From 8d00547ea8754afdc4a550af2fb7af2e3ba93cf8 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Thu, 16 May 2024 10:09:28 +0800 Subject: [PATCH 01/15] MAINTAINERS: Add myself as reviewer of ARM64 BPF JIT I am working on ARM64 BPF JIT for a while, hence add myself as reviewer. Signed-off-by: Xu Kuohai Acked-by: Hengqi Chen Link: https://lore.kernel.org/r/20240516020928.156125-1-xukuohai@huaweicloud.com Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 3fdc3b09c171..5e279e9ff63f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3816,6 +3816,7 @@ BPF JIT for ARM64 M: Daniel Borkmann M: Alexei Starovoitov M: Puranjay Mohan +R: Xu Kuohai L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ From 44382b3ed6b2787710c8ade06c0e97f5970a47c8 Mon Sep 17 00:00:00 2001 From: Friedrich Vock Date: Tue, 14 May 2024 09:09:31 +0200 Subject: [PATCH 02/15] bpf: Fix potential integer overflow in resolve_btfids err is a 32-bit integer, but elf_update returns an off_t, which is 64-bit at least on 64-bit platforms. If symbols_patch is called on a binary between 2-4GB in size, the result will be negative when cast to a 32-bit integer, which the code assumes means an error occurred. This can wrongly trigger build failures when building very large kernel images. Fixes: fbbb68de80a4 ("bpf: Add resolve_btfids tool to resolve BTF IDs in ELF object") Signed-off-by: Friedrich Vock Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240514070931.199694-1-friedrich.vock@gmx.de --- tools/bpf/resolve_btfids/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index d9520cb826b3..af393c7dee1f 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -728,7 +728,7 @@ static int sets_patch(struct object *obj) static int symbols_patch(struct object *obj) { - int err; + off_t err; if (__symbols_patch(obj, &obj->structs) || __symbols_patch(obj, &obj->unions) || From 46ba0e49b64232adac35a2bc892f1710c5b0fb7f Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 May 2024 09:33:57 -0700 Subject: [PATCH 03/15] bpf: fix multi-uprobe PID filtering logic Current implementation of PID filtering logic for multi-uprobes in uprobe_prog_run() is filtering down to exact *thread*, while the intent for PID filtering it to filter by *process* instead. The check in uprobe_prog_run() also differs from the analogous one in uprobe_multi_link_filter() for some reason. The latter is correct, checking task->mm, not the task itself. Fix the check in uprobe_prog_run() to perform the same task->mm check. While doing this, we also update get_pid_task() use to use PIDTYPE_TGID type of lookup, given the intent is to get a representative task of an entire process. This doesn't change behavior, but seems more logical. It would hold task group leader task now, not any random thread task. Last but not least, given multi-uprobe support is half-broken due to this PID filtering logic (depending on whether PID filtering is important or not), we need to make it easy for user space consumers (including libbpf) to easily detect whether PID filtering logic was already fixed. We do it here by adding an early check on passed pid parameter. If it's negative (and so has no chance of being a valid PID), we return -EINVAL. Previous behavior would eventually return -ESRCH ("No process found"), given there can't be any process with negative PID. This subtle change won't make any practical change in behavior, but will allow applications to detect PID filtering fixes easily. Libbpf fixes take advantage of this in the next patch. Cc: stable@vger.kernel.org Acked-by: Jiri Olsa Fixes: b733eeade420 ("bpf: Add pid filter support for uprobe_multi link") Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240521163401.3005045-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 8 ++++---- .../testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f5154c051d2c..1baaeb9ca205 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3295,7 +3295,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; - if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0; if (sleepable) @@ -3396,8 +3396,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3421,10 +3422,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } - pid = attr->link_create.uprobe_multi.pid; if (pid) { rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); rcu_read_unlock(); if (!task) { err = -ESRCH; diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 8269cdee33ae..38fda42fd70f 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -397,7 +397,7 @@ static void test_attach_api_fails(void) link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); if (!ASSERT_ERR(link_fd, "link_fd")) goto cleanup; - ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong"); cleanup: if (link_fd >= 0) From 4a8f635a60540888dab3804992e86410360339c8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 May 2024 09:33:58 -0700 Subject: [PATCH 04/15] bpf: remove unnecessary rcu_read_{lock,unlock}() in multi-uprobe attach logic