Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751991AbcCGB6s (ORCPT ); Sun, 6 Mar 2016 20:58:48 -0500 Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:1157 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751236AbcCGB6j (ORCPT ); Sun, 6 Mar 2016 20:58:39 -0500 From: Alexei Starovoitov To: "David S . Miller" CC: Daniel Borkmann , Daniel Wagner , Tom Zanussi , Wang Nan , He Kuang , Martin KaFai Lau , Brendan Gregg , , , Subject: [PATCH net-next 0/9] bpf: hash map pre-alloc Date: Sun, 6 Mar 2016 17:58:28 -0800 Message-ID: <1457315917-1970307-1-git-send-email-ast@fb.com> X-Mailer: git-send-email 2.6.5 X-FB-Internal: Safe MIME-Version: 1.0 Content-Type: text/plain X-Proofpoint-Spam-Reason: safe X-FB-Internal: Safe X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2016-03-07_01:,, signatures=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3406 Lines: 78 Hi, this path set switches bpf hash map to use pre-allocation by default and introduces BPF_F_NO_PREALLOC flag to keep old behavior for cases where full map pre-allocation is too memory expensive. Some time back Daniel Wagner reported crashes when bpf hash map is used to compute time intervals between preempt_disable->preempt_enable and recently Tom Zanussi reported a dead lock in iovisor/bcc/funccount tool if it's used to count the number of invocations of kernel '*spin*' functions. Both problems are due to the recursive use of slub and can only be solved by pre-allocating all map elements. A lot of different solutions were considered. Many implemented, but at the end pre-allocation seems to be the only feasible answer. As far as pre-allocation goes it also was implemented 4 different ways: - simple free-list with single lock - percpu_ida with optimizations - blk-mq-tag variant customized for bpf use case - percpu_freelist For bpf style of alloc/free patterns percpu_freelist is the best and implemented in this patch set. Detailed performance numbers in patch 3. Patch 2 introduces percpu_freelist Patch 1 fixes simple deadlocks due to missing recursion checks Patches 4-7: prepare test infra Patch 8: stress test for hash map infra. It attaches to spin_lock functions and bpf_map_update/delete are called from different contexts (except nmi, which is unsupported by bpf still) Patch 9: map performance test Reported-by: Daniel Wagner Reported-by: Tom Zanussi Alexei Starovoitov (9): bpf: prevent kprobe+bpf deadlocks bpf: introduce percpu_freelist bpf: pre-allocate hash map elements samples/bpf: make map creation more verbose samples/bpf: move ksym_search() into library samples/bpf: add map_flags to bpf loader samples/bpf: test both pre-alloc and normal maps samples/bpf: add bpf map stress test samples/bpf: add map performance test include/linux/bpf.h | 4 + include/uapi/linux/bpf.h | 3 + kernel/bpf/Makefile | 2 +- kernel/bpf/hashtab.c | 264 ++++++++++++++++++++++++++++----------- kernel/bpf/percpu_freelist.c | 81 ++++++++++++ kernel/bpf/percpu_freelist.h | 31 +++++ kernel/bpf/syscall.c | 15 ++- kernel/trace/bpf_trace.c | 2 - samples/bpf/Makefile | 8 ++ samples/bpf/bpf_helpers.h | 1 + samples/bpf/bpf_load.c | 70 ++++++++++- samples/bpf/bpf_load.h | 6 + samples/bpf/fds_example.c | 2 +- samples/bpf/libbpf.c | 5 +- samples/bpf/libbpf.h | 2 +- samples/bpf/map_perf_test_kern.c | 100 +++++++++++++++ samples/bpf/map_perf_test_user.c | 155 +++++++++++++++++++++++ samples/bpf/offwaketime_user.c | 67 +--------- samples/bpf/sock_example.c | 2 +- samples/bpf/spintest_kern.c | 59 +++++++++ samples/bpf/spintest_user.c | 50 ++++++++ samples/bpf/test_maps.c | 29 +++-- samples/bpf/test_verifier.c | 4 +- 23 files changed, 802 insertions(+), 160 deletions(-) create mode 100644 kernel/bpf/percpu_freelist.c create mode 100644 kernel/bpf/percpu_freelist.h create mode 100644 samples/bpf/map_perf_test_kern.c create mode 100644 samples/bpf/map_perf_test_user.c create mode 100644 samples/bpf/spintest_kern.c create mode 100644 samples/bpf/spintest_user.c -- 2.6.5