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>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <netdev@vger.kernel.org>
Subject: [PATCH v1 net-next 15/16] af_unix: Remove lock dance in unix_peek_fds().
Date: Fri, 2 Feb 2024 19:00:57 -0800 [thread overview]
Message-ID: <20240203030058.60750-16-kuniyu@amazon.com> (raw)
In-Reply-To: <20240203030058.60750-1-kuniyu@amazon.com>
In the previous GC implementation, the shape of the inflight graph
was not expected to change while GC was in progress.
MSG_PEEK was tricky because it could install inflight fd silently
and transform the graph.
Let's say we peeked a fd, which was a listening socket, and accept()ed
some embryo sockets from it. The garbage collection algorithm would
have been confused as the set of sockets visited in scan_inflight()
were different within the same GC invocation.
That's why we placed spin_lock(&unix_gc_lock) and spin_unlock() in
unix_peek_fds() with a fat comment.
In a new implementation, we no longer garbage-collect the socket if
it exists in another queue, that is, if it has a bridge to another
SCC. Also, accept() will require the lock if it has edges.
Thus, we need not do the complicated lock dance.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
include/net/af_unix.h | 1 -
net/unix/af_unix.c | 42 ------------------------------------------
net/unix/garbage.c | 2 +-
3 files changed, 1 insertion(+), 44 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 78ab1107ffb3..33ddfe27bf50 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -17,7 +17,6 @@ static inline struct unix_sock *unix_get_socket(struct file *filp)
}
#endif
-extern spinlock_t unix_gc_lock;
extern unsigned int unix_tot_inflight;
void unix_init_vertex(struct unix_sock *u);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 9022a3a5dccc..d55fc3e9875b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1827,48 +1827,6 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
scm->fp = scm_fp_dup(UNIXCB(skb).fp);
-
- /*
- * Garbage collection of unix sockets starts by selecting a set of
- * candidate sockets which have reference only from being in flight
- * (total_refs == inflight_refs). This condition is checked once during
- * the candidate collection phase, and candidates are marked as such, so
- * that non-candidates can later be ignored. While inflight_refs is
- * protected by unix_gc_lock, total_refs (file count) is not, hence this
- * is an instantaneous decision.
- *
- * Once a candidate, however, the socket must not be reinstalled into a
- * file descriptor while the garbage collection is in progress.
- *
- * If the above conditions are met, then the directed graph of
- * candidates (*) does not change while unix_gc_lock is held.
- *
- * Any operations that changes the file count through file descriptors
- * (dup, close, sendmsg) does not change the graph since candidates are
- * not installed in fds.
- *
- * Dequeing a candidate via recvmsg would install it into an fd, but
- * that takes unix_gc_lock to decrement the inflight count, so it's
- * serialized with garbage collection.
- *
- * MSG_PEEK is special in that it does not change the inflight count,
- * yet does install the socket into an fd. The following lock/unlock
- * pair is to ensure serialization with garbage collection. It must be
- * done between incrementing the file count and installing the file into
- * an fd.
- *
- * If garbage collection starts after the barrier provided by the
- * lock/unlock, then it will see the elevated refcount and not mark this
- * as a candidate. If a garbage collection is already in progress
- * before the file count was incremented, then the lock/unlock pair will
- * ensure that garbage collection is finished before progressing to
- * installing the fd.
- *
- * (*) A -> B where B is on the queue of A or B is on the queue of C
- * which is on the queue of listening socket A.
- */
- spin_lock(&unix_gc_lock);
- spin_unlock(&unix_gc_lock);
}
static void unix_destruct_scm(struct sk_buff *skb)
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 84c445c79f8c..d9dd97d3d4a6 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -127,7 +127,7 @@ static void unix_graph_update(struct unix_edge *edge)
unix_graph_maybe_cyclic = true;
}
-DEFINE_SPINLOCK(unix_gc_lock);
+static DEFINE_SPINLOCK(unix_gc_lock);
static LIST_HEAD(unix_unvisited_vertices);
unsigned int unix_tot_inflight;
--
2.30.2
next prev parent reply other threads:[~2024-02-03 3:07 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-03 3:00 [PATCH v1 net-next 00/16] af_unix: Reimplment GC Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 01/16] af_unix: Add struct unix_vertex in struct unix_sock Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 02/16] af_unix: Allocate struct unix_edge for each inflight AF_UNIX fd Kuniyuki Iwashima
2024-02-03 20:20 ` kernel test robot
2024-02-03 3:00 ` [PATCH v1 net-next 03/16] af_unix: Link struct unix_edge when queuing skb Kuniyuki Iwashima
2024-02-20 12:06 ` Paolo Abeni
2024-02-03 3:00 ` [PATCH v1 net-next 04/16] af_unix: Save listener for embryo socket Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 05/16] af_unix: Fix up unix_edge.successor " Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 06/16] af_unix: Bulk update unix_tot_inflight/unix_inflight when queuing skb Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 07/16] af_unix: Detect Strongly Connected Components Kuniyuki Iwashima
2024-02-03 19:59 ` kernel test robot
2024-02-03 21:36 ` kernel test robot
2024-02-03 3:00 ` [PATCH v1 net-next 08/16] af_unix: Save O(n) setup of Tarjan's algo Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 09/16] af_unix: Avoid Tarjan's algorithm if unnecessary Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 10/16] af_unix: Skip GC if no cycle exists Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 11/16] af_unix: Assign a unique index to SCC Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 12/16] af_unix: Detect dead SCC Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 13/16] af_unix: Replace garbage collection algorithm Kuniyuki Iwashima
2024-02-03 3:00 ` [PATCH v1 net-next 14/16] af_unix: Remove scm_fp_dup() in unix_attach_fds() Kuniyuki Iwashima
2024-02-03 3:00 ` Kuniyuki Iwashima [this message]
2024-02-03 3:00 ` [PATCH v1 net-next 16/16] selftest: af_unix: Test GC for SCM_RIGHTS Kuniyuki Iwashima
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=20240203030058.60750-16-kuniyu@amazon.com \
--to=kuniyu@amazon.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).