From: Peter Zijlstra <peterz@infradead.org>
To: Kai Huang <kai.huang@intel.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
linux-mm@kvack.org, x86@kernel.org, dave.hansen@intel.com,
kirill.shutemov@linux.intel.com, tony.luck@intel.com,
tglx@linutronix.de, bp@alien8.de, mingo@redhat.com,
hpa@zytor.com, seanjc@google.com, pbonzini@redhat.com,
david@redhat.com, dan.j.williams@intel.com,
rafael.j.wysocki@intel.com, ashok.raj@intel.com,
reinette.chatre@intel.com, len.brown@intel.com,
ak@linux.intel.com, isaku.yamahata@intel.com,
ying.huang@intel.com, chao.gao@intel.com,
sathyanarayanan.kuppuswamy@linux.intel.com, nik.borisov@suse.com,
bagasdotme@gmail.com, sagis@google.com, imammedo@redhat.com
Subject: Re: [PATCH v12 20/22] x86/virt/tdx: Allow SEAMCALL to handle #UD and #GP
Date: Wed, 28 Jun 2023 17:29:00 +0200 [thread overview]
Message-ID: <20230628152900.GI2438817@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <c124550719716f1f7759c2bdea70f4722d8e0167.1687784645.git.kai.huang@intel.com>
On Tue, Jun 27, 2023 at 02:12:50AM +1200, Kai Huang wrote:
> diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S
> index 49a54356ae99..757b0c34be10 100644
> --- a/arch/x86/virt/vmx/tdx/tdxcall.S
> +++ b/arch/x86/virt/vmx/tdx/tdxcall.S
> @@ -1,6 +1,7 @@
> /* SPDX-License-Identifier: GPL-2.0 */
> #include <asm/asm-offsets.h>
> #include <asm/tdx.h>
> +#include <asm/asm.h>
>
> /*
> * TDCALL and SEAMCALL are supported in Binutils >= 2.36.
> @@ -45,6 +46,7 @@
> /* Leave input param 2 in RDX */
>
> .if \host
> +1:
> seamcall
So what registers are actually clobbered by SEAMCALL ? There's a
distinct lack of it in SDM Vol.2 instruction list :-(
> /*
> * SEAMCALL instruction is essentially a VMExit from VMX root
> @@ -57,10 +59,23 @@
> * This value will never be used as actual SEAMCALL error code as
> * it is from the Reserved status code class.
> */
> - jnc .Lno_vmfailinvalid
> + jnc .Lseamcall_out
> mov $TDX_SEAMCALL_VMFAILINVALID, %rax
> -.Lno_vmfailinvalid:
> + jmp .Lseamcall_out
> +2:
> + /*
> + * SEAMCALL caused #GP or #UD. By reaching here %eax contains
> + * the trap number. Convert the trap number to the TDX error
> + * code by setting TDX_SW_ERROR to the high 32-bits of %rax.
> + *
> + * Note cannot OR TDX_SW_ERROR directly to %rax as OR instruction
> + * only accepts 32-bit immediate at most.
> + */
> + mov $TDX_SW_ERROR, %r12
> + orq %r12, %rax
>
> + _ASM_EXTABLE_FAULT(1b, 2b)
> +.Lseamcall_out:
This is all pretty atrocious code flow... would it at all be possible to
write it like:
SYM_FUNC_START(...)
.if \host
1: seamcall
cmovc %spare, %rax
2:
.else
tdcall
.endif
.....
RET
3:
mov $TDX_SW_ERROR, %r12
orq %r12, %rax
jmp 2b
_ASM_EXTABLE_FAULT(1b, 3b)
SYM_FUNC_END()
That is, having all that inline in the hotpath is quite horrific.
next prev parent reply other threads:[~2023-06-28 15:29 UTC|newest]
Thread overview: 159+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-26 14:12 [PATCH v12 00/22] TDX host kernel support Kai Huang
2023-06-26 14:12 ` [PATCH v12 01/22] x86/tdx: Define TDX supported page sizes as macros Kai Huang
2023-06-26 14:12 ` [PATCH v12 02/22] x86/virt/tdx: Detect TDX during kernel boot Kai Huang
2023-06-26 14:12 ` [PATCH v12 03/22] x86/virt/tdx: Make INTEL_TDX_HOST depend on X86_X2APIC Kai Huang
2023-06-26 14:12 ` [PATCH v12 04/22] x86/cpu: Detect TDX partial write machine check erratum Kai Huang
2023-06-29 11:22 ` David Hildenbrand
2023-06-26 14:12 ` [PATCH v12 05/22] x86/virt/tdx: Add SEAMCALL infrastructure Kai Huang
2023-06-27 9:48 ` kirill.shutemov
2023-06-27 10:28 ` Huang, Kai
2023-06-27 11:36 ` kirill.shutemov
2023-06-28 0:19 ` Isaku Yamahata
2023-06-28 3:09 ` Chao Gao
2023-06-28 3:34 ` Huang, Kai
2023-06-28 11:50 ` kirill.shutemov
2023-06-28 23:31 ` Huang, Kai
2023-06-29 11:25 ` David Hildenbrand
2023-06-28 12:58 ` Peter Zijlstra
2023-06-28 13:54 ` Peter Zijlstra
2023-06-28 23:25 ` Huang, Kai
2023-06-29 10:15 ` kirill.shutemov
2023-06-28 23:21 ` Huang, Kai
2023-06-29 3:40 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 06/22] x86/virt/tdx: Handle SEAMCALL running out of entropy error Kai Huang
2023-06-28 13:02 ` Peter Zijlstra
2023-06-28 23:30 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 07/22] x86/virt/tdx: Add skeleton to enable TDX on demand Kai Huang
2023-06-26 21:21 ` Sathyanarayanan Kuppuswamy
2023-06-27 10:37 ` Huang, Kai
2023-06-27 9:50 ` kirill.shutemov
2023-06-27 10:34 ` Huang, Kai
2023-06-27 12:18 ` kirill.shutemov
2023-06-27 22:37 ` Huang, Kai
2023-06-28 0:28 ` Huang, Kai
2023-06-28 11:55 ` kirill.shutemov
2023-06-28 13:35 ` Peter Zijlstra
2023-06-29 0:15 ` Huang, Kai
2023-06-30 9:22 ` Peter Zijlstra
2023-06-30 10:09 ` Huang, Kai
2023-06-30 18:42 ` Isaku Yamahata
2023-07-01 8:15 ` Huang, Kai
2023-06-28 0:31 ` Isaku Yamahata
2023-06-28 13:04 ` Peter Zijlstra
2023-06-29 0:00 ` Huang, Kai
2023-06-30 9:25 ` Peter Zijlstra
2023-06-30 9:48 ` Huang, Kai
2023-06-28 13:08 ` Peter Zijlstra
2023-06-29 0:08 ` Huang, Kai
2023-06-28 13:17 ` Peter Zijlstra
2023-06-29 0:10 ` Huang, Kai
2023-06-30 9:26 ` Peter Zijlstra
2023-06-30 9:55 ` Huang, Kai
2023-06-30 18:30 ` Peter Zijlstra
2023-06-30 19:05 ` Isaku Yamahata
2023-06-30 21:24 ` Sean Christopherson
2023-06-30 21:58 ` Dan Williams
2023-06-30 23:13 ` Dave Hansen
2023-07-03 10:38 ` Peter Zijlstra
2023-07-03 10:49 ` Peter Zijlstra
2023-07-03 14:40 ` Dave Hansen
2023-07-03 15:03 ` Peter Zijlstra
2023-07-03 15:26 ` Dave Hansen
2023-07-03 17:55 ` kirill.shutemov
2023-07-03 18:26 ` Dave Hansen
2023-07-05 7:14 ` Peter Zijlstra
2023-07-04 16:58 ` Peter Zijlstra
2023-07-04 21:50 ` Huang, Kai
2023-07-05 7:16 ` Peter Zijlstra
2023-07-05 7:54 ` Huang, Kai
2023-07-05 14:34 ` Dave Hansen
2023-07-05 14:57 ` Peter Zijlstra
2023-07-06 14:49 ` Dave Hansen
2023-07-10 17:58 ` Sean Christopherson
2023-06-29 11:31 ` David Hildenbrand
2023-06-29 22:58 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 08/22] x86/virt/tdx: Get information about TDX module and TDX-capable memory Kai Huang
2023-06-27 9:51 ` kirill.shutemov
2023-06-27 10:45 ` Huang, Kai
2023-06-27 11:37 ` kirill.shutemov
2023-06-27 11:46 ` Huang, Kai
2023-06-28 14:10 ` Peter Zijlstra
2023-06-29 9:15 ` Huang, Kai
2023-06-30 9:34 ` Peter Zijlstra
2023-06-30 9:58 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 09/22] x86/virt/tdx: Use all system memory when initializing TDX module as TDX memory Kai Huang
2023-06-28 14:17 ` Peter Zijlstra
2023-06-29 0:57 ` Huang, Kai
2023-07-11 11:38 ` David Hildenbrand
2023-07-11 12:27 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 10/22] x86/virt/tdx: Add placeholder to construct TDMRs to cover all TDX memory regions Kai Huang
2023-06-26 14:12 ` [PATCH v12 11/22] x86/virt/tdx: Fill out " Kai Huang
2023-07-04 7:28 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 12/22] x86/virt/tdx: Allocate and set up PAMTs for TDMRs Kai Huang
2023-06-27 9:51 ` kirill.shutemov
2023-07-04 7:40 ` Yuan Yao
2023-07-04 8:59 ` Huang, Kai
2023-07-11 11:42 ` David Hildenbrand
2023-07-11 11:49 ` Huang, Kai
2023-07-11 11:55 ` David Hildenbrand
2023-06-26 14:12 ` [PATCH v12 13/22] x86/virt/tdx: Designate reserved areas for all TDMRs Kai Huang
2023-07-05 5:29 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 14/22] x86/virt/tdx: Configure TDX module with the TDMRs and global KeyID Kai Huang
2023-07-05 6:49 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 15/22] x86/virt/tdx: Configure global KeyID on all packages Kai Huang
2023-07-05 8:13 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 16/22] x86/virt/tdx: Initialize all TDMRs Kai Huang
2023-07-06 5:31 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 17/22] x86/kexec: Flush cache of TDX private memory Kai Huang
2023-06-26 14:12 ` [PATCH v12 18/22] x86/virt/tdx: Keep TDMRs when module initialization is successful Kai Huang
2023-06-28 9:04 ` Nikolay Borisov
2023-06-29 1:03 ` Huang, Kai
2023-06-28 12:23 ` kirill.shutemov
2023-06-28 12:48 ` Nikolay Borisov
2023-06-29 0:24 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 19/22] x86/kexec(): Reset TDX private memory on platforms with TDX erratum Kai Huang
2023-06-28 9:20 ` Nikolay Borisov
2023-06-29 0:32 ` Dave Hansen
2023-06-29 0:58 ` Huang, Kai
2023-06-29 3:19 ` Huang, Kai
2023-06-29 5:38 ` Huang, Kai
2023-06-29 9:45 ` Huang, Kai
2023-06-29 9:48 ` Nikolay Borisov
2023-06-28 12:29 ` kirill.shutemov
2023-06-29 0:27 ` Huang, Kai
2023-07-07 4:01 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 20/22] x86/virt/tdx: Allow SEAMCALL to handle #UD and #GP Kai Huang
2023-06-28 12:32 ` kirill.shutemov
2023-06-28 15:29 ` Peter Zijlstra [this message]
2023-06-28 20:38 ` Peter Zijlstra
2023-06-28 21:11 ` Peter Zijlstra
2023-06-28 21:16 ` Peter Zijlstra
2023-06-30 9:03 ` kirill.shutemov
2023-06-30 10:02 ` Huang, Kai
2023-06-30 10:22 ` kirill.shutemov
2023-06-30 11:06 ` Huang, Kai
2023-06-29 10:33 ` Huang, Kai
2023-06-30 10:06 ` Peter Zijlstra
2023-06-30 10:18 ` Huang, Kai
2023-06-30 15:16 ` Dave Hansen
2023-07-01 8:16 ` Huang, Kai
2023-06-30 10:21 ` Peter Zijlstra
2023-06-30 11:05 ` Huang, Kai
2023-06-30 12:06 ` Peter Zijlstra
2023-06-30 15:14 ` Peter Zijlstra
2023-07-03 12:15 ` Huang, Kai
2023-07-05 10:21 ` Peter Zijlstra
2023-07-05 11:34 ` Huang, Kai
2023-07-05 12:19 ` Peter Zijlstra
2023-07-05 12:53 ` Huang, Kai
2023-07-05 20:56 ` Isaku Yamahata
2023-07-05 12:21 ` Peter Zijlstra
2023-06-29 11:16 ` kirill.shutemov
2023-06-29 10:00 ` Huang, Kai
2023-06-26 14:12 ` [PATCH v12 21/22] x86/mce: Improve error log of kernel space TDX #MC due to erratum Kai Huang
2023-06-28 12:38 ` kirill.shutemov
2023-07-07 7:26 ` Yuan Yao
2023-06-26 14:12 ` [PATCH v12 22/22] Documentation/x86: Add documentation for TDX host support Kai Huang
2023-06-28 7:04 ` [PATCH v12 00/22] TDX host kernel support Yuan Yao
2023-06-28 8:12 ` Huang, Kai
2023-06-29 1:01 ` Yuan Yao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230628152900.GI2438817@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=ak@linux.intel.com \
--cc=ashok.raj@intel.com \
--cc=bagasdotme@gmail.com \
--cc=bp@alien8.de \
--cc=chao.gao@intel.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=hpa@zytor.com \
--cc=imammedo@redhat.com \
--cc=isaku.yamahata@intel.com \
--cc=kai.huang@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=len.brown@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@redhat.com \
--cc=nik.borisov@suse.com \
--cc=pbonzini@redhat.com \
--cc=rafael.j.wysocki@intel.com \
--cc=reinette.chatre@intel.com \
--cc=sagis@google.com \
--cc=sathyanarayanan.kuppuswamy@linux.intel.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox