diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/cgroup-defs.h | 4 | ||||
| -rw-r--r-- | include/linux/cgroup.h | 15 | ||||
| -rw-r--r-- | include/linux/delayacct.h | 23 | ||||
| -rw-r--r-- | include/linux/hmm.h | 2 | ||||
| -rw-r--r-- | include/linux/huge_mm.h | 8 | ||||
| -rw-r--r-- | include/linux/iomap.h | 4 | ||||
| -rw-r--r-- | include/linux/linkage.h | 1 | ||||
| -rw-r--r-- | include/linux/math64.h | 3 | ||||
| -rw-r--r-- | include/linux/memblock.h | 15 | ||||
| -rw-r--r-- | include/linux/memcontrol.h | 15 | ||||
| -rw-r--r-- | include/linux/mm.h | 48 | ||||
| -rw-r--r-- | include/linux/mmu_notifier.h | 27 | ||||
| -rw-r--r-- | include/linux/mmzone.h | 4 | ||||
| -rw-r--r-- | include/linux/page-flags.h | 14 | ||||
| -rw-r--r-- | include/linux/pfn_t.h | 4 | ||||
| -rw-r--r-- | include/linux/psi.h | 53 | ||||
| -rw-r--r-- | include/linux/psi_types.h | 92 | ||||
| -rw-r--r-- | include/linux/sched.h | 13 | ||||
| -rw-r--r-- | include/linux/sched/loadavg.h | 24 | ||||
| -rw-r--r-- | include/linux/slab.h | 56 | ||||
| -rw-r--r-- | include/linux/swap.h | 15 |
21 files changed, 326 insertions, 114 deletions
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..5e1694fe035b 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 @@ -436,6 +437,9 @@ 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 b622d6608605..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -650,6 +650,11 @@ 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) { /* @@ -703,6 +708,16 @@ 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/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4c92e3ba3e16..dde947083d4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -107,7 +107,7 @@ enum hmm_pfn_flag_e { * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3555d54bf79a..9a4258154b25 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -6,6 +6,7 @@ #include <linux/bitmap.h> #include <linux/mm.h> #include <linux/types.h> +#include <linux/mm_types.h> struct address_space; struct fiemap_extent_info; @@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, + const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d7618c41f74c..7c47b1a471d4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -90,6 +90,7 @@ #ifndef WEAK #define WEAK(name) \ .weak name ASM_NL \ + ALIGN ASM_NL \ name: #endif diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 652f602167df..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* @@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); + +#ifdef CONFIG_MEMCG_KMEM int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else + +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { @@ -2304,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); +extern int __do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); @@ -2502,11 +2506,11 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,32 +2529,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) @@ -2558,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 133ba78820ee..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -31,15 +27,6 @@ struct mmu_notifier_mm { struct mmu_notifier_ops { /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier @@ -153,7 +140,9 @@ struct mmu_notifier_ops { * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. + * otherwise. Please note that if invalidate_range_start approves + * a non-blocking behavior then the same applies to + * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, @@ -181,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -239,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -493,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,8 +161,10 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. @@ -180,7 +182,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..50ce1bddaf56 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, @@ -162,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * @@ -280,6 +289,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ @@ -292,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 21713dc14ce2..7bb77850c65a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,8 +9,10 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver + * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not + * get_user_pages */ -#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..8e0725aac0aa --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include <linux/psi_types.h> +#include <linux/sched.h> + +struct seq_file; +struct css_set; + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +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) {} + +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/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include <linux/seqlock.h> +#include <linux/types.h> + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/signal_types.h> +#include <linux/psi_types.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> #include <linux/rseq.h> @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -719,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; @@ -965,6 +967,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1397,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,26 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +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) extern void calc_global_load(unsigned long ticks); diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,43 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + int type_dma = 0; + int is_reclaimable; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +532,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +575,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL @@ -296,7 +297,7 @@ 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 */ |