bpf_test *self, void *arg, * test is designed to verify e.g. the ALU and ALU64 operations for JITs that * emit different code depending on the magnitude of the immediate value. */ - -static bool __bpf_alu_result(u64 *res, u64 v1, u64 v2, u8 op) -{ - *res = 0; - switch (op) { - case BPF_MOV: - *res = v2; - break; - case BPF_AND: - *res = v1 & v2; - break; - case BPF_OR: - *res = v1 | v2; - break; - case BPF_XOR: - *res = v1 ^ v2; - break; - case BPF_ADD: - *res = v1 + v2; - break; - case BPF_SUB: - *res = v1 - v2; - break; - case BPF_MUL: - *res = v1 * v2; - break; - case BPF_DIV: - if (v2 == 0) - return false; - *res = div64_u64(v1, v2); - break; - case BPF_MOD: - if (v2 == 0) - return false; - div64_u64_rem(v1, v2, res); - break; - } - return true; -} - static int __bpf_emit_alu64_imm(struct bpf_test *self, void *arg, struct bpf_insn *insns, s64 dst, s64 imm) { @@ -7881,7 +7874,7 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test successful return", .u.insns_int = { BPF_LD_IMM64(R1, 0x0123456789abcdefULL), - BPF_LD_IMM64(R2, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL), BPF_ALU64_REG(BPF_MOV, R0, R1), BPF_STX_MEM(BPF_DW, R10, R1, -40), BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40), @@ -7898,7 +7891,7 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test successful store", .u.insns_int = { BPF_LD_IMM64(R1, 0x0123456789abcdefULL), - BPF_LD_IMM64(R2, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL), BPF_ALU64_REG(BPF_MOV, R0, R1), BPF_STX_MEM(BPF_DW, R10, R0, -40), BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40), @@ -7916,7 +7909,7 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test failure return", .u.insns_int = { BPF_LD_IMM64(R1, 0x0123456789abcdefULL), - BPF_LD_IMM64(R2, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL), BPF_ALU64_REG(BPF_MOV, R0, R1), BPF_ALU64_IMM(BPF_ADD, R0, 1), BPF_STX_MEM(BPF_DW, R10, R1, -40), @@ -7934,7 +7927,7 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test failure store", .u.insns_int = { BPF_LD_IMM64(R1, 0x0123456789abcdefULL), - BPF_LD_IMM64(R2, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL), BPF_ALU64_REG(BPF_MOV, R0, R1), BPF_ALU64_IMM(BPF_ADD, R0, 1), BPF_STX_MEM(BPF_DW, R10, R1, -40), @@ -7953,11 +7946,11 @@ static struct bpf_test tests[] = { "BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test side effects", .u.insns_int = { BPF_LD_IMM64(R1, 0x0123456789abcdefULL), - BPF_LD_IMM64(R2, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R2, 0xfedcba9876543210ULL), BPF_ALU64_REG(BPF_MOV, R0, R1), BPF_STX_MEM(BPF_DW, R10, R1, -40), BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40), - BPF_LD_IMM64(R0, 0xfecdba9876543210ULL), + BPF_LD_IMM64(R0, 0xfedcba9876543210ULL), BPF_JMP_REG(BPF_JNE, R0, R2, 1), BPF_ALU64_REG(BPF_SUB, R0, R2), BPF_EXIT_INSN(), From daed6083f4fbcbb57da26d80f15365219ae793de Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:45 +0200 Subject: [PATCH 80/85] bpf/tests: Add exhaustive tests of ALU register combinations This patch replaces the current register combination test with new exhaustive tests. Before, only a subset of register combinations was tested for ALU64 DIV. Now, all combinatons of operand registers are tested, including the case when they are the same, and for all ALU32 and ALU64 operations. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-8-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 834 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 763 insertions(+), 71 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 919323a3b69f..924bf4c9783c 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1130,6 +1130,381 @@ static int bpf_fill_alu32_mod_reg(struct bpf_test *self) return __bpf_fill_alu32_reg(self, BPF_MOD); } +/* + * Test JITs that implement complex ALU operations as function + * calls, and must re-arrange operands for argument passing. + */ +static int __bpf_fill_alu_imm_regs(struct bpf_test *self, u8 op, bool alu32) +{ + int len = 2 + 10 * 10; + struct bpf_insn *insns; + u64 dst, res; + int i = 0; + u32 imm; + int rd; + + insns = kmalloc_array(len, sizeof(*insns), GFP_KERNEL); + if (!insns) + return -ENOMEM; + + /* Operand and result values according to operation */ + if (alu32) + dst = 0x76543210U; + else + dst = 0x7edcba9876543210ULL; + imm = 0x01234567U; + + if (op == BPF_LSH || op == BPF_RSH || op == BPF_ARSH) + imm &= 31; + + __bpf_alu_result(&res, dst, imm, op); + + if (alu32) + res = (u32)res; + + /* Check all operand registers */ + for (rd = R0; rd <= R9; rd++) { + i += __bpf_ld_imm64(&insns[i], rd, dst); + + if (alu32) + insns[i++] = BPF_ALU32_IMM(op, rd, imm); + else + insns[i++] = BPF_ALU64_IMM(op, rd, imm); + + insns[i++] = BPF_JMP32_IMM(BPF_JEQ, rd, res, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_ALU64_IMM(BPF_RSH, rd, 32); + insns[i++] = BPF_JMP32_IMM(BPF_JEQ, rd, res >> 32, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + } + + insns[i++] = BPF_MOV64_IMM(R0, 1); + insns[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insns; + self->u.ptr.len = len; + BUG_ON(i != len); + + return 0; +} + +/* ALU64 K registers */ +static int bpf_fill_alu64_mov_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MOV, false); +} + +static int bpf_fill_alu64_and_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_AND, false); +} + +static int bpf_fill_alu64_or_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_OR, false); +} + +static int bpf_fill_alu64_xor_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_XOR, false); +} + +static int bpf_fill_alu64_lsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_LSH, false); +} + +static int bpf_fill_alu64_rsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_RSH, false); +} + +static int bpf_fill_alu64_arsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_ARSH, false); +} + +static int bpf_fill_alu64_add_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_ADD, false); +} + +static int bpf_fill_alu64_sub_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_SUB, false); +} + +static int bpf_fill_alu64_mul_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MUL, false); +} + +static int bpf_fill_alu64_div_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_DIV, false); +} + +static int bpf_fill_alu64_mod_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MOD, false); +} + +/* ALU32 K registers */ +static int bpf_fill_alu32_mov_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MOV, true); +} + +static int bpf_fill_alu32_and_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_AND, true); +} + +static int bpf_fill_alu32_or_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_OR, true); +} + +static int bpf_fill_alu32_xor_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_XOR, true); +} + +static int bpf_fill_alu32_lsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_LSH, true); +} + +static int bpf_fill_alu32_rsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_RSH, true); +} + +static int bpf_fill_alu32_arsh_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_ARSH, true); +} + +static int bpf_fill_alu32_add_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_ADD, true); +} + +static int bpf_fill_alu32_sub_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_SUB, true); +} + +static int bpf_fill_alu32_mul_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MUL, true); +} + +static int bpf_fill_alu32_div_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_DIV, true); +} + +static int bpf_fill_alu32_mod_imm_regs(struct bpf_test *self) +{ + return __bpf_fill_alu_imm_regs(self, BPF_MOD, true); +} + +/* + * Test JITs that implement complex ALU operations as function + * calls, and must re-arrange operands for argument passing. + */ +static int __bpf_fill_alu_reg_pairs(struct bpf_test *self, u8 op, bool alu32) +{ + int len = 2 + 10 * 10 * 12; + u64 dst, src, res, same; + struct bpf_insn *insns; + int rd, rs; + int i = 0; + + insns = kmalloc_array(len, sizeof(*insns), GFP_KERNEL); + if (!insns) + return -ENOMEM; + + /* Operand and result values according to operation */ + if (alu32) { + dst = 0x76543210U; + src = 0x01234567U; + } else { + dst = 0x7edcba9876543210ULL; + src = 0x0123456789abcdefULL; + } + + if (op == BPF_LSH || op == BPF_RSH || op == BPF_ARSH) + src &= 31; + + __bpf_alu_result(&res, dst, src, op); + __bpf_alu_result(&same, src, src, op); + + if (alu32) { + res = (u32)res; + same = (u32)same; + } + + /* Check all combinations of operand registers */ + for (rd = R0; rd <= R9; rd++) { + for (rs = R0; rs <= R9; rs++) { + u64 val = rd == rs ? same : res; + + i += __bpf_ld_imm64(&insns[i], rd, dst); + i += __bpf_ld_imm64(&insns[i], rs, src); + + if (alu32) + insns[i++] = BPF_ALU32_REG(op, rd, rs); + else + insns[i++] = BPF_ALU64_REG(op, rd, rs); + + insns[i++] = BPF_JMP32_IMM(BPF_JEQ, rd, val, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + + insns[i++] = BPF_ALU64_IMM(BPF_RSH, rd, 32); + insns[i++] = BPF_JMP32_IMM(BPF_JEQ, rd, val >> 32, 2); + insns[i++] = BPF_MOV64_IMM(R0, __LINE__); + insns[i++] = BPF_EXIT_INSN(); + } + } + + insns[i++] = BPF_MOV64_IMM(R0, 1); + insns[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insns; + self->u.ptr.len = len; + BUG_ON(i != len); + + return 0; +} + +/* ALU64 X register combinations */ +static int bpf_fill_alu64_mov_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MOV, false); +} + +static int bpf_fill_alu64_and_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_AND, false); +} + +static int bpf_fill_alu64_or_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_OR, false); +} + +static int bpf_fill_alu64_xor_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_XOR, false); +} + +static int bpf_fill_alu64_lsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_LSH, false); +} + +static int bpf_fill_alu64_rsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_RSH, false); +} + +static int bpf_fill_alu64_arsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_ARSH, false); +} + +static int bpf_fill_alu64_add_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_ADD, false); +} + +static int bpf_fill_alu64_sub_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_SUB, false); +} + +static int bpf_fill_alu64_mul_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MUL, false); +} + +static int bpf_fill_alu64_div_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_DIV, false); +} + +static int bpf_fill_alu64_mod_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MOD, false); +} + +/* ALU32 X register combinations */ +static int bpf_fill_alu32_mov_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MOV, true); +} + +static int bpf_fill_alu32_and_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_AND, true); +} + +static int bpf_fill_alu32_or_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_OR, true); +} + +static int bpf_fill_alu32_xor_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_XOR, true); +} + +static int bpf_fill_alu32_lsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_LSH, true); +} + +static int bpf_fill_alu32_rsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_RSH, true); +} + +static int bpf_fill_alu32_arsh_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_ARSH, true); +} + +static int bpf_fill_alu32_add_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_ADD, true); +} + +static int bpf_fill_alu32_sub_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_SUB, true); +} + +static int bpf_fill_alu32_mul_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MUL, true); +} + +static int bpf_fill_alu32_div_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_DIV, true); +} + +static int bpf_fill_alu32_mod_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_alu_reg_pairs(self, BPF_MOD, true); +} + /* * Exhaustive tests of atomic operations for all power-of-two operand * magnitudes, both for positive and negative values. @@ -3737,77 +4112,6 @@ static struct bpf_test tests[] = { { }, { { 0, -1 } } }, - { - /* - * Test 32-bit JITs that implement complex ALU64 operations as - * function calls R0 = f(R1, R2), and must re-arrange operands. - */ -#define NUMER 0xfedcba9876543210ULL -#define DENOM 0x0123456789abcdefULL - "ALU64_DIV X: Operand register permutations", - .u.insns_int = { - /* R0 / R2 */ - BPF_LD_IMM64(R0, NUMER), - BPF_LD_IMM64(R2, DENOM), - BPF_ALU64_REG(BPF_DIV, R0, R2), - BPF_JMP_IMM(BPF_JEQ, R0, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R1 / R0 */ - BPF_LD_IMM64(R1, NUMER), - BPF_LD_IMM64(R0, DENOM), - BPF_ALU64_REG(BPF_DIV, R1, R0), - BPF_JMP_IMM(BPF_JEQ, R1, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R0 / R1 */ - BPF_LD_IMM64(R0, NUMER), - BPF_LD_IMM64(R1, DENOM), - BPF_ALU64_REG(BPF_DIV, R0, R1), - BPF_JMP_IMM(BPF_JEQ, R0, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R2 / R0 */ - BPF_LD_IMM64(R2, NUMER), - BPF_LD_IMM64(R0, DENOM), - BPF_ALU64_REG(BPF_DIV, R2, R0), - BPF_JMP_IMM(BPF_JEQ, R2, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R2 / R1 */ - BPF_LD_IMM64(R2, NUMER), - BPF_LD_IMM64(R1, DENOM), - BPF_ALU64_REG(BPF_DIV, R2, R1), - BPF_JMP_IMM(BPF_JEQ, R2, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R1 / R2 */ - BPF_LD_IMM64(R1, NUMER), - BPF_LD_IMM64(R2, DENOM), - BPF_ALU64_REG(BPF_DIV, R1, R2), - BPF_JMP_IMM(BPF_JEQ, R1, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* R1 / R1 */ - BPF_LD_IMM64(R1, NUMER), - BPF_ALU64_REG(BPF_DIV, R1, R1), - BPF_JMP_IMM(BPF_JEQ, R1, 1, 1), - BPF_EXIT_INSN(), - /* R2 / R2 */ - BPF_LD_IMM64(R2, DENOM), - BPF_ALU64_REG(BPF_DIV, R2, R2), - BPF_JMP_IMM(BPF_JEQ, R2, 1, 1), - BPF_EXIT_INSN(), - /* R3 / R4 */ - BPF_LD_IMM64(R3, NUMER), - BPF_LD_IMM64(R4, DENOM), - BPF_ALU64_REG(BPF_DIV, R3, R4), - BPF_JMP_IMM(BPF_JEQ, R3, NUMER / DENOM, 1), - BPF_EXIT_INSN(), - /* Successful return */ - BPF_LD_IMM64(R0, 1), - BPF_EXIT_INSN(), - }, - INTERNAL, - { }, - { { 0, 1 } }, -#undef NUMER -#undef DENOM - }, #ifdef CONFIG_32BIT { "INT: 32-bit context pointer word order and zero-extension", @@ -10849,6 +11153,394 @@ static struct bpf_test tests[] = { BPF_JMP32_REG_ZEXT(JSLT), BPF_JMP32_REG_ZEXT(JSLE), #undef BPF_JMP2_REG_ZEXT + /* ALU64 K register combinations */ + { + "ALU64_MOV_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mov_imm_regs, + }, + { + "ALU64_AND_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_and_imm_regs, + }, + { + "ALU64_OR_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_or_imm_regs, + }, + { + "ALU64_XOR_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_xor_imm_regs, + }, + { + "ALU64_LSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_lsh_imm_regs, + }, + { + "ALU64_RSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_rsh_imm_regs, + }, + { + "ALU64_ARSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_arsh_imm_regs, + }, + { + "ALU64_ADD_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_add_imm_regs, + }, + { + "ALU64_SUB_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_sub_imm_regs, + }, + { + "ALU64_MUL_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mul_imm_regs, + }, + { + "ALU64_DIV_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_div_imm_regs, + }, + { + "ALU64_MOD_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mod_imm_regs, + }, + /* ALU32 K registers */ + { + "ALU32_MOV_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mov_imm_regs, + }, + { + "ALU32_AND_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_and_imm_regs, + }, + { + "ALU32_OR_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_or_imm_regs, + }, + { + "ALU32_XOR_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_xor_imm_regs, + }, + { + "ALU32_LSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_lsh_imm_regs, + }, + { + "ALU32_RSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_rsh_imm_regs, + }, + { + "ALU32_ARSH_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_arsh_imm_regs, + }, + { + "ALU32_ADD_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_add_imm_regs, + }, + { + "ALU32_SUB_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_sub_imm_regs, + }, + { + "ALU32_MUL_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mul_imm_regs, + }, + { + "ALU32_DIV_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_div_imm_regs, + }, + { + "ALU32_MOD_K: registers", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mod_imm_regs, + }, + /* ALU64 X register combinations */ + { + "ALU64_MOV_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mov_reg_pairs, + }, + { + "ALU64_AND_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_and_reg_pairs, + }, + { + "ALU64_OR_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_or_reg_pairs, + }, + { + "ALU64_XOR_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_xor_reg_pairs, + }, + { + "ALU64_LSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_lsh_reg_pairs, + }, + { + "ALU64_RSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_rsh_reg_pairs, + }, + { + "ALU64_ARSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_arsh_reg_pairs, + }, + { + "ALU64_ADD_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_add_reg_pairs, + }, + { + "ALU64_SUB_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_sub_reg_pairs, + }, + { + "ALU64_MUL_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mul_reg_pairs, + }, + { + "ALU64_DIV_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_div_reg_pairs, + }, + { + "ALU64_MOD_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_mod_reg_pairs, + }, + /* ALU32 X register combinations */ + { + "ALU32_MOV_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mov_reg_pairs, + }, + { + "ALU32_AND_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_and_reg_pairs, + }, + { + "ALU32_OR_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_or_reg_pairs, + }, + { + "ALU32_XOR_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_xor_reg_pairs, + }, + { + "ALU32_LSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_lsh_reg_pairs, + }, + { + "ALU32_RSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_rsh_reg_pairs, + }, + { + "ALU32_ARSH_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_arsh_reg_pairs, + }, + { + "ALU32_ADD_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_add_reg_pairs, + }, + { + "ALU32_SUB_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_sub_reg_pairs, + }, + { + "ALU32_MUL_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mul_reg_pairs, + }, + { + "ALU32_DIV_X: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_div_reg_pairs, + }, + { + "ALU32_MOD_X register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_mod_reg_pairs, + }, /* Exhaustive test of ALU64 shift operations */ { "ALU64_LSH_K: all shift values", From 6fae2e8a1d9ee09e25aee6514b7544e059a8ee68 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:46 +0200 Subject: [PATCH 81/85] bpf/tests: Add exhaustive tests of BPF_ATOMIC register combinations This patch adds tests of all register combinations for BPF_ATOMIC operations on both BPF_W and BPF_DW sizes. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-9-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 422 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 422 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 924bf4c9783c..40db4cee4f51 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1805,6 +1805,246 @@ static int bpf_fill_cmpxchg32(struct bpf_test *self) &__bpf_emit_cmpxchg32); } +/* + * Test JITs that implement ATOMIC operations as function calls or + * other primitives, and must re-arrange operands for argument passing. + */ +static int __bpf_fill_atomic_reg_pairs(struct bpf_test *self, u8 width, u8 op) +{ + struct bpf_insn *insn; + int len = 2 + 34 * 10 * 10; + u64 mem, upd, res; + int rd, rs, i = 0; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + /* Operand and memory values */ + if (width == BPF_DW) { + mem = 0x0123456789abcdefULL; + upd = 0xfedcba9876543210ULL; + } else { /* BPF_W */ + mem = 0x01234567U; + upd = 0x76543210U; + } + + /* Memory updated according to operation */ + switch (op) { + case BPF_XCHG: + res = upd; + break; + case BPF_CMPXCHG: + res = mem; + break; + default: + __bpf_alu_result(&res, mem, upd, BPF_OP(op)); + } + + /* Test all operand registers */ + for (rd = R0; rd <= R9; rd++) { + for (rs = R0; rs <= R9; rs++) { + u64 cmp, src; + + /* Initialize value in memory */ + i += __bpf_ld_imm64(&insn[i], R0, mem); + insn[i++] = BPF_STX_MEM(width, R10, R0, -8); + + /* Initialize registers in order */ + i += __bpf_ld_imm64(&insn[i], R0, ~mem); + i += __bpf_ld_imm64(&insn[i], rs, upd); + insn[i++] = BPF_MOV64_REG(rd, R10); + + /* Perform atomic operation */ + insn[i++] = BPF_ATOMIC_OP(width, op, rd, rs, -8); + if (op == BPF_CMPXCHG && width == BPF_W) + insn[i++] = BPF_ZEXT_REG(R0); + + /* Check R0 register value */ + if (op == BPF_CMPXCHG) + cmp = mem; /* Expect value from memory */ + else if (R0 == rd || R0 == rs) + cmp = 0; /* Aliased, checked below */ + else + cmp = ~mem; /* Expect value to be preserved */ + if (cmp) { + insn[i++] = BPF_JMP32_IMM(BPF_JEQ, R0, + (u32)cmp, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + insn[i++] = BPF_ALU64_IMM(BPF_RSH, R0, 32); + insn[i++] = BPF_JMP32_IMM(BPF_JEQ, R0, + cmp >> 32, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + } + + /* Check source register value */ + if (rs == R0 && op == BPF_CMPXCHG) + src = 0; /* Aliased with R0, checked above */ + else if (rs == rd && (op == BPF_CMPXCHG || + !(op & BPF_FETCH))) + src = 0; /* Aliased with rd, checked below */ + else if (op == BPF_CMPXCHG) + src = upd; /* Expect value to be preserved */ + else if (op & BPF_FETCH) + src = mem; /* Expect fetched value from mem */ + else /* no fetch */ + src = upd; /* Expect value to be preserved */ + if (src) { + insn[i++] = BPF_JMP32_IMM(BPF_JEQ, rs, + (u32)src, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + insn[i++] = BPF_ALU64_IMM(BPF_RSH, rs, 32); + insn[i++] = BPF_JMP32_IMM(BPF_JEQ, rs, + src >> 32, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + } + + /* Check destination register value */ + if (!(rd == R0 && op == BPF_CMPXCHG) && + !(rd == rs && (op & BPF_FETCH))) { + insn[i++] = BPF_JMP_REG(BPF_JEQ, rd, R10, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + } + + /* Check value in memory */ + if (rs != rd) { /* No aliasing */ + i += __bpf_ld_imm64(&insn[i], R1, res); + } else if (op == BPF_XCHG) { /* Aliased, XCHG */ + insn[i++] = BPF_MOV64_REG(R1, R10); + } else if (op == BPF_CMPXCHG) { /* Aliased, CMPXCHG */ + i += __bpf_ld_imm64(&insn[i], R1, mem); + } else { /* Aliased, ALU oper */ + i += __bpf_ld_imm64(&insn[i], R1, mem); + insn[i++] = BPF_ALU64_REG(BPF_OP(op), R1, R10); + } + + insn[i++] = BPF_LDX_MEM(width, R0, R10, -8); + if (width == BPF_DW) + insn[i++] = BPF_JMP_REG(BPF_JEQ, R0, R1, 2); + else /* width == BPF_W */ + insn[i++] = BPF_JMP32_REG(BPF_JEQ, R0, R1, 2); + insn[i++] = BPF_MOV32_IMM(R0, __LINE__); + insn[i++] = BPF_EXIT_INSN(); + } + } + + insn[i++] = BPF_MOV64_IMM(R0, 1); + insn[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = i; + BUG_ON(i > len); + + return 0; +} + +/* 64-bit atomic register tests */ +static int bpf_fill_atomic64_add_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_ADD); +} + +static int bpf_fill_atomic64_and_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_AND); +} + +static int bpf_fill_atomic64_or_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_OR); +} + +static int bpf_fill_atomic64_xor_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_XOR); +} + +static int bpf_fill_atomic64_add_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_ADD | BPF_FETCH); +} + +static int bpf_fill_atomic64_and_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_AND | BPF_FETCH); +} + +static int bpf_fill_atomic64_or_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_OR | BPF_FETCH); +} + +static int bpf_fill_atomic64_xor_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_XOR | BPF_FETCH); +} + +static int bpf_fill_atomic64_xchg_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_XCHG); +} + +static int bpf_fill_atomic64_cmpxchg_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_DW, BPF_CMPXCHG); +} + +/* 32-bit atomic register tests */ +static int bpf_fill_atomic32_add_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_ADD); +} + +static int bpf_fill_atomic32_and_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_AND); +} + +static int bpf_fill_atomic32_or_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_OR); +} + +static int bpf_fill_atomic32_xor_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_XOR); +} + +static int bpf_fill_atomic32_add_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_ADD | BPF_FETCH); +} + +static int bpf_fill_atomic32_and_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_AND | BPF_FETCH); +} + +static int bpf_fill_atomic32_or_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_OR | BPF_FETCH); +} + +static int bpf_fill_atomic32_xor_fetch_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_XOR | BPF_FETCH); +} + +static int bpf_fill_atomic32_xchg_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_XCHG); +} + +static int bpf_fill_atomic32_cmpxchg_reg_pairs(struct bpf_test *self) +{ + return __bpf_fill_atomic_reg_pairs(self, BPF_W, BPF_CMPXCHG); +} + /* * Test the two-instruction 64-bit immediate load operation for all * power-of-two magnitudes of the immediate operand. For each MSB, a block @@ -11976,6 +12216,188 @@ static struct bpf_test tests[] = { { { 0, 1 } }, .fill_helper = bpf_fill_ld_imm64, }, + /* 64-bit ATOMIC register combinations */ + { + "ATOMIC_DW_ADD: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_add_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_AND: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_and_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_OR: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_or_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_XOR: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xor_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_ADD_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_add_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_AND_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_and_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_OR_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_or_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_XOR_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xor_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_XCHG: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_xchg_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_DW_CMPXCHG: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic64_cmpxchg_reg_pairs, + .stack_depth = 8, + }, + /* 32-bit ATOMIC register combinations */ + { + "ATOMIC_W_ADD: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_add_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_AND: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_and_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_OR: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_or_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_XOR: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xor_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_ADD_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_add_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_AND_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_and_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_OR_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_or_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_XOR_FETCH: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xor_fetch_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_XCHG: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_xchg_reg_pairs, + .stack_depth = 8, + }, + { + "ATOMIC_W_CMPXCHG: register combinations", + { }, + INTERNAL, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_atomic32_cmpxchg_reg_pairs, + .stack_depth = 8, + }, /* 64-bit ATOMIC magnitudes */ { "ATOMIC_DW_ADD: all operand magnitudes", From 68813605dea69ca0af26af7dd00384c78c1df05d Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:47 +0200 Subject: [PATCH 82/85] bpf/tests: Add test of ALU shifts with operand register aliasing This patch adds a tests of ALU32 and ALU64 LSH/RSH/ARSH operations for the case when the two operands are the same register. Mainly intended to test JITs that implement ALU64 shifts with 32-bit CPU instructions. Also renamed related helper functions for consistency with the new tests. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-10-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 162 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 149 insertions(+), 13 deletions(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 40db4cee4f51..dfcbdff714b6 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -660,37 +660,37 @@ static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op, self->u.ptr.insns = insn; self->u.ptr.len = len; - BUG_ON(i > len); + BUG_ON(i != len); return 0; } -static int bpf_fill_alu_lsh_imm(struct bpf_test *self) +static int bpf_fill_alu64_lsh_imm(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_LSH, BPF_K, false); } -static int bpf_fill_alu_rsh_imm(struct bpf_test *self) +static int bpf_fill_alu64_rsh_imm(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_RSH, BPF_K, false); } -static int bpf_fill_alu_arsh_imm(struct bpf_test *self) +static int bpf_fill_alu64_arsh_imm(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_K, false); } -static int bpf_fill_alu_lsh_reg(struct bpf_test *self) +static int bpf_fill_alu64_lsh_reg(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_LSH, BPF_X, false); } -static int bpf_fill_alu_rsh_reg(struct bpf_test *self) +static int bpf_fill_alu64_rsh_reg(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_RSH, BPF_X, false); } -static int bpf_fill_alu_arsh_reg(struct bpf_test *self) +static int bpf_fill_alu64_arsh_reg(struct bpf_test *self) { return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_X, false); } @@ -725,6 +725,86 @@ static int bpf_fill_alu32_arsh_reg(struct bpf_test *self) return __bpf_fill_alu_shift(self, BPF_ARSH, BPF_X, true); } +/* + * Test an ALU register shift operation for all valid shift values + * for the case when the source and destination are the same. + */ +static int __bpf_fill_alu_shift_same_reg(struct bpf_test *self, u8 op, + bool alu32) +{ + int bits = alu32 ? 32 : 64; + int len = 3 + 6 * bits; + struct bpf_insn *insn; + int i = 0; + u64 val; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 0); + + for (val = 0; val < bits; val++) { + u64 res; + + /* Perform operation */ + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R1, val); + if (alu32) + insn[i++] = BPF_ALU32_REG(op, R1, R1); + else + insn[i++] = BPF_ALU64_REG(op, R1, R1); + + /* Compute the reference result */ + __bpf_alu_result(&res, val, val, op); + if (alu32) + res = (u32)res; + i += __bpf_ld_imm64(&insn[i], R2, res); + + /* Check the actual result */ + insn[i++] = BPF_JMP_REG(BPF_JEQ, R1, R2, 1); + insn[i++] = BPF_EXIT_INSN(); + } + + insn[i++] = BPF_ALU64_IMM(BPF_MOV, R0, 1); + insn[i++] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + BUG_ON(i != len); + + return 0; +} + +static int bpf_fill_alu64_lsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_LSH, false); +} + +static int bpf_fill_alu64_rsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_RSH, false); +} + +static int bpf_fill_alu64_arsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_ARSH, false); +} + +static int bpf_fill_alu32_lsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_LSH, true); +} + +static int bpf_fill_alu32_rsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_RSH, true); +} + +static int bpf_fill_alu32_arsh_same_reg(struct bpf_test *self) +{ + return __bpf_fill_alu_shift_same_reg(self, BPF_ARSH, true); +} + /* * Common operand pattern generator for exhaustive power-of-two magnitudes * tests. The block size parameters can be adjusted to increase/reduce the @@ -11788,7 +11868,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_lsh_imm, + .fill_helper = bpf_fill_alu64_lsh_imm, }, { "ALU64_RSH_K: all shift values", @@ -11796,7 +11876,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_rsh_imm, + .fill_helper = bpf_fill_alu64_rsh_imm, }, { "ALU64_ARSH_K: all shift values", @@ -11804,7 +11884,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_arsh_imm, + .fill_helper = bpf_fill_alu64_arsh_imm, }, { "ALU64_LSH_X: all shift values", @@ -11812,7 +11892,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_lsh_reg, + .fill_helper = bpf_fill_alu64_lsh_reg, }, { "ALU64_RSH_X: all shift values", @@ -11820,7 +11900,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_rsh_reg, + .fill_helper = bpf_fill_alu64_rsh_reg, }, { "ALU64_ARSH_X: all shift values", @@ -11828,7 +11908,7 @@ static struct bpf_test tests[] = { INTERNAL | FLAG_NO_DATA, { }, { { 0, 1 } }, - .fill_helper = bpf_fill_alu_arsh_reg, + .fill_helper = bpf_fill_alu64_arsh_reg, }, /* Exhaustive test of ALU32 shift operations */ { @@ -11879,6 +11959,62 @@ static struct bpf_test tests[] = { { { 0, 1 } }, .fill_helper = bpf_fill_alu32_arsh_reg, }, + /* + * Exhaustive test of ALU64 shift operations when + * source and destination register are the same. + */ + { + "ALU64_LSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_lsh_same_reg, + }, + { + "ALU64_RSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_rsh_same_reg, + }, + { + "ALU64_ARSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu64_arsh_same_reg, + }, + /* + * Exhaustive test of ALU32 shift operations when + * source and destination register are the same. + */ + { + "ALU32_LSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_lsh_same_reg, + }, + { + "ALU32_RSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_rsh_same_reg, + }, + { + "ALU32_ARSH_X: all shift values with the same register", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_alu32_arsh_same_reg, + }, /* ALU64 immediate magnitudes */ { "ALU64_MOV_K: all immediate value magnitudes", From 7bceeb95726b105bd4241c9635acc0836df675d4 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Fri, 1 Oct 2021 15:03:48 +0200 Subject: [PATCH 83/85] bpf/tests: Add test of LDX_MEM with operand aliasing This patch adds a set of tests of BPF_LDX_MEM where both operand registers are the same register. Mainly testing 32-bit JITs that may load a 64-bit value in two 32-bit loads, and must not overwrite the address register. Signed-off-by: Johan Almbladh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211001130348.3670534-11-johan.almbladh@anyfinetworks.com --- lib/test_bpf.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index dfcbdff714b6..b9fc330fc83b 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -11133,6 +11133,64 @@ static struct bpf_test tests[] = { {}, { { 0, 2 } }, }, + /* BPF_LDX_MEM with operand aliasing */ + { + "LDX_MEM_B: operand register aliasing", + .u.insns_int = { + BPF_ST_MEM(BPF_B, R10, -8, 123), + BPF_MOV64_REG(R0, R10), + BPF_LDX_MEM(BPF_B, R0, R0, -8), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 123 } }, + .stack_depth = 8, + }, + { + "LDX_MEM_H: operand register aliasing", + .u.insns_int = { + BPF_ST_MEM(BPF_H, R10, -8, 12345), + BPF_MOV64_REG(R0, R10), + BPF_LDX_MEM(BPF_H, R0, R0, -8), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 12345 } }, + .stack_depth = 8, + }, + { + "LDX_MEM_W: operand register aliasing", + .u.insns_int = { + BPF_ST_MEM(BPF_W, R10, -8, 123456789), + BPF_MOV64_REG(R0, R10), + BPF_LDX_MEM(BPF_W, R0, R0, -8), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 123456789 } }, + .stack_depth = 8, + }, + { + "LDX_MEM_DW: operand register aliasing", + .u.insns_int = { + BPF_LD_IMM64(R1, 0x123456789abcdefULL), + BPF_STX_MEM(BPF_DW, R10, R1, -8), + BPF_MOV64_REG(R0, R10), + BPF_LDX_MEM(BPF_DW, R0, R0, -8), + BPF_ALU64_REG(BPF_SUB, R0, R1), + BPF_MOV64_REG(R1, R0), + BPF_ALU64_IMM(BPF_RSH, R1, 32), + BPF_ALU64_REG(BPF_OR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + .stack_depth = 8, + }, /* * Register (non-)clobbering tests for the case where a JIT implements * complex ALU or ATOMIC operations via function calls. If so, the From f731052325efc3726577feb743c7495f880ae07d Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Fri, 1 Oct 2021 00:14:55 +0800 Subject: [PATCH 84/85] libbpf: Support uniform BTF-defined key/value specification across all BPF maps A bunch of BPF maps do not support specifying BTF types for key and value. This is non-uniform and inconvenient[0]. Currently, libbpf uses a retry logic which removes BTF type IDs when BPF map creation failed. Instead of retrying, this commit recognizes those specialized maps and removes BTF type IDs when creating BPF map. [0] Closes: https://github.com/libbpf/libbpf/issues/355 Signed-off-by: Hengqi Chen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210930161456.3444544-2-hengqi.chen@gmail.com --- tools/lib/bpf/libbpf.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7544d7d09160..e23f1b6b9402 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4669,6 +4669,30 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.inner_map_fd = map->inner_map_fd; } + switch (def->type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + default: + break; + } + if (obj->gen_loader) { bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. From bd368cb554d685c60e65ab799bf238663c682105 Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Fri, 1 Oct 2021 00:14:56 +0800 Subject: [PATCH 85/85] selftests/bpf: Use BTF-defined key/value for map definitions Change map definitions in BPF selftests to use BTF-defined key/value types. This unifies the map definitions and ensures libbpf won't emit warning about retrying map creation. Signed-off-by: Hengqi Chen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210930161456.3444544-3-hengqi.chen@gmail.com --- tools/testing/selftests/bpf/progs/kfree_skb.c | 4 ++-- .../selftests/bpf/progs/perf_event_stackmap.c | 4 ++-- .../selftests/bpf/progs/sockmap_verdict_prog.c | 12 ++++++------ .../selftests/bpf/progs/test_btf_map_in_map.c | 14 +++++++------- .../testing/selftests/bpf/progs/test_map_in_map.c | 10 ++++------ .../selftests/bpf/progs/test_map_in_map_invalid.c | 2 +- .../selftests/bpf/progs/test_pe_preserve_elems.c | 8 ++++---- .../testing/selftests/bpf/progs/test_perf_buffer.c | 4 ++-- .../bpf/progs/test_select_reuseport_kern.c | 4 ++-- .../selftests/bpf/progs/test_stacktrace_build_id.c | 4 ++-- .../selftests/bpf/progs/test_stacktrace_map.c | 4 ++-- .../selftests/bpf/progs/test_tcpnotify_kern.c | 4 ++-- .../testing/selftests/bpf/progs/test_xdp_bpf2bpf.c | 4 ++-- 13 files changed, 38 insertions(+), 40 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 55e283050cab..7236da72ce80 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -9,8 +9,8 @@ char _license[] SEC("license") = "GPL"; struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); #define _(P) (__builtin_preserve_access_index(P)) diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c index 25467d13c356..b3fcb5274ee0 100644 --- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -11,8 +11,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 4797dc985064..73872c535cbb 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -7,22 +7,22 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_rx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_tx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_msg SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c index c1e0c8c7c55f..c218cf8989a9 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -21,8 +21,8 @@ struct inner_map_sz2 { struct outer_arr { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); /* it's possible to use anonymous struct as inner map definition here */ __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -61,8 +61,8 @@ struct inner_map_sz4 { struct outer_arr_dyn { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(map_flags, BPF_F_INNER_MAP); @@ -81,7 +81,7 @@ struct outer_arr_dyn { struct outer_hash { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 5); - __uint(key_size, sizeof(int)); + __type(key, int); /* Here everything works flawlessly due to reuse of struct inner_map * and compiler will complain at the attempt to use non-inner_map * references below. This is great experience. @@ -111,8 +111,8 @@ struct sockarr_sz2 { struct outer_sockarr_sz1 { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct sockarr_sz1); } outer_sockarr SEC(".maps") = { .values = { (void *)&sockarr_sz1 }, diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 5f0e0bfc151e..a6d91932dcd5 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -9,18 +9,16 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(__u32)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } mim_array SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(int)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } mim_hash SEC(".maps"); SEC("xdp") diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c index 703c08e06442..9c7d75cf0bd6 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c @@ -13,7 +13,7 @@ struct inner { struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 0); /* This will make map creation to fail */ - __uint(key_size, sizeof(__u32)); + __type(key, __u32); __array(values, struct inner); } mim SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c index fb22de7c365d..1249a945699f 100644 --- a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c +++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c @@ -7,15 +7,15 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } array_1 SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __uint(map_flags, BPF_F_PRESERVE_ELEMS); } array_2 SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index 8207a2dc2f9d..d37ce29fd393 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -8,8 +8,8 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); SEC("tp/raw_syscalls/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 26e77dcc7e91..0f9bc258225e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -24,8 +24,8 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } outer_map SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index 0cf0134631b4..7449fdb1763b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -28,8 +28,8 @@ struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 128); __uint(map_flags, BPF_F_STACK_BUILD_ID); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 00ed48672620..a8233e7f173b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -27,8 +27,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ac63410bb541..24e9344994ef 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -24,8 +24,8 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 2); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } perf_event_map SEC(".maps"); int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index a038e827f850..58cf4345f5cc 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -36,8 +36,8 @@ struct meta { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); __u64 test_result_fentry = 0;