From: Will Deacon <will@kernel.org>
To: kvmarm@lists.linux.dev
Cc: linux-arm-kernel@lists.infradead.org,
Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
Oliver Upton <oupton@kernel.org>, Joey Gouly <joey.gouly@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Zenghui Yu <yuzenghui@huawei.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Quentin Perret <qperret@google.com>,
Fuad Tabba <tabba@google.com>,
Vincent Donnefort <vdonnefort@google.com>,
Mostafa Saleh <smostafa@google.com>,
Alexandru Elisei <alexandru.elisei@arm.com>
Subject: [PATCH v4 19/38] KVM: arm64: Inject SIGSEGV on illegal accesses
Date: Fri, 27 Mar 2026 14:00:18 +0000 [thread overview]
Message-ID: <20260327140039.21228-20-will@kernel.org> (raw)
In-Reply-To: <20260327140039.21228-1-will@kernel.org>
From: Quentin Perret <qperret@google.com>
The pKVM hypervisor will currently panic if the host tries to access
memory that it doesn't own (e.g. protected guest memory). Sadly, as
guest memory can still be mapped into the VMM's address space, userspace
can trivially crash the kernel/hypervisor by poking into guest memory.
To prevent this, inject the abort back in the host with S1PTW set in the
ESR, hence allowing the host to differentiate this abort from normal
userspace faults and inject a SIGSEGV cleanly.
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 37 +++++++++++++++++++++++++++
arch/arm64/mm/fault.c | 22 ++++++++++++++++
2 files changed, 59 insertions(+)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index ca266a4d9d50..0e57dc1881e0 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -18,6 +18,7 @@
#include <nvhe/memory.h>
#include <nvhe/mem_protect.h>
#include <nvhe/mm.h>
+#include <nvhe/trap_handler.h>
#define KVM_HOST_S2_FLAGS (KVM_PGTABLE_S2_AS_S1 | KVM_PGTABLE_S2_IDMAP)
@@ -612,6 +613,39 @@ static int host_stage2_idmap(u64 addr)
return ret;
}
+static void host_inject_mem_abort(struct kvm_cpu_context *host_ctxt)
+{
+ u64 ec, esr, spsr;
+
+ esr = read_sysreg_el2(SYS_ESR);
+ spsr = read_sysreg_el2(SYS_SPSR);
+
+ /* Repaint the ESR to report a same-level fault if taken from EL1 */
+ if ((spsr & PSR_MODE_MASK) != PSR_MODE_EL0t) {
+ ec = ESR_ELx_EC(esr);
+ if (ec == ESR_ELx_EC_DABT_LOW)
+ ec = ESR_ELx_EC_DABT_CUR;
+ else if (ec == ESR_ELx_EC_IABT_LOW)
+ ec = ESR_ELx_EC_IABT_CUR;
+ else
+ WARN_ON(1);
+ esr &= ~ESR_ELx_EC_MASK;
+ esr |= ec << ESR_ELx_EC_SHIFT;
+ }
+
+ /*
+ * Since S1PTW should only ever be set for stage-2 faults, we're pretty
+ * much guaranteed that it won't be set in ESR_EL1 by the hardware. So,
+ * let's use that bit to allow the host abort handler to differentiate
+ * this abort from normal userspace faults.
+ *
+ * Note: although S1PTW is RES0 at EL1, it is guaranteed by the
+ * architecture to be backed by flops, so it should be safe to use.
+ */
+ esr |= ESR_ELx_S1PTW;
+ inject_host_exception(esr);
+}
+
void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
{
struct kvm_vcpu_fault_info fault;
@@ -635,6 +669,9 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
switch (host_stage2_idmap(addr)) {
+ case -EPERM:
+ host_inject_mem_abort(host_ctxt);
+ fallthrough;
case -EEXIST:
case 0:
break;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index be9dab2c7d6a..3abfc7272d63 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -43,6 +43,7 @@
#include <asm/system_misc.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>
+#include <asm/virt.h>
struct fault_info {
int (*fn)(unsigned long far, unsigned long esr,
@@ -269,6 +270,15 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr
return false;
}
+static bool is_pkvm_stage2_abort(unsigned int esr)
+{
+ /*
+ * S1PTW should only ever be set in ESR_EL1 if the pkvm hypervisor
+ * injected a stage-2 abort -- see host_inject_mem_abort().
+ */
+ return is_pkvm_initialized() && (esr & ESR_ELx_S1PTW);
+}
+
static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
unsigned long esr,
struct pt_regs *regs)
@@ -279,6 +289,9 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr))
return false;
+ if (is_pkvm_stage2_abort(esr))
+ return false;
+
local_irq_save(flags);
asm volatile("at s1e1r, %0" :: "r" (addr));
isb();
@@ -395,6 +408,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
msg = "read from unreadable memory";
} else if (addr < PAGE_SIZE) {
msg = "NULL pointer dereference";
+ } else if (is_pkvm_stage2_abort(esr)) {
+ msg = "access to hypervisor-protected memory";
} else {
if (esr_fsc_is_translation_fault(esr) &&
kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))
@@ -621,6 +636,13 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
addr, esr, regs);
}
+ if (is_pkvm_stage2_abort(esr)) {
+ if (!user_mode(regs))
+ goto no_context;
+ arm64_force_sig_fault(SIGSEGV, SEGV_ACCERR, far, "stage-2 fault");
+ return 0;
+ }
+
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
if (!(mm_flags & FAULT_FLAG_USER))
--
2.53.0.1018.g2bb0e51243-goog
next prev parent reply other threads:[~2026-03-27 14:02 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-27 13:59 [PATCH v4 00/38] KVM: arm64: Add support for protected guest memory with pKVM Will Deacon
2026-03-27 14:00 ` [PATCH v4 01/38] KVM: arm64: Remove unused PKVM_ID_FFA definition Will Deacon
2026-03-27 14:00 ` [PATCH v4 02/38] KVM: arm64: Don't leak stage-2 page-table if VM fails to init under pKVM Will Deacon
2026-03-27 14:00 ` [PATCH v4 03/38] KVM: arm64: Move handle check into pkvm_pgtable_stage2_destroy_range() Will Deacon
2026-03-27 14:00 ` [PATCH v4 04/38] KVM: arm64: Rename __pkvm_pgtable_stage2_unmap() Will Deacon
2026-03-27 14:00 ` [PATCH v4 05/38] KVM: arm64: Don't advertise unsupported features for protected guests Will Deacon
2026-03-27 14:00 ` [PATCH v4 06/38] KVM: arm64: Expose self-hosted debug regs as RAZ/WI " Will Deacon
2026-03-27 14:00 ` [PATCH v4 07/38] KVM: arm64: Remove is_protected_kvm_enabled() checks from hypercalls Will Deacon
2026-03-27 14:00 ` [PATCH v4 08/38] KVM: arm64: Ignore MMU notifier callbacks for protected VMs Will Deacon
2026-03-27 14:00 ` [PATCH v4 09/38] KVM: arm64: Prevent unsupported memslot operations on " Will Deacon
2026-03-27 14:00 ` [PATCH v4 10/38] KVM: arm64: Ignore -EAGAIN when mapping in pages for the pKVM host Will Deacon
2026-03-27 14:00 ` [PATCH v4 11/38] KVM: arm64: Split teardown hypercall into two phases Will Deacon
2026-03-27 14:00 ` [PATCH v4 12/38] KVM: arm64: Introduce __pkvm_host_donate_guest() Will Deacon
2026-03-27 14:00 ` [PATCH v4 13/38] KVM: arm64: Hook up donation hypercall to pkvm_pgtable_stage2_map() Will Deacon
2026-03-27 14:00 ` [PATCH v4 14/38] KVM: arm64: Handle aborts from protected VMs Will Deacon
2026-03-27 14:00 ` [PATCH v4 15/38] KVM: arm64: Introduce __pkvm_reclaim_dying_guest_page() Will Deacon
2026-03-27 14:00 ` [PATCH v4 16/38] KVM: arm64: Hook up reclaim hypercall to pkvm_pgtable_stage2_destroy() Will Deacon
