From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by passt.top (Postfix) with ESMTP id B025B5A026F for ; Fri, 29 Sep 2023 17:20:27 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696000826; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=LpRBbnddCaF/hVLdM78pyfMywt3j1Ob9yMkIJVtmCe0=; b=F1pXZ0AigB1KhdwReJ4yHhz4rGxJ6BNRoh7zgEeWlfbZO/CXTv+Io4e8xY72iQl5YClsdm hofc8vr7BbrJ5bW4MukZlTO89WsmbbD3c52zEzFNp1Ex+qBvsFwYB2TusxvdLB7ffQCVsD wGwwAS4ZKweZzqx6S2RRO0qzY4uxzKk= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-614-D1ANdaHgMByhlShgl5gT1Q-1; Fri, 29 Sep 2023 11:20:24 -0400 X-MC-Unique: D1ANdaHgMByhlShgl5gT1Q-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id D55CF2810D63; Fri, 29 Sep 2023 15:20:23 +0000 (UTC) Received: from elisabeth (unknown [10.39.208.38]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 617B7492B05; Fri, 29 Sep 2023 15:20:22 +0000 (UTC) Date: Fri, 29 Sep 2023 17:20:15 +0200 From: Stefano Brivio To: David Gibson Subject: Re: [PATCH RFT 2/5] tcp: Reset STALLED flag on ACK only, check for pending socket data Message-ID: <20230929172015.3b5969bc@elisabeth> In-Reply-To: References: <20230922220610.58767-1-sbrivio@redhat.com> <20230922220610.58767-3-sbrivio@redhat.com> <20230927190533.2fc53bbf@elisabeth> Organization: Red Hat MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.10 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Message-ID-Hash: LY7CDTGLGEEDX32WUMAEM7AOUSYN553X X-Message-ID-Hash: LY7CDTGLGEEDX32WUMAEM7AOUSYN553X X-MailFrom: sbrivio@redhat.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: Matej Hrica , passt-dev@passt.top X-Mailman-Version: 3.3.8 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: On Thu, 28 Sep 2023 11:48:38 +1000 David Gibson wrote: > On Wed, Sep 27, 2023 at 07:05:33PM +0200, Stefano Brivio wrote: > > On Mon, 25 Sep 2023 13:07:24 +1000 > > David Gibson wrote: > > > > > I think the change itself here is sound, but I have some nits to pick > > > with the description and reasoning. > > > > > > On Sat, Sep 23, 2023 at 12:06:07AM +0200, Stefano Brivio wrote: > > > > In tcp_tap_handler(), we shouldn't reset the STALLED flag (indicating > > > > that we ran out of tap-side window space, or that all available > > > > socket data is already in flight -- better names welcome! > > > > > > Hmm.. when you put it like that it makes me wonder if those two quite > > > different conditions really need the same handling. Hrm.. I guess > > > both conditions mean that we can't accept data from the socket, even > > > if it's availble. > > > > Right. I mean, we can also call them differently... or maybe pick a > > name that reflects the outcome/handling instead of what happened. > > Sure, if we could think of one. Except, on second thoughts, I'm not > sure my characterization is correct. If the tap side window is full > then, indeed, we can't accept data from the socket. However if > everything we have is in flight that doesn't mean we couldn't put more > data into flight if it arrived. Right, but that's why we set EPOLLET... > That consideration, together with the way we use MSG_PEEK possibly > means that we fundamentally need to use edge-triggered interrupts - > with the additional trickiness that entails - to avoid busy polling. > Although even that only works if we get a new edge interrupt when data > is added to a buffer that's been PEEKed but not TRUNCed. If that's > not true the MSG_PEEK approach might be doomed :(. without EPOLLONESHOT, which wouldn't have this behaviour. From epoll(7): Since even with edge-triggered epoll, multiple events can be generated upon receipt of multiple chunks of data, the caller has the option to specify the EPOLLONESHOT flag [...] so yes, in general, when the socket has more data, we'll get another event. I didn't test this in an isolated case, perhaps we should, but from my memory it always worked. On the other hand, we could actually use EPOLLONESHOT in the other case, as an optimisation, when we're waiting for an ACK from the tap side. > > > > ) on any > > > > event: do that only if the first packet in a batch has the ACK flag > > > > set. > > > > > > "First packet in a batch" may not be accurate here - we're looking at > > > whichever packet we were up to before calling data_from_tap(). There > > > could have been earlier packets in the receive batch that were already > > > processed. > > > > Well, it depends on what we call "batch" -- here I meant the pool of > > packets (that are passed as a batch to tcp_tap_handler()). Yes, "pool" > > would be more accurate. > > Uh.. I don't think that actually helps. Remember pools aren't queues. > The point here is that is that the packet we're considering is not the > first of the batch/pool/whatever, but the first of what's left. Right, yes, I actually meant the sub-pool starting from the index (now) given by the caller. > > > This also raises the question of why the first data packet should be > > > particularly privileged here. > > > > No reason other than convenience, and yes, it can be subtly wrong. > > > > > I'm wondering if what we really want to > > > check is whether data_from_tap() advanced the ack pointer at all. > > > > Right, we probably should do that instead. > > Ok. > > > > I'm not clear on when the th->ack check would ever fail in practice: > > > aren't the only normal packets in a TCP connection without ACK the > > > initial SYN or an RST? We've handled the SYN case earlier, so should > > > we just have a blanket case above this that if we get a packet with > > > !ACK, we reset the connection? > > > > One thing that's legitimate (rarely seen, but I've seen it, I don't > > remember if the Linux kernel ever does that) is a segment without ACK, > > and without data, that just updates the window (for example after a > > zero window). > > > > If the sequence received/processed so far doesn't correspond to the > > latest sequence sent, omitting the ACK flag is useful so that the > > window update is not taken as duplicate ACK (that would trigger > > retransmission). > > Ah, ok, I wasn't aware of that case. On a second thought, in that case, we just got a window update, so it's very reasonable to actually check again if we can send more. Hence the check on th->ack is bogus anyway. > > > > Make sure we check for pending socket data when we reset it: > > > > reverting back to level-triggered epoll events, as tcp_epoll_ctl() > > > > does, isn't guaranteed to actually trigger a socket event. > > > > > > Which sure seems like a kernel bug. Some weird edge conditions for > > > edge-triggered seems expected, but this doesn't seem like valid > > > level-triggered semantics. > > > > Hmm, yes, and by doing a quick isolated test actually this seems to work > > as intended in the kernel. I should drop this and try again. > > > > > Hmmm... is toggling EPOLLET even what we want. IIUC, the heart of > > > what's going on here is that we can't take more data from the socket > > > until something happens on the tap side (either the window expands, or > > > it acks some data). In which case should we be toggling EPOLLIN on > > > the socket instead? That seems more explicitly to be saying to the > > > socket side "we don't currently care if you have data available". > > > > The reason was to act on EPOLLRDHUP at the same time. But well, we > > could just mask EPOLLIN and EPOLLRDHUP, then -- I guess that would make > > more sense. > > So specifically to mask EPOLLRDHUP as well? On the grounds that if > we're still chewing on what we got already we don't yet care that > we've reached the end, yes? Right. > So yes, explicitly masking both those > makes more sense to me.. except that as above, I suspect we can't have > level-triggered + MSG_PEEK + no busy polling all at once. Hmm, right, that's the other problem if we mask EPOLLIN: we won't get events on new data. I think EPOLLET is really what we need here, at least for the case where we are not necessarily waiting for an ACK. For the other case (window full), we can either mask EPOLLIN | EPOLLRDHUP or set EPOLLONESHOT (possibly slightly more complicated because we need to re-add the file descriptor). -- Stefano