From 60a9ce57e7c5ac1df3a39fb941022bbfa40c0862 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 29 Jun 2017 19:15:09 +0200 Subject: sched/cputime: Rename vtime fields The current "snapshot" based naming on vtime fields suggests we record some past event but that's a low level picture of their actual purpose which comes out blurry. The real point of these fields is to run a basic state machine that tracks down cputime entry while switching between contexts. So lets reflect that with more meaningful names. Tested-by: Luiz Capitulino Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Rik van Riel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1498756511-11714-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c4ca7433d9d..ff001646549e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -689,7 +689,7 @@ struct task_struct { struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_t vtime_seqcount; - unsigned long long vtime_snap; + unsigned long long vtime_starttime; enum { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, @@ -697,7 +697,7 @@ struct task_struct { VTIME_USER, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, - } vtime_snap_whence; + } vtime_state; #endif #ifdef CONFIG_NO_HZ_FULL -- cgit From bac5b6b6b11560f323e71d0ebac4061cfe5f56c0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 29 Jun 2017 19:15:10 +0200 Subject: sched/cputime: Move the vtime task fields to their own struct We are about to add vtime accumulation fields to the task struct. Let's avoid more bloatification and gather vtime information to their own struct. Tested-by: Luiz Capitulino Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Rik van Riel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1498756511-11714-5-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff001646549e..eeff8a024f0c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -223,6 +223,21 @@ struct task_cputime { #define prof_exp stime #define sched_exp sum_exec_runtime +enum vtime_state { + /* Task is sleeping or running in a CPU with VTIME inactive: */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active: */ + VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active: */ + VTIME_SYS, +}; + +struct vtime { + seqcount_t seqcount; + unsigned long long starttime; + enum vtime_state state; +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -688,16 +703,7 @@ struct task_struct { u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqcount_t vtime_seqcount; - unsigned long long vtime_starttime; - enum { - /* Task is sleeping or running in a CPU with VTIME inactive: */ - VTIME_INACTIVE = 0, - /* Task runs in userspace in a CPU with VTIME active: */ - VTIME_USER, - /* Task runs in kernelspace in a CPU with VTIME active: */ - VTIME_SYS, - } vtime_state; + struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL -- cgit From 2a42eb9594a1480b4ead9e036e06ee1290e5fa6d Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 29 Jun 2017 19:15:11 +0200 Subject: sched/cputime: Accumulate vtime on top of nsec clocksource Currently the cputime source used by vtime is jiffies. When we cross a context boundary and jiffies have changed since the last snapshot, the pending cputime is accounted to the switching out context. This system works ok if the ticks are not aligned across CPUs. If they instead are aligned (ie: all fire at the same time) and the CPUs run in userspace, the jiffies change is only observed on tick exit and therefore the user cputime is accounted as system cputime. This is because the CPU that maintains timekeeping fires its tick at the same time as the others. It updates jiffies in the middle of the tick and the other CPUs see that update on IRQ exit: CPU 0 (timekeeper) CPU 1 ------------------- ------------- jiffies = N ... run in userspace for a jiffy tick entry tick entry (sees jiffies = N) set jiffies = N + 1 tick exit tick exit (sees jiffies = N + 1) account 1 jiffy as stime Fix this with using a nanosec clock source instead of jiffies. The cputime is then accumulated and flushed everytime the pending delta reaches a jiffy in order to mitigate the accounting overhead. [ fweisbec: changelog, rebase on struct vtime, field renames, add delta on cputime readers, keep idle vtime as-is (low overhead accounting), harmonize clock sources. ] Suggested-by: Thomas Gleixner Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Signed-off-by: Wanpeng Li Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Rik van Riel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1498756511-11714-6-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index eeff8a024f0c..4818126c5153 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -236,6 +236,9 @@ struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; + u64 utime; + u64 stime; + u64 gtime; }; struct sched_info { -- cgit