From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 008A4378D93 for ; Thu, 20 Aug 2026 22:28:12 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787264894; cv=none; b=txNFXzPmKasodPET3vE4g9LiF6SMemD0JRPea4x1tAEmwY2WyoN6F7cCsiPiIMeEUTcpwZADsPYICAjPHKV9LqHcpykN9B2KEXtexk50qpUEyftsG8PvPamavnecXjcgTnIA6aONhWc6HUKgfqUt190bto8N8qsfyC4k+3AKCyg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787264894; c=relaxed/simple; bh=epM0fBIpiYt4K/qU6j6znNeRqBtMf6RCVhXXKnRgbXM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=NWo0Yzyrd/XlHFbS1Zae5s7hLC+GOgLk8F5BzC1TPWF8szMwqwhAjIHDjlYZtA332Dvj2c2up+tGU2U248wKFv/RQCe1e/LSoWVj/GcFxB20d0irunlTPng34qdREQUdX7VPY0rc+pX3xVVaBFWAWj3wypa/7GLrU5EbC08pjgg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=THSWJZ+r; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="THSWJZ+r" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 3BAB91F00A3E; Thu, 20 Aug 2026 22:28:12 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787264892; bh=EjcyIa5bXbGBHIPOFbUNP0K9nvBFbbGrcTe0BZybzsQ=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=THSWJZ+rM+oFAqFaH1PS85EEkodtL6+CAbwGaraOJdYReh1N1JpsyQj383iAOggQc 7plTRrrZ34g3LRNuRpFbnKT6GYVf7ohIuo21P0uWKnf42Q3TbuCsQA8UqiOlZV06C4 BCa+4FHljM5mYvsf+NzJdZyC0VqXgkbNm9kS4idwq+BJlS2OQmpPcpX6MhIjsjLWb3 Y9bGgCHMh/Jrh/0pT3MX144ZS4WAX8v1ef1PIUKftAHX4X2Nrf9Ao4ksbop5bFXGwi Gc7i1yh/0tGQNbcF4DzrM6a8B+t3Qw6Z7O/G8pwX1ebLpmRaHedEfcXH/QDP2BP61+ 4TYmMtpelSOhw== From: Sasha Levin To: stable@vger.kernel.org Cc: Peter Zijlstra , Ravi Bangoria , Sasha Levin Subject: [PATCH 6.6.y 1/2] perf: Unify perf_event_free_task() / perf_event_exit_task_context() Date: Thu, 20 Aug 2026 18:28:09 -0400 Message-ID: <20260820222810.2320933-1-sashal@kernel.org> X-Mailer: git-send-email 2.53.0 In-Reply-To: <2026081730-clay-squid-bf75@gregkh> References: <2026081730-clay-squid-bf75@gregkh> Precedence: bulk X-Mailing-List: stable@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Peter Zijlstra [ Upstream commit 90661365021a6d0d7f3a2c5046ebe33e4df53b92 ] Both perf_event_free_task() and perf_event_exit_task_context() are very similar, except perf_event_exit_task_context() is a little more generic / makes less assumptions. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ravi Bangoria Link: https://lkml.kernel.org/r/20250307193723.274039710@infradead.org Stable-dep-of: 42c5ca1f0a28 ("perf/core: Fix group leader use-after-free after sibling detach") Signed-off-by: Sasha Levin --- kernel/events/core.c | 96 ++++++++++++-------------------------------- 1 file changed, 26 insertions(+), 70 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d45bce2acdbc7..e4e375376f455 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2393,6 +2393,7 @@ __perf_remove_from_context(struct perf_event *event, perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, min(event->state, state)); + if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) @@ -13276,13 +13277,11 @@ perf_event_exit_event(struct perf_event *event, perf_event_wakeup(event); } -static void perf_event_exit_task_context(struct task_struct *child) +static void perf_event_exit_task_context(struct task_struct *child, bool exit) { struct perf_event_context *child_ctx, *clone_ctx = NULL; struct perf_event *child_event, *next; - WARN_ON_ONCE(child != current); - child_ctx = perf_pin_task_context(child); if (!child_ctx) return; @@ -13305,7 +13304,8 @@ static void perf_event_exit_task_context(struct task_struct *child) * in. */ raw_spin_lock_irq(&child_ctx->lock); - task_ctx_sched_out(child_ctx, EVENT_ALL); + if (exit) + task_ctx_sched_out(child_ctx, EVENT_ALL); /* * Now that the context is inactive, destroy the task <-> ctx relation @@ -13314,7 +13314,7 @@ static void perf_event_exit_task_context(struct task_struct *child) RCU_INIT_POINTER(child->perf_event_ctxp, NULL); put_ctx(child_ctx); /* cannot be last */ WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); - put_task_struct(current); /* cannot be last */ + put_task_struct(child); /* cannot be last */ clone_ctx = unclone_ctx(child_ctx); raw_spin_unlock_irq(&child_ctx->lock); @@ -13327,13 +13327,31 @@ static void perf_event_exit_task_context(struct task_struct *child) * won't get any samples after PERF_RECORD_EXIT. We can however still * get a few PERF_RECORD_READ events. */ - perf_event_task(child, child_ctx, 0); + if (exit) + perf_event_task(child, child_ctx, 0); list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) perf_event_exit_event(child_event, child_ctx, 0); mutex_unlock(&child_ctx->mutex); + if (!exit) { + /* + * perf_event_release_kernel() could still have a reference on + * this context. In that case we must wait for these events to + * have been freed (in particular all their references to this + * task must've been dropped). + * + * Without this copy_process() will unconditionally free this + * task (irrespective of its reference count) and + * _free_event()'s put_task_struct(event->hw.target) will be a + * use-after-free. + * + * Wait for all events to drop their context reference. + */ + wait_var_event(&child_ctx->refcount, + refcount_read(&child_ctx->refcount) == 1); + } put_ctx(child_ctx); } @@ -13361,7 +13379,7 @@ void perf_event_exit_task(struct task_struct *child) } mutex_unlock(&child->perf_event_mutex); - perf_event_exit_task_context(child); + perf_event_exit_task_context(child, true); /* * The perf_event_exit_task_context calls perf_event_task @@ -13372,27 +13390,6 @@ void perf_event_exit_task(struct task_struct *child) perf_event_task(child, NULL, 0); } -static void perf_free_event(struct perf_event *event, - struct perf_event_context *ctx) -{ - struct perf_event *parent = event->parent; - - if (WARN_ON_ONCE(!parent)) - return; - - mutex_lock(&parent->child_mutex); - list_del_init(&event->child_list); - mutex_unlock(&parent->child_mutex); - - put_event(parent); - - raw_spin_lock_irq(&ctx->lock); - perf_group_detach(event); - list_del_event(event, ctx); - raw_spin_unlock_irq(&ctx->lock); - free_event(event); -} - /* * Free a context as created by inheritance by perf_event_init_task() below, * used by fork() in case of fail. @@ -13402,48 +13399,7 @@ static void perf_free_event(struct perf_event *event, */ void perf_event_free_task(struct task_struct *task) { - struct perf_event_context *ctx; - struct perf_event *event, *tmp; - - ctx = rcu_access_pointer(task->perf_event_ctxp); - if (!ctx) - return; - - mutex_lock(&ctx->mutex); - raw_spin_lock_irq(&ctx->lock); - /* - * Destroy the task <-> ctx relation and mark the context dead. - * - * This is important because even though the task hasn't been - * exposed yet the context has been (through child_list). - */ - RCU_INIT_POINTER(task->perf_event_ctxp, NULL); - WRITE_ONCE(ctx->task, TASK_TOMBSTONE); - put_task_struct(task); /* cannot be last */ - raw_spin_unlock_irq(&ctx->lock); - - - list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) - perf_free_event(event, ctx); - - mutex_unlock(&ctx->mutex); - - /* - * perf_event_release_kernel() could've stolen some of our - * child events and still have them on its free_list. In that - * case we must wait for these events to have been freed (in - * particular all their references to this task must've been - * dropped). - * - * Without this copy_process() will unconditionally free this - * task (irrespective of its reference count) and - * _free_event()'s put_task_struct(event->hw.target) will be a - * use-after-free. - * - * Wait for all events to drop their context reference. - */ - wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1); - put_ctx(ctx); /* must be last */ + perf_event_exit_task_context(task, false); } void perf_event_delayed_put(struct task_struct *task) -- 2.53.0