Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Kuniyuki Iwashima <kuniyu@amazon.com>
To:     "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Luis Chamberlain <mcgrof@kernel.org>,
        Kees Cook <keescook@chromium.org>,
        Iurii Zaikin <yzaikin@google.com>
CC:     Kuniyuki Iwashima <kuniyu@amazon.com>,
        Kuniyuki Iwashima <kuni1840@gmail.com>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH v1 net 03/16] sysctl: Add proc_dointvec_lockless().
Date:   Tue, 5 Jul 2022 22:21:17 -0700
Message-ID: <20220706052130.16368-4-kuniyu@amazon.com>
In-Reply-To: <20220706052130.16368-1-kuniyu@amazon.com>
References: <20220706052130.16368-1-kuniyu@amazon.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
Precedence: bulk

A sysctl variable is accessed concurrently, and there is always a chance of
data-race.  So, all readers and writers need some basic protection to avoid
load/store-tearing.

This patch changes proc_dointvec() to use READ_ONCE()/WRITE_ONCE()
internally to fix a data-race on the sysctl side.  For now, proc_dointvec()
itself is tolerant to a data-race, but we still need to add annotations on
the other subsystem's side.

In case we miss such fixes, this patch converts proc_dointvec() to a
wrapper of proc_dointvec_lockless().  When we fix a data-race in the other
subsystem, we can explicitly set it as a handler.

Also, this patch removes proc_dointvec()'s document and adds
proc_dointvec_lockless()'s one so that no one will use proc_dointvec()
anymore.

While we are on it, we remove some trailing spaces.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
 include/linux/sysctl.h |  1 +
 kernel/sysctl.c        | 27 +++++++++++++++++++--------
 2 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index fcafc16abbad..cb87919b5508 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -84,6 +84,7 @@ PROC_HANDLER(proc_do_large_bitmap);
 PROC_HANDLER(proc_do_static_key);
 
 PROC_HANDLER(proc_dobool_lockless);
+PROC_HANDLER(proc_dointvec_lockless);
 
 /*
  * Register a set of sysctl names by calling register_sysctl_table
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bc6fcc64eeaf..50d9b78aa0b3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -445,14 +445,17 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 		if (*negp) {
 			if (*lvalp > (unsigned long) INT_MAX + 1)
 				return -EINVAL;
-			*valp = -*lvalp;
+
+			WRITE_ONCE(*valp, -*lvalp);
 		} else {
 			if (*lvalp > (unsigned long) INT_MAX)
 				return -EINVAL;
-			*valp = *lvalp;
+
+			WRITE_ONCE(*valp, *lvalp);
 		}
 	} else {
-		int val = *valp;
+		int val = READ_ONCE(*valp);
+
 		if (val < 0) {
 			*negp = true;
 			*lvalp = -(unsigned long)val;
@@ -491,12 +494,12 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 	int *i, vleft, first = 1, err = 0;
 	size_t left;
 	char *p;
-	
+
 	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
-	
+
 	i = (int *) tbl_data;
 	vleft = table->maxlen / sizeof(*i);
 	left = *lenp;
@@ -726,7 +729,7 @@ int proc_dobool(struct ctl_table *table, int write, void *buffer,
 }
 
 /**
- * proc_dointvec - read a vector of integers
+ * proc_dointvec_lockless - read/write a vector of integers locklessly
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
  * @buffer: the user buffer
@@ -734,14 +737,20 @@ int proc_dobool(struct ctl_table *table, int write, void *buffer,
  * @ppos: file position
  *
  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
+ * values from/to the user buffer, treated as an ASCII string.
  *
  * Returns 0 on success.
  */
+int proc_dointvec_lockless(struct ctl_table *table, int write, void *buffer,
+			   size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
 int proc_dointvec(struct ctl_table *table, int write, void *buffer,
 		  size_t *lenp, loff_t *ppos)
 {
-	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+	return proc_dointvec_lockless(table, write, buffer, lenp, ppos);
 }
 
 #ifdef CONFIG_COMPACTION
@@ -1503,6 +1512,7 @@ PROC_HANDLER_ENOSYS(proc_do_cad_pid);
 PROC_HANDLER_ENOSYS(proc_do_large_bitmap);
 
 PROC_HANDLER_ENOSYS(proc_dobool_lockless);
+PROC_HANDLER_ENOSYS(proc_dointvec_lockless);
 
 #endif /* CONFIG_PROC_SYSCTL */
 
@@ -2414,3 +2424,4 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
 EXPORT_SYMBOL(proc_do_large_bitmap);
 
 EXPORT_SYMBOL(proc_dobool_lockless);
+EXPORT_SYMBOL(proc_dointvec_lockless);
-- 
2.30.2