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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Fri, 29 Jun 2012 14:33:14 +0100
From:	Mel Gorman <mgorman@...e.de>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Linux-MM <linux-mm@...ck.org>,
	Linux-Netdev <netdev@...r.kernel.org>,
	Linux-NFS <linux-nfs@...r.kernel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	David Miller <davem@...emloft.net>,
	Trond Myklebust <Trond.Myklebust@...app.com>,
	Neil Brown <neilb@...e.de>,
	Christoph Hellwig <hch@...radead.org>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Mike Christie <michaelc@...wisc.edu>,
	Eric B Munson <emunson@...bm.net>,
	Sebastian Andrzej Siewior <sebastian@...akpoint.cc>,
	Mel Gorman <mgorman@...e.de>
Subject: [PATCH 01/12] netvm: Prevent a stream-specific deadlock

It could happen that all !SOCK_MEMALLOC sockets have buffered so
much data that we're over the global rmem limit. This will prevent
SOCK_MEMALLOC buffers from receiving data, which will prevent userspace
from running, which is needed to reduce the buffered data.

Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit.
Once this change it applied, it is important that sockets that set
SOCK_MEMALLOC do not clear the flag until the socket is being torn down.
If this happens, a warning is generated and the tokens reclaimed to
avoid accounting errors until the bug is fixed.

[davem@...emloft.net: Warning about clearing SOCK_MEMALLOC]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Signed-off-by: Mel Gorman <mgorman@...e.de>
Acked-by: David S. Miller <davem@...emloft.net>
Acked-by: Rik van Riel<riel@...hat.com>
---
 include/net/sock.h     |    8 +++++---
 net/caif/caif_socket.c |    2 +-
 net/core/sock.c        |   14 +++++++++++++-
 net/ipv4/tcp_input.c   |   21 +++++++++++----------
 net/sctp/ulpevent.c    |    3 ++-
 5 files changed, 32 insertions(+), 16 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 767c443..5faae49 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1326,12 +1326,14 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size)
 		__sk_mem_schedule(sk, size, SK_MEM_SEND);
 }
 
-static inline bool sk_rmem_schedule(struct sock *sk, int size)
+static inline bool
+sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size)
 {
 	if (!sk_has_account(sk))
 		return true;
-	return size <= sk->sk_forward_alloc ||
-		__sk_mem_schedule(sk, size, SK_MEM_RECV);
+	return size<= sk->sk_forward_alloc ||
+		__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
+		skb_pfmemalloc(skb);
 }
 
 static inline void sk_mem_reclaim(struct sock *sk)
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 78f1cda..095259f 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -141,7 +141,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	err = sk_filter(sk, skb);
 	if (err)
 		return err;
-	if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
 		set_rx_flow_off(cf_sk);
 		net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
 		caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);
diff --git a/net/core/sock.c b/net/core/sock.c
index c551563..5cbca0e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -295,6 +295,18 @@ void sk_clear_memalloc(struct sock *sk)
 	sock_reset_flag(sk, SOCK_MEMALLOC);
 	sk->sk_allocation &= ~__GFP_MEMALLOC;
 	static_key_slow_dec(&memalloc_socks);
+
+	/*
+	 * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+	 * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+	 * it has rmem allocations there is a risk that the user of the
+	 * socket cannot make forward progress due to exceeding the rmem
+	 * limits. By rights, sk_clear_memalloc() should only be called
+	 * on sockets being torn down but warn and reset the accounting if
+	 * that assumption breaks.
+	 */
+	if (WARN_ON(sk->sk_forward_alloc))
+		sk_mem_reclaim(sk);
 }
 EXPORT_SYMBOL_GPL(sk_clear_memalloc);
 
@@ -396,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	if (!sk_rmem_schedule(sk, skb->truesize)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
 		atomic_inc(&sk->sk_drops);
 		return -ENOBUFS;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8416f8a..7d6ff91 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4512,19 +4512,20 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk);
 static int tcp_prune_queue(struct sock *sk);
 
-static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
+static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
+				 unsigned int size)
 {
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	    !sk_rmem_schedule(sk, size)) {
+	    !sk_rmem_schedule(sk, skb, size)) {
 
 		if (tcp_prune_queue(sk) < 0)
 			return -1;
 
-		if (!sk_rmem_schedule(sk, size)) {
+		if (!sk_rmem_schedule(sk, skb, size)) {
 			if (!tcp_prune_ofo_queue(sk))
 				return -1;
 
-			if (!sk_rmem_schedule(sk, size))
+			if (!sk_rmem_schedule(sk, skb, size))
 				return -1;
 		}
 	}
@@ -4579,7 +4580,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	TCP_ECN_check_ce(tp, skb);
 
-	if (tcp_try_rmem_schedule(sk, skb->truesize)) {
+	if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
 		/* TODO: should increment a counter */
 		__kfree_skb(skb);
 		return;
@@ -4710,17 +4711,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct tcphdr *th;
 	bool fragstolen;
 
-	if (tcp_try_rmem_schedule(sk, size + sizeof(*th)))
-		goto err;
-
 	skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th)))
+		goto err_free;
+
 	th = (struct tcphdr *)skb_put(skb, sizeof(*th));
 	skb_reset_transport_header(skb);
 	memset(th, 0, sizeof(*th));
@@ -4791,7 +4792,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		if (eaten <= 0) {
 queue_and_out:
 			if (eaten < 0 &&
-			    tcp_try_rmem_schedule(sk, skb->truesize))
+			    tcp_try_rmem_schedule(sk, skb, skb->truesize))
 				goto drop;
 
 			eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8a84017..1f89add 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -702,7 +702,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	if (rx_count >= asoc->base.sk->sk_rcvbuf) {
 
 		if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
-		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize)))
+		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
+				       chunk->skb->truesize)))
 			goto fail;
 	}
 
-- 
1.7.9.2

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists