linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Valentin Schneider <vschneid@redhat.com>
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" <rostedt@goodmis.org>,
	"Masami Hiramatsu" <mhiramat@kernel.org>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Wanpeng Li" <wanpengli@tencent.com>,
	"Vitaly Kuznetsov" <vkuznets@redhat.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Frederic Weisbecker" <frederic@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Uladzislau Rezki" <urezki@gmail.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Lorenzo Stoakes" <lstoakes@gmail.com>,
	"Josh Poimboeuf" <jpoimboe@kernel.org>,
	"Kees Cook" <keescook@chromium.org>,
	"Sami Tolvanen" <samitolvanen@google.com>,
	"Ard Biesheuvel" <ardb@kernel.org>,
	"Nicholas Piggin" <npiggin@gmail.com>,
	"Juerg Haefliger" <juerg.haefliger@canonical.com>,
	"Nicolas Saenz Julienne" <nsaenz@kernel.org>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	"Nadav Amit" <namit@vmware.com>,
	"Dan Carpenter" <error27@gmail.com>,
	"Chuang Wang" <nashuiliang@gmail.com>,
	"Yang Jihong" <yangjihong1@huawei.com>,
	"Petr Mladek" <pmladek@suse.com>,
	"Jason A. Donenfeld" <Jason@zx2c4.com>,
	"Song Liu" <song@kernel.org>,
	"Julian Pidancet" <julian.pidancet@oracle.com>,
	"Tom Lendacky" <thomas.lendacky@amd.com>,
	"Dionna Glaze" <dionnaglaze@google.com>,
	"Thomas Weißschuh" <linux@weissschuh.net>,
	"Juri Lelli" <juri.lelli@redhat.com>,
	"Daniel Bristot de Oliveira" <bristot@redhat.com>,
	"Marcelo Tosatti" <mtosatti@redhat.com>,
	"Yair Podemsky" <ypodemsk@redhat.com>
Subject: [RFC PATCH 03/14] tracing/filters: Enable filtering a scalar field by a cpumask
Date: Wed,  5 Jul 2023 19:12:45 +0100	[thread overview]
Message-ID: <20230705181256.3539027-4-vschneid@redhat.com> (raw)
In-Reply-To: <20230705181256.3539027-1-vschneid@redhat.com>

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 <vschneid@redhat.com>
---
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] == '"') {
-- 
2.31.1



  parent reply	other threads:[~2023-07-05 18:16 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-05 18:12 [RFC PATCH 00/14] context_tracking,x86: Defer some IPIs until a user->kernel transition Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 01/14] tracing/filters: Dynamically allocate filter_pred.regex Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 02/14] tracing/filters: Enable filtering a cpumask field by another cpumask Valentin Schneider
2023-07-05 18:54   ` Steven Rostedt
2023-07-05 18:12 ` Valentin Schneider [this message]
2023-07-05 19:00   ` [RFC PATCH 03/14] tracing/filters: Enable filtering a scalar field by a cpumask Steven Rostedt
2023-07-05 18:12 ` [RFC PATCH 04/14] tracing/filters: Enable filtering the CPU common " Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 05/14] tracing/filters: Document cpumask filtering Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 06/14] objtool: Flesh out warning related to pv_ops[] calls Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 07/14] objtool: Warn about non __ro_after_init static key usage in .noinstr Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 08/14] BROKEN: context_tracking: Make context_tracking_key __ro_after_init Valentin Schneider
2023-07-05 20:41   ` Peter Zijlstra
2023-07-05 18:12 ` [RFC PATCH 09/14] x86/kvm: Make kvm_async_pf_enabled __ro_after_init Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 10/14] x86/sev-es: Make sev_es_enable_key __ro_after_init Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 11/14] context-tracking: Introduce work deferral infrastructure Valentin Schneider
2023-07-05 22:23   ` Frederic Weisbecker
2023-07-05 22:41     ` Peter Zijlstra
2023-07-06  9:53       ` Frederic Weisbecker
2023-07-06 10:01     ` Frederic Weisbecker
2023-07-06 11:30     ` Valentin Schneider
2023-07-06 11:40       ` Frederic Weisbecker
2023-07-06 16:39         ` Paul E. McKenney
2023-07-06 18:05           ` Valentin Schneider
2023-07-06 11:55     ` Frederic Weisbecker
2023-07-05 22:39   ` Peter Zijlstra
2023-07-06 11:31     ` Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 12/14] context_tracking,x86: Defer kernel text patching IPIs Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 13/14] context_tracking,x86: Add infrastructure to defer kernel TLBI Valentin Schneider
2023-07-05 18:12 ` [RFC PATCH 14/14] x86/mm, mm/vmalloc: Defer flush_tlb_kernel_range() targeting NOHZ_FULL CPUs Valentin Schneider
2023-07-05 18:48 ` [RFC PATCH 00/14] context_tracking,x86: Defer some IPIs until a user->kernel transition Nadav Amit
2023-07-06 11:29   ` Valentin Schneider
2023-07-05 19:03 ` Steven Rostedt
2023-07-06 11:30   ` Valentin Schneider

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230705181256.3539027-4-vschneid@redhat.com \
    --to=vschneid@redhat.com \
    --cc=Jason@zx2c4.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=bp@alien8.de \
    --cc=bpf@vger.kernel.org \
    --cc=bristot@redhat.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=dionnaglaze@google.com \
    --cc=error27@gmail.com \
    --cc=frederic@kernel.org \
    --cc=hch@infradead.org \
    --cc=hpa@zytor.com \
    --cc=jpoimboe@kernel.org \
    --cc=juerg.haefliger@canonical.com \
    --cc=julian.pidancet@oracle.com \
    --cc=juri.lelli@redhat.com \
    --cc=keescook@chromium.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=linux@weissschuh.net \
    --cc=lstoakes@gmail.com \
    --cc=luto@kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=namit@vmware.com \
    --cc=nashuiliang@gmail.com \
    --cc=npiggin@gmail.com \
    --cc=nsaenz@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=pmladek@suse.com \
    --cc=rostedt@goodmis.org \
    --cc=samitolvanen@google.com \
    --cc=song@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=urezki@gmail.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=x86@kernel.org \
    --cc=yangjihong1@huawei.com \
    --cc=ypodemsk@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox