[5.15,v2,02/10] KVM: arm64: Discard any SVE state when entering KVM guests

Commit Message

Mark Brown April 2, 2025, 11:20 p.m. UTC

[ Upstream commit 93ae6b01bafee8fa385aa25ee7ebdb40057f6abe ]

Since 8383741ab2e773a99 (KVM: arm64: Get rid of host SVE tracking/saving)
KVM has not tracked the host SVE state, relying on the fact that we
currently disable SVE whenever we perform a syscall. This may not be true
in future since performance optimisation may result in us keeping SVE
enabled in order to avoid needing to take access traps to reenable it.
Handle this by clearing TIF_SVE and converting the stored task state to
FPSIMD format when preparing to run the guest.  This is done with a new
call fpsimd_kvm_prepare() to keep the direct state manipulation
functions internal to fpsimd.c.

Signed-off-by: Mark Brown <[e-mail]>
Reviewed-by: Catalin Marinas <[e-mail]>
Reviewed-by: Marc Zyngier <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Will Deacon <[e-mail]>
[ Mark: trivial backport to v6.1 ]
Signed-off-by: Mark Rutland <[e-mail]>
Signed-off-by: Mark Brown <[e-mail]>
---
 arch/arm64/include/asm/fpsimd.h |  1 +
 arch/arm64/kernel/fpsimd.c      | 23 +++++++++++++++++++++++
 arch/arm64/kvm/fpsimd.c         |  5 ++++-
 3 files changed, 28 insertions(+), 1 deletion(-)

Patch

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 9a62884183e5..f7faf0f4507c 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -44,6 +44,7 @@  extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
+extern void fpsimd_kvm_prepare(void);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl);
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e22571e57ae1..57e89361edcb 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1108,6 +1108,29 @@  void fpsimd_signal_preserve_current_state(void)
 		sve_to_fpsimd(current);
 }
 
+/*
+ * Called by KVM when entering the guest.
+ */
+void fpsimd_kvm_prepare(void)
+{
+	if (!system_supports_sve())
+		return;
+
+	/*
+	 * KVM does not save host SVE state since we can only enter
+	 * the guest from a syscall so the ABI means that only the
+	 * non-saved SVE state needs to be saved.  If we have left
+	 * SVE enabled for performance reasons then update the task
+	 * state to be FPSIMD only.
+	 */
+	get_cpu_fpsimd_context();
+
+	if (test_and_clear_thread_flag(TIF_SVE))
+		sve_to_fpsimd(current);
+
+	put_cpu_fpsimd_context();
+}
+
 /*
  * Associate current's FPSIMD context with this cpu
  * The caller must have ownership of the cpu FPSIMD context before calling
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 2d15e1d6e214..16e29f03dcbf 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -70,11 +70,14 @@  int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(!current->mm);
-	BUG_ON(test_thread_flag(TIF_SVE));
 
 	vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED;
 	vcpu->arch.flags |= KVM_ARM64_FP_HOST;
 
+	fpsimd_kvm_prepare();
+
+	vcpu->arch.flags &= ~KVM_ARM64_HOST_SVE_ENABLED;
+
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
 }