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(¤t->perf_event_mutex);
list_add_tail(&event->owner_entry, ¤t->perf_event_list);
mutex_unlock(¤t->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() */
next prev 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.