RE: [EXTERNAL] Re: [PATCH net-next v2 0/7] net: mana: harden the HWC and add dynamic queue depth

[Long Li]

> -----Original Message-----
> From: Paolo Abeni <pabeni@xxxxxxxxxx>
> Sent: Tuesday, July 28, 2026 3:53 AM
> To: Long Li <longli@xxxxxxxxxxxxx>; Konstantin Taranov
> <kotaranov@xxxxxxxxxxxxx>; Jakub Kicinski <kuba@xxxxxxxxxx>; David S .
> Miller <davem@xxxxxxxxxxxxx>; Eric Dumazet <edumazet@xxxxxxxxxx>;
> Andrew Lunn <andrew+netdev@xxxxxxx>; Jason Gunthorpe <jgg@xxxxxxxx>;
> Leon Romanovsky <leon@xxxxxxxxxx>; Haiyang Zhang
> <haiyangz@xxxxxxxxxxxxx>; KY Srinivasan <kys@xxxxxxxxxxxxx>; Wei Liu
> <wei.liu@xxxxxxxxxx>; Dexuan Cui <DECUI@xxxxxxxxxxxxx>;
> shradhagupta@xxxxxxxxxxxxxxxxxxx; Simon Horman <horms@xxxxxxxxxx>;
> ernis@xxxxxxxxxxxxxxxxxxx; stephen@xxxxxxxxxxxxxxxxxx
> Cc: netdev@xxxxxxxxxxxxxxx; linux-rdma@xxxxxxxxxxxxxxx; linux-
> hyperv@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx
> Subject: [EXTERNAL] Re: [PATCH net-next v2 0/7] net: mana: harden the HWC
> and add dynamic queue depth
> 
> On 7/22/26 1:43 AM, Long Li wrote:
> > This series hardens the MANA Hardware Channel (HWC) control-plane path
> > and then builds on that to support a dynamic HWC queue depth.
> >
> > The HWC is the command channel the driver uses to talk to the device.
> > Today it is created at a fixed depth of one outstanding request, and
> > several of its lookup and teardown paths predate the RCU and
> > DMA-lifetime rules they now need to follow.  Raising the queue depth
> > and allowing concurrent commands makes those latent races reachable,
> > so the fixes come first and the feature builds on them.
> >
> > Patches 1-5 are fixes for pre-existing HWC bugs, each with a Fixes: tag:
> >
> >   1: cq_table was a plain pointer array freed with no grace period while
> >      the EQ interrupt handler dereferenced it; put it under RCU.
> >   2: the HWC RQ and SQ were sized with each other's message size, so a
> >      response could overflow the RQ buffer and the RX slot stride was
> >      computed with the wrong size.
> >   3: comp_buf was freed before the EQ was destroyed, so a late completion
> >      handler could touch freed memory.
> >   4: the RX path consumed device-supplied lengths and indices without
> >      validation; validate them before use (this matters for confidential
> >      VMs, where the DMA buffer is shared with the host).
> >   5: a failed mana_hwc_establish_channel() could leave live MST entries
> >      while the driver freed the queue buffers, and destroy_channel() freed
> >      the TXQ/RXQ before the EQ was quiesced; add a setup_active teardown
> >      gate and destroy the CQ first.
> 
> Fixes should go via the net tree. Targeting net-next to avoid waiting the
> merge to post the dependant features is not a valid reason.
> 
> Also both sashikos agrees pcie_fpr() in patch 5 is not the correct function to
> be used there.
> 
> Also please note the expectations WRT LLMs feedback, commit c82ff94592fb.
> 
> /P

I'll post Patch 1-5 to net.

Thank you,
Long