mainline inclusion from mainline-v5.4 commit e0c274472d5d27f277af722e017525e0b33784cj category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA
--------------------------------
Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others.
With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier:
1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time.
To avoid double negatives, rename psi_disabled= to psi=.
2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled.
In terms of numbers before and after this patch, Mel says:
: The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so;
Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Tested-by: Mel Gorman mgorman@techsingularity.net Reported-by: Mel Gorman mgorman@techsingularity.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn --- Documentation/admin-guide/kernel-parameters.txt | 4 ++++ include/linux/psi.h | 3 ++- init/Kconfig | 9 ++++++++ kernel/sched/psi.c | 30 +++++++++++++++++-------- kernel/sched/stats.h | 8 +++---- 5 files changed, 40 insertions(+), 14 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 257b0d1..2a5e76c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3710,6 +3710,10 @@ before loading. See Documentation/blockdev/ramdisk.txt.
+ psi= [KNL] Enable or disable pressure stall information + tracking. + Format: <bool> + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725a..7006008 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H
+#include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h>
@@ -9,7 +10,7 @@
#ifdef CONFIG_PSI
-extern bool psi_disabled; +extern struct static_key_false psi_disabled;
void psi_init(void);
diff --git a/init/Kconfig b/init/Kconfig index c797e89..ea7cfe74 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -522,6 +522,15 @@ config PSI
Say N if unsure.
+config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi_enable=1 + on the kernel commandline during boot. + endmenu # "CPU/Task time and stats accounting"
config CPU_ISOLATION diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3d7355d..fe24de3 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@
static int psi_bug __read_mostly;
-bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi);
/* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group)
void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + }
psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq;
- if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
*flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq;
- if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0;
cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -637,7 +649,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq;
- if (psi_disabled) { + if (static_branch_likely(&psi_disabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -673,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full;
- if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP;
update_stats(group); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 7cd0104..1b49905 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -87,7 +87,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING;
- if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
if (!wakeup || p->sched_psi_wake_requeue) { @@ -107,7 +107,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0;
- if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
if (!sleep) { @@ -123,7 +123,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep)
static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -149,7 +149,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return;
if (unlikely(rq->curr->flags & PF_MEMSTALL))