From: Johannes Weiner hannes@cmpxchg.org

Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset.

During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing.

Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing.

How many page->flags does this leave us with on 32-bit?

20 bits are always page flags

21 if you have an MMU

23 with the zone bits for DMA, Normal, HighMem, Movable

29 with the sparsemem section bits

30 if PAE is enabled

31 with this patch.

So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits.

Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Daniel Drake drake@endlessm.com Tested-by: Suren Baghdasaryan surenb@google.com Cc: Christopher Lameter cl@linux.com Cc: Ingo Molnar mingo@redhat.com Cc: Johannes Weiner jweiner@fb.com Cc: Mike Galbraith efault@gmx.de Cc: Peter Enderborg peter.enderborg@sony.com Cc: Randy Dunlap rdunlap@infradead.org Cc: Shakeel Butt shakeelb@google.com Cc: Tejun Heo tj@kernel.org Cc: Vinayak Menon vinmenon@codeaurora.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 2cbfbc7903756e79b10ac97e44be2e80d1b091c6) Signed-off-by: Jack Wang jinpu.wang@cloud.ionos.com --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 +- include/linux/swap.h | 2 +- include/trace/events/mmflags.h | 1 + mm/filemap.c | 9 ++-- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/swap_state.c | 1 + mm/vmscan.c | 1 + mm/vmstat.c | 1 + mm/workingset.c | 95 ++++++++++++++++++++++------------ 11 files changed, 77 insertions(+), 42 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f679f5268467..71b7a8bc82ea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 584b14c774c1..6900ad07554b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -74,13 +74,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -273,6 +274,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 4fd1ab9565ba..1db5eca571d3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -304,7 +304,7 @@ struct vma_swap_readahead {

/* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); void workingset_update_node(struct radix_tree_node *node, void *private);

diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 72162f3a03fa..40b9cc3bfaf9 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -89,6 +89,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/mm/filemap.c b/mm/filemap.c index e2e738cc08b1..9f995985e12f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -817,12 +817,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 930f2aa3bb4d..4ef967ad24ec 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2327,6 +2327,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/migrate.c b/mm/migrate.c index 8c57cdd77ba5..4e018550f8e7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -673,6 +673,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index 326439428daf..3931379fac4d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -435,6 +435,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/vmscan.c b/mm/vmscan.c index 9734e62654fa..06a7d1605a5d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2056,6 +2056,7 @@ static void shrink_active_list(unsigned long nr_to_scan, }

ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); }

diff --git a/mm/vmstat.c b/mm/vmstat.c index 6389e876c7a7..efab0fca0bb7 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1074,6 +1074,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index a1d3ccf1cd24..44ac09bf92fd 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */

#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT)

/* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly;

-static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);

return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); }

static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset;

entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; }

/** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)

lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); }

/** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid;

- unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);

rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);

/* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK;

inc_lruvec_state(lruvec, WORKINGSET_REFAULT);

- if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; }

/**

From: Johannes Weiner hannes@cmpxchg.org

There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version.

[akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Suren Baghdasaryan surenb@google.com Tested-by: Daniel Drake drake@endlessm.com Cc: Christopher Lameter cl@linux.com Cc: Ingo Molnar mingo@redhat.com Cc: Johannes Weiner jweiner@fb.com Cc: Mike Galbraith efault@gmx.de Cc: Peter Enderborg peter.enderborg@sony.com Cc: Randy Dunlap rdunlap@infradead.org Cc: Shakeel Butt shakeelb@google.com Cc: Tejun Heo tj@kernel.org Cc: Vinayak Menon vinmenon@codeaurora.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 5fc05f18905a39f2809484541ec75b1c1c501ef9) Signed-off-by: Jack Wang jinpu.wang@cloud.ionos.com --- .../platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +++----- arch/s390/appldata/appldata_os.c | 4 ---- drivers/cpuidle/governors/menu.c | 4 ---- fs/proc/loadavg.c | 3 --- include/linux/sched/loadavg.h | 21 +++++++++++++++---- kernel/debug/kdb/kdb_main.c | 7 +------ kernel/sched/loadavg.c | 15 ------------- 8 files changed, 22 insertions(+), 43 deletions(-)

diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 882944c36ef5..5d8e8b6bb1cc 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -49,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info) cpu = info->policy->cpu; busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);

- CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1); + info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1); pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n", cpu, busy_spus, info->busy_spus);

diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 1fbb5da17dd2..509cf6709131 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -987,9 +987,9 @@ static void spu_calc_load(void) unsigned long active_tasks; /* fixed-point */

active_tasks = count_active_contexts() * FIXED_1; - CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks); - CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks); - CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks); + spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks); + spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks); + spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks); }

static void spusched_wake(unsigned long data) @@ -1071,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx, } }

-#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int show_spu_loadavg(struct seq_file *s, void *private) { int a, b, c; diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 45b3178200ab..a8aac17e1e82 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -24,10 +24,6 @@

#include "appldata.h"

- -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - /* * OS data * diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 48eaf2879228..b459d5680a0c 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -132,10 +132,6 @@ struct menu_device { int interval_ptr; };

- -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static inline int get_loadavg(unsigned long load) { return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 9bc5c58c00ee..b3c0475f88de 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -10,9 +10,6 @@ #include <linux/seqlock.h> #include <linux/time.h>

-#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int loadavg_proc_show(struct seq_file *m, void *v) { unsigned long avnrun[3]; diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */

-#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)

extern void calc_global_load(unsigned long ticks);

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 993db6b2348e..3083df2a783e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2586,16 +2586,11 @@ static int kdb_summary(int argc, const char **argv) } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60);

- /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); -#undef LOAD_INT -#undef LOAD_FRAC + /* Display in kilobytes */ #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 89a989e4d758..d37eb9fe8aa8 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -95,21 +95,6 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; }

-/* - * a1 = a0 * e + a * (1 - e) - */ -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - unsigned long newload; - - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; - - return newload / FIXED_1; -} - #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average.

From: Johannes Weiner hannes@cmpxchg.org

kernel/sched/sched.h includes "stats.h" half-way through the file. The next patch introduces users of sched.h's rq locking functions and update_rq_clock() in kernel/sched/stats.h. Move those definitions up in the file so they are available in stats.h.

Link: http://lkml.kernel.org/r/20180828172258.3185-7-hannes@cmpxchg.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Suren Baghdasaryan surenb@google.com Tested-by: Daniel Drake drake@endlessm.com Cc: Christopher Lameter cl@linux.com Cc: Ingo Molnar mingo@redhat.com Cc: Johannes Weiner jweiner@fb.com Cc: Mike Galbraith efault@gmx.de Cc: Peter Enderborg peter.enderborg@sony.com Cc: Randy Dunlap rdunlap@infradead.org Cc: Shakeel Butt shakeelb@google.com Cc: Tejun Heo tj@kernel.org Cc: Vinayak Menon vinmenon@codeaurora.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 69d22d2b3563701686c4b97b3c1c8a00238f7d13) Signed-off-by: Jack Wang jinpu.wang@cloud.ionos.com

Conflicts: kernel/sched/sched.h --- kernel/sched/sched.h | 164 +++++++++++++++++++++---------------------- 1 file changed, 82 insertions(+), 82 deletions(-)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 452b56923c6d..5ea86c072c07 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -848,6 +848,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues)

+extern void update_rq_clock(struct rq *rq); + static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); @@ -959,6 +961,86 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) #endif }

+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irqsave(&rq->lock, rf->flags); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock_irq(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irq(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_relock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_repin_lock(rq, rf); +} + +static inline void +rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irqrestore(&rq->lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irq(&rq->lock); +} + +static inline void +rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, @@ -1623,8 +1705,6 @@ static inline void rq_last_tick_reset(struct rq *rq) #endif }

-extern void update_rq_clock(struct rq *rq); - extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);

@@ -1698,86 +1778,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } static inline void sched_avg_update(struct rq *rq) { } #endif

-struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(rq->lock); - -struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(p->pi_lock) - __acquires(rq->lock); - -static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) - __releases(rq->lock) - __releases(p->pi_lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); -} - -static inline void -rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irqsave(&rq->lock, rf->flags); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock_irq(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irq(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_relock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_repin_lock(rq, rf); -} - -static inline void -rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irqrestore(&rq->lock, rf->flags); -} - -static inline void -rq_unlock_irq(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irq(&rq->lock); -} - -static inline void -rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT

From: Johannes Weiner hannes@cmpxchg.org

When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous.

In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system.

A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays:

cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions

These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs.

To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage).

[hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Daniel Drake drake@endlessm.com Tested-by: Suren Baghdasaryan surenb@google.com Cc: Christopher Lameter cl@linux.com Cc: Ingo Molnar mingo@redhat.com Cc: Johannes Weiner jweiner@fb.com Cc: Mike Galbraith efault@gmx.de Cc: Peter Enderborg peter.enderborg@sony.com Cc: Randy Dunlap rdunlap@infradead.org Cc: Shakeel Butt shakeelb@google.com Cc: Tejun Heo tj@kernel.org Cc: Vinayak Menon vinmenon@codeaurora.org Cc: Randy Dunlap rdunlap@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit e8574dc1f30d2d7f10a64acab3c7d64f22f8e991) Signed-off-by: Jack Wang jinpu.wang@cloud.ionos.com

Conflicts: kernel/sched/Makefile kernel/sched/sched.h --- Documentation/accounting/psi.txt | 64 +++ include/linux/psi.h | 28 ++ include/linux/psi_types.h | 92 +++++ include/linux/sched.h | 10 + init/Kconfig | 15 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 12 +- kernel/sched/psi.c | 657 +++++++++++++++++++++++++++++++ kernel/sched/sched.h | 3 + kernel/sched/stats.h | 86 ++++ mm/compaction.c | 5 + mm/filemap.c | 15 +- mm/page_alloc.c | 9 + mm/vmscan.c | 11 + 15 files changed, 1006 insertions(+), 6 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c

diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt new file mode 100644 index 000000000000..3753a82f1cf5 --- /dev/null +++ b/Documentation/accounting/psi.txt @@ -0,0 +1,64 @@ +================================ +PSI - Pressure Stall Information +================================ + +:Date: April, 2018 +:Author: Johannes Weiner hannes@cmpxchg.org + +When CPU, memory or IO devices are contended, workloads experience +latency spikes, throughput losses, and run the risk of OOM kills. + +Without an accurate measure of such contention, users are forced to +either play it safe and under-utilize their hardware resources, or +roll the dice and frequently suffer the disruptions resulting from +excessive overcommit. + +The psi feature identifies and quantifies the disruptions caused by +such resource crunches and the time impact it has on complex workloads +or even entire systems. + +Having an accurate measure of productivity losses caused by resource +scarcity aids users in sizing workloads to hardware--or provisioning +hardware according to workload demand. + +As psi aggregates this information in realtime, systems can be managed +dynamically using techniques such as load shedding, migrating jobs to +other systems or data centers, or strategically pausing or killing low +priority or restartable batch jobs. + +This allows maximizing hardware utilization without sacrificing +workload health or risking major disruptions such as OOM kills. + +Pressure interface +================== + +Pressure information for each resource is exported through the +respective file in /proc/pressure/ -- cpu, memory, and io. + +The format for CPU is as such: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +and for memory and IO: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 +full avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +The "some" line indicates the share of time in which at least some +tasks are stalled on a given resource. + +The "full" line indicates the share of time in which all non-idle +tasks are stalled on a given resource simultaneously. In this state +actual CPU cycles are going to waste, and a workload that spends +extended time in this state is considered to be thrashing. This has +severe impact on performance, and it's useful to distinguish this +situation from a state where some tasks are stalled but the CPU is +still doing productive work. As such, time spent in this subset of the +stall state is tracked separately and exported in the "full" averages. + +The ratios are tracked as recent trends over ten, sixty, and three +hundred second windows, which gives insight into short term events as +well as medium and long term trends. The total absolute stall time is +tracked and exported as well, to allow detection of latency spikes +which wouldn't necessarily make a dent in the time averages, or to +average trends over custom time frames. diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include <linux/psi_types.h> +#include <linux/sched.h> + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include <linux/seqlock.h> +#include <linux/types.h> + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 866439c361a9..abfa2ad97e19 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/signal_types.h> +#include <linux/psi_types.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h>

@@ -668,6 +669,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0;

@@ -926,6 +931,10 @@ struct task_struct { siginfo_t *last_siginfo;

struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1355,6 +1364,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/init/Kconfig b/init/Kconfig index 46075327c165..d19c853088c1 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -470,6 +470,21 @@ config TASK_IO_ACCOUNTING

Say N if unsure.

+config PSI + bool "Pressure stall information tracking" + help + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. + + If you say Y here, the kernel will create /proc/pressure/ with the + pressure statistics files cpu, memory, and io. These will indicate + the share of walltime in which some or all tasks in the system are + delayed due to contention of the respective resource. + + For more details see Documentation/accounting/psi.txt. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting"

source "kernel/rcu/Kconfig" diff --git a/kernel/fork.c b/kernel/fork.c index 6d6ce2c3a364..b6df619c6e67 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1667,6 +1667,10 @@ static __latent_entropy struct task_struct *copy_process(

p->default_timer_slack_ns = current->timer_slack_ns;

+#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p);

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index a9ee16bbc693..d996b71d6713 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -27,3 +27,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a0b7e66c7281..7387ab03c40a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -756,8 +756,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq);

- if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + }

p->sched_class->enqueue_task(rq, p, flags); } @@ -767,8 +769,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq);

- if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + }

p->sched_class->dequeue_task(rq, p, flags); } @@ -2071,6 +2075,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); }

@@ -3032,6 +3037,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq);

rq_unlock(rq, &rf);

@@ -5962,6 +5968,8 @@ void __init sched_init(void)

init_schedstats();

+ psi_init(); + scheduler_running = 1; }

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..595414599b98 --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,657 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner hannes@cmpxchg.org + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include <linux/sched/loadavg.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/seqlock.h> +#include <linux/cgroup.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/psi.h> +#include "sched.h" + +static int psi_bug __read_mostly; + +bool psi_disabled __read_mostly; +core_param(psi_disabled, psi_disabled, bool, 0644); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (psi_disabled) + return; + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires > psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); + + if (!delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + psi_group_change(&psi_system, cpu, clear, set); +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(psi_system.pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +static int psi_show(struct seq_file *m, struct psi_group *group, + enum psi_res res) +{ + int full; + + if (psi_disabled) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index e73d5d68602d..8139982a18a6 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -268,6 +268,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED

#include <linux/cgroup.h> +#include <linux/psi.h>

struct cfs_rq; struct rt_rq; @@ -1717,6 +1718,8 @@ static inline void rq_last_tick_reset(struct rq *rq) #endif }

+extern void update_rq_clock(struct rq *rq); + extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);

diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baf500d12b7c..8ee534f7ac42 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) #define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */

+#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (psi_disabled) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (psi_disabled) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (psi_disabled) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (psi_disabled) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/mm/compaction.c b/mm/compaction.c index 85395dc6eb13..c9827c820a92 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -22,6 +22,7 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/page_owner.h> +#include <linux/psi.h> #include "internal.h"

#ifdef CONFIG_COMPACTION @@ -2038,11 +2039,15 @@ static int kcompactd(void *p) pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;

while (!kthread_should_stop()) { + unsigned long pflags; + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); wait_event_freezable(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat));

+ psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); }

return 0; diff --git a/mm/filemap.c b/mm/filemap.c index 51ed20eb2f2b..739750167f13 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -37,6 +37,7 @@ #include <linux/cleancache.h> #include <linux/rmap.h> #include <linux/delayacct.h> +#include <linux/psi.h> #include "internal.h"

#define CREATE_TRACE_POINTS @@ -977,11 +978,14 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; + unsigned long pflags; int ret = 0;

- if (bit_nr == PG_locked && !PageSwapBacked(page) && + if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { - delayacct_thrashing_start(); + if (!PageSwapBacked(page)) + delayacct_thrashing_start(); + psi_memstall_enter(&pflags); thrashing = true; }

@@ -1023,8 +1027,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,

finish_wait(q, wait);

- if (thrashing) - delayacct_thrashing_end(); + if (thrashing) { + if (!PageSwapBacked(page)) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + }

/* * A signal could leave PageWaiters set. Clearing it here if diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a2f365f40433..69041ffd87bc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -67,6 +67,7 @@ #include <linux/ftrace.h> #include <linux/lockdep.h> #include <linux/nmi.h> +#include <linux/psi.h>

#include <asm/sections.h> #include <asm/tlbflush.h> @@ -3371,15 +3372,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned long pflags; unsigned int noreclaim_flag;

if (!order) return NULL;

+ psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags);

if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3568,11 +3574,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct reclaim_state reclaim_state; int progress; unsigned int noreclaim_flag; + unsigned long pflags;

cond_resched();

/* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); fs_reclaim_acquire(gfp_mask); reclaim_state.reclaimed_slab = 0; @@ -3584,6 +3592,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; fs_reclaim_release(gfp_mask); memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags);

cond_resched();

diff --git a/mm/vmscan.c b/mm/vmscan.c index 06a7d1605a5d..860fc0f12176 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -49,6 +49,7 @@ #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> +#include <linux/psi.h>

#include <asm/tlbflush.h> #include <asm/div64.h> @@ -3134,6 +3135,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, { struct zonelist *zonelist; unsigned long nr_reclaimed; + unsigned long pflags; int nid; unsigned int noreclaim_flag; struct scan_control sc = { @@ -3162,9 +3164,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx);

+ psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags);

trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);

@@ -3329,6 +3335,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long pflags; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -3338,6 +3345,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) .may_unmap = 1, .may_swap = 1, }; + + psi_memstall_enter(&pflags); + count_vm_event(PAGEOUTRUN);

do { @@ -3432,6 +3442,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)

out: snapshot_refaults(NULL, pgdat); + psi_memstall_leave(&pflags); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller

From: Olof Johansson olof@lixom.net

The existing code triggered an invalid warning about 'rq' possibly being used uninitialized. Instead of doing the silly warning suppression by initializa it to NULL, refactor the code to bail out early instead.

Warning was:

kernel/sched/psi.c: In function `cgroup_move_task': kernel/sched/psi.c:639:13: warning: `rq' may be used uninitialized in this function [-Wmaybe-uninitialized]

Link: http://lkml.kernel.org/r/20181103183339.8669-1-olof@lixom.net Fixes: 2ce7135adc9ad ("psi: cgroup support") Signed-off-by: Olof Johansson olof@lixom.net Reviewed-by: Andrew Morton akpm@linux-foundation.org Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit c904648b96279bd44e1f08f474274cd1ee52675d) Signed-off-by: Jack Wang jinpu.wang@cloud.ionos.com --- kernel/sched/psi.c | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7cdecfc010af..3d7355d7c3e3 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -633,38 +633,39 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - bool move_psi = !psi_disabled; unsigned int task_flags = 0; struct rq_flags rf; struct rq *rq;

- if (move_psi) { - rq = task_rq_lock(task, &rf); + if (psi_disabled) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + }

- if (task_on_rq_queued(task)) - task_flags = TSK_RUNNING; - else if (task->in_iowait) - task_flags = TSK_IOWAIT; + rq = task_rq_lock(task, &rf);

- if (task->flags & PF_MEMSTALL) - task_flags |= TSK_MEMSTALL; + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT;

- if (task_flags) - psi_task_change(task, task_flags, 0); - } + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL;

- /* - * Lame to do this here, but the scheduler cannot be locked - * from the outside, so we move cgroups from inside sched/. - */ + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ rcu_assign_pointer(task->cgroups, to);

- if (move_psi) { - if (task_flags) - psi_task_change(task, 0, task_flags); + if (task_flags) + psi_task_change(task, 0, task_flags);

- task_rq_unlock(rq, task, &rf); - } + task_rq_unlock(rq, task, &rf); } #endif /* CONFIG_CGROUPS */