Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-SDR: cNJhpmmZYHzpR+XXnCiEoC4o4US7hEOlcyW+QIJaYo5+HG3fFH++CDEq6k6ffBxPjjxq9lqCWW
 mnlbZAHtFSlg==
IronPort-SDR: 3/Dyycd6QdTlaUFlmPkr07zoPMXZLTCiu5jZ+TSZahhEAI8FLNcFbUmgcmbSuF4BIhRP9Hc0as
 h1pWGKojsfJg==
Subject: Re: [PATCH] x86/hotplug: Silence APIC only after all irq's are
 migrated
To:     Ashok Raj <ashok.raj@intel.com>, linux-kernel@vger.kernel.org,
        tglx@linutronix.de
Cc:     Sukumar Ghorai <sukumar.ghorai@intel.com>,
        Srikanth Nandamuri <srikanth.nandamuri@intel.com>,
        Evan Green <evgreen@chromium.org>,
        Bjorn Helgaas <bhelgaas@google.com>, stable@vger.kernel.org
References: <20200814213842.31151-1-ashok.raj@intel.com>
From:   Mathias Nyman <mathias.nyman@linux.intel.com>
Openpgp: preference=signencrypt
Autocrypt: addr=mathias.nyman@linux.intel.com; prefer-encrypt=mutual; keydata=
 mQINBFMB0ccBEADd+nZnZrFDsIjQtclVz6OsqFOQ6k0nQdveiDNeBuwyFYykkBpaGekoHZ6f
 lH4ogPZzQ+pzoJEMlRGXc881BIggKMCMH86fYJGfZKWdfpg9O6mqSxyEuvBHKe9eZCBKPvoC
 L2iwygtO8TcXXSCynvXSeZrOwqAlwnxWNRm4J2ikDck5S5R+Qie0ZLJIfaId1hELofWfuhy+
 tOK0plFR0HgVVp8O7zWYT2ewNcgAzQrRbzidA3LNRfkL7jrzyAxDapuejuK8TMrFQT/wW53e
 uegnXcRJaibJD84RUJt+mJrn5BvZ0MYfyDSc1yHVO+aZcpNr+71yZBQVgVEI/AuEQ0+p9wpt
 O9Wt4zO2KT/R5lq2lSz1MYMJrtfFRKkqC6PsDSB4lGSgl91XbibK5poxrIouVO2g9Jabg04T
 MIPpVUlPme3mkYHLZUsboemRQp5/pxV4HTFR0xNBCmsidBICHOYAepCzNmfLhfo1EW2Uf+t4
 L8IowAaoURKdgcR2ydUXjhACVEA/Ldtp3ftF4hTQ46Qhba/p4MUFtDAQ5yeA5vQVuspiwsqB
 BoL/298+V119JzM998d70Z1clqTc8fiGMXyVnFv92QKShDKyXpiisQn2rrJVWeXEIVoldh6+
 J8M3vTwzetnvIKpoQdSFJ2qxOdQ8iYRtz36WYl7hhT3/hwkHuQARAQABtCdNYXRoaWFzIE55
 bWFuIDxtYXRoaWFzLm55bWFuQGdtYWlsLmNvbT6JAjsEEwECACUCGwMGCwkIBwMCBhUIAgkK
 CwQWAgMBAh4BAheABQJTAeo1AhkBAAoJEFiDn/uYk8VJOdIP/jhA+RpIZ7rdUHFIYkHEKzHw
 tkwrJczGA5TyLgQaI8YTCTPSvdNHU9Rj19mkjhUO/9MKvwfoT2RFYqhkrtk0K92STDaBNXTL
 JIi4IHBqjXOyJ/dPADU0xiRVtCHWkBgjEgR7Wihr7McSdVpgupsaXhbZjXXgtR/N7PE0Wltz
 hAL2GAnMuIeJyXhIdIMLb+uyoydPCzKdH6znfu6Ox76XfGWBCqLBbvqPXvk4oH03jcdt+8UG
 2nfSeti/To9ANRZIlSKGjddCGMa3xzjtTx9ryf1Xr0MnY5PeyNLexpgHp93sc1BKxKKtYaT0
 lR6p0QEKeaZ70623oB7Sa2Ts4IytqUVxkQKRkJVWeQiPJ/dZYTK5uo15GaVwufuF8VTwnMkC
 4l5X+NUYNAH1U1bpRtlT40aoLEUhWKAyVdowxW4yGCP3nL5E69tZQQgsag+OnxBa6f88j63u
 wxmOJGNXcwCerkCb+wUPwJzChSifFYmuV5l89LKHgSbv0WHSN9OLkuhJO+I9fsCNvro1Y7dT
 U/yq4aSVzjaqPT3yrnQkzVDxrYT54FLWO1ssFKAOlcfeWzqrT9QNcHIzHMQYf5c03Kyq3yMI
 Xi91hkw2uc/GuA2CZ8dUD3BZhUT1dm0igE9NViE1M7F5lHQONEr7MOCg1hcrkngY62V6vh0f
 RcDeV0ISwlZWuQINBFMB0ccBEACXKmWvojkaG+kh/yipMmqZTrCozsLeGitxJzo5hq9ev31N
 2XpPGx4AGhpccbco63SygpVN2bOd0W62fJJoxGohtf/g0uVtRSuK43OTstoBPqyY/35+VnAV
 oA5cnfvtdx5kQPIL6LRcxmYKgN4/3+A7ejIxbOrjWFmbWCC+SgX6mzHHBrV0OMki8R+NnrNa
 NkUmMmosi7jBSKdoi9VqDqgQTJF/GftvmaZHqgmVJDWNrCv7UiorhesfIWPt1O/AIk9luxlE
 dHwkx5zkWa9CGYvV6LfP9BznendEoO3qYZ9IcUlW727Le80Q1oh69QnHoI8pODDBBTJvEq1h
 bOWcPm/DsNmDD8Rwr/msRmRyIoxjasFi5WkM/K/pzujICKeUcNGNsDsEDJC5TCmRO/TlvCvm
 0X+vdfEJRZV6Z+QFBflK1asUz9QHFre5csG8MyVZkwTR9yUiKi3KiqQdaEu+LuDD2CGF5t68
 xEl66Y6mwfyiISkkm3ETA4E8rVZP1rZQBBm83c5kJEDvs0A4zrhKIPTcI1smK+TWbyVyrZ/a
 mGYDrZzpF2N8DfuNSqOQkLHIOL3vuOyx3HPzS05lY3p+IIVmnPOEdZhMsNDIGmVorFyRWa4K
 uYjBP/W3E5p9e6TvDSDzqhLoY1RHfAIadM3I8kEx5wqco67VIgbIHHB9DbRcxQARAQABiQIf
 BBgBAgAJBQJTAdHHAhsMAAoJEFiDn/uYk8VJb7AQAK56tgX8V1Wa6RmZDmZ8dmBC7W8nsMRz
 PcKWiDSMIvTJT5bygMy1lf7gbHXm7fqezRtSfXAXr/OJqSA8LB2LWfThLyuuCvrdNsQNrI+3
 D+hjHJjhW/4185y3EdmwwHcelixPg0X9EF+lHCltV/w29Pv3PiGDkoKxJrnOpnU6jrwiBebz
 eAYBfpSEvrCm4CR4hf+T6MdCs64UzZnNt0nxL8mLCCAGmq1iks9M4bZk+LG36QjCKGh8PDXz
 9OsnJmCggptClgjTa7pO6040OW76pcVrP2rZrkjo/Ld/gvSc7yMO/m9sIYxLIsR2NDxMNpmE
 q/H7WO+2bRG0vMmsndxpEYS4WnuhKutoTA/goBEhtHu1fg5KC+WYXp9wZyTfeNPrL0L8F3N1
 BCEYefp2JSZ/a355X6r2ROGSRgIIeYjAiSMgGAZMPEVsdvKsYw6BH17hDRzltNyIj5S0dIhb
 Gjynb3sXforM/GVbr4mnuxTdLXQYlj2EJ4O4f0tkLlADT7podzKSlSuZsLi2D+ohKxtP3U/r
 42i8PBnX2oAV0UIkYk7Oel/3hr0+BP666SnTls9RJuoXc7R5XQVsomqXID6GmjwFQR5Wh/RE
 IJtkiDAsk37cfZ9d1kZ2gCQryTV9lmflSOB6AFZkOLuEVSC5qW8M/s6IGDfYXN12YJaZPptJ fiD/
Message-ID: <563d77c0-ab5b-df9c-8f4d-b16a0d1211a2@linux.intel.com>
Date:   Thu, 20 Aug 2020 15:11:45 +0300
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.9.0
MIME-Version: 1.0
In-Reply-To: <20200814213842.31151-1-ashok.raj@intel.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 15.8.2020 0.38, Ashok Raj wrote:
> When offlining CPU's, fixup_irqs() migrates all interrupts away from the
> outgoing CPU to an online CPU. Its always possible the device sent an
> interrupt to the previous CPU destination. Pending interrupt bit in IRR in
> lapic identifies such interrupts. apic_soft_disable() will not capture any
> new interrupts in IRR. This causes interrupts from device to be lost during
> cpu offline. The issue was found when explicitly setting MSI affinity to a
> CPU and immediately offlining it. It was simple to recreate with a USB
> ethernet device and doing I/O to it while the CPU is offlined. Lost
> interrupts happen even when Interrupt Remapping is enabled.
> 
> Current code does apic_soft_disable() before migrating interrupts.
> 
> native_cpu_disable()
> {
> 	...
> 	apic_soft_disable();
> 	cpu_disable_common();
> 	  --> fixup_irqs(); // Too late to capture anything in IRR.
> }
> 
> Just fliping the above call sequence seems to hit the IRR checks
> and the lost interrupt is fixed for both legacy MSI and when
> interrupt remapping is enabled.
> 
> 
> Fixes: 60dcaad5736f ("x86/hotplug: Silence APIC and NMI when CPU is dead")
> Link: https://lore.kernel.org/lkml/875zdarr4h.fsf@nanos.tec.linutronix.de/
> Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> 
> To: linux-kernel@vger.kernel.org
> To: Thomas Gleixner <tglx@linutronix.de>
> Cc: Sukumar Ghorai <sukumar.ghorai@intel.com>
> Cc: Srikanth Nandamuri <srikanth.nandamuri@intel.com>
> Cc: Evan Green <evgreen@chromium.org>
> Cc: Mathias Nyman <mathias.nyman@linux.intel.com>
> Cc: Bjorn Helgaas <bhelgaas@google.com>
> Cc: stable@vger.kernel.org
> ---

This fixes the lost xhci interrupt for me.
Before this patch a msi interupt was lost after ~200 cycles of toggling CPUs
offline/online under heavy usb traffic.

With this patch I ran 3x2000 cycles without any issues (Comet lake, patch on top of 5.8)
Tried both with and without CONFIG_IRQ_REMAP. No issues seen.

Tested-by: Mathias Nyman <mathias.nyman@linux.intel.com>