Re: [PATCH v3 6/9] x86/smpboot: Support parallel startup of secondary CPUs

From: Tom Lendacky
Date: Thu Dec 16 2021 - 09:25:02 EST

On 12/15/21 8:56 AM, David Woodhouse wrote:
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

...
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8b3ebd2bb85..0249212e23d2 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -25,6 +25,7 @@
#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/fixmap.h>
+#include <asm/smp.h>
/*
* We are not able to switch in one step to the final KERNEL ADDRESS SPACE
@@ -176,6 +177,64 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
1:
UNWIND_HINT_EMPTY
+ /*
+ * Is this the boot CPU coming up? If so everything is available
+ * in initial_gs, initial_stack and early_gdt_descr.
+ */
+ movl smpboot_control(%rip), %eax
+ testl %eax, %eax
+ jz .Lsetup_cpu
+
+ /*
+ * 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
+ */
+ testl $STARTUP_USE_CPUID_0B, %eax
+ jz .Lsetup_AP
+
+ mov $0x0B, %eax
+ xorl %ecx, %ecx
+ cpuid

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.

Thanks,
Tom


+ mov %edx, %eax
+
+.Lsetup_AP:
+ /* EAX contains the APICID of the current CPU */
+ andl $0xFFFF, %eax
+ xorl %ecx, %ecx
+ leaq cpuid_to_apicid(%rip), %rbx
+
+.Lfind_cpunr:
+ cmpl (%rbx), %eax
+ jz .Linit_cpu_data
+ addq $4, %rbx
+ addq $8, %rcx
+ jmp .Lfind_cpunr
+
+.Linit_cpu_data:
+ /* Get the per cpu offset */
+ leaq __per_cpu_offset(%rip), %rbx
+ addq %rcx, %rbx
+ movq (%rbx), %rbx
+ /* Save it for GS BASE setup */
+ movq %rbx, initial_gs(%rip)
+
+ /* Calculate the GDT address */
+ movq $gdt_page, %rcx
+ addq %rbx, %rcx
+ movq %rcx, early_gdt_descr_base(%rip)
+
+ /* Find the idle task stack */
+ movq $idle_threads, %rcx
+ addq %rbx, %rcx
+ movq (%rcx), %rcx
+ movq TASK_threadsp(%rcx), %rcx
+ movq %rcx, initial_stack(%rip)
+
+.Lsetup_cpu:
/*
* We must switch to a new descriptor in kernel space for the GDT
* because soon the kernel won't have access anymore to the userspace
@@ -216,6 +275,14 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
*/
movq initial_stack(%rip), %rsp
+ /* Drop the realmode protection. For the boot CPU the pointer is NULL! */
+ movq trampoline_lock(%rip), %rax
+ testq %rax, %rax
+ jz .Lsetup_idt
+ lock
+ btrl $0, (%rax)
+
+.Lsetup_idt:
/* Setup and Load IDT */
pushq %rsi
call early_setup_idt
@@ -347,6 +414,7 @@ SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb)
* reliably detect the end of the stack.
*/
SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - FRAME_SIZE)
+SYM_DATA(trampoline_lock, .quad 0);
__FINITDATA
__INIT
@@ -572,6 +640,9 @@ SYM_DATA_END(level1_fixmap_pgt)
SYM_DATA(early_gdt_descr, .word GDT_ENTRIES*8-1)
SYM_DATA_LOCAL(early_gdt_descr_base, .quad INIT_PER_CPU_VAR(gdt_page))
+ .align 16
+SYM_DATA(smpboot_control, .long 0)
+
.align 16
/* This must match the first entry in level2_kernel_pgt */
SYM_DATA(phys_base, .quad 0x0)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7a763b84b6e5..1e38d44c3603 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1104,9 +1104,19 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
unsigned long boot_error = 0;
idle->thread.sp = (unsigned long)task_pt_regs(idle);
- early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
initial_code = (unsigned long)start_secondary;
- initial_stack = idle->thread.sp;
+
+ 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 {
+ smpboot_control = STARTUP_USE_CPUID_0B;
+ }
/* Enable the espfix hack for this CPU */
init_espfix_ap(cpu);
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 4a3da7592b99..7dc2e817bd02 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -127,6 +127,9 @@ static void __init setup_real_mode(void)
trampoline_header->flags = 0;
+ trampoline_lock = &trampoline_header->lock;
+ *trampoline_lock = 0;
+
trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
trampoline_pgd[0] = trampoline_pgd_entry.pgd;
trampoline_pgd[511] = init_top_pgt[511].pgd;
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index cc8391f86cdb..12a540904e80 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -49,6 +49,19 @@ SYM_CODE_START(trampoline_start)
mov %ax, %es
mov %ax, %ss
+ /*
+ * Make sure only one CPU fiddles with the realmode stack
+ */
+.Llock_rm:
+ btl $0, tr_lock
+ jnc 2f
+ pause
+ jmp .Llock_rm
+2:
+ lock
+ btsl $0, tr_lock
+ jc .Llock_rm
+
# Setup stack
movl $rm_stack_end, %esp
@@ -192,6 +205,7 @@ SYM_DATA_START(trampoline_header)
SYM_DATA(tr_efer, .space 8)
SYM_DATA(tr_cr4, .space 4)
SYM_DATA(tr_flags, .space 4)
+ SYM_DATA(tr_lock, .space 4)
SYM_DATA_END(trampoline_header)
#include "trampoline_common.S"
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f6bc0bc8a2aa..934e64ff4eed 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -25,7 +25,7 @@
* For the hotplug case we keep the task structs around and reuse
* them.
*/
-static DEFINE_PER_CPU(struct task_struct *, idle_threads);
+DEFINE_PER_CPU(struct task_struct *, idle_threads);
struct task_struct *idle_thread_get(unsigned int cpu)
{