Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.35 as permitted sender) client-ip=23.128.96.35;
From:   Chuyi Zhou <zhouchuyi@bytedance.com>
To:     bpf@vger.kernel.org
Cc:     ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
        martin.lau@kernel.org, tj@kernel.org, linux-kernel@vger.kernel.org,
        Chuyi Zhou <zhouchuyi@bytedance.com>
Subject: [PATCH bpf-next v3 1/7] cgroup: Prepare for using css_task_iter_*() in BPF
Date:   Mon, 25 Sep 2023 18:55:46 +0800
Message-Id: <20230925105552.817513-2-zhouchuyi@bytedance.com>
In-Reply-To: <20230925105552.817513-1-zhouchuyi@bytedance.com>
References: <20230925105552.817513-1-zhouchuyi@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patch makes some preparations for using css_task_iter_*() in BPF
Program.

1. Flags CSS_TASK_ITER_* are #define-s and it's not easy for bpf prog to
use them. Convert them to enum so bpf prog can take them from vmlinux.h.

2. In the next patch we will add css_task_iter_*() in common kfuncs which
is not safe. Since css_task_iter_*() does spin_unlock_irq() which might
screw up irq flags depending on the context where bpf prog is running.
So we should use irqsave/irqrestore here and the switching is harmless.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 12 +++++-------
 kernel/cgroup/cgroup.c | 18 ++++++++++++------
 2 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b307013b9c6c..0ef0af66080e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -40,13 +40,11 @@ struct kernel_clone_args;
 #define CGROUP_WEIGHT_DFL		100
 #define CGROUP_WEIGHT_MAX		10000
 
-/* walk only threadgroup leaders */
-#define CSS_TASK_ITER_PROCS		(1U << 0)
-/* walk all threaded css_sets in the domain */
-#define CSS_TASK_ITER_THREADED		(1U << 1)
-
-/* internal flags */
-#define CSS_TASK_ITER_SKIPPED		(1U << 16)
+enum {
+	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
+	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
+	CSS_TASK_ITER_SKIPPED  = (1U << 16), /* internal flags */
+};
 
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1fb7f562289d..b6d64f3b8888 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4917,9 +4917,11 @@ static void css_task_iter_advance(struct css_task_iter *it)
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	memset(it, 0, sizeof(*it));
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	it->ss = css->ss;
 	it->flags = flags;
@@ -4933,7 +4935,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	css_task_iter_advance(it);
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 }
 
 /**
@@ -4946,12 +4948,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
  */
 struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_task) {
 		put_task_struct(it->cur_task);
 		it->cur_task = NULL;
 	}
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	/* @it may be half-advanced by skips, finish advancing */
 	if (it->flags & CSS_TASK_ITER_SKIPPED)
@@ -4964,7 +4968,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		css_task_iter_advance(it);
 	}
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 
 	return it->cur_task;
 }
@@ -4977,11 +4981,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
  */
 void css_task_iter_end(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_cset) {
-		spin_lock_irq(&css_set_lock);
+		spin_lock_irqsave(&css_set_lock, irqflags);
 		list_del(&it->iters_node);
 		put_css_set_locked(it->cur_cset);
-		spin_unlock_irq(&css_set_lock);
+		spin_unlock_irqrestore(&css_set_lock, irqflags);
 	}
 
 	if (it->cur_dcset)
-- 
2.20.1