From mboxrd@z Thu Jan 1 00:00:00 1970 From: shankerd@codeaurora.org (Shanker Donthineni) Date: Tue, 30 Aug 2016 07:22:03 -0500 Subject: [PATCH v2] arm64: KVM: Save four instructions in __guest_enter/exit() In-Reply-To: <57C565E6.4020109@arm.com> References: <1472529074-19261-1-git-send-email-shankerd@codeaurora.org> <20160830095534.GD10162@cbox> <57C565E6.4020109@arm.com> Message-ID: <3d494915-26b3-60c4-fe3a-9067dff7ace0@codeaurora.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi Marc, On 08/30/2016 05:54 AM, Marc Zyngier wrote: > On 30/08/16 10:55, Christoffer Dall wrote: >> On Mon, Aug 29, 2016 at 10:51:14PM -0500, Shanker Donthineni wrote: >>> We are doing an unnecessary stack push/pop operation when restoring >>> the guest registers x0-x18 in __guest_enter(). This patch saves the >>> two instructions by using x18 as a base register. No need to store >>> the vcpu context pointer in stack because it is redundant, the same >>> information is available in tpidr_el2. The function __guest_exit() >>> prototype is simplified and caller pushes the regs x0-x1 to stack >>> instead of regs x0-x3. >>> >>> Signed-off-by: Shanker Donthineni >> This looks reasonable to me: >> >> Reviewed-by: Christoffer Dall >> >> Unless Marc has any insight into this having a negative effect on ARM >> CPUs, I'll go ahead an merge this. > I've given it a go on Seattle, and couldn't observe any difference with > the original code, which is pretty good news! > > I have some comments below, though: > >> -Christoffer >> >>> --- >>> Changes since v1: >>> Incorporated Cristoffer suggestions. >>> __guest_exit prototype is changed to 'void __guest_exit(u64 reason, > struct kvm_vcpu *vcpu)'. >>> arch/arm64/kvm/hyp/entry.S | 101 > +++++++++++++++++++++-------------------- >>> arch/arm64/kvm/hyp/hyp-entry.S | 11 +++-- >>> 2 files changed, 57 insertions(+), 55 deletions(-) >>> >>> diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S >>> index ce9e5e5..f70489a 100644 >>> --- a/arch/arm64/kvm/hyp/entry.S >>> +++ b/arch/arm64/kvm/hyp/entry.S >>> @@ -55,75 +55,76 @@ >>> */ >>> ENTRY(__guest_enter) >>> // x0: vcpu >>> - // x1: host/guest context >>> - // x2-x18: clobbered by macros >>> + // x1: host context >>> + // x2-x17: clobbered by macros >>> + // x18: guest context >>> >>> // Store the host regs >>> save_callee_saved_regs x1 >>> >>> - // Preserve vcpu & host_ctxt for use at exit time >>> - stp x0, x1, [sp, #-16]! >>> + // Store the host_ctxt for use at exit time >>> + str x1, [sp, #-16]! >>> >>> - add x1, x0, #VCPU_CONTEXT >>> + add x18, x0, #VCPU_CONTEXT >>> >>> - // Prepare x0-x1 for later restore by pushing them onto the stack >>> - ldp x2, x3, [x1, #CPU_XREG_OFFSET(0)] >>> - stp x2, x3, [sp, #-16]! >>> + // Restore guest regs x0-x17 >>> + ldp x0, x1, [x18, #CPU_XREG_OFFSET(0)] >>> + ldp x2, x3, [x18, #CPU_XREG_OFFSET(2)] >>> + ldp x4, x5, [x18, #CPU_XREG_OFFSET(4)] >>> + ldp x6, x7, [x18, #CPU_XREG_OFFSET(6)] >>> + ldp x8, x9, [x18, #CPU_XREG_OFFSET(8)] >>> + ldp x10, x11, [x18, #CPU_XREG_OFFSET(10)] >>> + ldp x12, x13, [x18, #CPU_XREG_OFFSET(12)] >>> + ldp x14, x15, [x18, #CPU_XREG_OFFSET(14)] >>> + ldp x16, x17, [x18, #CPU_XREG_OFFSET(16)] >>> >>> - // x2-x18 >>> - ldp x2, x3, [x1, #CPU_XREG_OFFSET(2)] >>> - ldp x4, x5, [x1, #CPU_XREG_OFFSET(4)] >>> - ldp x6, x7, [x1, #CPU_XREG_OFFSET(6)] >>> - ldp x8, x9, [x1, #CPU_XREG_OFFSET(8)] >>> - ldp x10, x11, [x1, #CPU_XREG_OFFSET(10)] >>> - ldp x12, x13, [x1, #CPU_XREG_OFFSET(12)] >>> - ldp x14, x15, [x1, #CPU_XREG_OFFSET(14)] >>> - ldp x16, x17, [x1, #CPU_XREG_OFFSET(16)] >>> - ldr x18, [x1, #CPU_XREG_OFFSET(18)] >>> + // Restore guest regs x19-x29, lr >>> + restore_callee_saved_regs x18 >>> >>> - // x19-x29, lr >>> - restore_callee_saved_regs x1 >>> - >>> - // Last bits of the 64bit state >>> - ldp x0, x1, [sp], #16 >>> + // Restore guest reg x18 >>> + ldr x18, [x18, #CPU_XREG_OFFSET(18)] >>> >>> // Do not touch any register after this! >>> eret >>> ENDPROC(__guest_enter) >>> >>> +/* >>> + * void __guest_exit(u64 exit_reason, struct kvm_vcpu *vcpu); >>> + */ > I'm not sure this comment makes much sense as it stands. This is not a C > function by any stretch of the imagination, but the continuation of > __guest_enter. The calling convention is not the C one at all (see how > the stack is involved), and caller-saved registers are going to be > clobbered. I'll remove this confusing comments. >>> ENTRY(__guest_exit) >>> - // x0: vcpu >>> - // x1: return code >>> - // x2-x3: free >>> - // x4-x29,lr: vcpu regs >>> - // vcpu x0-x3 on the stack >>> - >>> - add x2, x0, #VCPU_CONTEXT >>> - >>> - stp x4, x5, [x2, #CPU_XREG_OFFSET(4)] >>> - stp x6, x7, [x2, #CPU_XREG_OFFSET(6)] >>> - stp x8, x9, [x2, #CPU_XREG_OFFSET(8)] >>> - stp x10, x11, [x2, #CPU_XREG_OFFSET(10)] >>> - stp x12, x13, [x2, #CPU_XREG_OFFSET(12)] >>> - stp x14, x15, [x2, #CPU_XREG_OFFSET(14)] >>> - stp x16, x17, [x2, #CPU_XREG_OFFSET(16)] >>> - str x18, [x2, #CPU_XREG_OFFSET(18)] >>> - >>> - ldp x6, x7, [sp], #16 // x2, x3 >>> - ldp x4, x5, [sp], #16 // x0, x1 >>> - >>> - stp x4, x5, [x2, #CPU_XREG_OFFSET(0)] >>> - stp x6, x7, [x2, #CPU_XREG_OFFSET(2)] >>> + // x0: return code >>> + // x1: vcpu >>> + // x2-x29,lr: vcpu regs >>> + // vcpu x0-x1 on the stack >>> + >>> + add x1, x1, #VCPU_CONTEXT >>> + >>> + // Store the guest regs x2 and x3 >>> + stp x2, x3, [x1, #CPU_XREG_OFFSET(2)] >>> + >>> + // Retrieve the guest regs x0-x1 from the stack >>> + ldp x2, x3, [sp], #16 // x0, x1 >>> + >>> + // Store the guest regs x0-x1 and x4-x18 >>> + stp x2, x3, [x1, #CPU_XREG_OFFSET(0)] >>> + stp x4, x5, [x1, #CPU_XREG_OFFSET(4)] >>> + stp x6, x7, [x1, #CPU_XREG_OFFSET(6)] >>> + stp x8, x9, [x1, #CPU_XREG_OFFSET(8)] >>> + stp x10, x11, [x1, #CPU_XREG_OFFSET(10)] >>> + stp x12, x13, [x1, #CPU_XREG_OFFSET(12)] >>> + stp x14, x15, [x1, #CPU_XREG_OFFSET(14)] >>> + stp x16, x17, [x1, #CPU_XREG_OFFSET(16)] >>> + str x18, [x1, #CPU_XREG_OFFSET(18)] >>> + >>> + // Store the guest regs x19-x29, lr >>> + save_callee_saved_regs x1 >>> >>> - save_callee_saved_regs x2 >>> + // Restore the host_ctxt from the stack >>> + ldr x2, [sp], #16 >>> >>> - // Restore vcpu & host_ctxt from the stack >>> - // (preserving return code in x1) >>> - ldp x0, x2, [sp], #16 >>> // Now restore the host regs >>> restore_callee_saved_regs x2 >>> >>> - mov x0, x1 >>> ret >>> ENDPROC(__guest_exit) >>> >>> diff --git a/arch/arm64/kvm/hyp/hyp-entry.S > b/arch/arm64/kvm/hyp/hyp-entry.S >>> index f6d9694..06e8b3b 100644 >>> --- a/arch/arm64/kvm/hyp/hyp-entry.S >>> +++ b/arch/arm64/kvm/hyp/hyp-entry.S >>> @@ -121,14 +121,15 @@ el1_trap: >>> cmp x2, #ESR_ELx_EC_FP_ASIMD >>> b.eq __fpsimd_guest_restore >>> >>> - mrs x0, tpidr_el2 >>> - mov x1, #ARM_EXCEPTION_TRAP >>> + ldp x2, x3, [sp], #16 >>> + mrs x1, tpidr_el2 >>> + mov x0, #ARM_EXCEPTION_TRAP >>> b __guest_exit >>> >>> el1_irq: >>> - save_x0_to_x3 > So the save_x0_to_x3 macro now only has one single user (and so does > restore_x0_to_x3). Should we consider inline it? Sure, I'll change to inline in v3 patch. >>> - mrs x0, tpidr_el2 >>> - mov x1, #ARM_EXCEPTION_IRQ >>> + stp x0, x1, [sp, #-16]! >>> + mrs x1, tpidr_el2 >>> + mov x0, #ARM_EXCEPTION_IRQ >>> b __guest_exit >>> >>> ENTRY(__hyp_do_panic) >>> -- >>> Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm > Technologies, Inc. >>> Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a > Linux Foundation Collaborative Project. > Thanks, > > M. -- Shanker Donthineni Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.