From: Thomas Gleixner <tglx@linutronix.de> To: Bjorn Helgaas <helgaas@kernel.org>, Kalle Valo <kvalo@codeaurora.org> Cc: Govind Singh <govinds@codeaurora.org>, linux-pci@vger.kernel.org, linux-wireless@vger.kernel.org, Devin Bayer <dev@doubly.so>, Thomas Krause <thomaskrause@posteo.de>, ath11k@lists.infradead.org, Christoph Hellwig <hch@lst.de> Subject: Re: pci_alloc_irq_vectors fails ENOSPC for XPS 13 9310 Date: Tue, 03 Nov 2020 22:08:49 +0100 [thread overview] Message-ID: <874km61732.fsf@nanos.tec.linutronix.de> (raw) In-Reply-To: <20201103160838.GA246433@bjorn-Precision-5520> On Tue, Nov 03 2020 at 10:08, Bjorn Helgaas wrote: > On Tue, Nov 03, 2020 at 08:49:06AM +0200, Kalle Valo wrote: >> Bjorn Helgaas <helgaas@kernel.org> writes: >> > On Mon, Nov 02, 2020 at 08:49:51PM +0200, Kalle Valo wrote: >> >> Thomas Krause <thomaskrause@posteo.de> writes: >> >> >> >> >> I had the same problem as well back in the days, for me enabling >> >> >> CONFIG_IRQ_REMAP helped. If it helps for you also I wonder if we should >> >> >> mention that in the ath11k warning above :) Interrupt remapping only helps when the device supports only MSI (not MSI-X) because x86 (kernel) does not support multiple MSI interrupts without remapping. So if only MSI is available then you get exactly _one_ MSI vector without remapping. >> >> > CONFIG_IRQ_REMAP did not do the trick. The config alone does not help. The hardware has to support it and the BIOS has to enable it. Check the BIOS for a switch which is named 'VT-d' or such. It might depend on 'Intel Virtualization Technology' or such. >> > 00:1c.0 PCI bridge: Intel Corporation Device a0b8 (rev 20) >> > Bus: primary=00, secondary=56, subordinate=56, sec-latency=0 >> > Memory behind bridge: 8c300000-8c3fffff [size=1M] >> > 56:00.0 Network controller: Qualcomm Device 1101 (rev 01) >> > Region 0: Memory at 8c300000 (64-bit, non-prefetchable) [size=1M] So I grabbed the PCI info from the link and it has: Capabilities: [50] MSI: Enable- Count=1/32 Maskable+ 64bit- So no MSI-X, ergo only one MSI interrupt without remapping. >> >> To summarise: Thomas is reporting[1] a problem with ath11k on QCA6390 >> >> PCI device where he is not having enough MSI vectors. ath11k needs 32 >> >> vectors but pci_alloc_irq_vectors() returns -ENOSPC. PCI support is new >> >> for ath11k and introduced in v5.10-rc1. The irq allocation code is in >> >> drivers/net/wireless/ath/ath11k/pci.c. [2] > >> > But it seems a little greedy if the device can't operate at all unless >> > it gets 32 vectors. Are you sure that's a hard requirement? Most >> > devices can work with fewer vectors, even if it reduces performance. Right, even most high end network cards work with one interrupt. >> This was my first reaction as well when I saw the code for the first >> time. And the reply I got is that the firmware needs all 32 vectors, it >> won't work with less. Great design. > I do see a couple other drivers that are completely inflexible (they > request min==max). But I don't know the system constraint you're > hitting. CC'd Thomas & Christoph in case they have time to give us a > hint. Can I have a full dmesg please? Please enable CONFIG_IRQ_REMAP and CONFIG_INTEL_IOMMU (not strictly required, but it's a Dell BIOS after all). Also set CONFIG_INTEL_IOMMU_DEFAULT_ON. Or simply try a distro kernel. Thanks, tglx
WARNING: multiple messages have this Message-ID (diff)
From: Thomas Gleixner <tglx@linutronix.de> To: Bjorn Helgaas <helgaas@kernel.org>, Kalle Valo <kvalo@codeaurora.org> Cc: Govind Singh <govinds@codeaurora.org>, linux-pci@vger.kernel.org, linux-wireless@vger.kernel.org, Devin Bayer <dev@doubly.so>, Christoph Hellwig <hch@lst.de>, Thomas Krause <thomaskrause@posteo.de>, ath11k@lists.infradead.org Subject: Re: pci_alloc_irq_vectors fails ENOSPC for XPS 13 9310 Date: Tue, 03 Nov 2020 22:08:49 +0100 [thread overview] Message-ID: <874km61732.fsf@nanos.tec.linutronix.de> (raw) In-Reply-To: <20201103160838.GA246433@bjorn-Precision-5520> On Tue, Nov 03 2020 at 10:08, Bjorn Helgaas wrote: > On Tue, Nov 03, 2020 at 08:49:06AM +0200, Kalle Valo wrote: >> Bjorn Helgaas <helgaas@kernel.org> writes: >> > On Mon, Nov 02, 2020 at 08:49:51PM +0200, Kalle Valo wrote: >> >> Thomas Krause <thomaskrause@posteo.de> writes: >> >> >> >> >> I had the same problem as well back in the days, for me enabling >> >> >> CONFIG_IRQ_REMAP helped. If it helps for you also I wonder if we should >> >> >> mention that in the ath11k warning above :) Interrupt remapping only helps when the device supports only MSI (not MSI-X) because x86 (kernel) does not support multiple MSI interrupts without remapping. So if only MSI is available then you get exactly _one_ MSI vector without remapping. >> >> > CONFIG_IRQ_REMAP did not do the trick. The config alone does not help. The hardware has to support it and the BIOS has to enable it. Check the BIOS for a switch which is named 'VT-d' or such. It might depend on 'Intel Virtualization Technology' or such. >> > 00:1c.0 PCI bridge: Intel Corporation Device a0b8 (rev 20) >> > Bus: primary=00, secondary=56, subordinate=56, sec-latency=0 >> > Memory behind bridge: 8c300000-8c3fffff [size=1M] >> > 56:00.0 Network controller: Qualcomm Device 1101 (rev 01) >> > Region 0: Memory at 8c300000 (64-bit, non-prefetchable) [size=1M] So I grabbed the PCI info from the link and it has: Capabilities: [50] MSI: Enable- Count=1/32 Maskable+ 64bit- So no MSI-X, ergo only one MSI interrupt without remapping. >> >> To summarise: Thomas is reporting[1] a problem with ath11k on QCA6390 >> >> PCI device where he is not having enough MSI vectors. ath11k needs 32 >> >> vectors but pci_alloc_irq_vectors() returns -ENOSPC. PCI support is new >> >> for ath11k and introduced in v5.10-rc1. The irq allocation code is in >> >> drivers/net/wireless/ath/ath11k/pci.c. [2] > >> > But it seems a little greedy if the device can't operate at all unless >> > it gets 32 vectors. Are you sure that's a hard requirement? Most >> > devices can work with fewer vectors, even if it reduces performance. Right, even most high end network cards work with one interrupt. >> This was my first reaction as well when I saw the code for the first >> time. And the reply I got is that the firmware needs all 32 vectors, it >> won't work with less. Great design. > I do see a couple other drivers that are completely inflexible (they > request min==max). But I don't know the system constraint you're > hitting. CC'd Thomas & Christoph in case they have time to give us a > hint. Can I have a full dmesg please? Please enable CONFIG_IRQ_REMAP and CONFIG_INTEL_IOMMU (not strictly required, but it's a Dell BIOS after all). Also set CONFIG_INTEL_IOMMU_DEFAULT_ON. Or simply try a distro kernel. Thanks, tglx -- ath11k mailing list ath11k@lists.infradead.org http://lists.infradead.org/mailman/listinfo/ath11k
