* [PATCH v11 01/12] x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 02/12] cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h> Usama Arif
` (10 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
Each of the sibling CPUs in a cluster uses the same clustermask. The first
CPU in a cluster will need a new clustermask allocated, while subsequent
siblings will use the same clustermask as the first.
However, the CPU being brought up cannot yet perform memory allocations
at the point that this occurs in init_x2apic_ldr().
So at present, the alloc_clustermask() function allocates a clustermask
just in case it's needed, storing it in the global cluster_hotplug_mask.
A CPU which is the first sibling of a cluster will "take" it from there
and set cluster_hotplug_mask to NULL, in order for alloc_clustermask()
to allocate a new one before bringing up the next CPU.
To facilitate parallel bringup of CPUs in future, switch to a model
where alloc_clustermask() prepopulates the clustermask in the per_cpu
data for each present CPU in the cluster in advance. All that the CPU
needs to do for itself in init_x2apic_ldr() is set its own bit in that
mask.
The 'node' and 'clusterid' members of struct cluster_mask are thus
redundant, and it can become a simple struct cpumask instead.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
arch/x86/kernel/apic/x2apic_cluster.c | 126 +++++++++++++++++---------
1 file changed, 82 insertions(+), 44 deletions(-)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index e696e22d0531..b2b2b7f3e03f 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -9,11 +9,7 @@
#include "local.h"
-struct cluster_mask {
- unsigned int clusterid;
- int node;
- struct cpumask mask;
-};
+#define apic_cluster(apicid) ((apicid) >> 4)
/*
* __x2apic_send_IPI_mask() possibly needs to read
@@ -23,8 +19,7 @@ struct cluster_mask {
static u32 *x86_cpu_to_logical_apicid __read_mostly;
static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
-static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks);
-static struct cluster_mask *cluster_hotplug_mask;
+static DEFINE_PER_CPU_READ_MOSTLY(struct cpumask *, cluster_masks);
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
@@ -60,10 +55,10 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
/* Collapse cpus in a cluster so a single IPI per cluster is sent */
for_each_cpu(cpu, tmpmsk) {
- struct cluster_mask *cmsk = per_cpu(cluster_masks, cpu);
+ struct cpumask *cmsk = per_cpu(cluster_masks, cpu);
dest = 0;
- for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask)
+ for_each_cpu_and(clustercpu, tmpmsk, cmsk)
dest |= x86_cpu_to_logical_apicid[clustercpu];
if (!dest)
@@ -71,7 +66,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
/* Remove cluster CPUs from tmpmask */
- cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask);
+ cpumask_andnot(tmpmsk, tmpmsk, cmsk);
}
local_irq_restore(flags);
@@ -105,55 +100,98 @@ static u32 x2apic_calc_apicid(unsigned int cpu)
static void init_x2apic_ldr(void)
{
- struct cluster_mask *cmsk = this_cpu_read(cluster_masks);
- u32 cluster, apicid = apic_read(APIC_LDR);
- unsigned int cpu;
+ struct cpumask *cmsk = this_cpu_read(cluster_masks);
- x86_cpu_to_logical_apicid[smp_processor_id()] = apicid;
+ BUG_ON(!cmsk);
- if (cmsk)
- goto update;
-
- cluster = apicid >> 16;
- for_each_online_cpu(cpu) {
- cmsk = per_cpu(cluster_masks, cpu);
- /* Matching cluster found. Link and update it. */
- if (cmsk && cmsk->clusterid == cluster)
- goto update;
+ cpumask_set_cpu(smp_processor_id(), cmsk);
+}
+
+/*
+ * As an optimisation during boot, set the cluster_mask for all present
+ * CPUs at once, to prevent each of them having to iterate over the others
+ * to find the existing cluster_mask.
+ */
+static void prefill_clustermask(struct cpumask *cmsk, unsigned int cpu, u32 cluster)
+{
+ int cpu_i;
+
+ for_each_present_cpu(cpu_i) {
+ struct cpumask **cpu_cmsk = &per_cpu(cluster_masks, cpu_i);
+ u32 apicid = apic->cpu_present_to_apicid(cpu_i);
+
+ if (apicid == BAD_APICID || cpu_i == cpu || apic_cluster(apicid) != cluster)
+ continue;
+
+ if (WARN_ON_ONCE(*cpu_cmsk == cmsk))
+ continue;
+
+ BUG_ON(*cpu_cmsk);
+ *cpu_cmsk = cmsk;
}
- cmsk = cluster_hotplug_mask;
- cmsk->clusterid = cluster;
- cluster_hotplug_mask = NULL;
-update:
- this_cpu_write(cluster_masks, cmsk);
- cpumask_set_cpu(smp_processor_id(), &cmsk->mask);
}
-static int alloc_clustermask(unsigned int cpu, int node)
+static int alloc_clustermask(unsigned int cpu, u32 cluster, int node)
{
+ struct cpumask *cmsk = NULL;
+ unsigned int cpu_i;
+
+ /*
+ * At boot time, the CPU present mask is stable. The cluster mask is
+ * allocated for the first CPU in the cluster and propagated to all
+ * present siblings in the cluster. If the cluster mask is already set
+ * on entry to this function for a given CPU, there is nothing to do.
+ */
if (per_cpu(cluster_masks, cpu))
return 0;
+
+ if (system_state < SYSTEM_RUNNING)
+ goto alloc;
+
/*
- * If a hotplug spare mask exists, check whether it's on the right
- * node. If not, free it and allocate a new one.
+ * On post boot hotplug for a CPU which was not present at boot time,
+ * iterate over all possible CPUs (even those which are not present
+ * any more) to find any existing cluster mask.
*/
- if (cluster_hotplug_mask) {
- if (cluster_hotplug_mask->node == node)
- return 0;
- kfree(cluster_hotplug_mask);
+ for_each_possible_cpu(cpu_i) {
+ u32 apicid = apic->cpu_present_to_apicid(cpu_i);
+
+ if (apicid != BAD_APICID && apic_cluster(apicid) == cluster) {
+ cmsk = per_cpu(cluster_masks, cpu_i);
+ /*
+ * If the cluster is already initialized, just store
+ * the mask and return. There's no need to propagate.
+ */
+ if (cmsk) {
+ per_cpu(cluster_masks, cpu) = cmsk;
+ return 0;
+ }
+ }
}
-
- cluster_hotplug_mask = kzalloc_node(sizeof(*cluster_hotplug_mask),
- GFP_KERNEL, node);
- if (!cluster_hotplug_mask)
+ /*
+ * No CPU in the cluster has ever been initialized, so fall through to
+ * the boot time code which will also populate the cluster mask for any
+ * other CPU in the cluster which is (now) present.
+ */
+alloc:
+ cmsk = kzalloc_node(sizeof(*cmsk), GFP_KERNEL, node);
+ if (!cmsk)
return -ENOMEM;
- cluster_hotplug_mask->node = node;
+ per_cpu(cluster_masks, cpu) = cmsk;
+ prefill_clustermask(cmsk, cpu, cluster);
+
return 0;
}
static int x2apic_prepare_cpu(unsigned int cpu)
{
- if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0)
+ u32 phys_apicid = apic->cpu_present_to_apicid(cpu);
+ u32 cluster = apic_cluster(phys_apicid);
+ u32 logical_apicid = (cluster << 16) | (1 << (phys_apicid & 0xf));
+
+ x86_cpu_to_logical_apicid[cpu] = logical_apicid;
+
+ if (alloc_clustermask(cpu, cluster, cpu_to_node(cpu)) < 0)
return -ENOMEM;
if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL))
return -ENOMEM;
@@ -162,10 +200,10 @@ static int x2apic_prepare_cpu(unsigned int cpu)
static int x2apic_dead_cpu(unsigned int dead_cpu)
{
- struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
+ struct cpumask *cmsk = per_cpu(cluster_masks, dead_cpu);
if (cmsk)
- cpumask_clear_cpu(dead_cpu, &cmsk->mask);
+ cpumask_clear_cpu(dead_cpu, cmsk);
free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
return 0;
}
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 02/12] cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h>
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
2023-02-23 19:11 ` [PATCH v11 01/12] x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 03/12] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU Usama Arif
` (9 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
Instead of relying purely on the special-case wrapper in bringup_cpu()
to pass the idle thread to __cpu_up(), expose idle_thread_get() so that
the architecture code can obtain it directly when necessary.
This will be useful when the existing __cpu_up() is split into multiple
phases, only *one* of which will actually need the idle thread.
If the architecture code is to register its new pre-bringup states with
the cpuhp core, having a special-case wrapper to pass extra arguments is
non-trivial and it's easier just to let the arch register its function
pointer to be invoked with the standard API.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
include/linux/smpboot.h | 7 +++++++
kernel/smpboot.h | 2 --
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index 9d1bc65d226c..3862addcaa34 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -5,6 +5,13 @@
#include <linux/types.h>
struct task_struct;
+
+#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
+struct task_struct *idle_thread_get(unsigned int cpu);
+#else
+static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; }
+#endif
+
/* Cookie handed to the thread_fn*/
struct smpboot_thread_data;
diff --git a/kernel/smpboot.h b/kernel/smpboot.h
index 34dd3d7ba40b..60c609318ad6 100644
--- a/kernel/smpboot.h
+++ b/kernel/smpboot.h
@@ -5,11 +5,9 @@
struct task_struct;
#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
-struct task_struct *idle_thread_get(unsigned int cpu);
void idle_thread_set_boot_cpu(void);
void idle_threads_init(void);
#else
-static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; }
static inline void idle_thread_set_boot_cpu(void) { }
static inline void idle_threads_init(void) { }
#endif
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 03/12] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
2023-02-23 19:11 ` [PATCH v11 01/12] x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel Usama Arif
2023-02-23 19:11 ` [PATCH v11 02/12] cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h> Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 04/12] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector() Usama Arif
` (8 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
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
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 04/12] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector()
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (2 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 03/12] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 05/12] x86/smpboot: Split up native_cpu_up into separate phases and document them Usama Arif
` (7 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
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
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 05/12] x86/smpboot: Split up native_cpu_up into separate phases and document them
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (3 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 04/12] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector() Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 06/12] x86/smpboot: Support parallel startup of secondary CPUs Usama Arif
` (6 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
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
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 06/12] x86/smpboot: Support parallel startup of secondary CPUs
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (4 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 05/12] x86/smpboot: Split up native_cpu_up into separate phases and document them Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 07/12] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel Usama Arif
` (5 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <tglx@linutronix.de>
Co-developed-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
.../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/asm-offsets.c | 1 +
arch/x86/kernel/head_64.S | 98 ++++++++++++++++++-
arch/x86/kernel/smpboot.c | 62 +++++++++++-
arch/x86/realmode/init.c | 3 +
arch/x86/realmode/rm/trampoline_64.S | 14 +++
10 files changed, 196 insertions(+), 7 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/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 82c783da16a8..797ae1a15c91 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -108,6 +108,7 @@ static void __used common(void)
OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
+ OFFSET(X86_current_task, pcpu_hot, current_task);
#ifdef CONFIG_CALL_DEPTH_TRACKING
OFFSET(X86_call_depth, pcpu_hot, call_depth);
#endif
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 222efd4a09bc..c32e5b06a9ce 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 +242,85 @@ 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
+
+ /*
+ * 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_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 CPU# 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
+ movl %edx, %ecx
+ jmp .Linit_cpu_data
+
+.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 pcpu_hot + X86_current_task(%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 +361,14 @@ 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 +460,11 @@ SYM_CODE_END(secondary_startup_64)
SYM_CODE_START(start_cpu0)
ANNOTATE_NOENDBR
UNWIND_HINT_EMPTY
- movq initial_stack(%rip), %rsp
+
+ /* Find the idle task stack */
+ movq PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx
+ movq TASK_threadsp(%rcx), %rsp
+
jmp .Ljump_to_C_code
SYM_CODE_END(start_cpu0)
#endif
@@ -426,6 +518,7 @@ 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 +753,9 @@ 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..74c76c78f7d2 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 | cpu;
+ }
/* 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"
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 07/12] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (5 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 06/12] x86/smpboot: Support parallel startup of secondary CPUs Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-24 18:46 ` Michael Kelley (LINUX)
2023-02-23 19:11 ` [PATCH v11 08/12] x86/smpboot: Serialize topology updates for secondary bringup Usama Arif
` (4 subsequent siblings)
11 siblings, 1 reply; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
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 74c76c78f7d2..85ce6a8978ff 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
^ permalink raw reply related [flat|nested] 17+ messages in thread* RE: [PATCH v11 07/12] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel
2023-02-23 19:11 ` [PATCH v11 07/12] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel Usama Arif
@ 2023-02-24 18:46 ` Michael Kelley (LINUX)
0 siblings, 0 replies; 17+ messages in thread
From: Michael Kelley (LINUX) @ 2023-02-24 18:46 UTC (permalink / raw)
To: Usama Arif, dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse
From: Usama Arif <usama.arif@bytedance.com> Sent: Thursday, February 23, 2023 11:12 AM
>
> From: David Woodhouse <dwmw@amazon.co.uk>
>
> 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.
I built and tested this series in a Hyper-V VM with 64 vCPUs running
on an AMD EPYC "Milan" processor. The VM has an xapic, not an x2apic.
The patch set works correctly, with and without the no_parallel_bringup
kernel boot option. In a running Linux instance, I was looking for a way to
confirm whether it used parallel bringup. I could only find checking for the
"x86/cpu:kick" state in /sys/devices/system/cpu/hotplug/states. Always
outputting a boot message to indicate the approach might be helpful.
Interestingly, I found no reduction in elapsed time to bring up the 64 vCPUs.
Depending on exactly where you measure, it is 80 to 90 milliseconds
before applying the patch set, and after applying the patch set (with or
without no_parallel_bringup). Evidently, VMs already avoid a good
part of the overhead in the existing serialized approach.
[ 1.503699] smp: Bringing up secondary CPUs ...
[ 1.507339] x86: Booting SMP configuration:
[ 1.511192] .... 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 #24 #25 #26 #27 #28 #29
#30 #31 #32 #33 #34 #35 #36 #37 #38 #39 #40 #41 #42 #43 #44 #45 #46 #47
#48 #49 #50 #51 #52 #53 #54 #55 #56 #57 #58 #59 #60 #61 #62 #63
[ 1.588039] smp: Brought up 1 node, 64 CPUs
[ 1.595513] smpboot: Max logical packages: 1
[ 1.599186] smpboot: Total of 64 processors activated (255524.22 BogoMIPS)
The "x86/cpu:kick" state was present for the parallel bringup case, so
presumably the parallel behavior *did* happen, unless there is later
bailout path that I missed. But there weren't any boot messages
indicating such.
Michael
For the series, on Hyper-V guests:
Tested-by: Michael Kelley <mikelley@microsoft.com>
>
> 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 <dwmw@amazon.co.uk>
> Signed-off-by: Usama Arif <usama.arif@bytedance.com>
> Tested-by: Paul E. McKenney <paulmck@kernel.org>
> Tested-by: Kim Phillips <kim.phillips@amd.com>
> Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
> ---
> 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 74c76c78f7d2..85ce6a8978ff 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
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH v11 08/12] x86/smpboot: Serialize topology updates for secondary bringup
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (6 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 07/12] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit Usama Arif
` (3 subsequent siblings)
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: David Woodhouse <dwmw@amazon.co.uk>
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 <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
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 85ce6a8978ff..69ef0860feea 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
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (7 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 08/12] x86/smpboot: Serialize topology updates for secondary bringup Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-24 18:24 ` Michael Kelley (LINUX)
2023-02-23 19:11 ` [PATCH v11 10/12] x86/smpboot: Remove early_gdt_descr " Usama Arif
` (2 subsequent siblings)
11 siblings, 1 reply; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: Brian Gerst <brgerst@gmail.com>
Load RSP from current_task->thread.sp instead.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Usama Arif <usama.arif@bytedance.com>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
---
arch/x86/include/asm/processor.h | 6 +++++-
arch/x86/kernel/acpi/sleep.c | 2 +-
arch/x86/kernel/head_64.S | 35 ++++++++++++++++++--------------
arch/x86/xen/xen-head.S | 2 +-
4 files changed, 27 insertions(+), 18 deletions(-)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4e35c66edeb7..9c4a5c4d46c1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -648,7 +648,11 @@ static inline void spin_lock_prefetch(const void *x)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
-#define INIT_THREAD { }
+extern unsigned long __end_init_task[];
+
+#define INIT_THREAD { \
+ .sp = (unsigned long)&__end_init_task - PTREGS_SIZE, \
+}
extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 47e75c056cb5..008fda8b1982 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -113,7 +113,7 @@ int x86_acpi_suspend_lowlevel(void)
saved_magic = 0x12345678;
#else /* CONFIG_64BIT */
#ifdef CONFIG_SMP
- initial_stack = (unsigned long)temp_stack + sizeof(temp_stack);
+ current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_rw(smp_processor_id());
initial_gs = per_cpu_offset(smp_processor_id());
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index c32e5b06a9ce..f7905ba4b992 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -62,8 +62,8 @@ SYM_CODE_START_NOALIGN(startup_64)
* tables and then reload them.
*/
- /* Set up the stack for verify_cpu(), similar to initial_stack below */
- leaq (__end_init_task - FRAME_SIZE)(%rip), %rsp
+ /* Set up the stack for verify_cpu() */
+ leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp
leaq _text(%rip), %rdi
@@ -245,11 +245,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
#ifdef CONFIG_SMP
/*
* Is this the boot CPU coming up? If so everything is available
- * in initial_gs, initial_stack and early_gdt_descr.
+ * in initial_gs and early_gdt_descr.
*/
movl smpboot_control(%rip), %edx
testl $STARTUP_SECONDARY, %edx
- jz .Lsetup_cpu
+ jz .Linit_cpu0_data
/*
* For parallel boot, the APIC ID is retrieved from CPUID, and then
@@ -302,6 +302,10 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
hlt
jmp 1b
+.Linit_cpu0_data:
+ movq __per_cpu_offset(%rip), %rdx
+ jmp .Lsetup_cpu
+
.Linit_cpu_data:
/* Get the per cpu offset for the given CPU# which is in ECX */
leaq __per_cpu_offset(%rip), %rbx
@@ -314,13 +318,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
addq %rbx, %rcx
movq %rcx, early_gdt_descr_base(%rip)
- /* Find the idle task stack */
- movq pcpu_hot + X86_current_task(%rbx), %rcx
- movq TASK_threadsp(%rcx), %rcx
- movq %rcx, initial_stack(%rip)
+ movq %rbx, %rdx
+#else
+ xorl %edx, %edx
#endif /* CONFIG_SMP */
.Lsetup_cpu:
+ /*
+ * Setup a boot time stack - Any secondary CPU will have lost its stack
+ * by now because the cr3-switch above unmaps the real-mode stack
+ *
+ * RDX contains the per-cpu offset
+ */
+ movq pcpu_hot + X86_current_task(%rdx), %rax
+ movq TASK_threadsp(%rax), %rsp
+
/*
* 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
@@ -355,12 +367,6 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
movl initial_gs+4(%rip),%edx
wrmsr
- /*
- * Setup a boot time stack - Any secondary CPU will have lost its stack
- * by now because the cr3-switch above unmaps the real-mode stack
- */
- 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
@@ -517,7 +523,6 @@ SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb)
* The FRAME_SIZE gap is a convention which helps the in-kernel unwinder
* 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
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index ffaa62167f6e..6bd391476656 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen)
ANNOTATE_NOENDBR
cld
- mov initial_stack(%rip), %rsp
+ leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp
/* Set up %gs.
*
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* RE: [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit
2023-02-23 19:11 ` [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit Usama Arif
@ 2023-02-24 18:24 ` Michael Kelley (LINUX)
2023-02-24 18:28 ` David Woodhouse
0 siblings, 1 reply; 17+ messages in thread
From: Michael Kelley (LINUX) @ 2023-02-24 18:24 UTC (permalink / raw)
To: Usama Arif, dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse
From: Usama Arif <usama.arif@bytedance.com> Sent: Thursday, February 23, 2023 11:12 AM
>
> From: Brian Gerst <brgerst@gmail.com>
>
> Load RSP from current_task->thread.sp instead.
>
> Signed-off-by: Brian Gerst <brgerst@gmail.com>
> Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
> Tested-by: Usama Arif <usama.arif@bytedance.com>
> Signed-off-by: Usama Arif <usama.arif@bytedance.com>
> ---
> arch/x86/include/asm/processor.h | 6 +++++-
> arch/x86/kernel/acpi/sleep.c | 2 +-
> arch/x86/kernel/head_64.S | 35 ++++++++++++++++++--------------
> arch/x86/xen/xen-head.S | 2 +-
> 4 files changed, 27 insertions(+), 18 deletions(-)
>
> diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
> index 4e35c66edeb7..9c4a5c4d46c1 100644
> --- a/arch/x86/include/asm/processor.h
> +++ b/arch/x86/include/asm/processor.h
> @@ -648,7 +648,11 @@ static inline void spin_lock_prefetch(const void *x)
> #define KSTK_ESP(task) (task_pt_regs(task)->sp)
>
> #else
> -#define INIT_THREAD { }
> +extern unsigned long __end_init_task[];
> +
> +#define INIT_THREAD { \
> + .sp = (unsigned long)&__end_init_task - PTREGS_SIZE, \
> +}
I'm getting a compile error on the new reference to PTREGS_SIZE:
In file included from ./arch/x86/include/asm/cpufeature.h:5:0,
from ./arch/x86/include/asm/thread_info.h:53,
from ./include/linux/thread_info.h:60,
from ./arch/x86/include/asm/preempt.h:9,
from ./include/linux/preempt.h:78,
from ./include/linux/rcupdate.h:27,
from ./include/linux/init_task.h:5,
from init/init_task.c:2:
./arch/x86/include/asm/processor.h:654:42: error: 'PTREGS_SIZE' undeclared here (not in a function); did you mean 'TLS_SIZE'?
.sp = (unsigned long)&__end_init_task - PTREGS_SIZE, \
^
init/init_task.c:115:13: note: in expansion of macro 'INIT_THREAD'
.thread = INIT_THREAD,
^~~~~~~~~~~
scripts/Makefile.build:252: recipe for target 'init/init_task.o' failed
Michael
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit
2023-02-24 18:24 ` Michael Kelley (LINUX)
@ 2023-02-24 18:28 ` David Woodhouse
2023-02-24 19:17 ` [External] " Usama Arif
0 siblings, 1 reply; 17+ messages in thread
From: David Woodhouse @ 2023-02-24 18:28 UTC (permalink / raw)
To: Michael Kelley (LINUX), Usama Arif, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma
[-- Attachment #1: Type: text/plain, Size: 279 bytes --]
On Fri, 2023-02-24 at 18:24 +0000, Michael Kelley (LINUX) wrote:
> I'm getting a compile error on the new reference to PTREGS_SIZE:
Is it just that <asm/asm-offsets.h> is included conditionally, and not
in your build? What if you include it directly from <asm/processor.h>
[-- Attachment #2: smime.p7s --]
[-- Type: application/pkcs7-signature, Size: 5965 bytes --]
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [External] Re: [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit
2023-02-24 18:28 ` David Woodhouse
@ 2023-02-24 19:17 ` Usama Arif
0 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-24 19:17 UTC (permalink / raw)
To: David Woodhouse, Michael Kelley (LINUX), tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma
On 24/02/2023 18:28, David Woodhouse wrote:
> On Fri, 2023-02-24 at 18:24 +0000, Michael Kelley (LINUX) wrote:
>> I'm getting a compile error on the new reference to PTREGS_SIZE:
>
> Is it just that <asm/asm-offsets.h> is included conditionally, and not
> in your build? What if you include it directly from <asm/processor.h>
This is fixed in the v2 patch that Brian sent.
diff --git a/arch/x86/include/asm/processor.h
b/arch/x86/include/asm/processor.h
index 9c4a5c4d46c1..bdde7316e75b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -650,8 +650,8 @@ static inline void spin_lock_prefetch(const void *x)
#else
extern unsigned long __end_init_task[];
-#define INIT_THREAD { \
- .sp = (unsigned long)&__end_init_task - PTREGS_SIZE, \
+#define INIT_THREAD {
\
+ .sp = (unsigned long)&__end_init_task - sizeof(struct
pt_regs), \
}
extern unsigned long KSTK_ESP(struct task_struct *task);
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [PATCH v11 10/12] x86/smpboot: Remove early_gdt_descr on 64-bit
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (8 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 09/12] x86/smpboot: Remove initial_stack on 64-bit Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 11/12] x86/smpboot: Remove initial_gs Usama Arif
2023-02-23 19:11 ` [PATCH v11 12/12] x86/smpboot: Simplify boot CPU setup Usama Arif
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: Brian Gerst <brgerst@gmail.com>
Build the GDT descriptor on the stack instead.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Usama Arif <usama.arif@bytedance.com>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
---
arch/x86/kernel/acpi/sleep.c | 2 --
arch/x86/kernel/head_64.S | 19 +++++++------------
2 files changed, 7 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 008fda8b1982..6538ddb55f28 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -114,8 +114,6 @@ int x86_acpi_suspend_lowlevel(void)
#else /* CONFIG_64BIT */
#ifdef CONFIG_SMP
current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
- 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);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index f7905ba4b992..0dd57d573a0e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -245,7 +245,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
#ifdef CONFIG_SMP
/*
* Is this the boot CPU coming up? If so everything is available
- * in initial_gs and early_gdt_descr.
+ * in initial_gs.
*/
movl smpboot_control(%rip), %edx
testl $STARTUP_SECONDARY, %edx
@@ -313,11 +313,6 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
/* 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)
-
movq %rbx, %rdx
#else
xorl %edx, %edx
@@ -339,7 +334,12 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
* addresses where we're currently running on. We have to do that here
* because in 32bit we couldn't load a 64bit linear address.
*/
- lgdt early_gdt_descr(%rip)
+ subq $16, %rsp
+ movw $(GDT_SIZE-1), (%rsp)
+ leaq gdt_page(%rdx), %rax
+ movq %rax, 2(%rsp)
+ lgdt (%rsp)
+ addq $16, %rsp
/* set up data segments */
xorl %eax,%eax
@@ -754,11 +754,6 @@ SYM_DATA_END(level1_fixmap_pgt)
.data
.align 16
-
-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
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 11/12] x86/smpboot: Remove initial_gs
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (9 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 10/12] x86/smpboot: Remove early_gdt_descr " Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
2023-02-23 19:11 ` [PATCH v11 12/12] x86/smpboot: Simplify boot CPU setup Usama Arif
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: Brian Gerst <brgerst@gmail.com>
Use the percpu offset directly to set GSBASE.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Usama Arif <usama.arif@bytedance.com>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
---
arch/x86/include/asm/realmode.h | 1 -
arch/x86/kernel/acpi/sleep.c | 1 -
arch/x86/kernel/head_64.S | 34 ++++++++++-----------------------
3 files changed, 10 insertions(+), 26 deletions(-)
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index f0357cfe2fb0..87e5482acd0d 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -60,7 +60,6 @@ extern struct real_mode_header *real_mode_header;
extern unsigned char real_mode_blob_end[];
extern unsigned long initial_code;
-extern unsigned long initial_gs;
extern unsigned long initial_stack;
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern unsigned long initial_vc_handler;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 6538ddb55f28..214dd4a79860 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -114,7 +114,6 @@ int x86_acpi_suspend_lowlevel(void)
#else /* CONFIG_64BIT */
#ifdef CONFIG_SMP
current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
- initial_gs = per_cpu_offset(smp_processor_id());
/* Force the startup into boot mode */
saved_smpboot_ctrl = xchg(&smpboot_control, 0);
#endif
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0dd57d573a0e..9ed87ba0609f 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -67,18 +67,10 @@ SYM_CODE_START_NOALIGN(startup_64)
leaq _text(%rip), %rdi
- /*
- * initial_gs points to initial fixed_percpu_data struct with storage for
- * the stack protector canary. Global pointer fixups are needed at this
- * stage, so apply them as is done in fixup_pointer(), and initialize %gs
- * such that the canary can be accessed at %gs:40 for subsequent C calls.
- */
+ /* Setup GSBASE to allow stack canary access for C code */
movl $MSR_GS_BASE, %ecx
- movq initial_gs(%rip), %rax
- movq $_text, %rdx
- subq %rdx, %rax
- addq %rdi, %rax
- movq %rax, %rdx
+ leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+ movl %edx, %eax
shrq $32, %rdx
wrmsr
@@ -243,10 +235,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
ANNOTATE_NOENDBR // above
#ifdef CONFIG_SMP
- /*
- * Is this the boot CPU coming up? If so everything is available
- * in initial_gs.
- */
+ /* Is this the boot CPU coming up? */
movl smpboot_control(%rip), %edx
testl $STARTUP_SECONDARY, %edx
jz .Linit_cpu0_data
@@ -308,12 +297,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
.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)
-
- movq %rbx, %rdx
+ movq __per_cpu_offset(,%rcx,8), %rdx
#else
xorl %edx, %edx
#endif /* CONFIG_SMP */
@@ -363,8 +347,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
* the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
- movl initial_gs(%rip),%eax
- movl initial_gs+4(%rip),%edx
+#ifndef CONFIG_SMP
+ leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+#endif
+ movl %edx, %eax
+ shrq $32, %rdx
wrmsr
/* Drop the realmode protection. For the boot CPU the pointer is NULL! */
@@ -514,7 +501,6 @@ SYM_CODE_END(vc_boot_ghcb)
__REFDATA
.balign 8
SYM_DATA(initial_code, .quad x86_64_start_kernel)
-SYM_DATA(initial_gs, .quad INIT_PER_CPU_VAR(fixed_percpu_data))
#ifdef CONFIG_AMD_MEM_ENCRYPT
SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb)
#endif
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v11 12/12] x86/smpboot: Simplify boot CPU setup
2023-02-23 19:11 [PATCH v11 00/12] Parallel CPU bringup for x86_64 Usama Arif
` (10 preceding siblings ...)
2023-02-23 19:11 ` [PATCH v11 11/12] x86/smpboot: Remove initial_gs Usama Arif
@ 2023-02-23 19:11 ` Usama Arif
11 siblings, 0 replies; 17+ messages in thread
From: Usama Arif @ 2023-02-23 19:11 UTC (permalink / raw)
To: dwmw2, tglx, kim.phillips, brgerst
Cc: piotrgorski, oleksandr, arjan, mingo, bp, dave.hansen, hpa, x86,
pbonzini, paulmck, linux-kernel, kvm, rcu, mimoja, hewenliang4,
thomas.lendacky, seanjc, pmenzel, fam.zheng, punit.agrawal,
simon.evans, liangma, David Woodhouse, Usama Arif
From: Brian Gerst <brgerst@gmail.com>
Now that the per-cpu GSBASE, stack, and GDT descriptor can be derived
dynamically by CPU number, the boot CPU can use a fixed CPU number and
take the same path as secondary CPUs.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Usama Arif <usama.arif@bytedance.com>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
---
arch/x86/include/asm/smp.h | 5 ++---
arch/x86/kernel/head_64.S | 25 +++++++------------------
arch/x86/kernel/smpboot.c | 6 +++---
3 files changed, 12 insertions(+), 24 deletions(-)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index b4b29e052b6e..97a36d029b0e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -202,8 +202,7 @@ 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
+#define STARTUP_APICID_CPUID_0B 0x80000000
+#define STARTUP_APICID_CPUID_01 0x40000000
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 9ed87ba0609f..949c13b26811 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -235,28 +235,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
ANNOTATE_NOENDBR // above
#ifdef CONFIG_SMP
- /* Is this the boot CPU coming up? */
- movl smpboot_control(%rip), %edx
- testl $STARTUP_SECONDARY, %edx
- jz .Linit_cpu0_data
-
/*
* 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_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 CPU# if STARTUP_APICID_CPUID_xx flags are not set
*/
- testl $STARTUP_APICID_CPUID_0B, %edx
+ movl smpboot_control(%rip), %ecx
+ testl $STARTUP_APICID_CPUID_0B, %ecx
jnz .Luse_cpuid_0b
- testl $STARTUP_APICID_CPUID_01, %edx
+ testl $STARTUP_APICID_CPUID_01, %ecx
jnz .Luse_cpuid_01
- andl $0x0FFFFFFF, %edx
- movl %edx, %ecx
- jmp .Linit_cpu_data
+ andl $0x0FFFFFFF, %ecx
+ jmp .Lsetup_cpu
.Luse_cpuid_01:
mov $0x01, %eax
@@ -277,7 +271,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
.Lfind_cpunr:
cmpl (%rbx,%rcx,4), %edx
- jz .Linit_cpu_data
+ jz .Lsetup_cpu
inc %ecx
cmpl nr_cpu_ids(%rip), %ecx
jb .Lfind_cpunr
@@ -291,18 +285,13 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
hlt
jmp 1b
-.Linit_cpu0_data:
- movq __per_cpu_offset(%rip), %rdx
- jmp .Lsetup_cpu
-
-.Linit_cpu_data:
+.Lsetup_cpu:
/* Get the per cpu offset for the given CPU# which is in ECX */
movq __per_cpu_offset(,%rcx,8), %rdx
#else
xorl %edx, %edx
#endif /* CONFIG_SMP */
-.Lsetup_cpu:
/*
* Setup a boot time stack - Any secondary CPU will have lost its stack
* by now because the cr3-switch above unmaps the real-mode stack
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 69ef0860feea..9d956571ecc1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1140,7 +1140,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
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 | cpu;
+ smpboot_control = cpu;
}
/* Enable the espfix hack for this CPU */
@@ -1580,7 +1580,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
*/
if (eax) {
pr_debug("Using CPUID 0xb for parallel CPU startup\n");
- smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_0B;
+ smpboot_control = STARTUP_APICID_CPUID_0B;
} else {
pr_info("Disabling parallel bringup because CPUID 0xb looks untrustworthy\n");
do_parallel_bringup = false;
@@ -1588,7 +1588,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
} 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;
+ smpboot_control = STARTUP_APICID_CPUID_01;
}
if (do_parallel_bringup) {
--
2.25.1
^ permalink raw reply related [flat|nested] 17+ messages in thread