linux-kernel - Re: [PATCH 06/15] x86/irq: Set up per host CPU posted interrupt descriptors

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Tue, 13 Feb 2024 11:44:57 -0800
From: Jacob Pan <jacob.jun.pan@...ux.intel.com>
To: LKML <linux-kernel@...r.kernel.org>, X86 Kernel <x86@...nel.org>, Peter
 Zijlstra <peterz@...radead.org>, iommu@...ts.linux.dev, Thomas Gleixner
 <tglx@...utronix.de>, "Lu Baolu" <baolu.lu@...ux.intel.com>,
 kvm@...r.kernel.org, Dave Hansen <dave.hansen@...el.com>, Joerg Roedel
 <joro@...tes.org>, "H. Peter Anvin" <hpa@...or.com>, "Borislav Petkov"
 <bp@...en8.de>, "Ingo Molnar" <mingo@...hat.com>
Cc: Paul Luse <paul.e.luse@...el.com>, Dan Williams
 <dan.j.williams@...el.com>, Jens Axboe <axboe@...nel.dk>, Raj Ashok
 <ashok.raj@...el.com>, "Tian, Kevin" <kevin.tian@...el.com>,
 maz@...nel.org, seanjc@...gle.com, "Robin Murphy" <robin.murphy@....com>,
 jacob.jun.pan@...ux.intel.com, oliver.sang@...el.com
Subject: Re: [PATCH 06/15] x86/irq: Set up per host CPU posted interrupt
 descriptors

On Fri, 26 Jan 2024 15:42:28 -0800, Jacob Pan
<jacob.jun.pan@...ux.intel.com> wrote:
I have made a couple of mistakes here, caught by LKP testing.
Reported by Oliver Sang.

>  
> +#ifdef CONFIG_X86_POSTED_MSI
> +
> +/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
> +DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_interrupt_desc);
> +
> +void intel_posted_msi_init(void)
> +{
> +	struct pi_desc *pid = this_cpu_ptr(&posted_interrupt_desc);
> +
> +	pid->nv = POSTED_MSI_NOTIFICATION_VECTOR;
> +	pid->ndst = this_cpu_read(x86_cpu_to_apicid);
Based on VT-d specification 9.11, middle portion of the 32 bit field
are used in xAPIC mode instead of the lowest 8 bit. Not sure why it was
designed this way, making sure people ready the spec carefully :)

xAPIC Mode (Physical): 
 319:304 - Reserved (0)
 303:296 - APIC DestinationID[7:0]
 295:288 - Reserved (0)
x2APIC Mode (Physical):
 319:288 - APIC DestinationID[31:0]

So it should be something like:
	pid->ndst = x2apic_enabled() ? apic_id : apic_id << 8;

> +}
> +}
partitioning mistake, will fix.

> +#endif /* X86_POSTED_MSI */

Thanks,

Jacob