diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h index 859b5e969826302baf456044a48272f0cb66bfc0..24312387fa244c453b6840441fe26eb6dcb974c6 100644 --- a/include/asm-s390/pgtable.h +++ b/include/asm-s390/pgtable.h @@ -657,13 +657,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) __pte; \ }) -#define SetPageUptodate(_page) \ - do { \ - struct page *__page = (_page); \ - if (!test_and_set_bit(PG_uptodate, &__page->flags)) \ - page_test_and_clear_dirty(_page); \ - } while (0) - #ifdef __s390x__ #define pfn_pmd(pfn, pgprot) \ diff --git a/include/linux/mm.h b/include/linux/mm.h index c41a1299b8cf354cc8b9d9677f328aa4bc8b8533..75179529e39979d397ce438778acad1dd93dbd87 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -36,7 +36,6 @@ extern int sysctl_legacy_va_layout; #include #include #include -#include #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -515,6 +514,11 @@ static inline void set_page_links(struct page *page, unsigned long zone, set_page_section(page, pfn_to_section_nr(pfn)); } +/* + * Some inline functions in vmstat.h depend on page_zone() + */ +#include + #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ extern struct page *mem_map; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0c076d58c6760751a3e82fda67c71fc02c7cc83a..ff235c4b79ea620dcc4ed56277b059d4d5a2312a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -5,12 +5,8 @@ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H -#include -#include #include -#include - /* * Various page->flags bits: * @@ -102,134 +98,6 @@ #define PG_uncached 31 /* Page has been mapped as uncached */ #endif -/* - * Global page accounting. One instance per CPU. Only unsigned longs are - * allowed. - * - * - Fields can be modified with xxx_page_state and xxx_page_state_zone at - * any time safely (which protects the instance from modification by - * interrupt. - * - The __xxx_page_state variants can be used safely when interrupts are - * disabled. - * - The __xxx_page_state variants can be used if the field is only - * modified from process context and protected from preemption, or only - * modified from interrupt context. In this case, the field should be - * commented here. - */ -struct page_state { - unsigned long nr_dirty; /* Dirty writeable pages */ - unsigned long nr_writeback; /* Pages under writeback */ - unsigned long nr_unstable; /* NFS unstable pages */ - unsigned long nr_page_table_pages;/* Pages used for pagetables */ - unsigned long nr_mapped; /* mapped into pagetables. - * only modified from process context */ - unsigned long nr_slab; /* In slab */ -#define GET_PAGE_STATE_LAST nr_slab - - /* - * The below are zeroed by get_page_state(). Use get_full_page_state() - * to add up all these. - */ - unsigned long pgpgin; /* Disk reads */ - unsigned long pgpgout; /* Disk writes */ - unsigned long pswpin; /* swap reads */ - unsigned long pswpout; /* swap writes */ - - unsigned long pgalloc_high; /* page allocations */ - unsigned long pgalloc_normal; - unsigned long pgalloc_dma32; - unsigned long pgalloc_dma; - - unsigned long pgfree; /* page freeings */ - unsigned long pgactivate; /* pages moved inactive->active */ - unsigned long pgdeactivate; /* pages moved active->inactive */ - - unsigned long pgfault; /* faults (major+minor) */ - unsigned long pgmajfault; /* faults (major only) */ - - unsigned long pgrefill_high; /* inspected in refill_inactive_zone */ - unsigned long pgrefill_normal; - unsigned long pgrefill_dma32; - unsigned long pgrefill_dma; - - unsigned long pgsteal_high; /* total highmem pages reclaimed */ - unsigned long pgsteal_normal; - unsigned long pgsteal_dma32; - unsigned long pgsteal_dma; - - unsigned long pgscan_kswapd_high;/* total highmem pages scanned */ - unsigned long pgscan_kswapd_normal; - unsigned long pgscan_kswapd_dma32; - unsigned long pgscan_kswapd_dma; - - unsigned long pgscan_direct_high;/* total highmem pages scanned */ - unsigned long pgscan_direct_normal; - unsigned long pgscan_direct_dma32; - unsigned long pgscan_direct_dma; - - unsigned long pginodesteal; /* pages reclaimed via inode freeing */ - unsigned long slabs_scanned; /* slab objects scanned */ - unsigned long kswapd_steal; /* pages reclaimed by kswapd */ - unsigned long kswapd_inodesteal;/* reclaimed via kswapd inode freeing */ - unsigned long pageoutrun; /* kswapd's calls to page reclaim */ - unsigned long allocstall; /* direct reclaim calls */ - - unsigned long pgrotated; /* pages rotated to tail of the LRU */ - unsigned long nr_bounce; /* pages for bounce buffers */ -}; - -extern void get_page_state(struct page_state *ret); -extern void get_page_state_node(struct page_state *ret, int node); -extern void get_full_page_state(struct page_state *ret); -extern unsigned long read_page_state_offset(unsigned long offset); -extern void mod_page_state_offset(unsigned long offset, unsigned long delta); -extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); - -#define read_page_state(member) \ - read_page_state_offset(offsetof(struct page_state, member)) - -#define mod_page_state(member, delta) \ - mod_page_state_offset(offsetof(struct page_state, member), (delta)) - -#define __mod_page_state(member, delta) \ - __mod_page_state_offset(offsetof(struct page_state, member), (delta)) - -#define inc_page_state(member) mod_page_state(member, 1UL) -#define dec_page_state(member) mod_page_state(member, 0UL - 1) -#define add_page_state(member,delta) mod_page_state(member, (delta)) -#define sub_page_state(member,delta) mod_page_state(member, 0UL - (delta)) - -#define __inc_page_state(member) __mod_page_state(member, 1UL) -#define __dec_page_state(member) __mod_page_state(member, 0UL - 1) -#define __add_page_state(member,delta) __mod_page_state(member, (delta)) -#define __sub_page_state(member,delta) __mod_page_state(member, 0UL - (delta)) - -#define page_state(member) (*__page_state(offsetof(struct page_state, member))) - -#define state_zone_offset(zone, member) \ -({ \ - unsigned offset; \ - if (is_highmem(zone)) \ - offset = offsetof(struct page_state, member##_high); \ - else if (is_normal(zone)) \ - offset = offsetof(struct page_state, member##_normal); \ - else if (is_dma32(zone)) \ - offset = offsetof(struct page_state, member##_dma32); \ - else \ - offset = offsetof(struct page_state, member##_dma); \ - offset; \ -}) - -#define __mod_page_state_zone(zone, member, delta) \ - do { \ - __mod_page_state_offset(state_zone_offset(zone, member), (delta)); \ - } while (0) - -#define mod_page_state_zone(zone, member, delta) \ - do { \ - mod_page_state_offset(state_zone_offset(zone, member), (delta)); \ - } while (0) - /* * Manipulation of page state flags */ @@ -254,7 +122,14 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags) #define PageUptodate(page) test_bit(PG_uptodate, &(page)->flags) -#ifndef SetPageUptodate +#ifdef CONFIG_S390 +#define SetPageUptodate(_page) \ + do { \ + struct page *__page = (_page); \ + if (!test_and_set_bit(PG_uptodate, &__page->flags)) \ + page_test_and_clear_dirty(_page); \ + } while (0) +#else #define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags) #endif #define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h new file mode 100644 index 0000000000000000000000000000000000000000..3ca0c1989fc2eb7de31b55dcb05748c47b13bf14 --- /dev/null +++ b/include/linux/vmstat.h @@ -0,0 +1,138 @@ +#ifndef _LINUX_VMSTAT_H +#define _LINUX_VMSTAT_H + +#include +#include + +/* + * Global page accounting. One instance per CPU. Only unsigned longs are + * allowed. + * + * - Fields can be modified with xxx_page_state and xxx_page_state_zone at + * any time safely (which protects the instance from modification by + * interrupt. + * - The __xxx_page_state variants can be used safely when interrupts are + * disabled. + * - The __xxx_page_state variants can be used if the field is only + * modified from process context and protected from preemption, or only + * modified from interrupt context. In this case, the field should be + * commented here. + */ +struct page_state { + unsigned long nr_dirty; /* Dirty writeable pages */ + unsigned long nr_writeback; /* Pages under writeback */ + unsigned long nr_unstable; /* NFS unstable pages */ + unsigned long nr_page_table_pages;/* Pages used for pagetables */ + unsigned long nr_mapped; /* mapped into pagetables. + * only modified from process context */ + unsigned long nr_slab; /* In slab */ +#define GET_PAGE_STATE_LAST nr_slab + + /* + * The below are zeroed by get_page_state(). Use get_full_page_state() + * to add up all these. + */ + unsigned long pgpgin; /* Disk reads */ + unsigned long pgpgout; /* Disk writes */ + unsigned long pswpin; /* swap reads */ + unsigned long pswpout; /* swap writes */ + + unsigned long pgalloc_high; /* page allocations */ + unsigned long pgalloc_normal; + unsigned long pgalloc_dma32; + unsigned long pgalloc_dma; + + unsigned long pgfree; /* page freeings */ + unsigned long pgactivate; /* pages moved inactive->active */ + unsigned long pgdeactivate; /* pages moved active->inactive */ + + unsigned long pgfault; /* faults (major+minor) */ + unsigned long pgmajfault; /* faults (major only) */ + + unsigned long pgrefill_high; /* inspected in refill_inactive_zone */ + unsigned long pgrefill_normal; + unsigned long pgrefill_dma32; + unsigned long pgrefill_dma; + + unsigned long pgsteal_high; /* total highmem pages reclaimed */ + unsigned long pgsteal_normal; + unsigned long pgsteal_dma32; + unsigned long pgsteal_dma; + + unsigned long pgscan_kswapd_high;/* total highmem pages scanned */ + unsigned long pgscan_kswapd_normal; + unsigned long pgscan_kswapd_dma32; + unsigned long pgscan_kswapd_dma; + + unsigned long pgscan_direct_high;/* total highmem pages scanned */ + unsigned long pgscan_direct_normal; + unsigned long pgscan_direct_dma32; + unsigned long pgscan_direct_dma; + + unsigned long pginodesteal; /* pages reclaimed via inode freeing */ + unsigned long slabs_scanned; /* slab objects scanned */ + unsigned long kswapd_steal; /* pages reclaimed by kswapd */ + unsigned long kswapd_inodesteal;/* reclaimed via kswapd inode freeing */ + unsigned long pageoutrun; /* kswapd's calls to page reclaim */ + unsigned long allocstall; /* direct reclaim calls */ + + unsigned long pgrotated; /* pages rotated to tail of the LRU */ + unsigned long nr_bounce; /* pages for bounce buffers */ +}; + +extern void get_page_state(struct page_state *ret); +extern void get_page_state_node(struct page_state *ret, int node); +extern void get_full_page_state(struct page_state *ret); +extern unsigned long read_page_state_offset(unsigned long offset); +extern void mod_page_state_offset(unsigned long offset, unsigned long delta); +extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); + +#define read_page_state(member) \ + read_page_state_offset(offsetof(struct page_state, member)) + +#define mod_page_state(member, delta) \ + mod_page_state_offset(offsetof(struct page_state, member), (delta)) + +#define __mod_page_state(member, delta) \ + __mod_page_state_offset(offsetof(struct page_state, member), (delta)) + +#define inc_page_state(member) mod_page_state(member, 1UL) +#define dec_page_state(member) mod_page_state(member, 0UL - 1) +#define add_page_state(member,delta) mod_page_state(member, (delta)) +#define sub_page_state(member,delta) mod_page_state(member, 0UL - (delta)) + +#define __inc_page_state(member) __mod_page_state(member, 1UL) +#define __dec_page_state(member) __mod_page_state(member, 0UL - 1) +#define __add_page_state(member,delta) __mod_page_state(member, (delta)) +#define __sub_page_state(member,delta) __mod_page_state(member, 0UL - (delta)) + +#define page_state(member) (*__page_state(offsetof(struct page_state, member))) + +#define state_zone_offset(zone, member) \ +({ \ + unsigned offset; \ + if (is_highmem(zone)) \ + offset = offsetof(struct page_state, member##_high); \ + else if (is_normal(zone)) \ + offset = offsetof(struct page_state, member##_normal); \ + else if (is_dma32(zone)) \ + offset = offsetof(struct page_state, member##_dma32); \ + else \ + offset = offsetof(struct page_state, member##_dma); \ + offset; \ +}) + +#define __mod_page_state_zone(zone, member, delta) \ + do { \ + __mod_page_state_offset(state_zone_offset(zone, member), (delta)); \ + } while (0) + +#define mod_page_state_zone(zone, member, delta) \ + do { \ + mod_page_state_offset(state_zone_offset(zone, member), (delta)); \ + } while (0) + +DECLARE_PER_CPU(struct page_state, page_states); + +#endif /* _LINUX_VMSTAT_H */ + diff --git a/mm/Makefile b/mm/Makefile index 0b8f73f2ed1640a86832dafac9301b003011a91f..9dd824c11eeb9602e95fbdb9a28ffb6276acf5e0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -10,7 +10,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ page_alloc.o page-writeback.o pdflush.o \ readahead.o swap.o truncate.o vmscan.o \ - prio_tree.o util.o mmzone.o $(mmu-y) + prio_tree.o util.o mmzone.o vmstat.o $(mmu-y) obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 084a2de7e52a8c8b4ceaa3c78997199d17f770e5..87dc1297fe39691dfc9dbb16d84a07f75ba3c889 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1231,141 +1231,6 @@ static void show_node(struct zone *zone) #define show_node(zone) do { } while (0) #endif -/* - * Accumulate the page_state information across all CPUs. - * The result is unavoidably approximate - it can change - * during and after execution of this function. - */ -static DEFINE_PER_CPU(struct page_state, page_states) = {0}; - -atomic_t nr_pagecache = ATOMIC_INIT(0); -EXPORT_SYMBOL(nr_pagecache); -#ifdef CONFIG_SMP -DEFINE_PER_CPU(long, nr_pagecache_local) = 0; -#endif - -static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask) -{ - unsigned cpu; - - memset(ret, 0, nr * sizeof(unsigned long)); - cpus_and(*cpumask, *cpumask, cpu_online_map); - - for_each_cpu_mask(cpu, *cpumask) { - unsigned long *in; - unsigned long *out; - unsigned off; - unsigned next_cpu; - - in = (unsigned long *)&per_cpu(page_states, cpu); - - next_cpu = next_cpu(cpu, *cpumask); - if (likely(next_cpu < NR_CPUS)) - prefetch(&per_cpu(page_states, next_cpu)); - - out = (unsigned long *)ret; - for (off = 0; off < nr; off++) - *out++ += *in++; - } -} - -void get_page_state_node(struct page_state *ret, int node) -{ - int nr; - cpumask_t mask = node_to_cpumask(node); - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr+1, &mask); -} - -void get_page_state(struct page_state *ret) -{ - int nr; - cpumask_t mask = CPU_MASK_ALL; - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr + 1, &mask); -} - -void get_full_page_state(struct page_state *ret) -{ - cpumask_t mask = CPU_MASK_ALL; - - __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask); -} - -unsigned long read_page_state_offset(unsigned long offset) -{ - unsigned long ret = 0; - int cpu; - - for_each_online_cpu(cpu) { - unsigned long in; - - in = (unsigned long)&per_cpu(page_states, cpu) + offset; - ret += *((unsigned long *)in); - } - return ret; -} - -void __mod_page_state_offset(unsigned long offset, unsigned long delta) -{ - void *ptr; - - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; -} -EXPORT_SYMBOL(__mod_page_state_offset); - -void mod_page_state_offset(unsigned long offset, unsigned long delta) -{ - unsigned long flags; - void *ptr; - - local_irq_save(flags); - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; - local_irq_restore(flags); -} -EXPORT_SYMBOL(mod_page_state_offset); - -void __get_zone_counts(unsigned