diff options
author | Alexei Starovoitov <ast@kernel.org> | 2022-01-24 19:55:41 -0800 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2022-01-24 19:59:38 -0800 |
commit | c45c79e546664c6e404f47772ebba28ea90262d0 (patch) | |
tree | 34071034e4092118810dc213cd49b28c989f1fa6 /tools | |
parent | caaba96131b3a132590316c49887af85e07930b6 (diff) | |
parent | 45105c2eb751e2a3dd9858622cf72e2d588209a0 (diff) |
Merge branch 'Add bpf_copy_from_user_task helper and sleepable bpf iterator programs'
Kenny Yu says:
====================
This patch series makes the following changes:
* Adds a new bpf helper `bpf_copy_from_user_task` to read user space
memory from a different task.
* Adds the ability to create sleepable bpf iterator programs.
As an example of how this will be used, at Meta we are using bpf task
iterator programs and this new bpf helper to read C++ async stack traces of
a running process for debugging C++ binaries in production.
Changes since v6:
* Split first patch into two patches: first patch to add support
for bpf iterators to use sleepable helpers, and the second to add
the new bpf helper.
* Simplify implementation of `bpf_copy_from_user_task` based on feedback.
* Add to docs that the destination buffer will be zero-ed on error.
Changes since v5:
* Rename `bpf_access_process_vm` to `bpf_copy_from_user_task`.
* Change return value to be all-or-nothing. If we get a partial read,
memset all bytes to 0 and return -EFAULT.
* Add to docs that the helper can only be used by sleepable BPF programs.
* Fix nits in selftests.
Changes since v4:
* Make `flags` into u64.
* Use `user_ptr` arg name to be consistent with `bpf_copy_from_user`.
* Add an extra check in selftests to verify access_process_vm calls
succeeded.
Changes since v3:
* Check if `flags` is 0 and return -EINVAL if not.
* Rebase on latest bpf-next branch and fix merge conflicts.
Changes since v2:
* Reorder arguments in `bpf_access_process_vm` to match existing related
bpf helpers (e.g. `bpf_probe_read_kernel`, `bpf_probe_read_user`,
`bpf_copy_from_user`).
* `flags` argument is provided for future extensibility and is not
currently used, and we always invoke `access_process_vm` with no flags.
* Merge bpf helper patch and `bpf_iter_run_prog` patch together for better
bisectability in case of failures.
* Clean up formatting and comments in selftests.
Changes since v1:
* Fixed "Invalid wait context" issue in `bpf_iter_run_prog` by using
`rcu_read_lock_trace()` for sleepable bpf iterator programs.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 11 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 1 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 20 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/bpf_iter_task.c | 54 |
4 files changed, 86 insertions, 0 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 16a7574292a5..4a2f7041ebae 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5076,6 +5076,16 @@ union bpf_attr { * associated to *xdp_md*, at *offset*. * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5269,6 +5279,7 @@ union bpf_attr { FN(xdp_get_buff_len), \ FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a8c750373ad5..57894f125df3 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -8612,6 +8612,7 @@ static const struct bpf_sec_def section_defs[] = { 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("iter.s/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index b84f859b1267..5142a7d130b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -138,6 +138,24 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_sleepable(void) +{ + struct bpf_iter_task *skel; + + skel = bpf_iter_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + return; + + do_dummy_read(skel->progs.dump_task_sleepable); + + ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0, + "num_expected_failure_copy_from_user_task"); + ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, + "num_success_copy_from_user_task"); + + bpf_iter_task__destroy(skel); +} + static void test_task_stack(void) { struct bpf_iter_task_stack *skel; @@ -1252,6 +1270,8 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_sleepable")) + test_task_sleepable(); if (test__start_subtest("task_stack")) test_task_stack(); if (test__start_subtest("task_file")) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index c86b93f33b32..d22741272692 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; @@ -23,3 +24,56 @@ int dump_task(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); return 0; } + +int num_expected_failure_copy_from_user_task = 0; +int num_success_copy_from_user_task = 0; + +SEC("iter.s/task") +int dump_task_sleepable(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static const char info[] = " === END ==="; + struct pt_regs *regs; + void *ptr; + uint32_t user_data = 0; + int ret; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + ++num_expected_failure_copy_from_user_task; + } else { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Try to read the contents of the task's instruction pointer from the + * remote task's address space. + */ + regs = (struct pt_regs *)bpf_task_pt_regs(task); + if (regs == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ptr = (void *)PT_REGS_IP(regs); + + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ++num_success_copy_from_user_task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid data\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data); + return 0; +} |