From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 1899ad18c6072d689896badafb81267b0a1092a4 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

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 Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.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 | 94 +++++++++++++++++++++++++++--------------- 11 files changed, 76 insertions(+), 42 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e7d2bca..b55dd22 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -164,6 +164,7 @@ 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 7eb776a..97c0918 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ 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, @@ -281,6 +282,8 @@ static inline int PagePoisoned(const struct page *page) 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 b7cfad3..12a39b2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -322,7 +322,7 @@ 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);

/* Do not use directly, use workingset_lookup_update */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index b817bf1..edc9adf 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -88,6 +88,7 @@ {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 f578d4e..fd906c1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1023,12 +1023,9 @@ 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); if (!PagePercpuRef(page)) lru_cache_add(page); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 31f1c58..f71b7a7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2531,6 +2531,7 @@ 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 90aa493..a41ef7f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -684,6 +684,8 @@ 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 2137e2d..3b538ef 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -460,6 +460,7 @@ 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 e8befe7..90b47ca 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2188,6 +2188,7 @@ 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 96028cc..e183cb2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1145,6 +1145,7 @@ int fragmentation_index(struct zone *zone, unsigned int order) "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 a1f61b3..039eea7 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 +280,50 @@ 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);

/* + * Calculate the refault distance * 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 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. + * 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

mainline inclusion from mainline-v5.4 commit 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

It's going to be used in a later patch. Keep the churn separate.

Link: http://lkml.kernel.org/r/20180828172258.3185-6-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 Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- include/linux/sched/loadavg.h | 3 + kernel/sched/loadavg.c | 138 +++++++++++++++++++++--------------------- 2 files changed, 72 insertions(+), 69 deletions(-)

diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62..4859bea 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ return newload / FIXED_1; }

+extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)

diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 54fbdfb..28a5165 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -91,6 +91,75 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; }

+/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. @@ -210,75 +279,6 @@ static long calc_load_nohz_fold(void) return delta; }

-/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-CPU ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 246b3b3342c9b0a2e24cda2178be87bc36e1c874 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

do_sched_yield() disables IRQs, looks up this_rq() and locks it. The next patch is adding another site with the same pattern, so provide a convenience function for it.

Link: http://lkml.kernel.org/r/20180828172258.3185-8-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 Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- kernel/sched/core.c | 4 +--- kernel/sched/sched.h | 12 ++++++++++++ 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4870913..a8dece9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5026,9 +5026,7 @@ static void do_sched_yield(void) struct rq_flags rf; struct rq *rq;

- local_irq_disable(); - rq = this_rq(); - rq_lock(rq, &rf); + rq = this_rq_lock_irq(&rf);

schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index afcd75a..6d0a6a6 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1219,6 +1219,18 @@ static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) raw_spin_unlock(&rq->lock); }

+static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + rq_lock(rq, rf); + return rq; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT,

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 2ce7135adc9ad081aa3c49744144376ac74fea60 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others.

This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup.

Link: http://lkml.kernel.org/r/20180828172258.3185-10-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: Vinayak Menon vinmenon@codeaurora.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- Documentation/accounting/psi.txt | 9 +++ Documentation/admin-guide/cgroup-v2.rst | 18 +++++ include/linux/cgroup-defs.h | 4 ++ include/linux/cgroup.h | 15 ++++ include/linux/psi.h | 25 +++++++ init/Kconfig | 4 ++ kernel/cgroup/cgroup.c | 44 +++++++++++- kernel/sched/psi.c | 118 +++++++++++++++++++++++++++++--- 8 files changed, 227 insertions(+), 10 deletions(-)

diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index 3753a82..b8ca28b 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -62,3 +62,12 @@ 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. + +Cgroup2 interface +================= + +In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem +mounted, pressure stall information is also tracked for tasks grouped +into cgroups. Each subdirectory in the cgroupfs mountpoint contains +cpu.pressure, memory.pressure, and io.pressure files; the format is +the same as the /proc/pressure/ files. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 9c194bc..c57b4fc 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -966,6 +966,12 @@ All time durations are in microseconds. $PERIOD duration. "max" for $MAX indicates no limit. If only one number is written, $MAX is updated.

+ cpu.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for CPU. See + Documentation/accounting/psi.txt for details. +

Memory ------ @@ -1287,6 +1293,12 @@ PAGE_SIZE multiple when read back. higher than the limit for an extended period of time. This reduces the impact on the workload and memory management.

+ memory.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for memory. See + Documentation/accounting/psi.txt for details. +

Usage Guidelines ~~~~~~~~~~~~~~~~ @@ -1424,6 +1436,12 @@ IO Interface Files

8:16 rbps=2097152 wbps=max riops=max wiops=max

+ io.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for IO. See + Documentation/accounting/psi.txt for details. +

Writeback ~~~~~~~~~ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index cad1a82..c026665 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> #include <linux/bpf-cgroup.h> +#include <linux/psi_types.h>

#ifdef CONFIG_CGROUPS

@@ -442,6 +443,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work;

+ /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf;

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f227364..60b68ff 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -669,6 +669,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); }

+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -723,6 +728,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; }

+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf05..8e0725a 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,9 @@ #include <linux/psi_types.h> #include <linux/sched.h>

+struct seq_file; +struct css_set; + #ifdef CONFIG_PSI

extern bool psi_disabled; @@ -16,6 +19,14 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags);

+int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */

static inline void psi_init(void) {} @@ -23,6 +34,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {}

+#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */

#endif /* _LINUX_PSI_H */ diff --git a/init/Kconfig b/init/Kconfig index 17a057d..a6e412a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -515,6 +515,10 @@ config PSI the share of walltime in which some or all tasks in the system are delayed due to contention of the respective resource.

+ In kernels with cgroup support, cgroups (cgroup2 only) will + have cpu.pressure, memory.pressure, and io.pressure files, + which aggregate pressure stalls for the grouped tasks only. + For more details see Documentation/accounting/psi.txt.

Say N if unsure. diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6f4dcdd..f6ad3ae 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -55,6 +55,7 @@ #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/sched/cputime.h> +#include <linux/psi.h> #include <net/sock.h>

#define CREATE_TRACE_POINTS @@ -842,7 +843,7 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING);

- rcu_assign_pointer(task->cgroups, to_cset); + cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } @@ -3451,6 +3452,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) return ret; }

+#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); +} +#endif + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4632,6 +4648,23 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of, .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cpu_stat_show, }, +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_io_pressure_show, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_memory_pressure_show, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_cpu_pressure_show, + }, +#endif { } /* terminate */ };

@@ -4692,6 +4725,7 @@ static void css_free_rwork_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + psi_cgroup_free(cgrp); if (cgroup_on_dfl(cgrp)) cgroup_rstat_exit(cgrp); kfree(cgrp); @@ -4950,10 +4984,14 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; - ret = cgroup_bpf_inherit(cgrp); + ret = psi_cgroup_alloc(cgrp); if (ret) goto out_idr_free;

+ ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_psi_free; + spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4993,6 +5031,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)

return cgrp;

+out_psi_free: + psi_cgroup_free(cgrp); out_idr_free: cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_stat_exit: diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 5954145..7cdecfc 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -473,9 +473,35 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->clock_work, PSI_FREQ); }

+static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); + struct psi_group *group; + void *iter = NULL;

if (!task->pid) return; @@ -492,17 +518,23 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set;

- psi_group_change(&psi_system, cpu, clear, set); + while ((group = iterate_groups(task, &iter))) + psi_group_change(group, cpu, clear, set); }

void psi_memstall_tick(struct task_struct *task, int cpu) { - struct psi_group_cpu *groupc; + struct psi_group *group; + void *iter = NULL;

- groupc = per_cpu_ptr(psi_system.pcpu, cpu); - write_seqcount_begin(&groupc->seq); - record_times(groupc, cpu, true); - write_seqcount_end(&groupc->seq); + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } }

/** @@ -565,8 +597,78 @@ void psi_memstall_leave(unsigned long *flags) rq_unlock_irq(rq, &rf); }

-static int psi_show(struct seq_file *m, struct psi_group *group, - enum psi_res res) +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (psi_disabled) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (psi_disabled) + return; + + cancel_delayed_work_sync(&cgroup->psi.clock_work); + free_percpu(cgroup->psi.pcpu); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +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 (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + } + + /* + * 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); + + if (move_psi) { + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); + } +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full;

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit e0c274472d5d27f277af722e017525e0b33784cd 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- 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 54127ef..a3621003 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3638,6 +3638,10 @@ 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 a6e412a..0aee577 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -523,6 +523,15 @@ 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))

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 1b69ac6b40ebd85eed73e4dbccde2a36961ab990 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

psi has provisions to shut off the periodic aggregation worker when there is a period of no task activity - and thus no data that needs aggregating. However, while developing psi monitoring, Suren noticed that the aggregation clock currently won't stay shut off for good.

Debugging this revealed a flaw in the idle design: an aggregation run will see no task activity and decide to go to sleep; shortly thereafter, the kworker thread that executed the aggregation will go idle and cause a scheduling change, during which the psi callback will kick the !pending worker again. This will ping-pong forever, and is equivalent to having no shut-off logic at all (but with more code!)

Fix this by exempting aggregation workers from psi's clock waking logic when the state change is them going to sleep. To do this, tag workers with the last work function they executed, and if in psi we see a worker going to sleep after aggregating psi data, we will not reschedule the aggregation work item.

What if the worker is also executing other items before or after?

Any psi state times that were incurred by work items preceding the aggregation work will have been collected from the per-cpu buckets during the aggregation itself. If there are work items following the aggregation work, the worker's last_func tag will be overwritten and the aggregator will be kept alive to process this genuine new activity.

If the aggregation work is the last thing the worker does, and we decide to go idle, the brief period of non-idle time incurred between the aggregation run and the kworker's dequeue will be stranded in the per-cpu buckets until the clock is woken by later activity. But that should not be a problem. The buckets can hold 4s worth of time, and future activity will wake the clock with a 2s delay, giving us 2s worth of data we can leave behind when disabling aggregation. If it takes a worker more than two seconds to go idle after it finishes its last work item, we likely have bigger problems in the system, and won't notice one sample that was averaged with a bogus per-CPU weight.

Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org Fixes: eb414681d5a0 ("psi: pressure stall information for CPU, memory, and IO") Signed-off-by: Johannes Weiner hannes@cmpxchg.org Reported-by: Suren Baghdasaryan surenb@google.com Acked-by: Tejun Heo tj@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Lai Jiangshan jiangshanlai@gmail.com 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- kernel/sched/psi.c | 21 +++++++++++++++++---- kernel/workqueue.c | 23 +++++++++++++++++++++++ kernel/workqueue_internal.h | 6 +++++- 3 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3..c348478 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */

+#include "../workqueue_internal.h" #include <linux/sched/loadavg.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++;

write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); }

static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL;

if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set;

- while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } }

void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a46532b..60f5730 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -906,6 +906,26 @@ void wq_worker_sleeping(struct task_struct *task) }

/** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + +/** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set @@ -2191,6 +2211,9 @@ static void process_one_work(struct worker *worker, struct work_struct *work) worker_clr_flags(worker, WORKER_NICED); }

+ /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 30cfed2..498de0e 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -54,6 +54,9 @@ struct worker {

/* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; };

/** @@ -68,9 +71,10 @@ static inline struct worker *current_wq_worker(void)

/* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task);

#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 147e1a97c4a0bdd43f55a582a9416bb9092563a9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Patch series "psi: pressure stall monitors", v3.

Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices.

Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now.

This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached.

As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring.

With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish.

In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly.

The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.:

/* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd);

When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal.

The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded.

Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files.

The patches were developed in collaboration with Johannes Weiner.

This patch (of 5):

Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default.

This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations.

Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner hannes@cmpxchg.org Signed-off-by: Suren Baghdasaryan surenb@google.com Cc: Dennis Zhou dennis@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Li Zefan lizefan@huawei.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tejun Heo tj@kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- fs/kernfs/file.c | 31 ++++++++++++++++++++----------- include/linux/kernfs.h | 6 ++++++ 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index dbf5bc2..2d8b91f 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + + return DEFAULT_POLLMASK; +} + static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + __poll_t ret;

if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;

- poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait);

kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + return ret; }

static void kernfs_notify_workfn(struct work_struct *work) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index c41790d..ab81a22 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -26,6 +26,7 @@ struct vm_area_struct; struct super_block; struct file_system_type; +struct poll_table_struct;

struct kernfs_open_node; struct kernfs_iattrs; @@ -268,6 +269,9 @@ struct kernfs_ops { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off);

+ __poll_t (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);

#ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -360,6 +364,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn);

const void *kernfs_super_ns(struct super_block *sb);

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v5.4 commit 33b2d6302abc4ccea1d9b3f095e2e27b02ca264e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Patch series "psi: pressure stall monitors", v6.

This is a respin of: https://lwn.net/ml/linux-kernel/20190308184311.144521-1-surenb%40google.com/

Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices.

Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high-enough frequency right now.

This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached.

As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring.

With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly.

The new interface is straight-forward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.:

/* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000" fd = open("/proc/pressure/memory") write(fd, trigger, sizeof(trigger)) while (poll() >= 0) { ... }; close(fd);

When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal.

The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded.

Patches 1-6 prepare the psi code for polling support. Patch 7 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files.

The patches were developed in collaboration with Johannes Weiner.

This patch (of 7):

The psi monitoring patches will need to determine the same states as record_times(). To avoid calculating them twice, maintain a state mask that can be consulted cheaply. Do this in a separate patch to keep the churn in the main feature patch at a minimum.

This adds 4-byte state_mask member into psi_group_cpu struct which results in its first cacheline-aligned part becoming 52 bytes long. Add explicit values to enumeration element counters that affect psi_group_cpu struct size.

Link: http://lkml.kernel.org/r/20190124211518.244221-4-surenb@google.com Signed-off-by: Suren Baghdasaryan surenb@google.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Dennis Zhou dennis@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Li Zefan lizefan@huawei.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tejun Heo tj@kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- include/linux/psi_types.h | 9 ++++++--- kernel/sched/psi.c | 29 +++++++++++++++++++---------- 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 2cf422d..762c6bb 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -11,7 +11,7 @@ enum psi_task_count { NR_IOWAIT, NR_MEMSTALL, NR_RUNNING, - NR_PSI_TASK_COUNTS, + NR_PSI_TASK_COUNTS = 3, };

/* Task state bitmasks */ @@ -24,7 +24,7 @@ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES, + NR_PSI_RESOURCES = 3, };

/* @@ -41,7 +41,7 @@ enum psi_states { PSI_CPU_SOME, /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES, + NR_PSI_STATES = 6, };

struct psi_group_cpu { @@ -53,6 +53,9 @@ struct psi_group_cpu { /* States of the tasks belonging to this group */ unsigned int tasks[NR_PSI_TASK_COUNTS];

+ /* Aggregate pressure state derived from the tasks */ + u32 state_mask; + /* Period time sampling buckets for each state of interest (ns) */ u32 times[NR_PSI_STATES];

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 0e97ca9..22c1505 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -213,17 +213,17 @@ static bool test_state(unsigned int *tasks, enum psi_states state) 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; + enum psi_states s; unsigned int seq; - int s; + u32 state_mask;

/* 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_mask = groupc->state_mask; state_start = groupc->state_start; } while (read_seqcount_retry(&groupc->seq, seq));

@@ -239,7 +239,7 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) * (u32) and our reported pressure close to what's * actually happening. */ - if (test_state(tasks, s)) + if (state_mask & (1 << s)) times[s] += now - state_start;

delta = times[s] - groupc->times_prev[s]; @@ -407,15 +407,15 @@ static void record_times(struct psi_group_cpu *groupc, int cpu, delta = now - groupc->state_start; groupc->state_start = now;

- if (test_state(groupc->tasks, PSI_IO_SOME)) { + if (groupc->state_mask & (1 << PSI_IO_SOME)) { groupc->times[PSI_IO_SOME] += delta; - if (test_state(groupc->tasks, PSI_IO_FULL)) + if (groupc->state_mask & (1 << PSI_IO_FULL)) groupc->times[PSI_IO_FULL] += delta; }

- if (test_state(groupc->tasks, PSI_MEM_SOME)) { + if (groupc->state_mask & (1 << PSI_MEM_SOME)) { groupc->times[PSI_MEM_SOME] += delta; - if (test_state(groupc->tasks, PSI_MEM_FULL)) + if (groupc->state_mask & (1 << PSI_MEM_FULL)) groupc->times[PSI_MEM_FULL] += delta; else if (memstall_tick) { u32 sample; @@ -436,10 +436,10 @@ static void record_times(struct psi_group_cpu *groupc, int cpu, } }

- if (test_state(groupc->tasks, PSI_CPU_SOME)) + if (groupc->state_mask & (1 << PSI_CPU_SOME)) groupc->times[PSI_CPU_SOME] += delta;

- if (test_state(groupc->tasks, PSI_NONIDLE)) + if (groupc->state_mask & (1 << PSI_NONIDLE)) groupc->times[PSI_NONIDLE] += delta; }

@@ -448,6 +448,8 @@ static void psi_group_change(struct psi_group *group, int cpu, { struct psi_group_cpu *groupc; unsigned int t, m; + enum psi_states s; + u32 state_mask = 0;

groupc = per_cpu_ptr(group->pcpu, cpu);

@@ -480,6 +482,13 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++;

+ /* Calculate state mask representing active states */ + for (s = 0; s < NR_PSI_STATES; s++) { + if (test_state(groupc->tasks, s)) + state_mask |= (1 << s); + } + groupc->state_mask = state_mask; + write_seqcount_end(&groupc->seq); }

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v5.4 commit bcc78db64168eb6dede056fed2999f75f7ace309 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Rename psi_group structure member fields used for calculating psi totals and averages for clear distinction between them and for trigger-related fields that will be added by "psi: introduce psi monitor".

[surenb@google.com: v6] Link: http://lkml.kernel.org/r/20190319235619.260832-4-surenb@google.com Link: http://lkml.kernel.org/r/20190124211518.244221-5-surenb@google.com Signed-off-by: Suren Baghdasaryan surenb@google.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Dennis Zhou dennis@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Li Zefan lizefan@huawei.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tejun Heo tj@kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- include/linux/psi_types.h | 14 +++++++------- kernel/sched/psi.c | 41 +++++++++++++++++++++-------------------- 2 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 762c6bb..4d1c1f6 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -69,17 +69,17 @@ struct psi_group_cpu { };

struct psi_group { - /* Protects data updated during an aggregation */ - struct mutex stat_lock; + /* Protects data used by the aggregator */ + struct mutex avgs_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; + /* Running pressure averages */ + u64 avg_total[NR_PSI_STATES - 1]; + u64 avg_last_update; + u64 avg_next_update; + struct delayed_work avgs_work;

/* Total stall times and sampled pressure averages */ u64 total[NR_PSI_STATES - 1]; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 281702d..4fb4d991 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -165,7 +165,7 @@ static int __init setup_psi(char *str) .pcpu = &system_group_pcpu, };

-static void psi_update_work(struct work_struct *work); +static void psi_avgs_work(struct work_struct *work);

static void group_init(struct psi_group *group) { @@ -173,9 +173,9 @@ static void group_init(struct psi_group *group)

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); + group->avg_next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); + mutex_init(&group->avgs_lock); }

void __init psi_init(void) @@ -278,7 +278,7 @@ static bool update_stats(struct psi_group *group) int cpu; int s;

- mutex_lock(&group->stat_lock); + mutex_lock(&group->avgs_lock);

/* * Collect the per-cpu time buckets and average them into a @@ -319,7 +319,7 @@ static bool update_stats(struct psi_group *group)

/* avgX= */ now = sched_clock(); - expires = group->next_update; + expires = group->avg_next_update; if (now < expires) goto out; if (now - expires >= psi_period) @@ -332,14 +332,14 @@ static bool update_stats(struct psi_group *group) * 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; + group->avg_next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->avg_last_update + (missed_periods * psi_period)); + group->avg_last_update = now;

for (s = 0; s < NR_PSI_STATES - 1; s++) { u32 sample;

- sample = group->total[s] - group->total_prev[s]; + sample = group->total[s] - group->avg_total[s]; /* * Due to the lockless sampling of the time buckets, * recorded time deltas can slip into the next period, @@ -359,22 +359,22 @@ static bool update_stats(struct psi_group *group) */ if (sample > period) sample = period; - group->total_prev[s] += sample; + group->avg_total[s] += sample; calc_avgs(group->avg[s], missed_periods, sample, period); } out: - mutex_unlock(&group->stat_lock); + mutex_unlock(&group->avgs_lock); return nonidle_total; }

-static void psi_update_work(struct work_struct *work) +static void psi_avgs_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); + group = container_of(dwork, struct psi_group, avgs_work);

/* * If there is task activity, periodically fold the per-cpu @@ -391,8 +391,9 @@ static void psi_update_work(struct work_struct *work) u64 now;

now = sched_clock(); - if (group->next_update > now) - delay = nsecs_to_jiffies(group->next_update - now) + 1; + if (group->avg_next_update > now) + delay = nsecs_to_jiffies( + group->avg_next_update - now) + 1; schedule_delayed_work(dwork, delay); } } @@ -546,13 +547,13 @@ void psi_task_change(struct task_struct *task, int clear, int set) */ if (unlikely((clear & TSK_RUNNING) && (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_update_work)) + wq_worker_last_func(task) == psi_avgs_work)) wake_clock = false;

while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); - if (wake_clock && !delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); + if (wake_clock && !delayed_work_pending(&group->avgs_work)) + schedule_delayed_work(&group->avgs_work, PSI_FREQ); } }

@@ -649,7 +650,7 @@ void psi_cgroup_free(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return;

- cancel_delayed_work_sync(&cgroup->psi.clock_work); + cancel_delayed_work_sync(&cgroup->psi.avgs_work); free_percpu(cgroup->psi.pcpu); }

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v5.4 commit 333f3017c5a893b000b2b4a3529814ce93fa83d7 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Introduce changed_states parameter into collect_percpu_times to track the states changed since the last update.

This will be needed to detect whether polled states activated in the monitor patch.

Link: http://lkml.kernel.org/r/20190319235619.260832-6-surenb@google.com Signed-off-by: Suren Baghdasaryan surenb@google.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Dennis Zhou dennis@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Li Zefan lizefan@huawei.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tejun Heo tj@kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- kernel/sched/psi.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ace5ed9..1b99eef 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -210,7 +210,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state) } }

-static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +static void get_recent_times(struct psi_group *group, int cpu, u32 *times, + u32 *pchanged_states) { struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); u64 now, state_start; @@ -218,6 +219,8 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) unsigned int seq; u32 state_mask;

+ *pchanged_states = 0; + /* Snapshot a coherent view of the CPU state */ do { seq = read_seqcount_begin(&groupc->seq); @@ -246,6 +249,8 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) groupc->times_prev[s] = times[s];

times[s] = delta; + if (delta) + *pchanged_states |= (1 << s); } }

@@ -269,10 +274,11 @@ static void calc_avgs(unsigned long avg[3], int missed_periods, avg[2] = calc_load(avg[2], EXP_300s, pct); }

-static bool collect_percpu_times(struct psi_group *group) +static void collect_percpu_times(struct psi_group *group, u32 *pchanged_states) { u64 deltas[NR_PSI_STATES - 1] = { 0, }; unsigned long nonidle_total = 0; + u32 changed_states = 0; int cpu; int s;

@@ -287,8 +293,11 @@ static bool collect_percpu_times(struct psi_group *group) for_each_possible_cpu(cpu) { u32 times[NR_PSI_STATES]; u32 nonidle; + u32 cpu_changed_states;

- get_recent_times(group, cpu, times); + get_recent_times(group, cpu, times, + &cpu_changed_states); + changed_states |= cpu_changed_states;

nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); nonidle_total += nonidle; @@ -313,7 +322,8 @@ static bool collect_percpu_times(struct psi_group *group) for (s = 0; s < NR_PSI_STATES - 1; s++) group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));

- return nonidle_total; + if (pchanged_states) + *pchanged_states = changed_states; }

static u64 update_averages(struct psi_group *group, u64 now) @@ -373,6 +383,7 @@ static void psi_avgs_work(struct work_struct *work) { struct delayed_work *dwork; struct psi_group *group; + u32 changed_states; bool nonidle; u64 now;

@@ -383,7 +394,8 @@ static void psi_avgs_work(struct work_struct *work)

now = sched_clock();

- nonidle = collect_percpu_times(group); + collect_percpu_times(group, &changed_states); + nonidle = changed_states & (1 << PSI_NONIDLE); /* * If there is task activity, periodically fold the per-cpu * times and feed samples into the running averages. If things @@ -719,7 +731,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) /* Update averages before reporting them */ mutex_lock(&group->avgs_lock); now = sched_clock(); - collect_percpu_times(group); + collect_percpu_times(group, NULL); if (now >= group->avg_next_update) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock);

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v5.4 commit 0e94682b73bfa6c44c98af7a26771c9c08c055d5 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Psi monitor aims to provide a low-latency short-term pressure detection mechanism configurable by users. It allows users to monitor psi metrics growth and trigger events whenever a metric raises above user-defined threshold within user-defined time window.

Time window and threshold are both expressed in usecs. Multiple psi resources with different thresholds and window sizes can be monitored concurrently.

Psi monitors activate when system enters stall state for the monitored psi metric and deactivate upon exit from the stall state. While system is in the stall state psi signal growth is monitored at a rate of 10 times per tracking window. Min window size is 500ms, therefore the min monitoring interval is 50ms. Max window size is 10s with monitoring interval of 1s.

When activated psi monitor stays active for at least the duration of one tracking window to avoid repeated activations/deactivations when psi signal is bouncing.

Notifications to the users are rate-limited to one per tracking window.

Link: http://lkml.kernel.org/r/20190319235619.260832-8-surenb@google.com Signed-off-by: Suren Baghdasaryan surenb@google.com Signed-off-by: Johannes Weiner hannes@cmpxchg.org Cc: Dennis Zhou dennis@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Li Zefan lizefan@huawei.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tejun Heo tj@kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- Documentation/accounting/psi.txt | 107 +++++++++ include/linux/psi.h | 8 + include/linux/psi_types.h | 82 ++++++- kernel/cgroup/cgroup.c | 71 +++++- kernel/sched/psi.c | 494 +++++++++++++++++++++++++++++++++++++-- 5 files changed, 742 insertions(+), 20 deletions(-)

diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index b8ca28b..4fb40fe 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -63,6 +63,110 @@ 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.

+Monitoring for pressure thresholds +================================== + +Users can register triggers and use poll() to be woken up when resource +pressure exceeds certain thresholds. + +A trigger describes the maximum cumulative stall time over a specific +time window, e.g. 100ms of total stall time within any 500ms window to +generate a wakeup event. + +To register a trigger user has to open psi interface file under +/proc/pressure/ representing the resource to be monitored and write the +desired threshold and time window. The open file descriptor should be +used to wait for trigger events using select(), poll() or epoll(). +The following format is used: + +<some|full> <stall amount in us> <time window in us> + +For example writing "some 150000 1000000" into /proc/pressure/memory +would add 150ms threshold for partial memory stall measured within +1sec time window. Writing "full 50000 1000000" into /proc/pressure/io +would add 50ms threshold for full io stall measured within 1sec time window. + +Triggers can be set on more than one psi metric and more than one trigger +for the same psi metric can be specified. However for each trigger a separate +file descriptor is required to be able to poll it separately from others, +therefore for each trigger a separate open() syscall should be made even +when opening the same psi interface file. + +Monitors activate only when system enters stall state for the monitored +psi metric and deactivates upon exit from the stall state. While system is +in the stall state psi signal growth is monitored at a rate of 10 times per +tracking window. + +The kernel accepts window sizes ranging from 500ms to 10s, therefore min +monitoring update interval is 50ms and max is 1s. Min limit is set to +prevent overly frequent polling. Max limit is chosen as a high enough number +after which monitors are most likely not needed and psi averages can be used +instead. + +When activated, psi monitor stays active for at least the duration of one +tracking window to avoid repeated activations/deactivations when system is +bouncing in and out of the stall state. + +Notifications to the userspace are rate-limited to one per tracking window. + +The trigger will de-register when the file descriptor used to define the +trigger is closed. + +Userspace monitor usage example +=============================== + +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <poll.h> +#include <string.h> +#include <unistd.h> + +/* + * Monitor memory partial stall with 1s tracking window size + * and 150ms threshold. + */ +int main() { + const char trig[] = "some 150000 1000000"; + struct pollfd fds; + int n; + + fds.fd = open("/proc/pressure/memory", O_RDWR | O_NONBLOCK); + if (fds.fd < 0) { + printf("/proc/pressure/memory open error: %s\n", + strerror(errno)); + return 1; + } + fds.events = POLLPRI; + + if (write(fds.fd, trig, strlen(trig) + 1) < 0) { + printf("/proc/pressure/memory write error: %s\n", + strerror(errno)); + return 1; + } + + printf("waiting for events...\n"); + while (1) { + n = poll(&fds, 1, -1); + if (n < 0) { + printf("poll error: %s\n", strerror(errno)); + return 1; + } + if (fds.revents & POLLERR) { + printf("got POLLERR, event source is gone\n"); + return 0; + } + if (fds.revents & POLLPRI) { + printf("event triggered!\n"); + } else { + printf("unknown event received: 0x%x\n", fds.revents); + return 1; + } + } + + return 0; +} + Cgroup2 interface =================

@@ -71,3 +175,6 @@ mounted, pressure stall information is also tracked for tasks grouped into cgroups. Each subdirectory in the cgroupfs mountpoint contains cpu.pressure, memory.pressure, and io.pressure files; the format is the same as the /proc/pressure/ files. + +Per-cgroup psi monitors can be specified and used the same way as +system-wide ones. diff --git a/include/linux/psi.h b/include/linux/psi.h index 7006008..af892c2 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,7 @@ #include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> +#include <linux/poll.h>

struct seq_file; struct css_set; @@ -26,6 +27,13 @@ int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); + +struct psi_trigger *psi_trigger_create(struct psi_group *group, + char *buf, size_t nbytes, enum psi_res res); +void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); + +__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, + poll_table *wait); #endif

#else /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 4d1c1f6..07aaf9b 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -1,8 +1,11 @@ #ifndef _LINUX_PSI_TYPES_H #define _LINUX_PSI_TYPES_H

+#include <linux/kthread.h> #include <linux/seqlock.h> #include <linux/types.h> +#include <linux/kref.h> +#include <linux/wait.h>

#ifdef CONFIG_PSI

@@ -44,6 +47,12 @@ enum psi_states { NR_PSI_STATES = 6, };

+enum psi_aggregators { + PSI_AVGS = 0, + PSI_POLL, + NR_PSI_AGGREGATORS, +}; + struct psi_group_cpu { /* 1st cacheline updated by the scheduler */

@@ -65,7 +74,55 @@ struct psi_group_cpu { /* 2nd cacheline updated by the aggregator */

/* Delta detection against the sampling buckets */ - u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; + u32 times_prev[NR_PSI_AGGREGATORS][NR_PSI_STATES] + ____cacheline_aligned_in_smp; +}; + +/* PSI growth tracking window */ +struct psi_window { + /* Window size in ns */ + u64 size; + + /* Start time of the current window in ns */ + u64 start_time; + + /* Value at the start of the window */ + u64 start_value; + + /* Value growth in the previous window */ + u64 prev_growth; +}; + +struct psi_trigger { + /* PSI state being monitored by the trigger */ + enum psi_states state; + + /* User-spacified threshold in ns */ + u64 threshold; + + /* List node inside triggers list */ + struct list_head node; + + /* Backpointer needed during trigger destruction */ + struct psi_group *group; + + /* Wait queue for polling */ + wait_queue_head_t event_wait; + + /* Pending event flag */ + int event; + + /* Tracking window */ + struct psi_window win; + + /* + * Time last event was generated. Used for rate-limiting + * events to one per window + */ + u64 last_event_time; + + /* Refcounting to prevent premature destruction */ + struct kref refcount; };

struct psi_group { @@ -79,11 +136,32 @@ struct psi_group { u64 avg_total[NR_PSI_STATES - 1]; u64 avg_last_update; u64 avg_next_update; + + /* Aggregator work control */ struct delayed_work avgs_work;

/* Total stall times and sampled pressure averages */ - u64 total[NR_PSI_STATES - 1]; + u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; + + /* Monitor work control */ + atomic_t poll_scheduled; + struct kthread_worker __rcu *poll_kworker; + struct kthread_delayed_work poll_work; + + /* Protects data used by the monitor */ + struct mutex trigger_lock; + + /* Configured polling triggers */ + struct list_head triggers; + u32 nr_triggers[NR_PSI_STATES - 1]; + u32 poll_states; + u64 poll_min_period; + + /* Total stall times at the start of monitor activation */ + u64 polling_total[NR_PSI_STATES - 1]; + u64 polling_next_update; + u64 polling_until; };

#else /* CONFIG_PSI */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 581c40a..b6230c8 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3465,7 +3465,65 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); } -#endif + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) +{ + struct psi_trigger *new; + struct cgroup *cgrp; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + cgroup_get(cgrp); + cgroup_kn_unlock(of->kn); + + new = psi_trigger_create(&cgrp->psi, buf, nbytes, res); + if (IS_ERR(new)) { + cgroup_put(cgrp); + return PTR_ERR(new); + } + + psi_trigger_replace(&of->priv, new); + + cgroup_put(cgrp); + + return nbytes; +} + +static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_IO); +} + +static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_MEM); +} + +static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); +} + +static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, + poll_table *pt) +{ + return psi_trigger_poll(&of->priv, of->file, pt); +} + +static void cgroup_pressure_release(struct kernfs_open_file *of) +{ + psi_trigger_replace(&of->priv, NULL); +} +#endif /* CONFIG_PSI */

static int cgroup_file_open(struct kernfs_open_file *of) { @@ -4665,18 +4723,27 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of, .name = "io.pressure", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_io_pressure_show, + .write = cgroup_io_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, }, { .name = "memory.pressure", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_memory_pressure_show, + .write = cgroup_memory_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_cpu_pressure_show, + .write = cgroup_cpu_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, }, -#endif +#endif /* CONFIG_PSI */ { } /* terminate */ };

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 1b99eef..e88918e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -4,6 +4,9 @@ * Copyright (c) 2018 Facebook, Inc. * Author: Johannes Weiner hannes@cmpxchg.org * + * Polling support by Suren Baghdasaryan surenb@google.com + * Copyright (c) 2018 Google, Inc. + * * 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 @@ -129,9 +132,13 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/seqlock.h> +#include <linux/uaccess.h> #include <linux/cgroup.h> #include <linux/module.h> #include <linux/sched.h> +#include <linux/ctype.h> +#include <linux/file.h> +#include <linux/poll.h> #include <linux/psi.h> #include "sched.h"

@@ -156,6 +163,11 @@ static int __init setup_psi(char *str) #define EXP_60s 1981 /* 1/exp(2s/60s) */ #define EXP_300s 2034 /* 1/exp(2s/300s) */

+/* PSI trigger definitions */ +#define WINDOW_MIN_US 500000 /* Min window size is 500ms */ +#define WINDOW_MAX_US 10000000 /* Max window size is 10s */ +#define UPDATES_PER_WINDOW 10 /* 10 updates per window */ + /* Sampling frequency in nanoseconds */ static u64 psi_period __read_mostly;

@@ -176,6 +188,17 @@ static void group_init(struct psi_group *group) group->avg_next_update = sched_clock() + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); + /* Init trigger-related members */ + atomic_set(&group->poll_scheduled, 0); + mutex_init(&group->trigger_lock); + INIT_LIST_HEAD(&group->triggers); + memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); + group->poll_states = 0; + group->poll_min_period = U32_MAX; + memset(group->polling_total, 0, sizeof(group->polling_total)); + group->polling_next_update = ULLONG_MAX; + group->polling_until = 0; + rcu_assign_pointer(group->poll_kworker, NULL); }

void __init psi_init(void) @@ -210,7 +233,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state) } }

-static void get_recent_times(struct psi_group *group, int cpu, u32 *times, +static void get_recent_times(struct psi_group *group, int cpu, + enum psi_aggregators aggregator, u32 *times, u32 *pchanged_states) { struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); @@ -245,8 +269,8 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times, if (state_mask & (1 << s)) times[s] += now - state_start;

- delta = times[s] - groupc->times_prev[s]; - groupc->times_prev[s] = times[s]; + delta = times[s] - groupc->times_prev[aggregator][s]; + groupc->times_prev[aggregator][s] = times[s];

times[s] = delta; if (delta) @@ -274,7 +298,9 @@ static void calc_avgs(unsigned long avg[3], int missed_periods, avg[2] = calc_load(avg[2], EXP_300s, pct); }

-static void collect_percpu_times(struct psi_group *group, u32 *pchanged_states) +static void collect_percpu_times(struct psi_group *group, + enum psi_aggregators aggregator, + u32 *pchanged_states) { u64 deltas[NR_PSI_STATES - 1] = { 0, }; unsigned long nonidle_total = 0; @@ -295,7 +321,7 @@ static void collect_percpu_times(struct psi_group *group, u32 *pchanged_states) u32 nonidle; u32 cpu_changed_states;

- get_recent_times(group, cpu, times, + get_recent_times(group, cpu, aggregator, times, &cpu_changed_states); changed_states |= cpu_changed_states;

@@ -320,7 +346,8 @@ static void collect_percpu_times(struct psi_group *group, u32 *pchanged_states)

/* total= */ for (s = 0; s < NR_PSI_STATES - 1; s++) - group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + group->total[aggregator][s] += + div_u64(deltas[s], max(nonidle_total, 1UL));

if (pchanged_states) *pchanged_states = changed_states; @@ -352,7 +379,7 @@ static u64 update_averages(struct psi_group *group, u64 now) for (s = 0; s < NR_PSI_STATES - 1; s++) { u32 sample;

- sample = group->total[s] - group->avg_total[s]; + sample = group->total[PSI_AVGS][s] - group->avg_total[s]; /* * Due to the lockless sampling of the time buckets, * recorded time deltas can slip into the next period, @@ -394,7 +421,7 @@ static void psi_avgs_work(struct work_struct *work)

now = sched_clock();

- collect_percpu_times(group, &changed_states); + collect_percpu_times(group, PSI_AVGS, &changed_states); nonidle = changed_states & (1 << PSI_NONIDLE); /* * If there is task activity, periodically fold the per-cpu @@ -414,6 +441,187 @@ static void psi_avgs_work(struct work_struct *work) mutex_unlock(&group->avgs_lock); }

+/* Trigger tracking window manupulations */ +static void window_reset(struct psi_window *win, u64 now, u64 value, + u64 prev_growth) +{ + win->start_time = now; + win->start_value = value; + win->prev_growth = prev_growth; +} + +/* + * PSI growth tracking window update and growth calculation routine. + * + * This approximates a sliding tracking window by interpolating + * partially elapsed windows using historical growth data from the + * previous intervals. This minimizes memory requirements (by not storing + * all the intermediate values in the previous window) and simplifies + * the calculations. It works well because PSI signal changes only in + * positive direction and over relatively small window sizes the growth + * is close to linear. + */ +static u64 window_update(struct psi_window *win, u64 now, u64 value) +{ + u64 elapsed; + u64 growth; + + elapsed = now - win->start_time; + growth = value - win->start_value; + /* + * After each tracking window passes win->start_value and + * win->start_time get reset and win->prev_growth stores + * the average per-window growth of the previous window. + * win->prev_growth is then used to interpolate additional + * growth from the previous window assuming it was linear. + */ + if (elapsed > win->size) + window_reset(win, now, value, growth); + else { + u32 remaining; + + remaining = win->size - elapsed; + growth += div_u64(win->prev_growth * remaining, win->size); + } + + return growth; +} + +static void init_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + + list_for_each_entry(t, &group->triggers, node) + window_reset(&t->win, now, + group->total[PSI_POLL][t->state], 0); + memcpy(group->polling_total, group->total[PSI_POLL], + sizeof(group->polling_total)); + group->polling_next_update = now + group->poll_min_period; +} + +static u64 update_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + bool new_stall = false; + u64 *total = group->total[PSI_POLL]; + + /* + * On subsequent updates, calculate growth deltas and let + * watchers know when their specified thresholds are exceeded. + */ + list_for_each_entry(t, &group->triggers, node) { + u64 growth; + + /* Check for stall activity */ + if (group->polling_total[t->state] == total[t->state]) + continue; + + /* + * Multiple triggers might be looking at the same state, + * remember to update group->polling_total[] once we've + * been through all of them. Also remember to extend the + * polling time if we see new stall activity. + */ + new_stall = true; + + /* Calculate growth since last update */ + growth = window_update(&t->win, now, total[t->state]); + if (growth < t->threshold) + continue; + + /* Limit event signaling to once per window */ + if (now < t->last_event_time + t->win.size) + continue; + + /* Generate an event */ + if (cmpxchg(&t->event, 0, 1) == 0) + wake_up_interruptible(&t->event_wait); + t->last_event_time = now; + } + + if (new_stall) + memcpy(group->polling_total, total, + sizeof(group->polling_total)); + + return now + group->poll_min_period; +} + +/* + * Schedule polling if it's not already scheduled. It's safe to call even from + * hotpath because even though kthread_queue_delayed_work takes worker->lock + * spinlock that spinlock is never contended due to poll_scheduled atomic + * preventing such competition. + */ +static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay) +{ + struct kthread_worker *kworker; + + /* Do not reschedule if already scheduled */ + if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0) + return; + + rcu_read_lock(); + + kworker = rcu_dereference(group->poll_kworker); + /* + * kworker might be NULL in case psi_trigger_destroy races with + * psi_task_change (hotpath) which can't use locks + */ + if (likely(kworker)) + kthread_queue_delayed_work(kworker, &group->poll_work, delay); + else + atomic_set(&group->poll_scheduled, 0); + + rcu_read_unlock(); +} + +static void psi_poll_work(struct kthread_work *work) +{ + struct kthread_delayed_work *dwork; + struct psi_group *group; + u32 changed_states; + u64 now; + + dwork = container_of(work, struct kthread_delayed_work, work); + group = container_of(dwork, struct psi_group, poll_work); + + atomic_set(&group->poll_scheduled, 0); + + mutex_lock(&group->trigger_lock); + + now = sched_clock(); + + collect_percpu_times(group, PSI_POLL, &changed_states); + + if (changed_states & group->poll_states) { + /* Initialize trigger windows when entering polling mode */ + if (now > group->polling_until) + init_triggers(group, now); + + /* + * Keep the monitor active for at least the duration of the + * minimum tracking window as long as monitor states are + * changing. + */ + group->polling_until = now + + group->poll_min_period * UPDATES_PER_WINDOW; + } + + if (now > group->polling_until) { + group->polling_next_update = ULLONG_MAX; + goto out; + } + + if (now >= group->polling_next_update) + group->polling_next_update = update_triggers(group, now); + + psi_schedule_poll_work(group, + nsecs_to_jiffies(group->polling_next_update - now) + 1); + +out: + mutex_unlock(&group->trigger_lock); +} + static void record_times(struct psi_group_cpu *groupc, int cpu, bool memstall_tick) { @@ -460,8 +668,8 @@ static void record_times(struct psi_group_cpu *groupc, int cpu, groupc->times[PSI_NONIDLE] += delta; }

-static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set) +static u32 psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) { struct psi_group_cpu *groupc; unsigned int t, m; @@ -507,6 +715,8 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->state_mask = state_mask;

write_seqcount_end(&groupc->seq); + + return state_mask; }

static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -567,7 +777,11 @@ void psi_task_change(struct task_struct *task, int clear, int set) wake_clock = false;

while ((group = iterate_groups(task, &iter))) { - psi_group_change(group, cpu, clear, set); + u32 state_mask = psi_group_change(group, cpu, clear, set); + + if (state_mask & group->poll_states) + psi_schedule_poll_work(group, 1); + if (wake_clock && !delayed_work_pending(&group->avgs_work)) schedule_delayed_work(&group->avgs_work, PSI_FREQ); } @@ -668,6 +882,8 @@ void psi_cgroup_free(struct cgroup *cgroup)

cancel_delayed_work_sync(&cgroup->psi.avgs_work); free_percpu(cgroup->psi.pcpu); + /* All triggers must be removed by now */ + WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n"); }

/** @@ -731,7 +947,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) /* Update averages before reporting them */ mutex_lock(&group->avgs_lock); now = sched_clock(); - collect_percpu_times(group, NULL); + collect_percpu_times(group, PSI_AVGS, NULL); if (now >= group->avg_next_update) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock); @@ -743,7 +959,8 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)

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); + total = div_u64(group->total[PSI_AVGS][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", @@ -786,25 +1003,270 @@ static int psi_cpu_open(struct inode *inode, struct file *file) return single_open(file, psi_cpu_show, NULL); }

+struct psi_trigger *psi_trigger_create(struct psi_group *group, + char *buf, size_t nbytes, enum psi_res res) +{ + struct psi_trigger *t; + enum psi_states state; + u32 threshold_us; + u32 window_us; + + if (static_branch_likely(&psi_disabled)) + return ERR_PTR(-EOPNOTSUPP); + + if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2) + state = PSI_IO_SOME + res * 2; + else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2) + state = PSI_IO_FULL + res * 2; + else + return ERR_PTR(-EINVAL); + + if (state >= PSI_NONIDLE) + return ERR_PTR(-EINVAL); + + if (window_us < WINDOW_MIN_US || + window_us > WINDOW_MAX_US) + return ERR_PTR(-EINVAL); + + /* Check threshold */ + if (threshold_us == 0 || threshold_us > window_us) + return ERR_PTR(-EINVAL); + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return ERR_PTR(-ENOMEM); + + t->group = group; + t->state = state; + t->threshold = threshold_us * NSEC_PER_USEC; + t->win.size = window_us * NSEC_PER_USEC; + window_reset(&t->win, 0, 0, 0); + + t->event = 0; + t->last_event_time = 0; + init_waitqueue_head(&t->event_wait); + kref_init(&t->refcount); + + mutex_lock(&group->trigger_lock); + + if (!rcu_access_pointer(group->poll_kworker)) { + struct sched_param param = { + .sched_priority = MAX_RT_PRIO - 1, + }; + struct kthread_worker *kworker; + + kworker = kthread_create_worker(0, "psimon"); + if (IS_ERR(kworker)) { + kfree(t); + mutex_unlock(&group->trigger_lock); + return ERR_CAST(kworker); + } + sched_setscheduler(kworker->task, SCHED_FIFO, &param); + kthread_init_delayed_work(&group->poll_work, + psi_poll_work); + rcu_assign_pointer(group->poll_kworker, kworker); + } + + list_add(&t->node, &group->triggers); + group->poll_min_period = min(group->poll_min_period, + div_u64(t->win.size, UPDATES_PER_WINDOW)); + group->nr_triggers[t->state]++; + group->poll_states |= (1 << t->state); + + mutex_unlock(&group->trigger_lock); + + return t; +} + +static void psi_trigger_destroy(struct kref *ref) +{ + struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); + struct psi_group *group = t->group; + struct kthread_worker *kworker_to_destroy = NULL; + + if (static_branch_likely(&psi_disabled)) + return; + + /* + * Wakeup waiters to stop polling. Can happen if cgroup is deleted + * from under a polling process. + */ + wake_up_interruptible(&t->event_wait); + + mutex_lock(&group->trigger_lock); + + if (!list_empty(&t->node)) { + struct psi_trigger *tmp; + u64 period = ULLONG_MAX; + + list_del(&t->node); + group->nr_triggers[t->state]--; + if (!group->nr_triggers[t->state]) + group->poll_states &= ~(1 << t->state); + /* reset min update period for the remaining triggers */ + list_for_each_entry(tmp, &group->triggers, node) + period = min(period, div_u64(tmp->win.size, + UPDATES_PER_WINDOW)); + group->poll_min_period = period; + /* Destroy poll_kworker when the last trigger is destroyed */ + if (group->poll_states == 0) { + group->polling_until = 0; + kworker_to_destroy = rcu_dereference_protected( + group->poll_kworker, + lockdep_is_held(&group->trigger_lock)); + rcu_assign_pointer(group->poll_kworker, NULL); + } + } + + mutex_unlock(&group->trigger_lock); + + /* + * Wait for both *trigger_ptr from psi_trigger_replace and + * poll_kworker RCUs to complete their read-side critical sections + * before destroying the trigger and optionally the poll_kworker + */ + synchronize_rcu(); + /* + * Destroy the kworker after releasing trigger_lock to prevent a + * deadlock while waiting for psi_poll_work to acquire trigger_lock + */ + if (kworker_to_destroy) { + kthread_cancel_delayed_work_sync(&group->poll_work); + kthread_destroy_worker(kworker_to_destroy); + } + kfree(t); +} + +void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) +{ + struct psi_trigger *old = *trigger_ptr; + + if (static_branch_likely(&psi_disabled)) + return; + + rcu_assign_pointer(*trigger_ptr, new); + if (old) + kref_put(&old->refcount, psi_trigger_destroy); +} + +__poll_t psi_trigger_poll(void **trigger_ptr, + struct file *file, poll_table *wait) +{ + __poll_t ret = DEFAULT_POLLMASK; + struct psi_trigger *t; + + if (static_branch_likely(&psi_disabled)) + return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; + + rcu_read_lock(); + + t = rcu_dereference(*(void __rcu __force **)trigger_ptr); + if (!t) { + rcu_read_unlock(); + return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; + } + kref_get(&t->refcount); + + rcu_read_unlock(); + + poll_wait(file, &t->event_wait, wait); + + if (cmpxchg(&t->event, 1, 0) == 1) + ret |= EPOLLPRI; + + kref_put(&t->refcount, psi_trigger_destroy); + + return ret; +} + +static ssize_t psi_write(struct file *file, const char __user *user_buf, + size_t nbytes, enum psi_res res) +{ + char buf[32]; + size_t buf_size; + struct seq_file *seq; + struct psi_trigger *new; + + if (static_branch_likely(&psi_disabled)) + return -EOPNOTSUPP; + + buf_size = min(nbytes, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size - 1] = '\0'; + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) + return PTR_ERR(new); + + seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ + mutex_lock(&seq->lock); + psi_trigger_replace(&seq->private, new); + mutex_unlock(&seq->lock); + + return nbytes; +} + +static ssize_t psi_io_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_IO); +} + +static ssize_t psi_memory_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_MEM); +} + +static ssize_t psi_cpu_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_CPU); +} + +static __poll_t psi_fop_poll(struct file *file, poll_table *wait) +{ + struct seq_file *seq = file->private_data; + + return psi_trigger_poll(&seq->private, file, wait); +} + +static int psi_fop_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + + psi_trigger_replace(&seq->private, NULL); + return single_release(inode, file); +} + static const struct file_operations psi_io_fops = { .open = psi_io_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .write = psi_io_write, + .poll = psi_fop_poll, + .release = psi_fop_release, };

static const struct file_operations psi_memory_fops = { .open = psi_memory_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .write = psi_memory_write, + .poll = psi_fop_poll, + .release = psi_fop_release, };

static const struct file_operations psi_cpu_fops = { .open = psi_cpu_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .write = psi_cpu_write, + .poll = psi_fop_poll, + .release = psi_fop_release, };

static int __init psi_proc_init(void)

From: Peter Zijlstra peterz@infradead.org

mainline inclusion from mainline-v5.4 commit 14f5c7b46a41a595fc61db37f55721714729e59e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

PSI defaults to a FIFO-99 thread, reduce this to FIFO-1.

FIFO-99 is the very highest priority available to SCHED_FIFO and it not a suitable default; it would indicate the psi work is the most important work on the machine.

Since Real-Time tasks will have pre-allocated memory and locked it in place, Real-Time tasks do not care about PSI. All it needs is to be above OTHER.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Johannes Weiner hannes@cmpxchg.org Tested-by: Suren Baghdasaryan surenb@google.com Cc: Thomas Gleixner tglx@linutronix.de Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7acc632..7fe2c5f 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1051,7 +1051,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,

if (!rcu_access_pointer(group->poll_kworker)) { struct sched_param param = { - .sched_priority = MAX_RT_PRIO - 1, + .sched_priority = 1, }; struct kthread_worker *kworker;

From: Jason Xing kerneljasonxing@linux.alibaba.com

mainline inclusion from mainline-v5.4 commit 7b2b55da1db10a5525460633ae4b6fb0be060c41 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Only when calling the poll syscall the first time can user receive POLLPRI correctly. After that, user always fails to acquire the event signal.

Reproduce case: 1. Get the monitor code in Documentation/accounting/psi.txt 2. Run it, and wait for the event triggered. 3. Kill and restart the process.

The question is why we can end up with poll_scheduled = 1 but the work not running (which would reset it to 0). And the answer is because the scheduling side sees group->poll_kworker under RCU protection and then schedules it, but here we cancel the work and destroy the worker. The cancel needs to pair with resetting the poll_scheduled flag.

Link: http://lkml.kernel.org/r/1566357985-97781-1-git-send-email-joseph.qi@linux.a... Signed-off-by: Jason Xing kerneljasonxing@linux.alibaba.com Signed-off-by: Joseph Qi joseph.qi@linux.alibaba.com Reviewed-by: Caspar Zhang caspar@linux.alibaba.com Reviewed-by: Suren Baghdasaryan surenb@google.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: stable@vger.kernel.org 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 # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- kernel/sched/psi.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 23fbbcc..6e52b67 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1131,7 +1131,15 @@ static void psi_trigger_destroy(struct kref *ref) * deadlock while waiting for psi_poll_work to acquire trigger_lock */ if (kworker_to_destroy) { + /* + * After the RCU grace period has expired, the worker + * can no longer be found through group->poll_kworker. + * But it might have been already scheduled before + * that - deschedule it cleanly before destroying it. + */ kthread_cancel_delayed_work_sync(&group->poll_work); + atomic_set(&group->poll_scheduled, 0); + kthread_destroy_worker(kworker_to_destroy); } kfree(t);

From: Johannes Weiner hannes@cmpxchg.org

mainline inclusion from mainline-v5.4 commit 74e2bdcb7d16fcfb7ddbda615a91094abc727114 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

[ Upstream commit 3dfbe25c27eab7c90c8a7e97b4c354a9d24dd985 ]

Jingfeng reports rare div0 crashes in psi on systems with some uptime:

[58914.066423] divide error: 0000 [#1] SMP [58914.070416] Modules linked in: ipmi_poweroff ipmi_watchdog toa overlay fuse tcp_diag inet_diag binfmt_misc aisqos(O) aisqos_hotfixes(O) [58914.083158] CPU: 94 PID: 140364 Comm: kworker/94:2 Tainted: G W OE K 4.9.151-015.ali3000.alios7.x86_64 #1 [58914.093722] Hardware name: Alibaba Alibaba Cloud ECS/Alibaba Cloud ECS, BIOS 3.23.34 02/14/2019 [58914.102728] Workqueue: events psi_update_work [58914.107258] task: ffff8879da83c280 task.stack: ffffc90059dcc000 [58914.113336] RIP: 0010:[] [] psi_update_stats+0x1c1/0x330 [58914.122183] RSP: 0018:ffffc90059dcfd60 EFLAGS: 00010246 [58914.127650] RAX: 0000000000000000 RBX: ffff8858fe98be50 RCX: 000000007744d640 [58914.134947] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00003594f700648e [58914.142243] RBP: ffffc90059dcfdf8 R08: 0000359500000000 R09: 0000000000000000 [58914.149538] R10: 0000000000000000 R11: 0000000000000000 R12: 0000359500000000 [58914.156837] R13: 0000000000000000 R14: 0000000000000000 R15: ffff8858fe98bd78 [58914.164136] FS: 0000000000000000(0000) GS:ffff887f7f380000(0000) knlGS:0000000000000000 [58914.172529] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [58914.178467] CR2: 00007f2240452090 CR3: 0000005d5d258000 CR4: 00000000007606f0 [58914.185765] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [58914.193061] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [58914.200360] PKRU: 55555554 [58914.203221] Stack: [58914.205383] ffff8858fe98bd48 00000000000002f0 0000002e81036d09 ffffc90059dcfde8 [58914.213168] ffff8858fe98bec8 0000000000000000 0000000000000000 0000000000000000 [58914.220951] 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [58914.228734] Call Trace: [58914.231337] [] psi_update_work+0x22/0x60 [58914.237067] [] process_one_work+0x189/0x420 [58914.243063] [] worker_thread+0x4e/0x4b0 [58914.248701] [] ? process_one_work+0x420/0x420 [58914.254869] [] kthread+0xe6/0x100 [58914.259994] [] ? kthread_park+0x60/0x60 [58914.265640] [] ret_from_fork+0x39/0x50 [58914.271193] Code: 41 29 c3 4d 39 dc 4d 0f 42 dc <49> f7 f1 48 8b 13 48 89 c7 48 c1 [58914.279691] RIP [] psi_update_stats+0x1c1/0x330

The crashing instruction is trying to divide the observed stall time by the sampling period. The period, stored in R8, is not 0, but we are dividing by the lower 32 bits only, which are all 0 in this instance.

We could switch to a 64-bit division, but the period shouldn't be that big in the first place. It's the time between the last update and the next scheduled one, and so should always be around 2s and comfortably fit into 32 bits.

The bug is in the initialization of new cgroups: we schedule the first sampling event in a cgroup as an offset of sched_clock(), but fail to initialize the last_update timestamp, and it defaults to 0. That results in a bogusly large sampling period the first time we run the sampling code, and consequently we underreport pressure for the first 2s of a cgroup's life. But worse, if sched_clock() is sufficiently advanced on the system, and the user gets unlucky, the period's lower 32 bits can all be 0 and the sampling division will crash.

Fix this by initializing the last update timestamp to the creation time of the cgroup, thus correctly marking the start of the first pressure sampling period in a new cgroup.

Reported-by: Jingfeng Xie xiejingfeng@linux.alibaba.com Signed-off-by: Johannes Weiner hannes@cmpxchg.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Suren Baghdasaryan surenb@google.com Link: https://lkml.kernel.org/r/20191203183524.41378-2-hannes@cmpxchg.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- kernel/sched/psi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 517e371..970db46 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)

for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->avg_next_update = sched_clock() + psi_period; + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v5.4 commit e61c236dcf3416211008774b6c2bfa01753a82c1 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

commit 6fcca0fa48118e6d63733eb4644c6cd880c15b8f upstream.

Issuing write() with count parameter set to 0 on any file under /proc/pressure/ will cause an OOB write because of the access to buf[buf_size-1] when NUL-termination is performed. Fix this by checking for buf_size to be non-zero.

Signed-off-by: Suren Baghdasaryan surenb@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Acked-by: Johannes Weiner hannes@cmpxchg.org Link: https://lkml.kernel.org/r/20200203212216.7076-1-surenb@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- kernel/sched/psi.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ce8f674..9154e74 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1199,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP;

+ if (!nbytes) + return -EINVAL; + buf_size = min(nbytes, sizeof(buf)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT;

From: Odin Ugedal odin@uged.al

mainline inclusion from mainline-v5.4 commit 385aac1519417b89cb91b77c22e4ca21db563cd0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

-------------------------------- Fix NULL pointer dereference when adding new psi monitor to the root cgroup. PSI files for root cgroup was introduced in df5ba5be742 by using system wide psi struct when reading, but file write/monitor was not properly fixed. Since the PSI config for the root cgroup isn't initialized, the current implementation tries to lock a NULL ptr, resulting in a crash.

Can be triggered by running this as root: $ tee /sys/fs/cgroup/cpu.pressure <<< "some 10000 1000000"

Signed-off-by: Odin Ugedal odin@uged.al Reviewed-by: Suren Baghdasaryan surenb@google.com Acked-by: Dan Schatzberg dschatzberg@fb.com Fixes: df5ba5be7425 ("kernel/sched/psi.c: expose pressure metrics on root cgroup") Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: stable@vger.kernel.org # 5.2+ Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor --- kernel/cgroup/cgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0f75362..fabdaf6 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3480,6 +3480,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, { struct psi_trigger *new; struct cgroup *cgrp; + struct psi_group *psi;

cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) @@ -3488,7 +3489,8 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn);

- new = psi_trigger_create(&cgrp->psi, buf, nbytes, res); + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; + new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new);

Enable the psi feature in x86&arm64 openeuler config

openEuler inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA

--------------------------------

Signed-off-by: Liu Xinpeng liuxp11@chinatelecom.cn # openEuler_contributor Signed-off-by: Ctyun Kernel ctyuncommiter01@chinatelecom.cn # openEuler_contributor Reviewed-by: Chen Hui judy.chenhui@huawei.com --- arch/arm64/configs/openeuler_defconfig | 2 ++ arch/x86/configs/openeuler_defconfig | 2 ++ 2 files changed, 4 insertions(+)

diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index c2cb98d..0300ad0 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -89,6 +89,8 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_PSI_DEFAULT_DISABLED=y CONFIG_CPU_ISOLATION=y

# diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 7043426..0225af7 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -94,6 +94,8 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_PSI_DEFAULT_DISABLED=y CONFIG_CPU_ISOLATION=y

#