net/mlx4: TX helpers and deferred doorbell fix

Started by Joe Damato on Nov 17, 2026 · 12 messages from 3 authors · Last reply Nov 20, 2026

Series

5 patches, 2 files

+66 −32

Subsystems (4)

Show 1 more

Maintainers (7)

Show 3 more
WARM1d REVIEWED

Status: Reviewed.

open the first message on its own page

  1. [PATCH net-next v2 1/5] net/mlx4: factor VLAN parsing into mlx4_en_prep_vlan()
    Related patches
  2. [PATCH net-next v2 2/5] net/mlx4: factor csum flags into mlx4_en_csum_flags()
    Related patches
  3. [PATCH net-next v2 3/5] net/mlx4: factor HW loopback DMAC into mlx4_en_set_loopback_dmac()
    Related patches
  4. [PATCH net-next v2 4/5] net/mlx4: track whether a TX doorbell is pending
    Related patches
  5. [PATCH net-next v2 5/5] net/mlx4: flush pending doorbell when dropping a TX skb
    Related patches
Message details and related content
Greetings:

I am working on adding support for SW USO to mlx4 and the branch I have with
those changes locally is becoming a bit long, so I thought I'd try to break it
up to make it easier to review and merge by first sending this prep series.

FWIW: I plan to include more detailed data in my SW USO series, but I'm
working on SW USO because it significantly improves performance on hosts with
an IOMMU and an mlx4 NIC. I have a lot of hosts like that in production that
would benefit.

Anyway, back to this series.

Patches 1-3 factor common code out into helpers which currently have only 1
call site each, but I will be calling these helpers in the SW USO code I plan
to submit next.

Patch 4 and 5 add code to track when a doorbell is deferred so that it can
be written in the drop path. This is technically a bug fix (and I need this
to avoid the same type of bug in SW USO), but since I have never seen this bug
occur in reality I am sending to net-next.

Thanks,
Joe

v2:
  - Better cover letter subject line :)
  - Added Daniel's Reviewed-by to all patches, including patch 4 which has a
    minor change (hope that is OK, Daniel).
  - Patch 4:
    - Change the struct placement to address Sashiko's review. The new flag
      is moved to the area of the struct marked as "cache line used and
      dirtied in mlx4_en_xmit" and tx_dropped is moved down with the fields
      not used in the fast path since it is only written on drop and read
      for stats.
    - Update the commit message to explain this.

v1: https://lore.kernel.org/netdev/20261110231304.1859217-1-joe@dama.to/

Joe Damato (5):

15 more lines

[PATCH net-next v2 1/5] net/mlx4: factor VLAN parsing into mlx4_en_prep_vlan()

Message details and related content
Extract the code which converts an skb VLAN tag into WQE fields into a
small helper. This helper will be used by a follow-up series implementing
software USO, to avoid code duplication.

Signed-off-by: Joe Damato <redacted>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 33 ++++++++++++++--------
 1 file changed, 21 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c5d564e5a581..00210dbae1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -861,6 +861,26 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv,
 	return false;
 }
 
+static bool mlx4_en_prep_vlan(const struct sk_buff *skb,
+			      union mlx4_wqe_qpn_vlan *qpn_vlan)
+{
+	u16 vlan_proto;
+
+	if (!skb_vlan_tag_present(skb))
+		return false;
+
+	qpn_vlan->vlan_tag = cpu_to_be16(skb_vlan_tag_get(skb));
+	vlan_proto = be16_to_cpu(skb->vlan_proto);
+	if (vlan_proto == ETH_P_8021AD)
+		qpn_vlan->ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
+	else if (vlan_proto == ETH_P_8021Q)
+		qpn_vlan->ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
+	else
+		qpn_vlan->ins_vlan = 0;
+
+	return true;
+}
+
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -902,19 +922,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	nr_txbb = desc_size >> LOG_TXBB_SIZE;
 
 	bf_ok = ring->bf_enabled;
-	if (skb_vlan_tag_present(skb)) {
-		u16 vlan_proto;
-
-		qpn_vlan.vlan_tag = cpu_to_be16(skb_vlan_tag_get(skb));
-		vlan_proto = be16_to_cpu(skb->vlan_proto);
-		if (vlan_proto == ETH_P_8021AD)
-			qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
-		else if (vlan_proto == ETH_P_8021Q)
-			qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
-		else
-			qpn_vlan.ins_vlan = 0;
+	if (mlx4_en_prep_vlan(skb, &qpn_vlan))
 		bf_ok = false;
-	}
 