2026-03-27 14:00 ` [PATCH v4 17/38] KVM: arm64: Factor out pKVM host exception injection logic Will Deacon
2026-03-27 14:00 ` [PATCH v4 18/38] KVM: arm64: Support translation faults in inject_host_exception() Will Deacon
2026-03-27 14:00 ` Will Deacon [this message]
2026-03-27 14:00 ` [PATCH v4 20/38] KVM: arm64: Avoid pointless annotation when mapping host-owned pages Will Deacon
2026-03-27 14:00 ` [PATCH v4 21/38] KVM: arm64: Generalise kvm_pgtable_stage2_set_owner() Will Deacon
2026-03-27 14:00 ` [PATCH v4 22/38] KVM: arm64: Introduce host_stage2_set_owner_metadata_locked() Will Deacon
2026-03-27 14:00 ` [PATCH v4 23/38] KVM: arm64: Change 'pkvm_handle_t' to u16 Will Deacon
2026-03-27 14:00 ` [PATCH v4 24/38] KVM: arm64: Annotate guest donations with handle and gfn in host stage-2 Will Deacon
2026-03-27 14:00 ` [PATCH v4 25/38] KVM: arm64: Introduce hypercall to force reclaim of a protected page Will Deacon
2026-03-27 14:00 ` [PATCH v4 26/38] KVM: arm64: Reclaim faulting page from pKVM in spurious fault handler Will Deacon
2026-03-27 14:00 ` [PATCH v4 27/38] KVM: arm64: Return -EFAULT from VCPU_RUN on access to a poisoned pte Will Deacon
2026-03-27 14:00 ` [PATCH v4 28/38] KVM: arm64: Add hvc handler at EL2 for hypercalls from protected VMs Will Deacon
2026-03-27 14:00 ` [PATCH v4 29/38] KVM: arm64: Implement the MEM_SHARE hypercall for " Will Deacon
2026-03-27 14:00 ` [PATCH v4 30/38] KVM: arm64: Implement the MEM_UNSHARE " Will Deacon
2026-03-27 14:00 ` [PATCH v4 31/38] KVM: arm64: Allow userspace to create protected VMs when pKVM is enabled Will Deacon
2026-03-27 14:00 ` [PATCH v4 32/38] KVM: arm64: Add some initial documentation for pKVM Will Deacon
2026-03-27 14:00 ` [PATCH v4 33/38] KVM: arm64: Extend pKVM page ownership selftests to cover guest donation Will Deacon
2026-03-27 14:00 ` [PATCH v4 34/38] KVM: arm64: Register 'selftest_vm' in the VM table Will Deacon
2026-03-27 14:00 ` [PATCH v4 35/38] KVM: arm64: Extend pKVM page ownership selftests to cover forced reclaim Will Deacon
2026-03-27 14:00 ` [PATCH v4 36/38] KVM: arm64: Extend pKVM page ownership selftests to cover guest hvcs Will Deacon
2026-03-27 14:00 ` [PATCH v4 37/38] KVM: arm64: Rename PKVM_PAGE_STATE_MASK Will Deacon
2026-03-27 14:00 ` [PATCH v4 38/38] drivers/virt: pkvm: Add Kconfig dependency on DMA_RESTRICTED_POOL Will Deacon
2026-03-27 18:13 ` [PATCH v4 00/38] KVM: arm64: Add support for protected guest memory with pKVM Will Deacon
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=20260327140039.21228-20-will@kernel.org \
--to=will@kernel.org \
--cc=alexandru.elisei@arm.com \
--cc=catalin.marinas@arm.com \
--cc=joey.gouly@arm.com \
--cc=kvmarm@lists.linux.dev \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=maz@kernel.org \
--cc=oupton@kernel.org \
--cc=qperret@google.com \
--cc=smostafa@google.com \
--cc=suzuki.poulose@arm.com \
--cc=tabba@google.com \
--cc=vdonnefort@google.com \
--cc=yuzenghui@huawei.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox