Received: by 2002:a05:7412:419a:b0:f3:1519:9f41 with SMTP id i26csp3068796rdh; Mon, 27 Nov 2023 06:02:03 -0800 (PST) X-Google-Smtp-Source: AGHT+IE9m1d12drz/aME5OIe+67LRauqD2JzS998GB7GMYwCs3MJbDdxyzQlBbtP0afe4PxNYZPF X-Received: by 2002:a05:6808:2209:b0:3b8:5e54:b3c1 with SMTP id bd9-20020a056808220900b003b85e54b3c1mr3303784oib.27.1701093722886; Mon, 27 Nov 2023 06:02:02 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1701093722; cv=none; d=google.com; s=arc-20160816; b=YjoWCOh3BZuXlHnucs5v5Cf9d77nT9nfLjCAI6PKEQ9WoQmCRpGhfgsmg2jC/3WUKM iMgIcCeyNC34XotAERwX1rQ6/0CKQ7L85lvoKQkIUzrafwqrqxE16CGMbcMHStC72XbW ULT5RA/3ikwZDFYy+F0M0flOHq6VlcQB4Xc2bg1w6XrYYfXB5PjKYwuH1vhFarlQTbVP co8LNt4QPMErEYJgtRiUzUSo86xpYuBPKWDfs4kcpgI50QZba7adDVdbF1mWTMQRanps 8l28LG7utQIj9Q5eIr84IQyG+iBNJYgKguOgTbYLfoZuyVzvOStU4lGAtAUOjaLaw8rT 1eMg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=scIUeHglBht4jmg4BlZgY4goRZdBm2zZzH/NOq5U4Gs=; fh=SIgps5XdV0XNwjZfT2uAI7g3mrspDldK9Qs8qQAfoa4=; b=ImG/cW1LILJS2xtJ58WB3EnxxYk9WrFFNsukjuIkdHgN9Hpdvd7fupQAU+kJfGbFZl VaU03GCoyUhRjnltVnxBEoRND4kpPJroLZn8W313pHanLrB48Xn6NYXc5xjFYBFSAMOS j9sMuIhk0+FcLhTPP18LsLEobP/fxK0bCSUl8Pokf44GM7tA9LgPTkQ3DyLw8+JMTCJO 4n2RYfjTAyk0mwvF7SmKUBux6eXM5ILLNj149a7yTWkYcAm01ud0DGkhqyxoYeIsgxn+ C7KjAIQGFTqraw+3Ds7aj8ISqKdGz2aEYR+H+amCaeFhNvAGxa7q2yhRwgaRGHAvgjqL yohQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@kernel.org header.s=k20201202 header.b=B1tvLS6t; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=kernel.org Return-Path: Received: from fry.vger.email (fry.vger.email. [2620:137:e000::3:8]) by mx.google.com with ESMTPS id fu22-20020a0568082a7600b003b85c5813f7si1867891oib.295.2023.11.27.06.01.59 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 27 Nov 2023 06:02:02 -0800 (PST) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8; Authentication-Results: mx.google.com; dkim=pass header.i=@kernel.org header.s=k20201202 header.b=B1tvLS6t; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=kernel.org Received: from out1.vger.email (depot.vger.email [IPv6:2620:137:e000::3:0]) by fry.vger.email (Postfix) with ESMTP id 4DB8B8068132; Mon, 27 Nov 2023 06:01:54 -0800 (PST) X-Virus-Status: Clean X-Virus-Scanned: clamav-milter 0.103.11 at fry.vger.email Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233516AbjK0OBL (ORCPT + 99 others); Mon, 27 Nov 2023 09:01:11 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53988 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233614AbjK0N7C (ORCPT ); Mon, 27 Nov 2023 08:59:02 -0500 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7C357211E for ; Mon, 27 Nov 2023 05:56:31 -0800 (PST) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 285FDC433D9; Mon, 27 Nov 2023 13:56:26 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1701093391; bh=bEmKPtX4VZv4hW/cbKkJPMLtohKC5T+Wkpa4vqI+jos=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=B1tvLS6tXxcXoAmkiTRlCNz31Btw7dOkdmRJJbtaLc3BdJEkAalkPC2QYfqd/KvON k6dQotJjBDlznb8Jhn8cZwKWATdb9NrlRf12eYASmWIKJcqGgud72DBrKGTGhIM8c4 UYWtM5x84kQBMb9E6dg1njZBJqSChatXy678QXiCPABCPduItxojo2am30TMxLP+D6 KpkGJHJLqZuy5BFM/ABUNmLG+xxhmJgIzJ4MJMjHJ1OA2KCk2FhQM319/UNc/yyTXF QNm9KyJJtHj7JBPI9F1m/5tAg64ltdAaqVhdDT1KwQ8ECUfz+en7MCGtaQLVre/w3m rhdC3E/569svA== 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 v3 17/33] function_graph: Implement fgraph_reserve_data() and fgraph_retrieve_data() Date: Mon, 27 Nov 2023 22:56:24 +0900 Message-Id: <170109338411.343914.7434126754301624440.stgit@devnote2> X-Mailer: git-send-email 2.34.1 In-Reply-To: <170109317214.343914.4784420430328654397.stgit@devnote2> References: <170109317214.343914.4784420430328654397.stgit@devnote2> User-Agent: StGit/0.19 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-1.2 required=5.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=unavailable autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on fry.vger.email Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (fry.vger.email [0.0.0.0]); Mon, 27 Nov 2023 06:01:54 -0800 (PST) From: Steven Rostedt (VMware) Added functions that can be called by a fgraph_ops entryfunc and retfunc to store state between the entry of the function being traced to the exit of the same function. The fgraph_ops entryfunc() may call fgraph_reserve_data() to store up to 32 words onto the task's shadow ret_stack and this then can be retrieved by fgraph_retrieve_data() called by the corresponding retfunc(). Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Masami Hiramatsu (Google) --- Changes in v3: - Store fgraph_array index to the data entry. - Both function requires fgraph_array index to store/retrieve data. - Reserve correct size of the data. - Return correct data area. Changes in v2: - Retrieve the reserved size by fgraph_retrieve_data(). - Expand the maximum data size to 32 words. - Update stack index with __get_index(val) if FGRAPH_TYPE_ARRAY entry. - fix typos and make description lines shorter than 76 chars. --- include/linux/ftrace.h | 3 + kernel/trace/fgraph.c | 175 ++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 170 insertions(+), 8 deletions(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 09ca4bba63f2..1c121237016e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1075,6 +1075,9 @@ struct fgraph_ops { int idx; }; +void *fgraph_reserve_data(int idx, int size_bytes); +void *fgraph_retrieve_data(int idx, int *size_bytes); + /* * Stack of return addresses for functions * of a thread. diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index d1981fe8edf0..317202943936 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -41,17 +41,29 @@ * bits: 10 - 11 Type of storage * 0 - reserved * 1 - bitmap of fgraph_array index + * 2 - reserved data * * For bitmap of fgraph_array index * bits: 12 - 27 The bitmap of fgraph_ops fgraph_array index * + * For reserved data: + * bits: 12 - 17 The size in words that is stored + * bits: 18 - 23 The index of fgraph_array, which shows who is stored + * * That is, at the end of function_graph_enter, if the first and forth * fgraph_ops on the fgraph_array[] (index 0 and 3) needs their retfunc called - * on the return of the function being traced, this is what will be on the - * task's shadow ret_stack: (the stack grows upward) + * on the return of the function being traced, and the forth fgraph_ops + * stored two words of data, this is what will be on the task's shadow + * ret_stack: (the stack grows upward) * * | | <- task->curr_ret_stack * +--------------------------------------------+ + * | data_type(idx:3, size:2, | + * | offset:FGRAPH_RET_INDEX+3) | ( Data with size of 2 words) + * +--------------------------------------------+ ( It is 4 words from the ret_stack) + * | STORED DATA WORD 2 | + * | STORED DATA WORD 1 | + * +------i-------------------------------------+ * | bitmap_type(bitmap:(BIT(3)|BIT(0)), | * | offset:FGRAPH_RET_INDEX) | <- the offset is from here * +--------------------------------------------+ @@ -78,14 +90,23 @@ enum { FGRAPH_TYPE_RESERVED = 0, FGRAPH_TYPE_BITMAP = 1, + FGRAPH_TYPE_DATA = 2, }; #define FGRAPH_INDEX_SIZE 16 #define FGRAPH_INDEX_MASK GENMASK(FGRAPH_INDEX_SIZE - 1, 0) #define FGRAPH_INDEX_SHIFT (FGRAPH_TYPE_SHIFT + FGRAPH_TYPE_SIZE) -/* Currently the max stack index can't be more than register callers */ -#define FGRAPH_MAX_INDEX (FGRAPH_INDEX_SIZE + FGRAPH_RET_INDEX) +#define FGRAPH_DATA_SIZE 5 +#define FGRAPH_DATA_MASK ((1 << FGRAPH_DATA_SIZE) - 1) +#define FGRAPH_DATA_SHIFT (FGRAPH_TYPE_SHIFT + FGRAPH_TYPE_SIZE) + +#define FGRAPH_DATA_INDEX_SIZE 4 +#define FGRAPH_DATA_INDEX_MASK ((1 << FGRAPH_DATA_INDEX_SIZE) - 1) +#define FGRAPH_DATA_INDEX_SHIFT (FGRAPH_DATA_SHIFT + FGRAPH_DATA_SIZE) + +#define FGRAPH_MAX_INDEX \ + ((FGRAPH_INDEX_SIZE << FGRAPH_DATA_SIZE) + FGRAPH_RET_INDEX) #define FGRAPH_ARRAY_SIZE FGRAPH_INDEX_SIZE @@ -97,6 +118,8 @@ enum { #define RET_STACK(t, index) ((struct ftrace_ret_stack *)(&(t)->ret_stack[index])) +#define FGRAPH_MAX_DATA_SIZE (sizeof(long) * (1 << FGRAPH_DATA_SIZE)) + /* * Each fgraph_ops has a reservered unsigned long at the end (top) of the * ret_stack to store task specific state. @@ -111,14 +134,39 @@ static int fgraph_array_cnt; static struct fgraph_ops *fgraph_array[FGRAPH_ARRAY_SIZE]; +static inline int __get_index(unsigned long val) +{ + return val & FGRAPH_RET_INDEX_MASK; +} + +static inline int __get_type(unsigned long val) +{ + return (val >> FGRAPH_TYPE_SHIFT) & FGRAPH_TYPE_MASK; +} + +static inline int __get_data_index(unsigned long val) +{ + return (val >> FGRAPH_DATA_INDEX_SHIFT) & FGRAPH_DATA_INDEX_MASK; +} + +static inline int __get_data_size(unsigned long val) +{ + return (val >> FGRAPH_DATA_SHIFT) & FGRAPH_DATA_MASK; +} + +static inline unsigned long get_fgraph_entry(struct task_struct *t, int index) +{ + return t->ret_stack[index]; +} + static inline int get_ret_stack_index(struct task_struct *t, int offset) { - return t->ret_stack[offset] & FGRAPH_RET_INDEX_MASK; + return __get_index(t->ret_stack[offset]); } static inline int get_fgraph_type(struct task_struct *t, int offset) { - return (t->ret_stack[offset] >> FGRAPH_TYPE_SHIFT) & FGRAPH_TYPE_MASK; + return __get_type(t->ret_stack[offset]); } static inline unsigned long @@ -145,6 +193,22 @@ add_fgraph_index_bitmap(struct task_struct *t, int offset, unsigned long bitmap) t->ret_stack[offset] |= (bitmap << FGRAPH_INDEX_SHIFT); } +static inline void *get_fgraph_data(struct task_struct *t, int index) +{ + unsigned long val = t->ret_stack[index]; + + if (__get_type(val) != FGRAPH_TYPE_DATA) + return NULL; + index -= __get_data_size(val); + return (void *)&t->ret_stack[index]; +} + +static inline unsigned long make_fgraph_data(int idx, int size, int offset) +{ + return (idx << FGRAPH_DATA_INDEX_SHIFT) | (size << FGRAPH_DATA_SHIFT) | + (FGRAPH_TYPE_DATA << FGRAPH_TYPE_SHIFT) | offset; +} + /* ftrace_graph_entry set to this to tell some archs to run function graph */ static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops) { @@ -178,6 +242,92 @@ static void ret_stack_init_task_vars(unsigned long *ret_stack) memset(gvals, 0, sizeof(*gvals) * FGRAPH_ARRAY_SIZE); } +/** + * fgraph_reserve_data - Reserve storage on the task's ret_stack + * @idx: The index of fgraph_array + * @size_bytes: The size in bytes to reserve + * + * Reserves space of up to FGRAPH_MAX_DATA_SIZE bytes on the + * task's ret_stack shadow stack, for a given fgraph_ops during + * the entryfunc() call. If entryfunc() returns zero, the storage + * is discarded. An entryfunc() can only call this once per iteration. + * The fgraph_ops retfunc() can retrieve this stored data with + * fgraph_retrieve_data(). + * + * Returns: On success, a pointer to the data on the stack. + * Otherwise, NULL if there's not enough space left on the + * ret_stack for the data, or if fgraph_reserve_data() was called + * more than once for a single entryfunc() call. + */ +void *fgraph_reserve_data(int idx, int size_bytes) +{ + unsigned long val; + void *data; + int curr_ret_stack = current->curr_ret_stack; + int data_size; + + if (size_bytes > FGRAPH_MAX_DATA_SIZE) + return NULL; + + /* Convert to number of longs + data word */ + data_size = DIV_ROUND_UP(size_bytes, sizeof(long)); + + val = get_fgraph_entry(current, curr_ret_stack - 1); + data = ¤t->ret_stack[curr_ret_stack]; + + curr_ret_stack += data_size + 1; + if (unlikely(curr_ret_stack >= SHADOW_STACK_MAX_INDEX)) + return NULL; + + val = make_fgraph_data(idx, data_size, __get_index(val) + data_size + 1); + + /* Set the last word to be reserved */ + current->ret_stack[curr_ret_stack - 1] = val; + + /* Make sure interrupts see this */ + barrier(); + current->curr_ret_stack = curr_ret_stack; + /* Again sync with interrupts, and reset reserve */ + current->ret_stack[curr_ret_stack - 1] = val; + + return data; +} + +/** + * fgraph_retrieve_data - Retrieve stored data from fgraph_reserve_data() + * @idx: the index of fgraph_array (fgraph_ops::idx) + * @size_bytes: pointer to retrieved data size. + * + * This is to be called by a fgraph_ops retfunc(), to retrieve data that + * was stored by the fgraph_ops entryfunc() on the function entry. + * That is, this will retrieve the data that was reserved on the + * entry of the function that corresponds to the exit of the function + * that the fgraph_ops retfunc() is called on. + * + * Returns: The stored data from fgraph_reserve_data() called by the + * matching entryfunc() for the retfunc() this is called from. + * Or NULL if there was nothing stored. + */ +void *fgraph_retrieve_data(int idx, int *size_bytes) +{ + int index = current->curr_ret_stack - 1; + unsigned long val; + + val = get_fgraph_entry(current, index); + while (__get_type(val) == FGRAPH_TYPE_DATA) { + if (__get_data_index(val) == idx) + goto found; + index -= __get_data_size(val) + 1; + val = get_fgraph_entry(current, index); + } + return NULL; +found: + if (size_bytes) + *size_bytes = __get_data_size(val) * + sizeof(long); + return get_fgraph_data(current, index); +} + /** * fgraph_get_task_var - retrieve a task specific state variable * @gops: The ftrace_ops that owns the task specific variable @@ -424,13 +574,18 @@ int function_graph_enter(unsigned long ret, unsigned long func, for (i = 0; i < fgraph_array_cnt; i++) { struct fgraph_ops *gops = fgraph_array[i]; + int save_curr_ret_stack; if (gops == &fgraph_stub) continue; + save_curr_ret_stack = current->curr_ret_stack; if (ftrace_ops_test(&gops->ops, func, NULL) && gops->entryfunc(&trace, gops)) bitmap |= BIT(i); + else + /* Clear out any saved storage */ + current->curr_ret_stack = save_curr_ret_stack; } if (!bitmap) @@ -452,6 +607,7 @@ int function_graph_enter_ops(unsigned long ret, unsigned long func, struct fgraph_ops *gops) { struct ftrace_graph_ent trace; + int save_curr_ret_stack; int index; int type; @@ -468,13 +624,15 @@ int function_graph_enter_ops(unsigned long ret, unsigned long func, trace.func = func; trace.depth = current->curr_ret_depth; + save_curr_ret_stack = current->curr_ret_stack; if (gops->entryfunc(&trace, gops)) { if (type == FGRAPH_TYPE_RESERVED) set_fgraph_index_bitmap(current, index, BIT(gops->idx)); else add_fgraph_index_bitmap(current, index, BIT(gops->idx)); return 0; - } + } else + current->curr_ret_stack = save_curr_ret_stack; if (type == FGRAPH_TYPE_RESERVED) { current->curr_ret_stack -= FGRAPH_RET_INDEX + 1; @@ -619,7 +777,8 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs * curr_ret_stack is after that. */ barrier(); - current->curr_ret_stack -= FGRAPH_RET_INDEX + 1; + current->curr_ret_stack = index - FGRAPH_RET_INDEX; + current->curr_ret_depth--; return ret; }