From 3dc167ba5729ddd2d8e3fa1841653792c295d3f1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 19 May 2020 19:25:06 +0200 Subject: sched/cputime: Improve cputime_adjust() People report that utime and stime from /proc//stat become very wrong when the numbers are big enough, especially if you watch these counters incrementally. Specifically, the current implementation of: stime*rtime/total, results in a saw-tooth function on top of the desired line, where the teeth grow in size the larger the values become. IOW, it has a relative error. The result is that, when watching incrementally as time progresses (for large values), we'll see periods of pure stime or utime increase, irrespective of the actual ratio we're striving for. Replace scale_stime() with a math64.h helper: mul_u64_u64_div_u64() that is far more accurate. This also allows architectures to override the implementation -- for instance they can opt for the old algorithm if this new one turns out to be too expensive for them. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200519172506.GA317395@hirez.programming.kicks-ass.net --- lib/math/div64.c | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'lib') diff --git a/lib/math/div64.c b/lib/math/div64.c index 368ca7fd0d82..3952a07130d8 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -190,3 +190,44 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) return __iter_div_u64_rem(dividend, divisor, remainder); } EXPORT_SYMBOL(iter_div_u64_rem); + +#ifndef mul_u64_u64_div_u64 +u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c) +{ + u64 res = 0, div, rem; + int shift; + + /* can a * b overflow ? */ + if (ilog2(a) + ilog2(b) > 62) { + /* + * (b * a) / c is equal to + * + * (b / c) * a + + * (b % c) * a / c + * + * if nothing overflows. Can the 1st multiplication + * overflow? Yes, but we do not care: this can only + * happen if the end result can't fit in u64 anyway. + * + * So the code below does + * + * res = (b / c) * a; + * b = b % c; + */ + div = div64_u64_rem(b, c, &rem); + res = div * a; + b = rem; + + shift = ilog2(a) + ilog2(b) - 62; + if (shift > 0) { + /* drop precision */ + b >>= shift; + c >>= shift; + if (!c) + return res; + } + } + + return res + div64_u64(a * b, c); +} +#endif -- cgit v1.2.3 From 1abdfe706a579a702799fce465bceb9fb01d407c Mon Sep 17 00:00:00 2001 From: Alex Belits Date: Thu, 25 Jun 2020 18:34:41 -0400 Subject: lib: Restrict cpumask_local_spread to houskeeping CPUs The current implementation of cpumask_local_spread() does not respect the isolated CPUs, i.e., even if a CPU has been isolated for Real-Time task, it will return it to the caller for pinning of its IRQ threads. Having these unwanted IRQ threads on an isolated CPU adds up to a latency overhead. Restrict the CPUs that are returned for spreading IRQs only to the available housekeeping CPUs. Signed-off-by: Alex Belits Signed-off-by: Nitesh Narayan Lal Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200625223443.2684-2-nitesh@redhat.com --- lib/cpumask.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/cpumask.c b/lib/cpumask.c index fb22fb266f93..85da6ab4fbb5 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -6,6 +6,7 @@ #include #include #include +#include /** * cpumask_next - get the next cpu in a cpumask @@ -205,22 +206,27 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) */ unsigned int cpumask_local_spread(unsigned int i, int node) { - int cpu; + int cpu, hk_flags; + const struct cpumask *mask; + hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ; + mask = housekeeping_cpumask(hk_flags); /* Wrap: we always want a cpu. */ - i %= num_online_cpus(); + i %= cpumask_weight(mask); if (node == NUMA_NO_NODE) { - for_each_cpu(cpu, cpu_online_mask) + for_each_cpu(cpu, mask) { if (i-- == 0) return cpu; + } } else { /* NUMA first. */ - for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) + for_each_cpu_and(cpu, cpumask_of_node(node), mask) { if (i-- == 0) return cpu; + } - for_each_cpu(cpu, cpu_online_mask) { + for_each_cpu(cpu, mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; -- cgit v1.2.3