On Sun, Dec 03, 2017 at 02:49:58PM +0100, Andrew Jones wrote:
> On Fri, Dec 01, 2017 at 06:52:03PM +0100, Christoffer Dall wrote:
> > On Tue, Nov 07, 2017 at 03:48:57PM +0100, Andrew Jones wrote:
> > > On Thu, Oct 12, 2017 at 12:41:15PM +0200, Christoffer Dall wrote:
> > > > Instead of having multiple calls from the world switch path to the debug
> > > > logic, each figuring out if the dirty bit is set and if we should
> > > > save/restore the debug registes, let's just provide two hooks to the
> > > > debug save/restore functionality, one for switching to the guest
> > > > context, and one for switching to the host context, and we get the
> > > > benefit of only having to evaluate the dirty flag once on each path,
> > > > plus we give the compiler some more room to inline some of this
> > > > functionality.
> > > >
> > > > Signed-off-by: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
> > > > ---
> > > > arch/arm64/include/asm/kvm_hyp.h | 10 ++-----
> > > > arch/arm64/kvm/hyp/debug-sr.c | 56 +++++++++++++++++++++++++++-------------
> > > > arch/arm64/kvm/hyp/switch.c | 6 ++---
> > > > 3 files changed, 42 insertions(+), 30 deletions(-)
> > > >
> > > > diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
> > > > index 08d3bb6..a0e5a70 100644
> > > > --- a/arch/arm64/include/asm/kvm_hyp.h
> > > > +++ b/arch/arm64/include/asm/kvm_hyp.h
> > > > @@ -139,14 +139,8 @@ void __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt);
> > > > void __sysreg32_save_state(struct kvm_vcpu *vcpu);
> > > > void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
> > > >
> > > > -void __debug_save_state(struct kvm_vcpu *vcpu,
> > > > - struct kvm_guest_debug_arch *dbg,
> > > > - struct kvm_cpu_context *ctxt);
> > > > -void __debug_restore_state(struct kvm_vcpu *vcpu,
> > > > - struct kvm_guest_debug_arch *dbg,
> > > > - struct kvm_cpu_context *ctxt);
> > > > -void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
> > > > -void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
> > > > +void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
> > > > +void __debug_switch_to_host(struct kvm_vcpu *vcpu);
> > > >
> > > > void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
> > > > void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
> > > > diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
> > > > index a2291b6..b4cd8e0 100644
> > > > --- a/arch/arm64/kvm/hyp/debug-sr.c
> > > > +++ b/arch/arm64/kvm/hyp/debug-sr.c
> > > > @@ -116,16 +116,13 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
> > > > write_sysreg_s(pmscr_el1, PMSCR_EL1);
> > > > }
> > > >
> > > > -void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
> > > > - struct kvm_guest_debug_arch *dbg,
> > > > - struct kvm_cpu_context *ctxt)
> > > > +static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
> > > > + struct kvm_guest_debug_arch *dbg,
> > > > + struct kvm_cpu_context *ctxt)
> > > > {
> > > > u64 aa64dfr0;
> > > > int brps, wrps;
> > > >
> > > > - if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
> > > > - return;
> > > > -
> > > > aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
> > > > brps = (aa64dfr0 >> 12) & 0xf;
> > > > wrps = (aa64dfr0 >> 20) & 0xf;
> > > > @@ -138,16 +135,13 @@ void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
> > > > ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
> > > > }
> > > >
> > > > -void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
> > > > - struct kvm_guest_debug_arch *dbg,
> > > > - struct kvm_cpu_context *ctxt)
> > > > +static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
> > > > + struct kvm_guest_debug_arch *dbg,
> > > > + struct kvm_cpu_context *ctxt)
> > > > {
> > > > u64 aa64dfr0;
> > > > int brps, wrps;
> > > >
> > > > - if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
> > > > - return;
> > > > -
> > > > aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
> > > >
> > > > brps = (aa64dfr0 >> 12) & 0xf;
> > > > @@ -161,24 +155,50 @@ void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
> > > > write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
> > > > }
> > > >
> > > > -void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu)
> > > > +void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
> > > > {
> > > > - __debug_save_state(vcpu, &vcpu->arch.host_debug_state.regs,
> > > > - kern_hyp_va(vcpu->arch.host_cpu_context));
> > > > + struct kvm_cpu_context *__host_ctxt;
> > > > + struct kvm_cpu_context *__guest_ctxt;
> > > > + struct kvm_guest_debug_arch *__host_dbg;
> > > > + struct kvm_guest_debug_arch *__guest_dbg;
> > >
> > > I caught in your reply to Marc that the __ prefix here is for hyp mode
> > > accessible code and data, but do we also need to use it for stack data?
> > > No big deal, but it's not very pretty.
> > >
> >
> > sure.
> >
> > > >
> > > > /* Non-VHE: Disable and flush SPE data generation
> > > > * VHE: The vcpu can run. but it can't hide. */
> > > > if (!has_vhe())
> > > > __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
> > > > +
> > > > + if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
> > > > + return;
> > > > +
> > > > + __host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
> > > > + __guest_ctxt = &vcpu->arch.ctxt;
> > > > + __host_dbg = &vcpu->arch.host_debug_state.regs;
> > > > + __guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
> > > > +
> > > > + __debug_save_state(vcpu, __host_dbg, __host_ctxt);
> > > > + __debug_restore_state(vcpu, __guest_dbg, __guest_ctxt);
> > > > }
> > > >
> > > > -void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu)
> > > > +void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
> > > > {
> > > > + struct kvm_cpu_context *__host_ctxt;
> > > > + struct kvm_cpu_context *__guest_ctxt;
> > > > + struct kvm_guest_debug_arch *__host_dbg;
> > > > + struct kvm_guest_debug_arch *__guest_dbg;
> > > > +
> > > > if (!has_vhe())
> > > > __debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
> > > >
> > > > - __debug_restore_state(vcpu, &vcpu->arch.host_debug_state.regs,
> > > > - kern_hyp_va(vcpu->arch.host_cpu_context));
> > > > + if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
> > > > + return;
> > > > +
> > > > + __host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
> > > > + __guest_ctxt = &vcpu->arch.ctxt;
> > > > + __host_dbg = &vcpu->arch.host_debug_state.regs;
> > > > + __guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
> > > > +
> > > > + __debug_save_state(vcpu, __guest_dbg, __guest_ctxt);
> > > > + __debug_restore_state(vcpu, __host_dbg, __host_ctxt);
> > > >
> > > > vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY;
> > > > }
> > > > diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
> > > > index ef05c59..e270cba 100644
> > > > --- a/arch/arm64/kvm/hyp/switch.c
> > > > +++ b/arch/arm64/kvm/hyp/switch.c
> > > > @@ -271,7 +271,6 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
> > > > guest_ctxt = &vcpu->arch.ctxt;
> > > >
> > > > __sysreg_save_host_state(host_ctxt);
> > > > - __debug_cond_save_host_state(vcpu);
> > > >
> > > > __activate_traps(vcpu);
> > > > __activate_vm(vcpu);
> > > > @@ -285,7 +284,7 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
> > > > */
> > > > __sysreg32_restore_state(vcpu);
> > > > __sysreg_restore_guest_state(guest_ctxt);
> > > > - __debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
> > > > + __debug_switch_to_guest(vcpu);
> > > >
> > > > /* Jump in the fire! */
> > > > again:
> > > > @@ -353,12 +352,11 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
> > > >
> > > > __sysreg_restore_host_state(host_ctxt);
> > > >
> > > > - __debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
> > > > /*
> > > > * This must come after restoring the host sysregs, since a non-VHE
> > > > * system may enable SPE here and make use of the TTBRs.
> > > > */
> > > > - __debug_cond_restore_host_state(vcpu);
> > > > + __debug_switch_to_host(vcpu);
> > > >
> > > > return exit_code;
> > > > }
> > > > --
> > > > 2.9.0
> > > >
> > >
> > > This looks like a nice cleanup, but can you please add a note to the
> > > commit message about why we don't need to use the
> > >
> > > save-host-state
> > > activate-traps-and-vm
> > > restore-guest-state
> > >
> > > and the reverse, patterns for the debug registers?
> >
> > I think the current commit message motivates the change fine.
> >
>
> The motivation is obvious, the justification for an additional change
> is not. How does it justify changing the sequence
>
> save-debug-host-state
> activate-debug-traps /* and other stuff in between */
> restore-debug-guest-state
>
> to
>
> activate-debug-traps /* and other stuff in between */
> save-debug-host-state
> restore-debug-guest-state
>
It doesn't, and I don't think it has to. The code is there, and I can't
argue all possible interdependencies between all code lines in English
and explain why it's safe, that requires looking at the code. The
commit message should motivate the change, not explain code which
requires understanding the software and the architecture.
If there was a clear rule that we do 'save, activate, restore' for
everything, it would make sense to explain why we can break that, but
that is not how I see the implementation. For example, there is no
particular reason why we restore the vgic before the timer, or the vgic
after we activate the stage 2 translation. The key here is
understanding the flexibility the architecture gives you.
You can then argue that since this bothers you, I should just add
something in the commit message, but I think that can be just as
misleading, because it would imply a total order, which doesn't exist.
Also, since you clearly understood the flow and what is going on, we're
probably fine as it is.
Thanks,
-Christoffer
