[PATCH v14 09/12] x86/smpboot: Support parallel startup of secondary CPUs
From: Usama Arif
Date: Wed Mar 08 2023 - 12:14:39 EST
From: David Woodhouse <dwmw@xxxxxxxxxxxx>
Rework the real-mode startup code to allow for APs to be brought up in
parallel. This is in two parts:
1. Introduce a bit-spinlock to prevent them from all using the real
mode stack at the same time.
2. Avoid needing to use the global smpboot_control variable to pass
each AP its CPU#.
To achieve the latter, export the cpuid_to_apicid[] array so that each
AP can find its own CPU# by searching therein based on its APIC ID.
Introduce flags in the top bits of smpboot_control which indicate methods
by which an AP should find its CPU#. For a serialized bringup, the CPU#
is explicitly passed in the low bits of smpboot_control as before. For
parallel mode there are flags directing the AP to find its APIC ID in
CPUID leaf 0x0b (for X2APIC mode) or CPUID leaf 0x01 where 8 bits are
sufficient, then perform the cpuid_to_apicid[] lookup with that.
Parallel startup may be disabled by a command line option, and also if:
• AMD SEV-ES is in use, since the AP may not use CPUID that early.
• X2APIC is enabled, but CPUID leaf 0xb is not present and correct.
• X2APIC is not enabled but not even CPUID leaf 0x01 exists.
Aside from the fact that APs will now look up their CPU# via the
newly-exported cpuid_to_apicid[] table, there is no behavioural change
intended yet, since new parallel CPUHP states have not — yet — been
added.
[ tglx: Initial proof of concept patch with bitlock and APIC ID lookup ]
[ dwmw2: Rework and testing, commit message, CPUID 0x1 and CPU0 support ]
[ seanc: Fix stray override of initial_gs in common_cpu_up() ]
[ Oleksandr Natalenko: reported suspend/resume issue fixed in
x86_acpi_suspend_lowlevel ]
Co-developed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Co-developed-by: Brian Gerst <brgerst@xxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Brian Gerst <brgerst@xxxxxxxxx>
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Usama Arif <usama.arif@xxxxxxxxxxxxx>
Tested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Tested-by: Kim Phillips <kim.phillips@xxxxxxx>
Tested-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx>
Tested-by: Guilherme G. Piccoli <gpiccoli@xxxxxxxxxx>
---
.../admin-guide/kernel-parameters.txt | 3 +
arch/x86/include/asm/cpu.h | 1 +
arch/x86/include/asm/realmode.h | 3 +
arch/x86/include/asm/smp.h | 6 ++
arch/x86/kernel/acpi/sleep.c | 9 ++-
arch/x86/kernel/apic/apic.c | 2 +-
arch/x86/kernel/cpu/topology.c | 2 +-
arch/x86/kernel/head_64.S | 64 +++++++++++++++++++
arch/x86/kernel/smpboot.c | 50 ++++++++++++++-
arch/x86/realmode/init.c | 3 +
arch/x86/realmode/rm/trampoline_64.S | 27 ++++++--
11 files changed, 161 insertions(+), 9 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6cfa6e3996cf..7bb7020f97e2 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3819,6 +3819,9 @@
nomodule Disable module load
+ no_parallel_bringup
+ [X86,SMP] Disable parallel bring-up of secondary cores.
+
nopat [X86] Disable PAT (page attribute table extension of
pagetables) support.
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 78796b98a544..ef8ba318dca1 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -97,5 +97,6 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1,
extern u64 x86_read_arch_cap_msr(void);
int intel_find_matching_signature(void *mc, unsigned int csig, int cpf);
int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type);
+int check_extended_topology_leaf(int leaf);
#endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index f6a1737c77be..87e5482acd0d 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -52,6 +52,7 @@ struct trampoline_header {
u64 efer;
u32 cr4;
u32 flags;
+ u32 lock;
#endif
};
@@ -64,6 +65,8 @@ extern unsigned long initial_stack;
extern unsigned long initial_vc_handler;
#endif
+extern u32 *trampoline_lock;
+
extern unsigned char real_mode_blob[];
extern unsigned char real_mode_relocs[];
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index bf2c51df9e0b..1cf4f1e57570 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -203,4 +203,10 @@ extern unsigned int smpboot_control;
#endif /* !__ASSEMBLY__ */
+/* Control bits for startup_64 */
+#define STARTUP_APICID_CPUID_0B 0x80000000
+#define STARTUP_APICID_CPUID_01 0x40000000
+
+#define STARTUP_PARALLEL_MASK (STARTUP_APICID_CPUID_01 | STARTUP_APICID_CPUID_0B)
+
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 1328c221af30..6dfecb27b846 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
#include <asm/cacheflush.h>
#include <asm/realmode.h>
#include <asm/hypervisor.h>
+#include <asm/smp.h>
#include <linux/ftrace.h>
#include "../../realmode/rm/wakeup.h"
@@ -127,7 +128,13 @@ int x86_acpi_suspend_lowlevel(void)
* value is in the actual %rsp register.
*/
current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
- smpboot_control = smp_processor_id();
+ /*
+ * Ensure the CPU knows which one it is when it comes back, if
+ * it isn't in parallel mode and expected to work that out for
+ * itself.
+ */
+ if (!(smpboot_control & STARTUP_PARALLEL_MASK))
+ smpboot_control = smp_processor_id();
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0L;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 20d9a604da7c..ac1d7e5da1f2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2377,7 +2377,7 @@ static int nr_logical_cpuids = 1;
/*
* Used to store mapping between logical CPU IDs and APIC IDs.
*/
-static int cpuid_to_apicid[] = {
+int cpuid_to_apicid[] = {
[0 ... NR_CPUS - 1] = -1,
};
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 5e868b62a7c4..1dc20f4dfa6e 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -32,7 +32,7 @@ EXPORT_SYMBOL(__max_die_per_package);
/*
* Check if given CPUID extended topology "leaf" is implemented
*/
-static int check_extended_topology_leaf(int leaf)
+int check_extended_topology_leaf(int leaf)
{
unsigned int eax, ebx, ecx, edx;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 6a8238702eab..c35f7c173832 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
@@ -234,8 +235,61 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
ANNOTATE_NOENDBR // above
#ifdef CONFIG_SMP
+ /*
+ * For parallel boot, the APIC ID is retrieved from CPUID, 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_APICID_CPUID_0B flag (use CPUID 0x0b)
+ * Bit 30 STARTUP_APICID_CPUID_01 flag (use CPUID 0x01)
+ * Bit 0-24 CPU# if STARTUP_APICID_CPUID_xx flags are not set
+ */
movl smpboot_control(%rip), %ecx
+ testl $STARTUP_APICID_CPUID_0B, %ecx
+ jnz .Luse_cpuid_0b
+ testl $STARTUP_APICID_CPUID_01, %ecx
+ jnz .Luse_cpuid_01
+ andl $0x0FFFFFFF, %ecx
+ jmp .Lsetup_cpu
+
+.Luse_cpuid_01:
+ mov $0x01, %eax
+ cpuid
+ mov %ebx, %edx
+ shr $24, %edx
+ jmp .Lsetup_AP
+.Luse_cpuid_0b:
+ mov $0x0B, %eax
+ xorl %ecx, %ecx
+ cpuid
+
+.Lsetup_AP:
+ /* EDX contains the APIC ID of the current CPU */
+ xorq %rcx, %rcx
+ leaq cpuid_to_apicid(%rip), %rbx
+
+.Lfind_cpunr:
+ cmpl (%rbx,%rcx,4), %edx
+ 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
+ lock
+ btrl $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
@@ -293,6 +347,14 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
shrq $32, %rdx
wrmsr
+ /* 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
@@ -435,6 +497,8 @@ 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
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b04520085582..fd4e678b6588 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -797,6 +797,16 @@ static int __init cpu_init_udelay(char *str)
}
early_param("cpu_init_udelay", cpu_init_udelay);
+static bool do_parallel_bringup __ro_after_init = true;
+
+static int __init no_parallel_bringup(char *str)
+{
+ do_parallel_bringup = false;
+
+ return 0;
+}
+early_param("no_parallel_bringup", no_parallel_bringup);
+
static void __init smp_quirk_init_udelay(void)
{
/* if cmdline changed it from default, leave it alone */
@@ -1113,7 +1123,7 @@ 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 {
+ } else if (!do_parallel_bringup) {
smpboot_control = cpu;
}
@@ -1475,6 +1485,41 @@ void __init smp_prepare_cpus_common(void)
set_cpu_sibling_map(0);
}
+/*
+ * We can do 64-bit AP bringup in parallel if the CPU reports its APIC
+ * ID in CPUID (either leaf 0x0B if we need the full APIC ID in X2APIC
+ * mode, or leaf 0x01 if 8 bits are sufficient). Otherwise it's too
+ * hard. And not for SEV-ES guests because they can't use CPUID that
+ * early.
+ */
+static bool prepare_parallel_bringup(void)
+{
+ if (IS_ENABLED(CONFIG_X86_32) || cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+ return false;
+
+ if (x2apic_mode) {
+ if (boot_cpu_data.cpuid_level < 0x0b)
+ return false;
+
+ if (check_extended_topology_leaf(0x0b) != 0) {
+ pr_info("Disabling parallel bringup because CPUID 0xb looks untrustworthy\n");
+ return false;
+ }
+
+ pr_debug("Using CPUID 0xb for parallel CPU startup\n");
+ smpboot_control = STARTUP_APICID_CPUID_0B;
+ } else {
+ /* Without X2APIC, what's in CPUID 0x01 should suffice. */
+ if (boot_cpu_data.cpuid_level < 0x01)
+ return false;
+
+ pr_debug("Using CPUID 0x1 for parallel CPU startup\n");
+ smpboot_control = STARTUP_APICID_CPUID_01;
+ }
+
+ return true;
+}
+
/*
* Prepare for SMP bootup.
* @max_cpus: configured maximum number of CPUs, It is a legacy parameter
@@ -1515,6 +1560,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
speculative_store_bypass_ht_init();
+ if (do_parallel_bringup)
+ do_parallel_bringup = prepare_parallel_bringup();
+
snp_set_wakeup_secondary_cpu();
}
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index af565816d2ba..788e5559549f 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -154,6 +154,9 @@ 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);
/* Map the real mode stub as virtual == physical */
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index e38d61d6562e..2dfb1c400167 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -37,6 +37,24 @@
.text
.code16
+.macro LOAD_REALMODE_ESP
+ /*
+ * 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
+.endm
+
.balign PAGE_SIZE
SYM_CODE_START(trampoline_start)
cli # We should be safe anyway
@@ -49,8 +67,7 @@ SYM_CODE_START(trampoline_start)
mov %ax, %es
mov %ax, %ss
- # Setup stack
- movl $rm_stack_end, %esp
+ LOAD_REALMODE_ESP
call verify_cpu # Verify the cpu supports long mode
testl %eax, %eax # Check for return code
@@ -93,8 +110,7 @@ SYM_CODE_START(sev_es_trampoline_start)
mov %ax, %es
mov %ax, %ss
- # Setup stack
- movl $rm_stack_end, %esp
+ LOAD_REALMODE_ESP
jmp .Lswitch_to_protected
SYM_CODE_END(sev_es_trampoline_start)
@@ -177,7 +193,7 @@ SYM_CODE_START(pa_trampoline_compat)
* In compatibility mode. Prep ESP and DX for startup_32, then disable
* paging and complete the switch to legacy 32-bit mode.
*/
- movl $rm_stack_end, %esp
+ LOAD_REALMODE_ESP
movw $__KERNEL_DS, %dx
movl $(CR0_STATE & ~X86_CR0_PG), %eax
@@ -241,6 +257,7 @@ 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"
--
2.25.1