Merge tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP updates from Thomas Gleixner:
 "A large update for SMP management:

   - Parallel CPU bringup

     The reason why people are interested in parallel bringup is to
     shorten the (kexec) reboot time of cloud servers to reduce the
     downtime of the VM tenants.

     The current fully serialized bringup does the following per AP:

       1) Prepare callbacks (allocate, intialize, create threads)
       2) Kick the AP alive (e.g. INIT/SIPI on x86)
       3) Wait for the AP to report alive state
       4) Let the AP continue through the atomic bringup
       5) Let the AP run the threaded bringup to full online state

     There are two significant delays:

       #3 The time for an AP to report alive state in start_secondary()
          on x86 has been measured in the range between 350us and 3.5ms
          depending on vendor and CPU type, BIOS microcode size etc.

       #4 The atomic bringup does the microcode update. This has been
          measured to take up to ~8ms on the primary threads depending
          on the microcode patch size to apply.

     On a two socket SKL server with 56 cores (112 threads) the boot CPU
     spends on current mainline about 800ms busy waiting for the APs to
     come up and apply microcode. That's more than 80% of the actual
     onlining procedure.

     This can be reduced significantly by splitting the bringup
     mechanism into two parts:

       1) Run the prepare callbacks and kick the AP alive for each AP
          which needs to be brought up.

          The APs wake up, do their firmware initialization and run the
          low level kernel startup code including microcode loading in
          parallel up to the first synchronization point. (#1 and #2
          above)

       2) Run the rest of the bringup code strictly serialized per CPU
          (#3 - #5 above) as it's done today.

          Parallelizing that stage of the CPU bringup might be possible
          in theory, but it's questionable whether required surgery
          would be justified for a pretty small gain.

     If the system is large enough the first AP is already waiting at
     the first synchronization point when the boot CPU finished the
     wake-up of the last AP. That reduces the AP bringup time on that
     SKL from ~800ms to ~80ms, i.e. by a factor ~10x.

     The actual gain varies wildly depending on the system, CPU,
     microcode patch size and other factors. There are some
     opportunities to reduce the overhead further, but that needs some
     deep surgery in the x86 CPU bringup code.

     For now this is only enabled on x86, but the core functionality
     obviously works for all SMP capable architectures.

   - Enhancements for SMP function call tracing so it is possible to
     locate the scheduling and the actual execution points. That allows
     to measure IPI delivery time precisely"

* tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  trace,smp: Add tracepoints for scheduling remotelly called functions
  trace,smp: Add tracepoints around remotelly called functions
  MAINTAINERS: Add CPU HOTPLUG entry
  x86/smpboot: Fix the parallel bringup decision
  x86/realmode: Make stack lock work in trampoline_compat()
  x86/smp: Initialize cpu_primary_thread_mask late
  cpu/hotplug: Fix off by one in cpuhp_bringup_mask()
  x86/apic: Fix use of X{,2}APIC_ENABLE in asm with older binutils
  x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it
  x86/smpboot: Support parallel startup of secondary CPUs
  x86/smpboot: Implement a bit spinlock to protect the realmode stack
  x86/apic: Save the APIC virtual base address
  cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE
  x86/apic: Provide cpu_primary_thread mask
  x86/smpboot: Enable split CPU startup
  cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism
  cpu/hotplug: Reset task stack state in _cpu_up()
  cpu/hotplug: Remove unused state functions
  riscv: Switch to hotplug core state synchronization
  parisc: Switch to hotplug core state synchronization
  ...

