[PATCH v2] Enable haltpoll for arm64

[PATCH v2] Enable haltpoll for arm64

[Mihai Carabas]

This patchset enables the usage of haltpoll governer on arm64. This is
specifically interesting for KVM guests by reducing the IPC latencies.

Here are some benchmarks without/with haltpoll for a KVM guest:

a) without haltpoll:
perf bench sched pipe
# Running 'sched/pipe' benchmark:
# Executed 1000000 pipe operations between two processes

     Total time: 8.138 [sec]

            8.138094 usecs/op
             122878 ops/sec

b) with haltpoll:
perf bench sched pipe
# Running 'sched/pipe' benchmark:
# Executed 1000000 pipe operations between two processes

     Total time: 5.003 [sec]

            5.003085 usecs/op
             199876 ops/sec

v2 changes from v1:
- added patch 7 where we change cpu_relax with smp_cond_load_relaxed per PeterZ
  (this improves by 50% at least the CPU cycles consumed in the tests above:
  10,716,881,137 now vs 14,503,014,257 before)
- removed the ifdef from patch 1 per RafaelW


Joao Martins (6):
  x86: Move ARCH_HAS_CPU_RELAX to arch
  x86/kvm: Move haltpoll_want() to be arch defined
  governors/haltpoll: Drop kvm_para_available() check
  arm64: Select ARCH_HAS_CPU_RELAX
  arm64: Define TIF_POLLING_NRFLAG
  cpuidle-haltpoll: ARM64 support

Mihai Carabas (1):
  cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

 arch/Kconfig                            |  3 +++
 arch/arm64/Kconfig                      |  1 +
 arch/arm64/include/asm/thread_info.h    |  6 ++++++
 arch/x86/Kconfig                        |  1 +
 arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
 arch/x86/kernel/kvm.c                   | 10 ++++++++++
 drivers/cpuidle/Kconfig                 |  4 ++--
 drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
 drivers/cpuidle/governors/haltpoll.c    |  5 +----
 drivers/cpuidle/poll_state.c            | 14 +++++++++-----
 include/linux/cpuidle_haltpoll.h        |  5 +++++
 11 files changed, 41 insertions(+), 17 deletions(-)

-- 
1.8.3.1

[PATCH v2] Enable haltpoll for arm64

[Mihai Carabas]

This patchset enables the usage of haltpoll governer on arm64. This is
specifically interesting for KVM guests by reducing the IPC latencies.

Here are some benchmarks without/with haltpoll for a KVM guest:

a) without haltpoll:
perf bench sched pipe
# Running 'sched/pipe' benchmark:
# Executed 1000000 pipe operations between two processes

     Total time: 8.138 [sec]

            8.138094 usecs/op
             122878 ops/sec

b) with haltpoll:
perf bench sched pipe
# Running 'sched/pipe' benchmark:
# Executed 1000000 pipe operations between two processes

     Total time: 5.003 [sec]

            5.003085 usecs/op
             199876 ops/sec

v2 changes from v1:
- added patch 7 where we change cpu_relax with smp_cond_load_relaxed per PeterZ
  (this improves by 50% at least the CPU cycles consumed in the tests above:
  10,716,881,137 now vs 14,503,014,257 before)
- removed the ifdef from patch 1 per RafaelW


Joao Martins (6):
  x86: Move ARCH_HAS_CPU_RELAX to arch
  x86/kvm: Move haltpoll_want() to be arch defined
  governors/haltpoll: Drop kvm_para_available() check
  arm64: Select ARCH_HAS_CPU_RELAX
  arm64: Define TIF_POLLING_NRFLAG
  cpuidle-haltpoll: ARM64 support

Mihai Carabas (1):
  cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

 arch/Kconfig                            |  3 +++
 arch/arm64/Kconfig                      |  1 +
 arch/arm64/include/asm/thread_info.h    |  6 ++++++
 arch/x86/Kconfig                        |  1 +
 arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
 arch/x86/kernel/kvm.c                   | 10 ++++++++++
 drivers/cpuidle/Kconfig                 |  4 ++--
 drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
 drivers/cpuidle/governors/haltpoll.c    |  5 +----
 drivers/cpuidle/poll_state.c            | 14 +++++++++-----
 include/linux/cpuidle_haltpoll.h        |  5 +++++
 11 files changed, 41 insertions(+), 17 deletions(-)

-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

ARM64 is going to use it for haltpoll support (for poll-state)
so move the definition to be arch-agnostic and allow architectures
to override it.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/Kconfig     | 3 +++
 arch/x86/Kconfig | 1 +
 2 files changed, 4 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index 4a85a10b12fd..92af0e9bc35e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1371,6 +1371,9 @@ config RELR
 config ARCH_HAS_MEM_ENCRYPT
 	bool
 
+config ARCH_HAS_CPU_RELAX
+	bool
+
 config ARCH_HAS_CC_PLATFORM
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1c362f479d9..0c77670d020e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -73,6 +73,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_RELAX
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

ARM64 is going to use it for haltpoll support (for poll-state)
so move the definition to be arch-agnostic and allow architectures
to override it.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/Kconfig     | 3 +++
 arch/x86/Kconfig | 1 +
 2 files changed, 4 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index 4a85a10b12fd..92af0e9bc35e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1371,6 +1371,9 @@ config RELR
 config ARCH_HAS_MEM_ENCRYPT
 	bool
 
+config ARCH_HAS_CPU_RELAX
+	bool
+
 config ARCH_HAS_CC_PLATFORM
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1c362f479d9..0c77670d020e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -73,6 +73,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_RELAX
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
-- 
1.8.3.1

[PATCH 2/7] x86/kvm: Move haltpoll_want() to be arch defined

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

Right now, kvm_para_has_hint(KVM_HINTS_REALTIME) is x86 only, and so in the
pursuit of making cpuidle-haltpoll arch independent, move the check for
haltpoll enablement to be defined per architecture. Same thing for
boot_option_idle_override. To that end, add a arch_haltpoll_want() and move the
check there.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
 arch/x86/kernel/kvm.c                   | 10 ++++++++++
 drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
 include/linux/cpuidle_haltpoll.h        |  5 +++++
 4 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h
index c8b39c6716ff..2c5a53ce266f 100644
--- a/arch/x86/include/asm/cpuidle_haltpoll.h
+++ b/arch/x86/include/asm/cpuidle_haltpoll.h
@@ -4,5 +4,6 @@
 
 void arch_haltpoll_enable(unsigned int cpu);
 void arch_haltpoll_disable(unsigned int cpu);
+bool arch_haltpoll_want(void);
 
 #endif
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1cceac5984da..75a24f107b2a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -1151,4 +1151,14 @@ void arch_haltpoll_disable(unsigned int cpu)
 	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
+
+bool arch_haltpoll_want(void)
+{
+	/* Do not load haltpoll if idle= is passed */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return false;
+
+	return kvm_para_has_hint(KVM_HINTS_REALTIME);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_want);
 #endif
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index e66df22f9695..72f9c84990c5 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -96,7 +96,7 @@ static void haltpoll_uninit(void)
 
 static bool haltpoll_want(void)
 {
-	return kvm_para_has_hint(KVM_HINTS_REALTIME) || force;
+	return (kvm_para_available() && arch_haltpoll_want()) || force;
 }
 
 static int __init haltpoll_init(void)
@@ -104,11 +104,7 @@ static int __init haltpoll_init(void)
 	int ret;
 	struct cpuidle_driver *drv = &haltpoll_driver;
 
-	/* Do not load haltpoll if idle= is passed */
-	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
-		return -ENODEV;
-
-	if (!kvm_para_available() || !haltpoll_want())
+	if (!haltpoll_want())
 		return -ENODEV;
 
 	cpuidle_poll_state_init(drv);
diff --git a/include/linux/cpuidle_haltpoll.h b/include/linux/cpuidle_haltpoll.h
index d50c1e0411a2..bae68a6603e3 100644
--- a/include/linux/cpuidle_haltpoll.h
+++ b/include/linux/cpuidle_haltpoll.h
@@ -12,5 +12,10 @@ static inline void arch_haltpoll_enable(unsigned int cpu)
 static inline void arch_haltpoll_disable(unsigned int cpu)
 {
 }
+
+static inline bool arch_haltpoll_want(void)
+{
+	return false;
+}
 #endif
 #endif
-- 
1.8.3.1

[PATCH 2/7] x86/kvm: Move haltpoll_want() to be arch defined

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

Right now, kvm_para_has_hint(KVM_HINTS_REALTIME) is x86 only, and so in the
pursuit of making cpuidle-haltpoll arch independent, move the check for
haltpoll enablement to be defined per architecture. Same thing for
boot_option_idle_override. To that end, add a arch_haltpoll_want() and move the
check there.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
 arch/x86/kernel/kvm.c                   | 10 ++++++++++
 drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
 include/linux/cpuidle_haltpoll.h        |  5 +++++
 4 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h
index c8b39c6716ff..2c5a53ce266f 100644
--- a/arch/x86/include/asm/cpuidle_haltpoll.h
+++ b/arch/x86/include/asm/cpuidle_haltpoll.h
@@ -4,5 +4,6 @@
 
 void arch_haltpoll_enable(unsigned int cpu);
 void arch_haltpoll_disable(unsigned int cpu);
+bool arch_haltpoll_want(void);
 
 #endif
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1cceac5984da..75a24f107b2a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -1151,4 +1151,14 @@ void arch_haltpoll_disable(unsigned int cpu)
 	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
+
+bool arch_haltpoll_want(void)
+{
+	/* Do not load haltpoll if idle= is passed */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return false;
+
+	return kvm_para_has_hint(KVM_HINTS_REALTIME);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_want);
 #endif
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index e66df22f9695..72f9c84990c5 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -96,7 +96,7 @@ static void haltpoll_uninit(void)
 
 static bool haltpoll_want(void)
 {
-	return kvm_para_has_hint(KVM_HINTS_REALTIME) || force;
+	return (kvm_para_available() && arch_haltpoll_want()) || force;
 }
 
 static int __init haltpoll_init(void)
@@ -104,11 +104,7 @@ static int __init haltpoll_init(void)
 	int ret;
 	struct cpuidle_driver *drv = &haltpoll_driver;
 
-	/* Do not load haltpoll if idle= is passed */
-	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
-		return -ENODEV;
-
-	if (!kvm_para_available() || !haltpoll_want())
+	if (!haltpoll_want())
 		return -ENODEV;
 
 	cpuidle_poll_state_init(drv);
diff --git a/include/linux/cpuidle_haltpoll.h b/include/linux/cpuidle_haltpoll.h
index d50c1e0411a2..bae68a6603e3 100644
--- a/include/linux/cpuidle_haltpoll.h
+++ b/include/linux/cpuidle_haltpoll.h
@@ -12,5 +12,10 @@ static inline void arch_haltpoll_enable(unsigned int cpu)
 static inline void arch_haltpoll_disable(unsigned int cpu)
 {
 }
+
+static inline bool arch_haltpoll_want(void)
+{
+	return false;
+}
 #endif
 #endif
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 3/7] governors/haltpoll: Drop kvm_para_available() check

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

This is duplicated already in the haltpoll idle driver,
and there's no need to re-check KVM guest availability in
the governor.

Either guests uses the module which explicitly selects this
governor, and given that it has the lowest rating of all governors
(menu=20,teo=19,ladder=10/25,haltpoll=9) means that unless it's
the only one compiled in, it won't be selected.

Dropping such check also allows to test haltpoll in baremetal.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
---
 drivers/cpuidle/governors/haltpoll.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
index 1dff3a52917d..c9b69651d377 100644
--- a/drivers/cpuidle/governors/haltpoll.c
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -143,10 +143,7 @@ static int haltpoll_enable_device(struct cpuidle_driver *drv,
 
 static int __init init_haltpoll(void)
 {
-	if (kvm_para_available())
-		return cpuidle_register_governor(&haltpoll_governor);
-
-	return 0;
+	return cpuidle_register_governor(&haltpoll_governor);
 }
 
 postcore_initcall(init_haltpoll);
-- 
1.8.3.1

[PATCH 3/7] governors/haltpoll: Drop kvm_para_available() check

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

This is duplicated already in the haltpoll idle driver,
and there's no need to re-check KVM guest availability in
the governor.

Either guests uses the module which explicitly selects this
governor, and given that it has the lowest rating of all governors
(menu=20,teo=19,ladder=10/25,haltpoll=9) means that unless it's
the only one compiled in, it won't be selected.

Dropping such check also allows to test haltpoll in baremetal.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
---
 drivers/cpuidle/governors/haltpoll.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
index 1dff3a52917d..c9b69651d377 100644
--- a/drivers/cpuidle/governors/haltpoll.c
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -143,10 +143,7 @@ static int haltpoll_enable_device(struct cpuidle_driver *drv,
 
 static int __init init_haltpoll(void)
 {
-	if (kvm_para_available())
-		return cpuidle_register_governor(&haltpoll_governor);
-
-	return 0;
+	return cpuidle_register_governor(&haltpoll_governor);
 }
 
 postcore_initcall(init_haltpoll);
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 4/7] arm64: Select ARCH_HAS_CPU_RELAX

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

ARCH_HAS_CPU_RELAX controls the build of poll-state, so select it from ARM64
kconfig.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/arm64/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 87ade6549790..7c47617b5722 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -105,6 +105,7 @@ config ARM64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
+	select ARCH_HAS_CPU_RELAX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
-- 
1.8.3.1

[PATCH 4/7] arm64: Select ARCH_HAS_CPU_RELAX

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

ARCH_HAS_CPU_RELAX controls the build of poll-state, so select it from ARM64
kconfig.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/arm64/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 87ade6549790..7c47617b5722 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -105,6 +105,7 @@ config ARM64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
+	select ARCH_HAS_CPU_RELAX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 5/7] arm64: Define TIF_POLLING_NRFLAG

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

The default idle method for arm64 is WFI and it therefore
unconditionally requires the reschedule interrupt when idle.

Commit 842514849a61 ("arm64: Remove TIF_POLLING_NRFLAG") had
reverted it because WFI was the only idle method. ARM64 support
for haltpoll means that poll_idle() polls for TIF_POLLING_NRFLAG,
so define on arm64 *only if* haltpoll is built, using the same bit.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/arm64/include/asm/thread_info.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 2c62ab3aeb84..c5fd3107c8ce 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -69,6 +69,9 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
 #define TIF_SECCOMP		11	/* syscall secure computing */
 #define TIF_SYSCALL_EMU		12	/* syscall emulation active */
+#if IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE) || IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE_MODULE)
+#define TIF_POLLING_NRFLAG      16      /* poll_idle() polls TIF_NEED_RESCHED */
+#endif
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
@@ -94,6 +97,9 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
+#if IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE) || IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE_MODULE)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+#endif
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
-- 
1.8.3.1

[PATCH 5/7] arm64: Define TIF_POLLING_NRFLAG

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

The default idle method for arm64 is WFI and it therefore
unconditionally requires the reschedule interrupt when idle.

Commit 842514849a61 ("arm64: Remove TIF_POLLING_NRFLAG") had
reverted it because WFI was the only idle method. ARM64 support
for haltpoll means that poll_idle() polls for TIF_POLLING_NRFLAG,
so define on arm64 *only if* haltpoll is built, using the same bit.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 arch/arm64/include/asm/thread_info.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 2c62ab3aeb84..c5fd3107c8ce 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -69,6 +69,9 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
 #define TIF_SECCOMP		11	/* syscall secure computing */
 #define TIF_SYSCALL_EMU		12	/* syscall emulation active */
+#if IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE) || IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE_MODULE)
+#define TIF_POLLING_NRFLAG      16      /* poll_idle() polls TIF_NEED_RESCHED */
+#endif
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
@@ -94,6 +97,9 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
+#if IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE) || IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE_MODULE)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+#endif
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 6/7] cpuidle-haltpoll: ARM64 support

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

To test whether it's a guest or not for the default cases, the haltpoll
driver uses the kvm_para* helpers to find out if it's a guest or not.

ARM64 doesn't have or defined any of these, so it remains disabled on
the default. Although it allows to be force-loaded.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 drivers/cpuidle/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index cac5997dca50..067927eda466 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -35,7 +35,7 @@ config CPU_IDLE_GOV_TEO
 
 config CPU_IDLE_GOV_HALTPOLL
 	bool "Haltpoll governor (for virtualized systems)"
-	depends on KVM_GUEST
+	depends on (X86 && KVM_GUEST) || ARM64
 	help
 	  This governor implements haltpoll idle state selection, to be
 	  used in conjunction with the haltpoll cpuidle driver, allowing
@@ -73,7 +73,7 @@ endmenu
 
 config HALTPOLL_CPUIDLE
 	tristate "Halt poll cpuidle driver"
-	depends on X86 && KVM_GUEST
+	depends on (X86 && KVM_GUEST) || ARM64
 	select CPU_IDLE_GOV_HALTPOLL
 	default y
 	help
-- 
1.8.3.1

[PATCH 6/7] cpuidle-haltpoll: ARM64 support

[Mihai Carabas]

From: Joao Martins <joao.m.martins@oracle.com>

To test whether it's a guest or not for the default cases, the haltpoll
driver uses the kvm_para* helpers to find out if it's a guest or not.

ARM64 doesn't have or defined any of these, so it remains disabled on
the default. Although it allows to be force-loaded.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 drivers/cpuidle/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index cac5997dca50..067927eda466 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -35,7 +35,7 @@ config CPU_IDLE_GOV_TEO
 
 config CPU_IDLE_GOV_HALTPOLL
 	bool "Haltpoll governor (for virtualized systems)"
-	depends on KVM_GUEST
+	depends on (X86 && KVM_GUEST) || ARM64
 	help
 	  This governor implements haltpoll idle state selection, to be
 	  used in conjunction with the haltpoll cpuidle driver, allowing
@@ -73,7 +73,7 @@ endmenu
 
 config HALTPOLL_CPUIDLE
 	tristate "Halt poll cpuidle driver"
-	depends on X86 && KVM_GUEST
+	depends on (X86 && KVM_GUEST) || ARM64
 	select CPU_IDLE_GOV_HALTPOLL
 	default y
 	help
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

cpu_relax on ARM64 does a simple "yield". Thus we replace it with
smp_cond_load_relaxed which basically does a "wfe".

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 drivers/cpuidle/poll_state.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index 9b6d90a72601..440cd713e39a 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
 
 		limit = cpuidle_poll_time(drv, dev);
 
-		while (!need_resched()) {
-			cpu_relax();
-			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
-				continue;
-
+		for (;;) {
 			loop_count = 0;
+
+			smp_cond_load_relaxed(&current_thread_info()->flags,
+					      (VAL & _TIF_NEED_RESCHED) ||
+					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
+
+			if (loop_count < POLL_IDLE_RELAX_COUNT)
+				break;
+
 			if (local_clock_noinstr() - time_start > limit) {
 				dev->poll_time_limit = true;
 				break;
-- 
1.8.3.1

[PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

cpu_relax on ARM64 does a simple "yield". Thus we replace it with
smp_cond_load_relaxed which basically does a "wfe".

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
---
 drivers/cpuidle/poll_state.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index 9b6d90a72601..440cd713e39a 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
 
 		limit = cpuidle_poll_time(drv, dev);
 
-		while (!need_resched()) {
-			cpu_relax();
-			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
-				continue;
-
+		for (;;) {
 			loop_count = 0;
+
+			smp_cond_load_relaxed(&current_thread_info()->flags,
+					      (VAL & _TIF_NEED_RESCHED) ||
+					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
+
+			if (loop_count < POLL_IDLE_RELAX_COUNT)
+				break;
+
 			if (local_clock_noinstr() - time_start > limit) {
 				dev->poll_time_limit = true;
 				break;
-- 
1.8.3.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Christoph Lameter]

On Mon, 20 Nov 2023, Mihai Carabas wrote:

> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> smp_cond_load_relaxed which basically does a "wfe".

Well it clears events first (which requires the first WFE) and then does a 
WFE waiting for any events if no events were pending.

WFE does not cause a VMEXIT? Or does the inner loop of 
smp_cond_load_relaxed now do 2x VMEXITS?

KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
kvm_handle_wfx().

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Christoph Lameter]

On Mon, 20 Nov 2023, Mihai Carabas wrote:

> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> smp_cond_load_relaxed which basically does a "wfe".

Well it clears events first (which requires the first WFE) and then does a 
WFE waiting for any events if no events were pending.

WFE does not cause a VMEXIT? Or does the inner loop of 
smp_cond_load_relaxed now do 2x VMEXITS?

KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
kvm_handle_wfx().

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

La 22.11.2023 22:51, Christoph Lameter a scris:
>
> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>
>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>> smp_cond_load_relaxed which basically does a "wfe".
>
> Well it clears events first (which requires the first WFE) and then 
> does a WFE waiting for any events if no events were pending.
>
> WFE does not cause a VMEXIT? Or does the inner loop of 
> smp_cond_load_relaxed now do 2x VMEXITS?
>
> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
> kvm_handle_wfx().

In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are 
more tasks waiting on the same core (e.g. on an oversubscribed system).

In arch/arm64/kvm/arm.c:

  457 >-------if (single_task_running())
  458 >------->-------vcpu_clear_wfx_traps(vcpu);
  459 >-------else
  460 >------->-------vcpu_set_wfx_traps(vcpu);

This of course can be improved by having a knob where you can completly 
disable wfx traping by your needs, but I left this as another subject to 
tackle.

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

La 22.11.2023 22:51, Christoph Lameter a scris:
>
> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>
>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>> smp_cond_load_relaxed which basically does a "wfe".
>
> Well it clears events first (which requires the first WFE) and then 
> does a WFE waiting for any events if no events were pending.
>
> WFE does not cause a VMEXIT? Or does the inner loop of 
> smp_cond_load_relaxed now do 2x VMEXITS?
>
> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
> kvm_handle_wfx().

In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are 
more tasks waiting on the same core (e.g. on an oversubscribed system).

In arch/arm64/kvm/arm.c:

  457 >-------if (single_task_running())
  458 >------->-------vcpu_clear_wfx_traps(vcpu);
  459 >-------else
  460 >------->-------vcpu_set_wfx_traps(vcpu);

This of course can be improved by having a knob where you can completly 
disable wfx traping by your needs, but I left this as another subject to 
tackle.


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Petr Mladek]

On Mon 2023-11-20 16:01:32, Mihai Carabas wrote:
> From: Joao Martins <joao.m.martins@oracle.com>
> 
> ARM64 is going to use it for haltpoll support (for poll-state)
> so move the definition to be arch-agnostic and allow architectures
> to override it.

This says that the definition is moved.

> diff --git a/arch/Kconfig b/arch/Kconfig
> index 4a85a10b12fd..92af0e9bc35e 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -1371,6 +1371,9 @@ config RELR
>  config ARCH_HAS_MEM_ENCRYPT
>  	bool
>  
> +config ARCH_HAS_CPU_RELAX
> +	bool
> +
>  config ARCH_HAS_CC_PLATFORM
>  	bool
>  
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index d1c362f479d9..0c77670d020e 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -73,6 +73,7 @@ config X86
>  	select ARCH_HAS_CACHE_LINE_SIZE
>  	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
>  	select ARCH_HAS_CPU_FINALIZE_INIT
> +	select ARCH_HAS_CPU_RELAX
>  	select ARCH_HAS_CURRENT_STACK_POINTER
>  	select ARCH_HAS_DEBUG_VIRTUAL
>  	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE

But the definion is only added here.

I would expect that the patch also removes the original definion.


Best Regards,
Petr

Re: [PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Petr Mladek]

On Mon 2023-11-20 16:01:32, Mihai Carabas wrote:
> From: Joao Martins <joao.m.martins@oracle.com>
> 
> ARM64 is going to use it for haltpoll support (for poll-state)
> so move the definition to be arch-agnostic and allow architectures
> to override it.

This says that the definition is moved.

> diff --git a/arch/Kconfig b/arch/Kconfig
> index 4a85a10b12fd..92af0e9bc35e 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -1371,6 +1371,9 @@ config RELR
>  config ARCH_HAS_MEM_ENCRYPT
>  	bool
>  
> +config ARCH_HAS_CPU_RELAX
> +	bool
> +
>  config ARCH_HAS_CC_PLATFORM
>  	bool
>  
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index d1c362f479d9..0c77670d020e 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -73,6 +73,7 @@ config X86
>  	select ARCH_HAS_CACHE_LINE_SIZE
>  	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
>  	select ARCH_HAS_CPU_FINALIZE_INIT
> +	select ARCH_HAS_CPU_RELAX
>  	select ARCH_HAS_CURRENT_STACK_POINTER
>  	select ARCH_HAS_DEBUG_VIRTUAL
>  	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE

But the definion is only added here.

I would expect that the patch also removes the original definion.


Best Regards,
Petr

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Christoph Lameter (Ampere)]

[-- Attachment #1: Type: text/plain, Size: 1471 bytes --]

On Wed, 22 Nov 2023, Mihai Carabas wrote:

> La 22.11.2023 22:51, Christoph Lameter a scris:
>> 
>> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>> 
>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>> smp_cond_load_relaxed which basically does a "wfe".
>> 
>> Well it clears events first (which requires the first WFE) and then does a 
>> WFE waiting for any events if no events were pending.
>> 
>> WFE does not cause a VMEXIT? Or does the inner loop of 
>> smp_cond_load_relaxed now do 2x VMEXITS?
>> 
>> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
>> kvm_handle_wfx().
>
> In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are more 
> tasks waiting on the same core (e.g. on an oversubscribed system).
>
> In arch/arm64/kvm/arm.c:
>
>  457 >-------if (single_task_running())
>  458 >------->-------vcpu_clear_wfx_traps(vcpu);
>  459 >-------else
>  460 >------->-------vcpu_set_wfx_traps(vcpu);

Ahh. Cool did not know about that. But still: Lots of VMEXITs once the 
load has to be shared.

> This of course can be improved by having a knob where you can completly 
> disable wfx traping by your needs, but I left this as another subject to 
> tackle.

kvm_arch_vcpu_load() looks strange. On the one hand we pass a cpu 
number into it and then we use functions that only work if we are running 
on that cpu?

It would be better to use smp_processor_id() in the function 
and not pass the cpu number to it.

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Christoph Lameter (Ampere)]

[-- Attachment #1: Type: text/plain, Size: 1471 bytes --]

On Wed, 22 Nov 2023, Mihai Carabas wrote:

> La 22.11.2023 22:51, Christoph Lameter a scris:
>> 
>> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>> 
>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>> smp_cond_load_relaxed which basically does a "wfe".
>> 
>> Well it clears events first (which requires the first WFE) and then does a 
>> WFE waiting for any events if no events were pending.
>> 
>> WFE does not cause a VMEXIT? Or does the inner loop of 
>> smp_cond_load_relaxed now do 2x VMEXITS?
>> 
>> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
>> kvm_handle_wfx().
>
> In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are more 
> tasks waiting on the same core (e.g. on an oversubscribed system).
>
> In arch/arm64/kvm/arm.c:
>
>  457 >-------if (single_task_running())
>  458 >------->-------vcpu_clear_wfx_traps(vcpu);
>  459 >-------else
>  460 >------->-------vcpu_set_wfx_traps(vcpu);

Ahh. Cool did not know about that. But still: Lots of VMEXITs once the 
load has to be shared.

> This of course can be improved by having a knob where you can completly 
> disable wfx traping by your needs, but I left this as another subject to 
> tackle.

kvm_arch_vcpu_load() looks strange. On the one hand we pass a cpu 
number into it and then we use functions that only work if we are running 
on that cpu?

It would be better to use smp_processor_id() in the function 
and not pass the cpu number to it.

[-- Attachment #2: Type: text/plain, Size: 176 bytes --]

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Mihai Carabas]

>> From: Joao Martins <joao.m.martins@oracle.com>
>>
>> ARM64 is going to use it for haltpoll support (for poll-state)
>> so move the definition to be arch-agnostic and allow architectures
>> to override it.
> This says that the definition is moved.
>
>> diff --git a/arch/Kconfig b/arch/Kconfig
>> index 4a85a10b12fd..92af0e9bc35e 100644
>> --- a/arch/Kconfig
>> +++ b/arch/Kconfig
>> @@ -1371,6 +1371,9 @@ config RELR
>>   config ARCH_HAS_MEM_ENCRYPT
>>   	bool
>>   
>> +config ARCH_HAS_CPU_RELAX
>> +	bool
>> +
>>   config ARCH_HAS_CC_PLATFORM
>>   	bool
>>   
>> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
>> index d1c362f479d9..0c77670d020e 100644
>> --- a/arch/x86/Kconfig
>> +++ b/arch/x86/Kconfig
>> @@ -73,6 +73,7 @@ config X86
>>   	select ARCH_HAS_CACHE_LINE_SIZE
>>   	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
>>   	select ARCH_HAS_CPU_FINALIZE_INIT
>> +	select ARCH_HAS_CPU_RELAX
>>   	select ARCH_HAS_CURRENT_STACK_POINTER
>>   	select ARCH_HAS_DEBUG_VIRTUAL
>>   	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
> But the definion is only added here.
>
> I would expect that the patch also removes the original definion.

Thanks for catching this. I updated the patch:

diff --git a/arch/Kconfig b/arch/Kconfig
index 12d51495caec..626ddd9ba7e0 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1371,6 +1371,9 @@ config RELR
  config ARCH_HAS_MEM_ENCRYPT
         bool

+config ARCH_HAS_CPU_RELAX
+       bool
+
  config ARCH_HAS_CC_PLATFORM
         bool

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 66bfabae8814..aaca90ba791a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -72,6 +72,7 @@ config X86
         select ARCH_HAS_CACHE_LINE_SIZE
         select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
         select ARCH_HAS_CPU_FINALIZE_INIT
+       select ARCH_HAS_CPU_RELAX
         select ARCH_HAS_CURRENT_STACK_POINTER
         select ARCH_HAS_DEBUG_VIRTUAL
         select ARCH_HAS_DEBUG_VM_PGTABLE        if !X86_PAE
@@ -363,9 +364,6 @@ config ARCH_MAY_HAVE_PC_FDC
  config GENERIC_CALIBRATE_DELAY
         def_bool y

-config ARCH_HAS_CPU_RELAX
-       def_bool y
-
  config ARCH_HIBERNATION_POSSIBLE
         def_bool y

Re: [PATCH 1/7] x86: Move ARCH_HAS_CPU_RELAX to arch

[Mihai Carabas]

>> From: Joao Martins <joao.m.martins@oracle.com>
>>
>> ARM64 is going to use it for haltpoll support (for poll-state)
>> so move the definition to be arch-agnostic and allow architectures
>> to override it.
> This says that the definition is moved.
>
>> diff --git a/arch/Kconfig b/arch/Kconfig
>> index 4a85a10b12fd..92af0e9bc35e 100644
>> --- a/arch/Kconfig
>> +++ b/arch/Kconfig
>> @@ -1371,6 +1371,9 @@ config RELR
>>   config ARCH_HAS_MEM_ENCRYPT
>>   	bool
>>   
>> +config ARCH_HAS_CPU_RELAX
>> +	bool
>> +
>>   config ARCH_HAS_CC_PLATFORM
>>   	bool
>>   
>> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
>> index d1c362f479d9..0c77670d020e 100644
>> --- a/arch/x86/Kconfig
>> +++ b/arch/x86/Kconfig
>> @@ -73,6 +73,7 @@ config X86
>>   	select ARCH_HAS_CACHE_LINE_SIZE
>>   	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
>>   	select ARCH_HAS_CPU_FINALIZE_INIT
>> +	select ARCH_HAS_CPU_RELAX
>>   	select ARCH_HAS_CURRENT_STACK_POINTER
>>   	select ARCH_HAS_DEBUG_VIRTUAL
>>   	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
> But the definion is only added here.
>
> I would expect that the patch also removes the original definion.

Thanks for catching this. I updated the patch:

diff --git a/arch/Kconfig b/arch/Kconfig
index 12d51495caec..626ddd9ba7e0 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1371,6 +1371,9 @@ config RELR
  config ARCH_HAS_MEM_ENCRYPT
         bool

+config ARCH_HAS_CPU_RELAX
+       bool
+
  config ARCH_HAS_CC_PLATFORM
         bool

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 66bfabae8814..aaca90ba791a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -72,6 +72,7 @@ config X86
         select ARCH_HAS_CACHE_LINE_SIZE
         select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
         select ARCH_HAS_CPU_FINALIZE_INIT
+       select ARCH_HAS_CPU_RELAX
         select ARCH_HAS_CURRENT_STACK_POINTER
         select ARCH_HAS_DEBUG_VIRTUAL
         select ARCH_HAS_DEBUG_VM_PGTABLE        if !X86_PAE
@@ -363,9 +364,6 @@ config ARCH_MAY_HAVE_PC_FDC
  config GENERIC_CALIBRATE_DELAY
         def_bool y

-config ARCH_HAS_CPU_RELAX
-       def_bool y
-
  config ARCH_HIBERNATION_POSSIBLE
         def_bool y


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 2/7] x86/kvm: Move haltpoll_want() to be arch defined

[Rafael J. Wysocki]

On Mon, Nov 20, 2023 at 4:15 PM Mihai Carabas <mihai.carabas@oracle.com> wrote:
>
> From: Joao Martins <joao.m.martins@oracle.com>
>
> Right now, kvm_para_has_hint(KVM_HINTS_REALTIME) is x86 only, and so in the
> pursuit of making cpuidle-haltpoll arch independent, move the check for
> haltpoll enablement to be defined per architecture. Same thing for
> boot_option_idle_override. To that end, add a arch_haltpoll_want() and move the
> check there.
>
> Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>

From the cpuidle side:

Acked-by: Rafael J. Wysocki <rafael@kernel.org>

> ---
>  arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
>  arch/x86/kernel/kvm.c                   | 10 ++++++++++
>  drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
>  include/linux/cpuidle_haltpoll.h        |  5 +++++
>  4 files changed, 18 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h
> index c8b39c6716ff..2c5a53ce266f 100644
> --- a/arch/x86/include/asm/cpuidle_haltpoll.h
> +++ b/arch/x86/include/asm/cpuidle_haltpoll.h
> @@ -4,5 +4,6 @@
>
>  void arch_haltpoll_enable(unsigned int cpu);
>  void arch_haltpoll_disable(unsigned int cpu);
> +bool arch_haltpoll_want(void);
>
>  #endif
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index 1cceac5984da..75a24f107b2a 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -1151,4 +1151,14 @@ void arch_haltpoll_disable(unsigned int cpu)
>         smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
>  }
>  EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
> +
> +bool arch_haltpoll_want(void)
> +{
> +       /* Do not load haltpoll if idle= is passed */
> +       if (boot_option_idle_override != IDLE_NO_OVERRIDE)
> +               return false;
> +
> +       return kvm_para_has_hint(KVM_HINTS_REALTIME);
> +}
> +EXPORT_SYMBOL_GPL(arch_haltpoll_want);
>  #endif
> diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
> index e66df22f9695..72f9c84990c5 100644
> --- a/drivers/cpuidle/cpuidle-haltpoll.c
> +++ b/drivers/cpuidle/cpuidle-haltpoll.c
> @@ -96,7 +96,7 @@ static void haltpoll_uninit(void)
>
>  static bool haltpoll_want(void)
>  {
> -       return kvm_para_has_hint(KVM_HINTS_REALTIME) || force;
> +       return (kvm_para_available() && arch_haltpoll_want()) || force;
>  }
>
>  static int __init haltpoll_init(void)
> @@ -104,11 +104,7 @@ static int __init haltpoll_init(void)
>         int ret;
>         struct cpuidle_driver *drv = &haltpoll_driver;
>
> -       /* Do not load haltpoll if idle= is passed */
> -       if (boot_option_idle_override != IDLE_NO_OVERRIDE)
> -               return -ENODEV;
> -
> -       if (!kvm_para_available() || !haltpoll_want())
> +       if (!haltpoll_want())
>                 return -ENODEV;
>
>         cpuidle_poll_state_init(drv);
> diff --git a/include/linux/cpuidle_haltpoll.h b/include/linux/cpuidle_haltpoll.h
> index d50c1e0411a2..bae68a6603e3 100644
> --- a/include/linux/cpuidle_haltpoll.h
> +++ b/include/linux/cpuidle_haltpoll.h
> @@ -12,5 +12,10 @@ static inline void arch_haltpoll_enable(unsigned int cpu)
>  static inline void arch_haltpoll_disable(unsigned int cpu)
>  {
>  }
> +
> +static inline bool arch_haltpoll_want(void)
> +{
> +       return false;
> +}
>  #endif
>  #endif
> --
> 1.8.3.1
>

Re: [PATCH 2/7] x86/kvm: Move haltpoll_want() to be arch defined

[Rafael J. Wysocki]

On Mon, Nov 20, 2023 at 4:15 PM Mihai Carabas <mihai.carabas@oracle.com> wrote:
>
> From: Joao Martins <joao.m.martins@oracle.com>
>
> Right now, kvm_para_has_hint(KVM_HINTS_REALTIME) is x86 only, and so in the
> pursuit of making cpuidle-haltpoll arch independent, move the check for
> haltpoll enablement to be defined per architecture. Same thing for
> boot_option_idle_override. To that end, add a arch_haltpoll_want() and move the
> check there.
>
> Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>

From the cpuidle side:

Acked-by: Rafael J. Wysocki <rafael@kernel.org>

> ---
>  arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
>  arch/x86/kernel/kvm.c                   | 10 ++++++++++
>  drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
>  include/linux/cpuidle_haltpoll.h        |  5 +++++
>  4 files changed, 18 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h
> index c8b39c6716ff..2c5a53ce266f 100644
> --- a/arch/x86/include/asm/cpuidle_haltpoll.h
> +++ b/arch/x86/include/asm/cpuidle_haltpoll.h
> @@ -4,5 +4,6 @@
>
>  void arch_haltpoll_enable(unsigned int cpu);
>  void arch_haltpoll_disable(unsigned int cpu);
> +bool arch_haltpoll_want(void);
>
>  #endif
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index 1cceac5984da..75a24f107b2a 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -1151,4 +1151,14 @@ void arch_haltpoll_disable(unsigned int cpu)
>         smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
>  }
>  EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
> +
> +bool arch_haltpoll_want(void)
> +{
> +       /* Do not load haltpoll if idle= is passed */
> +       if (boot_option_idle_override != IDLE_NO_OVERRIDE)
> +               return false;
> +
> +       return kvm_para_has_hint(KVM_HINTS_REALTIME);
> +}
> +EXPORT_SYMBOL_GPL(arch_haltpoll_want);
>  #endif
> diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
> index e66df22f9695..72f9c84990c5 100644
> --- a/drivers/cpuidle/cpuidle-haltpoll.c
> +++ b/drivers/cpuidle/cpuidle-haltpoll.c
> @@ -96,7 +96,7 @@ static void haltpoll_uninit(void)
>
>  static bool haltpoll_want(void)
>  {
> -       return kvm_para_has_hint(KVM_HINTS_REALTIME) || force;
> +       return (kvm_para_available() && arch_haltpoll_want()) || force;
>  }
>
>  static int __init haltpoll_init(void)
> @@ -104,11 +104,7 @@ static int __init haltpoll_init(void)
>         int ret;
>         struct cpuidle_driver *drv = &haltpoll_driver;
>
> -       /* Do not load haltpoll if idle= is passed */
> -       if (boot_option_idle_override != IDLE_NO_OVERRIDE)
> -               return -ENODEV;
> -
> -       if (!kvm_para_available() || !haltpoll_want())
> +       if (!haltpoll_want())
>                 return -ENODEV;
>
>         cpuidle_poll_state_init(drv);
> diff --git a/include/linux/cpuidle_haltpoll.h b/include/linux/cpuidle_haltpoll.h
> index d50c1e0411a2..bae68a6603e3 100644
> --- a/include/linux/cpuidle_haltpoll.h
> +++ b/include/linux/cpuidle_haltpoll.h
> @@ -12,5 +12,10 @@ static inline void arch_haltpoll_enable(unsigned int cpu)
>  static inline void arch_haltpoll_disable(unsigned int cpu)
>  {
>  }
> +
> +static inline bool arch_haltpoll_want(void)
> +{
> +       return false;
> +}
>  #endif
>  #endif
> --
> 1.8.3.1
>

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Ankur Arora]

Christoph Lameter (Ampere) <cl@linux.com> writes:

> On Wed, 22 Nov 2023, Mihai Carabas wrote:
>
>> La 22.11.2023 22:51, Christoph Lameter a scris:
>>> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>>>
>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>> smp_cond_load_relaxed which basically does a "wfe".
>>> Well it clears events first (which requires the first WFE) and then does a
>>> WFE waiting for any events if no events were pending.
>>> WFE does not cause a VMEXIT? Or does the inner loop of
>>> smp_cond_load_relaxed now do 2x VMEXITS?
>>> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See
>>> kvm_handle_wfx().
>>
>> In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are more
>> tasks waiting on the same core (e.g. on an oversubscribed system).
>>
>> In arch/arm64/kvm/arm.c:
>>
>>  457 >-------if (single_task_running())
>>  458 >------->-------vcpu_clear_wfx_traps(vcpu);
>>  459 >-------else
>>  460 >------->-------vcpu_set_wfx_traps(vcpu);
>
> Ahh. Cool did not know about that. But still: Lots of VMEXITs once the load has
> to be shared.

Yeah, anytime there's more than one runnable process. Another, more
critical place where we will vmexit is the qspinlock slowpath which
uses smp_cond_load.

>> This of course can be improved by having a knob where you can completly
>> disable wfx traping by your needs, but I left this as another subject to
>> tackle.

Probably needs to be adaptive since we use WFE in error paths as well
(for instance to park the CPU.)


Ankur

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Ankur Arora]

Christoph Lameter (Ampere) <cl@linux.com> writes:

> On Wed, 22 Nov 2023, Mihai Carabas wrote:
>
>> La 22.11.2023 22:51, Christoph Lameter a scris:
>>> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>>>
>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>> smp_cond_load_relaxed which basically does a "wfe".
>>> Well it clears events first (which requires the first WFE) and then does a
>>> WFE waiting for any events if no events were pending.
>>> WFE does not cause a VMEXIT? Or does the inner loop of
>>> smp_cond_load_relaxed now do 2x VMEXITS?
>>> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See
>>> kvm_handle_wfx().
>>
>> In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are more
>> tasks waiting on the same core (e.g. on an oversubscribed system).
>>
>> In arch/arm64/kvm/arm.c:
>>
>>  457 >-------if (single_task_running())
>>  458 >------->-------vcpu_clear_wfx_traps(vcpu);
>>  459 >-------else
>>  460 >------->-------vcpu_set_wfx_traps(vcpu);
>
> Ahh. Cool did not know about that. But still: Lots of VMEXITs once the load has
> to be shared.

Yeah, anytime there's more than one runnable process. Another, more
critical place where we will vmexit is the qspinlock slowpath which
uses smp_cond_load.

>> This of course can be improved by having a knob where you can completly
>> disable wfx traping by your needs, but I left this as another subject to
>> tackle.

Probably needs to be adaptive since we use WFE in error paths as well
(for instance to park the CPU.)


Ankur

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Will Deacon]

On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> smp_cond_load_relaxed which basically does a "wfe".
> 
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
> ---
>  drivers/cpuidle/poll_state.c | 14 +++++++++-----
>  1 file changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
> index 9b6d90a72601..440cd713e39a 100644
> --- a/drivers/cpuidle/poll_state.c
> +++ b/drivers/cpuidle/poll_state.c
> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>  
>  		limit = cpuidle_poll_time(drv, dev);
>  
> -		while (!need_resched()) {
> -			cpu_relax();
> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
> -				continue;
> -
> +		for (;;) {
>  			loop_count = 0;
> +
> +			smp_cond_load_relaxed(&current_thread_info()->flags,
> +					      (VAL & _TIF_NEED_RESCHED) ||
> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
> +
> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
> +				break;
> +
>  			if (local_clock_noinstr() - time_start > limit) {
>  				dev->poll_time_limit = true;
>  				break;

Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?

Will

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Will Deacon]

On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> smp_cond_load_relaxed which basically does a "wfe".
> 
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
> ---
>  drivers/cpuidle/poll_state.c | 14 +++++++++-----
>  1 file changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
> index 9b6d90a72601..440cd713e39a 100644
> --- a/drivers/cpuidle/poll_state.c
> +++ b/drivers/cpuidle/poll_state.c
> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>  
>  		limit = cpuidle_poll_time(drv, dev);
>  
> -		while (!need_resched()) {
> -			cpu_relax();
> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
> -				continue;
> -
> +		for (;;) {
>  			loop_count = 0;
> +
> +			smp_cond_load_relaxed(&current_thread_info()->flags,
> +					      (VAL & _TIF_NEED_RESCHED) ||
> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
> +
> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
> +				break;
> +
>  			if (local_clock_noinstr() - time_start > limit) {
>  				dev->poll_time_limit = true;
>  				break;

Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?

Will

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v2] Enable haltpoll for arm64

[Christoph Lameter (Ampere)]

On Mon, 20 Nov 2023, Mihai Carabas wrote:

> This patchset enables the usage of haltpoll governer on arm64. This is
> specifically interesting for KVM guests by reducing the IPC latencies.

Any updates on this one? We see good improvements with this patchset using 
a variety of loads on Ampere platforms.

Re: [PATCH v2] Enable haltpoll for arm64

[Christoph Lameter (Ampere)]

On Mon, 20 Nov 2023, Mihai Carabas wrote:

> This patchset enables the usage of haltpoll governer on arm64. This is
> specifically interesting for KVM guests by reducing the IPC latencies.

Any updates on this one? We see good improvements with this patchset using 
a variety of loads on Ampere platforms.

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v2] Enable haltpoll for arm64

[Mihai Carabas]

Hello,

How can we move this patchset forward?

Thank you,
Mihai

La 20.11.2023 16:01, Mihai Carabas a scris:
> This patchset enables the usage of haltpoll governer on arm64. This is
> specifically interesting for KVM guests by reducing the IPC latencies.
>
> Here are some benchmarks without/with haltpoll for a KVM guest:
>
> a) without haltpoll:
> perf bench sched pipe
> # Running 'sched/pipe' benchmark:
> # Executed 1000000 pipe operations between two processes
>
>       Total time: 8.138 [sec]
>
>              8.138094 usecs/op
>               122878 ops/sec
>
> b) with haltpoll:
> perf bench sched pipe
> # Running 'sched/pipe' benchmark:
> # Executed 1000000 pipe operations between two processes
>
>       Total time: 5.003 [sec]
>
>              5.003085 usecs/op
>               199876 ops/sec
>
> v2 changes from v1:
> - added patch 7 where we change cpu_relax with smp_cond_load_relaxed per PeterZ
>    (this improves by 50% at least the CPU cycles consumed in the tests above:
>    10,716,881,137 now vs 14,503,014,257 before)
> - removed the ifdef from patch 1 per RafaelW
>
>
> Joao Martins (6):
>    x86: Move ARCH_HAS_CPU_RELAX to arch
>    x86/kvm: Move haltpoll_want() to be arch defined
>    governors/haltpoll: Drop kvm_para_available() check
>    arm64: Select ARCH_HAS_CPU_RELAX
>    arm64: Define TIF_POLLING_NRFLAG
>    cpuidle-haltpoll: ARM64 support
>
> Mihai Carabas (1):
>    cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed
>
>   arch/Kconfig                            |  3 +++
>   arch/arm64/Kconfig                      |  1 +
>   arch/arm64/include/asm/thread_info.h    |  6 ++++++
>   arch/x86/Kconfig                        |  1 +
>   arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
>   arch/x86/kernel/kvm.c                   | 10 ++++++++++
>   drivers/cpuidle/Kconfig                 |  4 ++--
>   drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
>   drivers/cpuidle/governors/haltpoll.c    |  5 +----
>   drivers/cpuidle/poll_state.c            | 14 +++++++++-----
>   include/linux/cpuidle_haltpoll.h        |  5 +++++
>   11 files changed, 41 insertions(+), 17 deletions(-)
>


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v2] Enable haltpoll for arm64

[Mihai Carabas]

Hello,

How can we move this patchset forward?

Thank you,
Mihai

La 20.11.2023 16:01, Mihai Carabas a scris:
> This patchset enables the usage of haltpoll governer on arm64. This is
> specifically interesting for KVM guests by reducing the IPC latencies.
>
> Here are some benchmarks without/with haltpoll for a KVM guest:
>
> a) without haltpoll:
> perf bench sched pipe
> # Running 'sched/pipe' benchmark:
> # Executed 1000000 pipe operations between two processes
>
>       Total time: 8.138 [sec]
>
>              8.138094 usecs/op
>               122878 ops/sec
>
> b) with haltpoll:
> perf bench sched pipe
> # Running 'sched/pipe' benchmark:
> # Executed 1000000 pipe operations between two processes
>
>       Total time: 5.003 [sec]
>
>              5.003085 usecs/op
>               199876 ops/sec
>
> v2 changes from v1:
> - added patch 7 where we change cpu_relax with smp_cond_load_relaxed per PeterZ
>    (this improves by 50% at least the CPU cycles consumed in the tests above:
>    10,716,881,137 now vs 14,503,014,257 before)
> - removed the ifdef from patch 1 per RafaelW
>
>
> Joao Martins (6):
>    x86: Move ARCH_HAS_CPU_RELAX to arch
>    x86/kvm: Move haltpoll_want() to be arch defined
>    governors/haltpoll: Drop kvm_para_available() check
>    arm64: Select ARCH_HAS_CPU_RELAX
>    arm64: Define TIF_POLLING_NRFLAG
>    cpuidle-haltpoll: ARM64 support
>
> Mihai Carabas (1):
>    cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed
>
>   arch/Kconfig                            |  3 +++
>   arch/arm64/Kconfig                      |  1 +
>   arch/arm64/include/asm/thread_info.h    |  6 ++++++
>   arch/x86/Kconfig                        |  1 +
>   arch/x86/include/asm/cpuidle_haltpoll.h |  1 +
>   arch/x86/kernel/kvm.c                   | 10 ++++++++++
>   drivers/cpuidle/Kconfig                 |  4 ++--
>   drivers/cpuidle/cpuidle-haltpoll.c      |  8 ++------
>   drivers/cpuidle/governors/haltpoll.c    |  5 +----
>   drivers/cpuidle/poll_state.c            | 14 +++++++++-----
>   include/linux/cpuidle_haltpoll.h        |  5 +++++
>   11 files changed, 41 insertions(+), 17 deletions(-)
>

Re: [PATCH v2] Enable haltpoll for arm64

[Rafael J. Wysocki]

Hi,

On Thu, Jan 25, 2024 at 3:40 PM Mihai Carabas <mihai.carabas@oracle.com> wrote:
>
> Hello,
>
> How can we move this patchset forward?

There have been some comments and a tag has been given.

Update the series (to address the comments and add the tag where
applicable) and resend.

Thanks!

Re: [PATCH v2] Enable haltpoll for arm64

[Rafael J. Wysocki]

Hi,

On Thu, Jan 25, 2024 at 3:40 PM Mihai Carabas <mihai.carabas@oracle.com> wrote:
>
> Hello,
>
> How can we move this patchset forward?

There have been some comments and a tag has been given.

Update the series (to address the comments and add the tag where
applicable) and resend.

Thanks!

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

La 11.12.2023 13:46, Will Deacon a scris:
> On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>> smp_cond_load_relaxed which basically does a "wfe".
>>
>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>> ---
>>   drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>   1 file changed, 9 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>> index 9b6d90a72601..440cd713e39a 100644
>> --- a/drivers/cpuidle/poll_state.c
>> +++ b/drivers/cpuidle/poll_state.c
>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>   
>>   		limit = cpuidle_poll_time(drv, dev);
>>   
>> -		while (!need_resched()) {
>> -			cpu_relax();
>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>> -				continue;
>> -
>> +		for (;;) {
>>   			loop_count = 0;
>> +
>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>> +					      (VAL & _TIF_NEED_RESCHED) ||
>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>> +
>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>> +				break;
>> +
>>   			if (local_clock_noinstr() - time_start > limit) {
>>   				dev->poll_time_limit = true;
>>   				break;
> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?

This controls the build of poll_state.c and the generic definition of 
smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose 
other approach here?


>
> Will

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

La 11.12.2023 13:46, Will Deacon a scris:
> On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>> smp_cond_load_relaxed which basically does a "wfe".
>>
>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>> ---
>>   drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>   1 file changed, 9 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>> index 9b6d90a72601..440cd713e39a 100644
>> --- a/drivers/cpuidle/poll_state.c
>> +++ b/drivers/cpuidle/poll_state.c
>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>   
>>   		limit = cpuidle_poll_time(drv, dev);
>>   
>> -		while (!need_resched()) {
>> -			cpu_relax();
>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>> -				continue;
>> -
>> +		for (;;) {
>>   			loop_count = 0;
>> +
>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>> +					      (VAL & _TIF_NEED_RESCHED) ||
>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>> +
>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>> +				break;
>> +
>>   			if (local_clock_noinstr() - time_start > limit) {
>>   				dev->poll_time_limit = true;
>>   				break;
> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?

This controls the build of poll_state.c and the generic definition of 
smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose 
other approach here?


>
> Will



_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Will Deacon]

On Sun, Jan 28, 2024 at 11:22:50PM +0200, Mihai Carabas wrote:
> La 11.12.2023 13:46, Will Deacon a scris:
> > On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
> > > cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> > > smp_cond_load_relaxed which basically does a "wfe".
> > > 
> > > Suggested-by: Peter Zijlstra <peterz@infradead.org>
> > > Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
> > > ---
> > >   drivers/cpuidle/poll_state.c | 14 +++++++++-----
> > >   1 file changed, 9 insertions(+), 5 deletions(-)
> > > 
> > > diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
> > > index 9b6d90a72601..440cd713e39a 100644
> > > --- a/drivers/cpuidle/poll_state.c
> > > +++ b/drivers/cpuidle/poll_state.c
> > > @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
> > >   		limit = cpuidle_poll_time(drv, dev);
> > > -		while (!need_resched()) {
> > > -			cpu_relax();
> > > -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
> > > -				continue;
> > > -
> > > +		for (;;) {
> > >   			loop_count = 0;
> > > +
> > > +			smp_cond_load_relaxed(&current_thread_info()->flags,
> > > +					      (VAL & _TIF_NEED_RESCHED) ||
> > > +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
> > > +
> > > +			if (loop_count < POLL_IDLE_RELAX_COUNT)
> > > +				break;
> > > +
> > >   			if (local_clock_noinstr() - time_start > limit) {
> > >   				dev->poll_time_limit = true;
> > >   				break;
> > Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
> 
> This controls the build of poll_state.c and the generic definition of
> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
> other approach here?

Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
that doesn't use cpu_relax() doesn't make sense to me.

Will

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Will Deacon]

On Sun, Jan 28, 2024 at 11:22:50PM +0200, Mihai Carabas wrote:
> La 11.12.2023 13:46, Will Deacon a scris:
> > On Mon, Nov 20, 2023 at 04:01:38PM +0200, Mihai Carabas wrote:
> > > cpu_relax on ARM64 does a simple "yield". Thus we replace it with
> > > smp_cond_load_relaxed which basically does a "wfe".
> > > 
> > > Suggested-by: Peter Zijlstra <peterz@infradead.org>
> > > Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
> > > ---
> > >   drivers/cpuidle/poll_state.c | 14 +++++++++-----
> > >   1 file changed, 9 insertions(+), 5 deletions(-)
> > > 
> > > diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
> > > index 9b6d90a72601..440cd713e39a 100644
> > > --- a/drivers/cpuidle/poll_state.c
> > > +++ b/drivers/cpuidle/poll_state.c
> > > @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
> > >   		limit = cpuidle_poll_time(drv, dev);
> > > -		while (!need_resched()) {
> > > -			cpu_relax();
> > > -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
> > > -				continue;
> > > -
> > > +		for (;;) {
> > >   			loop_count = 0;
> > > +
> > > +			smp_cond_load_relaxed(&current_thread_info()->flags,
> > > +					      (VAL & _TIF_NEED_RESCHED) ||
> > > +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
> > > +
> > > +			if (loop_count < POLL_IDLE_RELAX_COUNT)
> > > +				break;
> > > +
> > >   			if (local_clock_noinstr() - time_start > limit) {
> > >   				dev->poll_time_limit = true;
> > >   				break;
> > Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
> 
> This controls the build of poll_state.c and the generic definition of
> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
> other approach here?

Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
that doesn't use cpu_relax() doesn't make sense to me.

Will

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>> smp_cond_load_relaxed which basically does a "wfe".
>>>>
>>>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>>>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>>>> ---
>>>>    drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>>>    1 file changed, 9 insertions(+), 5 deletions(-)
>>>>
>>>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>>>> index 9b6d90a72601..440cd713e39a 100644
>>>> --- a/drivers/cpuidle/poll_state.c
>>>> +++ b/drivers/cpuidle/poll_state.c
>>>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>>>    		limit = cpuidle_poll_time(drv, dev);
>>>> -		while (!need_resched()) {
>>>> -			cpu_relax();
>>>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>>>> -				continue;
>>>> -
>>>> +		for (;;) {
>>>>    			loop_count = 0;
>>>> +
>>>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>>>> +					      (VAL & _TIF_NEED_RESCHED) ||
>>>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>>>> +
>>>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>>>> +				break;
>>>> +
>>>>    			if (local_clock_noinstr() - time_start > limit) {
>>>>    				dev->poll_time_limit = true;
>>>>    				break;
>>> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
>> This controls the build of poll_state.c and the generic definition of
>> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
>> other approach here?
> Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
> that doesn't use cpu_relax() doesn't make sense to me.

The generic code for smp_cond_load_relaxed is using cpu_relax and this 
one is used on x86 - so ARCH_HAS_CPU_RELAX is a prerequisite on x86 when 
using haltpoll. Only on ARM64 this is overwritten. Moreover 
ARCH_HAS_CPU_RELAX is controlling the function definition for 
cpuidle_poll_state_init (this is how it was originally designed).

Thanks,
Mihai

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Mihai Carabas]

>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>> smp_cond_load_relaxed which basically does a "wfe".
>>>>
>>>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>>>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>>>> ---
>>>>    drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>>>    1 file changed, 9 insertions(+), 5 deletions(-)
>>>>
>>>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>>>> index 9b6d90a72601..440cd713e39a 100644
>>>> --- a/drivers/cpuidle/poll_state.c
>>>> +++ b/drivers/cpuidle/poll_state.c
>>>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>>>    		limit = cpuidle_poll_time(drv, dev);
>>>> -		while (!need_resched()) {
>>>> -			cpu_relax();
>>>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>>>> -				continue;
>>>> -
>>>> +		for (;;) {
>>>>    			loop_count = 0;
>>>> +
>>>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>>>> +					      (VAL & _TIF_NEED_RESCHED) ||
>>>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>>>> +
>>>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>>>> +				break;
>>>> +
>>>>    			if (local_clock_noinstr() - time_start > limit) {
>>>>    				dev->poll_time_limit = true;
>>>>    				break;
>>> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
>> This controls the build of poll_state.c and the generic definition of
>> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
>> other approach here?
> Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
> that doesn't use cpu_relax() doesn't make sense to me.

The generic code for smp_cond_load_relaxed is using cpu_relax and this 
one is used on x86 - so ARCH_HAS_CPU_RELAX is a prerequisite on x86 when 
using haltpoll. Only on ARM64 this is overwritten. Moreover 
ARCH_HAS_CPU_RELAX is controlling the function definition for 
cpuidle_poll_state_init (this is how it was originally designed).

Thanks,
Mihai

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Ankur Arora]

Mihai Carabas <mihai.carabas@oracle.com> writes:

>>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>>> smp_cond_load_relaxed which basically does a "wfe".
>>>>>
>>>>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>>>>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>>>>> ---
>>>>>    drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>>>>    1 file changed, 9 insertions(+), 5 deletions(-)
>>>>>
>>>>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>>>>> index 9b6d90a72601..440cd713e39a 100644
>>>>> --- a/drivers/cpuidle/poll_state.c
>>>>> +++ b/drivers/cpuidle/poll_state.c
>>>>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>>>>    		limit = cpuidle_poll_time(drv, dev);
>>>>> -		while (!need_resched()) {
>>>>> -			cpu_relax();
>>>>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>>>>> -				continue;
>>>>> -
>>>>> +		for (;;) {
>>>>>    			loop_count = 0;
>>>>> +
>>>>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>>>>> +					      (VAL & _TIF_NEED_RESCHED) ||
>>>>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>>>>> +
>>>>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>>>>> +				break;
>>>>> +
>>>>>    			if (local_clock_noinstr() - time_start > limit) {
>>>>>    				dev->poll_time_limit = true;
>>>>>    				break;
>>>> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
>>> This controls the build of poll_state.c and the generic definition of
>>> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
>>> other approach here?
>> Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
>> that doesn't use cpu_relax() doesn't make sense to me.
>
> The generic code for smp_cond_load_relaxed is using cpu_relax and this one is
> used on x86 - so ARCH_HAS_CPU_RELAX is a prerequisite on x86 when using
> haltpoll. Only on ARM64 this is overwritten. Moreover ARCH_HAS_CPU_RELAX is
> controlling the function definition for cpuidle_poll_state_init (this is how it
> was originally designed).

I suspect Will's point is that the term ARCH_HAS_CPU_RELAX doesn't make
a whole lot of sense when we are only indirectly using cpu_relax() in
the series.

Also, all archs define cpu_relax() (though some as just a barrier()) so
ARCH_HAS_CPU_RELAX .

Maybe an arch can instead just opt into polling in idle?

Perhaps something like this trivial patch:

--
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5edec175b9bf..d80c98c64fd4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -367,7 +367,7 @@ config ARCH_MAY_HAVE_PC_FDC
 config GENERIC_CALIBRATE_DELAY
 	def_bool y

-config ARCH_HAS_CPU_RELAX
+config ARCH_WANTS_IDLE_POLL
 	def_bool y

 config ARCH_HIBERNATION_POSSIBLE
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 55437f5e0c3a..6a0a1f16a5c3 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -36,7 +36,7 @@
 #include <asm/cpu.h>
 #endif

-#define ACPI_IDLE_STATE_START	(IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX) ? 1 : 0)
+#define ACPI_IDLE_STATE_START	(IS_ENABLED(CONFIG_ARCH_WANTS_IDLE_POLL) ? 1 : 0)

 static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER;
 module_param(max_cstate, uint, 0400);
@@ -787,7 +787,7 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 	if (max_cstate == 0)
 		max_cstate = 1;

-	if (IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX)) {
+	if (IS_ENABLED(CONFIG_ARCH_WANTS_IDLE_POLL)) {
 		cpuidle_poll_state_init(drv);
 		count = 1;
 	} else {
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index d103342b7cfc..23f48d99f0f2 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -7,7 +7,7 @@ obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 obj-$(CONFIG_DT_IDLE_GENPD)		  += dt_idle_genpd.o
-obj-$(CONFIG_ARCH_HAS_CPU_RELAX)	  += poll_state.o
+obj-$(CONFIG_ARCH_WANTS_IDLE_POLL)	  += poll_state.o
 obj-$(CONFIG_HALTPOLL_CPUIDLE)		  += cpuidle-haltpoll.o

 ##################################################################################
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3183aeb7f5b4..53e55a91d55d 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -275,7 +275,7 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev,
 }
 #endif

-#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_HAS_CPU_RELAX)
+#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_WANTS_IDLE_POLL)
 void cpuidle_poll_state_init(struct cpuidle_driver *drv);
 #else
 static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {}

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 7/7] cpuidle/poll_state: replace cpu_relax with smp_cond_load_relaxed

[Ankur Arora]

Mihai Carabas <mihai.carabas@oracle.com> writes:

>>>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>>>> smp_cond_load_relaxed which basically does a "wfe".
>>>>>
>>>>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>>>>> Signed-off-by: Mihai Carabas <mihai.carabas@oracle.com>
>>>>> ---
>>>>>    drivers/cpuidle/poll_state.c | 14 +++++++++-----
>>>>>    1 file changed, 9 insertions(+), 5 deletions(-)
>>>>>
>>>>> diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
>>>>> index 9b6d90a72601..440cd713e39a 100644
>>>>> --- a/drivers/cpuidle/poll_state.c
>>>>> +++ b/drivers/cpuidle/poll_state.c
>>>>> @@ -26,12 +26,16 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
>>>>>    		limit = cpuidle_poll_time(drv, dev);
>>>>> -		while (!need_resched()) {
>>>>> -			cpu_relax();
>>>>> -			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
>>>>> -				continue;
>>>>> -
>>>>> +		for (;;) {
>>>>>    			loop_count = 0;
>>>>> +
>>>>> +			smp_cond_load_relaxed(&current_thread_info()->flags,
>>>>> +					      (VAL & _TIF_NEED_RESCHED) ||
>>>>> +					      (loop_count++ >= POLL_IDLE_RELAX_COUNT));
>>>>> +
>>>>> +			if (loop_count < POLL_IDLE_RELAX_COUNT)
>>>>> +				break;
>>>>> +
>>>>>    			if (local_clock_noinstr() - time_start > limit) {
>>>>>    				dev->poll_time_limit = true;
>>>>>    				break;
>>>> Doesn't this make ARCH_HAS_CPU_RELAX a complete misnomer?
>>> This controls the build of poll_state.c and the generic definition of
>>> smp_cond_load_relaxed (used by x86) is using cpu_relax(). Do you propose
>>> other approach here?
>> Give it a better name? Having ARCH_HAS_CPU_RELAX control a piece of code
>> that doesn't use cpu_relax() doesn't make sense to me.
>
> The generic code for smp_cond_load_relaxed is using cpu_relax and this one is
> used on x86 - so ARCH_HAS_CPU_RELAX is a prerequisite on x86 when using
> haltpoll. Only on ARM64 this is overwritten. Moreover ARCH_HAS_CPU_RELAX is
> controlling the function definition for cpuidle_poll_state_init (this is how it
> was originally designed).

I suspect Will's point is that the term ARCH_HAS_CPU_RELAX doesn't make
a whole lot of sense when we are only indirectly using cpu_relax() in
the series.

Also, all archs define cpu_relax() (though some as just a barrier()) so
ARCH_HAS_CPU_RELAX .

Maybe an arch can instead just opt into polling in idle?

Perhaps something like this trivial patch:

--
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5edec175b9bf..d80c98c64fd4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -367,7 +367,7 @@ config ARCH_MAY_HAVE_PC_FDC
 config GENERIC_CALIBRATE_DELAY
 	def_bool y

-config ARCH_HAS_CPU_RELAX
+config ARCH_WANTS_IDLE_POLL
 	def_bool y

 config ARCH_HIBERNATION_POSSIBLE
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 55437f5e0c3a..6a0a1f16a5c3 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -36,7 +36,7 @@
 #include <asm/cpu.h>
 #endif

-#define ACPI_IDLE_STATE_START	(IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX) ? 1 : 0)
+#define ACPI_IDLE_STATE_START	(IS_ENABLED(CONFIG_ARCH_WANTS_IDLE_POLL) ? 1 : 0)

 static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER;
 module_param(max_cstate, uint, 0400);
@@ -787,7 +787,7 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 	if (max_cstate == 0)
 		max_cstate = 1;

-	if (IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX)) {
+	if (IS_ENABLED(CONFIG_ARCH_WANTS_IDLE_POLL)) {
 		cpuidle_poll_state_init(drv);
 		count = 1;
 	} else {
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index d103342b7cfc..23f48d99f0f2 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -7,7 +7,7 @@ obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 obj-$(CONFIG_DT_IDLE_GENPD)		  += dt_idle_genpd.o
-obj-$(CONFIG_ARCH_HAS_CPU_RELAX)	  += poll_state.o
+obj-$(CONFIG_ARCH_WANTS_IDLE_POLL)	  += poll_state.o
 obj-$(CONFIG_HALTPOLL_CPUIDLE)		  += cpuidle-haltpoll.o

 ##################################################################################
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3183aeb7f5b4..53e55a91d55d 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -275,7 +275,7 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev,
 }
 #endif

-#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_HAS_CPU_RELAX)
+#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_WANTS_IDLE_POLL)
 void cpuidle_poll_state_init(struct cpuidle_driver *drv);
 #else
 static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {}