LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Deepa Dinamani <deepa.kernel@gmail.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 3.18 19/47] sock: Make sock->sk_stamp thread-safe
Date: Fri, 11 Jan 2019 15:08:04 +0100
Message-ID: <20190111130958.590868862@linuxfoundation.org> (raw)
In-Reply-To: <20190111130956.170952125@linuxfoundation.org>

3.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Deepa Dinamani <deepa.kernel@gmail.com>

[ Upstream commit 3a0ed3e9619738067214871e9cb826fa23b2ddb9 ]

Al Viro mentioned (Message-ID
<20170626041334.GZ10672@ZenIV.linux.org.uk>)
that there is probably a race condition
lurking in accesses of sk_stamp on 32-bit machines.

sock->sk_stamp is of type ktime_t which is always an s64.
On a 32 bit architecture, we might run into situations of
unsafe access as the access to the field becomes non atomic.

Use seqlocks for synchronization.
This allows us to avoid using spinlocks for readers as
readers do not need mutual exclusion.

Another approach to solve this is to require sk_lock for all
modifications of the timestamps. The current approach allows
for timestamps to have their own lock: sk_stamp_lock.
This allows for the patch to not compete with already
existing critical sections, and side effects are limited
to the paths in the patch.

The addition of the new field maintains the data locality
optimizations from
commit 9115e8cd2a0c ("net: reorganize struct sock for better data
locality")

Note that all the instances of the sk_stamp accesses
are either through the ioctl or the syscall recvmsg.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/net/sock.h   |   36 ++++++++++++++++++++++++++++++++++--
 net/compat.c         |   15 +++++++++------
 net/core/sock.c      |    3 +++
 net/sunrpc/svcsock.c |    2 +-
 4 files changed, 47 insertions(+), 9 deletions(-)

--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -279,6 +279,7 @@ struct cg_proto;
   *	@sk_protinfo: private area, net family specific, when not using slab
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_socket: Identd and reporting IO signals
@@ -411,6 +412,9 @@ struct sock {
 	void			*sk_protinfo;
 	struct timer_list	sk_timer;
 	ktime_t			sk_stamp;
+#if BITS_PER_LONG==32
+	seqlock_t		sk_stamp_seq;
+#endif
 	u16			sk_tsflags;
 	u32			sk_tskey;
 	struct socket		*sk_socket;
@@ -2161,6 +2165,34 @@ static inline int sock_intr_errno(long t
 	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
 }
 
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	unsigned int seq;
+	ktime_t kt;
+
+	do {
+		seq = read_seqbegin(&sk->sk_stamp_seq);
+		kt = sk->sk_stamp;
+	} while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+	return kt;
+#else
+	return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	sk->sk_stamp = kt;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	sk->sk_stamp = kt;
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2185,7 +2217,7 @@ sock_recv_timestamp(struct msghdr *msg,
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
-		sk->sk_stamp = kt;
+		sock_write_timestamp(sk, kt);
 
 	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
 		__sock_recv_wifi_status(msg, sk, skb);
@@ -2205,7 +2237,7 @@ static inline void sock_recv_ts_and_drop
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else
-		sk->sk_stamp = skb->tstamp;
+		sock_write_timestamp(sk, skb->tstamp);
 }
 
 void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
--- a/net/compat.c
+++ b/net/compat.c
@@ -472,12 +472,14 @@ int compat_sock_get_timestamp(struct soc
 	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
+
 	if (tv.tv_sec == -1)
 		return err;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	err = 0;
 	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
@@ -500,12 +502,13 @@ int compat_sock_get_timestampns(struct s
 	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return err;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		ts = ktime_to_timespec(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		ts = ktime_to_timespec(kt);
 	}
 	err = 0;
 	if (put_user(ts.tv_sec, &ctv->tv_sec) ||
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2332,6 +2332,9 @@ void sock_init_data(struct socket *sock,
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
 	sk->sk_stamp = ktime_set(-1L, 0);
+#if BITS_PER_LONG==32
+	seqlock_init(&sk->sk_stamp_seq);
+#endif
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -589,7 +589,7 @@ static int svc_udp_recvfrom(struct svc_r
 		/* Don't enable netstamp, sunrpc doesn't
 		   need that much accuracy */
 	}
-	svsk->sk_sk->sk_stamp = skb->tstamp;
+	sock_write_timestamp(svsk->sk_sk, skb->tstamp);
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
 	len  = skb->len - sizeof(struct udphdr);



  parent reply index

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-11 14:07 [PATCH 3.18 00/47] 3.18.132-stable review Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 01/47] USB: hso: Fix OOB memory access in hso_probe/hso_get_config_data Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 02/47] USB: serial: option: add HP lt4132 Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 03/47] mmc: core: Reset HPI enabled state during re-init and in case of errors Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 04/47] mmc: omap_hsmmc: fix DMA API warning Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 05/47] gpio: max7301: fix driver for use with CONFIG_VMAP_STACK Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 06/47] Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 07/47] x86/mtrr: Dont copy uninitialized gentry fields back to userspace Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 08/47] ax25: fix a use-after-free in ax25_fillin_cb() Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 09/47] ibmveth: fix DMA unmap error in ibmveth_xmit_start error path Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 10/47] ipv6: explicitly initialize udp6_addr in udp_sock_create6() Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 11/47] isdn: fix kernel-infoleak in capi_unlocked_ioctl Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 12/47] netrom: fix locking in nr_find_socket() Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 13/47] packet: validate address length Greg Kroah-Hartman
2019-01-11 14:07 ` [PATCH 3.18 14/47] packet: validate address length if non-zero Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 15/47] sctp: initialize sin6_flowinfo for ipv6 addrs in sctp_inet6addr_event Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 16/47] vhost: make sure used idx is seen before log in vhost_add_used_n() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 17/47] VSOCK: Send reset control packet when socket is partially bound Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 18/47] xen/netfront: tolerate frags with no data Greg Kroah-Hartman
2019-01-11 14:08 ` Greg Kroah-Hartman [this message]
2019-01-11 14:08 ` [PATCH 3.18 20/47] USB: serial: pl2303: add ids for Hewlett-Packard HP POS pole displays Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 21/47] usb: r8a66597: Fix a possible concurrency use-after-free bug in r8a66597_endpoint_disable() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 22/47] KVM: x86: Use jmp to invoke kvm_spurious_fault() from .fixup Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 23/47] ext4: fix possible use after free in ext4_quota_enable Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 24/47] ext4: missing unlock/put_page() in ext4_try_to_write_inline_data() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 25/47] ext4: force inode writes when nfsd calls commit_metadata() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 26/47] cdc-acm: fix abnormal DATA RX issue for Mediatek Preloader Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 27/47] media: vivid: free bitmap_cap when updating std/timings/etc Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 28/47] MIPS: Ensure pmd_present() returns false after pmd_mknotpresent() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 29/47] MIPS: Align kernel load address to 64KB Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 30/47] CIFS: Fix error mapping for SMB2_LOCK command which caused OFD lock problem Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 31/47] scsi: zfcp: fix posting too many status read buffers leading to adapter shutdown Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 32/47] fork: record start_time late Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 33/47] sunrpc: fix cache_head leak due to queued request Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 34/47] sunrpc: use SVC_NET() in svcauth_gss_* functions Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 35/47] ALSA: cs46xx: Potential NULL dereference in probe Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 36/47] ALSA: usb-audio: Avoid access before bLength check in build_audio_procunit() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 37/47] ALSA: usb-audio: Fix an out-of-bound read in create_composite_quirks Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 38/47] dlm: fixed memory leaks after failed ls_remove_names allocation Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 39/47] dlm: possible memory leak on error path in create_lkb() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 40/47] dlm: lost put_lkb on error path in receive_convert() and receive_unlock() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 41/47] dlm: memory leaks on error path in dlm_user_request() Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 42/47] gfs2: Fix loop in gfs2_rbm_find Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 43/47] b43: Fix error in cordic routine Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 44/47] 9p/net: put a lower bound on msize Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 45/47] ceph: dont update importing caps mseq when handing cap export Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 46/47] genwqe: Fix size check Greg Kroah-Hartman
2019-01-11 14:08 ` [PATCH 3.18 47/47] power: supply: olpc_battery: correct the temperature units Greg Kroah-Hartman
2019-01-11 21:50 ` [PATCH 3.18 00/47] 3.18.132-stable review shuah
2019-01-12 14:58 ` Harsh Shandilya
2019-01-12 17:42 ` Guenter Roeck
2019-01-13  7:44   ` Greg Kroah-Hartman

Reply instructions:

You may reply publically 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=20190111130958.590868862@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=davem@davemloft.net \
    --cc=deepa.kernel@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    /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://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.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://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


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