From: Jason Gunthorpe <jgg@nvidia.com>
To: Abhijit Gangurde <abhijit.gangurde@amd.com>
Cc: leon@kernel.org, brett.creeley@amd.com, andrew+netdev@lunn.ch,
davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, allen.hubbe@amd.com, nikhil.agarwal@amd.com,
linux-rdma@vger.kernel.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [for-next v2 2/4] net: ionic: Add PHC state page for user space access
Date: Mon, 25 May 2026 13:15:27 -0300 [thread overview]
Message-ID: <20260525161527.GA2492788@nvidia.com> (raw)
In-Reply-To: <20260512092623.1157199-3-abhijit.gangurde@amd.com>
On Tue, May 12, 2026 at 02:56:21PM +0530, Abhijit Gangurde wrote:
> +/*
> + * struct ib_uverbs_phc_state - timecounter state shared with userspace
> + *
> + * Drivers that use a software timecounter over a free-running hardware
> + * cycle counter can map this page read-only into userspace, allowing
> + * conversion of hardware timestamps to system time without a syscall.
> + *
> + * Synchronization uses a sequence counter (@seq): the kernel sets it
> + * to an odd value before updating, then to the next even value after.
> + * Userspace must retry the read if @seq is odd or changed during the read.
> + *
> + * @seq: Sequence counter (even = stable, odd = update in progress)
> + * @rsvd: Reserved
> + * @mask: Cycle counter bitmask
> + * @cycles: Cycle counter value at last update
> + * @nsec: Nanoseconds at last update
> + * @frac: Fractional nanoseconds at last update
> + * @mult: Cycle-to-nanosecond multiplier
> + * @shift: Cycle-to-nanosecond shift
> + * @overflow_period: Max interval (nsec) between reads before counter wraps
> + */
> +struct ib_uverbs_phc_state {
> + __u32 seq;
> + __u32 rsvd;
> + __aligned_u64 mask;
> + __aligned_u64 cycles;
> + __aligned_u64 nsec;
> + __aligned_u64 frac;
> + __u32 mult;
> + __u32 shift;
> + __aligned_u64 overflow_period;
> +};
If we are going to do this then let's re-use the mlx5 struct and protocol
struct mlx5_ib_clock_info {
__u32 sign;
__u32 resv;
__aligned_u64 nsec;
__aligned_u64 cycles;
__aligned_u64 frac;
__u32 mult;
__u32 shift;
__aligned_u64 mask;
__aligned_u64 overflow_period;
};
So at least two drivers can implement this new uAPI.
Jason
next prev parent reply other threads:[~2026-05-25 16:15 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-12 9:26 [for-next v2 0/4] ionic: RDMA completion timestamping support Abhijit Gangurde
2026-05-12 9:26 ` [for-next v2 1/4] net: ionic: register PHC for rdma timestamping Abhijit Gangurde
2026-05-12 9:26 ` [for-next v2 2/4] net: ionic: Add PHC state page for user space access Abhijit Gangurde
2026-05-25 16:15 ` Jason Gunthorpe [this message]
2026-05-12 9:26 ` [for-next v2 3/4] RDMA/ionic: map PHC state into user space Abhijit Gangurde
2026-05-12 9:26 ` [for-next v2 4/4] RDMA/ionic: add completion timestamp to CQE format Abhijit Gangurde
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=20260525161527.GA2492788@nvidia.com \
--to=jgg@nvidia.com \
--cc=abhijit.gangurde@amd.com \
--cc=allen.hubbe@amd.com \
--cc=andrew+netdev@lunn.ch \
--cc=brett.creeley@amd.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=nikhil.agarwal@amd.com \
--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