next prev parent reply other threads:[~2020-11-03 21:19 UTC|newest] Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-10-17 11:01 pci_alloc_irq_vectors fails ENOSPC for XPS 13 9310 Thomas Krause 2020-10-19 8:09 ` Kalle Valo 2020-10-20 20:46 ` Thomas Krause 2020-11-02 18:34 ` Kalle Valo 2020-11-02 18:49 ` Kalle Valo 2020-11-02 18:49 ` Kalle Valo 2020-11-02 20:57 ` Bjorn Helgaas 2020-11-02 20:57 ` Bjorn Helgaas 2020-11-03 3:01 ` Carl Huang 2020-11-03 3:01 ` Carl Huang 2020-11-03 6:49 ` Kalle Valo 2020-11-03 6:49 ` Kalle Valo 2020-11-03 16:08 ` Bjorn Helgaas 2020-11-03 16:08 ` Bjorn Helgaas 2020-11-03 21:08 ` Thomas Gleixner [this message] 2020-11-03 21:08 ` Thomas Gleixner 2020-11-03 22:42 ` Thomas Gleixner 2020-11-03 22:42 ` Thomas Gleixner 2020-11-09 18:44 ` Kalle Valo 2020-11-09 18:44 ` Kalle Valo 2020-11-04 13:04 ` Thomas Krause 2020-11-04 13:04 ` Thomas Krause 2020-11-04 15:26 ` Thomas Gleixner 2020-11-04 15:26 ` Thomas Gleixner 2020-11-05 13:23 ` Kalle Valo 2020-11-05 13:23 ` Kalle Valo 2020-11-06 11:57 ` Stefani Seibold 2020-11-10 8:33 ` Kalle Valo 2020-11-10 8:33 ` Kalle Valo 2020-11-11 8:53 ` Thomas Krause 2020-11-11 8:53 ` Thomas Krause 2020-11-11 9:22 ` Kalle Valo 2020-11-11 9:22 ` Kalle Valo 2020-11-11 19:10 ` Kalle Valo 2020-11-11 19:10 ` Kalle Valo 2020-11-11 19:24 ` wi nk 2020-11-11 19:24 ` wi nk 2020-11-11 19:30 ` wi nk 2020-11-11 19:30 ` wi nk 2020-11-11 19:45 ` Kalle Valo 2020-11-11 19:45 ` Kalle Valo 2020-11-11 20:12 ` wi nk 2020-11-11 20:12 ` wi nk 2020-11-11 21:35 ` Stefani Seibold 2020-11-11 21:35 ` Stefani Seibold 2020-11-11 22:02 ` Stefani Seibold 2020-11-11 22:02 ` Stefani Seibold 2020-11-12 0:24 ` wi nk 2020-11-12 0:24 ` wi nk 2020-11-12 1:10 ` wi nk 2020-11-12 1:10 ` wi nk 2020-11-12 1:11 ` wi nk 2020-11-12 1:11 ` wi nk 2020-11-12 2:31 ` wi nk 2020-11-12 2:31 ` wi nk 2020-11-12 6:29 ` Carl Huang 2020-11-12 6:29 ` Carl Huang 2020-11-12 7:05 ` Stefani Seibold 2020-11-12 7:05 ` Stefani Seibold 2020-11-12 7:15 ` Kalle Valo 2020-11-12 7:15 ` Kalle Valo 2020-11-12 7:41 ` wi nk 2020-11-12 7:41 ` wi nk 2020-11-12 8:59 ` Kalle Valo 2020-11-12 8:59 ` Kalle Valo 2020-11-12 15:44 ` wi nk 2020-11-12 15:44 ` wi nk 2020-11-13 9:52 ` wi nk 2020-11-13 9:52 ` wi nk 2020-11-15 13:30 ` Thomas Krause 2020-11-15 13:30 ` Thomas Krause 2020-11-15 19:55 ` wi nk 2020-11-15 19:55 ` wi nk 2020-11-17 15:49 ` wi nk 2020-11-17 15:49 ` wi nk 2020-11-17 20:59 ` Thomas Gleixner 2020-11-17 20:59 ` Thomas Gleixner 2020-11-18 10:22 ` wi nk 2020-11-18 10:22 ` wi nk 2020-11-11 9:39 ` Thomas Gleixner 2020-11-11 9:39 ` Thomas Gleixner 2020-11-06 11:45 ` Devin Bayer 2020-11-06 11:45 ` Devin Bayer 2020-11-09 18:48 ` Kalle Valo 2020-11-09 18:48 ` Kalle Valo 2020-11-03 11:20 ` Devin Bayer 2020-11-03 11:20 ` Devin Bayer
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=874km61732.fsf@nanos.tec.linutronix.de \ --to=tglx@linutronix.de \ --cc=ath11k@lists.infradead.org \ --cc=dev@doubly.so \ --cc=govinds@codeaurora.org \ --cc=hch@lst.de \ --cc=helgaas@kernel.org \ --cc=kvalo@codeaurora.org \ --cc=linux-pci@vger.kernel.org \ --cc=linux-wireless@vger.kernel.org \ --cc=thomaskrause@posteo.de \ /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.