From: Peter Oh <peter.oh@eero.com> To: Adrian Chadd <adrian@freebsd.org> Cc: Zhi Chen <zhichen@codeaurora.org>, ath10k <ath10k@lists.infradead.org>, linux-wireless@vger.kernel.org Subject: Re: [PATCH RFC] Revert "ath10k: fix DMA related firmware crashes on multiple devices" Date: Tue, 29 Oct 2019 23:04:32 -0700 [thread overview] Message-ID: <8211c499-ec34-d1de-221e-e037e1fd0332@eero.com> (raw) In-Reply-To: <CAJ-VmonXbUQ=Gv9fBbpN+ez25c3Pz+xxLoL67etMdC0Q+bwyXg@mail.gmail.com> On 10/22/19 11:24 AM, Adrian Chadd wrote: > On Tue, 22 Oct 2019 at 10:17, Peter Oh <peter.oh@eero.com> wrote: >> >> On 10/22/19 1:57 AM, Zhi Chen wrote: >>> This reverts commit 76d164f582150fd0259ec0fcbc485470bcd8033e. >>> PCIe hung issue was observed on multiple platforms. The issue was reproduced >>> when DUT was configured as AP and associated with 50+ STAs. >>> >>> With PCIe protocol analyzer, we can see DMA Read crossing 4KB boundary when >>> issue happened. It broke PCIe spec and caused PCIe stuck. Can you elaborate how 64 bytes DMA size breaks PCIe spec? >> How can you say value 0 (I believe it's 64 bytes) DMA burst size causes >> the symptom and 1 fixes it? > > +1 to this question. > > Also, shouldn't the DMA engine be doing what the firmware says? Is the > firmware/copy engine actually somehow bursting / prefetching across a > 4K page boundary? > > Surely this is something that can be fixed in software/firmware by > correctly configuring up buffer size/offsets? > > > > -adrian
WARNING: multiple messages have this Message-ID (diff)
From: Peter Oh <peter.oh@eero.com> To: Adrian Chadd <adrian@freebsd.org> Cc: Zhi Chen <zhichen@codeaurora.org>, linux-wireless@vger.kernel.org, ath10k <ath10k@lists.infradead.org> Subject: Re: [PATCH RFC] Revert "ath10k: fix DMA related firmware crashes on multiple devices" Date: Tue, 29 Oct 2019 23:04:32 -0700 [thread overview] Message-ID: <8211c499-ec34-d1de-221e-e037e1fd0332@eero.com> (raw) In-Reply-To: <CAJ-VmonXbUQ=Gv9fBbpN+ez25c3Pz+xxLoL67etMdC0Q+bwyXg@mail.gmail.com> On 10/22/19 11:24 AM, Adrian Chadd wrote: > On Tue, 22 Oct 2019 at 10:17, Peter Oh <peter.oh@eero.com> wrote: >> >> On 10/22/19 1:57 AM, Zhi Chen wrote: >>> This reverts commit 76d164f582150fd0259ec0fcbc485470bcd8033e. >>> PCIe hung issue was observed on multiple platforms. The issue was reproduced >>> when DUT was configured as AP and associated with 50+ STAs. >>> >>> With PCIe protocol analyzer, we can see DMA Read crossing 4KB boundary when >>> issue happened. It broke PCIe spec and caused PCIe stuck. Can you elaborate how 64 bytes DMA size breaks PCIe spec? >> How can you say value 0 (I believe it's 64 bytes) DMA burst size causes >> the symptom and 1 fixes it? > > +1 to this question. > > Also, shouldn't the DMA engine be doing what the firmware says? Is the > firmware/copy engine actually somehow bursting / prefetching across a > 4K page boundary? > > Surely this is something that can be fixed in software/firmware by > correctly configuring up buffer size/offsets? > > > > -adrian _______________________________________________ ath10k mailing list ath10k@lists.infradead.org http://lists.infradead.org/mailman/listinfo/ath10k
next prev parent reply other threads:[~2019-10-30 6:04 UTC|newest] Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-10-22 8:57 [PATCH RFC] Revert "ath10k: fix DMA related firmware crashes on multiple devices" Zhi Chen 2019-10-22 8:57 ` Zhi Chen 2019-10-22 10:07 ` Tom Psyborg 2019-10-22 10:07 ` Tom Psyborg 2019-10-30 2:44 ` zhichen 2019-10-30 2:44 ` zhichen 2019-11-06 10:01 ` Tom Psyborg 2019-11-06 10:01 ` Tom Psyborg 2019-11-07 5:35 ` zhichen 2019-11-07 5:35 ` zhichen 2019-10-22 17:16 ` Peter Oh 2019-10-22 17:16 ` Peter Oh 2019-10-22 18:24 ` Adrian Chadd 2019-10-22 18:24 ` Adrian Chadd 2019-10-30 6:04 ` Peter Oh [this message] 2019-10-30 6:04 ` Peter Oh 2019-10-30 6:28 ` zhichen 2019-10-30 6:28 ` zhichen 2019-10-30 6:16 ` zhichen 2019-10-30 6:16 ` zhichen 2019-10-30 23:01 ` Peter Oh 2019-10-30 23:01 ` Peter Oh 2019-11-03 15:36 ` Tom Psyborg 2019-11-03 15:36 ` Tom Psyborg 2019-11-04 18:41 ` Peter Oh 2019-11-04 18:41 ` Peter Oh
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=8211c499-ec34-d1de-221e-e037e1fd0332@eero.com \ --to=peter.oh@eero.com \ --cc=adrian@freebsd.org \ --cc=ath10k@lists.infradead.org \ --cc=linux-wireless@vger.kernel.org \ --cc=zhichen@codeaurora.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.