[RFC PATCH v2 5/7] Documentation: Add three sysctls for smart idle poll

[Yang Zhang]

To reduce the cost of poll, we introduce three sysctl to control the
poll time.

Signed-off-by: Yang Zhang <yang.zhang.wz@xxxxxxxxx>
Signed-off-by: Quan Xu <quan.xu0@xxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Cc: Chris Wright <chrisw@xxxxxxxxxxxx>
Cc: Alok Kataria <akataria@xxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: "Luis R. Rodriguez" <mcgrof@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx>
Cc: Krzysztof Kozlowski <krzk@xxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Petr Mladek <pmladek@xxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Jessica Yu <jeyu@xxxxxxxxxx>
Cc: Larry Finger <Larry.Finger@xxxxxxxxxxxx>
Cc: zijun_hu <zijun_hu@xxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Johannes Berg <johannes.berg@xxxxxxxxx>
Cc: Ian Abbott <abbotti@xxxxxxxxx>
Cc: linux-doc@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
---
 Documentation/sysctl/kernel.txt | 25 +++++++++++++++++++++++++
 arch/x86/kernel/paravirt.c      |  4 ++++
 include/linux/kernel.h          |  6 ++++++
 kernel/sysctl.c                 | 23 +++++++++++++++++++++++
 4 files changed, 58 insertions(+)

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index bac23c1..67447b8 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -63,6 +63,9 @@ show up in /proc/sys/kernel:
 - perf_event_max_stack
 - perf_event_max_contexts_per_stack
 - pid_max
+- poll_grow                   [ X86 only ]
+- poll_shrink                 [ X86 only ]
+- poll_threshold_ns           [ X86 only ]
 - powersave-nap               [ PPC only ]
 - printk
 - printk_delay
@@ -702,6 +705,28 @@ kernel tries to allocate a number starting from this one.
 
 ==============================================================
 
+poll_grow: (X86 only)
+
+This parameter is multiplied in the grow_poll_ns() to increase the poll time.
+By default, the values is 2.
+
+==============================================================
+poll_shrink: (X86 only)
+
+This parameter is divided in the shrink_poll_ns() to reduce the poll time.
+By default, the values is 2.
+
+==============================================================
+poll_threshold_ns: (X86 only)
+
+This parameter controls the max poll time before entering real idle path.
+This parameter is expected to take effect only when running inside a VM.
+It would make no sense to turn on it in bare mental.
+By default, the values is 0 means don't poll. It is recommended to change
+the value to non-zero if running latency-bound workloads inside VM.
+
+==============================================================
+
 powersave-nap: (PPC only)
 
 If set, Linux-PPC will use the 'nap' mode of powersaving,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index a11b2c2..0b92f8f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -318,6 +318,10 @@ struct pv_idle_ops pv_idle_ops = {
 	.update = paravirt_nop,
 };
 
+unsigned long poll_threshold_ns;
+unsigned int poll_shrink = 2;
+unsigned int poll_grow = 2;
+
 __visible struct pv_irq_ops pv_irq_ops = {
 	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
 	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index bd6d96c..6cb2820 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -462,6 +462,12 @@ extern __scanf(2, 0)
 
 extern bool crash_kexec_post_notifiers;
 
+#ifdef CONFIG_PARAVIRT
+extern unsigned long poll_threshold_ns;
+extern unsigned int poll_shrink;
+extern unsigned int poll_grow;
+#endif
+
 /*
  * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
  * holds a CPU number which is executing panic() currently. A value of
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6648fbb..9b86a8f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1229,6 +1229,29 @@ static int sysrq_sysctl_handler(struct ctl_table *table, int write,
 		.extra2		= &one,
 	},
 #endif
+#ifdef CONFIG_PARAVIRT
+	{
+		.procname       = "halt_poll_threshold",
+		.data           = &poll_threshold_ns,
+		.maxlen         = sizeof(unsigned long),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "halt_poll_grow",
+		.data           = &poll_grow,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "halt_poll_shrink",
+		.data           = &poll_shrink,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif
 	{ }
 };
 
-- 
1.8.3.1