diff options
author | Dave Martin <Dave.Martin@arm.com> | 2018-04-06 14:55:59 +0100 |
---|---|---|
committer | Marc Zyngier <marc.zyngier@arm.com> | 2018-05-25 12:28:28 +0100 |
commit | e6b673b741ea0d7cd275ad40748bfc225accc423 (patch) | |
tree | e77366c66971f00874ecc0406bca68ad5671df93 /arch/arm64/kvm/hyp/switch.c | |
parent | fa89d31c53061139bd66f9de6e55340ac7bd5480 (diff) | |
download | blackbird-op-linux-e6b673b741ea0d7cd275ad40748bfc225accc423.tar.gz blackbird-op-linux-e6b673b741ea0d7cd275ad40748bfc225accc423.zip |
KVM: arm64: Optimise FPSIMD handling to reduce guest/host thrashing
This patch refactors KVM to align the host and guest FPSIMD
save/restore logic with each other for arm64. This reduces the
number of redundant save/restore operations that must occur, and
reduces the common-case IRQ blackout time during guest exit storms
by saving the host state lazily and optimising away the need to
restore the host state before returning to the run loop.
Four hooks are defined in order to enable this:
* kvm_arch_vcpu_run_map_fp():
Called on PID change to map necessary bits of current to Hyp.
* kvm_arch_vcpu_load_fp():
Set up FP/SIMD for entering the KVM run loop (parse as
"vcpu_load fp").
* kvm_arch_vcpu_ctxsync_fp():
Get FP/SIMD into a safe state for re-enabling interrupts after a
guest exit back to the run loop.
For arm64 specifically, this involves updating the host kernel's
FPSIMD context tracking metadata so that kernel-mode NEON use
will cause the vcpu's FPSIMD state to be saved back correctly
into the vcpu struct. This must be done before re-enabling
interrupts because kernel-mode NEON may be used by softirqs.
* kvm_arch_vcpu_put_fp():
Save guest FP/SIMD state back to memory and dissociate from the
CPU ("vcpu_put fp").
Also, the arm64 FPSIMD context switch code is updated to enable it
to save back FPSIMD state for a vcpu, not just current. A few
helpers drive this:
* fpsimd_bind_state_to_cpu(struct user_fpsimd_state *fp):
mark this CPU as having context fp (which may belong to a vcpu)
currently loaded in its registers. This is the non-task
equivalent of the static function fpsimd_bind_to_cpu() in
fpsimd.c.
* task_fpsimd_save():
exported to allow KVM to save the guest's FPSIMD state back to
memory on exit from the run loop.
* fpsimd_flush_state():
invalidate any context's FPSIMD state that is currently loaded.
Used to disassociate the vcpu from the CPU regs on run loop exit.
These changes allow the run loop to enable interrupts (and thus
softirqs that may use kernel-mode NEON) without having to save the
guest's FPSIMD state eagerly.
Some new vcpu_arch fields are added to make all this work. Because
host FPSIMD state can now be saved back directly into current's
thread_struct as appropriate, host_cpu_context is no longer used
for preserving the FPSIMD state. However, it is still needed for
preserving other things such as the host's system registers. To
avoid ABI churn, the redundant storage space in host_cpu_context is
not removed for now.
arch/arm is not addressed by this patch and continues to use its
current save/restore logic. It could provide implementations of
the helpers later if desired.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Diffstat (limited to 'arch/arm64/kvm/hyp/switch.c')
-rw-r--r-- | arch/arm64/kvm/hyp/switch.c | 51 |
1 files changed, 25 insertions, 26 deletions
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index c0796c4d93a5..118f3002b9ce 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -23,19 +23,21 @@ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/fpsimd.h> #include <asm/debug-monitors.h> +#include <asm/thread_info.h> -static bool __hyp_text __fpsimd_enabled_nvhe(void) +/* Check whether the FP regs were dirtied while in the host-side run loop: */ +static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu) { - return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP); -} + if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_FP_HOST); -static bool fpsimd_enabled_vhe(void) -{ - return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN); + return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED); } /* Save the 32-bit only FPSIMD system register state */ @@ -92,7 +94,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN); + val &= ~CPACR_EL1_ZEN; + if (!update_fp_enabled(vcpu)) + val &= ~CPACR_EL1_FPEN; + write_sysreg(val, cpacr_el1); write_sysreg(kvm_get_hyp_vector(), vbar_el1); @@ -105,7 +110,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) __activate_traps_common(vcpu); val = CPTR_EL2_DEFAULT; - val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ; + val |= CPTR_EL2_TTA | CPTR_EL2_TZ; + if (!update_fp_enabled(vcpu)) + val |= CPTR_EL2_TFP; + write_sysreg(val, cptr_el2); } @@ -321,8 +329,6 @@ static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu) void __hyp_text __hyp_switch_fpsimd(u64 esr __always_unused, struct kvm_vcpu *vcpu) { - kvm_cpu_context_t *host_ctxt; - if (has_vhe()) write_sysreg(read_sysreg(cpacr_el1) | CPACR_EL1_FPEN, cpacr_el1); @@ -332,14 +338,19 @@ void __hyp_text __hyp_switch_fpsimd(u64 esr __always_unused, isb(); - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); - __fpsimd_save_state(&host_ctxt->gp_regs.fp_regs); + if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { + __fpsimd_save_state(vcpu->arch.host_fpsimd_state); + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + } + __fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs); /* Skip restoring fpexc32 for AArch64 guests */ if (!(read_sysreg(hcr_el2) & HCR_RW)) write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2], fpexc32_el2); + + vcpu->arch.flags |= KVM_ARM64_FP_ENABLED; } /* @@ -418,7 +429,6 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; u64 exit_code; host_ctxt = vcpu->arch.host_cpu_context; @@ -440,19 +450,14 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); - fp_enabled = fpsimd_enabled_vhe(); - sysreg_save_guest_state_vhe(guest_ctxt); __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); - if (fp_enabled) { - __fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs); - __fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs); + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) __fpsimd_save_fpexc32(vcpu); - } __debug_switch_to_host(vcpu); @@ -464,7 +469,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; u64 exit_code; vcpu = kern_hyp_va(vcpu); @@ -496,8 +500,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); - fp_enabled = __fpsimd_enabled_nvhe(); - __sysreg_save_state_nvhe(guest_ctxt); __sysreg32_save_state(vcpu); __timer_disable_traps(vcpu); @@ -508,11 +510,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_restore_state_nvhe(host_ctxt); - if (fp_enabled) { - __fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs); - __fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs); + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) __fpsimd_save_fpexc32(vcpu); - } /* * This must come after restoring the host sysregs, since a non-VHE |