linux-kernel - Re: [PATCH v9 0/8] Parallel CPU bringup for x86

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5c557f9b6f55dc2a612ee89142971298e6ae12d8.camel@infradead.org>
Date:   Tue, 21 Feb 2023 08:17:54 +0000
From:   David Woodhouse <dwmw2@...radead.org>
To:     Oleksandr Natalenko <oleksandr@...alenko.name>
Cc:     Kim Phillips <kim.phillips@....com>, tglx@...utronix.de,
        Usama Arif <usama.arif@...edance.com>, arjan@...ux.intel.com,
        mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com,
        hpa@...or.com, x86@...nel.org, pbonzini@...hat.com,
        paulmck@...nel.org, linux-kernel@...r.kernel.org,
        kvm@...r.kernel.org, rcu@...r.kernel.org, mimoja@...oja.de,
        hewenliang4@...wei.com, thomas.lendacky@....com, seanjc@...gle.com,
        pmenzel@...gen.mpg.de, fam.zheng@...edance.com,
        punit.agrawal@...edance.com, simon.evans@...edance.com,
        liangma@...ngbit.com,
        "Limonciello, Mario" <Mario.Limonciello@....com>,
        Piotr Gorski <piotrgorski@...hyos.org>
Subject: Re: [PATCH v9 0/8] Parallel CPU bringup for x86_64

On Tue, 2023-02-21 at 09:05 +0100, Oleksandr Natalenko wrote:
> 
> Please see here: http://ix.io/4oLm

Was that just for one CPU? Can we have them all please?

The interesting part is the line starting 00000001. We're looking at
the top 8 bits of EBX:

Leaf     Subleaf    EAX            EBX            ECX            EDX            
00000000 00000000:  00000010 ....  68747541 Auth  444d4163 cAMD  69746e65 enti
00000001 00000000:  00a20f12 ....  00200800 .. .  7ef8320b .2.~  178bfbff ....
                                   ↑↑

So the first CPU is CPU0. Could have told you that... what about the others? :)

If anyone can reproduce this with a serial port, can you try this?

From 98ad11d0fb88f081f49f7b1496420dbfbeff8833 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@...zon.co.uk>
Date: Sat, 4 Feb 2023 15:20:24 +0000
Subject: [PATCH] parallel debug

---
 arch/x86/kernel/head_64.S | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0e4e53d231db..da7f4d2d9951 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -281,6 +281,15 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 
 .Lsetup_AP:
 	/* EDX contains the APIC ID of the current CPU */
+#if 1
+	/* Test hack: Print APIC ID and then CPU# when we find it. */
+	mov	%edx, %ecx
+	mov	%edx, %eax
+	addb	$'A', %al
+	mov	$0x3f8, %dx
+	outb    %al, %dx
+	mov	%ecx, %edx
+#endif
 	xorq	%rcx, %rcx
 	leaq	cpuid_to_apicid(%rip), %rbx
 
@@ -302,6 +311,14 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 
 .Linit_cpu_data:
 	/* Get the per cpu offset for the given CPU# which is in ECX */
+#if 1
+	mov	%rcx, %rax
+	shr	$3, %rax
+	addb	$'a', %al
+
+	mov	$0x3f8, %dx
+	outb    %al, %dx
+#endif
 	leaq	__per_cpu_offset(%rip), %rbx
 	movq	(%rbx,%rcx,8), %rbx
 	/* Save it for GS BASE setup */
-- 
2.39.0



Download attachment "smime.p7s" of type "application/pkcs7-signature" (5965 bytes)