From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 192EBA0548; Tue, 22 Jun 2021 19:32:16 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 999604003F; Tue, 22 Jun 2021 19:32:15 +0200 (CEST) Received: from mail-il1-f179.google.com (mail-il1-f179.google.com [209.85.166.179]) by mails.dpdk.org (Postfix) with ESMTP id AC7484003E for ; Tue, 22 Jun 2021 19:32:14 +0200 (CEST) Received: by mail-il1-f179.google.com with SMTP id q9so39425ilj.3 for ; Tue, 22 Jun 2021 10:32:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=7eVTv51l1AFvUf16XNyY0m5yCRCstOQBgKwariwzylM=; b=BzBboFig/R/C4zyut1qTnLjfCxKc5ANETwZqwoToMa0MPMsZuiOqHEAAVAlWM/W8qS 6GsUQ9hNmi4actrsYBFr+TO+n6EW3XNBi6GxzccNSmSKmbgukU60f3FFINX58LmGajWn p/9nWZxEMOWqceeV6ozzqAARVLxkjD/PqgChUy4ah+0/zuoBYpoAUXXT/0eoLV+WCtfw wrqfSWxPP1pa7fw5vLw/ZSssJxs1WHPXny8vrWKnG5OIWvZSDIgCLQiTKtfa8a9zv+OB WQ8DcLcS0SEsNRUliRx1CpIPjAnI9MBuD93A6Q9TfSmPsdTF7v73wSSMRyDJKENXRAKz 6euw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc:content-transfer-encoding; bh=7eVTv51l1AFvUf16XNyY0m5yCRCstOQBgKwariwzylM=; b=MinJcHhYmZ9VG2Xq3tZKAZxw8KP3ozWCW8hwDFFJHp7FEr2/27nNXBbijfbHycdzHL gKJGAVflLnwWyzNB0EgCeCs0FKT3gZxN0F+3HL9mqv3oFu+UpDDOYqPCsWZJXD7uRHnb vpdg0dCciNTIm01Qo86jTRLVCfpASfHv2pUYYKGplofpVGUqdGzjBfi3Oz26Q9gdgOxn Xx+FyIwi+dLeUiejzwyGBf80AMHTlyiJTFGw1KWoKM9JHM/LZc21e6N3U7ZZvaXcAOvB OgQFF484il8UJLaXPomUh3Sn+mCZ3j1oZ86Zml32bHXolMnbzIlGTrj/+teGXCMHFv6d juXg== X-Gm-Message-State: AOAM531VGiOpL3ujLQjw5Gvvvpvrf8+iXur+6JHYwDLl4E6fGssmgXMI M3on3SlC66R8HwZ7IgZiZ92z8A3tO04dhMpNdOc= X-Google-Smtp-Source: ABdhPJzzrCHD1Cmo+daE/kUWsmzGs/MyfnLQYJs2yNdTvkWnh1rzHd9IJUxLYmFG8FF7TIQmtKgFJaHb4EoVLxPm1FU= X-Received: by 2002:a05:6e02:e0e:: with SMTP id a14mr3356511ilk.294.1624383133911; Tue, 22 Jun 2021 10:32:13 -0700 (PDT) MIME-Version: 1.0 References: <1623763327-30987-1-git-send-email-fengchengwen@huawei.com> <98CBD80474FA8B44BF855DF32C47DC35C61860@smartserver.smartshare.dk> In-Reply-To: From: Jerin Jacob Date: Tue, 22 Jun 2021 23:01:47 +0530 Message-ID: To: Bruce Richardson Cc: fengchengwen , =?UTF-8?Q?Morten_Br=C3=B8rup?= , Thomas Monjalon , Ferruh Yigit , dpdk-dev , Nipun Gupta , Hemant Agrawal , Maxime Coquelin , Honnappa Nagarahalli , Jerin Jacob , David Marchand , Satananda Burla , Prasun Kapoor Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [dpdk-dev] [RFC PATCH] dmadev: introduce DMA device library X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On Fri, Jun 18, 2021 at 3:25 PM Bruce Richardson wrote: > > On Fri, Jun 18, 2021 at 11:22:28AM +0530, Jerin Jacob wrote: > > On Thu, Jun 17, 2021 at 2:46 PM Bruce Richardson > > wrote: > > > > > > On Wed, Jun 16, 2021 at 08:07:26PM +0530, Jerin Jacob wrote: > > > > On Wed, Jun 16, 2021 at 3:47 PM fengchengwen wrote: > > > > > > > > > > On 2021/6/16 15:09, Morten Br=C3=B8rup wrote: > > > > > >> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Bruce Ric= hardson > > > > > >> Sent: Tuesday, 15 June 2021 18.39 > > > > > >> > > > > > >> On Tue, Jun 15, 2021 at 09:22:07PM +0800, Chengwen Feng wrote: > > > > > >>> This patch introduces 'dmadevice' which is a generic type of = DMA > > > > > >>> device. > > > > > >>> > > > > > >>> The APIs of dmadev library exposes some generic operations wh= ich can > > > > > >>> enable configuration and I/O with the DMA devices. > > > > > >>> > > > > > >>> Signed-off-by: Chengwen Feng > > > > > >>> --- > > > > > >> Thanks for sending this. > > > > > >> > > > > > >> Of most interest to me right now are the key data-plane APIs. = While we > > > > > >> are > > > > > >> still in the prototyping phase, below is a draft of what we ar= e > > > > > >> thinking > > > > > >> for the key enqueue/perform_ops/completed_ops APIs. > > > > > >> > > > > > >> Some key differences I note in below vs your original RFC: > > > > > >> * Use of void pointers rather than iova addresses. While using= iova's > > > > > >> makes > > > > > >> sense in the general case when using hardware, in that it ca= n work > > > > > >> with > > > > > >> both physical addresses and virtual addresses, if we change = the APIs > > > > > >> to use > > > > > >> void pointers instead it will still work for DPDK in VA mode= , while > > > > > >> at the > > > > > >> same time allow use of software fallbacks in error cases, an= d also a > > > > > >> stub > > > > > >> driver than uses memcpy in the background. Finally, using io= va's > > > > > >> makes the > > > > > >> APIs a lot more awkward to use with anything but mbufs or si= milar > > > > > >> buffers > > > > > >> where we already have a pre-computed physical address. > > > > > >> * Use of id values rather than user-provided handles. Allowing= the > > > > > >> user/app > > > > > >> to manage the amount of data stored per operation is a bette= r > > > > > >> solution, I > > > > > >> feel than proscribing a certain about of in-driver tracking.= Some > > > > > >> apps may > > > > > >> not care about anything other than a job being completed, wh= ile other > > > > > >> apps > > > > > >> may have significant metadata to be tracked. Taking the user= -context > > > > > >> handles out of the API also makes the driver code simpler. > > > > > >> * I've kept a single combined API for completions, which diffe= rs from > > > > > >> the > > > > > >> separate error handling completion API you propose. I need t= o give > > > > > >> the > > > > > >> two function approach a bit of thought, but likely both coul= d work. > > > > > >> If we > > > > > >> (likely) never expect failed ops, then the specifics of erro= r > > > > > >> handling > > > > > >> should not matter that much. > > > > > >> > > > > > >> For the rest, the control / setup APIs are likely to be rather > > > > > >> uncontroversial, I suspect. However, I think that rather than = xstats > > > > > >> APIs, > > > > > >> the library should first provide a set of standardized stats l= ike > > > > > >> ethdev > > > > > >> does. If driver-specific stats are needed, we can add xstats l= ater to > > > > > >> the > > > > > >> API. > > > > > >> > > > > > >> Appreciate your further thoughts on this, thanks. > > > > > >> > > > > > >> Regards, > > > > > >> /Bruce > > > > > > > > > > > > I generally agree with Bruce's points above. > > > > > > > > > > > > I would like to share a couple of ideas for further discussion: > > > > > > > > > > > > I believe some of the other requirements and comments for generic D= MA will be > > > > > > > > 1) Support for the _channel_, Each channel may have different > > > > capabilities and functionalities. > > > > Typical cases are, each channel have separate source and destinatio= n > > > > devices like > > > > DMA between PCIe EP to Host memory, Host memory to Host memory, PCI= e > > > > EP to PCIe EP. > > > > So we need some notion of the channel in the specification. > > > > > > > > > > Can you share a bit more detail on what constitutes a channel in this= case? > > > Is it equivalent to a device queue (which we are flattening to indivi= dual > > > devices in this API), or to a specific configuration on a queue? > > > > It not a queue. It is one of the attributes for transfer. > > I.e in the same queue, for a given transfer it can specify the > > different "source" and "destination" device. > > Like CPU to Sound card, CPU to network card etc. > > > Ok. Thanks for clarifying. Do you think it's best given as a > device-specific parameter to the various functions, and NULL for hardware > that doesn't need it? Various functions won't scales. As we will have N number of channel and M number of ops. Things could blow up easily if we have separate functions and fast path function pointers space will run out easily in the dev structure. > > > > > > > > > > 2) I assume current data plane APIs are not thread-safe. Is it righ= t? > > > > > > > Yes. > > > > > > > > > > > 3) Cookie scheme outlined earlier looks good to me. Instead of havi= ng > > > > generic dequeue() API > > > > > > > > 4) Can split the rte_dmadev_enqueue_copy(uint16_t dev_id, void * sr= c, > > > > void * dst, unsigned int length); > > > > to two stage API like, Where one will be used in fastpath and other > > > > one will use used in slowpath. > > > > > > > > - slowpath API will for take channel and take other attributes for = transfer > > > > > > > > Example syantx will be: > > > > > > > > struct rte_dmadev_desc { > > > > channel id; > > > > ops ; // copy, xor, fill etc > > > > other arguments specific to dma transfer // it can be set > > > > based on capability. > > > > > > > > }; > > > > > > > > rte_dmadev_desc_t rte_dmadev_preprare(uint16_t dev_id, struct > > > > rte_dmadev_desc *dec); > > > > > > > > - Fastpath takes arguments that need to change per transfer along w= ith > > > > slow-path handle. > > > > > > > > rte_dmadev_enqueue(uint16_t dev_id, void * src, void * dst, unsigne= d > > > > int length, rte_dmadev_desc_t desc) > > > > > > > > This will help to driver to > > > > -Former API form the device-specific descriptors in slow path for = a > > > > given channel and fixed attributes per transfer > > > > -Later API blend "variable" arguments such as src, dest address wit= h > > > > slow-path created descriptors > > > > > > > > > > This seems like an API for a context-aware device, where the channel = is the > > > config data/context that is preserved across operations - is that cor= rect? > > > At least from the Intel DMA accelerators side, we have no concept of = this > > > context, and each operation is completely self-described. The locatio= n or > > > type of memory for copies is irrelevant, you just pass the src/dst > > > addresses to reference. > > > > it is not context-aware device. Each HW JOB is self-described. > > You can view it different attributes of transfer. > > > > > > > > > > > The above will give better performance and is the best trade-off c > > > > between performance and per transfer variables. > > > > > > We may need to have different APIs for context-aware and context-unaw= are > > > processing, with which to use determined by the capabilities discover= y. > > > Given that for these DMA devices the offload cost is critical, more s= o than > > > any other dev class I've looked at before, I'd like to avoid having A= PIs > > > with extra parameters than need to be passed about since that just ad= ds > > > extra CPU cycles to the offload. > > > > If driver does not support additional attributes and/or the > > application does not need it, rte_dmadev_desc_t can be NULL. > > So that it won't have any cost in the datapath. I think, we can go to > > different API > > cases if we can not abstract problems without performance impact. > > Otherwise, it will be too much > > pain for applications. > > Ok. Having one extra parameter ignored by some drivers should not be that > big of a deal. [With all these, we'll only really know for sure when > implemented and offload cost measured] > > > > > Just to understand, I think, we need to HW capabilities and how to > > have a common API. > > I assume HW will have some HW JOB descriptors which will be filled in > > SW and submitted to HW. > > In our HW, Job descriptor has the following main elements > > > > - Channel // We don't expect the application to change per transfer > > - Source address - It can be scatter-gather too - Will be changed per t= ransfer > > - Destination address - It can be scatter-gather too - Will be changed > > per transfer > > - Transfer Length - - It can be scatter-gather too - Will be changed > > per transfer > > - IOVA address where HW post Job completion status PER Job descriptor > > - Will be changed per transfer > > - Another sideband information related to channel // We don't expect > > the application to change per transfer > > - As an option, Job completion can be posted as an event to > > rte_event_queue too // We don't expect the application to change per > > transfer > > > > @Richardson, Bruce @fengchengwen @Hemant Agrawal > > > > Could you share the options for your HW descriptors which you are > > planning to expose through API like above so that we can easily > > converge on fastpath API > > > Taking the case of a simple copy op, the parameters we need are: > > * src > * dst > * length OK. Is it the case where no other attribute that supported in HW or you are not planning to expose that through DPDK generic DMA API. > > Depending on the specific hardware there will also be passed in the > descriptor a completion address, but we plan for these cases to always ha= ve > the completions written back to a set location so that we have essentiall= y > ring-writeback, as with the hardware which doesn't explicitly have a > separate completion address. Beyond that, I believe the only descriptor > fields we will use are just the flags field indicating the op type etc. OK. In HW, we need to have IOVA for completion address that's only the constraint. rest looks good to me. > > /Bruce