 	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
 
-- 
2.53.1-Meta

[PATCH net-next v2 2/5] net/mlx4: factor csum flags into mlx4_en_csum_flags()

Message details and related content
Extract the code which converts skb csum fields to WQE fields into a
helper. This helper will be used by a follow-up series implementing
software USO, to reduce code duplication.

Signed-off-by: Joe Damato <redacted>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 00210dbae1c3..f6059b533eac 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -861,6 +861,16 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv,
 	return false;
 }
 
+static __be32 mlx4_en_csum_flags(const struct sk_buff *skb)
+{
+	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL))
+		return 0;
+	if (skb->encapsulation)
+		return cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM);
+
+	return cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | MLX4_WQE_CTRL_TCP_UDP_CSUM);
+}
+
 static bool mlx4_en_prep_vlan(const struct sk_buff *skb,
 			      union mlx4_wqe_qpn_vlan *qpn_vlan)
 {
@@ -891,12 +901,12 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct mlx4_wqe_data_seg *data;
 	struct mlx4_en_tx_info *tx_info;
 	u32 __maybe_unused ring_cons;
+	__be32 op_own, csum_flags;
 	int tx_ind;
 	int nr_txbb;
 	int desc_size;
 	int real_size;
 	u32 index, bf_index;
-	__be32 op_own;
 	int lso_header_size;
 	void *fragptr = NULL;
 	bool bounce = false;
@@ -991,12 +1001,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Prepare ctrl segment apart opcode+ownership, which depends on
 	 * whether LSO is used */
 	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
-	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
-		if (!skb->encapsulation)
-			tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
-								 MLX4_WQE_CTRL_TCP_UDP_CSUM);
-		else
-			tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM);
+
+	csum_flags = mlx4_en_csum_flags(skb);
+	if (csum_flags) {
+		tx_desc->ctrl.srcrb_flags |= csum_flags;
 		ring->tx_csum++;
 	}
 
-- 
2.53.1-Meta

[PATCH net-next v2 3/5] net/mlx4: factor HW loopback DMAC into mlx4_en_set_loopback_dmac()

Message details and related content
Extract the code which copies the destination MAC into the WQE for
eSwitch loopback into a helper. This helper will be used by a follow-up
series implementing software USO, so USO packets between functions on
the same port are looped back too.

Signed-off-by: Joe Damato <redacted>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 28 ++++++++++++++--------
 1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f6059b533eac..97f27e005810 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -871,6 +871,23 @@ static __be32 mlx4_en_csum_flags(const struct sk_buff *skb)
 	return cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | MLX4_WQE_CTRL_TCP_UDP_CSUM);
 }
 
+static void mlx4_en_set_loopback_dmac(const struct mlx4_en_priv *priv,
+				      struct mlx4_en_tx_desc *tx_desc,
+				      const struct sk_buff *skb)
+{
+	struct ethhdr *ethh;
+
+	if (!(priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK))
+		return;
+
+	/* Copy dst mac address to wqe. This allows loopback in eSwitch,
+	 * so that VFs and PF can communicate with each other
+	 */
+	ethh = (struct ethhdr *)skb->data;
+	tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest);
+	tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2));
+}
+
 static bool mlx4_en_prep_vlan(const struct sk_buff *skb,
 			      union mlx4_wqe_qpn_vlan *qpn_vlan)
 {
@@ -1008,16 +1025,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		ring->tx_csum++;
 	}
 
-	if (priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK) {
-		struct ethhdr *ethh;
-
-		/* Copy dst mac address to wqe. This allows loopback in eSwitch,
-		 * so that VFs and PF can communicate with each other
-		 */
-		ethh = (struct ethhdr *)skb->data;
-		tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest);
-		tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2));
-	}
+	mlx4_en_set_loopback_dmac(priv, tx_desc, skb);
 
 	/* Handle LSO (TSO) packets */
 	if (lso_header_size) {
-- 
2.53.1-Meta

[PATCH net-next v2 4/5] net/mlx4: track whether a TX doorbell is pending

Message details and related content
When the stack sets xmit_more, mlx4_en_xmit() skips the doorbell and
relies on a later call in the same batch to write it. Nothing records
that a doorbell is owed, so a path that ends the batch without writing
the doorbell leaves the WQEs posted before it unannounced to HW.

Add ring->doorbell_pending, set when the doorbell is deferred and
cleared whenever a doorbell or a BlueFlame write is issued, so such a
path can flush the deferred doorbell.

Place the flag in the cache line dirtied by mlx4_en_xmit(), next to
prod. That line has no room left, so move tx_dropped, which is only
written when an skb is dropped, to the end of the struct among the
fields not used in the fast path.

Signed-off-by: Joe Damato <redacted>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
---
v2:
  - doorbell_pending moved to the area of the struct marked as cache line
    used and dirtied in mlx4_en_xmit. In exchange, tx_dropped is moved
    among fields not written in the fast path. It is only written for
    drops and is read for stats.
  - Update the commit message.

 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 9 +++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++-
 2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 97f27e005810..123071a47bed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -194,6 +194,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	ring->prod = 0;
 	ring->cons = 0xffffffff;
 	ring->last_nr_txbb = 1;
+	ring->doorbell_pending = false;
 	memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
 	memset(ring->buf, 0, ring->buf_size);
 	ring->free_tx_desc = mlx4_en_free_tx_desc;
@@ -757,6 +758,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring)
 	iowrite32be(
 #endif
 		  (__force u32)ring->doorbell_qpn, ring->doorbell_address);
+	ring->doorbell_pending = false;
 }
 
 static void mlx4_en_tx_write_desc(struct mlx4_en_tx_ring *ring,
@@ -784,16 +786,19 @@ static void mlx4_en_tx_write_desc(struct mlx4_en_tx_ring *ring,
 		wmb();
 
 		ring->bf.offset ^= ring->bf.buf_size;
+		ring->doorbell_pending = false;
 	} else {
 		/* Ensure new descriptor hits memory
 		 * before setting ownership of this descriptor to HW
 		 */
 		dma_wmb();
 		tx_desc->ctrl.owner_opcode = op_own;
-		if (send_doorbell)
+		if (send_doorbell) {
 			mlx4_en_xmit_doorbell(ring);
-		else
+		} else {
 			ring->xmit_more++;
+			ring->doorbell_pending = true;
+		}
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index aab97694f86b..c28d5213cccd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -274,7 +274,7 @@ struct mlx4_en_tx_ring {
 
 	/* cache line used and dirtied in mlx4_en_xmit() */
 	u32			prod ____cacheline_aligned_in_smp;
-	unsigned int		tx_dropped;
+	bool			doorbell_pending;
 	unsigned long		bytes;
 	unsigned long		packets;
 	unsigned long		tx_csum;
@@ -311,6 +311,7 @@ struct mlx4_en_tx_ring {
 	enum mlx4_qp_state	sp_qp_state;
 	u16			sp_stride;
 	u16			sp_cqn;	/* index of port CQ associated with this ring */
+	unsigned int		tx_dropped;
 } ____cacheline_aligned_in_smp;
 
 struct mlx4_en_rx_desc {
-- 
2.53.1-Meta

[PATCH net-next v2 5/5] net/mlx4: flush pending doorbell when dropping a TX skb

Message details and related content
If mlx4_en_xmit drops an skb (for example because DMA mapping fails) and
that skb happens to be the last one in the batch, the doorbell for the
WQEs posted earlier in the batch isn't written.

The queue stays awake, though, so those WQEs are eventually announced to
the HW after the next TX, but that depends on traffic and could induce
latency.

Avoid all of that by writing the pending doorbell in the drop path.

Signed-off-by: Joe Damato <redacted>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 3 +++
 1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 123071a47bed..3166837711be 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -1135,6 +1135,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 tx_drop_count:
 	ring->tx_dropped++;
+	/* an earlier skb in this batch may have deferred the doorbell */
+	if (ring->doorbell_pending)
+		mlx4_en_xmit_doorbell(ring);
 tx_drop:
 	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
-- 
2.53.1-Meta
Message details and related content
Hi!

This is an automated message. This series looks like a fix, but its
commit messages seem to be missing some information:

 - What hardware the change was tested on. For driver fixes please
   mention the device (and if relevant firmware version) used for
   testing, or say that the change was not tested on real hardware.

Please do not repost the series just to address the above. Instead,
reply to this email with the missing information, so that reviewers
can take it into account.

*IMPORTANT*: If you do repost (for other reasons) - please include
the relevant info in the cover letter or commit messages.
-- 
The evaluation is done by an LLM so it may be wrong, if you think
that is the case please reply and explain.
Message details and related content
On Tue, Nov 17, 2026 at 03:57:47PM +0000, netdev-bot+sinfo@kernel.org wrote:
Hi!

This is an automated message. This series looks like a fix, but its
commit messages seem to be missing some information:

 - What hardware the change was tested on. For driver fixes please
   mention the device (and if relevant firmware version) used for
   testing, or say that the change was not tested on real hardware.

Please do not repost the series just to address the above. Instead,
reply to this email with the missing information, so that reviewers
can take it into account.

*IMPORTANT*: If you do repost (for other reasons) - please include
the relevant info in the cover letter or commit messages.
-- 
The evaluation is done by an LLM so it may be wrong, if you think
that is the case please reply and explain.
I should have updated the cover letter to address this, but I forgot (sorry).

As I mentioned in the v1:

I ran this code as part of a larger series that also includes SW USO
support on an mlx4 machine.

The only fix in this series is the deferred doorbell flush (patch 5), but I
need the other code (patches 1-4) for SW USO support I plan to submit next
if this series is applied.

Since patch 5 fixes an issue I've never actually seen, I am sending this
series to net-next without a fixes tag.
Message details and related content
On Tue, 17 Nov 2026 08:43:25 -0800 Joe Damato wrote:
The only fix in this series is the deferred doorbell flush (patch 5), but I
need the other code (patches 1-4) for SW USO support I plan to submit next
if this series is applied.
Not sure if this is what you meant but this may read as if you were
sending a fix for net-next for convenience of sending more patches.
To be clear - that's not a valid excuse. That said, here, we're talking
about a 10 year old error path bug which nobody apparently have been
bothered by. We don't have space in net for such things at this point
of the cycle, anyway :S

Tariq, could you ack?
Message details and related content
On Thu, Nov 19, 2026 at 02:38:52PM -0800, Jakub Kicinski wrote:
On Tue, 17 Nov 2026 08:43:25 -0800 Joe Damato wrote:
quoted
The only fix in this series is the deferred doorbell flush (patch 5), but I
need the other code (patches 1-4) for SW USO support I plan to submit next
if this series is applied.
Not sure if this is what you meant but this may read as if you were
sending a fix for net-next for convenience of sending more patches.
To be clear - that's not a valid excuse. That said, here, we're talking
about a 10 year old error path bug which nobody apparently have been
bothered by. We don't have space in net for such things at this point
of the cycle, anyway :S
I'm probably just being dense and not following what you mean here.

I was looking at a local branch that implements SW USO in mlx4 and it was
getting to be quite long with a lot of patches. I thought that breaking it up
and moving some of the patches into a standalone series would make it easier
to review.

I suppose you are saying I should have just kept it as one longer series,
instead?

Sorry if I am not following what you mean.
Message details and related content
On Thu, 19 Nov 2026 15:34:21 -0800 Joe Damato wrote:
On Thu, Nov 19, 2026 at 02:38:52PM -0800, Jakub Kicinski wrote:
quoted
On Tue, 17 Nov 2026 08:43:25 -0800 Joe Damato wrote:  
quoted
The only fix in this series is the deferred doorbell flush (patch 5), but I
need the other code (patches 1-4) for SW USO support I plan to submit next
if this series is applied.  
Not sure if this is what you meant but this may read as if you were
sending a fix for net-next for convenience of sending more patches.
To be clear - that's not a valid excuse. That said, here, we're talking
about a 10 year old error path bug which nobody apparently have been
bothered by. We don't have space in net for such things at this point
of the cycle, anyway :S  
I'm probably just being dense and not following what you mean here.

I was looking at a local branch that implements SW USO in mlx4 and it was
getting to be quite long with a lot of patches. I thought that breaking it up
and moving some of the patches into a standalone series would make it easier
to review.

I suppose you are saying I should have just kept it as one longer series,
instead?
No, not at all. 

You said "The only fix in this series is....I plan to submit next if
this series is applied". Which triggers my suspicion that you packed
a fix with -next stuff for expedience / not having to wait for a
net->net-next merge before you send the rest of USO. I don't think
that's what you meant but since I had to ping Tariq anyway I decided
to wag a finger at you. 

IOW I'm commenting purely on packing what can be perceived as a net
fix in a net-next series.
Message details and related content
On Thu, Nov 19, 2026 at 04:05:59PM -0800, Jakub Kicinski wrote:
On Thu, 19 Nov 2026 15:34:21 -0800 Joe Damato wrote:
quoted
On Thu, Nov 19, 2026 at 02:38:52PM -0800, Jakub Kicinski wrote:
quoted
On Tue, 17 Nov 2026 08:43:25 -0800 Joe Damato wrote:  
quoted
The only fix in this series is the deferred doorbell flush (patch 5), but I
need the other code (patches 1-4) for SW USO support I plan to submit next
if this series is applied.  
Not sure if this is what you meant but this may read as if you were
sending a fix for net-next for convenience of sending more patches.
To be clear - that's not a valid excuse. That said, here, we're talking
about a 10 year old error path bug which nobody apparently have been
bothered by. We don't have space in net for such things at this point
of the cycle, anyway :S  
I'm probably just being dense and not following what you mean here.

I was looking at a local branch that implements SW USO in mlx4 and it was
getting to be quite long with a lot of patches. I thought that breaking it up
and moving some of the patches into a standalone series would make it easier
to review.

I suppose you are saying I should have just kept it as one longer series,
instead?
No, not at all. 

You said "The only fix in this series is....I plan to submit next if
this series is applied". Which triggers my suspicion that you packed
a fix with -next stuff for expedience / not having to wait for a
net->net-next merge before you send the rest of USO. I don't think
that's what you meant but since I had to ping Tariq anyway I decided
to wag a finger at you. 
Oh, OK.

To be clear: I was not trying to circumvent the system or the rules and if you
(or Tariq) prefers, I am happy to peel this apart and send it to net in the
next cycle.

I am not trying to rush anything in; I'm happy to wait until the next
cycle if that is what is preferred.

I included it to net-next because my perception (which is clearly incorrect)
is that net is much stricter lately and issues which have never been triggered
IRL or reported by users may not meet the bar required for net.

I'll be more careful in the future; I just legitimately did not think this
change would be accepted to net.
IOW I'm commenting purely on packing what can be perceived as a net
fix in a net-next series.
Sorry for the confusion I caused :(
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help