From 8b401f9ed2441ad9e219953927a842d24ed051fc Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:45 -0700 Subject: bpf: implement bpf_send_signal() helper This patch tries to solve the following specific use case. Currently, bpf program can already collect stack traces through kernel function get_perf_callchain() when certain events happens (e.g., cache miss counter or cpu clock counter overflows). But such stack traces are not enough for jitted programs, e.g., hhvm (jited php). To get real stack trace, jit engine internal data structures need to be traversed in order to get the real user functions. bpf program itself may not be the best place to traverse the jit engine as the traversing logic could be complex and it is not a stable interface either. Instead, hhvm implements a signal handler, e.g. for SIGALARM, and a set of program locations which it can dump stack traces. When it receives a signal, it will dump the stack in next such program location. Such a mechanism can be implemented in the following way: . a perf ring buffer is created between bpf program and tracing app. . once a particular event happens, bpf program writes to the ring buffer and the tracing app gets notified. . the tracing app sends a signal SIGALARM to the hhvm. But this method could have large delays and causing profiling results skewed. This patch implements bpf_send_signal() helper to send a signal to hhvm in real time, resulting in intended stack traces. Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 63e0cf66f01a..68d4470523a0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2672,6 +2672,20 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2782,7 +2796,8 @@ union bpf_attr { FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3-55-g7522 From c240eff63a1cf1c4edc768e0cfc374811c02f069 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 24 May 2019 23:25:16 +0100 Subject: bpf: introduce new bpf prog load flags "BPF_F_TEST_RND_HI32" x86_64 and AArch64 perhaps are two arches that running bpf testsuite frequently, however the zero extension insertion pass is not enabled for them because of their hardware support. It is critical to guarantee the pass correction as it is supposed to be enabled at default for a couple of other arches, for example PowerPC, SPARC, arm, NFP etc. Therefore, it would be very useful if there is a way to test this pass on for example x86_64. The test methodology employed by this set is "poisoning" useless bits. High 32-bit of a definition is randomized if it is identified as not used by any later insn. Such randomization is only enabled under testing mode which is gated by the new bpf prog load flags "BPF_F_TEST_RND_HI32". Suggested-by: Alexei Starovoitov Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ kernel/bpf/syscall.c | 4 +++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 68d4470523a0..7c6aef253173 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -260,6 +260,24 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) +/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ +#define BPF_F_TEST_RND_HI32 (1U << 2) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb5440b02e82..3d546b6f4646 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1604,7 +1604,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; - if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT)) + if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | + BPF_F_ANY_ALIGNMENT | + BPF_F_TEST_RND_HI32)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && -- cgit v1.2.3-55-g7522