Message-Id: <20230720163056.2564824-3-vschneid@redhat.com>
Date:   Thu, 20 Jul 2023 17:30:38 +0100
From:   Valentin Schneider <vschneid@...hat.com>
To:     linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
        linux-doc@...r.kernel.org, kvm@...r.kernel.org, linux-mm@...ck.org,
        bpf@...r.kernel.org, x86@...nel.org, rcu@...r.kernel.org,
        linux-kselftest@...r.kernel.org
Cc:     Steven Rostedt <rostedt@...dmis.org>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Jonathan Corbet <corbet@....net>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        "H. Peter Anvin" <hpa@...or.com>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Frederic Weisbecker <frederic@...nel.org>,
        "Paul E. McKenney" <paulmck@...nel.org>,
        Neeraj Upadhyay <quic_neeraju@...cinc.com>,
        Joel Fernandes <joel@...lfernandes.org>,
        Josh Triplett <josh@...htriplett.org>,
        Boqun Feng <boqun.feng@...il.com>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Lai Jiangshan <jiangshanlai@...il.com>,
        Zqiang <qiang.zhang1211@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Uladzislau Rezki <urezki@...il.com>,
        Christoph Hellwig <hch@...radead.org>,
        Lorenzo Stoakes <lstoakes@...il.com>,
        Josh Poimboeuf <jpoimboe@...nel.org>,
        Jason Baron <jbaron@...mai.com>,
        Kees Cook <keescook@...omium.org>,
        Sami Tolvanen <samitolvanen@...gle.com>,
        Ard Biesheuvel <ardb@...nel.org>,
        Nicholas Piggin <npiggin@...il.com>,
        Juerg Haefliger <juerg.haefliger@...onical.com>,
        Nicolas Saenz Julienne <nsaenz@...nel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Nadav Amit <namit@...are.com>,
        Dan Carpenter <error27@...il.com>,
        Chuang Wang <nashuiliang@...il.com>,
        Yang Jihong <yangjihong1@...wei.com>,
        Petr Mladek <pmladek@...e.com>,
        "Jason A. Donenfeld" <Jason@...c4.com>, Song Liu <song@...nel.org>,
        Julian Pidancet <julian.pidancet@...cle.com>,
        Tom Lendacky <thomas.lendacky@....com>,
        Dionna Glaze <dionnaglaze@...gle.com>,
        Thomas Weißschuh <linux@...ssschuh.net>,
        Juri Lelli <juri.lelli@...hat.com>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Marcelo Tosatti <mtosatti@...hat.com>,
        Yair Podemsky <ypodemsk@...hat.com>
Subject: [RFC PATCH v2 02/20] tracing/filters: Enable filtering a cpumask field by another cpumask

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:
"CPUS{$cpulist}". The use of curly braces instead of parentheses is to
prevent predicate_parse() from parsing the contents of CPUS{...} as a
full-fledged predicate subexpression.

This enables e.g.:

$ trace-cmd record -e 'ipi_send_cpumask' -f 'cpumask & CPUS{2,4,6,8-32}'

Signed-off-by: Valentin Schneider <vschneid@...hat.com>
---
 include/linux/trace_events.h       |  1 +
 kernel/trace/trace_events_filter.c | 97 +++++++++++++++++++++++++++++-
 2 files changed, 96 insertions(+), 2 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 3930e676436c9..302be73918336 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -807,6 +807,7 @@ 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 91fc9990107f1..cb1863dfa280b 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"),			\
@@ -190,6 +195,7 @@ static void free_predicate(struct filter_pred *pred)
 {
 	if (pred) {
 		kfree(pred->regex);
+		kfree(pred->mask);
 		kfree(pred);
 	}
 }
@@ -877,6 +883,26 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event)
 	}
 }
 
+/* Filter predicate for cpumask field vs user-provided cpumask */
+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)
 {
@@ -1244,8 +1270,12 @@ 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;
@@ -1357,6 +1387,8 @@ 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:
@@ -1568,6 +1600,67 @@ 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, "CPUS", 4)) {
+		unsigned int maskstart;
+		char *tmp;
+
+		switch (field->filter_type) {
+		case FILTER_CPUMASK:
+			break;
+		default:
+			parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+			goto err_free;
+		}
+
+		switch (op) {
+		case OP_EQ:
+		case OP_NE:
+		case OP_BAND:
+			break;
+		default:
+			parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+			goto err_free;
+		}
+
+		/* Skip CPUS */
+		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);
+		strscpy(tmp, str + maskstart, (i - maskstart) + 1);
+
+		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];
-- 
2.31.1

Powered by blists - more mailing lists