Netdev List
 help / color / mirror / Atom feed
* [PATCH net-next v8 0/9] net: bcmgenet: support larger MTUs
@ 2026-11-18 15:03 Nicolai Buchwitz
  2026-11-18 15:03 ` [PATCH net-next v8 1/9] net: bcmgenet: ring the doorbell when the last frame of a batch is dropped Nicolai Buchwitz
                   ` (8 more replies)
  0 siblings, 9 replies; 12+ messages in thread
From: Nicolai Buchwitz @ 2026-11-18 15:03 UTC (permalink / raw)
  To: Doug Berger, Florian Fainelli, Nicolai Buchwitz,
	Broadcom internal kernel review list, Andrew Lunn,
	David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni
  Cc: Florian Fainelli, netdev, linux-kernel, Pierre-Marin Leclercq,
	Dave Stevenson, Justin Chen

This is v8 of my genet series which adds larger MTU / jumbo packet support.

Larger MTU aka. jumbo frames are requested often by Raspberry Pi users, but
the hardware has its quirks with larger frames. Dave Stevenson's PoC [1] had
the receive side working, and thanks to Justin, who checked the RTL for what
the hardware does with long frames, I could add the missing puzzle pieces.

GENET never sets dev->max_mtu and the packet ready thresholds stay at their
2048 byte reset default, so long frames were dropped on receive and never
sent on transmit.

Patches 1 to 5 prepare the driver, patch 8 sets the MTU, as far as one
descriptor reaches (3564 bytes with 4K pages). Patch 9 reassembles what the
hardware hands up above that, which gets the ceiling to 16347 [2]. Patch 6
splits a frame ending just past the packet ready threshold, which otherwise
stops the transmitter [3]. Patch 7 builds the new rings before dropping the
old ones, so a failed MTU change leaves the interface alone.

Only v5 gets the larger MTU in this version. The TBUF sizing and the
transmit length width on v2 to v4 are unconfirmed, so those keep the
default until someone with the hardware or the RTL can say.

A split frame takes one descriptor more. Patch 6 adds it to the two limits
which 1e09af397bc7 and fbfd7cfd2019 put on the 32 descriptor rings, so the
queue stops one descriptor earlier and a frame is flattened one fragment
sooner.

Patch 8 needs bcmgenet_fini_dma() to clear rx_cbs and tx_cbs, which landed
in net as 1c1f51c3ee9c.

Tested on a Raspberry Pi CM4 (GENET v5), peer at the same MTU:
- MTU 1500: iperf3 TCP 942/936 Mbit/s, UDP 956 Mbit/s, unchanged
- MTU 9000: iperf3 TCP 991/986 Mbit/s, UDP 992 Mbit/s, no transmit loss
- MTU 1500 to 16347 with traffic and ifdown/ifup's
- pktgen at line rate, 3858/3872/3886 byte frames mixed with 64 byte ones
- raw frames across every receive descriptor boundary, byte exact
- CONFIG_MAX_SKB_FRAGS 31, 29 to 31 fragment frames in the split window
- every frame length from two below the threshold to 79 past it, linear
  and paged, each followed by a short frame, no stall
- the same with CONFIG_DMA_API_DEBUG, no error and no leaked mapping

Pierre-Marin Leclercq tested v5 on a Raspberry Pi 4.

[1] https://github.com/raspberrypi/linux/pull/7614
[2] https://github.com/raspberrypi/linux/pull/7617#issuecomment-5669564355
[3] https://github.com/raspberrypi/linux/pull/7617#issuecomment-5735557324

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
Changes in v8:
- Patch 5: the TDMA ring keeps its reset buffer size, it is unused (sashiko)
- Patch 6: the split window follows the DMA burst length, not a fixed 64
  (sashiko)
- Patch 6: track which descriptor owns the head mapping (sashiko)
- Patch 8: only v5 gets the larger MTU, v2 to v4 are unconfirmed
- Patch 8: replay a latched energy detect event after the MTU restart,
  bcmgenet_netif_stop() cancels the work that would have handled it
- Patch 9: count the frame a SOP with a bad length aborts (sashiko)
- Patch 9: clear frag_drop at the end of the dropped frame (sashiko)
- Dropped Florian's Reviewed-by on patch 5, it changed
- Link to v7: https://patch.msgid.link/20261112-nb-genet-mtu-nn-v2-v7-0-43a5d90b3256@tipi-net.de

To: Doug Berger <opendmb@gmail.com>
To: Florian Fainelli <florian.fainelli@broadcom.com>
To: Nicolai Buchwitz <nb@tipi-net.de>
To: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>
To: "David S. Miller" <davem@davemloft.net>
To: Eric Dumazet <edumazet@kernel.org>
To: Jakub Kicinski <kuba@kernel.org>
To: Paolo Abeni <pabeni@redhat.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

---
Nicolai Buchwitz (9):
      net: bcmgenet: ring the doorbell when the last frame of a batch is dropped
      net: bcmgenet: let the caller decide whether to start the PHY
      net: bcmgenet: allow a continuation descriptor without the alignment pad
      net: bcmgenet: rename ENET_MAX_MTU_SIZE to ENET_MAX_FRAME_LEN
      net: bcmgenet: derive the receive buffer length from the MTU
      net: bcmgenet: split frames that end just past the transmit threshold
      net: bcmgenet: build the DMA rings before giving up the running ones
      net: bcmgenet: allow the MTU to be changed
      net: bcmgenet: reassemble jumbo frames from status block fragments

 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 759 +++++++++++++++++++------
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  38 +-
 2 files changed, 613 insertions(+), 184 deletions(-)
---
base-commit: d6816d9a93b66a12bf01e10037e377f3333ad6cc
change-id: 20261002-nb-genet-mtu-nn-v2-402b5e6f306f

Best regards,
--  
Nicolai Buchwitz <nb@tipi-net.de>


^ permalink raw reply	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2026-11-19 18:06 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-18 15:03 [PATCH net-next v8 0/9] net: bcmgenet: support larger MTUs Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 1/9] net: bcmgenet: ring the doorbell when the last frame of a batch is dropped Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 2/9] net: bcmgenet: let the caller decide whether to start the PHY Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 3/9] net: bcmgenet: allow a continuation descriptor without the alignment pad Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 4/9] net: bcmgenet: rename ENET_MAX_MTU_SIZE to ENET_MAX_FRAME_LEN Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 5/9] net: bcmgenet: derive the receive buffer length from the MTU Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 6/9] net: bcmgenet: split frames that end just past the transmit threshold Nicolai Buchwitz
2026-11-19 18:05   ` netdev-bot+sashiko
2026-11-18 15:03 ` [PATCH net-next v8 7/9] net: bcmgenet: build the DMA rings before giving up the running ones Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 8/9] net: bcmgenet: allow the MTU to be changed Nicolai Buchwitz
2026-11-18 15:03 ` [PATCH net-next v8 9/9] net: bcmgenet: reassemble jumbo frames from status block fragments Nicolai Buchwitz
2026-11-19 18:05   ` netdev-bot+sashiko

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox