From patchwork Wed Jul 5 18:12:43 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302583 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 878BCC001DF for ; Wed, 5 Jul 2023 18:17:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233363AbjGESRQ (ORCPT ); Wed, 5 Jul 2023 14:17:16 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43602 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231913AbjGESRO (ORCPT ); Wed, 5 Jul 2023 14:17:14 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7170F1993 for ; Wed, 5 Jul 2023 11:15:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688580951; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=cr2h91iK1BhRzl41+qr9b8AIAdoW4uuXRZNrsLrfkns=; b=D03arb0VUq+IKd2+0zIjSGXczU8xicqva5koEyrs/4XMtdVrnlWWf60qMtTXoutca84FeW z0bQHqmtL9z++sq5R1auswYGNB5sOLzR5F68Myoi0/cxwQ5bdrTk3davXr35ivViLGLhV6 NQSnWnizYK9zBz/duOdpef1fI7YcA9g= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-638-Nhv5uZDOOuONs0L1KaIvxQ-1; Wed, 05 Jul 2023 14:15:46 -0400 X-MC-Unique: Nhv5uZDOOuONs0L1KaIvxQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 5FD79800C7F; Wed, 5 Jul 2023 18:15:44 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 0565A18EB4; Wed, 5 Jul 2023 18:15:37 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 01/14] tracing/filters: Dynamically allocate filter_pred.regex Date: Wed, 5 Jul 2023 19:12:43 +0100 Message-Id: <20230705181256.3539027-2-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Every predicate allocation includes a MAX_FILTER_STR_VAL (256) char array in the regex field, even if the predicate function does not use the field. A later commit will introduce a dynamically allocated cpumask to struct filter_pred, which will require a dedicated freeing function. Bite the bullet and make filter_pred.regex dynamically allocated. While at it, reorder the fields of filter_pred to fill in the byte holes. The struct now fits on a single cacheline. No change in behaviour intended. The kfree()'s were patched via Coccinelle: @@ struct filter_pred *pred; @@ -kfree(pred); +free_predicate(pred); Signed-off-by: Valentin Schneider --- kernel/trace/trace_events_filter.c | 62 ++++++++++++++++++------------ 1 file changed, 37 insertions(+), 25 deletions(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 1dad64267878c..d999a218fe833 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -70,15 +70,15 @@ enum filter_pred_fn { }; struct filter_pred { - enum filter_pred_fn fn_num; - u64 val; - u64 val2; - struct regex regex; + struct regex *regex; unsigned short *ops; struct ftrace_event_field *field; - int offset; + u64 val; + u64 val2; + enum filter_pred_fn fn_num; + int offset; int not; - int op; + int op; }; /* @@ -186,6 +186,12 @@ enum { PROCESS_OR = 4, }; +static void free_predicate(struct filter_pred *pred) +{ + kfree(pred->regex); + kfree(pred); +} + /* * Without going into a formal proof, this explains the method that is used in * parsing the logical expressions. @@ -623,7 +629,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, kfree(inverts); if (prog_stack) { for (i = 0; prog_stack[i].pred; i++) - kfree(prog_stack[i].pred); + free_predicate(prog_stack[i].pred); kfree(prog_stack); } return ERR_PTR(ret); @@ -750,7 +756,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event) char *addr = (char *)(event + pred->offset); int cmp, match; - cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len); + cmp = pred->regex->match(addr, pred->regex, pred->regex->field_len); match = cmp ^ pred->not; @@ -763,7 +769,7 @@ static __always_inline int filter_pchar(struct filter_pred *pred, char *str) int len; len = strlen(str) + 1; /* including tailing '\0' */ - cmp = pred->regex.match(str, &pred->regex, len); + cmp = pred->regex->match(str, pred->regex, len); match = cmp ^ pred->not; @@ -813,7 +819,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event) char *addr = (char *)(event + str_loc); int cmp, match; - cmp = pred->regex.match(addr, &pred->regex, str_len); + cmp = pred->regex->match(addr, pred->regex, str_len); match = cmp ^ pred->not; @@ -836,7 +842,7 @@ static int filter_pred_strrelloc(struct filter_pred *pred, void *event) char *addr = (char *)(&item[1]) + str_loc; int cmp, match; - cmp = pred->regex.match(addr, &pred->regex, str_len); + cmp = pred->regex->match(addr, pred->regex, str_len); match = cmp ^ pred->not; @@ -874,7 +880,7 @@ static int filter_pred_comm(struct filter_pred *pred, void *event) { int cmp; - cmp = pred->regex.match(current->comm, &pred->regex, + cmp = pred->regex->match(current->comm, pred->regex, TASK_COMM_LEN); return cmp ^ pred->not; } @@ -1004,7 +1010,7 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) static void filter_build_regex(struct filter_pred *pred) { - struct regex *r = &pred->regex; + struct regex *r = pred->regex; char *search; enum regex_type type = MATCH_FULL; @@ -1169,7 +1175,7 @@ static void free_prog(struct event_filter *filter) return; for (i = 0; prog[i].pred; i++) - kfree(prog[i].pred); + free_predicate(prog[i].pred); kfree(prog); } @@ -1553,9 +1559,12 @@ static int parse_pred(const char *str, void *data, goto err_free; } - pred->regex.len = len; - strncpy(pred->regex.pattern, str + s, len); - pred->regex.pattern[len] = 0; + pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL); + if (!pred->regex) + goto err_mem; + pred->regex->len = len; + strncpy(pred->regex->pattern, str + s, len); + pred->regex->pattern[len] = 0; /* This is either a string, or an integer */ } else if (str[i] == '\'' || str[i] == '"') { @@ -1597,9 +1606,12 @@ static int parse_pred(const char *str, void *data, goto err_free; } - pred->regex.len = len; - strncpy(pred->regex.pattern, str + s, len); - pred->regex.pattern[len] = 0; + pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL); + if (!pred->regex) + goto err_mem; + pred->regex->len = len; + strncpy(pred->regex->pattern, str + s, len); + pred->regex->pattern[len] = 0; filter_build_regex(pred); @@ -1608,7 +1620,7 @@ static int parse_pred(const char *str, void *data, } else if (field->filter_type == FILTER_STATIC_STRING) { pred->fn_num = FILTER_PRED_FN_STRING; - pred->regex.field_len = field->size; + pred->regex->field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) { pred->fn_num = FILTER_PRED_FN_STRLOC; @@ -1691,10 +1703,10 @@ static int parse_pred(const char *str, void *data, return i; err_free: - kfree(pred); + free_predicate(pred); return -EINVAL; err_mem: - kfree(pred); + free_predicate(pred); return -ENOMEM; } @@ -2287,8 +2299,8 @@ static int ftrace_function_set_filter_pred(struct filter_pred *pred, return ret; return __ftrace_function_set_filter(pred->op == OP_EQ, - pred->regex.pattern, - pred->regex.len, + pred->regex->pattern, + pred->regex->len, data); } From patchwork Wed Jul 5 18:12:44 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302582 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id DAA1FC0015E for ; Wed, 5 Jul 2023 18:17:11 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232559AbjGESRL (ORCPT ); Wed, 5 Jul 2023 14:17:11 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43610 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231913AbjGESRJ (ORCPT ); Wed, 5 Jul 2023 14:17:09 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7F7CC199D for ; Wed, 5 Jul 2023 11:15:55 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688580954; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=EWVIdw42kvaUEVB9fypVLDqQXfw7FfQjjY+1yjJwfjg=; b=HFhTOT+r+GQeFrzbb0zqhfox+JBCL6PNXvs3+SSI4nPqujjetenok20IFOwtlJ00tjloJF Ka38ddbWTY5BMHNkzLZm6IIQanYQtHn/WyA0b4WwAe/jOzhu32YLEJEIW3QzOkb9KncfqT Ot1zskqerMHrL7rUZy4il8yWlX+Jq/0= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-615-gN3SJfgUNXa5eGtNW0oHxQ-1; Wed, 05 Jul 2023 14:15:51 -0400 X-MC-Unique: gN3SJfgUNXa5eGtNW0oHxQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 87DBC2808E6A; Wed, 5 Jul 2023 18:15:49 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 8CD04F5CFA; Wed, 5 Jul 2023 18:15:44 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 02/14] tracing/filters: Enable filtering a cpumask field by another cpumask Date: Wed, 5 Jul 2023 19:12:44 +0100 Message-Id: <20230705181256.3539027-3-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org The recently introduced ipi_send_cpumask trace event contains a cpumask field, but it currently cannot be used in filter expressions. Make event filtering aware of cpumask fields, and allow these to be filtered by a user-provided cpumask. The user-provided cpumask is to be given in cpulist format and wrapped as: "MASK{$cpulist}". The use of curly braces instead of parentheses is to prevent predicate_parse() from parsing the contents of MASK{...} as a full-fledged predicate subexpression. This enables e.g.: $ trace-cmd record -e 'ipi_send_cpumask' -f 'cpu & MASK{2,4,6,8-32}' Signed-off-by: Valentin Schneider --- include/linux/trace_events.h | 1 + kernel/trace/trace_events_filter.c | 85 +++++++++++++++++++++++++++++- 2 files changed, 84 insertions(+), 2 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7c4a0b72334eb..974ef37a06c83 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -804,6 +804,7 @@ enum { FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_CPUMASK, FILTER_COMM, FILTER_CPU, FILTER_STACKTRACE, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index d999a218fe833..8af00caa363f7 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -64,6 +64,7 @@ enum filter_pred_fn { FILTER_PRED_FN_PCHAR_USER, FILTER_PRED_FN_PCHAR, FILTER_PRED_FN_CPU, + FILTER_PRED_FN_CPUMASK, FILTER_PRED_FN_FUNCTION, FILTER_PRED_FN_, FILTER_PRED_TEST_VISITED, @@ -71,6 +72,7 @@ enum filter_pred_fn { struct filter_pred { struct regex *regex; + struct cpumask *mask; unsigned short *ops; struct ftrace_event_field *field; u64 val; @@ -94,6 +96,8 @@ struct filter_pred { C(TOO_MANY_OPEN, "Too many '('"), \ C(TOO_MANY_CLOSE, "Too few '('"), \ C(MISSING_QUOTE, "Missing matching quote"), \ + C(MISSING_BRACE_OPEN, "Missing '{'"), \ + C(MISSING_BRACE_CLOSE, "Missing '}'"), \ C(OPERAND_TOO_LONG, "Operand too long"), \ C(EXPECT_STRING, "Expecting string field"), \ C(EXPECT_DIGIT, "Expecting numeric field"), \ @@ -103,6 +107,7 @@ struct filter_pred { C(BAD_SUBSYS_FILTER, "Couldn't find or set field in one of a subsystem's events"), \ C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \ C(INVALID_FILTER, "Meaningless filter expression"), \ + C(INVALID_CPULIST, "Invalid cpulist"), \ C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \ C(NO_FUNCTION, "Function not found"), \ @@ -189,6 +194,7 @@ enum { static void free_predicate(struct filter_pred *pred) { kfree(pred->regex); + kfree(pred->mask); kfree(pred); } @@ -875,6 +881,26 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event) } } +/* Filter predicate for cpumasks. */ +static int filter_pred_cpumask(struct filter_pred *pred, void *event) +{ + u32 item = *(u32 *)(event + pred->offset); + int loc = item & 0xffff; + const struct cpumask *mask = (event + loc); + const struct cpumask *cmp = pred->mask; + + switch (pred->op) { + case OP_EQ: + return cpumask_equal(mask, cmp); + case OP_NE: + return !cpumask_equal(mask, cmp); + case OP_BAND: + return cpumask_intersects(mask, cmp); + default: + return 0; + } +} + /* Filter predicate for COMM. */ static int filter_pred_comm(struct filter_pred *pred, void *event) { @@ -1242,8 +1268,12 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir, int filter_assign_type(const char *type) { - if (strstr(type, "__data_loc") && strstr(type, "char")) - return FILTER_DYN_STRING; + if (strstr(type, "__data_loc")) { + if (strstr(type, "char")) + return FILTER_DYN_STRING; + if (strstr(type, "cpumask_t")) + return FILTER_CPUMASK; + } if (strstr(type, "__rel_loc") && strstr(type, "char")) return FILTER_RDYN_STRING; @@ -1355,6 +1385,8 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event) return filter_pred_pchar(pred, event); case FILTER_PRED_FN_CPU: return filter_pred_cpu(pred, event); + case FILTER_PRED_FN_CPUMASK: + return filter_pred_cpumask(pred, event); case FILTER_PRED_FN_FUNCTION: return filter_pred_function(pred, event); case FILTER_PRED_TEST_VISITED: @@ -1566,6 +1598,55 @@ static int parse_pred(const char *str, void *data, strncpy(pred->regex->pattern, str + s, len); pred->regex->pattern[len] = 0; + } else if (!strncmp(str + i, "MASK", 4)) { + unsigned int maskstart; + char *tmp; + + if (field->filter_type != FILTER_CPUMASK) { + parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); + goto err_free; + } + + /* Skip MASK */ + i += 4; + if (str[i++] != '{') { + parse_error(pe, FILT_ERR_MISSING_BRACE_OPEN, pos + i); + goto err_free; + } + maskstart = i; + + /* Walk the cpulist until closing } */ + for (; str[i] && str[i] != '}'; i++); + if (str[i] != '}') { + parse_error(pe, FILT_ERR_MISSING_BRACE_CLOSE, pos + i); + goto err_free; + } + + if (maskstart == i) { + parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i); + goto err_free; + } + + /* Copy the cpulist between { and } */ + tmp = kmalloc(i - maskstart + 1, GFP_KERNEL); + strncpy(tmp, str + maskstart, i - maskstart); + tmp[i - maskstart] = '\0'; + + pred->mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!pred->mask) + goto err_mem; + + /* Now parse it */ + if (cpulist_parse(tmp, pred->mask)) { + parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i); + goto err_free; + } + + /* Move along */ + i++; + if (field->filter_type == FILTER_CPUMASK) + pred->fn_num = FILTER_PRED_FN_CPUMASK; + /* This is either a string, or an integer */ } else if (str[i] == '\'' || str[i] == '"') { char q = str[i]; From patchwork Wed Jul 5 18:12:45 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302584 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 011C9C001E0 for ; Wed, 5 Jul 2023 18:17:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231776AbjGESRV (ORCPT ); Wed, 5 Jul 2023 14:17:21 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43450 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233374AbjGESRS (ORCPT ); Wed, 5 Jul 2023 14:17:18 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 54D6E19A6 for ; Wed, 5 Jul 2023 11:16:01 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688580960; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=BTFUs8gxr9moRkZBUGlN4k/3c1CssODo/4E7AM+Boo0=; b=GfMTPF/Cfwf/3te7Jr2UlHrhSdKVEW6XQQEdIe24hCb1/q+T3pq2ClGsS5G1AlJZ3pLyUg 3WnAAqtklf4XHG1VxvYPECWdUrAd7wBXV0BaAuu0I004Btr1uWrnfbkqzoMaP5CrzVfqDF kPrj5RzejCd/arMjSurM3aO2luSrlSg= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-187-6Xa3y2PROnCrrdM8iKBVQA-1; Wed, 05 Jul 2023 14:15:56 -0400 X-MC-Unique: 6Xa3y2PROnCrrdM8iKBVQA-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 9D2EE185A78F; Wed, 5 Jul 2023 18:15:54 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id D149AF5CFA; Wed, 5 Jul 2023 18:15:49 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 03/14] tracing/filters: Enable filtering a scalar field by a cpumask Date: Wed, 5 Jul 2023 19:12:45 +0100 Message-Id: <20230705181256.3539027-4-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Several events use a scalar field to denote a CPU: o sched_wakeup.target_cpu o sched_migrate_task.orig_cpu,dest_cpu o sched_move_numa.src_cpu,dst_cpu o ipi_send_cpu.cpu o ... Filtering these currently requires using arithmetic comparison functions, which can be tedious when dealing with interleaved SMT or NUMA CPU ids. Allow these to be filtered by a user-provided cpumask, which enables e.g.: $ trace-cmd record -e 'sched_wakeup' -f 'target_cpu & MASK{2,4,6,8-32}' Signed-off-by: Valentin Schneider --- NOTE: I went with an implicit cpumask conversion of the event field, as AFAICT predicate_parse() does not support parsing the application of a function to a field (e.g. 'MASK(target_cpu) & MASK{2,4,6,8-32}') --- kernel/trace/trace_events_filter.c | 92 ++++++++++++++++++++++++++---- 1 file changed, 80 insertions(+), 12 deletions(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 8af00caa363f7..99e111c237a93 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -46,15 +46,19 @@ static const char * ops[] = { OPS }; enum filter_pred_fn { FILTER_PRED_FN_NOP, FILTER_PRED_FN_64, + FILTER_PRED_FN_64_CPUMASK, FILTER_PRED_FN_S64, FILTER_PRED_FN_U64, FILTER_PRED_FN_32, + FILTER_PRED_FN_32_CPUMASK, FILTER_PRED_FN_S32, FILTER_PRED_FN_U32, FILTER_PRED_FN_16, + FILTER_PRED_FN_16_CPUMASK, FILTER_PRED_FN_S16, FILTER_PRED_FN_U16, FILTER_PRED_FN_8, + FILTER_PRED_FN_8_CPUMASK, FILTER_PRED_FN_S8, FILTER_PRED_FN_U8, FILTER_PRED_FN_COMM, @@ -641,6 +645,37 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, return ERR_PTR(ret); } +static inline int +do_filter_cpumask(int op, const struct cpumask *mask, const struct cpumask *cmp) +{ + switch (op) { + case OP_EQ: + return cpumask_equal(mask, cmp); + case OP_NE: + return !cpumask_equal(mask, cmp); + case OP_BAND: + return cpumask_intersects(mask, cmp); + default: + return 0; + } +} + +/* Optimisation of do_filter_cpumask() for scalar values */ +static inline int +do_filter_cpumask_scalar(int op, unsigned int cpu, const struct cpumask *mask) +{ + switch (op) { + case OP_EQ: + return cpumask_equal(mask, cpumask_of(cpu)); + case OP_NE: + return !cpumask_equal(mask, cpumask_of(cpu)); + case OP_BAND: + return cpumask_test_cpu(cpu, mask); + default: + return 0; + } +} + enum pred_cmp_types { PRED_CMP_TYPE_NOP, PRED_CMP_TYPE_LT, @@ -684,6 +719,18 @@ static int filter_pred_##type(struct filter_pred *pred, void *event) \ } \ } +#define DEFINE_CPUMASK_COMPARISON_PRED(size) \ +static int filter_pred_##size##_cpumask(struct filter_pred *pred, void *event) \ +{ \ + u##size *addr = (u##size *)(event + pred->offset); \ + unsigned int cpu = *addr; \ + \ + if (cpu >= nr_cpu_ids) \ + return 0; \ + \ + return do_filter_cpumask_scalar(pred->op, cpu, pred->mask); \ +} + #define DEFINE_EQUALITY_PRED(size) \ static int filter_pred_##size(struct filter_pred *pred, void *event) \ { \ @@ -705,6 +752,11 @@ DEFINE_COMPARISON_PRED(u16); DEFINE_COMPARISON_PRED(s8); DEFINE_COMPARISON_PRED(u8); +DEFINE_CPUMASK_COMPARISON_PRED(64); +DEFINE_CPUMASK_COMPARISON_PRED(32); +DEFINE_CPUMASK_COMPARISON_PRED(16); +DEFINE_CPUMASK_COMPARISON_PRED(8); + DEFINE_EQUALITY_PRED(64); DEFINE_EQUALITY_PRED(32); DEFINE_EQUALITY_PRED(16); @@ -889,16 +941,7 @@ static int filter_pred_cpumask(struct filter_pred *pred, void *event) const struct cpumask *mask = (event + loc); const struct cpumask *cmp = pred->mask; - switch (pred->op) { - case OP_EQ: - return cpumask_equal(mask, cmp); - case OP_NE: - return !cpumask_equal(mask, cmp); - case OP_BAND: - return cpumask_intersects(mask, cmp); - default: - return 0; - } + return do_filter_cpumask(pred->op, mask, cmp); } /* Filter predicate for COMM. */ @@ -1349,24 +1392,32 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event) switch (pred->fn_num) { case FILTER_PRED_FN_64: return filter_pred_64(pred, event); + case FILTER_PRED_FN_64_CPUMASK: + return filter_pred_64_cpumask(pred, event); case FILTER_PRED_FN_S64: return filter_pred_s64(pred, event); case FILTER_PRED_FN_U64: return filter_pred_u64(pred, event); case FILTER_PRED_FN_32: return filter_pred_32(pred, event); + case FILTER_PRED_FN_32_CPUMASK: + return filter_pred_32_cpumask(pred, event); case FILTER_PRED_FN_S32: return filter_pred_s32(pred, event); case FILTER_PRED_FN_U32: return filter_pred_u32(pred, event); case FILTER_PRED_FN_16: return filter_pred_16(pred, event); + case FILTER_PRED_FN_16_CPUMASK: + return filter_pred_16_cpumask(pred, event); case FILTER_PRED_FN_S16: return filter_pred_s16(pred, event); case FILTER_PRED_FN_U16: return filter_pred_u16(pred, event); case FILTER_PRED_FN_8: return filter_pred_8(pred, event); + case FILTER_PRED_FN_8_CPUMASK: + return filter_pred_8_cpumask(pred, event); case FILTER_PRED_FN_S8: return filter_pred_s8(pred, event); case FILTER_PRED_FN_U8: @@ -1602,7 +1653,8 @@ static int parse_pred(const char *str, void *data, unsigned int maskstart; char *tmp; - if (field->filter_type != FILTER_CPUMASK) { + if (field->filter_type != FILTER_CPUMASK && + field->filter_type != FILTER_OTHER) { parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); goto err_free; } @@ -1644,8 +1696,24 @@ static int parse_pred(const char *str, void *data, /* Move along */ i++; - if (field->filter_type == FILTER_CPUMASK) + if (field->filter_type == FILTER_CPUMASK) { pred->fn_num = FILTER_PRED_FN_CPUMASK; + } else { + switch (field->size) { + case 8: + pred->fn_num = FILTER_PRED_FN_64_CPUMASK; + break; + case 4: + pred->fn_num = FILTER_PRED_FN_32_CPUMASK; + break; + case 2: + pred->fn_num = FILTER_PRED_FN_16_CPUMASK; + break; + case 1: + pred->fn_num = FILTER_PRED_FN_8_CPUMASK; + break; + } + } /* This is either a string, or an integer */ } else if (str[i] == '\'' || str[i] == '"') { From patchwork Wed Jul 5 18:12:46 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302585 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id EE0CEEB64DA for ; Wed, 5 Jul 2023 18:17:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233386AbjGESRc (ORCPT ); Wed, 5 Jul 2023 14:17:32 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43680 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233369AbjGESRY (ORCPT ); Wed, 5 Jul 2023 14:17:24 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 712B119AA for ; Wed, 5 Jul 2023 11:16:33 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688580992; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=HhCGDFDeE6330wjTb7+eVdOM5sDQ6eAc/Pd0Q124xLM=; b=R22xN/+ZjDdd6LFmggPVPoP0GFJ7q0Dgy60RnkUmijJXWwAX1fX+gd+3n5TdA4OEJ79BJZ ydZrUnafahdqN0JOxR7201Bt7FpsePnx1W049AN/k/0KNqJl2qY1uQPUj8OTtl+hEsV+iV MkPcbO2RDHrcTuz6iaMb9ZM9fDqlooc= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-630-9fom_J9fNdKBOQiCT3xrlw-1; Wed, 05 Jul 2023 14:16:26 -0400 X-MC-Unique: 9fom_J9fNdKBOQiCT3xrlw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 930C32808E6D; Wed, 5 Jul 2023 18:16:24 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id E602BF5CFB; Wed, 5 Jul 2023 18:15:54 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 04/14] tracing/filters: Enable filtering the CPU common field by a cpumask Date: Wed, 5 Jul 2023 19:12:46 +0100 Message-Id: <20230705181256.3539027-5-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org The tracing_cpumask lets us specify which CPUs are traced in a buffer instance, but doesn't let us do this on a per-event basis (unless one creates an instance per event). A previous commit added filtering scalar fields by a user-given cpumask, make this work with the CPU common field as well. This enables doing things like $ trace-cmd record -e 'sched_switch' -f 'CPU & MASK{12-52}' \ -e 'sched_wakeup' -f 'target_cpu & MASK{12-52}' Signed-off-by: Valentin Schneider --- kernel/trace/trace_events_filter.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 99e111c237a93..b3d2612d4670a 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -68,6 +68,7 @@ enum filter_pred_fn { FILTER_PRED_FN_PCHAR_USER, FILTER_PRED_FN_PCHAR, FILTER_PRED_FN_CPU, + FILTER_PRED_FN_CPU_CPUMASK, FILTER_PRED_FN_CPUMASK, FILTER_PRED_FN_FUNCTION, FILTER_PRED_FN_, @@ -933,6 +934,13 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event) } } +static int filter_pred_cpu_cpumask(struct filter_pred *pred, void *event) +{ + int cpu = raw_smp_processor_id(); + + return do_filter_cpumask_scalar(pred->op, cpu, pred->mask); +} + /* Filter predicate for cpumasks. */ static int filter_pred_cpumask(struct filter_pred *pred, void *event) { @@ -1436,6 +1444,8 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event) return filter_pred_pchar(pred, event); case FILTER_PRED_FN_CPU: return filter_pred_cpu(pred, event); + case FILTER_PRED_FN_CPU_CPUMASK: + return filter_pred_cpu_cpumask(pred, event); case FILTER_PRED_FN_CPUMASK: return filter_pred_cpumask(pred, event); case FILTER_PRED_FN_FUNCTION: @@ -1654,6 +1664,7 @@ static int parse_pred(const char *str, void *data, char *tmp; if (field->filter_type != FILTER_CPUMASK && + field->filter_type != FILTER_CPU && field->filter_type != FILTER_OTHER) { parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); goto err_free; @@ -1698,6 +1709,8 @@ static int parse_pred(const char *str, void *data, i++; if (field->filter_type == FILTER_CPUMASK) { pred->fn_num = FILTER_PRED_FN_CPUMASK; + } else if (field->filter_type == FILTER_CPU) { + pred->fn_num = FILTER_PRED_FN_CPU_CPUMASK; } else { switch (field->size) { case 8: From patchwork Wed Jul 5 18:12:47 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302586 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5C5B9EB64DD for ; Wed, 5 Jul 2023 18:17:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233414AbjGESRe (ORCPT ); Wed, 5 Jul 2023 14:17:34 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43738 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233383AbjGESRZ (ORCPT ); Wed, 5 Jul 2023 14:17:25 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 14CDA19AC for ; Wed, 5 Jul 2023 11:16:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688580997; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=snCuxFAiT0B/bnlHGtaiRqsJwVD+zCZujmUlSZJWpwM=; b=UJkwww8ur6I4iuG2kCGKEz4cbwcHxGRUYs6bPJ+ImI1j+s+jmvhTRnMtJaYO61/WCuGrlw Y2sWB6hCNbdMu2kaH1kRTe1blC57bC8MVzQ9+f5qPxKJHfL6K4uBZ+ZBHXWYbDYq0gSmkG 0CpqcZsITjnHXTb+wx31uKObUjMGDRE= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-668-hNYP9ME2PT2zK_PDEefSuQ-1; Wed, 05 Jul 2023 14:16:33 -0400 X-MC-Unique: hNYP9ME2PT2zK_PDEefSuQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 1D8FE3815EF2; Wed, 5 Jul 2023 18:16:31 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id CDDF218EB4; Wed, 5 Jul 2023 18:16:24 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 05/14] tracing/filters: Document cpumask filtering Date: Wed, 5 Jul 2023 19:12:47 +0100 Message-Id: <20230705181256.3539027-6-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Cpumask, scalar and CPU fields can now be filtered by a user-provided cpumask, document the syntax. Signed-off-by: Valentin Schneider --- Documentation/trace/events.rst | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst index f5fcb8e1218f6..e9bc9f23891a0 100644 --- a/Documentation/trace/events.rst +++ b/Documentation/trace/events.rst @@ -219,6 +219,20 @@ the function "security_prepare_creds" and less than the end of that function. The ".function" postfix can only be attached to values of size long, and can only be compared with "==" or "!=". +Cpumask fields or scalar fields that encode a CPU number can be filtered using +a user-provided cpumask in cpulist format. The format is as follows:: + + MASK{$cpulist} + +Operators available to cpumask filtering are: + +& (intersection), ==, != + +For example, this will filter events that have their .target_cpu field present +in the given cpumask:: + + target_cpu & MASK{17-42} + 5.2 Setting filters ------------------- From patchwork Wed Jul 5 18:12:48 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302587 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 709B5C001E0 for ; Wed, 5 Jul 2023 18:18:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233403AbjGESSA (ORCPT ); Wed, 5 Jul 2023 14:18:00 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43856 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231750AbjGESRh (ORCPT ); Wed, 5 Jul 2023 14:17:37 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5B8B319B2 for ; Wed, 5 Jul 2023 11:16:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581003; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=touy8a7//BeI9DXwQuTy3DIG1jDKoaRDRv3dbDYYd7A=; b=b9DQOT9sO4BglFGoKZtX5Zr+FmagkTK6xMmB4k+gu6+Uuv5oMXW5H9xctHwERUENqVgidC j5moN4uj2h44GcoK6/MfR51bBmetMaFiauOWEyrYUJulfoC0I+aTPgb4d2kGaIibocFGUJ 29bqD2kwf1FLqkshmMpnldanSeRimH0= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-281-rTU3Fnz6O_mjXhT8Or3jrg-1; Wed, 05 Jul 2023 14:16:38 -0400 X-MC-Unique: rTU3Fnz6O_mjXhT8Or3jrg-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 6BA218037BA; Wed, 5 Jul 2023 18:16:36 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 508F218EB4; Wed, 5 Jul 2023 18:16:31 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 06/14] objtool: Flesh out warning related to pv_ops[] calls Date: Wed, 5 Jul 2023 19:12:48 +0100 Message-Id: <20230705181256.3539027-7-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org I had to look into objtool itself to understand what this warning was about; make it more explicit. Signed-off-by: Valentin Schneider --- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 0fcf99c914000..fe62232f218f9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3404,7 +3404,7 @@ static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) { if (!target->sec->noinstr) { - WARN("pv_ops[%d]: %s", idx, target->name); + WARN("pv_ops[%d]: indirect call to %s() leaves .noinstr.text section", idx, target->name); file->pv_ops[idx].clean = false; } } From patchwork Wed Jul 5 18:12:49 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302588 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3EE86EB64DA for ; Wed, 5 Jul 2023 18:18:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233428AbjGESSC (ORCPT ); Wed, 5 Jul 2023 14:18:02 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43956 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232265AbjGESRr (ORCPT ); Wed, 5 Jul 2023 14:17:47 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C1D531731 for ; Wed, 5 Jul 2023 11:16:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581009; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=J8rXW514UBch39kVc1ygiPYqeRYBiljQKIWLWtG0jLw=; b=iUBwR4gU01hJGczrgZMoE6bIoLmoqbpg6gQtTHGuIbn9mVRAvzKdjBYhI60uoGZVACSnFX bFovQ4lk7gjoGkg+hMrdaP0+P+9lNuQAfLBqjF4+mYCQzIqWDwvpA3tC4+gjKzstxj10qK XFQ007/9WC61i/asA1O64tGDuI3BgLw= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-101-9oeIA5OgNLqp_60MHHVNcQ-1; Wed, 05 Jul 2023 14:16:43 -0400 X-MC-Unique: 9oeIA5OgNLqp_60MHHVNcQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id A8779810BB4; Wed, 5 Jul 2023 18:16:41 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id A081B18EB4; Wed, 5 Jul 2023 18:16:36 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Josh Poimboeuf , Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 07/14] objtool: Warn about non __ro_after_init static key usage in .noinstr Date: Wed, 5 Jul 2023 19:12:49 +0100 Message-Id: <20230705181256.3539027-8-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Later commits will depend on having no runtime-mutable text in early entry code. (ab)use the .noinstr section as a marker of early entry code and warn about static keys used in it that can be flipped at runtime. Suggested-by: Josh Poimboeuf Signed-off-by: Valentin Schneider --- tools/objtool/check.c | 20 ++++++++++++++++++++ tools/objtool/include/objtool/check.h | 1 + tools/objtool/include/objtool/special.h | 2 ++ tools/objtool/special.c | 3 +++ 4 files changed, 26 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index fe62232f218f9..7f8d210ec88c3 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2032,6 +2032,9 @@ static int add_special_section_alts(struct objtool_file *file) alt->next = orig_insn->alts; orig_insn->alts = alt; + if (special_alt->key_sym) + orig_insn->key_sym = special_alt->key_sym; + list_del(&special_alt->list); free(special_alt); } @@ -3520,6 +3523,20 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct return 0; } +static int validate_static_key(struct instruction *insn, struct insn_state *state) +{ + if (state->noinstr && state->instr <= 0) { + if ((strcmp(insn->key_sym->sec->name, ".data..ro_after_init"))) { + WARN_INSN(insn, + "Non __ro_after_init static key \"%s\" in .noinstr section", + insn->key_sym->name); + return 1; + } + } + + return 0; +} + static struct instruction *next_insn_to_validate(struct objtool_file *file, struct instruction *insn) { @@ -3670,6 +3687,9 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (handle_insn_ops(insn, next_insn, &state)) return 1; + if (insn->key_sym) + validate_static_key(insn, &state); + switch (insn->type) { case INSN_RETURN: diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index daa46f1f0965a..35dd21f8f41e1 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -77,6 +77,7 @@ struct instruction { struct symbol *sym; struct stack_op *stack_ops; struct cfi_state *cfi; + struct symbol *key_sym; }; static inline struct symbol *insn_func(struct instruction *insn) diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h index 86d4af9c5aa9d..0e61f34fe3a28 100644 --- a/tools/objtool/include/objtool/special.h +++ b/tools/objtool/include/objtool/special.h @@ -27,6 +27,8 @@ struct special_alt { struct section *new_sec; unsigned long new_off; + struct symbol *key_sym; + unsigned int orig_len, new_len; /* group only */ }; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index baa85c31526b3..830e6abf173a2 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -127,6 +127,9 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, return -1; } alt->key_addend = key_reloc->addend; + + reloc_to_sec_off(key_reloc, &sec, &offset); + alt->key_sym = find_symbol_by_offset(sec, offset & ~2); } return 0; From patchwork Wed Jul 5 18:12:50 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302589 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8387CEB64DA for ; Wed, 5 Jul 2023 18:18:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233446AbjGESSE (ORCPT ); Wed, 5 Jul 2023 14:18:04 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44364 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233445AbjGESRv (ORCPT ); Wed, 5 Jul 2023 14:17:51 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 978341BC6 for ; Wed, 5 Jul 2023 11:16:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581011; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Rmsxmag8ZkUExVz48NdRE4bjGysGk4VVErYcJqwPIM4=; b=AWK8d7z6mFMHw6US9ILqBYMeW/P9cE/bg421dFsnNLLYfHpPyR41npMqIZdhrx/oK8NH3j ZDJ8n3scitJulg2jApL5wOF9zJBcOuUWVNoKdfRH76gxW1DEUyYvCX4RpjWP/hFwFQRcxG tycUwOyjZC0gu+d/R57CvGtX6ZuqPvE= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-534-K-_lME6ZNbOFxO4KCoVoVw-1; Wed, 05 Jul 2023 14:16:49 -0400 X-MC-Unique: K-_lME6ZNbOFxO4KCoVoVw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 980F53815EF4; Wed, 5 Jul 2023 18:16:46 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id D5B65F5CFA; Wed, 5 Jul 2023 18:16:41 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 08/14] BROKEN: context_tracking: Make context_tracking_key __ro_after_init Date: Wed, 5 Jul 2023 19:12:50 +0100 Message-Id: <20230705181256.3539027-9-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org objtool now warns about it: vmlinux.o: warning: objtool: enter_from_user_mode+0x4e: Non __ro_after_init static key "context_tracking_key" in .noinstr section vmlinux.o: warning: objtool: enter_from_user_mode+0x50: Non __ro_after_init static key "context_tracking_key" in .noinstr section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x60: Non __ro_after_init static key "context_tracking_key" in .noinstr section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x62: Non __ro_after_init static key "context_tracking_key" in .noinstr section [...] The key can only be enabled (and not disabled) in the __init function ct_cpu_tracker_user(), so mark it as __ro_after_init. BROKEN: the struct static_key lives in a read-only mapping after mark_rodata_ro(), which falls apart when the KVM module is loaded after init and a write to the struct happens due to e.g. guest_state_exit_irqoff() relying on the static key: jump_label_add_module() `\ static_key_set_mod() static_key_set_linked() Signed-off-by: Valentin Schneider --- kernel/context_tracking.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index a09f1c19336ae..4e6cb14272fcb 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -432,7 +432,7 @@ static __always_inline void ct_kernel_enter(bool user, int offset) { } #define CREATE_TRACE_POINTS #include -DEFINE_STATIC_KEY_FALSE(context_tracking_key); +DEFINE_STATIC_KEY_FALSE_RO(context_tracking_key); EXPORT_SYMBOL_GPL(context_tracking_key); static noinstr bool context_tracking_recursion_enter(void) From patchwork Wed Jul 5 18:12:51 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302590 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6E2F0EB64DA for ; Wed, 5 Jul 2023 18:18:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232948AbjGESSR (ORCPT ); Wed, 5 Jul 2023 14:18:17 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43602 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233461AbjGESSH (ORCPT ); Wed, 5 Jul 2023 14:18:07 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EAE881732 for ; Wed, 5 Jul 2023 11:17:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581020; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=izi9UHkrSeZ4AHa49u6aA8W9HneeYs8L2V/Y70LmMpM=; b=BdrUwoZ/VBLjw/GxOuMrejCZHkr2EzEinFQKdum3zVSboixfe4H3EeFaiqsgQo+0Q9VhDk wLvx9fQzq60PCuvHb4J5/VmpuumdensVDfJOZ3p8HRRxtEVujQRMHwr3UJCZsWXmSVNLkN S67SdDGmS97cWA4OskGqtB14HmH/was= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-197-m-BHSRQXMT2rSYl1-eA5hQ-1; Wed, 05 Jul 2023 14:16:54 -0400 X-MC-Unique: m-BHSRQXMT2rSYl1-eA5hQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id B7B9F3815EF2; Wed, 5 Jul 2023 18:16:52 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id D1D60F5CFA; Wed, 5 Jul 2023 18:16:46 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 09/14] x86/kvm: Make kvm_async_pf_enabled __ro_after_init Date: Wed, 5 Jul 2023 19:12:51 +0100 Message-Id: <20230705181256.3539027-10-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org objtool now warns about it: vmlinux.o: warning: objtool: exc_page_fault+0x2a: Non __ro_after_init static key "kvm_async_pf_enabled" in .noinstr section The key can only be enabled (and not disabled) in the __init function kvm_guest_init(), so mark it as __ro_after_init. Signed-off-by: Valentin Schneider --- arch/x86/kernel/kvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1cceac5984daa..319460090a836 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -44,7 +44,7 @@ #include #include -DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); +DEFINE_STATIC_KEY_FALSE_RO(kvm_async_pf_enabled); static int kvmapf = 1; From patchwork Wed Jul 5 18:12:52 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302591 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 873A6EB64DA for ; Wed, 5 Jul 2023 18:18:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233513AbjGESS1 (ORCPT ); Wed, 5 Jul 2023 14:18:27 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43652 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233475AbjGESSL (ORCPT ); Wed, 5 Jul 2023 14:18:11 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 2C55E173F for ; Wed, 5 Jul 2023 11:17:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581022; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=QCdKg/xbfvFvfuEOm23BNeuog3oDcFdsQXIARij7I9Y=; b=K9s9wXO/tpOk9RQuuO9ysZ+jlgrY6U7yt0MSwxSqQn7qvWBCxEMZkeBmZX89iA63PnUDMJ X0phXmReSW0CyjOZrgj/hAs7pyjkMihQN2aCn/scj9LV/ZCMal2q7Lyi3Pq627YlhrtvxD y1M9DbF08tSL/vVRMuVFENFsyVB53q8= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-108-UhoNqooBN1GAazRibK82Gg-1; Wed, 05 Jul 2023 14:16:59 -0400 X-MC-Unique: UhoNqooBN1GAazRibK82Gg-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id E89FD3C108C9; Wed, 5 Jul 2023 18:16:57 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id E7BEE18EB4; Wed, 5 Jul 2023 18:16:52 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 10/14] x86/sev-es: Make sev_es_enable_key __ro_after_init Date: Wed, 5 Jul 2023 19:12:52 +0100 Message-Id: <20230705181256.3539027-11-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org objtool now warns about it: vmlinux.o: warning: objtool: exc_nmi+0xbf: Non __ro_after_init static key "sev_es_enable_key" in .noinstr section vmlinux.o: warning: objtool: exc_nmi+0x4d: Non __ro_after_init static key "sev_es_enable_key" in .noinstr section vmlinux.o: warning: objtool: exc_nmi+0xc: Non __ro_after_init static key "sev_es_enable_key" in .noinstr section The key can only be enabled (and not disabled) in the __init function sev_es_init_vc_handling(), so mark it as __ro_after_init. Signed-off-by: Valentin Schneider --- arch/x86/kernel/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index b031244d6d2df..4178e18383232 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -113,7 +113,7 @@ struct ghcb_state { }; static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); -DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); +DEFINE_STATIC_KEY_FALSE_RO(sev_es_enable_key); static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); From patchwork Wed Jul 5 18:12:53 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302592 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AD3DBEB64DA for ; Wed, 5 Jul 2023 18:18:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233168AbjGESSi (ORCPT ); Wed, 5 Jul 2023 14:18:38 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44814 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232096AbjGESSX (ORCPT ); Wed, 5 Jul 2023 14:18:23 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 220C21BDF for ; Wed, 5 Jul 2023 11:17:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581027; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=C/ucjOAEaHS5XCwJ7CRYxNKU/jQaRurVwoCVOxjEFxI=; b=doHzIz5vR47Xf9CIejudGcE01BiZCnGhpNJNAR/2YeImA+FDuyrUkME6Y4V6VtoOWCKfev T1mVqRUtCVQ41+t5KEGKwu0wr5punMiJXA/DStBf5Uy9To7idBVlyLUWztzlCxZJKg1hur ixgD4y7qA6OujgA7b0p1BibXKbfrVd8= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-550-LTvzUOljPxOE1cOXn7g4IA-1; Wed, 05 Jul 2023 14:17:05 -0400 X-MC-Unique: LTvzUOljPxOE1cOXn7g4IA-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 5994C881B28; Wed, 5 Jul 2023 18:17:03 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 26F1E18EB4; Wed, 5 Jul 2023 18:16:58 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Nicolas Saenz Julienne , Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 11/14] context-tracking: Introduce work deferral infrastructure Date: Wed, 5 Jul 2023 19:12:53 +0100 Message-Id: <20230705181256.3539027-12-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org smp_call_function() & friends have the unfortunate habit of sending IPIs to isolated, NOHZ_FULL, in-userspace CPUs, as they blindly target all online CPUs. Some callsites can be bent into doing the right, such as done by commit: cc9e303c91f5 ("x86/cpu: Disable frequency requests via aperfmperf IPI for nohz_full CPUs") Unfortunately, not all SMP callbacks can be omitted in this fashion. However, some of them only affect execution in kernelspace, which means they don't have to be executed *immediately* if the target CPU is in userspace: stashing the callback and executing it upon the next kernel entry would suffice. x86 kernel instruction patching or kernel TLB invalidation are prime examples of it. Add a field in struct context_tracking used as a bitmask to track deferred callbacks to execute upon kernel entry. The LSB of that field is used as a flag to prevent queueing deferred work when the CPU leaves userspace. Later commits introduce the bit:callback mappings. Note: A previous approach by PeterZ [1] used an extra bit in context_tracking.state to flag the presence of deferred callbacks to execute, and the actual callbacks were stored in a separate atomic variable. This meant that the atomic read of context_tracking.state was sufficient to determine whether there are any deferred callbacks to execute. Unfortunately, it presents a race window. Consider the work setting function as: preempt_disable(); seq = atomic_read(&ct->seq); if (__context_tracking_seq_in_user(seq)) { /* ctrl-dep */ atomic_or(work, &ct->work); ret = atomic_try_cmpxchg(&ct->seq, &seq, seq|CT_SEQ_WORK); } preempt_enable(); return ret; Then the following can happen: CPUx CPUy CT_SEQ_WORK \in context_tracking.state atomic_or(WORK_N, &ct->work); ct_kernel_enter() ct_state_inc(); atomic_try_cmpxchg(&ct->seq, &seq, seq|CT_SEQ_WORK); The cmpxchg() would fail, ultimately causing an IPI for WORK_N to be sent. Unfortunately, the work bit would remain set, and it can't be sanely cleared in case another CPU set it concurrently - this would ultimately lead to a double execution of the callback, one as a deferred callback and one in the IPI. As not all IPI callbacks are idempotent, this is undesirable. Link: https://lore.kernel.org/all/20210929151723.162004989@infradead.org/ Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Valentin Schneider --- arch/Kconfig | 9 +++ arch/x86/Kconfig | 1 + arch/x86/include/asm/context_tracking_work.h | 14 +++++ include/linux/context_tracking.h | 1 + include/linux/context_tracking_state.h | 1 + include/linux/context_tracking_work.h | 28 +++++++++ kernel/context_tracking.c | 63 ++++++++++++++++++++ kernel/time/Kconfig | 5 ++ 8 files changed, 122 insertions(+) create mode 100644 arch/x86/include/asm/context_tracking_work.h create mode 100644 include/linux/context_tracking_work.h diff --git a/arch/Kconfig b/arch/Kconfig index 205fd23e0cada..e453e9fb864be 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -851,6 +851,15 @@ config HAVE_CONTEXT_TRACKING_USER_OFFSTACK - No use of instrumentation, unless instrumentation_begin() got called. +config HAVE_CONTEXT_TRACKING_WORK + bool + help + Architecture supports deferring work while not in kernel context. + This is especially useful on setups with isolated CPUs that might + want to avoid being interrupted to perform housekeeping tasks (for + ex. TLB invalidation or icache invalidation). The housekeeping + operations are performed upon re-entering the kernel. + config HAVE_TIF_NOHZ bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 53bab123a8ee4..490c773105c0c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -197,6 +197,7 @@ config X86 select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING_USER if X86_64 select HAVE_CONTEXT_TRACKING_USER_OFFSTACK if HAVE_CONTEXT_TRACKING_USER + select HAVE_CONTEXT_TRACKING_WORK if X86_64 select HAVE_C_RECORDMCOUNT select HAVE_OBJTOOL_MCOUNT if HAVE_OBJTOOL select HAVE_OBJTOOL_NOP_MCOUNT if HAVE_OBJTOOL_MCOUNT diff --git a/arch/x86/include/asm/context_tracking_work.h b/arch/x86/include/asm/context_tracking_work.h new file mode 100644 index 0000000000000..5bc29e6b2ed38 --- /dev/null +++ b/arch/x86/include/asm/context_tracking_work.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CONTEXT_TRACKING_WORK_H +#define _ASM_X86_CONTEXT_TRACKING_WORK_H + +static __always_inline void arch_context_tracking_work(int work) +{ + switch (work) { + case CONTEXT_WORK_n: + // Do work... + break; + } +} + +#endif diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d3cbb6c16babf..80d571ddfc3a4 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index fdd537ea513ff..5af06ed26f858 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -36,6 +36,7 @@ struct context_tracking { int recursion; #endif #ifdef CONFIG_CONTEXT_TRACKING + atomic_t work; atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE diff --git a/include/linux/context_tracking_work.h b/include/linux/context_tracking_work.h new file mode 100644 index 0000000000000..0b06c3dab58c7 --- /dev/null +++ b/include/linux/context_tracking_work.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CONTEXT_TRACKING_WORK_H +#define _LINUX_CONTEXT_TRACKING_WORK_H + +#include + +enum { + CONTEXT_WORK_DISABLED_OFFSET, + CONTEXT_WORK_n_OFFSET, + CONTEXT_WORK_MAX_OFFSET +}; + +enum ct_work { + CONTEXT_WORK_DISABLED = BIT(CONTEXT_WORK_DISABLED_OFFSET), + CONTEXT_WORK_n = BIT(CONTEXT_WORK_n_OFFSET), + CONTEXT_WORK_MAX = BIT(CONTEXT_WORK_MAX_OFFSET) +}; + +#include + +#ifdef CONFIG_CONTEXT_TRACKING_WORK +extern bool ct_set_cpu_work(unsigned int cpu, unsigned int work); +#else +static inline bool +ct_set_cpu_work(unsigned int cpu, unsigned int work) { return false; } +#endif + +#endif diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 4e6cb14272fcb..b6aee3d0c0528 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -32,6 +32,9 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, #endif .state = ATOMIC_INIT(RCU_DYNTICKS_IDX), +#ifdef CONFIG_CONTEXT_TRACKING_WORK + .work = ATOMIC_INIT(CONTEXT_WORK_DISABLED), +#endif }; EXPORT_SYMBOL_GPL(context_tracking); @@ -72,6 +75,57 @@ static __always_inline void rcu_dynticks_task_trace_exit(void) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } +#ifdef CONFIG_CONTEXT_TRACKING_WORK +static __always_inline unsigned int ct_work_fetch(struct context_tracking *ct) +{ + return arch_atomic_fetch_or(CONTEXT_WORK_DISABLED, &ct->work); +} +static __always_inline void ct_work_clear(struct context_tracking *ct) +{ + arch_atomic_set(&ct->work, 0); +} + +static noinstr void ct_work_flush(unsigned long work) +{ + int bit; + + /* DISABLED is never set while there are deferred works */ + WARN_ON_ONCE(work & CONTEXT_WORK_DISABLED); + + /* + * arch_context_tracking_work() must be noinstr, non-blocking, + * and NMI safe. + */ + for_each_set_bit(bit, &work, CONTEXT_WORK_MAX) + arch_context_tracking_work(BIT(bit)); +} + +bool ct_set_cpu_work(unsigned int cpu, unsigned int work) +{ + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); + unsigned int old_work; + bool ret = false; + + preempt_disable(); + + old_work = atomic_read(&ct->work); + /* + * Try setting the work until either + * - the target CPU no longer accepts any more deferred work + * - the work has been set + */ + while (!(old_work & CONTEXT_WORK_DISABLED) && !ret) + ret = atomic_try_cmpxchg(&ct->work, &old_work, old_work | work); + + preempt_enable(); + return ret; +} +#else +static __always_inline void ct_work_flush(unsigned long work) { } +static __always_inline unsigned int ct_work_fetch(struct context_tracking *ct) { return 0; } +static __always_inline void ct_work_clear(struct context_tracking *ct) { } +#endif + /* * Record entry into an extended quiescent state. This is only to be * called when not already in an extended quiescent state, that is, @@ -89,6 +143,10 @@ static noinstr void ct_kernel_exit_state(int offset) */ rcu_dynticks_task_trace_enter(); // Before ->dynticks update! seq = ct_state_inc(offset); + + /* Let this CPU allow deferred callbacks again */ + ct_work_clear(this_cpu_ptr(&context_tracking)); + // RCU is no longer watching. Better be in extended quiescent state! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICKS_IDX)); } @@ -100,14 +158,19 @@ static noinstr void ct_kernel_exit_state(int offset) */ static noinstr void ct_kernel_enter_state(int offset) { + struct context_tracking *ct = this_cpu_ptr(&context_tracking); int seq; + unsigned int work; + work = ct_work_fetch(ct); /* * CPUs seeing atomic_add_return() must see prior idle sojourns, * and we also must force ordering with the next RCU read-side * critical section. */ seq = ct_state_inc(offset); + if (work) + ct_work_flush(work); // RCU is now watching. Better not be in an extended quiescent state! rcu_dynticks_task_trace_exit(); // After ->dynticks update! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICKS_IDX)); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index bae8f11070bef..fdb266f2d774b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -181,6 +181,11 @@ config CONTEXT_TRACKING_USER_FORCE Say N otherwise, this option brings an overhead that you don't want in production. +config CONTEXT_TRACKING_WORK + bool + depends on HAVE_CONTEXT_TRACKING_WORK && CONTEXT_TRACKING_USER + default y + config NO_HZ bool "Old Idle dynticks config" help From patchwork Wed Jul 5 18:12:54 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302593 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id EE2EDEB64DD for ; Wed, 5 Jul 2023 18:18:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233527AbjGESSm (ORCPT ); Wed, 5 Jul 2023 14:18:42 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:45006 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233418AbjGESS1 (ORCPT ); Wed, 5 Jul 2023 14:18:27 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 77E081993 for ; Wed, 5 Jul 2023 11:17:16 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581035; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=BI0V1APYLLZg+y9tuxzi74MUjtHjkVAo7OmZFgUYdFQ=; b=HbTfJ342CQmYq9Q6x2j3WTun1VKpe7uPza1lSRf0aQ1kwTDQ9wqR3YHvB3Y9whnTdWBLRr E3RGfH4NkCHl3chKkZ++20WSSOwIycfSzWeOWm5+oWcruJLuSRyHiRS0AQt/TLI4dfkTGo fWK8YmLTF4zwC45tIWdcVeJcSIiYQRc= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-654--O94TDN7PcGOu2Irqnh9Aw-1; Wed, 05 Jul 2023 14:17:11 -0400 X-MC-Unique: -O94TDN7PcGOu2Irqnh9Aw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 9A18E856F67; Wed, 5 Jul 2023 18:17:08 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 8918B18EB4; Wed, 5 Jul 2023 18:17:03 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Peter Zijlstra , Nicolas Saenz Julienne , Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 12/14] context_tracking,x86: Defer kernel text patching IPIs Date: Wed, 5 Jul 2023 19:12:54 +0100 Message-Id: <20230705181256.3539027-13-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org text_poke_bp_batch() sends IPIs to all online CPUs to synchronize them vs the newly patched instruction. CPUs that are executing in userspace do not need this synchronization to happen immediately, and this is actually harmful interference for NOHZ_FULL CPUs. As the synchronization IPIs are sent using a blocking call, returning from text_poke_bp_batch() implies all CPUs will observe the patched instruction(s), and this should be preserved even if the IPI is deferred. In other words, to safely defer this synchronization, any kernel instruction leading to the execution of the deferred instruction sync (ct_work_flush()) must *not* be mutable (patchable) at runtime. This means we must pay attention to mutable instructions in the early entry code: - alternatives - static keys - all sorts of probes (kprobes/ftrace/bpf/???) The early entry code leading to ct_work_flush() is noinstr, which gets rid of the probes. Alternatives are safe, because it's boot-time patching (before SMP is even brought up) which is before any IPI deferral can happen. This leaves us with static keys. Any static key used in early entry code should be only forever-enabled at boot time, IOW __ro_after_init (pretty much like alternatives). Objtool is now able to point at static keys that don't respect this, and all static keys used in early entry code have now been verified as behaving like so. Leverage the new context_tracking infrastructure to defer sync_core() IPIs to a target CPU's next kernel entry. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Valentin Schneider --- arch/x86/include/asm/context_tracking_work.h | 6 +++-- arch/x86/include/asm/text-patching.h | 1 + arch/x86/kernel/alternative.c | 24 ++++++++++++++++---- arch/x86/kernel/kprobes/core.c | 4 ++-- arch/x86/kernel/kprobes/opt.c | 4 ++-- arch/x86/kernel/module.c | 2 +- include/linux/context_tracking_work.h | 4 ++-- 7 files changed, 32 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/context_tracking_work.h b/arch/x86/include/asm/context_tracking_work.h index 5bc29e6b2ed38..2c66687ce00e2 100644 --- a/arch/x86/include/asm/context_tracking_work.h +++ b/arch/x86/include/asm/context_tracking_work.h @@ -2,11 +2,13 @@ #ifndef _ASM_X86_CONTEXT_TRACKING_WORK_H #define _ASM_X86_CONTEXT_TRACKING_WORK_H +#include + static __always_inline void arch_context_tracking_work(int work) { switch (work) { - case CONTEXT_WORK_n: - // Do work... + case CONTEXT_WORK_SYNC: + sync_core(); break; } } diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 29832c338cdc5..b6939e965e69d 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -43,6 +43,7 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); */ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void text_poke_sync(void); +extern void text_poke_sync_deferrable(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern void *text_poke_copy(void *addr, const void *opcode, size_t len); extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f615e0cb6d932..7770aef2204f3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1765,9 +1766,24 @@ static void do_sync_core(void *info) sync_core(); } +static bool do_sync_core_defer_cond(int cpu, void *info) +{ + return !ct_set_cpu_work(cpu, CONTEXT_WORK_SYNC); +} + +static void __text_poke_sync(smp_cond_func_t cond_func) +{ + on_each_cpu_cond(cond_func, do_sync_core, NULL, 1); +} + void text_poke_sync(void) { - on_each_cpu(do_sync_core, NULL, 1); + __text_poke_sync(NULL); +} + +void text_poke_sync_deferrable(void) +{ + __text_poke_sync(do_sync_core_defer_cond); } /* @@ -1967,7 +1983,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE); } - text_poke_sync(); + text_poke_sync_deferrable(); /* * Second step: update all but the first byte of the patched range. @@ -2029,7 +2045,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * not necessary and we'd be safe even without it. But * better safe than sorry (plus there's not only Intel). */ - text_poke_sync(); + text_poke_sync_deferrable(); } /* @@ -2050,7 +2066,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries } if (do_sync) - text_poke_sync(); + text_poke_sync_deferrable(); /* * Remove and wait for refs to be zero. diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f7f6042eb7e6c..a38c914753397 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -735,7 +735,7 @@ void arch_arm_kprobe(struct kprobe *p) u8 int3 = INT3_INSN_OPCODE; text_poke(p->addr, &int3, 1); - text_poke_sync(); + text_poke_sync_deferrable(); perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1); } @@ -745,7 +745,7 @@ void arch_disarm_kprobe(struct kprobe *p) perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1); text_poke(p->addr, &p->opcode, 1); - text_poke_sync(); + text_poke_sync_deferrable(); } void arch_remove_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 57b0037d0a996..88451a744ceda 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -521,11 +521,11 @@ void arch_unoptimize_kprobe(struct optimized_kprobe *op) JMP32_INSN_SIZE - INT3_INSN_SIZE); text_poke(addr, new, INT3_INSN_SIZE); - text_poke_sync(); + text_poke_sync_deferrable(); text_poke(addr + INT3_INSN_SIZE, new + INT3_INSN_SIZE, JMP32_INSN_SIZE - INT3_INSN_SIZE); - text_poke_sync(); + text_poke_sync_deferrable(); perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b05f62ee2344b..8b4542dc51b6d 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -242,7 +242,7 @@ static int write_relocate_add(Elf64_Shdr *sechdrs, write, apply); if (!early) { - text_poke_sync(); + text_poke_sync_deferrable(); mutex_unlock(&text_mutex); } diff --git a/include/linux/context_tracking_work.h b/include/linux/context_tracking_work.h index 0b06c3dab58c7..b0c7463048b60 100644 --- a/include/linux/context_tracking_work.h +++ b/include/linux/context_tracking_work.h @@ -6,13 +6,13 @@ enum { CONTEXT_WORK_DISABLED_OFFSET, - CONTEXT_WORK_n_OFFSET, + CONTEXT_WORK_SYNC_OFFSET, CONTEXT_WORK_MAX_OFFSET }; enum ct_work { CONTEXT_WORK_DISABLED = BIT(CONTEXT_WORK_DISABLED_OFFSET), - CONTEXT_WORK_n = BIT(CONTEXT_WORK_n_OFFSET), + CONTEXT_WORK_SYNC = BIT(CONTEXT_WORK_SYNC_OFFSET), CONTEXT_WORK_MAX = BIT(CONTEXT_WORK_MAX_OFFSET) }; From patchwork Wed Jul 5 18:12:55 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302594 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0155AC04A6A for ; Wed, 5 Jul 2023 18:19:27 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233465AbjGEST0 (ORCPT ); Wed, 5 Jul 2023 14:19:26 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:45306 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233383AbjGESSj (ORCPT ); Wed, 5 Jul 2023 14:18:39 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3E8A31BFD for ; Wed, 5 Jul 2023 11:17:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581041; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=O0XyYRqaKclSpF/kJo4Izh2sg6d7OQ7Oy14ALgDyLr0=; b=jE1QJBXJxYWRKXUM7JGPZzZaHZW35aDfenAFgmKF+/qwKucoKMZHOKiNAeHfgwhSXpanVZ cw/wCMtY+ATasc1AgdO0aD+0cHuU5YmN8IQW3pba74XTYfFL2tSD3bkpsxz330rxyH2Lwo BGmGVARbFVwV+vgR/TDKMix5EDYyhXg= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-528-mFoTFqj8OM6TsS7Ok5gs8A-1; Wed, 05 Jul 2023 14:17:17 -0400 X-MC-Unique: mFoTFqj8OM6TsS7Ok5gs8A-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 44FAB185A792; Wed, 5 Jul 2023 18:17:15 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id C6AE518EB4; Wed, 5 Jul 2023 18:17:08 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 13/14] context_tracking,x86: Add infrastructure to defer kernel TLBI Date: Wed, 5 Jul 2023 19:12:55 +0100 Message-Id: <20230705181256.3539027-14-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Kernel TLB invalidation IPIs are a common source of interference on NOHZ_FULL CPUs. Given NOHZ_FULL CPUs executing in userspace are not accessing any kernel addresses, these invalidations do not need to happen immediately, and can be deferred until the next user->kernel transition. Rather than make __flush_tlb_all() noinstr, add a minimal noinstr variant that doesn't try to leverage INVPCID. FIXME: not fully noinstr compliant XXX: same issue as with ins patching, when do we access data that should be invalidated? Signed-off-by: Valentin Schneider --- arch/x86/include/asm/context_tracking_work.h | 4 ++++ arch/x86/include/asm/tlbflush.h | 1 + arch/x86/mm/tlb.c | 17 +++++++++++++++++ include/linux/context_tracking_work.h | 2 ++ 4 files changed, 24 insertions(+) diff --git a/arch/x86/include/asm/context_tracking_work.h b/arch/x86/include/asm/context_tracking_work.h index 2c66687ce00e2..9d4f021b5a45b 100644 --- a/arch/x86/include/asm/context_tracking_work.h +++ b/arch/x86/include/asm/context_tracking_work.h @@ -3,6 +3,7 @@ #define _ASM_X86_CONTEXT_TRACKING_WORK_H #include +#include static __always_inline void arch_context_tracking_work(int work) { @@ -10,6 +11,9 @@ static __always_inline void arch_context_tracking_work(int work) case CONTEXT_WORK_SYNC: sync_core(); break; + case CONTEXT_WORK_TLBI: + __flush_tlb_all_noinstr(); + break; } } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 75bfaa4210303..9064aa0027d05 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -15,6 +15,7 @@ #include void __flush_tlb_all(void); +void noinstr __flush_tlb_all_noinstr(void); #define TLB_FLUSH_ALL -1UL #define TLB_GENERATION_INVALID 0 diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 267acf27480af..631df9189ded4 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -1237,6 +1237,23 @@ void __flush_tlb_all(void) } EXPORT_SYMBOL_GPL(__flush_tlb_all); +void noinstr __flush_tlb_all_noinstr(void) +{ + /* + * This is for invocation in early entry code that cannot be + * instrumented. A RMW to CR4 works for most cases, but relies on + * being able to flip either of the PGE or PCIDE bits. Flipping CR4.PCID + * would require also resetting CR3.PCID, so just try with CR4.PGE, else + * do the CR3 write. + * + * TODO: paravirt + */ + if (cpu_feature_enabled(X86_FEATURE_PGE)) + __native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4)); + else + flush_tlb_local(); +} + void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { struct flush_tlb_info *info; diff --git a/include/linux/context_tracking_work.h b/include/linux/context_tracking_work.h index b0c7463048b60..c084a60d2fec5 100644 --- a/include/linux/context_tracking_work.h +++ b/include/linux/context_tracking_work.h @@ -7,12 +7,14 @@ enum { CONTEXT_WORK_DISABLED_OFFSET, CONTEXT_WORK_SYNC_OFFSET, + CONTEXT_WORK_TLBI_OFFSET, CONTEXT_WORK_MAX_OFFSET }; enum ct_work { CONTEXT_WORK_DISABLED = BIT(CONTEXT_WORK_DISABLED_OFFSET), CONTEXT_WORK_SYNC = BIT(CONTEXT_WORK_SYNC_OFFSET), + CONTEXT_WORK_TLBI = BIT(CONTEXT_WORK_TLBI_OFFSET), CONTEXT_WORK_MAX = BIT(CONTEXT_WORK_MAX_OFFSET) }; From patchwork Wed Jul 5 18:12:56 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Valentin Schneider X-Patchwork-Id: 13302595 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 57F5AC04E69 for ; Wed, 5 Jul 2023 18:19:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233507AbjGEST3 (ORCPT ); Wed, 5 Jul 2023 14:19:29 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:45094 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233257AbjGESSn (ORCPT ); Wed, 5 Jul 2023 14:18:43 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D1E6D1996 for ; Wed, 5 Jul 2023 11:17:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1688581045; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=4KAtt5Wg9gvWlallwwTPlSO2JwaIw83isELp5cjnhmg=; b=FiDx++petWFoVlFU4wdVWFNOAZEWd3qrJ4nbsyTuguUgGFpVzqx6Lf4Y+U/+1RyGYDUWZX PSfSZmAfOl+H3L1c9jAQEbK6hsmo0uyS/YFeBvHGUSruThn5ifPkeJHzlqUqqoLKzfWAQU AyARbK+dPRqZtvLyxxvABIq+q+b9PkI= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-376-XnGbn6mUOsqBjFOroOxxLg-1; Wed, 05 Jul 2023 14:17:22 -0400 X-MC-Unique: XnGbn6mUOsqBjFOroOxxLg-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 48B262808E60; Wed, 5 Jul 2023 18:17:20 +0000 (UTC) Received: from vschneid.remote.csb (unknown [10.42.28.164]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 7229918EB4; Wed, 5 Jul 2023 18:17:15 +0000 (UTC) From: Valentin Schneider To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, x86@kernel.org Cc: Steven Rostedt , Masami Hiramatsu , Jonathan Corbet , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H. Peter Anvin" , Paolo Bonzini , Wanpeng Li , Vitaly Kuznetsov , Andy Lutomirski , Peter Zijlstra , Frederic Weisbecker , "Paul E. McKenney" , Andrew Morton , Uladzislau Rezki , Christoph Hellwig , Lorenzo Stoakes , Josh Poimboeuf , Kees Cook , Sami Tolvanen , Ard Biesheuvel , Nicholas Piggin , Juerg Haefliger , Nicolas Saenz Julienne , "Kirill A. Shutemov" , Nadav Amit , Dan Carpenter , Chuang Wang , Yang Jihong , Petr Mladek , "Jason A. Donenfeld" , Song Liu , Julian Pidancet , Tom Lendacky , Dionna Glaze , =?utf-8?q?Thomas_Wei=C3=9Fschuh?= , Juri Lelli , Daniel Bristot de Oliveira , Marcelo Tosatti , Yair Podemsky Subject: [RFC PATCH 14/14] x86/mm, mm/vmalloc: Defer flush_tlb_kernel_range() targeting NOHZ_FULL CPUs Date: Wed, 5 Jul 2023 19:12:56 +0100 Message-Id: <20230705181256.3539027-15-vschneid@redhat.com> In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com> References: <20230705181256.3539027-1-vschneid@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org vunmap()'s issued from housekeeping CPUs are a relatively common source of interference for isolated NOHZ_FULL CPUs, as they are hit by the flush_tlb_kernel_range() IPIs. Given that CPUs executing in userspace do not access data in the vmalloc range, these IPIs could be deferred until their next kernel entry. This does require a guarantee that nothing in the vmalloc range can be accessed in early entry code. vmalloc'd kernel stacks (VMAP_STACK) are AFAICT a safe exception, as a task running in userspace needs to enter kernelspace to execute do_exit() before its stack can be vfree'd. XXX: Validation that nothing in the vmalloc range is accessed in .noinstr or somesuch? Blindly deferring any and all flush of the kernel mappings is a risky move, so introduce a variant of flush_tlb_kernel_range() that explicitly allows deferral. Use it for vunmap flushes. Note that while flush_tlb_kernel_range() may end up issuing a full flush (including user mappings), this only happens when reaching a invalidation range threshold where it is cheaper to do a full flush than to individually invalidate each page in the range via INVLPG. IOW, it doesn't *require* invalidating user mappings, and thus remains safe to defer until a later kernel entry. Signed-off-by: Valentin Schneider --- arch/x86/include/asm/tlbflush.h | 1 + arch/x86/mm/tlb.c | 23 ++++++++++++++++++++--- mm/vmalloc.c | 15 ++++++++++----- 3 files changed, 31 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 9064aa0027d05..2b3605c09649c 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -255,6 +255,7 @@ extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned int stride_shift, bool freed_tables); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_tlb_kernel_range_deferrable(unsigned long start, unsigned long end); static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 631df9189ded4..bb18b35e61b4a 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -1045,6 +1046,11 @@ static void do_flush_tlb_all(void *info) __flush_tlb_all(); } +static bool do_kernel_flush_defer_cond(int cpu, void *info) +{ + return !ct_set_cpu_work(cpu, CONTEXT_WORK_TLBI); +} + void flush_tlb_all(void) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); @@ -1061,12 +1067,13 @@ static void do_kernel_range_flush(void *info) flush_tlb_one_kernel(addr); } -void flush_tlb_kernel_range(unsigned long start, unsigned long end) +static inline void +__flush_tlb_kernel_range(smp_cond_func_t cond_func, unsigned long start, unsigned long end) { /* Balance as user space task's flush, a bit conservative */ if (end == TLB_FLUSH_ALL || (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) { - on_each_cpu(do_flush_tlb_all, NULL, 1); + on_each_cpu_cond(cond_func, do_flush_tlb_all, NULL, 1); } else { struct flush_tlb_info *info; @@ -1074,13 +1081,23 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) info = get_flush_tlb_info(NULL, start, end, 0, false, TLB_GENERATION_INVALID); - on_each_cpu(do_kernel_range_flush, info, 1); + on_each_cpu_cond(cond_func, do_kernel_range_flush, info, 1); put_flush_tlb_info(); preempt_enable(); } } +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __flush_tlb_kernel_range(NULL, start, end); +} + +void flush_tlb_kernel_range_deferrable(unsigned long start, unsigned long end) +{ + __flush_tlb_kernel_range(do_kernel_flush_defer_cond, start, end); +} + /* * This can be used from process context to figure out what the value of * CR3 is without needing to do a (slow) __read_cr3(). diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1d13d71687d73..10f99224e12e0 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -439,6 +439,11 @@ void vunmap_range_noflush(unsigned long start, unsigned long end) __vunmap_range_noflush(start, end); } +#ifndef flush_tlb_kernel_range_deferrable +#define flush_tlb_kernel_range_deferrable(start, end) \ + flush_tlb_kernel_range(start, end) +#endif + /** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap @@ -452,7 +457,7 @@ void vunmap_range(unsigned long addr, unsigned long end) { flush_cache_vunmap(addr, end); vunmap_range_noflush(addr, end); - flush_tlb_kernel_range(addr, end); + flush_tlb_kernel_range_deferrable(addr, end); } static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, @@ -1747,7 +1752,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) list_last_entry(&local_purge_list, struct vmap_area, list)->va_end); - flush_tlb_kernel_range(start, end); + flush_tlb_kernel_range_deferrable(start, end); resched_threshold = lazy_max_pages() << 1; spin_lock(&free_vmap_area_lock); @@ -1849,7 +1854,7 @@ static void free_unmap_vmap_area(struct vmap_area *va) flush_cache_vunmap(va->va_start, va->va_end); vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) - flush_tlb_kernel_range(va->va_start, va->va_end); + flush_tlb_kernel_range_deferrable(va->va_start, va->va_end); free_vmap_area_noflush(va); } @@ -2207,7 +2212,7 @@ static void vb_free(unsigned long addr, unsigned long size) vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) - flush_tlb_kernel_range(addr, addr + size); + flush_tlb_kernel_range_deferrable(addr, addr + size); spin_lock(&vb->lock); @@ -2260,7 +2265,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); if (!__purge_vmap_area_lazy(start, end) && flush) - flush_tlb_kernel_range(start, end); + flush_tlb_kernel_range_deferrable(start, end); mutex_unlock(&vmap_purge_lock); }