From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754035AbdBNQDf (ORCPT ); Tue, 14 Feb 2017 11:03:35 -0500 Received: from bombadil.infradead.org ([65.50.211.133]:59894 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752976AbdBNQDZ (ORCPT ); Tue, 14 Feb 2017 11:03:25 -0500 Date: Tue, 14 Feb 2017 17:03:06 +0100 From: Peter Zijlstra To: Waiman Long Cc: Jeremy Fitzhardinge , Chris Wright , Alok Kataria , Rusty Russell , Ingo Molnar , Thomas Gleixner , "H. Peter Anvin" , linux-arch@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, xen-devel@lists.xenproject.org, kvm@vger.kernel.org, Pan Xinhui , Paolo Bonzini , Radim =?utf-8?B?S3LEjW3DocWZ?= , Boris Ostrovsky , Juergen Gross Subject: Re: [PATCH v2] x86/paravirt: Don't make vcpu_is_preempted() a callee-save function Message-ID: <20170214160306.GP6500@twins.programming.kicks-ass.net> References: <1c949ed0-1b88-ae6e-4e6c-426502bfab5f@redhat.com> <14854496-0baa-1bf6-c819-f3d7fae13c2c@redhat.com> <20170213104716.GM6515@twins.programming.kicks-ass.net> <20170213105343.GJ6536@twins.programming.kicks-ass.net> <3dc50409-60dd-ad47-f971-448191e66038@redhat.com> <6f69b112-7ae4-bf8f-b767-29a68fd48632@redhat.com> <20170213215220.GN25813@worktop.programming.kicks-ass.net> <933ba8c6-4ebe-63e2-3c3a-2e5afef9269a@redhat.com> <20170214093946.GM6500@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23.1 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Feb 14, 2017 at 09:46:17AM -0500, Waiman Long wrote: > On 02/14/2017 04:39 AM, Peter Zijlstra wrote: > > On Mon, Feb 13, 2017 at 05:34:01PM -0500, Waiman Long wrote: > >> It is the address of &steal_time that will exceed the 32-bit limit. > > That seems extremely unlikely. That would mean we have more than 4G > > worth of per-cpu variables declared in the kernel. > > I have some doubt about if the compiler is able to properly use > RIP-relative addressing for this. Its not RIP relative, &steal_time lives in the .data..percpu section and is absolute in that. > Anyway, it seems like constraints > aren't allowed for asm() when not in the function context, at least for > the the compiler that I am using (4.8.5). So it is a moot point. Well kvm_steal_time is (host/guest) ABI anyway, so the offset is fixed and hard-coding it isn't a problem. $ readelf -s defconfig-build/vmlinux | grep steal_time 100843: 0000000000017ac0 64 OBJECT WEAK DEFAULT 35 steal_time $ objdump -dr defconfig-build/vmlinux | awk '/[<][^>]*[>]:/ { o=0 } /[<]__raw_callee_save___kvm_vcpu_is_preempted[>]:/ {o=1} { if (o) print $0 }' ffffffff810b4480 <__raw_callee_save___kvm_vcpu_is_preempted>: ffffffff810b4480: 55 push %rbp ffffffff810b4481: 48 89 e5 mov %rsp,%rbp ffffffff810b4484: 48 8b 04 fd 00 94 46 mov -0x7db96c00(,%rdi,8),%rax ffffffff810b448b: 82 ffffffff810b4488: R_X86_64_32S __per_cpu_offset ffffffff810b448c: 80 b8 d0 7a 01 00 00 cmpb $0x0,0x17ad0(%rax) ffffffff810b448e: R_X86_64_32S steal_time+0x10 ffffffff810b4493: 0f 95 c0 setne %al ffffffff810b4496: 5d pop %rbp ffffffff810b4497: c3 retq And as you'll note, the displacement is correct and 'small'. The below relies on the 'extra' cast in PVOP_CALL_ARG1() to extend the argument to 64bit on the call side of things. --- arch/x86/kernel/kvm.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 099fcba..2c854b8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -589,6 +589,7 @@ static void kvm_wait(u8 *ptr, u8 val) local_irq_restore(flags); } +#ifdef CONFIG_X86_32 __visible bool __kvm_vcpu_is_preempted(int cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); @@ -597,6 +598,26 @@ __visible bool __kvm_vcpu_is_preempted(int cpu) } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); +#else + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(int cpu); + +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +FRAME_BEGIN +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, 16+steal_time(%rax);" +"setne %al;" +FRAME_END +"ret;" +".popsection" +); + +#endif + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH v2] x86/paravirt: Don't make vcpu_is_preempted() a callee-save function Date: Tue, 14 Feb 2017 17:03:06 +0100 Message-ID: <20170214160306.GP6500@twins.programming.kicks-ass.net> References: <1c949ed0-1b88-ae6e-4e6c-426502bfab5f@redhat.com> <14854496-0baa-1bf6-c819-f3d7fae13c2c@redhat.com> <20170213104716.GM6515@twins.programming.kicks-ass.net> <20170213105343.GJ6536@twins.programming.kicks-ass.net> <3dc50409-60dd-ad47-f971-448191e66038@redhat.com> <6f69b112-7ae4-bf8f-b767-29a68fd48632@redhat.com> <20170213215220.GN25813@worktop.programming.kicks-ass.net> <933ba8c6-4ebe-63e2-3c3a-2e5afef9269a@redhat.com> <20170214093946.GM6500@twins.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Waiman Long Cc: linux-arch@vger.kernel.org, Juergen Gross , Jeremy Fitzhardinge , x86@kernel.org, kvm@vger.kernel.org, Radim =?utf-8?B?S3LEjW3DocWZ?= , Boris Ostrovsky , Pan Xinhui , Paolo Bonzini , linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, Chris Wright , Ingo Molnar , "H. Peter Anvin" , xen-devel@lists.xenproject.org, Alok Kataria , Thomas Gleixner List-Id: linux-arch.vger.kernel.org On Tue, Feb 14, 2017 at 09:46:17AM -0500, Waiman Long wrote: > On 02/14/2017 04:39 AM, Peter Zijlstra wrote: > > On Mon, Feb 13, 2017 at 05:34:01PM -0500, Waiman Long wrote: > >> It is the address of &steal_time that will exceed the 32-bit limit. > > That seems extremely unlikely. That would mean we have more than 4G > > worth of per-cpu variables declared in the kernel. > > I have some doubt about if the compiler is able to properly use > RIP-relative addressing for this. Its not RIP relative, &steal_time lives in the .data..percpu section and is absolute in that. > Anyway, it seems like constraints > aren't allowed for asm() when not in the function context, at least for > the the compiler that I am using (4.8.5). So it is a moot point. Well kvm_steal_time is (host/guest) ABI anyway, so the offset is fixed and hard-coding it isn't a problem. $ readelf -s defconfig-build/vmlinux | grep steal_time 100843: 0000000000017ac0 64 OBJECT WEAK DEFAULT 35 steal_time $ objdump -dr defconfig-build/vmlinux | awk '/[<][^>]*[>]:/ { o=0 } /[<]__raw_callee_save___kvm_vcpu_is_preempted[>]:/ {o=1} { if (o) print $0 }' ffffffff810b4480 <__raw_callee_save___kvm_vcpu_is_preempted>: ffffffff810b4480: 55 push %rbp ffffffff810b4481: 48 89 e5 mov %rsp,%rbp ffffffff810b4484: 48 8b 04 fd 00 94 46 mov -0x7db96c00(,%rdi,8),%rax ffffffff810b448b: 82 ffffffff810b4488: R_X86_64_32S __per_cpu_offset ffffffff810b448c: 80 b8 d0 7a 01 00 00 cmpb $0x0,0x17ad0(%rax) ffffffff810b448e: R_X86_64_32S steal_time+0x10 ffffffff810b4493: 0f 95 c0 setne %al ffffffff810b4496: 5d pop %rbp ffffffff810b4497: c3 retq And as you'll note, the displacement is correct and 'small'. The below relies on the 'extra' cast in PVOP_CALL_ARG1() to extend the argument to 64bit on the call side of things. --- arch/x86/kernel/kvm.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 099fcba..2c854b8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -589,6 +589,7 @@ static void kvm_wait(u8 *ptr, u8 val) local_irq_restore(flags); } +#ifdef CONFIG_X86_32 __visible bool __kvm_vcpu_is_preempted(int cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); @@ -597,6 +598,26 @@ __visible bool __kvm_vcpu_is_preempted(int cpu) } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); +#else + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(int cpu); + +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +FRAME_BEGIN +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, 16+steal_time(%rax);" +"setne %al;" +FRAME_END +"ret;" +".popsection" +); + +#endif + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */