2023-02-21 22:36:17

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 0/8] Parallel CPU bringup for x86_64

This version fixes suspend/resume not working with parallel smpboot in v9
(reported by Oleksandr Natalenko) by saving smpboot_control properly in
x86_acpi_suspend_lowlevel.

The patches have also been rebased to v6.2 and retested and the improvement
in boot time is the same as v9.

Thanks,
Usama

Changes across versions:
v2: Cut it back to just INIT/SIPI/SIPI in parallel for now, nothing more
v3: Clean up x2apic patch, add MTRR optimisation, lock topology update
in preparation for more parallelisation.
v4: Fixes to the real mode parallelisation patch spotted by SeanC, to
avoid scribbling on initial_gs in common_cpu_up(), and to allow all
24 bits of the physical X2APIC ID to be used. That patch still needs
a Signed-off-by from its original author, who once claimed not to
remember writing it at all. But now we've fixed it, hopefully he'll
admit it now :)
v5: rebase to v6.1 and remeasure performance, disable parallel bringup
for AMD CPUs.
v6: rebase to v6.2-rc6, disabled parallel boot on amd as a cpu bug and
reused timer calibration for secondary CPUs.
v7: [David Woodhouse] iterate over all possible CPUs to find any existing
cluster mask in alloc_clustermask. (patch 1/9)
Keep parallel AMD support enabled in AMD, using APIC ID in CPUID leaf
0x0B (for x2APIC mode) or CPUID leaf 0x01 where 8 bits are sufficient.
Included sanity checks for APIC id from 0x0B. (patch 6/9)
Removed patch for reusing timer calibration for secondary CPUs.
commit message and code improvements.
v8: Fix CPU0 hotplug by setting up the initial_gs, initial_stack and
early_gdt_descr.
Drop trampoline lock and bail if APIC ID not found in find_cpunr.
Code comments improved and debug prints added.
v9: Drop patch to avoid repeated saves of MTRR at boot time.
rebased and retested at v6.2-rc8.
added kernel doc for no_parallel_bringup and made do_parallel_bringup
__ro_after_init.
v10: Fixed suspend/resume not working with parallel smpboot.
rebased and retested to 6.2.
fixed checkpatch errors.


David Woodhouse (8):
x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel
cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h>
cpu/hotplug: Add dynamic parallel bringup states before
CPUHP_BRINGUP_CPU
x86/smpboot: Reference count on smpboot_setup_warm_reset_vector()
x86/smpboot: Split up native_cpu_up into separate phases and document
them
x86/smpboot: Support parallel startup of secondary CPUs
x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel
x86/smpboot: Serialize topology updates for secondary bringup

.../admin-guide/kernel-parameters.txt | 3 +
arch/x86/include/asm/realmode.h | 3 +
arch/x86/include/asm/smp.h | 14 +-
arch/x86/include/asm/topology.h | 2 -
arch/x86/kernel/acpi/sleep.c | 7 +
arch/x86/kernel/apic/apic.c | 2 +-
arch/x86/kernel/apic/x2apic_cluster.c | 126 ++++---
arch/x86/kernel/cpu/common.c | 6 +-
arch/x86/kernel/head_64.S | 99 ++++-
arch/x86/kernel/smpboot.c | 350 +++++++++++++-----
arch/x86/realmode/init.c | 3 +
arch/x86/realmode/rm/trampoline_64.S | 14 +
arch/x86/xen/smp_pv.c | 4 +-
include/linux/cpuhotplug.h | 2 +
include/linux/smpboot.h | 7 +
kernel/cpu.c | 31 +-
kernel/smpboot.c | 2 +-
kernel/smpboot.h | 2 -
18 files changed, 519 insertions(+), 158 deletions(-)

--
2.25.1



2023-02-21 22:36:21

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 7/8] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel

From: David Woodhouse <[email protected]>

When the APs can find their own APIC ID without assistance, perform the
AP bringup in parallel.

Register a CPUHP_BP_PARALLEL_DYN stage "x86/cpu:kick" which just calls
do_boot_cpu() to deliver INIT/SIPI/SIPI to each AP in turn before the
normal native_cpu_up() does the rest of the hand-holding.

The APs will then take turns through the real mode code (which has its
own bitlock for exclusion) until they make it to their own stack, then
proceed through the first few lines of start_secondary() and execute
these parts in parallel:

start_secondary()
-> cr4_init()
-> (some 32-bit only stuff so not in the parallel cases)
-> cpu_init_secondary()
-> cpu_init_exception_handling()
-> cpu_init()
-> wait_for_master_cpu()

At this point they wait for the BSP to set their bit in cpu_callout_mask
(from do_wait_cpu_initialized()), and release them to continue through
the rest of cpu_init() and beyond.

This reduces the time taken for bringup on my 28-thread Haswell system
from about 120ms to 80ms. On a socket 96-thread Skylake it takes the
bringup time from 500ms to 100ms.

There is more speedup to be had by doing the remaining parts in parallel
too — especially notify_cpu_starting() in which the AP takes itself
through all the stages from CPUHP_BRINGUP_CPU to CPUHP_ONLINE. But those
require careful auditing to ensure they are reentrant, before we can go
that far.

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
arch/x86/kernel/smpboot.c | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6924d91b69ca..a8f52e03d55d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -57,6 +57,7 @@
#include <linux/pgtable.h>
#include <linux/overflow.h>
#include <linux/stackprotector.h>
+#include <linux/smpboot.h>

#include <asm/acpi.h>
#include <asm/cacheinfo.h>
@@ -1325,9 +1326,12 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int ret;

- ret = do_cpu_up(cpu, tidle);
- if (ret)
- return ret;
+ /* If parallel AP bringup isn't enabled, perform the first steps now. */
+ if (!do_parallel_bringup) {
+ ret = do_cpu_up(cpu, tidle);
+ if (ret)
+ return ret;
+ }

ret = do_wait_cpu_initialized(cpu);
if (ret)
@@ -1349,6 +1353,12 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
return ret;
}

+/* Bringup step one: Send INIT/SIPI to the target AP */
+static int native_cpu_kick(unsigned int cpu)
+{
+ return do_cpu_up(cpu, idle_thread_get(cpu));
+}
+
/**
* arch_disable_smp_support() - disables SMP support for x86 at runtime
*/
@@ -1566,6 +1576,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_01;
}

+ if (do_parallel_bringup) {
+ cpuhp_setup_state_nocalls(CPUHP_BP_PARALLEL_DYN, "x86/cpu:kick",
+ native_cpu_kick, NULL);
+ }
+
snp_set_wakeup_secondary_cpu();
}

--
2.25.1


2023-02-21 22:36:24

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 8/8] x86/smpboot: Serialize topology updates for secondary bringup

From: David Woodhouse <[email protected]>

The toplogy update is performed by the AP via smp_callin() after the BSP
has called do_wait_cpu_initialized(), setting the AP's bit in
cpu_callout_mask to allow it to proceed.

In preparation to enable further parallelism of AP bringup, add locking to
serialize the update even if multiple APs are (in future) permitted to
proceed through the next stages of bringup in parallel.

Without such ordering (and with that future extra parallelism), confusion
ensues:

[ 1.360149] x86: Booting SMP configuration:
[ 1.360221] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7 #8 #9 #10 #11 #12 #13 #14 #15 #16 #17 #18 #19 #20 #21 #22 #23
[ 1.366225] .... node #1, CPUs: #24 #25 #26 #27 #28 #29 #30 #31 #32 #33 #34 #35 #36 #37 #38 #39 #40 #41 #42 #43 #44 #45 #46 #47
[ 1.370219] .... node #0, CPUs: #48 #49 #50 #51 #52 #53 #54 #55 #56 #57 #58 #59 #60 #61 #62 #63 #64 #65 #66 #67 #68 #69 #70 #71
[ 1.378226] .... node #1, CPUs: #72 #73 #74 #75 #76 #77 #78 #79 #80 #81 #82 #83 #84 #85 #86 #87 #88 #89 #90 #91 #92 #93 #94 #95
[ 1.382037] Brought 96 CPUs to x86/cpu:kick in 72232606 cycles
[ 0.104104] smpboot: CPU 26 Converting physical 0 to logical die 1
[ 0.104104] smpboot: CPU 27 Converting physical 1 to logical package 2
[ 0.104104] smpboot: CPU 24 Converting physical 1 to logical package 3
[ 0.104104] smpboot: CPU 27 Converting physical 0 to logical die 2
[ 0.104104] smpboot: CPU 25 Converting physical 1 to logical package 4
[ 1.385609] Brought 96 CPUs to x86/cpu:wait-init in 9269218 cycles
[ 1.395285] Brought CPUs online in 28930764 cycles
[ 1.395469] smp: Brought up 2 nodes, 96 CPUs
[ 1.395689] smpboot: Max logical packages: 2
[ 1.396222] smpboot: Total of 96 processors activated (576000.00 BogoMIPS)

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
arch/x86/include/asm/smp.h | 4 +-
arch/x86/include/asm/topology.h | 2 -
arch/x86/kernel/cpu/common.c | 6 +--
arch/x86/kernel/smpboot.c | 73 ++++++++++++++++++++-------------
arch/x86/xen/smp_pv.c | 4 +-
5 files changed, 48 insertions(+), 41 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 33c0d5fd8af6..b4b29e052b6e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -48,8 +48,6 @@ struct smp_ops {
};

/* Globals due to paravirt */
-extern void set_cpu_sibling_map(int cpu);
-
#ifdef CONFIG_SMP
extern struct smp_ops smp_ops;

@@ -137,7 +135,7 @@ void native_send_call_func_single_ipi(int cpu);
void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle);

void smp_store_boot_cpu_info(void);
-void smp_store_cpu_info(int id);
+void smp_store_cpu_info(int id, bool force_single_core);

asmlinkage __visible void smp_reboot_interrupt(void);
__visible void smp_reschedule_interrupt(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 458c891a8273..4bccbd949a99 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -136,8 +136,6 @@ static inline int topology_max_smt_threads(void)
return __max_smt_threads;
}

-int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-int topology_update_die_map(unsigned int dieid, unsigned int cpu);
int topology_phys_to_logical_pkg(unsigned int pkg);
int topology_phys_to_logical_die(unsigned int die, unsigned int cpu);
bool topology_is_primary_thread(unsigned int cpu);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f3cc7699e1e1..06d7f9e55d45 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1771,7 +1771,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
* Validate that ACPI/mptables have the same information about the
* effective APIC id and update the package map.
*/
-static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
+static void validate_apic_id(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned int apicid, cpu = smp_processor_id();
@@ -1782,8 +1782,6 @@ static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
cpu, apicid, c->initial_apicid);
}
- BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
- BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
#else
c->logical_proc_id = 0;
#endif
@@ -1974,7 +1972,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_32
enable_sep_cpu();
#endif
- validate_apic_and_package_id(c);
+ validate_apic_id(c);
x86_spec_ctrl_setup_ap();
update_srbds_msr();

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a8f52e03d55d..47093e6356de 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -180,16 +180,12 @@ static void smp_callin(void)
apic_ap_setup();

/*
- * Save our processor parameters. Note: this information
- * is needed for clock calibration.
- */
- smp_store_cpu_info(cpuid);
-
- /*
+ * Save our processor parameters and update topology.
+ * Note: this information is needed for clock calibration.
* The topology information must be up to date before
* calibrate_delay() and notify_cpu_starting().
*/
- set_cpu_sibling_map(raw_smp_processor_id());
+ smp_store_cpu_info(cpuid, false);

ap_init_aperfmperf();

@@ -243,6 +239,12 @@ static void notrace start_secondary(void *unused)
* its bit in cpu_callout_mask to release it.
*/
cpu_init_secondary();
+
+ /*
+ * Even though notify_cpu_starting() will do this, it does so too late
+ * as the AP may already have triggered lockdep splats by then. See
+ * commit 29368e093 ("x86/smpboot: Move rcu_cpu_starting() earlier").
+ */
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();

@@ -351,7 +353,7 @@ EXPORT_SYMBOL(topology_phys_to_logical_die);
* @pkg: The physical package id as retrieved via CPUID
* @cpu: The cpu for which this is updated
*/
-int topology_update_package_map(unsigned int pkg, unsigned int cpu)
+static int topology_update_package_map(unsigned int pkg, unsigned int cpu)
{
int new;

@@ -374,7 +376,7 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
* @die: The die id as retrieved via CPUID
* @cpu: The cpu for which this is updated
*/
-int topology_update_die_map(unsigned int die, unsigned int cpu)
+static int topology_update_die_map(unsigned int die, unsigned int cpu)
{
int new;

@@ -405,25 +407,7 @@ void __init smp_store_boot_cpu_info(void)
c->initialized = true;
}

-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
- struct cpuinfo_x86 *c = &cpu_data(id);
-
- /* Copy boot_cpu_data only on the first bringup */
- if (!c->initialized)
- *c = boot_cpu_data;
- c->cpu_index = id;
- /*
- * During boot time, CPU0 has this setup already. Save the info when
- * bringing up AP or offlined CPU0.
- */
- identify_secondary_cpu(c);
- c->initialized = true;
-}
+static arch_spinlock_t topology_lock = __ARCH_SPIN_LOCK_UNLOCKED;

static bool
topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -629,7 +613,7 @@ static struct sched_domain_topology_level x86_topology[] = {
*/
static bool x86_has_numa_in_package;

-void set_cpu_sibling_map(int cpu)
+static void set_cpu_sibling_map(int cpu)
{
bool has_smt = smp_num_siblings > 1;
bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
@@ -708,6 +692,37 @@ void set_cpu_sibling_map(int cpu)
}
}

+/*
+ * The bootstrap kernel entry code has set these up. Save them for
+ * a given CPU
+ */
+void smp_store_cpu_info(int id, bool force_single_core)
+{
+ struct cpuinfo_x86 *c = &cpu_data(id);
+
+ /* Copy boot_cpu_data only on the first bringup */
+ if (!c->initialized)
+ *c = boot_cpu_data;
+ c->cpu_index = id;
+ /*
+ * During boot time, CPU0 has this setup already. Save the info when
+ * bringing up AP or offlined CPU0.
+ */
+ identify_secondary_cpu(c);
+
+ arch_spin_lock(&topology_lock);
+ BUG_ON(topology_update_package_map(c->phys_proc_id, id));
+ BUG_ON(topology_update_die_map(c->cpu_die_id, id));
+ c->initialized = true;
+
+ /* For Xen PV */
+ if (force_single_core)
+ c->x86_max_cores = 1;
+
+ set_cpu_sibling_map(id);
+ arch_spin_unlock(&topology_lock);
+}
+
/* maps the cpu to the sched domain representing multi-core */
const struct cpumask *cpu_coregroup_mask(int cpu)
{
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6175f2c5c822..09f94f940689 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -71,9 +71,7 @@ static void cpu_bringup(void)
xen_enable_syscall();
}
cpu = smp_processor_id();
- smp_store_cpu_info(cpu);
- cpu_data(cpu).x86_max_cores = 1;
- set_cpu_sibling_map(cpu);
+ smp_store_cpu_info(cpu, true);

speculative_store_bypass_ht_init();

--
2.25.1


2023-02-21 22:36:47

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 3/8] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU

From: David Woodhouse <[email protected]>

There is often significant latency in the early stages of CPU bringup,
and time is wasted by waking each CPU (e.g. with SIPI/INIT/INIT on x86)
and then waiting for it to respond before moving on to the next.

Allow a platform to register a set of pre-bringup CPUHP states to which
each CPU can be stepped in parallel, thus absorbing some of that latency.

There is a subtlety here: even with an empty CPUHP_BP_PARALLEL_DYN step,
this means that *all* CPUs are brought through the prepare states and to
CPUHP_BP_PREPARE_DYN before any of them are taken to CPUHP_BRINGUP_CPU
and then are allowed to run for themselves to CPUHP_ONLINE.

So any combination of prepare/start calls which depend on A-B ordering
for each CPU in turn, such as the X2APIC code which used to allocate a
cluster mask 'just in case' and store it in a global variable in the
prep stage, then potentially consume that preallocated structure from
the AP and set the global pointer to NULL to be reallocated in
CPUHP_X2APIC_PREPARE for the next CPU... would explode horribly.

Any platform enabling the CPUHP_BP_PARALLEL_DYN steps must be reviewed
and tested to ensure that such issues do not exist, and the existing
behaviour of bringing CPUs to CPUHP_BP_PREPARE_DYN and then immediately
to CPUHP_BRINGUP_CPU and CPUHP_ONLINE only one at a time does not change
unless such a state is registered.

Note that the new parallel stages do *not* yet bring each AP to the
CPUHP_BRINGUP_CPU state at the same time, only to the new states which
exist before it. The final loop in bringup_nonboot_cpus() is untouched,
bringing each AP in turn from the final PARALLEL_DYN state (or all the
way from CPUHP_OFFLINE) to CPUHP_BRINGUP_CPU and then waiting for that
AP to do its own processing and reach CPUHP_ONLINE before releasing the
next.

Parallelising that part by bringing them all to CPUHP_BRINGUP_CPU
and then waiting for them all is an exercise for the future.

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
include/linux/cpuhotplug.h | 2 ++
kernel/cpu.c | 31 +++++++++++++++++++++++++++++--
2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 6c6859bfc454..e5a73ae6ccc0 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -133,6 +133,8 @@ enum cpuhp_state {
CPUHP_MIPS_SOC_PREPARE,
CPUHP_BP_PREPARE_DYN,
CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20,
+ CPUHP_BP_PARALLEL_DYN,
+ CPUHP_BP_PARALLEL_DYN_END = CPUHP_BP_PARALLEL_DYN + 4,
CPUHP_BRINGUP_CPU,

/*
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6c0a92ca6bb5..fffb0da61ccc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1504,8 +1504,30 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu)

void bringup_nonboot_cpus(unsigned int setup_max_cpus)
{
+ unsigned int n = setup_max_cpus - num_online_cpus();
unsigned int cpu;

+ /*
+ * An architecture may have registered parallel pre-bringup states to
+ * which each CPU may be brought in parallel. For each such state,
+ * bring N CPUs to it in turn before the final round of bringing them
+ * online.
+ */
+ if (n > 0) {
+ enum cpuhp_state st = CPUHP_BP_PARALLEL_DYN;
+
+ while (st <= CPUHP_BP_PARALLEL_DYN_END && cpuhp_hp_states[st].name) {
+ int i = n;
+
+ for_each_present_cpu(cpu) {
+ cpu_up(cpu, st);
+ if (!--i)
+ break;
+ }
+ st++;
+ }
+ }
+
for_each_present_cpu(cpu) {
if (num_online_cpus() >= setup_max_cpus)
break;
@@ -1882,6 +1904,10 @@ static int cpuhp_reserve_state(enum cpuhp_state state)
step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN;
end = CPUHP_BP_PREPARE_DYN_END;
break;
+ case CPUHP_BP_PARALLEL_DYN:
+ step = cpuhp_hp_states + CPUHP_BP_PARALLEL_DYN;
+ end = CPUHP_BP_PARALLEL_DYN_END;
+ break;
default:
return -EINVAL;
}
@@ -1906,14 +1932,15 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
/*
* If name is NULL, then the state gets removed.
*
- * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on
+ * CPUHP_AP_ONLINE_DYN and CPUHP_BP_P*_DYN are handed out on
* the first allocation from these dynamic ranges, so the removal
* would trigger a new allocation and clear the wrong (already
* empty) state, leaving the callbacks of the to be cleared state
* dangling, which causes wreckage on the next hotplug operation.
*/
if (name && (state == CPUHP_AP_ONLINE_DYN ||
- state == CPUHP_BP_PREPARE_DYN)) {
+ state == CPUHP_BP_PREPARE_DYN ||
+ state == CPUHP_BP_PARALLEL_DYN)) {
ret = cpuhp_reserve_state(state);
if (ret < 0)
return ret;
--
2.25.1


2023-02-21 22:36:49

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 4/8] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector()

From: David Woodhouse <[email protected]>

When bringing up a secondary CPU from do_boot_cpu(), the warm reset flag
is set in CMOS and the starting IP for the trampoline written inside the
BDA at 0x467. Once the CPU is running, the CMOS flag is unset and the
value in the BDA cleared.

To allow for parallel bringup of CPUs, add a reference count to track the
number of CPUs currently bring brought up, and clear the state only when
the count reaches zero.

Since the RTC spinlock is required to write to the CMOS, it can be used
for mutual exclusion on the refcount too.

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
arch/x86/kernel/smpboot.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 55cad72715d9..3a793772a2aa 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -121,17 +121,20 @@ int arch_update_cpu_topology(void)
return retval;
}

+
+static unsigned int smpboot_warm_reset_vector_count;
+
static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
{
unsigned long flags;

spin_lock_irqsave(&rtc_lock, flags);
- CMOS_WRITE(0xa, 0xf);
+ if (!smpboot_warm_reset_vector_count++) {
+ CMOS_WRITE(0xa, 0xf);
+ *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4;
+ *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf;
+ }
spin_unlock_irqrestore(&rtc_lock, flags);
- *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
- start_eip >> 4;
- *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
- start_eip & 0xf;
}

static inline void smpboot_restore_warm_reset_vector(void)
@@ -143,10 +146,12 @@ static inline void smpboot_restore_warm_reset_vector(void)
* to default values.
*/
spin_lock_irqsave(&rtc_lock, flags);
- CMOS_WRITE(0, 0xf);
+ if (!--smpboot_warm_reset_vector_count) {
+ CMOS_WRITE(0, 0xf);
+ *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
+ }
spin_unlock_irqrestore(&rtc_lock, flags);

- *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}

/*
--
2.25.1


2023-02-21 22:36:54

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 5/8] x86/smpboot: Split up native_cpu_up into separate phases and document them

From: David Woodhouse <[email protected]>

There are four logical parts to what native_cpu_up() does on the BSP (or
on the controlling CPU for a later hotplug):

1) Wake the AP by sending the INIT/SIPI/SIPI sequence.

2) Wait for the AP to make it as far as wait_for_master_cpu() which
sets that CPU's bit in cpu_initialized_mask, then sets the bit in
cpu_callout_mask to let the AP proceed through cpu_init().

3) Wait for the AP to finish cpu_init() and get as far as the
smp_callin() call, which sets that CPU's bit in cpu_callin_mask.

4) Perform the TSC synchronization and wait for the AP to actually
mark itself online in cpu_online_mask.

In preparation to allow these phases to operate in parallel on multiple
APs, split them out into separate functions and document the interactions
a little more clearly in both the BSP and AP code paths.

No functional change intended.

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
arch/x86/kernel/smpboot.c | 181 ++++++++++++++++++++++++++------------
1 file changed, 127 insertions(+), 54 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3a793772a2aa..b18c1385e181 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -204,6 +204,10 @@ static void smp_callin(void)

wmb();

+ /*
+ * This runs the AP through all the cpuhp states to its target
+ * state (CPUHP_ONLINE in the case of serial bringup).
+ */
notify_cpu_starting(cpuid);

/*
@@ -231,17 +235,32 @@ static void notrace start_secondary(void *unused)
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
+ /*
+ * Sync point with do_wait_cpu_initialized(). Before proceeding through
+ * cpu_init(), the AP will call wait_for_master_cpu() which sets its
+ * own bit in cpu_initialized_mask and then waits for the BSP to set
+ * its bit in cpu_callout_mask to release it.
+ */
cpu_init_secondary();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
+
+ /*
+ * Sync point with do_wait_cpu_callin(). The AP doesn't wait here
+ * but just sets the bit to let the controlling CPU (BSP) know that
+ * it's got this far.
+ */
smp_callin();

enable_start_cpu0 = 0;

/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
+
/*
- * Check TSC synchronization with the boot CPU:
+ * Check TSC synchronization with the boot CPU (or whichever CPU
+ * is controlling the bringup). It will do its part of this from
+ * do_wait_cpu_online(), making it an implicit sync point.
*/
check_tsc_sync_target();

@@ -254,6 +273,7 @@ static void notrace start_secondary(void *unused)
* half valid vector space.
*/
lock_vector_lock();
+ /* Sync point with do_wait_cpu_online() */
set_cpu_online(smp_processor_id(), true);
lapic_online();
unlock_vector_lock();
@@ -1083,7 +1103,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
unsigned long start_ip = real_mode_header->trampoline_start;

unsigned long boot_error = 0;
- unsigned long timeout;

#ifdef CONFIG_X86_64
/* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
@@ -1144,55 +1163,94 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
cpu0_nmi_registered);

- if (!boot_error) {
- /*
- * Wait 10s total for first sign of life from AP
- */
- boot_error = -1;
- timeout = jiffies + 10*HZ;
- while (time_before(jiffies, timeout)) {
- if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
- /*
- * Tell AP to proceed with initialization
- */
- cpumask_set_cpu(cpu, cpu_callout_mask);
- boot_error = 0;
- break;
- }
- schedule();
- }
- }
+ return boot_error;
+}

- if (!boot_error) {
- /*
- * Wait till AP completes initial initialization
- */
- while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
- /*
- * Allow other tasks to run while we wait for the
- * AP to come online. This also gives a chance
- * for the MTRR work(triggered by the AP coming online)
- * to be completed in the stop machine context.
- */
- schedule();
- }
+static int do_wait_cpu_cpumask(unsigned int cpu, const struct cpumask *mask)
+{
+ unsigned long timeout;
+
+ /*
+ * Wait up to 10s for the CPU to report in.
+ */
+ timeout = jiffies + 10*HZ;
+ while (time_before(jiffies, timeout)) {
+ if (cpumask_test_cpu(cpu, mask))
+ return 0;
+
+ schedule();
}
+ return -1;
+}

- if (x86_platform.legacy.warm_reset) {
- /*
- * Cleanup possible dangling ends...
- */
- smpboot_restore_warm_reset_vector();
+/*
+ * Bringup step two: Wait for the target AP to reach cpu_init_secondary()
+ * and thus wait_for_master_cpu(), then set cpu_callout_mask to allow it
+ * to proceed. The AP will then proceed past setting its 'callin' bit
+ * and end up waiting in check_tsc_sync_target() until we reach
+ * do_wait_cpu_online() to tend to it.
+ */
+static int do_wait_cpu_initialized(unsigned int cpu)
+{
+ /*
+ * Wait for first sign of life from AP.
+ */
+ if (do_wait_cpu_cpumask(cpu, cpu_initialized_mask))
+ return -1;
+
+ cpumask_set_cpu(cpu, cpu_callout_mask);
+ return 0;
+}
+
+/*
+ * Bringup step three: Wait for the target AP to reach smp_callin().
+ * The AP is not waiting for us here so we don't need to parallelise
+ * this step. Not entirely clear why we care about this, since we just
+ * proceed directly to TSC synchronization which is the next sync
+ * point with the AP anyway.
+ */
+static int do_wait_cpu_callin(unsigned int cpu)
+{
+ /*
+ * Wait till AP completes initial initialization.
+ */
+ return do_wait_cpu_cpumask(cpu, cpu_callin_mask);
+}
+
+/*
+ * Bringup step four: Synchronize the TSC and wait for the target AP
+ * to reach set_cpu_online() in start_secondary().
+ */
+static int do_wait_cpu_online(unsigned int cpu)
+{
+ unsigned long flags;
+
+ /*
+ * Check TSC synchronization with the AP (keep irqs disabled
+ * while doing so):
+ */
+ local_irq_save(flags);
+ check_tsc_sync_source(cpu);
+ local_irq_restore(flags);
+
+ /*
+ * Wait for the AP to mark itself online. Not entirely
+ * clear why we care, since the generic cpuhp code will
+ * wait for it to each CPUHP_AP_ONLINE_IDLE before going
+ * ahead with the rest of the bringup anyway.
+ */
+ while (!cpu_online(cpu)) {
+ cpu_relax();
+ touch_nmi_watchdog();
}

- return boot_error;
+ return 0;
}

-int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+static int do_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
int cpu0_nmi_registered = 0;
- unsigned long flags;
int err, ret = 0;

lockdep_assert_irqs_enabled();
@@ -1239,19 +1297,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
goto unreg_nmi;
}

- /*
- * Check TSC synchronization with the AP (keep irqs disabled
- * while doing so):
- */
- local_irq_save(flags);
- check_tsc_sync_source(cpu);
- local_irq_restore(flags);
-
- while (!cpu_online(cpu)) {
- cpu_relax();
- touch_nmi_watchdog();
- }
-
unreg_nmi:
/*
* Clean up the nmi handler. Do this after the callin and callout sync
@@ -1263,6 +1308,34 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
return ret;
}

+int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ int ret;
+
+ ret = do_cpu_up(cpu, tidle);
+ if (ret)
+ return ret;
+
+ ret = do_wait_cpu_initialized(cpu);
+ if (ret)
+ return ret;
+
+ ret = do_wait_cpu_callin(cpu);
+ if (ret)
+ return ret;
+
+ ret = do_wait_cpu_online(cpu);
+
+ if (x86_platform.legacy.warm_reset) {
+ /*
+ * Cleanup possible dangling ends...
+ */
+ smpboot_restore_warm_reset_vector();
+ }
+
+ return ret;
+}
+
/**
* arch_disable_smp_support() - disables SMP support for x86 at runtime
*/
--
2.25.1


2023-02-21 22:36:56

by Usama Arif

[permalink] [raw]
Subject: [PATCH v10 6/8] x86/smpboot: Support parallel startup of secondary CPUs

From: David Woodhouse <[email protected]>

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 the use of global variables for passing per-CPU information to
the APs.

To achieve the latter, export the cpuid_to_apicid[] array so that each
AP can find its own per_cpu data (and thus initial_gs, initial_stack and
early_gdt_descr) by searching therein based on its APIC ID.

Introduce a global variable 'smpboot_control' indicating to the AP how
it should find its APIC ID. For a serialized bringup, the APIC ID is
explicitly passed in the low bits of smpboot_control, while 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.

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 correect.
• X2APIC is not enabled but not even CPUID leaf 0x01 exists.

Aside from the fact that APs will now look up their per-cpu data 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 <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
---
.../admin-guide/kernel-parameters.txt | 3 +
arch/x86/include/asm/realmode.h | 3 +
arch/x86/include/asm/smp.h | 10 +-
arch/x86/kernel/acpi/sleep.c | 7 ++
arch/x86/kernel/apic/apic.c | 2 +-
arch/x86/kernel/head_64.S | 99 ++++++++++++++++++-
arch/x86/kernel/smpboot.c | 62 +++++++++++-
arch/x86/realmode/init.c | 3 +
arch/x86/realmode/rm/trampoline_64.S | 14 +++
kernel/smpboot.c | 2 +-
10 files changed, 197 insertions(+), 8 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6cfa6e3996cf..ee099b8aac6d 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 brinugp of secondary cores.
+
nopat [X86] Disable PAT (page attribute table extension of
pagetables) support.

diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index a336feef0af1..f0357cfe2fb0 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
};

@@ -65,6 +66,8 @@ 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 b4dbb20dab1a..33c0d5fd8af6 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -199,5 +199,13 @@ extern void nmi_selftest(void);
#define nmi_selftest() do { } while (0)
#endif

-#endif /* __ASSEMBLY__ */
+extern unsigned int smpboot_control;
+
+#endif /* !__ASSEMBLY__ */
+
+/* Control bits for startup_64 */
+#define STARTUP_SECONDARY 0x80000000
+#define STARTUP_APICID_CPUID_0B 0x40000000
+#define STARTUP_APICID_CPUID_01 0x20000000
+
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 3b7f4cdbf2e0..47e75c056cb5 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"
@@ -57,6 +58,7 @@ asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state)
*/
int x86_acpi_suspend_lowlevel(void)
{
+ unsigned int __maybe_unused saved_smpboot_ctrl;
struct wakeup_header *header =
(struct wakeup_header *) __va(real_mode_header->wakeup_header);

@@ -115,6 +117,8 @@ int x86_acpi_suspend_lowlevel(void)
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_rw(smp_processor_id());
initial_gs = per_cpu_offset(smp_processor_id());
+ /* Force the startup into boot mode */
+ saved_smpboot_ctrl = xchg(&smpboot_control, 0);
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0L;
@@ -127,6 +131,9 @@ int x86_acpi_suspend_lowlevel(void)
pause_graph_tracing();
do_suspend_lowlevel();
unpause_graph_tracing();
+
+ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_SMP))
+ smpboot_control = saved_smpboot_ctrl;
return 0;
}

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/head_64.S b/arch/x86/kernel/head_64.S
index 222efd4a09bc..0e4e53d231db 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
@@ -241,6 +242,83 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
UNWIND_HINT_EMPTY
ANNOTATE_NOENDBR // above

+#ifdef CONFIG_SMP
+ /*
+ * 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), %edx
+ testl $STARTUP_SECONDARY, %edx
+ 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 31 STARTUP_SECONDARY flag (checked above)
+ * Bit 30 STARTUP_APICID_CPUID_0B flag (use CPUID 0x0b)
+ * Bit 29 STARTUP_APICID_CPUID_01 flag (use CPUID 0x01)
+ * Bit 0-24 APIC ID if STARTUP_APICID_CPUID_xx flags are not set
+ */
+ testl $STARTUP_APICID_CPUID_0B, %edx
+ jnz .Luse_cpuid_0b
+ testl $STARTUP_APICID_CPUID_01, %edx
+ jnz .Luse_cpuid_01
+ andl $0x0FFFFFFF, %edx
+ jmp .Lsetup_AP
+
+.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 .Linit_cpu_data
+ inc %ecx
+ cmpl nr_cpu_ids(%rip), %ecx
+ 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
+
+.Linit_cpu_data:
+ /* Get the per cpu offset for the given CPU# which is in ECX */
+ leaq __per_cpu_offset(%rip), %rbx
+ movq (%rbx,%rcx,8), %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(%rbx), %rcx
+ movq TASK_threadsp(%rcx), %rcx
+ movq %rcx, initial_stack(%rip)
+#endif /* CONFIG_SMP */
+
+.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
@@ -281,6 +359,14 @@ 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
@@ -372,7 +458,14 @@ SYM_CODE_END(secondary_startup_64)
SYM_CODE_START(start_cpu0)
ANNOTATE_NOENDBR
UNWIND_HINT_EMPTY
- movq initial_stack(%rip), %rsp
+ /* Load the per-cpu base for CPU#0 */
+ leaq __per_cpu_offset(%rip), %rbx
+ movq (%rbx), %rbx
+
+ /* Find the idle task stack */
+ movq idle_threads(%rbx), %rcx
+ movq TASK_threadsp(%rcx), %rsp
+
jmp .Ljump_to_C_code
SYM_CODE_END(start_cpu0)
#endif
@@ -426,6 +519,7 @@ 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
@@ -660,6 +754,9 @@ 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 b18c1385e181..6924d91b69ca 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 */
@@ -1084,8 +1094,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
-#else
- initial_gs = per_cpu_offset(cpu);
#endif
return 0;
}
@@ -1110,9 +1118,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
start_ip = real_mode_header->trampoline_start64;
#endif
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 (!do_parallel_bringup) {
+ smpboot_control = STARTUP_SECONDARY | apicid;
+ }

/* Enable the espfix hack for this CPU */
init_espfix_ap(cpu);
@@ -1512,6 +1525,47 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)

speculative_store_bypass_ht_init();

+ /*
+ * 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.
+ */
+ if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 1 ||
+ (x2apic_mode && boot_cpu_data.cpuid_level < 0xb) ||
+ cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+ do_parallel_bringup = false;
+
+ if (do_parallel_bringup && x2apic_mode) {
+ unsigned int eax, ebx, ecx, edx;
+
+ /*
+ * To support parallel bringup in x2apic mode, the AP will need
+ * to obtain its APIC ID from CPUID 0x0B, since CPUID 0x01 has
+ * only 8 bits. Check that it is present and seems correct.
+ */
+ cpuid_count(0xb, 0, &eax, &ebx, &ecx, &edx);
+
+ /*
+ * AMD says that if executed with an umimplemented level in
+ * ECX, then it will return all zeroes in EAX. Intel says it
+ * will return zeroes in both EAX and EBX. Checking only EAX
+ * should be sufficient.
+ */
+ if (eax) {
+ pr_debug("Using CPUID 0xb for parallel CPU startup\n");
+ smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_0B;
+ } else {
+ pr_info("Disabling parallel bringup because CPUID 0xb looks untrustworthy\n");
+ do_parallel_bringup = false;
+ }
+ } else if (do_parallel_bringup) {
+ /* Without X2APIC, what's in CPUID 0x01 should suffice. */
+ pr_debug("Using CPUID 0x1 for parallel CPU startup\n");
+ smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_01;
+ }
+
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..49ebc1636ffd 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

@@ -241,6 +254,7 @@ 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 2c7396da470c..a18a21dff9bc 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)
{
--
2.25.1


2023-02-24 05:59:55

by Yuan Yao

[permalink] [raw]
Subject: Re: [PATCH v10 6/8] x86/smpboot: Support parallel startup of secondary CPUs

On Tue, Feb 21, 2023 at 10:33:50PM +0000, Usama Arif wrote:
> From: David Woodhouse <[email protected]>
>
> 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 the use of global variables for passing per-CPU information to
> the APs.
>
> To achieve the latter, export the cpuid_to_apicid[] array so that each
> AP can find its own per_cpu data (and thus initial_gs, initial_stack and
> early_gdt_descr) by searching therein based on its APIC ID.
>
> Introduce a global variable 'smpboot_control' indicating to the AP how
> it should find its APIC ID. For a serialized bringup, the APIC ID is
> explicitly passed in the low bits of smpboot_control, while 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.
>
> 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 correect.
> • X2APIC is not enabled but not even CPUID leaf 0x01 exists.
>
> Aside from the fact that APs will now look up their per-cpu data 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 <[email protected]>
> Signed-off-by: Thomas Gleixner <[email protected]>
> Signed-off-by: David Woodhouse <[email protected]>
> Signed-off-by: Usama Arif <[email protected]>
> Tested-by: Paul E. McKenney <[email protected]>
> Tested-by: Kim Phillips <[email protected]>
> Tested-by: Oleksandr Natalenko <[email protected]>
> ---
> .../admin-guide/kernel-parameters.txt | 3 +
> arch/x86/include/asm/realmode.h | 3 +
> arch/x86/include/asm/smp.h | 10 +-
> arch/x86/kernel/acpi/sleep.c | 7 ++
> arch/x86/kernel/apic/apic.c | 2 +-
> arch/x86/kernel/head_64.S | 99 ++++++++++++++++++-
> arch/x86/kernel/smpboot.c | 62 +++++++++++-
> arch/x86/realmode/init.c | 3 +
> arch/x86/realmode/rm/trampoline_64.S | 14 +++
> kernel/smpboot.c | 2 +-
> 10 files changed, 197 insertions(+), 8 deletions(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 6cfa6e3996cf..ee099b8aac6d 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 brinugp of secondary cores.
> +
> nopat [X86] Disable PAT (page attribute table extension of
> pagetables) support.
>
> diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
> index a336feef0af1..f0357cfe2fb0 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
> };
>
> @@ -65,6 +66,8 @@ 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 b4dbb20dab1a..33c0d5fd8af6 100644
> --- a/arch/x86/include/asm/smp.h
> +++ b/arch/x86/include/asm/smp.h
> @@ -199,5 +199,13 @@ extern void nmi_selftest(void);
> #define nmi_selftest() do { } while (0)
> #endif
>
> -#endif /* __ASSEMBLY__ */
> +extern unsigned int smpboot_control;
> +
> +#endif /* !__ASSEMBLY__ */
> +
> +/* Control bits for startup_64 */
> +#define STARTUP_SECONDARY 0x80000000
> +#define STARTUP_APICID_CPUID_0B 0x40000000
> +#define STARTUP_APICID_CPUID_01 0x20000000
> +
> #endif /* _ASM_X86_SMP_H */
> diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
> index 3b7f4cdbf2e0..47e75c056cb5 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"
> @@ -57,6 +58,7 @@ asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state)
> */
> int x86_acpi_suspend_lowlevel(void)
> {
> + unsigned int __maybe_unused saved_smpboot_ctrl;
> struct wakeup_header *header =
> (struct wakeup_header *) __va(real_mode_header->wakeup_header);
>
> @@ -115,6 +117,8 @@ int x86_acpi_suspend_lowlevel(void)
> early_gdt_descr.address =
> (unsigned long)get_cpu_gdt_rw(smp_processor_id());
> initial_gs = per_cpu_offset(smp_processor_id());
> + /* Force the startup into boot mode */
> + saved_smpboot_ctrl = xchg(&smpboot_control, 0);
> #endif
> initial_code = (unsigned long)wakeup_long64;
> saved_magic = 0x123456789abcdef0L;
> @@ -127,6 +131,9 @@ int x86_acpi_suspend_lowlevel(void)
> pause_graph_tracing();
> do_suspend_lowlevel();
> unpause_graph_tracing();
> +
> + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_SMP))
> + smpboot_control = saved_smpboot_ctrl;
> return 0;
> }
>
> 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/head_64.S b/arch/x86/kernel/head_64.S
> index 222efd4a09bc..0e4e53d231db 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
> @@ -241,6 +242,83 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
> UNWIND_HINT_EMPTY
> ANNOTATE_NOENDBR // above
>
> +#ifdef CONFIG_SMP
> + /*
> + * 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), %edx
> + testl $STARTUP_SECONDARY, %edx
> + 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 31 STARTUP_SECONDARY flag (checked above)
> + * Bit 30 STARTUP_APICID_CPUID_0B flag (use CPUID 0x0b)
> + * Bit 29 STARTUP_APICID_CPUID_01 flag (use CPUID 0x01)
> + * Bit 0-24 APIC ID if STARTUP_APICID_CPUID_xx flags are not set
> + */
> + testl $STARTUP_APICID_CPUID_0B, %edx
> + jnz .Luse_cpuid_0b
> + testl $STARTUP_APICID_CPUID_01, %edx
> + jnz .Luse_cpuid_01
> + andl $0x0FFFFFFF, %edx
> + jmp .Lsetup_AP
> +
> +.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 .Linit_cpu_data
> + inc %ecx
> + cmpl nr_cpu_ids(%rip), %ecx
> + 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
> +
> +.Linit_cpu_data:
> + /* Get the per cpu offset for the given CPU# which is in ECX */
> + leaq __per_cpu_offset(%rip), %rbx
> + movq (%rbx,%rcx,8), %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(%rbx), %rcx
> + movq TASK_threadsp(%rcx), %rcx
> + movq %rcx, initial_stack(%rip)
> +#endif /* CONFIG_SMP */
> +
> +.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
> @@ -281,6 +359,14 @@ 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
> @@ -372,7 +458,14 @@ SYM_CODE_END(secondary_startup_64)
> SYM_CODE_START(start_cpu0)
> ANNOTATE_NOENDBR
> UNWIND_HINT_EMPTY
> - movq initial_stack(%rip), %rsp
> + /* Load the per-cpu base for CPU#0 */
> + leaq __per_cpu_offset(%rip), %rbx
> + movq (%rbx), %rbx
> +
> + /* Find the idle task stack */
> + movq idle_threads(%rbx), %rcx
> + movq TASK_threadsp(%rcx), %rsp
> +
> jmp .Ljump_to_C_code
> SYM_CODE_END(start_cpu0)
> #endif
> @@ -426,6 +519,7 @@ 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
> @@ -660,6 +754,9 @@ 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 b18c1385e181..6924d91b69ca 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 */
> @@ -1084,8 +1094,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
> #ifdef CONFIG_X86_32
> /* Stack for startup_32 can be just as for start_secondary onwards */
> per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
> -#else
> - initial_gs = per_cpu_offset(cpu);
> #endif
> return 0;
> }
> @@ -1110,9 +1118,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
> start_ip = real_mode_header->trampoline_start64;
> #endif
> 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 (!do_parallel_bringup) {
> + smpboot_control = STARTUP_SECONDARY | apicid;
> + }
>
> /* Enable the espfix hack for this CPU */
> init_espfix_ap(cpu);
> @@ -1512,6 +1525,47 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
>
> speculative_store_bypass_ht_init();
>
> + /*
> + * 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.
> + */
> + if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 1 ||
> + (x2apic_mode && boot_cpu_data.cpuid_level < 0xb) ||
> + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
> + do_parallel_bringup = false;
> +
> + if (do_parallel_bringup && x2apic_mode) {
> + unsigned int eax, ebx, ecx, edx;
> +
> + /*
> + * To support parallel bringup in x2apic mode, the AP will need
> + * to obtain its APIC ID from CPUID 0x0B, since CPUID 0x01 has
> + * only 8 bits. Check that it is present and seems correct.
> + */
> + cpuid_count(0xb, 0, &eax, &ebx, &ecx, &edx);
> +
> + /*
> + * AMD says that if executed with an umimplemented level in
> + * ECX, then it will return all zeroes in EAX. Intel says it
> + * will return zeroes in both EAX and EBX. Checking only EAX
> + * should be sufficient.
> + */
> + if (eax) {
> + pr_debug("Using CPUID 0xb for parallel CPU startup\n");
> + smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_0B;
> + } else {
> + pr_info("Disabling parallel bringup because CPUID 0xb looks untrustworthy\n");
> + do_parallel_bringup = false;
> + }
> + } else if (do_parallel_bringup) {
> + /* Without X2APIC, what's in CPUID 0x01 should suffice. */
> + pr_debug("Using CPUID 0x1 for parallel CPU startup\n");
> + smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_01;
> + }
> +
> 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..49ebc1636ffd 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
> +

Looks these changes should be applied to trampoline_start64()
yet, which is used for boot up APs when apic->wakeup_secondary_cpu_64
is available, e.g when ACPI_MADT_TYPE_MULTIPROC_WAKEUP is available.

One case I know is the INTEL TD guest, which using the MADT wakeup
for AP wake up now.

> # Setup stack
> movl $rm_stack_end, %esp
>
> @@ -241,6 +254,7 @@ 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 2c7396da470c..a18a21dff9bc 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)
> {
> --
> 2.25.1
>

2023-02-24 15:47:33

by David Woodhouse

[permalink] [raw]
Subject: Re: [PATCH v10 6/8] x86/smpboot: Support parallel startup of secondary CPUs

On Fri, 2023-02-24 at 13:59 +0800, Yuan Yao wrote:
>
> > +        * 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
> > +
>
> Looks these changes should be applied to trampoline_start64()
> yet, which is used for boot up APs when apic->wakeup_secondary_cpu_64
> is available, e.g when ACPI_MADT_TYPE_MULTIPROC_WAKEUP is available.
>
> One case I know is the INTEL TD guest, which using the MADT wakeup
> for AP wake up now.

Yeah.

I think we could probably pull that all out into a separate asm
"load_realmode_esp" function which takes the lock and actually does the
'movl $rm_stack_end, %esp'.

Then we call it from all the places which currently use $rm_stack_end,
including sev_es_trampoline_start (even though we currently disable
parallel startup there because CPUID doesn't work that early).

Oh... except of course it can't be a function because we haven't got a
stack, have we? It's a macro.

Usama, are you happy using .macro in gas?


Attachments:
smime.p7s (5.83 kB)

2023-02-24 19:17:28

by Usama Arif

[permalink] [raw]
Subject: Re: [External] Re: [PATCH v10 6/8] x86/smpboot: Support parallel startup of secondary CPUs



On 24/02/2023 15:46, David Woodhouse wrote:
> On Fri, 2023-02-24 at 13:59 +0800, Yuan Yao wrote:
>>
>>> +        * 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
>>> +
>>
>> Looks these changes should be applied to trampoline_start64()
>> yet, which is used for boot up APs when apic->wakeup_secondary_cpu_64
>> is available, e.g when ACPI_MADT_TYPE_MULTIPROC_WAKEUP is available.
>>
>> One case I know is the INTEL TD guest, which using the MADT wakeup
>> for AP wake up now.
>
> Yeah.
>
> I think we could probably pull that all out into a separate asm
> "load_realmode_esp" function which takes the lock and actually does the
> 'movl $rm_stack_end, %esp'.
>
> Then we call it from all the places which currently use $rm_stack_end,
> including sev_es_trampoline_start (even though we currently disable
> parallel startup there because CPUID doesn't work that early).
>
> Oh... except of course it can't be a function because we haven't got a
> stack, have we? It's a macro.
>
> Usama, are you happy using .macro in gas?

Yes, makes sense. I guess something like below should be ok?
It makes sense to add it for sev as well.

diff --git a/arch/x86/realmode/rm/trampoline_64.S
b/arch/x86/realmode/rm/trampoline_64.S
index e38d61d6562e..3a724d8d85b9 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -38,6 +38,25 @@
.code16

.balign PAGE_SIZE
+
+.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
+
SYM_CODE_START(trampoline_start)
cli # We should be safe anyway
wbinvd
@@ -49,8 +68,7 @@ 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 +111,7 @@ 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 +194,7 @@ 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