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}'

Link: https://lkml.kernel.org/r/20230707172155.70873-3-vschneid@redhat.com

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Leonardo Bras <leobras@redhat.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 95 insertions, 2 deletions

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 91fc9990107f..cb1863dfa280 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];