public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Marcelo Tosatti <mtosatti@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Daniel Bristot de Oliveira <bristot@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Frederic Weisbecker <frederic@kernel.org>,
	Leonardo Bras <leobras@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Marcelo Tosatti <mtosatti@redhat.com>
Subject: [patch 06/12] perf_event_open: check for block interference CPUs
Date: Tue, 06 Feb 2024 15:49:17 -0300	[thread overview]
Message-ID: <20240206185709.981989497@redhat.com> (raw)
In-Reply-To: 20240206184911.248214633@redhat.com

When creating perf events, return an error rather
than interfering with CPUs tagged as block interference.

Note: this patch is incomplete, installation of perf context 
on block interference CPUs via task context is not performed.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: linux-isolation/kernel/events/core.c
===================================================================
--- linux-isolation.orig/kernel/events/core.c
+++ linux-isolation/kernel/events/core.c
@@ -55,6 +55,7 @@
 #include <linux/pgtable.h>
 #include <linux/buildid.h>
 #include <linux/task_work.h>
+#include <linux/sched/isolation.h>
 
 #include "internal.h"
 
@@ -12435,6 +12436,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int err;
 	int f_flags = O_RDWR;
 	int cgroup_fd = -1;
+	int idx;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -12712,6 +12714,26 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
+	idx = block_interf_srcu_read_lock();
+	if (!task) {
+		if (move_group) {
+			for_each_sibling_event(sibling, group_leader) {
+				if (block_interf_cpu(sibling->cpu)) {
+					err = -EPERM;
+					goto err_block_interf;
+				}
+			}
+			if (block_interf_cpu(group_leader->cpu)) {
+				err = -EPERM;
+				goto err_block_interf;
+			}
+		}
+		if (block_interf_cpu(event->cpu)) {
+			err = -EPERM;
+			goto err_block_interf;
+		}
+	}
+
 	/*
 	 * This is the point on no return; we cannot fail hereafter. This is
 	 * where we start modifying current state.
@@ -12775,6 +12797,8 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_task_struct(task);
 	}
 
+	block_interf_srcu_read_unlock(idx);
+
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -12789,6 +12813,8 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
+err_block_interf:
+	block_interf_srcu_read_unlock(idx);
 err_context:
 	put_pmu_ctx(event->pmu_ctx);
 	event->pmu_ctx = NULL; /* _free_event() */



  parent reply	other threads:[~2024-02-06 19:00 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-06 18:49 [patch 00/12] cpu isolation: infra to block interference to select CPUs Marcelo Tosatti
2024-02-06 18:49 ` [patch 01/12] cpu isolation: basic block interference infrastructure Marcelo Tosatti
2024-02-06 18:49 ` [patch 02/12] introduce smp_call_func_single_fail Marcelo Tosatti
2024-02-06 18:49 ` [patch 03/12] Introduce _fail variants of stop_machine functions Marcelo Tosatti
2024-02-06 18:49 ` [patch 04/12] clockevent unbind: use smp_call_func_single_fail Marcelo Tosatti
2024-02-07 11:55   ` Thomas Gleixner
2024-02-07 12:51     ` Marcelo Tosatti
2024-02-11  8:52       ` Thomas Gleixner
2024-02-14 18:58         ` Marcelo Tosatti
2024-02-06 18:49 ` [patch 05/12] timekeeping_notify: use stop_machine_fail when appropriate Marcelo Tosatti
2024-02-07 11:57   ` Thomas Gleixner
2024-02-07 12:58     ` Marcelo Tosatti
2024-02-08 15:23       ` Thomas Gleixner
2024-02-09 15:30         ` Marcelo Tosatti
2024-02-12 15:29           ` Thomas Gleixner
2024-02-06 18:49 ` Marcelo Tosatti [this message]
2024-02-06 18:49 ` [patch 07/12] mtrr_add_page/mtrr_del_page: check for block interference CPUs Marcelo Tosatti
2024-02-06 18:49 ` [patch 08/12] arm64 kernel/topology: use smp_call_function_single_fail Marcelo Tosatti
2024-02-06 18:49 ` [patch 09/12] AMD MCE: use smp_call_func_single_fail Marcelo Tosatti
2024-02-06 18:49 ` [patch 10/12] x86/mce/inject.c: fail if target cpu is block interference Marcelo Tosatti
2024-02-06 18:49 ` [patch 11/12] x86/resctrl: use smp_call_function_single_fail Marcelo Tosatti
2024-02-12 15:19   ` Thomas Gleixner
2024-02-14 18:59     ` Marcelo Tosatti
2024-02-06 18:49 ` [patch 12/12] x86/cacheinfo.c: check for block interference CPUs Marcelo Tosatti
2024-02-07 12:41   ` Thomas Gleixner
2024-02-07 13:10     ` Marcelo Tosatti
2024-02-07 13:16       ` Marcelo Tosatti

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=20240206185709.981989497@redhat.com \
    --to=mtosatti@redhat.com \
    --cc=bristot@kernel.org \
    --cc=frederic@kernel.org \
    --cc=juri.lelli@redhat.com \
    --cc=leobras@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=vschneid@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