From 892fd259cbf6b1dc16116611b84f7f164a11fe2e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 21 Oct 2021 13:50:42 +0100 Subject: [PATCH 1/6] KVM: arm64: Reorder vcpu flag definitions The vcpu arch flags are in an interesting, semi random order. As I have made the mistake of reusing a flag once, let's rework this in an order that I find a bit less confusing. Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006ff..3bfd30137ce24 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -417,14 +417,12 @@ struct kvm_vcpu_arch { #define KVM_ARM64_VCPU_SVE_FINALIZED (1 << 6) /* SVE config completed */ #define KVM_ARM64_GUEST_HAS_PTRAUTH (1 << 7) /* PTRAUTH exposed to guest */ #define KVM_ARM64_PENDING_EXCEPTION (1 << 8) /* Exception pending */ +/* + * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be + * set together with an exception... + */ +#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ #define KVM_ARM64_EXCEPT_MASK (7 << 9) /* Target EL/MODE */ -#define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ -#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ - -#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ - KVM_GUESTDBG_USE_SW_BP | \ - KVM_GUESTDBG_USE_HW | \ - KVM_GUESTDBG_SINGLESTEP) /* * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can * take the following values: @@ -442,11 +440,13 @@ struct kvm_vcpu_arch { #define KVM_ARM64_EXCEPT_AA64_EL1 (0 << 11) #define KVM_ARM64_EXCEPT_AA64_EL2 (1 << 11) -/* - * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be - * set together with an exception... - */ -#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ +#define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ +#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ + +#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ + KVM_GUESTDBG_USE_SW_BP | \ + KVM_GUESTDBG_USE_HW | \ + KVM_GUESTDBG_SINGLESTEP) #define vcpu_has_sve(vcpu) (system_supports_sve() && \ ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE)) From 8383741ab2e773a992f1f0f8acdca5e7a4687c49 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 27 Oct 2021 11:18:00 +0100 Subject: [PATCH 2/6] KVM: arm64: Get rid of host SVE tracking/saving The SVE host tracking in KVM is pretty involved. It relies on a set of flags tracking the ownership of the SVE register, as well as that of the EL0 access. It is also pretty scary: __hyp_sve_save_host() computes a thread_struct pointer and obtains a sve_state which gets directly accessed without further ado, even on nVHE. How can this even work? The answer to that is that it doesn't, and that this is mostly dead code. Closer examination shows that on executing a syscall, userspace loses its SVE state entirely. This is part of the ABI. Another thing to notice is that although the kernel provides helpers such as kernel_neon_begin()/end(), they only deal with the FP/NEON state, and not SVE. Given that you can only execute a guest as the result of a syscall, and that the kernel cannot use SVE by itself, it becomes pretty obvious that there is never any host SVE state to save, and that this code is only there to increase confusion. Get rid of the TIF_SVE tracking and host save infrastructure altogether. Reviewed-by: Mark Brown Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/fpsimd.c | 20 +++++------------- arch/arm64/kvm/hyp/include/hyp/switch.h | 27 +++---------------------- 3 files changed, 8 insertions(+), 40 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3bfd30137ce24..3ccfc3e3e4366 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -411,7 +411,6 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_DIRTY (1 << 0) #define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ #define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ -#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ #define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ #define KVM_ARM64_GUEST_HAS_SVE (1 << 5) /* SVE exposed to guest */ #define KVM_ARM64_VCPU_SVE_FINALIZED (1 << 6) /* SVE config completed */ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 5621020b28de9..2d15e1d6e2141 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -66,22 +66,15 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) * * Here, we just set the correct metadata to indicate that the FPSIMD * state in the cpu regs (if any) belongs to current on the host. - * - * TIF_SVE is backed up here, since it may get clobbered with guest state. - * This flag is restored by kvm_arch_vcpu_put_fp(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 | - KVM_ARM64_HOST_SVE_IN_USE | - KVM_ARM64_HOST_SVE_ENABLED); + vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED; vcpu->arch.flags |= KVM_ARM64_FP_HOST; - if (test_thread_flag(TIF_SVE)) - vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } @@ -115,13 +108,11 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { unsigned long flags; - bool host_has_sve = system_supports_sve(); - bool guest_has_sve = vcpu_has_sve(vcpu); local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { - if (guest_has_sve) { + if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); /* Restore the VL that was saved when bound to the CPU */ @@ -131,7 +122,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) } fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && host_has_sve) { + } else if (has_vhe() && system_supports_sve()) { /* * The FPSIMD/SVE state in the CPU has not been touched, and we * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been @@ -145,8 +136,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - update_thread_flag(TIF_SVE, - vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + update_thread_flag(TIF_SVE, 0); local_irq_restore(flags); } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 7a0af1d39303c..e65c2956b881e 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -143,16 +143,6 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu) -{ - struct thread_struct *thread; - - thread = container_of(vcpu->arch.host_fpsimd_state, struct thread_struct, - uw.fpsimd_state); - - __sve_save_state(sve_pffr(thread), &vcpu->arch.host_fpsimd_state->fpsr); -} - static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) { sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); @@ -169,21 +159,14 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) */ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { - bool sve_guest, sve_host; + bool sve_guest; u8 esr_ec; u64 reg; if (!system_supports_fpsimd()) return false; - if (system_supports_sve()) { - sve_guest = vcpu_has_sve(vcpu); - sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE; - } else { - sve_guest = false; - sve_host = false; - } - + sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); /* Don't handle SVE traps for non-SVE vcpus here: */ @@ -207,11 +190,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { - if (sve_host) - __hyp_sve_save_host(vcpu); - else - __fpsimd_save_state(vcpu->arch.host_fpsimd_state); - + __fpsimd_save_state(vcpu->arch.host_fpsimd_state); vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; } From e66425fc9ba33e9716d6e7c6bc78bb62f981d4df Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 22 Nov 2021 15:59:23 +0000 Subject: [PATCH 3/6] KVM: arm64: Remove unused __sve_save_state Now that we don't have any users left for __sve_save_state, remove it altogether. Should we ever need to save the SVE state from the hypervisor again, we can always re-introduce it. Suggested-by: Zenghui Yu Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_hyp.h | 1 - arch/arm64/kvm/hyp/fpsimd.S | 6 ------ 2 files changed, 7 deletions(-) diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 5afd14ab15b9f..462882f356c77 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -90,7 +90,6 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu); void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); -void __sve_save_state(void *sve_pffr, u32 *fpsr); void __sve_restore_state(void *sve_pffr, u32 *fpsr); #ifndef __KVM_NVHE_HYPERVISOR__ diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S index e950875e31cee..61e6f3ba7b7d1 100644 --- a/arch/arm64/kvm/hyp/fpsimd.S +++ b/arch/arm64/kvm/hyp/fpsimd.S @@ -25,9 +25,3 @@ SYM_FUNC_START(__sve_restore_state) sve_load 0, x1, x2, 3 ret SYM_FUNC_END(__sve_restore_state) - -SYM_FUNC_START(__sve_save_state) - mov x2, #1 - sve_save 0, x1, x2, 3 - ret -SYM_FUNC_END(__sve_save_state) From af9a0e21d817f40595aa629de32d3bd96582abef Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 21 Oct 2021 14:10:35 +0100 Subject: [PATCH 4/6] KVM: arm64: Introduce flag shadowing TIF_FOREIGN_FPSTATE We currently have to maintain a mapping the thread_info structure at EL2 in order to be able to check the TIF_FOREIGN_FPSTATE flag. In order to eventually get rid of this, start with a vcpu flag that shadows the thread flag on each entry into the hypervisor. Reviewed-by: Mark Brown Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/kvm/arm.c | 1 + arch/arm64/kvm/fpsimd.c | 8 ++++++++ arch/arm64/kvm/hyp/include/hyp/switch.h | 2 +- 4 files changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3ccfc3e3e4366..9f1703ebae153 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -441,6 +441,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ +#define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ @@ -736,6 +737,7 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e4727dc771bf3..d1b93dc8d6390 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -849,6 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } kvm_arm_setup_debug(vcpu); + kvm_arch_vcpu_ctxflush_fp(vcpu); /************************************************************** * Enter the guest diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 2d15e1d6e2141..a18b9c1744d58 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -79,6 +79,14 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } +void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) +{ + if (test_thread_flag(TIF_FOREIGN_FPSTATE)) + vcpu->arch.flags |= KVM_ARM64_FP_FOREIGN_FPSTATE; + else + vcpu->arch.flags &= ~KVM_ARM64_FP_FOREIGN_FPSTATE; +} + /* * If the guest FPSIMD state was loaded, update the host's context * tracking data mark the CPU FPSIMD regs as dirty and belonging to vcpu diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index e65c2956b881e..a243a2a821319 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -49,7 +49,7 @@ static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) * trap the accesses. */ if (!system_supports_fpsimd() || - vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + vcpu->arch.flags & KVM_ARM64_FP_FOREIGN_FPSTATE) vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_FP_HOST); From bee14bca735a6f897a6ec3e42f3e5d2d8966e87e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 21 Oct 2021 14:18:00 +0100 Subject: [PATCH 5/6] KVM: arm64: Stop mapping current thread_info at EL2 Now that we can track an equivalent of TIF_FOREIGN_FPSTATE, drop the mapping of current's thread_info at EL2. Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/fpsimd.c | 12 +----------- arch/arm64/kvm/hyp/include/hyp/switch.h | 1 - arch/arm64/kvm/hyp/nvhe/switch.c | 1 - arch/arm64/kvm/hyp/vhe/switch.c | 1 - 5 files changed, 1 insertion(+), 16 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 9f1703ebae153..dd5810ea37a98 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -26,7 +26,6 @@ #include #include #include -#include #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -321,7 +320,6 @@ struct kvm_vcpu_arch { struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; - struct thread_info *host_thread_info; /* hyp VA */ struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ struct { diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index a18b9c1744d58..b5b59b9f2eff6 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -7,7 +7,6 @@ */ #include #include -#include #include #include #include @@ -28,17 +27,9 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) { int ret; - struct thread_info *ti = ¤t->thread_info; struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state; - /* - * Make sure the host task thread flags and fpsimd state are - * visible to hyp: - */ - ret = create_hyp_mappings(ti, ti + 1, PAGE_HYP); - if (ret) - goto error; - + /* Make sure the host task fpsimd state is visible to hyp: */ ret = create_hyp_mappings(fpsimd, fpsimd + 1, PAGE_HYP); if (ret) goto error; @@ -54,7 +45,6 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) goto error; } - vcpu->arch.host_thread_info = kern_hyp_va(ti); vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd); error: return ret; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index a243a2a821319..11e8580f2fdcb 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -29,7 +29,6 @@ #include #include #include -#include struct kvm_exception_table_entry { int insn, fixup; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c0e3fed26d930..329c706af39fe 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 5a2cb5d9bc4b2..1d162b9c78bf7 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -24,7 +24,6 @@ #include #include #include -#include /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); From 31aa126de88e1e9f562f708a9b0ec5917ba97dce Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 21 Oct 2021 15:33:22 +0100 Subject: [PATCH 6/6] arm64/fpsimd: Document the use of TIF_FOREIGN_FPSTATE by KVM The bit of documentation that talks about TIF_FOREIGN_FPSTATE does not mention the ungodly tricks that KVM plays with this flag. Try and document this for the posterity. Reviewed-by: Mark Brown Signed-off-by: Marc Zyngier --- arch/arm64/kernel/fpsimd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index fa244c426f610..6fb361e8bed8f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -78,7 +78,11 @@ * indicate whether or not the userland FPSIMD state of the current task is * present in the registers. The flag is set unless the FPSIMD registers of this * CPU currently contain the most recent userland FPSIMD state of the current - * task. + * task. If the task is behaving as a VMM, then this is will be managed by + * KVM which will clear it to indicate that the vcpu FPSIMD state is currently + * loaded on the CPU, allowing the state to be saved if a FPSIMD-aware + * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and + * flag the register state as invalid. * * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may * save the task's FPSIMD context back to task_struct from softirq context.