From patchwork Fri Jan 12 10:10:50 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Masami Hiramatsu (Google)" X-Patchwork-Id: 13518199 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 81C705C8FE; Fri, 12 Jan 2024 10:10:57 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="CzhPqmYc" Received: by smtp.kernel.org (Postfix) with ESMTPSA id D885AC433C7; Fri, 12 Jan 2024 10:10:52 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1705054257; bh=zMCldC3g0if4jocUa7hXngCNMXtp+UiFT5i/S3qyfxU=; h=From:To:Cc:Subject:Date:From; b=CzhPqmYcyijuC6OkxKcjAEV54/ThoBtq93+JD03SpasKNxKZyIdXCYGfzusHi/emr oVQhPe0WZyVlmL5yDFNSb0jlhHHxOKHwa+lx9XbgprRivq75UuS8Q90Zpk6XC8sZOW +OQDgC8bKjFaensf/VBlVYpTybZdnX7VLBK6UXA5Mwdf0jHxj7Fx1AYvxk2mvOTpxD NnlJMi2oOKl8i42Lf6JJYNgrQf56tFYfPA4mXMtlIFrZWWtxy87DiURkdMhEo6Q0rA XQQ1LSxdA3LD3no8kavQx6nufBptxd5PpyZVVAqTFj01GIV18trVEkEQ5T3Kt8pHJh 0qofCsrSxNTSg== From: "Masami Hiramatsu (Google)" To: Alexei Starovoitov , Steven Rostedt , Florent Revest Cc: linux-trace-kernel@vger.kernel.org, LKML , Martin KaFai Lau , bpf , Sven Schnelle , Alexei Starovoitov , Jiri Olsa , Arnaldo Carvalho de Melo , Daniel Borkmann , Alan Maguire , Mark Rutland , Peter Zijlstra , Thomas Gleixner , Guo Ren Subject: [PATCH v6 00/36] tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph Date: Fri, 12 Jan 2024 19:10:50 +0900 Message-Id: <170505424954.459169.10630626365737237288.stgit@devnote2> X-Mailer: git-send-email 2.34.1 User-Agent: StGit/0.19 Precedence: bulk X-Mailing-List: linux-trace-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Hi, Here is the 6th version of the series to re-implement the fprobe on function-graph tracer. The previous version is; https://lore.kernel.org/all/170290509018.220107.1347127510564358608.stgit@devnote2/ This version fixes use-after-unregister bug and arm64 stack unwinding bug [13/36], add an improvement for multiple interrupts during push operation[20/36], keep SAVE_REGS until BPF and fprobe_event using ftrace_regs[26/36], also reorder the patches[30/36][31/36] so that new fprobe can switch to SAVE_ARGS[32/36] safely. This series also temporarily adds a DIRECT_CALLS bugfix[1/36], which should be pushed separatedly as a stable bugfix. There are some TODOs: - Add s390x and loongarch support to fprobe (multiple fgraph). - Fix to get the symbol address from ftrace entry address on arm64. (This should be done in BPF trace event) - Cleanup code, rename some terms(offset/index) and FGRAPH_TYPE_BITMAP part should be merged to FGRAPH_TYPE_ARRAY patch. Overview -------- This series does major 2 changes, enable multiple function-graphs on the ftrace (e.g. allow function-graph on sub instances) and rewrite the fprobe on this function-graph. The former changes had been sent from Steven Rostedt 4 years ago (*), which allows users to set different setting function-graph tracer (and other tracers based on function-graph) in each trace-instances at the same time. (*) https://lore.kernel.org/all/20190525031633.811342628@goodmis.org/ The purpose of latter change are; 1) Remove dependency of the rethook from fprobe so that we can reduce the return hook code and shadow stack. 2) Make 'ftrace_regs' the common trace interface for the function boundary. 1) Currently we have 2(or 3) different function return hook codes, the function-graph tracer and rethook (and legacy kretprobe). But since this is redundant and needs double maintenance cost, I would like to unify those. From the user's viewpoint, function- graph tracer is very useful to grasp the execution path. For this purpose, it is hard to use the rethook in the function-graph tracer, but the opposite is possible. (Strictly speaking, kretprobe can not use it because it requires 'pt_regs' for historical reasons.) 2) Now the fprobe provides the 'pt_regs' for its handler, but that is wrong for the function entry and exit. Moreover, depending on the architecture, there is no way to accurately reproduce 'pt_regs' outside of interrupt or exception handlers. This means fprobe should not use 'pt_regs' because it does not use such exceptions. (Conversely, kprobe should use 'pt_regs' because it is an abstract interface of the software breakpoint exception.) This series changes fprobe to use function-graph tracer for tracing function entry and exit, instead of mixture of ftrace and rethook. Unlike the rethook which is a per-task list of system-wide allocated nodes, the function graph's ret_stack is a per-task shadow stack. Thus it does not need to set 'nr_maxactive' (which is the number of pre-allocated nodes). Also the handlers will get the 'ftrace_regs' instead of 'pt_regs'. Since eBPF mulit_kprobe/multi_kretprobe events still use 'pt_regs' as their register interface, this changes it to convert 'ftrace_regs' to 'pt_regs'. Of course this conversion makes an incomplete 'pt_regs', so users must access only registers for function parameters or return value. Design ------ Instead of using ftrace's function entry hook directly, the new fprobe is built on top of the function-graph's entry and return callbacks with 'ftrace_regs'. Since the fprobe requires access to 'ftrace_regs', the architecture must support CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS, which enables to call function-graph entry callback with 'ftrace_regs', and also CONFIG_HAVE_FUNCTION_GRAPH_FREGS, which passes the ftrace_regs to return_to_handler. All fprobes share a single function-graph ops (means shares a common ftrace filter) similar to the kprobe-on-ftrace. This needs another layer to find corresponding fprobe in the common function-graph callbacks, but has much better scalability, since the number of registered function-graph ops is limited. In the entry callback, the fprobe runs its entry_handler and saves the address of 'fprobe' on the function-graph's shadow stack as data. The return callback decodes the data to get the 'fprobe' address, and runs the exit_handler. The fprobe introduces two hash-tables, one is for entry callback which searches fprobes related to the given function address passed by entry callback. The other is for a return callback which checks if the given 'fprobe' data structure pointer is still valid. Note that it is possible to unregister fprobe before the return callback runs. Thus the address validation must be done before using it in the return callback. This series can be applied against the v6.7 kernel. This series can also be found below branch. https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=topic/fprobe-on-fgraph Thank you, --- Masami Hiramatsu (Google) (21): ftrace: Fix DIRECT_CALLS to use SAVE_REGS by default tracing: Add a comment about ftrace_regs definition tracing: Rename ftrace_regs_return_value to ftrace_regs_get_return_value x86: tracing: Add ftrace_regs definition in the header function_graph: Use a simple LRU for fgraph_array index number function_graph: Improve push operation for several interrupts function_graph: Add a new entry handler with parent_ip and ftrace_regs function_graph: Add a new exit handler with parent_ip and ftrace_regs x86/ftrace: Enable HAVE_FUNCTION_GRAPH_FREGS arm64: ftrace: Enable HAVE_FUNCTION_GRAPH_FREGS fprobe: Use ftrace_regs in fprobe entry handler fprobe: Use ftrace_regs in fprobe exit handler tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs tracing: Add ftrace_fill_perf_regs() for perf event tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled fprobe: Rewrite fprobe on function-graph tracer tracing/fprobe: Remove nr_maxactive from fprobe selftests: ftrace: Remove obsolate maxactive syntax check selftests/ftrace: Add a test case for repeating register/unregister fprobe Documentation: probes: Update fprobe on function-graph tracer Steven Rostedt (VMware) (15): function_graph: Convert ret_stack to a series of longs fgraph: Use BUILD_BUG_ON() to make sure we have structures divisible by long function_graph: Add an array structure that will allow multiple callbacks function_graph: Allow multiple users to attach to function graph function_graph: Remove logic around ftrace_graph_entry and return ftrace/function_graph: Pass fgraph_ops to function graph callbacks ftrace: Allow function_graph tracer to be enabled in instances ftrace: Allow ftrace startup flags exist without dynamic ftrace function_graph: Have the instances use their own ftrace_ops for filtering function_graph: Add "task variables" per task for fgraph_ops function_graph: Move set_graph_function tests to shadow stack global var function_graph: Move graph depth stored data to shadow stack global var function_graph: Move graph notrace bit to shadow stack global var function_graph: Implement fgraph_reserve_data() and fgraph_retrieve_data() function_graph: Add selftest for passing local variables Documentation/trace/fprobe.rst | 42 + arch/arm64/Kconfig | 2 arch/arm64/include/asm/ftrace.h | 24 arch/arm64/kernel/entry-ftrace.S | 28 + arch/arm64/kernel/ftrace.c | 21 arch/loongarch/Kconfig | 1 arch/loongarch/include/asm/ftrace.h | 2 arch/loongarch/kernel/ftrace_dyn.c | 6 arch/powerpc/include/asm/ftrace.h | 9 arch/powerpc/kernel/trace/ftrace.c | 2 arch/powerpc/kernel/trace/ftrace_64_pg.c | 10 arch/s390/Kconfig | 1 arch/s390/include/asm/ftrace.h | 7 arch/x86/Kconfig | 4 arch/x86/include/asm/ftrace.h | 17 arch/x86/kernel/ftrace.c | 51 + arch/x86/kernel/ftrace_64.S | 37 + include/linux/fprobe.h | 58 + include/linux/ftrace.h | 167 +++ include/linux/sched.h | 3 include/linux/trace_recursion.h | 39 - kernel/trace/Kconfig | 19 kernel/trace/bpf_trace.c | 14 kernel/trace/fgraph.c | 1067 ++++++++++++++++---- kernel/trace/fprobe.c | 631 ++++++++---- kernel/trace/ftrace.c | 23 kernel/trace/ftrace_internal.h | 2 kernel/trace/trace.h | 94 +- kernel/trace/trace_fprobe.c | 114 +- kernel/trace/trace_functions.c | 8 kernel/trace/trace_functions_graph.c | 96 +- kernel/trace/trace_irqsoff.c | 10 kernel/trace/trace_probe_tmpl.h | 2 kernel/trace/trace_sched_wakeup.c | 10 kernel/trace/trace_selftest.c | 178 +++ lib/test_fprobe.c | 51 - samples/fprobe/fprobe_example.c | 4 .../test.d/dynevent/add_remove_fprobe_repeat.tc | 19 .../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 4 39 files changed, 2177 insertions(+), 700 deletions(-) create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc -- Masami Hiramatsu (Google)