get_pid_task() internally already calls rcu_read_lock() and rcu_read_unlock(), so there is no point to do this one extra time. This is a drive-by improvement and has no correctness implications. Acked-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240521163401.3005045-3-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1baaeb9ca205..6249dac61701 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3423,9 +3423,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr } if (pid) { - rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); - rcu_read_unlock(); if (!task) { err = -ESRCH; goto error_path_put; From 04d939a2ab229a3821f04fc81f7c027842f501f1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 May 2024 09:33:59 -0700 Subject: [PATCH 05/15] libbpf: detect broken PID filtering logic for multi-uprobe Libbpf is automatically (and transparently to user) detecting multi-uprobe support in the kernel, and, if supported, uses multi-uprobes to improve USDT attachment speed. USDTs can be attached system-wide or for the specific process by PID. In the latter case, we rely on correct kernel logic of not triggering USDT for unrelated processes. As such, on older kernels that do support multi-uprobes, but still have broken PID filtering logic, we need to fall back to singular uprobes. Unfortunately, whether user is using PID filtering or not is known at the attachment time, which happens after relevant BPF programs were loaded into the kernel. Also unfortunately, we need to make a call whether to use multi-uprobes or singular uprobe for SEC("usdt") programs during BPF object load time, at which point we have no information about possible PID filtering. The distinction between single and multi-uprobes is small, but important for the kernel. Multi-uprobes get BPF_TRACE_UPROBE_MULTI attach type, and kernel internally substitiute different implementation of some of BPF helpers (e.g., bpf_get_attach_cookie()) depending on whether uprobe is multi or singular. So, multi-uprobes and singular uprobes cannot be intermixed. All the above implies that we have to make an early and conservative call about the use of multi-uprobes. And so this patch modifies libbpf's existing feature detector for multi-uprobe support to also check correct PID filtering. If PID filtering is not yet fixed, we fall back to singular uprobes for USDTs. This extension to feature detection is simple thanks to kernel's -EINVAL addition for pid < 0. Acked-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240521163401.3005045-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/features.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index a336786a22a3..3df0125ed5fa 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -392,11 +392,40 @@ static int probe_uprobe_multi_link(int token_fd) link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); err = -errno; /* close() can clobber errno */ + if (link_fd >= 0 || err != -EBADF) { + close(link_fd); + close(prog_fd); + return 0; + } + + /* Initial multi-uprobe support in kernel didn't handle PID filtering + * correctly (it was doing thread filtering, not process filtering). + * So now we'll detect if PID filtering logic was fixed, and, if not, + * we'll pretend multi-uprobes are not supported, if not. + * Multi-uprobes are used in USDT attachment logic, and we need to be + * conservative here, because multi-uprobe selection happens early at + * load time, while the use of PID filtering is known late at + * attachment time, at which point it's too late to undo multi-uprobe + * selection. + * + * Creating uprobe with pid == -1 for (invalid) '/' binary will fail + * early with -EINVAL on kernels with fixed PID filtering logic; + * otherwise -ESRCH would be returned if passed correct binary path + * (but we'll just get -BADF, of course). + */ + link_opts.uprobe_multi.pid = -1; /* invalid PID */ + link_opts.uprobe_multi.path = "/"; /* invalid path */ + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + if (link_fd >= 0) close(link_fd); close(prog_fd); - return link_fd < 0 && err == -EBADF; + return link_fd < 0 && err == -EINVAL; } static int probe_kern_bpf_cookie(int token_fd) From 70342420a1cf1173bdec456e5fa574a804e422db Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 May 2024 09:34:00 -0700 Subject: [PATCH 06/15] selftests/bpf: extend multi-uprobe tests with child thread case Extend existing multi-uprobe tests to test that PID filtering works correctly. We already have child *process* tests, but we need also child *thread* tests. This patch adds spawn_thread() helper to start child thread, wait for it to be ready, and then instruct it to trigger desired uprobes. Additionally, we extend BPF-side code to track thread ID, not just process ID. Also we detect whether extraneous triggerings with unexpected process IDs happened, and validate that none of that happened in practice. These changes prove that fixed PID filtering logic for multi-uprobe works as expected. These tests fail on old kernels. Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20240521163401.3005045-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- .../bpf/prog_tests/uprobe_multi_test.c | 107 ++++++++++++++++-- .../selftests/bpf/progs/uprobe_multi.c | 17 ++- 2 files changed, 115 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 38fda42fd70f..677232d31432 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include "uprobe_multi.skel.h" #include "uprobe_multi_bench.skel.h" @@ -27,7 +28,10 @@ noinline void uprobe_multi_func_3(void) struct child { int go[2]; + int c2p[2]; /* child -> parent channel */ int pid; + int tid; + pthread_t thread; }; static void release_child(struct child *child) @@ -38,6 +42,10 @@ static void release_child(struct child *child) return; close(child->go[1]); close(child->go[0]); + if (child->thread) + pthread_join(child->thread, NULL); + close(child->c2p[0]); + close(child->c2p[1]); if (child->pid > 0) waitpid(child->pid, &child_status, 0); } @@ -63,7 +71,7 @@ static struct child *spawn_child(void) if (pipe(child.go)) return NULL; - child.pid = fork(); + child.pid = child.tid = fork(); if (child.pid < 0) { release_child(&child); errno = EINVAL; @@ -89,6 +97,66 @@ static struct child *spawn_child(void) return &child; } +static void *child_thread(void *ctx) +{ + struct child *child = ctx; + int c = 0, err; + + child->tid = syscall(SYS_gettid); + + /* let parent know we are ready */ + err = write(child->c2p[1], &c, 1); + if (err != 1) + pthread_exit(&err); + + /* wait for parent's kick */ + err = read(child->go[0], &c, 1); + if (err != 1) + pthread_exit(&err); + + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + + err = 0; + pthread_exit(&err); +} + +static struct child *spawn_thread(void) +{ + static struct child child; + int c, err; + + /* pipe to notify child to execute the trigger functions */ + if (pipe(child.go)) + return NULL; + /* pipe to notify parent that child thread is ready */ + if (pipe(child.c2p)) { + close(child.go[0]); + close(child.go[1]); + return NULL; + } + + child.pid = getpid(); + + err = pthread_create(&child.thread, NULL, child_thread, &child); + if (err) { + err = -errno; + close(child.go[0]); + close(child.go[1]); + close(child.c2p[0]); + close(child.c2p[1]); + errno = -err; + return NULL; + } + + err = read(child.c2p[0], &c, 1); + if (!ASSERT_EQ(err, 1, "child_thread_ready")) + return NULL; + + return &child; +} + static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child) { skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1; @@ -103,15 +171,22 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child * passed at the probe attach. */ skel->bss->pid = child ? 0 : getpid(); + skel->bss->expect_pid = child ? child->pid : 0; + + /* trigger all probes, if we are testing child *process*, just to make + * sure that PID filtering doesn't let through activations from wrong + * PIDs; when we test child *thread*, we don't want to do this to + * avoid double counting number of triggering events + */ + if (!child || !child->thread) { + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + } if (child) kick_child(child); - /* trigger all probes */ - uprobe_multi_func_1(); - uprobe_multi_func_2(); - uprobe_multi_func_3(); - /* * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123] * function and each slepable probe (6) increments uprobe_multi_sleep_result. @@ -126,8 +201,12 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result"); - if (child) + ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen"); + + if (child) { ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid"); + } } static void test_skel_api(void) @@ -210,6 +289,13 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi return; __test_attach_api(binary, pattern, opts, child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_attach_api(binary, pattern, opts, child); } static void test_attach_api_pattern(void) @@ -495,6 +581,13 @@ static void test_link_api(void) return; __test_link_api(child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_link_api(child); } static void test_bench_attach_uprobe(void) diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c index 419d9aa28fce..86a7ff5d3726 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -22,6 +22,10 @@ __u64 uprobe_multi_sleep_result = 0; int pid = 0; int child_pid = 0; +int child_tid = 0; + +int expect_pid = 0; +bool bad_pid_seen = false; bool test_cookie = false; void *user_ptr = 0; @@ -36,11 +40,19 @@ static __always_inline bool verify_sleepable_user_copy(void) static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep) { - child_pid = bpf_get_current_pid_tgid() >> 32; + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; - if (pid && child_pid != pid) + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) return; + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen = true; + + child_pid = cur_pid_tgid >> 32; + child_tid = (__u32)cur_pid_tgid; + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; __u64 addr = bpf_get_func_ip(ctx); @@ -97,5 +109,6 @@ int uretprobe_sleep(struct pt_regs *ctx) SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") int uprobe_extra(struct pt_regs *ctx) { + /* we need this one just to mix PID-filtered and global uprobes */ return 0; } From 198034a87dfeb64d5a8359a5089022c6b923646e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 May 2024 09:34:01 -0700 Subject: [PATCH 07/15] selftests/bpf: extend multi-uprobe tests with USDTs Validate libbpf's USDT-over-multi-uprobe logic by adding USDTs to existing multi-uprobe tests. This checks correct libbpf fallback to singular uprobes (when run on older kernels with buggy PID filtering). We reuse already established child process and child thread testing infrastructure, so additions are minimal. These test fail on either older kernels or older version of libbpf that doesn't detect PID filtering problems. Acked-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240521163401.3005045-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- .../bpf/prog_tests/uprobe_multi_test.c | 25 ++++++++++++++ .../selftests/bpf/progs/uprobe_multi.c | 33 +++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 677232d31432..bf6ca8e3eb13 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -8,6 +8,7 @@ #include "uprobe_multi_usdt.skel.h" #include "bpf/libbpf_internal.h" #include "testing_helpers.h" +#include "../sdt.h" static char test_data[] = "test_data"; @@ -26,6 +27,11 @@ noinline void uprobe_multi_func_3(void) asm volatile (""); } +noinline void usdt_trigger(void) +{ + STAP_PROBE(test, pid_filter_usdt); +} + struct child { int go[2]; int c2p[2]; /* child -> parent channel */ @@ -90,6 +96,7 @@ static struct child *spawn_child(void) uprobe_multi_func_1(); uprobe_multi_func_2(); uprobe_multi_func_3(); + usdt_trigger(); exit(errno); } @@ -117,6 +124,7 @@ static void *child_thread(void *ctx) uprobe_multi_func_1(); uprobe_multi_func_2(); uprobe_multi_func_3(); + usdt_trigger(); err = 0; pthread_exit(&err); @@ -182,6 +190,7 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child uprobe_multi_func_1(); uprobe_multi_func_2(); uprobe_multi_func_3(); + usdt_trigger(); } if (child) @@ -269,8 +278,24 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi")) goto cleanup; + /* Attach (uprobe-backed) USDTs */ + skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid")) + goto cleanup; + + skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra")) + goto cleanup; + uprobe_multi_test_run(skel, child); + ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt"); + if (child) { + ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid"); + } cleanup: uprobe_multi__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c index 86a7ff5d3726..44190efcdba2 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include "vmlinux.h" #include #include -#include +#include char _license[] SEC("license") = "GPL"; @@ -23,9 +23,12 @@ __u64 uprobe_multi_sleep_result = 0; int pid = 0; int child_pid = 0; int child_tid = 0; +int child_pid_usdt = 0; +int child_tid_usdt = 0; int expect_pid = 0; bool bad_pid_seen = false; +bool bad_pid_seen_usdt = false; bool test_cookie = false; void *user_ptr = 0; @@ -112,3 +115,29 @@ int uprobe_extra(struct pt_regs *ctx) /* we need this one just to mix PID-filtered and global uprobes */ return 0; } + +SEC("usdt") +int usdt_pid(struct pt_regs *ctx) +{ + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; + + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) + return 0; + + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen_usdt = true; + + child_pid_usdt = cur_pid_tgid >> 32; + child_tid_usdt = (__u32)cur_pid_tgid; + + return 0; +} + +SEC("usdt") +int usdt_extra(struct pt_regs *ctx) +{ + /* we need this one just to mix PID-filtered and global USDT probes */ + return 0; +} From dd6a403795f0c7b5c566f86f2ee6b687278d3c1c Mon Sep 17 00:00:00 2001 From: Shahab Vahedi Date: Sat, 25 May 2024 05:56:28 +0200 Subject: [PATCH 08/15] ARC, bpf: Fix issues reported by the static analyzers Also updated couple of comments along the way. One of the issues reported was indeed a bug in the code: memset(ctx, 0, sizeof(ctx)) // original line memset(ctx, 0, sizeof(*ctx)) // fixed line That was a nice catch. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202405222314.UG5F2NHn-lkp@intel.com/ Closes: https://lore.kernel.org/oe-kbuild-all/202405232036.Xqoc3b0J-lkp@intel.com/ Signed-off-by: Shahab Vahedi Link: https://lore.kernel.org/r/20240525035628.1026-1-list+bpf@vahedi.org Signed-off-by: Alexei Starovoitov --- arch/arc/net/bpf_jit.h | 2 +- arch/arc/net/bpf_jit_arcv2.c | 10 ++++++---- arch/arc/net/bpf_jit_core.c | 22 +++++++++++----------- 3 files changed, 18 insertions(+), 16 deletions(-) diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h index ec44873c42d1..495f3023e4c1 100644 --- a/arch/arc/net/bpf_jit.h +++ b/arch/arc/net/bpf_jit.h @@ -39,7 +39,7 @@ /************** Functions that the back-end must provide **************/ /* Extension for 32-bit operations. */ -inline u8 zext(u8 *buf, u8 rd); +u8 zext(u8 *buf, u8 rd); /***** Moves *****/ u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext); u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm); diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 31bfb6e9ce00..4458e409ca0a 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -62,7 +62,7 @@ enum { * If/when we decide to add ARCv2 instructions that do use register pairs, * the mapping, hopefully, doesn't need to be revisited. */ -const u8 bpf2arc[][2] = { +static const u8 bpf2arc[][2] = { /* Return value from in-kernel function, and exit value from eBPF */ [BPF_REG_0] = {ARC_R_8, ARC_R_9}, /* Arguments from eBPF program to in-kernel function */ @@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset) /************* Packers (Deal with BPF_REGs) **************/ -inline u8 zext(u8 *buf, u8 rd) +u8 zext(u8 *buf, u8 rd) { if (rd != BPF_REG_FP) return arc_movi_r(buf, REG_HI(rd), 0); @@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } else { /* @@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } @@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size) #define JCC64_NR_OF_JMPS 3 /* Number of jumps in jcc64 template. */ #define JCC64_INSNS_TO_END 3 /* Number of insn. inclusive the 2nd jmp to end. */ #define JCC64_SKIP_JMP 1 /* Index of the "skip" jump to "end". */ -const struct { +static const struct { /* * "jit_off" is common between all "jmp[]" and is coupled with * "cond" of each "jmp[]" instance. e.g.: @@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst" * instruction that precedes the conditional branch. */ -const u8 arcv2_32_jmps[ARC_CC_LAST] = { +static const u8 arcv2_32_jmps[ARC_CC_LAST] = { [ARC_CC_UGT] = CC_great_u, [ARC_CC_UGE] = CC_great_eq_u, [ARC_CC_ULT] = CC_less_u, diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c index 6f6b4ffccf2c..e3628922c24a 100644 --- a/arch/arc/net/bpf_jit_core.c +++ b/arch/arc/net/bpf_jit_core.c @@ -159,7 +159,7 @@ static void jit_dump(const struct jit_context *ctx) /* Initialise the context so there's no garbage. */ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) { - memset(ctx, 0, sizeof(ctx)); + memset(ctx, 0, sizeof(*ctx)); ctx->orig_prog = prog; @@ -167,7 +167,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) ctx->prog = bpf_jit_blind_constants(prog); if (IS_ERR(ctx->prog)) return PTR_ERR(ctx->prog); - ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true); + ctx->blinded = (ctx->prog != ctx->orig_prog); /* If the verifier doesn't zero-extend, then we have to do it. */ ctx->do_zext = !ctx->prog->aux->verifier_zext; @@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx) } /* - * All the "handle_*()" functions have been called before by the - * "jit_prepare()". If there was an error, we would know by now. - * Therefore, no extra error checking at this point, other than - * a sanity check at the end that expects the calculated length - * (jit.len) to be equal to the length of generated instructions - * (jit.index). + * jit_compile() is the real compilation phase. jit_prepare() is + * invoked before jit_compile() as a dry-run to make sure everything + * will go OK and allocate the necessary memory. + * + * In the end, jit_compile() checks if it has produced the same number + * of instructions as jit_prepare() would. */ static int jit_compile(struct jit_context *ctx) { @@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog) /* * This function may be invoked twice for the same stream of BPF - * instructions. The "extra pass" happens, when there are "call"s - * involved that their addresses are not known during the first - * invocation. + * instructions. The "extra pass" happens, when there are + * (re)locations involved that their addresses are not known + * during the first run. */ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { From d6fe532b7499e4575f9647879b7a34625817fe7f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:16 +0200 Subject: [PATCH 09/15] netkit: Fix setting mac address in l2 mode When running Cilium connectivity test suite with netkit in L2 mode, we found that it is expected to be able to specify a custom MAC address for the devices, in particular, cilium-cni obtains the specified MAC address by querying the endpoint and sets the MAC address of the interface inside the Pod. Thus, fix the missing support in netkit for L2 mode. Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device") Signed-off-by: Daniel Borkmann Acked-by: Nikolay Aleksandrov Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20240524163619.26001-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- drivers/net/netkit.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index a4d2e76a8d58..272894053e2c 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -155,6 +155,16 @@ static void netkit_set_multicast(struct net_device *dev) /* Nothing to do, we receive whatever gets pushed to us! */ } +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + static void netkit_set_headroom(struct net_device *dev, int headroom) { struct netkit *nk = netkit_priv(dev), *nk2; @@ -198,6 +208,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_start_xmit = netkit_xmit, .ndo_set_rx_mode = netkit_set_multicast, .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, @@ -300,9 +311,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], if (!attr) return 0; - NL_SET_ERR_MSG_ATTR(extack, attr, - "Setting Ethernet address is not supported"); - return -EOPNOTSUPP; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; } static struct rtnl_link_ops netkit_link_ops; @@ -365,6 +378,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, strscpy(ifname, "nk%d", IFNAMSIZ); ifname_assign_type = NET_NAME_ENUM; } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) @@ -379,7 +395,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, netif_inherit_tso_max(peer, dev); - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; @@ -402,7 +418,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (err < 0) goto err_configure_peer; - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); From 3998d184267dfcff858aaa84d3de17429253629d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:17 +0200 Subject: [PATCH 10/15] netkit: Fix pkt_type override upon netkit pass verdict When running Cilium connectivity test suite with netkit in L2 mode, we found that compared to tcx a few tests were failing which pushed traffic into an L7 proxy sitting in host namespace. The problem in particular is around the invocation of eth_type_trans() in netkit. In case of tcx, this is run before the tcx ingress is triggered inside host namespace and thus if the BPF program uses the bpf_skb_change_type() helper the newly set type is retained. However, in case of netkit, the late eth_type_trans() invocation overrides the earlier decision from the BPF program which eventually leads to the test failure. Instead of eth_type_trans(), split out the relevant parts, meaning, reset of mac header and call to eth_skb_pkt_type() before the BPF program is run in order to have the same behavior as with tcx, and refactor a small helper called eth_skb_pull_mac() which is run in case it's passed up the stack where the mac header must be pulled. With this all connectivity tests pass. Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device") Signed-off-by: Daniel Borkmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240524163619.26001-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- drivers/net/netkit.c | 4 +++- include/linux/etherdevice.h | 8 ++++++++ net/ethernet/eth.c | 4 +--- 3 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 272894053e2c..16789cd446e9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad1ffa4ccb9..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* From 998ffeb2738e26f134dc8e63b5dcaece22573957 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:18 +0200 Subject: [PATCH 11/15] selftests/bpf: Add netkit tests for mac address This adds simple tests around setting MAC addresses in the different netkit modes. Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20240524163619.26001-3-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/tc_netkit.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 15ee7b2fc410..18b2e969a456 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -73,6 +73,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, "up primary"); ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"), "addr primary"); + + if (mode == NETKIT_L3) { + ASSERT_EQ(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512, + "set hwaddress"); + } else { + ASSERT_OK(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd"), + "set hwaddress"); + } if (same_netns) { ASSERT_OK(system("ip link set dev " netkit_peer " up"), "up peer"); From 95348e463eabc803341c67d562f9e0a5f0a48fe6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:19 +0200 Subject: [PATCH 12/15] selftests/bpf: Add netkit test for pkt_type Add a test case to assert that the skb->pkt_type which was set from the BPF program is retained from the netkit xmit side to the peer's device at tcx ingress location. # ./vmtest.sh -- ./test_progs -t netkit [...] ./test_progs -t netkit [ 1.140780] bpf_testmod: loading out-of-tree module taints kernel. [ 1.141127] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel [ 1.284601] tsc: Refined TSC clocksource calibration: 3408.006 MHz [ 1.286672] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fd9b189d, max_idle_ns: 440795225691 ns [ 1.290384] clocksource: Switched to clocksource tsc #345 tc_netkit_basic:OK #346 tc_netkit_device:OK #347 tc_netkit_multi_links:OK #348 tc_netkit_multi_opts:OK #349 tc_netkit_neigh_links:OK #350 tc_netkit_pkt_type:OK Summary: 6/0 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20240524163619.26001-4-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/tc_netkit.c | 84 +++++++++++++++++++ .../selftests/bpf/progs/test_tc_link.c | 35 +++++++- 2 files changed, 118 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 18b2e969a456..b9135720024c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -99,6 +99,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, return err; } +static void move_netkit(void) +{ + ASSERT_OK(system("ip link set " netkit_peer " netns foo"), + "move peer"); + ASSERT_OK(system("ip netns exec foo ip link set dev " + netkit_peer " up"), "up peer"); + ASSERT_OK(system("ip netns exec foo ip addr add dev " + netkit_peer " 10.0.0.2/24"), "addr peer"); +} + static void destroy_netkit(void) { ASSERT_OK(system("ip link del dev " netkit_name), "del primary"); @@ -695,3 +705,77 @@ void serial_test_tc_netkit_neigh_links(void) serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); } + +static void serial_test_tc_netkit_pkt_type_mode(int mode) +{ + LIBBPF_OPTS(bpf_netkit_opts, optl_nk); + LIBBPF_OPTS(bpf_tcx_opts, optl_tcx); + int err, ifindex, ifindex2; + struct test_tc_link *skel; + struct bpf_link *link; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, true); + if (err) + return; + + ifindex2 = if_nametoindex(netkit_peer); + ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7, + BPF_TCX_INGRESS), 0, "tc7_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc7 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1); + + move_netkit(); + + tc_skel_reset_all_seen(skel); + skel->bss->set_type = true; + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7"); + + ASSERT_EQ(skel->bss->seen_host, true, "seen_host"); + ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_pkt_type(void) +{ + serial_test_tc_netkit_pkt_type_mode(NETKIT_L2); + serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 992400acb957..ab3eae3d6af8 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -4,7 +4,8 @@ #include #include - +#include +#include #include #include @@ -16,7 +17,13 @@ bool seen_tc3; bool seen_tc4; bool seen_tc5; bool seen_tc6; +bool seen_tc7; + +bool set_type; + bool seen_eth; +bool seen_host; +bool seen_mcast; SEC("tc/ingress") int tc1(struct __sk_buff *skb) @@ -28,8 +35,16 @@ int tc1(struct __sk_buff *skb) if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) goto out; seen_eth = eth.h_proto == bpf_htons(ETH_P_IP); + seen_host = skb->pkt_type == PACKET_HOST; + if (seen_host && set_type) { + eth.h_dest[0] = 4; + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0)) + goto fail; + bpf_skb_change_type(skb, PACKET_MULTICAST); + } out: seen_tc1 = true; +fail: return TCX_NEXT; } @@ -67,3 +82,21 @@ int tc6(struct __sk_buff *skb) seen_tc6 = true; return TCX_PASS; } + +SEC("tc/ingress") +int tc7(struct __sk_buff *skb) +{ + struct ethhdr eth = {}; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IP)) + goto out; + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) + goto out; + if (eth.h_dest[0] == 4 && set_type) { + seen_mcast = skb->pkt_type == PACKET_MULTICAST; + bpf_skb_change_type(skb, PACKET_HOST); + } +out: + seen_tc7 = true; + return TCX_PASS; +} From 98e948fb60d41447fd8d2d0c3b8637fc6b6dc26d Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 27 May 2024 13:20:07 +0200 Subject: [PATCH 13/15] bpf: Allow delete from sockmap/sockhash only if update is allowed We have seen an influx of syzkaller reports where a BPF program attached to a tracepoint triggers a locking rule violation by performing a map_delete on a sockmap/sockhash. We don't intend to support this artificial use scenario. Extend the existing verifier allowed-program-type check for updating sockmap/sockhash to also cover deleting from a map. From now on only BPF programs which were previously allowed to update sockmap/sockhash can delete from these map types. Fixes: ff9105993240 ("bpf, sockmap: Prevent lock inversion deadlock in map delete elem") Reported-by: Tetsuo Handa Reported-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Tested-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com Acked-by: John Fastabend Closes: https://syzkaller.appspot.com/bug?extid=ec941d6e24f633a59172 Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-1-944b372f2101@cloudflare.com --- kernel/bpf/verifier.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 77da1f438bec..48f3a9acdef3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8882,7 +8882,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -8893,6 +8894,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -8988,7 +8994,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -8998,7 +9003,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && From 3b9ce0491a43e9af7f108b2f1bced7cd35931660 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 27 May 2024 13:20:08 +0200 Subject: [PATCH 14/15] Revert "bpf, sockmap: Prevent lock inversion deadlock in map delete elem" This reverts commit ff91059932401894e6c86341915615c5eb0eca48. This check is no longer needed. BPF programs attached to tracepoints are now rejected by the verifier when they attempt to delete from a sockmap/sockhash maps. Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-2-944b372f2101@cloudflare.com --- net/core/sock_map.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9402889840bf..63c016b4c169 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -948,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); From a63bf556160fb19591183383da6757f52119981d Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 27 May 2024 13:20:09 +0200 Subject: [PATCH 15/15] selftests/bpf: Cover verifier checks for mutating sockmap/sockhash Verifier enforces that only certain program types can mutate sock{map,hash} maps, that is update it or delete from it. Add test coverage for these checks so we don't regress. Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20240527-sockmap-verify-deletes-v1-3-944b372f2101@cloudflare.com --- .../selftests/bpf/prog_tests/verifier.c | 2 + .../bpf/progs/verifier_sockmap_mutate.c | 187 ++++++++++++++++++ 2 files changed, 189 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index c60db8beeb73..1c9c4ec1be11 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -67,6 +67,7 @@ #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_sock_addr.skel.h" +#include "verifier_sockmap_mutate.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" @@ -183,6 +184,7 @@ void test_verifier_sdiv(void) { RUN(verifier_sdiv); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_sock_addr(void) { RUN(verifier_sock_addr); } +void test_verifier_sockmap_mutate(void) { RUN(verifier_sockmap_mutate); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c new file mode 100644 index 000000000000..fe4b123187b8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#include "bpf_misc.h" + +#define __always_unused __attribute__((unused)) + +char _license[] SEC("license") = "GPL"; + +struct sock { +} __attribute__((preserve_access_index)); + +struct bpf_iter__sockmap { + union { + struct sock *sk; + }; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockhash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockmap SEC(".maps"); + +enum { CG_OK = 1 }; + +int zero = 0; + +static __always_inline void test_sockmap_delete(void) +{ + bpf_map_delete_elem(&sockmap, &zero); + bpf_map_delete_elem(&sockhash, &zero); +} + +static __always_inline void test_sockmap_update(void *sk) +{ + if (sk) { + bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY); + bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY); + } +} + +static __always_inline void test_sockmap_lookup_and_update(void) +{ + struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero); + + if (sk) { + test_sockmap_update(sk); + bpf_sk_release(sk); + } +} + +static __always_inline void test_sockmap_mutate(void *sk) +{ + test_sockmap_delete(); + test_sockmap_update(sk); +} + +static __always_inline void test_sockmap_lookup_and_mutate(void) +{ + test_sockmap_delete(); + test_sockmap_lookup_and_update(); +} + +SEC("action") +__success +int test_sched_act(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("classifier") +__success +int test_sched_cls(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("flow_dissector") +__success +int test_flow_dissector_delete(struct __sk_buff *skb __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("flow_dissector") +__failure __msg("program of this type cannot use helper bpf_sk_release") +int test_flow_dissector_update(struct __sk_buff *skb __always_unused) +{ + test_sockmap_lookup_and_update(); /* no access to skb->sk */ + return 0; +} + +SEC("iter/sockmap") +__success +int test_trace_iter(struct bpf_iter__sockmap *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_delete(const void *ctx __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_update(const void *ctx __always_unused) +{ + test_sockmap_lookup_and_update(); + return 0; +} + +SEC("sk_lookup") +__success +int test_sk_lookup(struct bpf_sk_lookup *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("sk_reuseport") +__success +int test_sk_reuseport(struct sk_reuseport_md *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("socket") +__success +int test_socket_filter(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("sockops") +__success +int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused) +{ + test_sockmap_delete(); + return CG_OK; +} + +SEC("sockops") +__failure __msg("cannot update sockmap in this context") +int test_sockops_update(struct bpf_sock_ops *ctx) +{ + test_sockmap_update(ctx->sk); + return CG_OK; +} + +SEC("sockops") +__success +int test_sockops_update_dedicated(struct bpf_sock_ops *ctx) +{ + bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY); + bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY); + return CG_OK; +} + +SEC("xdp") +__success +int test_xdp(struct xdp_md *ctx __always_unused) +{ + test_sockmap_lookup_and_mutate(); + return XDP_PASS; +}