1 files changed, 79 insertions, 6 deletions

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 113c13376e51..c5b9289837dc 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -24,7 +24,9 @@
 #include "../entry/calling.h"
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#include <asm/apicdef.h>
 #include <asm/fixmap.h>
+#include <asm/smp.h>
 
 /*
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
@@ -234,8 +236,67 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR // above
 
 #ifdef CONFIG_SMP
+	/*
+	 * For parallel boot, the APIC ID is read from the APIC, and then
+	 * used to look up the CPU number.  For booting a single CPU, the
+	 * CPU number is encoded in smpboot_control.
+	 *
+	 * Bit 31	STARTUP_READ_APICID (Read APICID from APIC)
+	 * Bit 0-23	CPU# if STARTUP_xx flags are not set
+	 */
 	movl	smpboot_control(%rip), %ecx
+	testl	$STARTUP_READ_APICID, %ecx
+	jnz	.Lread_apicid
+	/*
+	 * No control bit set, single CPU bringup. CPU number is provided
+	 * in bit 0-23. This is also the boot CPU case (CPU number 0).
+	 */
+	andl	$(~STARTUP_PARALLEL_MASK), %ecx
+	jmp	.Lsetup_cpu
 
+.Lread_apicid:
+	/* Check whether X2APIC mode is already enabled */
+	mov	$MSR_IA32_APICBASE, %ecx
+	rdmsr
+	testl	$X2APIC_ENABLE, %eax
+	jnz	.Lread_apicid_msr
+
+	/* Read the APIC ID from the fix-mapped MMIO space. */
+	movq	apic_mmio_base(%rip), %rcx
+	addq	$APIC_ID, %rcx
+	movl	(%rcx), %eax
+	shr	$24, %eax
+	jmp	.Llookup_AP
+
+.Lread_apicid_msr:
+	mov	$APIC_X2APIC_ID_MSR, %ecx
+	rdmsr
+
+.Llookup_AP:
+	/* EAX contains the APIC ID of the current CPU */
+	xorq	%rcx, %rcx
+	leaq	cpuid_to_apicid(%rip), %rbx
+
+.Lfind_cpunr:
+	cmpl	(%rbx,%rcx,4), %eax
+	jz	.Lsetup_cpu
+	inc	%ecx
+#ifdef CONFIG_FORCE_NR_CPUS
+	cmpl	$NR_CPUS, %ecx
+#else
+	cmpl	nr_cpu_ids(%rip), %ecx
+#endif
+	jb	.Lfind_cpunr
+
+	/*  APIC ID not found in the table. Drop the trampoline lock and bail. */
+	movq	trampoline_lock(%rip), %rax
+	movl	$0, (%rax)
+
+1:	cli
+	hlt
+	jmp	1b
+
+.Lsetup_cpu:
 	/* Get the per cpu offset for the given CPU# which is in ECX */
 	movq	__per_cpu_offset(,%rcx,8), %rdx
 #else
@@ -252,6 +313,16 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	movq	TASK_threadsp(%rax), %rsp
 
 	/*
+	 * Now that this CPU is running on its own stack, drop the realmode
+	 * protection. For the boot CPU the pointer is NULL!
+	 */
+	movq	trampoline_lock(%rip), %rax
+	testq	%rax, %rax
+	jz	.Lsetup_gdt
+	movl	$0, (%rax)
+
+.Lsetup_gdt:
+	/*
 	 * 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
 	 * addresses where we're currently running on. We have to do that here
@@ -375,13 +446,13 @@ SYM_CODE_END(secondary_startup_64)
 #include "verify_cpu.S"
 #include "sev_verify_cbit.S"
 
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_AMD_MEM_ENCRYPT)
 /*
- * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
- * up already except stack. We just set up stack here. Then call
- * start_secondary() via .Ljump_to_C_code.
+ * Entry point for soft restart of a CPU. Invoked from xxx_play_dead() for
+ * restarting the boot CPU or for restarting SEV guest CPUs after CPU hot
+ * unplug. Everything is set up already except the stack.
  */
-SYM_CODE_START(start_cpu0)
+SYM_CODE_START(soft_restart_cpu)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_END_OF_STACK
 
@@ -390,7 +461,7 @@ SYM_CODE_START(start_cpu0)
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
-SYM_CODE_END(start_cpu0)
+SYM_CODE_END(soft_restart_cpu)
 #endif
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -433,6 +504,8 @@ SYM_DATA(initial_code,	.quad x86_64_start_kernel)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 SYM_DATA(initial_vc_handler,	.quad handle_vc_boot_ghcb)
 #endif
+
+SYM_DATA(trampoline_lock, .quad 0);
 	__FINITDATA
 
 	__INIT