| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200603144949.1122421-2-a.darwish@linutronix.de>
Date: Wed, 3 Jun 2020 16:49:44 +0200
From: "Ahmed S. Darwish" <a.darwish@...utronix.de>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>
Cc: Thomas Gleixner <tglx@...utronix.de>,
"Paul E. McKenney" <paulmck@...nel.org>,
"Sebastian A. Siewior" <bigeasy@...utronix.de>,
Steven Rostedt <rostedt@...dmis.org>,
LKML <linux-kernel@...r.kernel.org>,
"Ahmed S. Darwish" <a.darwish@...utronix.de>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Eric Dumazet <edumazet@...gle.com>,
Stephen Hemminger <stephen@...workplumber.org>,
netdev@...r.kernel.org
Subject: [PATCH v2 1/6] net: core: device_rename: Use rwsem instead of a seqcount
Sequence counters write paths are critical sections that must never be
preempted, and blocking, even for CONFIG_PREEMPTION=n, is not allowed.
Commit 5dbe7c178d3f ("net: fix kernel deadlock with interface rename and
netdev name retrieval.") handled a deadlock, observed with
CONFIG_PREEMPTION=n, where the devnet_rename seqcount read side was
infinitely spinning: it got scheduled after the seqcount write side
blocked inside its own critical section.
To fix that deadlock, among other issues, the commit added a
cond_resched() inside the read side section. While this will get the
non-preemptible kernel eventually unstuck, the seqcount reader is fully
exhausting its slice just spinning -- until TIF_NEED_RESCHED is set.
The fix is also still broken: if the seqcount reader belongs to a
real-time scheduling policy, it can spin forever and the kernel will
livelock.
Disabling preemption over the seqcount write side critical section will
not work: inside it are a number of GFP_KERNEL allocations and mutex
locking through the drivers/base/ :: device_rename() call chain.
>From all the above, replace the seqcount with a rwsem.
Fixes: 5dbe7c178d3f (net: fix kernel deadlock with interface rename and netdev name retrieval.)
Fixes: 30e6c9fa93cf (net: devnet_rename_seq should be a seqcount)
Fixes: c91f6df2db49 (sockopt: Change getsockopt() of SO_BINDTODEVICE to return an interface name)
Cc: <stable@...r.kernel.org>
Reported-by: kbuild test robot <lkp@...el.com> [ v1 missing up_read() on error exit ]
Reported-by: Dan Carpenter <dan.carpenter@...cle.com> [ v1 missing up_read() on error exit ]
Signed-off-by: Ahmed S. Darwish <a.darwish@...utronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
net/core/dev.c | 40 ++++++++++++++++++----------------------
1 file changed, 18 insertions(+), 22 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2d8aceee4284..93a279ab4e97 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -79,6 +79,7 @@
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/mutex.h>
+#include <linux/rwsem.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
@@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock);
static unsigned int napi_gen_id = NR_CPUS;
static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
-static seqcount_t devnet_rename_seq;
+static DECLARE_RWSEM(devnet_rename_sem);
static inline void dev_base_seq_inc(struct net *net)
{
@@ -930,33 +931,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id);
* @net: network namespace
* @name: a pointer to the buffer where the name will be stored.
* @ifindex: the ifindex of the interface to get the name from.
- *
- * The use of raw_seqcount_begin() and cond_resched() before
- * retrying is required as we want to give the writers a chance
- * to complete when CONFIG_PREEMPTION is not set.
*/
int netdev_get_name(struct net *net, char *name, int ifindex)
{
struct net_device *dev;
- unsigned int seq;
+ int ret;
-retry:
- seq = raw_seqcount_begin(&devnet_rename_seq);
+ down_read(&devnet_rename_sem);
rcu_read_lock();
+
dev = dev_get_by_index_rcu(net, ifindex);
if (!dev) {
- rcu_read_unlock();
- return -ENODEV;
+ ret = -ENODEV;
+ goto out;
}
strcpy(name, dev->name);
- rcu_read_unlock();
- if (read_seqcount_retry(&devnet_rename_seq, seq)) {
- cond_resched();
- goto retry;
- }
- return 0;
+ ret = 0;
+out:
+ rcu_read_unlock();
+ up_read(&devnet_rename_sem);
+ return ret;
}
/**
@@ -1228,10 +1224,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
return -EBUSY;
- write_seqcount_begin(&devnet_rename_seq);
+ down_write(&devnet_rename_sem);
if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return 0;
}
@@ -1239,7 +1235,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
err = dev_get_valid_name(net, dev, newname);
if (err < 0) {
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return err;
}
@@ -1254,11 +1250,11 @@ int dev_change_name(struct net_device *dev, const char *newname)
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
dev->name_assign_type = old_assign_type;
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return ret;
}
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
netdev_adjacent_rename_links(dev, oldname);
@@ -1279,7 +1275,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
/* err >= 0 after dev_alloc_name() or stores the first errno */
if (err >= 0) {
err = ret;
- write_seqcount_begin(&devnet_rename_seq);
+ down_write(&devnet_rename_sem);
memcpy(dev->name, oldname, IFNAMSIZ);
memcpy(oldname, newname, IFNAMSIZ);
dev->name_assign_type = old_assign_type;
--
2.20.1
Powered by blists - more mailing lists