From: sashiko-bot@kernel.org
To: "Sascha Bischoff" <Sascha.Bischoff@arm.com>
Cc: kvmarm@lists.linux.dev, "Oliver Upton" <oupton@kernel.org>,
"Marc Zyngier" <maz@kernel.org>,
kvm@vger.kernel.org
Subject: Re: [PATCH v3 15/40] KVM: arm64: gic-v5: Add resident/non-resident hyp calls
Date: Fri, 03 Jul 2026 16:23:01 +0000 [thread overview]
Message-ID: <20260703162302.6A1311F000E9@smtp.kernel.org> (raw)
In-Reply-To: <20260703154811.3355680-16-sascha.bischoff@arm.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Critical] EL2 directly writes unvalidated, host-controlled memory to `SYS_ICH_CONTEXTR_EL2`, violating the pKVM trust boundary and allowing a compromised host to hijack protected VMs' interrupts.
- [High] Time-of-Check to Time-of-Use (TOCTOU) vulnerability due to a double-fetch of the host-shared `vgic_contextr` field when evaluating the hardware fault status.
--
commit 7cd120d3ed0e8b391f422c1d75c53d34d13d0b6c
Author: Sascha Bischoff <Sascha.Bischoff@arm.com>
KVM: arm64: gic-v5: Add resident/non-resident hyp calls
This commit introduces new hypercalls to make a GICv5 VPE resident or
non-resident by writing to ICH_CONTEXTR_EL2. It extends the load and put
functions to handle this residency interval and checks for residency faults.
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 1d01c6e547f5d..8d0896f50f879 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
[ ... ]
> @@ -689,6 +689,20 @@ static void handle___tracing_write_event(struct kvm_cpu_context *host_ctxt)
> trace_selftest(id);
> }
>
> +static void handle___vgic_v5_make_resident(struct kvm_cpu_context *host_ctxt)
> +{
> + DECLARE_REG(struct vgic_v5_cpu_if *, cpu_if, host_ctxt, 1);
> +
> + __vgic_v5_make_resident(kern_hyp_va(cpu_if));
> +}
[ ... ]
> diff --git a/arch/arm64/kvm/hyp/vgic-v5-sr.c b/arch/arm64/kvm/hyp/vgic-v5-sr.c
> index 6d69dfe89a96c..f064045a31aee 100644
> --- a/arch/arm64/kvm/hyp/vgic-v5-sr.c
> +++ b/arch/arm64/kvm/hyp/vgic-v5-sr.c
> @@ -7,6 +7,32 @@
>
> #include <asm/kvm_hyp.h>
>
> +void __vgic_v5_make_resident(struct vgic_v5_cpu_if *cpu_if)
> +{
> + write_sysreg_s(cpu_if->vgic_contextr, SYS_ICH_CONTEXTR_EL2);
[Severity: Critical]
Can this regression allow the host to force the GICv5 hardware to make a
protected VM's VPE resident?
The handle___vgic_v5_make_resident hypercall is exposed to the untrusted
host. Here, EL2 directly writes the host-controlled cpu_if->vgic_contextr
memory to the SYS_ICH_CONTEXTR_EL2 register without validating if
the requested VM/VPE belongs to a protected VM. This could break guest
isolation by allowing the host to modify a protected VM's interrupts.
> + isb();
> +
> + /* Catch any faults */
> + cpu_if->vgic_contextr = read_sysreg_s(SYS_ICH_CONTEXTR_EL2);
> + if (!!FIELD_GET(ICH_CONTEXTR_EL2_F, cpu_if->vgic_contextr))
[Severity: High]
Does this introduce a Time-of-Check to Time-of-Use (TOCTOU) regression?
The code writes the SYS_ICH_CONTEXTR_EL2 value into cpu_if->vgic_contextr,
which resides in host memory. It then immediately fetches it back
to check the ICH_CONTEXTR_EL2_F bit. A concurrent host CPU could overwrite
this value in the small window between the store and the load, clearing the
fault bit and hiding a hardware residency fault from the hypervisor.
> + return;
> +
> + cpu_if->gicv5_vpe.resident = true;
> +}
> +
> +void __vgic_v5_make_non_resident(struct vgic_v5_cpu_if *cpu_if)
> +{
> + /*
> + * Make as non-resident before actually making non-resident. Avoids race
> + * with doorbell arriving.
> + */
> + cpu_if->gicv5_vpe.resident = false;
> + dsb(st);
> +
> + write_sysreg_s(cpu_if->vgic_contextr, SYS_ICH_CONTEXTR_EL2);
[Severity: Critical]
Similar to the resident path, does this write introduce the same regression?
The non-resident path also directly writes the host-controlled vgic_contextr
value to the hardware register without validation.
> + isb();
> +}
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260703154811.3355680-1-sascha.bischoff@arm.com?part=15
next prev parent reply other threads:[~2026-07-03 16:23 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-03 15:50 [PATCH v3 00/40] KVM: arm64: Add GICv5 IRS support Sascha Bischoff
2026-07-03 15:51 ` [PATCH v3 01/40] irqchip/gic-v5: Allow KVM setup without a maintenance IRQ Sascha Bischoff
2026-07-03 16:33 ` sashiko-bot
2026-07-07 12:30 ` Sascha Bischoff
2026-07-03 15:51 ` [PATCH v3 02/40] irqchip/gic-v5: Provide OF IRS config frame attrs to KVM Sascha Bischoff
2026-07-03 16:24 ` sashiko-bot
2026-07-07 12:48 ` Sascha Bischoff
2026-07-03 15:52 ` [PATCH v3 03/40] irqchip/gic-v5: Set up gic_kvm_info on ACPI hosts Sascha Bischoff
2026-07-03 15:52 ` [PATCH v3 04/40] KVM: arm64: gic-v5: Define remaining IRS MMIO registers Sascha Bischoff
2026-07-03 15:53 ` [PATCH v3 05/40] arm64/sysreg: Add GICv5 GIC VDPEND and VDRCFG encodings Sascha Bischoff
2026-07-03 16:28 ` sashiko-bot
2026-07-07 14:28 ` Sascha Bischoff
2026-07-03 15:53 ` [PATCH v3 06/40] arm64/sysreg: Update ICC_CR0_EL1 with LINK and LINK_IDLE fields Sascha Bischoff
2026-07-03 16:22 ` sashiko-bot
2026-07-07 15:08 ` Sascha Bischoff
2026-07-03 15:54 ` [PATCH v3 07/40] KVM: arm64: gic-v5: Extract host IRS caps from IRS config frame Sascha Bischoff
2026-07-03 15:54 ` [PATCH v3 08/40] KVM: arm64: gic-v5: Add VPE doorbell domain Sascha Bischoff
2026-07-03 16:25 ` sashiko-bot
2026-07-07 15:11 ` Sascha Bischoff
2026-07-03 15:55 ` [PATCH v3 09/40] KVM: arm64: gic-v5: Create and manage VM and VPE tables Sascha Bischoff
2026-07-03 16:31 ` sashiko-bot
2026-07-08 14:44 ` Sascha Bischoff
2026-07-03 15:55 ` [PATCH v3 10/40] KVM: arm64: gic-v5: Introduce guest IST alloc and management Sascha Bischoff
2026-07-03 16:34 ` sashiko-bot
2026-07-08 14:46 ` Sascha Bischoff
2026-07-03 15:56 ` [PATCH v3 11/40] KVM: arm64: gic-v5: Implement VMT/vIST IRS MMIO Ops Sascha Bischoff
2026-07-03 16:39 ` sashiko-bot
2026-07-08 14:49 ` Sascha Bischoff
2026-07-03 15:56 ` [PATCH v3 12/40] KVM: arm64: gic-v5: Keep GICv5 vCPU limit model-specific Sascha Bischoff
2026-07-03 15:57 ` [PATCH v3 13/40] KVM: arm64: gic-v5: Implement VPE IRS MMIO Ops Sascha Bischoff
2026-07-03 16:26 ` sashiko-bot
2026-07-08 14:53 ` Sascha Bischoff
2026-07-03 15:57 ` [PATCH v3 14/40] KVM: arm64: gic-v5: Set up VMTEs and VPE doorbells Sascha Bischoff
2026-07-03 16:27 ` sashiko-bot
2026-07-08 14:56 ` Sascha Bischoff
2026-07-03 15:58 ` [PATCH v3 15/40] KVM: arm64: gic-v5: Add resident/non-resident hyp calls Sascha Bischoff
2026-07-03 16:23 ` sashiko-bot [this message]
2026-07-08 15:00 ` Sascha Bischoff
2026-07-03 15:58 ` [PATCH v3 16/40] KVM: arm64: gic-v5: Request doorbells when VPEs enter WFI Sascha Bischoff
2026-07-03 16:35 ` sashiko-bot
2026-07-08 15:35 ` Sascha Bischoff
2026-07-03 15:59 ` [PATCH v3 17/40] KVM: arm64: gic-v5: Introduce struct vgic_v5_irs and IRS base address Sascha Bischoff
2026-07-03 15:59 ` [PATCH v3 18/40] KVM: arm64: gic-v5: Add IRS IODEV support to MMIO handlers Sascha Bischoff
2026-07-03 16:00 ` [PATCH v3 19/40] KVM: arm64: gic-v5: Add KVM_VGIC_V5_ADDR_TYPE_IRS to UAPI Sascha Bischoff
2026-07-03 16:00 ` [PATCH v3 20/40] KVM: arm64: gic-v5: Add GICv5 IRS IODEV and MMIO emulation Sascha Bischoff
2026-07-03 16:38 ` sashiko-bot
2026-07-09 9:28 ` Sascha Bischoff
2026-07-03 16:01 ` [PATCH v3 21/40] KVM: arm64: gic-v5: Initialise per-VM IRS state Sascha Bischoff
2026-07-03 16:01 ` [PATCH v3 22/40] KVM: arm64: gic-v5: Register the IRS IODEV Sascha Bischoff
2026-07-03 16:47 ` sashiko-bot
2026-07-09 9:55 ` Sascha Bischoff
2026-07-03 16:02 ` [PATCH v3 23/40] KVM: arm64: gic-v5: Set IRICHPPIDIS based on IRS enable state Sascha Bischoff
2026-07-03 16:34 ` sashiko-bot
2026-07-09 11:39 ` Sascha Bischoff
2026-07-03 16:02 ` [PATCH v3 24/40] KVM: arm64: selftests: Update vGICv5 selftest to set IRS address Sascha Bischoff
2026-07-03 16:03 ` [PATCH v3 25/40] KVM: arm64: gic-v5: Introduce SPI AP list Sascha Bischoff
2026-07-03 16:03 ` [PATCH v3 26/40] KVM: arm64: gic-v5: Add GIC VDPEND and GIC VDRCFG hyp calls Sascha Bischoff
2026-07-03 16:31 ` sashiko-bot
2026-07-10 9:44 ` Sascha Bischoff
2026-07-03 16:04 ` [PATCH v3 27/40] KVM: arm64: gic-v5: Track SPI state for in-flight SPIs Sascha Bischoff
2026-07-03 16:41 ` sashiko-bot
2026-07-03 16:04 ` [PATCH v3 28/40] KVM: arm64: gic: Introduce set_pending_state() to irq_op Sascha Bischoff
2026-07-03 16:32 ` sashiko-bot
2026-07-10 9:51 ` Sascha Bischoff
2026-07-03 16:05 ` [PATCH v3 29/40] KVM: arm64: gic-v5: Support SPI injection Sascha Bischoff
2026-07-03 16:53 ` sashiko-bot
2026-07-03 16:05 ` [PATCH v3 30/40] Documentation: KVM: Extend VGICv5 docs for KVM_VGIC_V5_ADDR_TYPE_IRS Sascha Bischoff
2026-07-03 16:27 ` sashiko-bot
2026-07-03 16:06 ` [PATCH v3 31/40] KVM: arm64: gic-v5: Add GICv5 SPI injection to irqfd Sascha Bischoff
2026-07-03 16:36 ` sashiko-bot
2026-07-03 16:06 ` [PATCH v3 32/40] KVM: arm64: gic-v5: Mask per-vcpu PPI state in vgic_v5_finalize_ppi_state() Sascha Bischoff
2026-07-03 16:07 ` [PATCH v3 33/40] KVM: arm64: gic-v5: Add GICv5 EL1 sysreg userspace accessors Sascha Bischoff
2026-07-03 16:07 ` [PATCH v3 34/40] KVM: arm64: gic-v5: Handle userspace accesses to IRS MMIO region Sascha Bischoff
2026-07-03 16:42 ` sashiko-bot
2026-07-03 16:08 ` [PATCH v3 35/40] KVM: arm64: gic-v5: Add CoreSight MMIO regs to IRS Sascha Bischoff
2026-07-03 16:41 ` sashiko-bot
2026-07-03 16:08 ` [PATCH v3 36/40] KVM: arm64: gic-v5: Implement save/restore mechanisms for ISTs Sascha Bischoff
2026-07-03 16:43 ` sashiko-bot
2026-07-03 16:09 ` [PATCH v3 37/40] Documentation: KVM: Document KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS for VGICv5 Sascha Bischoff
2026-07-03 16:36 ` sashiko-bot
2026-07-03 16:09 ` [PATCH v3 38/40] Documentation: KVM: Add KVM_DEV_ARM_VGIC_GRP_IRS_REGS to VGICv5 docs Sascha Bischoff
2026-07-03 16:37 ` sashiko-bot
2026-07-03 16:10 ` [PATCH v3 39/40] Documentation: KVM: Add docs for KVM_DEV_ARM_VGIC_GRP_IST Sascha Bischoff
2026-07-03 16:10 ` [PATCH v3 40/40] Documentation: KVM: Add the VGICv5 IRS save/restore sequences Sascha Bischoff
2026-07-03 16:33 ` sashiko-bot
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=20260703162302.6A1311F000E9@smtp.kernel.org \
--to=sashiko-bot@kernel.org \
--cc=Sascha.Bischoff@arm.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.linux.dev \
--cc=maz@kernel.org \
--cc=oupton@kernel.org \
--cc=sashiko-reviews@lists.linux.dev \
/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: link
Be 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.