LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
To: Steffen Klassert <steffen.klassert@secunet.com>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>,
	"Sebastian A. Siewior" <sebastian.siewior@linutronix.de>,
	"Ahmed S. Darwish" <a.darwish@linutronix.de>
Subject: [PATCH v1 1/2] net: xfrm: Localize sequence counter per network namespace
Date: Tue, 16 Mar 2021 11:56:29 +0100
Message-ID: <20210316105630.1020270-2-a.darwish@linutronix.de> (raw)
In-Reply-To: <20210316105630.1020270-1-a.darwish@linutronix.de>

A sequence counter write section must be serialized or its internal
state can get corrupted. The "xfrm_state_hash_generation" seqcount is
global, but its write serialization lock (net->xfrm.xfrm_state_lock) is
instantiated per network namespace. The write protection is thus
insufficient.

To provide full protection, localize the sequence counter per network
namespace instead. This should be safe as both the seqcount read and
write sections access data exclusively within the network namespace. It
also lays the foundation for transforming "xfrm_state_hash_generation"
data type from seqcount_t to seqcount_LOCKNAME_t in further commits.

Fixes: b65e3d7be06f ("xfrm: state: add sequence count to detect hash resizes")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
---
 include/net/netns/xfrm.h |  4 +++-
 net/xfrm/xfrm_state.c    | 10 +++++-----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 59f45b1e9dac..b59d73d529ba 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -72,7 +72,9 @@ struct netns_xfrm {
 #if IS_ENABLED(CONFIG_IPV6)
 	struct dst_ops		xfrm6_dst_ops;
 #endif
-	spinlock_t xfrm_state_lock;
+	spinlock_t		xfrm_state_lock;
+	seqcount_t		xfrm_state_hash_generation;
+
 	spinlock_t xfrm_policy_lock;
 	struct mutex xfrm_cfg_mutex;
 };
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d01ca1a18418..ffd315cff984 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -44,7 +44,6 @@ static void xfrm_state_gc_task(struct work_struct *work);
  */
 
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
-static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
 static struct kmem_cache *xfrm_state_cache __ro_after_init;
 
 static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
@@ -140,7 +139,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	}
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	write_seqcount_begin(&xfrm_state_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
 
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
@@ -156,7 +155,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	rcu_assign_pointer(net->xfrm.state_byspi, nspi);
 	net->xfrm.state_hmask = nhashmask;
 
-	write_seqcount_end(&xfrm_state_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	osize = (ohashmask + 1) * sizeof(struct hlist_head);
@@ -1063,7 +1062,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 
 	to_put = NULL;
 
-	sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+	sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
 
 	rcu_read_lock();
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
@@ -1176,7 +1175,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	if (to_put)
 		xfrm_state_put(to_put);
 
-	if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+	if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) {
 		*err = -EAGAIN;
 		if (x) {
 			xfrm_state_put(x);
@@ -2666,6 +2665,7 @@ int __net_init xfrm_state_init(struct net *net)
 	net->xfrm.state_num = 0;
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	seqcount_init(&net->xfrm.xfrm_state_hash_generation);
 	return 0;
 
 out_byspi:
-- 
2.30.2


  reply index

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-16 10:56 [PATCH v1 0/2] net: xfrm: Use seqcount_spinlock_t Ahmed S. Darwish
2021-03-16 10:56 ` Ahmed S. Darwish [this message]
2021-03-16 10:56 ` [PATCH v1 2/2] net: xfrm: Use sequence counter with associated spinlock Ahmed S. Darwish
2021-03-23  8:13 ` [PATCH v1 0/2] net: xfrm: Use seqcount_spinlock_t Steffen Klassert

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=20210316105630.1020270-2-a.darwish@linutronix.de \
    --to=a.darwish@linutronix.de \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.apana.org.au \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=sebastian.siewior@linutronix.de \
    --cc=steffen.klassert@secunet.com \
    --cc=tglx@linutronix.de \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lkml.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lkml.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lkml.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lkml.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lkml.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lkml.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lkml.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lkml.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lkml.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lkml.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lkml.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git