From: David Woodhouse <dwmw2@infradead.org>
To: Tom Lendacky <thomas.lendacky@amd.com>,
Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"H . Peter Anvin" <hpa@zytor.com>,
Paolo Bonzini <pbonzini@redhat.com>,
"Paul E . McKenney" <paulmck@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"rcu@vger.kernel.org" <rcu@vger.kernel.org>,
"mimoja@mimoja.de" <mimoja@mimoja.de>,
"hewenliang4@huawei.com" <hewenliang4@huawei.com>,
"hushiyuan@huawei.com" <hushiyuan@huawei.com>,
"luolongjun@huawei.com" <luolongjun@huawei.com>,
"hejingxian@huawei.com" <hejingxian@huawei.com>,
Joerg Roedel <joro@8bytes.org>
Subject: Re: [PATCH v3 6/9] x86/smpboot: Support parallel startup of secondary CPUs
Date: Thu, 16 Dec 2021 19:20:55 +0000 [thread overview]
Message-ID: <e742473935bf81be84adea6fa8061ce0846cc630.camel@infradead.org> (raw)
In-Reply-To: <3d8e2d0d-1830-48fb-bc2d-995099f39ef0@amd.com>
[-- Attachment #1: Type: text/plain, Size: 3866 bytes --]
On Thu, 2021-12-16 at 13:00 -0600, Tom Lendacky wrote:
> On 12/16/21 12:24 PM, David Woodhouse wrote:
> > On Thu, 2021-12-16 at 08:24 -0600, Tom Lendacky wrote:
> >
> > > This will break an SEV-ES guest because CPUID will generate a #VC and a
> > > #VC handler has not been established yet.
> > >
> > > I guess for now, you can probably just not enable parallel startup for
> > > SEV-ES guests.
> >
> > OK, thanks. I'll expand it to allow 24 bits of (physical) APIC ID then,
> > since it's no longer limited to CPUs without X2APIC. Then we can
> > refrain from doing parallel bringup for SEV-ES guests, as you suggest.
> >
> > What precisely is the check I should be using for that?
>
> Calling cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT) will return true for
> an SEV-ES guest.
Thanks. Incremental patch (which I'll roll into Thomas's patch) looks a
bit like this. Testing it now...
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0b6012fd3e55..1ac33ce1d60e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -199,7 +199,6 @@ extern unsigned int smpboot_control;
#endif /* !__ASSEMBLY__ */
/* Control bits for startup_64 */
-#define STARTUP_USE_APICID 0x10000
-#define STARTUP_USE_CPUID_0B 0x20000
+#define STARTUP_PARALLEL 0x80000000
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0249212e23d2..3e4c3c416bce 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -189,11 +189,10 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
* Secondary CPUs find out the offsets via the APIC ID. For parallel
* boot the APIC ID is retrieved from CPUID, otherwise it's encoded
* in smpboot_control:
- * Bit 0-15 APICID if STARTUP_USE_CPUID_0B is not set
- * Bit 16 Secondary boot flag
- * Bit 17 Parallel boot flag
+ * Bit 0-30 APIC ID if STARTUP_PARALLEL is not set
+ * Bit 31 Parallel boot flag (use CPUID leaf 0x0b for APIC ID).
*/
- testl $STARTUP_USE_CPUID_0B, %eax
+ testl $STARTUP_PARALLEL, %eax
jz .Lsetup_AP
mov $0x0B, %eax
@@ -203,7 +202,6 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
.Lsetup_AP:
/* EAX contains the APICID of the current CPU */
- andl $0xFFFF, %eax
xorl %ecx, %ecx
leaq cpuid_to_apicid(%rip), %rbx
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 725fede281ac..acfb22ce8d4f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1125,13 +1125,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
if (IS_ENABLED(CONFIG_X86_32)) {
early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
initial_stack = idle->thread.sp;
- } else if (boot_cpu_data.cpuid_level < 0x0B) {
- /* Anything with X2APIC should have CPUID leaf 0x0B */
- if (WARN_ON_ONCE(x2apic_mode) && apicid > 0xffff)
- return -EIO;
- smpboot_control = apicid | STARTUP_USE_APICID;
+ } else if (do_parallel_bringup) {
+ smpboot_control = STARTUP_PARALLEL;
} else {
- smpboot_control = STARTUP_USE_CPUID_0B;
+ smpboot_control = apicid;
}
/* Enable the espfix hack for this CPU */
@@ -1553,9 +1550,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
/*
* We can do 64-bit AP bringup in parallel if the CPU reports its
- * APIC ID in CPUID leaf 0x0B. Otherwise it's too hard.
+ * APIC ID in CPUID leaf 0x0B. Otherwise it's too hard. And not
+ * for SEV-ES guests because they can't use CPUID that early.
*/
- if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 0x0B)
+ if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 0x0B ||
+ cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
do_parallel_bringup = false;
if (do_parallel_bringup)
[-- Attachment #2: smime.p7s --]
[-- Type: application/pkcs7-signature, Size: 5174 bytes --]
next prev parent reply other threads:[~2021-12-16 19:21 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-15 14:56 [PATCH v3 0/9] Parallel CPU bringup for x86_64 David Woodhouse
2021-12-15 14:56 ` [PATCH v3 1/9] x86/apic/x2apic: Fix parallel handling of cluster_mask David Woodhouse
2021-12-15 14:56 ` [PATCH v3 2/9] cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h> David Woodhouse
2021-12-15 14:56 ` [PATCH v3 3/9] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU David Woodhouse
2021-12-15 14:56 ` [PATCH v3 4/9] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector() David Woodhouse
2021-12-15 14:56 ` [PATCH v3 5/9] x86/smpboot: Split up native_cpu_up into separate phases and document them David Woodhouse
2021-12-15 14:56 ` [PATCH v3 6/9] x86/smpboot: Support parallel startup of secondary CPUs David Woodhouse
2021-12-16 14:24 ` Tom Lendacky
2021-12-16 18:24 ` David Woodhouse
2021-12-16 19:00 ` Tom Lendacky
2021-12-16 19:20 ` David Woodhouse [this message]
2022-01-29 12:04 ` David Woodhouse
2022-01-31 13:59 ` Borislav Petkov
2022-02-01 10:25 ` David Woodhouse
2022-02-01 10:56 ` Borislav Petkov
2022-02-01 12:39 ` David Woodhouse
2022-02-01 12:56 ` Borislav Petkov
2022-02-01 13:02 ` David Woodhouse
2021-12-15 14:56 ` [PATCH v3 7/9] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel David Woodhouse
2021-12-15 14:56 ` [PATCH v3 8/9] x86/mtrr: Avoid repeated save of MTRRs on boot-time CPU bringup David Woodhouse
2021-12-15 14:56 ` [PATCH v3 9/9] x86/smpboot: Serialize topology updates for secondary bringup David Woodhouse
2021-12-16 16:27 ` [PATCH v3 0/9] Parallel CPU bringup for x86_64 Tom Lendacky
2021-12-16 19:24 ` David Woodhouse
2021-12-16 22:52 ` Tom Lendacky
2021-12-17 0:13 ` David Woodhouse
2021-12-17 10:09 ` Igor Mammedov
2021-12-17 15:40 ` David Woodhouse
2021-12-20 17:10 ` David Woodhouse
2021-12-20 18:54 ` Tom Lendacky
2021-12-20 21:29 ` David Woodhouse
2021-12-20 21:47 ` Tom Lendacky
2021-12-21 22:25 ` Tom Lendacky
2021-12-21 22:33 ` David Woodhouse
2021-12-17 17:48 ` Tom Lendacky
2021-12-17 19:11 ` David Woodhouse
2021-12-17 19:26 ` David Woodhouse
2021-12-17 20:15 ` Tom Lendacky
2021-12-17 19:46 ` Tom Lendacky
2021-12-17 20:13 ` David Woodhouse
2021-12-17 20:55 ` Tom Lendacky
2021-12-17 22:48 ` David Woodhouse
2022-01-28 9:54 ` David Woodhouse
2022-01-28 21:40 ` Sean Christopherson
2022-01-28 21:48 ` David Woodhouse
2022-01-29 9:22 ` David Woodhouse
2021-12-16 19:52 ` David Woodhouse
2021-12-16 19:55 ` Tom Lendacky
2021-12-16 19:59 ` David Woodhouse
2021-12-27 16:57 ` Paul Menzel
2021-12-28 11:34 ` Paul Menzel
2021-12-28 14:18 ` David Woodhouse
2021-12-29 13:18 ` Paul Menzel
2021-12-29 13:54 ` David Woodhouse
2022-02-14 13:45 ` Paul Menzel
2022-04-21 10:00 ` Mimoja
2022-04-22 21:19 ` Tom Lendacky
2022-06-01 8:30 ` David Woodhouse
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=e742473935bf81be84adea6fa8061ce0846cc630.camel@infradead.org \
--to=dwmw2@infradead.org \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=hejingxian@huawei.com \
--cc=hewenliang4@huawei.com \
--cc=hpa@zytor.com \
--cc=hushiyuan@huawei.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luolongjun@huawei.com \
--cc=mimoja@mimoja.de \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=pbonzini@redhat.com \
--cc=rcu@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=x86@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).