[PATCH 00/10] Introduce SMT level and add PowerPC support

[PATCH 00/10] Introduce SMT level and add PowerPC support

[Laurent Dufour]

I'm taking over the series Michael sent previously [1] which is smartly
reviewing the initial series I sent [2].  This series is addressing the
comments sent by Thomas and me on the Michael's one.

Here is a short introduction to the issue this series is addressing:

When a new CPU is added, the kernel is activating all its threads. This
leads to weird, but functional, result when adding CPU on a SMT 4 system
for instance.

Here the newly added CPU 1 has 8 threads while the other one has 4 threads
active (system has been booted with the 'smt-enabled=4' kernel option):

ltcden3-lp12:~ # ppc64_cpu --info
Core   0:    0*    1*    2*    3*    4     5     6     7
Core   1:    8*    9*   10*   11*   12*   13*   14*   15*

This mixed SMT level may confused end users and/or some applications.

There is no SMT level recorded in the kernel (common code), neither in user
space, as far as I know. Such a level is helpful when adding new CPU or
when optimizing the energy efficiency (when reactivating CPUs).

When SMP and HOTPLUG_SMT are defined, this series is adding a new SMT level
(cpu_smt_num_threads) and few callbacks allowing the architecture code to
fine control this value, setting a max and a "at boot" level, and
controling whether a thread should be onlined or not.

[1] https://lore.kernel.org/linuxppc-dev/20230524155630.794584-1-mpe@ellerman.id.au/
[2] https://lore.kernel.org/linuxppc-dev/20230331153905.31698-1-ldufour@linux.ibm.com/

Laurent Dufour (1):
  cpu/SMT: Remove topology_smt_supported()

Michael Ellerman (9):
  cpu/SMT: Move SMT prototypes into cpu_smt.h
  cpu/SMT: Move smt/control simple exit cases earlier
  cpu/SMT: Store the current/max number of threads
  cpu/SMT: Create topology_smt_threads_supported()
  cpu/SMT: Create topology_smt_thread_allowed()
  cpu/SMT: Allow enabling partial SMT states via sysfs
  powerpc/pseries: Initialise CPU hotplug callbacks earlier
  powerpc: Add HOTPLUG_SMT support
  powerpc/pseries: Honour current SMT state when DLPAR onlining CPUs

 .../ABI/testing/sysfs-devices-system-cpu      |  1 +
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/include/asm/topology.h           | 20 +++++
 arch/powerpc/kernel/smp.c                     |  8 +-
 arch/powerpc/platforms/pseries/hotplug-cpu.c  | 30 +++++--
 arch/powerpc/platforms/pseries/pseries.h      |  2 +
 arch/powerpc/platforms/pseries/setup.c        |  2 +
 arch/x86/include/asm/topology.h               |  8 +-
 arch/x86/kernel/cpu/bugs.c                    |  3 +-
 arch/x86/kernel/smpboot.c                     | 25 +++++-
 include/linux/cpu.h                           | 25 +-----
 include/linux/cpu_smt.h                       | 33 ++++++++
 kernel/cpu.c                                  | 83 +++++++++++++++----
 13 files changed, 187 insertions(+), 54 deletions(-)
 create mode 100644 include/linux/cpu_smt.h

-- 
2.41.0

[PATCH 01/10] cpu/SMT: Move SMT prototypes into cpu_smt.h

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

A subsequent patch would like to use the cpuhp_smt_control enum as part
of the interface between generic and arch code.

Currently that leads to circular header dependencies. So split the enum
and related declarations into a separate header.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/x86/include/asm/topology.h |  2 ++
 include/linux/cpu.h             | 25 +------------------------
 include/linux/cpu_smt.h         | 29 +++++++++++++++++++++++++++++
 kernel/cpu.c                    |  1 +
 4 files changed, 33 insertions(+), 24 deletions(-)
 create mode 100644 include/linux/cpu_smt.h

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 458c891a8273..66927a59e822 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -136,6 +136,8 @@ static inline int topology_max_smt_threads(void)
 	return __max_smt_threads;
 }
 
+#include <linux/cpu_smt.h>
+
 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);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8582a7142623..40548f3c201c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -18,6 +18,7 @@
 #include <linux/compiler.h>
 #include <linux/cpumask.h>
 #include <linux/cpuhotplug.h>
+#include <linux/cpu_smt.h>
 
 struct device;
 struct device_node;
@@ -202,30 +203,6 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
-enum cpuhp_smt_control {
-	CPU_SMT_ENABLED,
-	CPU_SMT_DISABLED,
-	CPU_SMT_FORCE_DISABLED,
-	CPU_SMT_NOT_SUPPORTED,
-	CPU_SMT_NOT_IMPLEMENTED,
-};
-
-#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
-extern enum cpuhp_smt_control cpu_smt_control;
-extern void cpu_smt_disable(bool force);
-extern void cpu_smt_check_topology(void);
-extern bool cpu_smt_possible(void);
-extern int cpuhp_smt_enable(void);
-extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval);
-#else
-# define cpu_smt_control		(CPU_SMT_NOT_IMPLEMENTED)
-static inline void cpu_smt_disable(bool force) { }
-static inline void cpu_smt_check_topology(void) { }
-static inline bool cpu_smt_possible(void) { return false; }
-static inline int cpuhp_smt_enable(void) { return 0; }
-static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
-#endif
-
 extern bool cpu_mitigations_off(void);
 extern bool cpu_mitigations_auto_nosmt(void);
 
diff --git a/include/linux/cpu_smt.h b/include/linux/cpu_smt.h
new file mode 100644
index 000000000000..722c2e306fef
--- /dev/null
+++ b/include/linux/cpu_smt.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CPU_SMT_H_
+#define _LINUX_CPU_SMT_H_
+
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+	CPU_SMT_NOT_IMPLEMENTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+extern void cpu_smt_disable(bool force);
+extern void cpu_smt_check_topology(void);
+extern bool cpu_smt_possible(void);
+extern int cpuhp_smt_enable(void);
+extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval);
+#else
+# define cpu_smt_control               (CPU_SMT_NOT_IMPLEMENTED)
+static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_check_topology(void) { }
+static inline bool cpu_smt_possible(void) { return false; }
+static inline int cpuhp_smt_enable(void) { return 0; }
+static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
+#endif
+
+#endif /* _LINUX_CPU_SMT_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f4a2c5845bcb..237394e0574a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -413,6 +413,7 @@ static void lockdep_release_cpus_lock(void)
 void __weak arch_smt_update(void) { }
 
 #ifdef CONFIG_HOTPLUG_SMT
+
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
 
 void __init cpu_smt_disable(bool force)
-- 
2.41.0

Re: [PATCH 01/10] cpu/SMT: Move SMT prototypes into cpu_smt.h

[Thomas Gleixner]

On Thu, Jun 15 2023 at 17:46, Laurent Dufour wrote:
> From: Michael Ellerman <mpe@ellerman.id.au>
>
> A subsequent patch would like to use the cpuhp_smt_control enum as part
> of the interface between generic and arch code.

This still has the 'patch' and 'arch' style which I pointed out
before. It seems you fixed it only for one patch in the series.

Thanks,

        tglx

[PATCH 02/10] cpu/SMT: Move smt/control simple exit cases earlier

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

Move the simple exit cases, ie. which don't depend on the value written,
earlier in the function. That makes it clearer that regardless of the
input those states can not be transitioned out of.

That does have a user-visible effect, in that the error returned will
now always be EPERM/ENODEV for those states, regardless of the value
written. Previously writing an invalid value would return EINVAL even
when in those states.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 kernel/cpu.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 237394e0574a..c67049bb3fc8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2482,6 +2482,12 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
 {
 	int ctrlval, ret;
 
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+		return -EPERM;
+
+	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return -ENODEV;
+
 	if (sysfs_streq(buf, "on"))
 		ctrlval = CPU_SMT_ENABLED;
 	else if (sysfs_streq(buf, "off"))
@@ -2491,12 +2497,6 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
 	else
 		return -EINVAL;
 
-	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
-		return -EPERM;
-
-	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
-		return -ENODEV;
-
 	ret = lock_device_hotplug_sysfs();
 	if (ret)
 		return ret;
-- 
2.41.0

[PATCH 03/10] cpu/SMT: Store the current/max number of threads

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

Some architectures (ppc64) allows partial SMT states at boot time, ie. when
not all SMT threads are brought online.

To support that the SMT code needs to know the maximum number of SMT
threads, and also the currently configured number.

The architecture code knows the max number of threads, so have the
architecture code pass that value to cpu_smt_set_num_threads(). Note that
although topology_max_smt_threads() exists, it is not configured early
enough to be used here. As architecture, like PowerPC, allows the threads
number to be set through the kernel command line, also pass that value.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[ldufour: slightly reword the commit message]
[ldufour: rename cpu_smt_check_topology and add a num_threads argument]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
 arch/x86/kernel/cpu/bugs.c |  3 ++-
 include/linux/cpu_smt.h    |  8 ++++++--
 kernel/cpu.c               | 21 ++++++++++++++++++++-
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 182af64387d0..ed71ad385ea7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,6 +34,7 @@
 #include <asm/hypervisor.h>
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
+#include <asm/smp.h>
 
 #include "cpu.h"
 
@@ -133,7 +134,7 @@ void __init check_bugs(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology();
+	cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings);
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
diff --git a/include/linux/cpu_smt.h b/include/linux/cpu_smt.h
index 722c2e306fef..0c1664294b57 100644
--- a/include/linux/cpu_smt.h
+++ b/include/linux/cpu_smt.h
@@ -12,15 +12,19 @@ enum cpuhp_smt_control {
 
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
 extern enum cpuhp_smt_control cpu_smt_control;
+extern unsigned int cpu_smt_num_threads;
 extern void cpu_smt_disable(bool force);
-extern void cpu_smt_check_topology(void);
+extern void cpu_smt_set_num_threads(unsigned int num_threads,
+				    unsigned int max_threads);
 extern bool cpu_smt_possible(void);
 extern int cpuhp_smt_enable(void);
 extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval);
 #else
 # define cpu_smt_control               (CPU_SMT_NOT_IMPLEMENTED)
+# define cpu_smt_num_threads 1
 static inline void cpu_smt_disable(bool force) { }
-static inline void cpu_smt_check_topology(void) { }
+static inline void cpu_smt_set_num_threads(unsigned int num_threads,
+					   unsigned int max_threads) { }
 static inline bool cpu_smt_possible(void) { return false; }
 static inline int cpuhp_smt_enable(void) { return 0; }
 static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
diff --git a/kernel/cpu.c b/kernel/cpu.c
index c67049bb3fc8..edca8b7bd400 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -415,6 +415,8 @@ void __weak arch_smt_update(void) { }
 #ifdef CONFIG_HOTPLUG_SMT
 
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+static unsigned int cpu_smt_max_threads __ro_after_init;
+unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX;
 
 void __init cpu_smt_disable(bool force)
 {
@@ -428,16 +430,33 @@ void __init cpu_smt_disable(bool force)
 		pr_info("SMT: disabled\n");
 		cpu_smt_control = CPU_SMT_DISABLED;
 	}
+	cpu_smt_num_threads = 1;
 }
 
 /*
  * The decision whether SMT is supported can only be done after the full
  * CPU identification. Called from architecture code.
  */
-void __init cpu_smt_check_topology(void)
+void __init cpu_smt_set_num_threads(unsigned int num_threads,
+				    unsigned int max_threads)
 {
+	WARN_ON(!num_threads || (num_threads > max_threads));
+
 	if (!topology_smt_supported())
 		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
+	cpu_smt_max_threads = max_threads;
+
+	/*
+	 * If SMT has been disabled via the kernel command line or SMT is
+	 * not supported, set cpu_smt_num_threads to 1 for consistency.
+	 * If enabled, take the architecture requested number of threads
+	 * to bring up into account.
+	 */
+	if (cpu_smt_control != CPU_SMT_ENABLED)
+		cpu_smt_num_threads = 1;
+	else if (num_threads < cpu_smt_num_threads)
+		cpu_smt_num_threads = num_threads;
 }
 
 static int __init smt_cmdline_disable(char *str)
-- 
2.41.0

[PATCH 04/10] cpu/SMT: Remove topology_smt_supported()

[Laurent Dufour]

Since the maximum number of threads is now passed to
cpu_smt_set_num_threads(), checking that value is enough to know if SMT is
supported.

Cc: Michael Ellerman <mpe@ellerman.id.au>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
 arch/x86/include/asm/topology.h | 2 --
 arch/x86/kernel/smpboot.c       | 8 --------
 kernel/cpu.c                    | 2 +-
 3 files changed, 1 insertion(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 66927a59e822..87358a8fe843 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,7 +143,6 @@ 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);
-bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int
@@ -156,7 +155,6 @@ static inline int topology_phys_to_logical_die(unsigned int die,
 static inline int topology_max_die_per_package(void) { return 1; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
-static inline bool topology_smt_supported(void) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 352f0ce1ece4..3052c171668d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -278,14 +278,6 @@ bool topology_is_primary_thread(unsigned int cpu)
 	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
 }
 
-/**
- * topology_smt_supported - Check whether SMT is supported by the CPUs
- */
-bool topology_smt_supported(void)
-{
-	return smp_num_siblings > 1;
-}
-
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
diff --git a/kernel/cpu.c b/kernel/cpu.c
index edca8b7bd400..e354af92b2b8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -442,7 +442,7 @@ void __init cpu_smt_set_num_threads(unsigned int num_threads,
 {
 	WARN_ON(!num_threads || (num_threads > max_threads));
 
-	if (!topology_smt_supported())
+	if (max_threads == 1)
 		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
 
 	cpu_smt_max_threads = max_threads;
-- 
2.41.0

[PATCH 05/10] cpu/SMT: Create topology_smt_threads_supported()

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

A subsequent patch will enable partial SMT states, ie. when not all SMT
threads are brought online.

To support that, add an arch helper to check how many SMT threads are
supported.

To retain existing behaviour, the x86 implementation only allows a
single thread or all threads to be online.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/x86/include/asm/topology.h |  2 ++
 arch/x86/kernel/smpboot.c       | 12 ++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 87358a8fe843..232df5ffab34 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ 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);
+bool topology_smt_threads_supported(unsigned int threads);
 #else
 #define topology_max_packages()			(1)
 static inline int
@@ -155,6 +156,7 @@ static inline int topology_phys_to_logical_die(unsigned int die,
 static inline int topology_max_die_per_package(void) { return 1; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline bool topology_smt_threads_supported(unsigned int threads) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3052c171668d..d163ef55577b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -278,6 +278,18 @@ bool topology_is_primary_thread(unsigned int cpu)
 	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
 }
 
+/**
+ * topology_smt_threads_supported - Check if the given number of SMT threads
+ *				    is supported.
+ *
+ * @threads:	The number of SMT threads.
+ */
+bool topology_smt_threads_supported(unsigned int threads)
+{
+	// Only support a single thread or all threads.
+	return threads == 1 || threads == smp_num_siblings;
+}
+
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
-- 
2.41.0

[PATCH 06/10] cpu/SMT: Create topology_smt_thread_allowed()

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

A subsequent patch will enable partial SMT states, ie. when not all SMT
threads are brought online.

To support that, add an arch helper which checks whether a given CPU is
allowed to be brought online depending on how many SMT threads are
currently enabled.

Call the helper from cpu_smt_enable(), and cpu_smt_allowed() when SMT is
enabled, to check if the particular thread should be onlined. Notably,
also call it from cpu_smt_disable() if CPU_SMT_ENABLED, to allow
offlining some threads to move from a higher to lower number of threads
online.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/x86/include/asm/topology.h |  2 ++
 arch/x86/kernel/smpboot.c       | 15 +++++++++++++++
 kernel/cpu.c                    | 10 +++++++++-
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 232df5ffab34..4696d4566cb5 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -144,6 +144,7 @@ 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);
 bool topology_smt_threads_supported(unsigned int threads);
+bool topology_smt_thread_allowed(unsigned int cpu);
 #else
 #define topology_max_packages()			(1)
 static inline int
@@ -157,6 +158,7 @@ static inline int topology_max_die_per_package(void) { return 1; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 static inline bool topology_smt_threads_supported(unsigned int threads) { return false; }
+static inline bool topology_smt_thread_allowed(unsigned int cpu) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index d163ef55577b..cfae55c2d1b0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -290,6 +290,21 @@ bool topology_smt_threads_supported(unsigned int threads)
 	return threads == 1 || threads == smp_num_siblings;
 }
 
+/**
+ * topology_smt_thread_allowed - When enabling SMT check whether this particular
+ *				 CPU thread is allowed to be brought online.
+ * @cpu:	CPU to check
+ */
+bool topology_smt_thread_allowed(unsigned int cpu)
+{
+	/*
+	 * No extra logic s required here to support different thread values
+	 * because threads will always == 1 or smp_num_siblings because of
+	 * topology_smt_threads_supported().
+	 */
+	return true;
+}
+
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e354af92b2b8..ae2fa26a5b63 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -468,7 +468,7 @@ early_param("nosmt", smt_cmdline_disable);
 
 static inline bool cpu_smt_allowed(unsigned int cpu)
 {
-	if (cpu_smt_control == CPU_SMT_ENABLED)
+	if (cpu_smt_control == CPU_SMT_ENABLED && topology_smt_thread_allowed(cpu))
 		return true;
 
 	if (topology_is_primary_thread(cpu))
@@ -2283,6 +2283,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
 	for_each_online_cpu(cpu) {
 		if (topology_is_primary_thread(cpu))
 			continue;
+		/*
+		 * Disable can be called with CPU_SMT_ENABLED when changing
+		 * from a higher to lower number of SMT threads per core.
+		 */
+		if (ctrlval == CPU_SMT_ENABLED && topology_smt_thread_allowed(cpu))
+			continue;
 		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
 		if (ret)
 			break;
@@ -2317,6 +2323,8 @@ int cpuhp_smt_enable(void)
 		/* Skip online CPUs and CPUs on offline nodes */
 		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
 			continue;
+		if (!topology_smt_thread_allowed(cpu))
+			continue;
 		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
 		if (ret)
 			break;
-- 
2.41.0

[PATCH 07/10] cpu/SMT: Allow enabling partial SMT states via sysfs

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

Add support to the /sys/devices/system/cpu/smt/control interface for
enabling a specified number of SMT threads per core, including partial
SMT states where not all threads are brought online.

The current interface accepts "on" and "off", to enable either 1 or all
SMT threads per core.

This commit allows writing an integer, between 1 and the number of SMT
threads supported by the machine. Writing 1 is a synonym for "off", 2 or
more enables SMT with the specified number of threads.

When reading the file, if all threads are online "on" is returned, to
avoid changing behaviour for existing users. If some other number of
threads is online then the integer value is returned.

There is a hook which allows arch code to control how many threads per
core are supported. To retain the existing behaviour, the x86 hook only
supports 1 thread or all threads.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 .../ABI/testing/sysfs-devices-system-cpu      |  1 +
 kernel/cpu.c                                  | 39 ++++++++++++++++---
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index f54867cadb0f..3c4cfb59d495 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -555,6 +555,7 @@ Description:	Control Symmetric Multi Threading (SMT)
 			 ================ =========================================
 			 "on"		  SMT is enabled
 			 "off"		  SMT is disabled
+			 "<N>"		  SMT is enabled with N threads per core.
 			 "forceoff"	  SMT is force disabled. Cannot be changed.
 			 "notsupported"   SMT is not supported by the CPU
 			 "notimplemented" SMT runtime toggling is not
diff --git a/kernel/cpu.c b/kernel/cpu.c
index ae2fa26a5b63..248f0734098a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2507,7 +2507,7 @@ static ssize_t
 __store_smt_control(struct device *dev, struct device_attribute *attr,
 		    const char *buf, size_t count)
 {
-	int ctrlval, ret;
+	int ctrlval, ret, num_threads, orig_threads;
 
 	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
 		return -EPERM;
@@ -2515,20 +2515,38 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
 	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
 		return -ENODEV;
 
-	if (sysfs_streq(buf, "on"))
+	if (sysfs_streq(buf, "on")) {
 		ctrlval = CPU_SMT_ENABLED;
-	else if (sysfs_streq(buf, "off"))
+		num_threads = cpu_smt_max_threads;
+	} else if (sysfs_streq(buf, "off")) {
 		ctrlval = CPU_SMT_DISABLED;
-	else if (sysfs_streq(buf, "forceoff"))
+		num_threads = 1;
+	} else if (sysfs_streq(buf, "forceoff")) {
 		ctrlval = CPU_SMT_FORCE_DISABLED;
-	else
+		num_threads = 1;
+	} else if (kstrtoint(buf, 10, &num_threads) == 0) {
+		if (num_threads == 1)
+			ctrlval = CPU_SMT_DISABLED;
+		else if (num_threads > 1 && topology_smt_threads_supported(num_threads))
+			ctrlval = CPU_SMT_ENABLED;
+		else
+			return -EINVAL;
+	} else {
 		return -EINVAL;
+	}
 
 	ret = lock_device_hotplug_sysfs();
 	if (ret)
 		return ret;
 
-	if (ctrlval != cpu_smt_control) {
+	orig_threads = cpu_smt_num_threads;
+	cpu_smt_num_threads = num_threads;
+
+	if (num_threads > orig_threads) {
+		ret = cpuhp_smt_enable();
+	} else if (num_threads < orig_threads) {
+		ret = cpuhp_smt_disable(ctrlval);
+	} else if (ctrlval != cpu_smt_control) {
 		switch (ctrlval) {
 		case CPU_SMT_ENABLED:
 			ret = cpuhp_smt_enable();
@@ -2566,6 +2584,15 @@ static ssize_t control_show(struct device *dev,
 {
 	const char *state = smt_states[cpu_smt_control];
 
+	/*
+	 * If SMT is enabled but not all threads are enabled then show the
+	 * number of threads. If all threads are enabled show "on". Otherwise
+	 * show the state name.
+	 */
+	if (cpu_smt_control == CPU_SMT_ENABLED &&
+	    cpu_smt_num_threads != cpu_smt_max_threads)
+		return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
+
 	return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
 }
 
-- 
2.41.0

Re: [PATCH 07/10] cpu/SMT: Allow enabling partial SMT states via sysfs

[Thomas Gleixner]

On Thu, Jun 15 2023 at 17:46, Laurent Dufour wrote:
>  
> -	if (ctrlval != cpu_smt_control) {
> +	orig_threads = cpu_smt_num_threads;
> +	cpu_smt_num_threads = num_threads;
> +
> +	if (num_threads > orig_threads) {
> +		ret = cpuhp_smt_enable();
> +	} else if (num_threads < orig_threads) {
> +		ret = cpuhp_smt_disable(ctrlval);
> +	} else if (ctrlval != cpu_smt_control) {
>  		switch (ctrlval) {
>  		case CPU_SMT_ENABLED:
>  			ret = cpuhp_smt_enable();

This switch() is still as pointless as in the previous version.

OFF -> ON, ON -> OFF, ON -> FORCE_OFF are covered by the num_threads
comparisons.

So the only case where (ctrlval != cpu_smt_control) is relevant is the
OFF -> FORCE_OFF transition because in that case the number of threads
is not changing.

          force_off = ctrlval != cpu_smt_control && ctrval == CPU_SMT_FORCE_DISABLED;

	  if (num_threads > orig_threads)
		  ret = cpuhp_smt_enable();
	  else if (num_threads < orig_threads || force_off)
		  ret = cpuhp_smt_disable(ctrlval);

Should just work, no?

Thanks,

        tglx

Re: [PATCH 07/10] cpu/SMT: Allow enabling partial SMT states via sysfs

[Michael Ellerman]

Thomas Gleixner <tglx@linutronix.de> writes:
> On Thu, Jun 15 2023 at 17:46, Laurent Dufour wrote:
>>  
>> -	if (ctrlval != cpu_smt_control) {
>> +	orig_threads = cpu_smt_num_threads;
>> +	cpu_smt_num_threads = num_threads;
>> +
>> +	if (num_threads > orig_threads) {
>> +		ret = cpuhp_smt_enable();
>> +	} else if (num_threads < orig_threads) {
>> +		ret = cpuhp_smt_disable(ctrlval);
>> +	} else if (ctrlval != cpu_smt_control) {
>>  		switch (ctrlval) {
>>  		case CPU_SMT_ENABLED:
>>  			ret = cpuhp_smt_enable();
>
> This switch() is still as pointless as in the previous version.
>
> OFF -> ON, ON -> OFF, ON -> FORCE_OFF are covered by the num_threads
> comparisons.
>
> So the only case where (ctrlval != cpu_smt_control) is relevant is the
> OFF -> FORCE_OFF transition because in that case the number of threads
> is not changing.
>
>           force_off = ctrlval != cpu_smt_control && ctrval == CPU_SMT_FORCE_DISABLED;
>
> 	  if (num_threads > orig_threads)
> 		  ret = cpuhp_smt_enable();
> 	  else if (num_threads < orig_threads || force_off)
> 		  ret = cpuhp_smt_disable(ctrlval);
>
> Should just work, no?

Yes, I think so.

I'll fold that in and do a respin of this series for 6.6 in the next
week or two.

cheers

[PATCH 08/10] powerpc/pseries: Initialise CPU hotplug callbacks earlier

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

As part of the generic HOTPLUG_SMT code, there is support for disabling
secondary SMT threads at boot time, by passing "nosmt" on the kernel
command line.

The way that is implemented is the secondary threads are brought partly
online, and then taken back offline again. That is done to support x86
CPUs needing certain initialisation done on all threads. However powerpc
has similar needs, see commit d70a54e2d085 ("powerpc/powernv: Ignore
smt-enabled on Power8 and later").

For that to work the powerpc CPU hotplug callbacks need to be registered
before secondary CPUs are brought online, otherwise __cpu_disable()
fails due to smp_ops->cpu_disable being NULL.

So split the basic initialisation into pseries_cpu_hotplug_init() which
can be called early from setup_arch(). The DLPAR related initialisation
can still be done later, because it needs to do allocations.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/pseries/hotplug-cpu.c | 22 ++++++++++++--------
 arch/powerpc/platforms/pseries/pseries.h     |  2 ++
 arch/powerpc/platforms/pseries/setup.c       |  2 ++
 3 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 1a3cb313976a..61fb7cb00880 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -845,15 +845,9 @@ static struct notifier_block pseries_smp_nb = {
 	.notifier_call = pseries_smp_notifier,
 };
 
-static int __init pseries_cpu_hotplug_init(void)
+void __init pseries_cpu_hotplug_init(void)
 {
 	int qcss_tok;
-	unsigned int node;
-
-#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
-	ppc_md.cpu_probe = dlpar_cpu_probe;
-	ppc_md.cpu_release = dlpar_cpu_release;
-#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
 	rtas_stop_self_token = rtas_function_token(RTAS_FN_STOP_SELF);
 	qcss_tok = rtas_function_token(RTAS_FN_QUERY_CPU_STOPPED_STATE);
@@ -862,12 +856,22 @@ static int __init pseries_cpu_hotplug_init(void)
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
-		return 0;
+		return;
 	}
 
 	smp_ops->cpu_offline_self = pseries_cpu_offline_self;
 	smp_ops->cpu_disable = pseries_cpu_disable;
 	smp_ops->cpu_die = pseries_cpu_die;
+}
+
+static int __init pseries_dlpar_init(void)
+{
+	unsigned int node;
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	ppc_md.cpu_probe = dlpar_cpu_probe;
+	ppc_md.cpu_release = dlpar_cpu_release;
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
 	/* Processors can be added/removed only on LPAR */
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
@@ -886,4 +890,4 @@ static int __init pseries_cpu_hotplug_init(void)
 
 	return 0;
 }
-machine_arch_initcall(pseries, pseries_cpu_hotplug_init);
+machine_arch_initcall(pseries, pseries_dlpar_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index f8bce40ebd0c..f8893ba46e83 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -75,11 +75,13 @@ static inline int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
 
 #ifdef CONFIG_HOTPLUG_CPU
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog);
+void pseries_cpu_hotplug_init(void);
 #else
 static inline int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
 	return -EOPNOTSUPP;
 }
+static inline void pseries_cpu_hotplug_init(void) { }
 #endif
 
 /* PCI root bridge prepare function override for pseries */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e2a57cfa6c83..41451b76c6e5 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -816,6 +816,8 @@ static void __init pSeries_setup_arch(void)
 	/* Discover PIC type and setup ppc_md accordingly */
 	smp_init_pseries();
 
+	// Setup CPU hotplug callbacks
+	pseries_cpu_hotplug_init();
 
 	if (radix_enabled() && !mmu_has_feature(MMU_FTR_GTSE))
 		if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
-- 
2.41.0

[PATCH 09/10] powerpc: Add HOTPLUG_SMT support

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

Add support for HOTPLUG_SMT, which enables the generic sysfs SMT support
files in /sys/devices/system/cpu/smt, as well as the "nosmt" boot
parameter.

Implement the recently added hooks to allow partial SMT states, allow
any number of threads per core.

Tie the config symbol to HOTPLUG_CPU, which enables it on the major
platforms that support SMT. If there are other platforms that want the
SMT support that can be tweaked in future.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[ldufour: pass current SMT level to cpu_smt_set_num_threads]
[ldufour: remove topology_smt_supported]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
 arch/powerpc/Kconfig                |  1 +
 arch/powerpc/include/asm/topology.h | 20 ++++++++++++++++++++
 arch/powerpc/kernel/smp.c           |  8 +++++++-
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 539d1f03ff42..5cf87ca10a9c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -273,6 +273,7 @@ config PPC
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select HOTPLUG_SMT			if HOTPLUG_CPU
 	select HUGETLB_PAGE_SIZE_VARIABLE	if PPC_BOOK3S_64 && HUGETLB_PAGE
 	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8a4d4f4d9749..7602f17d688a 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -143,5 +143,25 @@ static inline int cpu_to_coregroup_id(int cpu)
 #endif
 #endif
 
+#ifdef CONFIG_HOTPLUG_SMT
+#include <linux/cpu_smt.h>
+#include <asm/cputhreads.h>
+
+static inline bool topology_smt_threads_supported(unsigned int num_threads)
+{
+	return num_threads <= threads_per_core;
+}
+
+static inline bool topology_is_primary_thread(unsigned int cpu)
+{
+	return cpu == cpu_first_thread_sibling(cpu);
+}
+
+static inline bool topology_smt_thread_allowed(unsigned int cpu)
+{
+	return cpu_thread_in_core(cpu) < cpu_smt_num_threads;
+}
+#endif
+
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_TOPOLOGY_H */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 265801a3e94c..cdb77d36cdd0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1087,7 +1087,7 @@ static int __init init_big_cores(void)
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int cpu;
+	unsigned int cpu, num_threads;
 
 	DBG("smp_prepare_cpus\n");
 
@@ -1154,6 +1154,12 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
 	if (smp_ops && smp_ops->probe)
 		smp_ops->probe();
+
+	// Initalise the generic SMT topology support
+	num_threads = 1;
+	if (smt_enabled_at_boot)
+		num_threads = smt_enabled_at_boot;
+	cpu_smt_set_num_threads(num_threads, threads_per_core);
 }
 
 void smp_prepare_boot_cpu(void)
-- 
2.41.0

[PATCH 10/10] powerpc/pseries: Honour current SMT state when DLPAR onlining CPUs

[Laurent Dufour]

From: Michael Ellerman <mpe@ellerman.id.au>

Integrate with the generic SMT support, so that when a CPU is DLPAR
onlined it is brought up with the correct SMT mode.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/pseries/hotplug-cpu.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 61fb7cb00880..e62835a12d73 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -398,6 +398,14 @@ static int dlpar_online_cpu(struct device_node *dn)
 		for_each_present_cpu(cpu) {
 			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
+
+			if (!topology_is_primary_thread(cpu)) {
+				if (cpu_smt_control != CPU_SMT_ENABLED)
+					break;
+				if (!topology_smt_thread_allowed(cpu))
+					break;
+			}
+
 			cpu_maps_update_done();
 			find_and_update_cpu_nid(cpu);
 			rc = device_online(get_cpu_device(cpu));
-- 
2.41.0