[PATCH net-next v3 0/3] udp: refactor memory accounting

STALE3668d SUPERSEDED

Revision v3 of 4 in this series.

4 messages, 3 authors, 2016-09-29 · open the first message on its own page

[PATCH net-next v3 0/3] udp: refactor memory accounting

From: Paolo Abeni <hidden>
Date: 2016-09-28 10:52:50

This patch series refactor the udp memory accounting, replacing the
generic implementation with a custom one, in order to remove the needs for
locking the socket on the enqueue and dequeue operations. The socket backlog
usage is dropped, as well.

The first patch factor out core pieces of some queue and memory management
socket helpers, so that they can later be used by the udp memory accounting
functions.
The second patch adds the memory account helpers, without using them.
The third patch replacse the old rx memory accounting path for udp over ipv4 and
udp over ipv6. In kernel UDP users are updated, as well.

The memory accounting schema is described in detail in the individual patch
commit message.

The performance gain depends on the specific scenario; with few flows (and
little contention in the original code) the differences are in the noise range,
while with several flows contending the same socket, the measured speed-up
is relevant (e.g. even over 100% in case of extreme contention)

v2 -> v3:
 - do not set the now unsed backlog_rcv callback

v1 -> v2:
 - changed slighly the memory accounting schema, we now perform lazy reclaim
 - fixed forward_alloc updating issue
 - fixed memory counter integer overflows

Paolo Abeni (3):
  net/socket: factor out helpers for memory and queue manipulation
  udp: implement memory accounting helpers
  udp: use it's own memory accounting schema

 include/linux/udp.h   |   2 +
 include/net/sock.h    |   5 ++
 include/net/udp.h     |   7 ++
 net/core/datagram.c   |  36 ++++++----
 net/core/sock.c       |  96 ++++++++++++++++++---------
 net/ipv4/udp.c        | 179 ++++++++++++++++++++++++++++++++++++++++++--------
 net/ipv6/udp.c        |  33 ++++------
 net/sunrpc/svcsock.c  |  20 ++++--
 net/sunrpc/xprtsock.c |   2 +-
 9 files changed, 279 insertions(+), 101 deletions(-)

-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH net-next v3 1/3] net/socket: factor out helpers for memory and queue manipulation

From: Paolo Abeni <pabeni@redhat.com>
Date: 2016-09-28 10:53:09

Basic sock operations that udp code can use with its own
memory accounting schema. No functional change is introduced
in the existing APIs.

v1 -> v2:
  - avoid export sock_rmem_free

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sock.h  |  5 +++
 net/core/datagram.c | 36 ++++++++++++--------
 net/core/sock.c     | 96 +++++++++++++++++++++++++++++++++++------------------
 3 files changed, 91 insertions(+), 46 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index ebf75db..7e42922 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h

@@ -1274,7 +1274,9 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
 /*
  * Functions for memory accounting
  */
+int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind);
 int __sk_mem_schedule(struct sock *sk, int size, int kind);
+void __sk_mem_reduce_allocated(struct sock *sk, int amount);
 void __sk_mem_reclaim(struct sock *sk, int amount);
 
 #define SK_MEM_QUANTUM ((int)PAGE_SIZE)

@@ -1950,6 +1952,9 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
+			unsigned int flags);
+void __sock_enqueue_skb(struct sock *sk, struct sk_buff *skb);
 int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b7de71f..bfb973a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c

@@ -323,6 +323,27 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
 }
 EXPORT_SYMBOL(__skb_free_datagram_locked);
 
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
+			unsigned int flags)
+{
+	int err = 0;
+
+	if (flags & MSG_PEEK) {
+		err = -ENOENT;
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		if (skb == skb_peek(&sk->sk_receive_queue)) {
+			__skb_unlink(skb, &sk->sk_receive_queue);
+			atomic_dec(&skb->users);
+			err = 0;
+		}
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+	}
+
+	atomic_inc(&sk->sk_drops);
+	return err;
+}
+EXPORT_SYMBOL(__sk_queue_drop_skb);
+
 /**
  *	skb_kill_datagram - Free a datagram skbuff forcibly
  *	@sk: socket

@@ -346,23 +367,10 @@ EXPORT_SYMBOL(__skb_free_datagram_locked);
 
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 {
-	int err = 0;
-
-	if (flags & MSG_PEEK) {
-		err = -ENOENT;
-		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
-			__skb_unlink(skb, &sk->sk_receive_queue);
-			atomic_dec(&skb->users);
-			err = 0;
-		}
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-	}
+	int err = __sk_queue_drop_skb(sk, skb, flags);
 
 	kfree_skb(skb);
-	atomic_inc(&sk->sk_drops);
 	sk_mem_reclaim_partial(sk);
-
 	return err;
 }
 EXPORT_SYMBOL(skb_kill_datagram);

diff --git a/net/core/sock.c b/net/core/sock.c
index 038e660..102f4d1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c

@@ -405,24 +405,12 @@ static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 }
 
 
-int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+void __sock_enqueue_skb(struct sock *sk, struct sk_buff *skb)
 {
 	unsigned long flags;
 	struct sk_buff_head *list = &sk->sk_receive_queue;
 
-	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
-		atomic_inc(&sk->sk_drops);
-		trace_sock_rcvqueue_full(sk, skb);
-		return -ENOMEM;
-	}
-
-	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
-		atomic_inc(&sk->sk_drops);
-		return -ENOBUFS;
-	}
-
 	skb->dev = NULL;
-	skb_set_owner_r(skb, sk);
 
 	/* we escape from rcu protected region, make sure we dont leak
 	 * a norefcounted dst

@@ -436,6 +424,24 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_data_ready(sk);
+}
+EXPORT_SYMBOL(__sock_enqueue_skb);
+
+int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
+		atomic_inc(&sk->sk_drops);
+		trace_sock_rcvqueue_full(sk, skb);
+		return -ENOMEM;
+	}
+
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+		atomic_inc(&sk->sk_drops);
+		return -ENOBUFS;
+	}
+
+	skb_set_owner_r(skb, sk);
+	__sock_enqueue_skb(sk, skb);
 	return 0;
 }
 EXPORT_SYMBOL(__sock_queue_rcv_skb);

@@ -2091,24 +2097,18 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 EXPORT_SYMBOL(sk_wait_data);
 
 /**
- *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
+ *	__sk_mem_raise_allocated - increase memory_allocated
  *	@sk: socket
  *	@size: memory size to allocate
+ *	@amt: pages to allocate
  *	@kind: allocation type
  *
- *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
- *	rmem allocation. This function assumes that protocols which have
- *	memory_pressure use sk_wmem_queued as write buffer accounting.
+ *	Similar to __sk_mem_schedule(), but does not update sk_forward_alloc
  */
-int __sk_mem_schedule(struct sock *sk, int size, int kind)
+int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 {
 	struct proto *prot = sk->sk_prot;
-	int amt = sk_mem_pages(size);
-	long allocated;
-
-	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-
-	allocated = sk_memory_allocated_add(sk, amt);
+	long allocated = sk_memory_allocated_add(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
 	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))

@@ -2169,9 +2169,6 @@ suppress_allocation:
 
 	trace_sock_exceed_buf_limit(sk, prot, allocated);
 
-	/* Alas. Undo changes. */
-	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-
 	sk_memory_allocated_sub(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)

@@ -2179,18 +2176,40 @@ suppress_allocation:
 
 	return 0;
 }
+EXPORT_SYMBOL(__sk_mem_raise_allocated);
+
+/**
+ *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
+ *	@sk: socket
+ *	@size: memory size to allocate
+ *	@kind: allocation type
+ *
+ *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
+ *	rmem allocation. This function assumes that protocols which have
+ *	memory_pressure use sk_wmem_queued as write buffer accounting.
+ */
+int __sk_mem_schedule(struct sock *sk, int size, int kind)
+{
+	int ret, amt = sk_mem_pages(size);
+
+	sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT;
+	ret = __sk_mem_raise_allocated(sk, size, amt, kind);
+	if (!ret)
+		sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT;
+	return ret;
+}
 EXPORT_SYMBOL(__sk_mem_schedule);
 
 /**
- *	__sk_mem_reclaim - reclaim memory_allocated
+ *	__sk_mem_reduce_allocated - reclaim memory_allocated
  *	@sk: socket
- *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
+ *	@amount: number of quanta
+ *
+ *	Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc
  */
-void __sk_mem_reclaim(struct sock *sk, int amount)
+void __sk_mem_reduce_allocated(struct sock *sk, int amount)
 {
-	amount >>= SK_MEM_QUANTUM_SHIFT;
 	sk_memory_allocated_sub(sk, amount);
-	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
 		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);

@@ -2199,6 +2218,19 @@ void __sk_mem_reclaim(struct sock *sk, int amount)
 	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
 		sk_leave_memory_pressure(sk);
 }
+EXPORT_SYMBOL(__sk_mem_reduce_allocated);
+
+/**
+ *	__sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated
+ *	@sk: socket
+ *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
+ */
+void __sk_mem_reclaim(struct sock *sk, int amount)
+{
+	amount >>= SK_MEM_QUANTUM_SHIFT;
+	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
+	__sk_mem_reduce_allocated(sk, amount);
+}
 EXPORT_SYMBOL(__sk_mem_reclaim);
 
 int sk_set_peek_off(struct sock *sk, int val)

-- 
1.8.3.1

[PATCH net-next v3 2/3] udp: implement memory accounting helpers

From: Paolo Abeni <pabeni@redhat.com>
Date: 2016-09-28 10:53:10

Avoid usage of common memory accounting functions, since
the logic is pretty much different.

To account for forward allocation, a couple of new atomic_t
members are added to udp_sock: 'mem_alloced' and 'can_reclaim'.
The current forward allocation is estimated as 'mem_alloced'
 minus 'sk_rmem_alloc'.

When the forward allocation can't cope with the packet to be
enqueued, 'mem_alloced' is incremented by the packet size
rounded-up to the next SK_MEM_QUANTUM.
After a dequeue, if under memory pressure, we try to partially
reclaim all forward allocated memory rounded down to an
SK_MEM_QUANTUM and 'mem_alloc' is decreased by that amount.
To protect against concurrent reclaim, we use 'can_reclaim' as
an unblocking synchronization point and let only one process
do the work.
sk->sk_forward_alloc is set after each memory update to the
currently estimated forward allocation, without any lock or
protection.
This value is updated/maintained only to expose some
semi-reasonable value to the eventual reader, and is guaranteed
to be 0 at socket destruction time.

The above needs custom memory reclaiming on shutdown, provided
by the udp_destruct_sock() helper, which completely reclaim
the allocated forward memory.

As a consequence of the above schema, enqueue to sk_error_queue
will cause fwd value to be understimated.

v1 -> v2:
  - use a udp specific destrctor to perform memory reclaiming
  - remove a couple of helpers, unneeded after the above cleanup
  - do not reclaim memory on dequeue if not under memory
    pressure
  - reworked the fwd accounting schema to avoid potential
    integer overflow

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/udp.h |   2 +
 include/net/udp.h   |   7 +++
 net/ipv4/udp.c      | 137 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 146 insertions(+)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index d1fd8cd..16aa22b 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h

@@ -42,6 +42,8 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask)
 struct udp_sock {
 	/* inet_sock has to be the first member */
 	struct inet_sock inet;
+	atomic_t	 mem_allocated;
+	atomic_t	 can_reclaim;
 #define udp_port_hash		inet.sk.__sk_common.skc_u16hashes[0]
 #define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
 #define udp_portaddr_node	inet.sk.__sk_common.skc_portaddr_node

diff --git a/include/net/udp.h b/include/net/udp.h
index ea53a87..b9563ef 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h

@@ -98,6 +98,8 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
 extern struct proto udp_prot;
 
 extern atomic_long_t udp_memory_allocated;
+extern int udp_memory_pressure;
+extern struct percpu_counter udp_sockets_allocated;
 
 /* sysctl variables for udp */
 extern long sysctl_udp_mem[3];

@@ -246,6 +248,10 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 }
 
 /* net/ipv4/udp.c */
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
+int udp_rmem_schedule(struct sock *sk, struct sk_buff *skb);
+void udp_enter_memory_pressure(struct sock *sk);
+
 void udp_v4_early_demux(struct sk_buff *skb);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,

@@ -258,6 +264,7 @@ void udp_flush_pending_frames(struct sock *sk);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int udp_init_sock(struct sock *sk);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7d96dc2..2218901 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c

@@ -131,6 +131,12 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min);
 atomic_long_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
+int udp_memory_pressure __read_mostly;
+EXPORT_SYMBOL(udp_memory_pressure);
+
+struct percpu_counter udp_sockets_allocated;
+EXPORT_SYMBOL(udp_sockets_allocated);
+
 #define MAX_UDP_PORTS 65536
 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)

@@ -1172,6 +1178,137 @@ out:
 	return ret;
 }
 
+static int __udp_forward(struct udp_sock *up, int rmem)
+{
+	return atomic_read(&up->mem_allocated) - rmem;
+}
+
+static bool udp_under_memory_pressure(const struct sock *sk)
+{
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
+	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
+		return true;
+
+	return READ_ONCE(udp_memory_pressure);
+}
+
+void udp_enter_memory_pressure(struct sock *sk)
+{
+	WRITE_ONCE(udp_memory_pressure, 1);
+}
+EXPORT_SYMBOL(udp_enter_memory_pressure);
+
+/* if partial != 0 do nothing if not under memory pressure and avoid
+ * reclaiming last quanta
+ */
+static void udp_rmem_release(struct sock *sk, int partial)
+{
+	struct udp_sock *up = udp_sk(sk);
+	int fwd, amt;
+
+	if (partial && !udp_under_memory_pressure(sk))
+		return;
+
+	/* we can have concurrent release; if we catch any conflict
+	 * we let only one of them do the work
+	 */
+	if (atomic_dec_if_positive(&up->can_reclaim) < 0)
+		return;
+
+	fwd = __udp_forward(up, atomic_read(&sk->sk_rmem_alloc));
+	if (fwd < SK_MEM_QUANTUM + partial) {
+		atomic_inc(&up->can_reclaim);
+		return;
+	}
+
+	amt = (fwd - partial) & ~(SK_MEM_QUANTUM - 1);
+	atomic_sub(amt, &up->mem_allocated);
+	atomic_inc(&up->can_reclaim);
+
+	__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
+	sk->sk_forward_alloc = fwd - amt;
+}
+
+static void udp_rmem_free(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+	udp_rmem_release(sk, 1);
+}
+
+int udp_rmem_schedule(struct sock *sk, struct sk_buff *skb)
+{
+	int fwd, amt, delta, rmem, err = -ENOMEM;
+	struct udp_sock *up = udp_sk(sk);
+
+	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+	if (rmem > sk->sk_rcvbuf)
+		goto drop;
+
+	fwd = __udp_forward(up, rmem);
+	if (fwd > 0)
+		goto no_alloc;
+
+	amt = sk_mem_pages(skb->truesize);
+	delta = amt << SK_MEM_QUANTUM_SHIFT;
+	if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
+		err = -ENOBUFS;
+		goto drop;
+	}
+
+	/* if we have some skbs in the error queue, the forward allocation could
+	 * be understimated, even below 0; avoid exporting such values
+	 */
+	fwd = atomic_add_return(delta, &up->mem_allocated) - rmem;
+	if (fwd < 0)
+		fwd = SK_MEM_QUANTUM;
+
+no_alloc:
+	sk->sk_forward_alloc = fwd;
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = udp_rmem_free;
+	return 0;
+
+drop:
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+	atomic_inc(&sk->sk_drops);
+	return err;
+}
+EXPORT_SYMBOL_GPL(udp_rmem_schedule);
+
+static void udp_destruct_sock(struct sock *sk)
+{
+	/* reclaim completely the forward allocated memory */
+	__skb_queue_purge(&sk->sk_receive_queue);
+	udp_rmem_release(sk, 0);
+	inet_sock_destruct(sk);
+}
+
+int udp_init_sock(struct sock *sk)
+{
+	struct udp_sock *up = udp_sk(sk);
+
+	atomic_set(&up->mem_allocated, 0);
+	atomic_set(&up->can_reclaim, 1);
+	sk->sk_destruct = udp_destruct_sock;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_init_sock);
+
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
+{
+	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
+		bool slow = lock_sock_fast(sk);
+
+		sk_peek_offset_bwd(sk, len);
+		unlock_sock_fast(sk, slow);
+	}
+	consume_skb(skb);
+}
+EXPORT_SYMBOL_GPL(skb_consume_udp);
+
 /**
  *	first_packet_length	- return length of first packet in receive queue
  *	@sk: socket

-- 
1.8.3.1

Re: [PATCH net-next v3 2/3] udp: implement memory accounting helpers

From: Eric Dumazet <hidden>
Date: 2016-09-29 01:43:01

On Wed, 2016-09-28 at 12:52 +0200, Paolo Abeni wrote:

quoted hunk

+static void udp_rmem_release(struct sock *sk, int partial)
+{
+	struct udp_sock *up = udp_sk(sk);
+	int fwd, amt;
+
+	if (partial && !udp_under_memory_pressure(sk))
+		return;
+
+	/* we can have concurrent release; if we catch any conflict
+	 * we let only one of them do the work
+	 */
+	if (atomic_dec_if_positive(&up->can_reclaim) < 0)
+		return;
+
+	fwd = __udp_forward(up, atomic_read(&sk->sk_rmem_alloc));
+	if (fwd < SK_MEM_QUANTUM + partial) {
+		atomic_inc(&up->can_reclaim);
+		return;
+	}
+
+	amt = (fwd - partial) & ~(SK_MEM_QUANTUM - 1);
+	atomic_sub(amt, &up->mem_allocated);
+	atomic_inc(&up->can_reclaim);
+
+	__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
+	sk->sk_forward_alloc = fwd - amt;
+}


This is racy... all these atomics make me nervous...

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help