long *active, unsigned long *inactive, - unsigned long *free, struct pglist_data *pgdat) -{ - struct zone *zones = pgdat->node_zones; - int i; - - *active = 0; - *inactive = 0; - *free = 0; - for (i = 0; i < MAX_NR_ZONES; i++) { - *active += zones[i].nr_active; - *inactive += zones[i].nr_inactive; - *free += zones[i].free_pages; - } -} - -void get_zone_counts(unsigned long *active, - unsigned long *inactive, unsigned long *free) -{ - struct pglist_data *pgdat; - - *active = 0; - *inactive = 0; - *free = 0; - for_each_online_pgdat(pgdat) { - unsigned long l, m, n; - __get_zone_counts(&l, &m, &n, pgdat); - *active += l; - *inactive += m; - *free += n; - } -} - void si_meminfo(struct sysinfo *val) { val->totalram = totalram_pages; @@ -2253,278 +2118,6 @@ void __init free_area_init(unsigned long *zones_size) __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); } -#ifdef CONFIG_PROC_FS - -#include - -static void *frag_start(struct seq_file *m, loff_t *pos) -{ - pg_data_t *pgdat; - loff_t node = *pos; - for (pgdat = first_online_pgdat(); - pgdat && node; - pgdat = next_online_pgdat(pgdat)) - --node; - - return pgdat; -} - -static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) -{ - pg_data_t *pgdat = (pg_data_t *)arg; - - (*pos)++; - return next_online_pgdat(pgdat); -} - -static void frag_stop(struct seq_file *m, void *arg) -{ -} - -/* - * This walks the free areas for each zone. - */ -static int frag_show(struct seq_file *m, void *arg) -{ - pg_data_t *pgdat = (pg_data_t *)arg; - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - int order; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) - seq_printf(m, "%6lu ", zone->free_area[order].nr_free); - spin_unlock_irqrestore(&zone->lock, flags); - seq_putc(m, '\n'); - } - return 0; -} - -struct seq_operations fragmentation_op = { - .start = frag_start, - .next = frag_next, - .stop = frag_stop, - .show = frag_show, -}; - -/* - * Output information about zones in @pgdat. - */ -static int zoneinfo_show(struct seq_file *m, void *arg) -{ - pg_data_t *pgdat = arg; - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) { - int i; - - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); - seq_printf(m, - "\n pages free %lu" - "\n min %lu" - "\n low %lu" - "\n high %lu" - "\n active %lu" - "\n inactive %lu" - "\n scanned %lu (a: %lu i: %lu)" - "\n spanned %lu" - "\n present %lu", - zone->free_pages, - zone->pages_min, - zone->pages_low, - zone->pages_high, - zone->nr_active, - zone->nr_inactive, - zone->pages_scanned, - zone->nr_scan_active, zone->nr_scan_inactive, - zone->spanned_pages, - zone->present_pages); - seq_printf(m, - "\n protection: (%lu", - zone->lowmem_reserve[0]); - for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); - seq_printf(m, - ")" - "\n pagesets"); - for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; - int j; - - pageset = zone_pcp(zone, i); - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - if (pageset->pcp[j].count) - break; - } - if (j == ARRAY_SIZE(pageset->pcp)) - continue; - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - seq_printf(m, - "\n cpu: %i pcp: %i" - "\n count: %i" - "\n high: %i" - "\n batch: %i", - i, j, - pageset->pcp[j].count, - pageset->pcp[j].high, - pageset->pcp[j].batch); - } -#ifdef CONFIG_NUMA - seq_printf(m, - "\n numa_hit: %lu" - "\n numa_miss: %lu" - "\n numa_foreign: %lu" - "\n interleave_hit: %lu" - "\n local_node: %lu" - "\n other_node: %lu", - pageset->numa_hit, - pageset->numa_miss, - pageset->numa_foreign, - pageset->interleave_hit, - pageset->local_node, - pageset->other_node); -#endif - } - seq_printf(m, - "\n all_unreclaimable: %u" - "\n prev_priority: %i" - "\n temp_priority: %i" - "\n start_pfn: %lu", - zone->all_unreclaimable, - zone->prev_priority, - zone->temp_priority, - zone->zone_start_pfn); - spin_unlock_irqrestore(&zone->lock, flags); - seq_putc(m, '\n'); - } - return 0; -} - -struct seq_operations zoneinfo_op = { - .start = frag_start, /* iterate over all zones. The same as in - * fragmentation. */ - .next = frag_next, - .stop = frag_stop, - .show = zoneinfo_show, -}; - -static char *vmstat_text[] = { - "nr_dirty", - "nr_writeback", - "nr_unstable", - "nr_page_table_pages", - "nr_mapped", - "nr_slab", - - "pgpgin", - "pgpgout", - "pswpin", - "pswpout", - - "pgalloc_high", - "pgalloc_normal", - "pgalloc_dma32", - "pgalloc_dma", - - "pgfree", - "pgactivate", - "pgdeactivate", - - "pgfault", - "pgmajfault", - - "pgrefill_high", - "pgrefill_normal", - "pgrefill_dma32", - "pgrefill_dma", - - "pgsteal_high", - "pgsteal_normal", - "pgsteal_dma32", - "pgsteal_dma", - - "pgscan_kswapd_high", - "pgscan_kswapd_normal", - "pgscan_kswapd_dma32", - "pgscan_kswapd_dma", - - "pgscan_direct_high", - "pgscan_direct_normal", - "pgscan_direct_dma32", - "pgscan_direct_dma", - - "pginodesteal", - "slabs_scanned", - "kswapd_steal", - "kswapd_inodesteal", - "pageoutrun", - "allocstall", - - "pgrotated", - "nr_bounce", -}; - -static void *vmstat_start(struct seq_file *m, loff_t *pos) -{ - struct page_state *ps; - - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; - - ps = kmalloc(sizeof(*ps), GFP_KERNEL); - m->private = ps; - if (!ps) - return ERR_PTR(-ENOMEM); - get_full_page_state(ps); - ps->pgpgin /= 2; /* sectors -> kbytes */ - ps->pgpgout /= 2; - return (unsigned long *)ps + *pos; -} - -static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) -{ - (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; - return (unsigned long *)m->private + *pos; -} - -static int vmstat_show(struct seq_file *m, void *arg) -{ - unsigned long *l = arg; - unsigned long off = l - (unsigned long *)m->private; - - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); - return 0; -} - -static void vmstat_stop(struct seq_file *m, void *arg) -{ - kfree(m->private); - m->private = NULL; -} - -struct seq_operations vmstat_op = { - .start = vmstat_start, - .next = vmstat_next, - .stop = vmstat_stop, - .show = vmstat_show, -}; - -#endif /* CONFIG_PROC_FS */ - #ifdef CONFIG_HOTPLUG_CPU static int page_alloc_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) diff --git a/mm/vmstat.c b/mm/vmstat.c new file mode 100644 index 0000000000000000000000000000000000000000..ad456202ff1a4ab28b0ab24e697c00d89efe5af6 --- /dev/null +++ b/mm/vmstat.c @@ -0,0 +1,417 @@ +/* + * linux/mm/vmstat.c + * + * Manages VM statistics + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +#include +#include + +/* + * Accumulate the page_state information across all CPUs. + * The result is unavoidably approximate - it can change + * during and after execution of this function. + */ +DEFINE_PER_CPU(struct page_state, page_states) = {0}; + +atomic_t nr_pagecache = ATOMIC_INIT(0); +EXPORT_SYMBOL(nr_pagecache); +#ifdef CONFIG_SMP +DEFINE_PER_CPU(long, nr_pagecache_local) = 0; +#endif + +static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask) +{ + unsigned cpu; + + memset(ret, 0, nr * sizeof(unsigned long)); + cpus_and(*cpumask, *cpumask, cpu_online_map); + + for_each_cpu_mask(cpu, *cpumask) { + unsigned long *in; + unsigned long *out; + unsigned off; + unsigned next_cpu; + + in = (unsigned long *)&per_cpu(page_states, cpu); + + next_cpu = next_cpu(cpu, *cpumask); + if (likely(next_cpu < NR_CPUS)) + prefetch(&per_cpu(page_states, next_cpu)); + + out = (unsigned long *)ret; + for (off = 0; off < nr; off++) + *out++ += *in++; + } +} + +void get_page_state_node(struct page_state *ret, int node) +{ + int nr; + cpumask_t mask = node_to_cpumask(node); + + nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); + nr /= sizeof(unsigned long); + + __get_page_state(ret, nr+1, &mask); +} + +void get_page_state(struct page_state *ret) +{ + int nr; + cpumask_t mask = CPU_MASK_ALL; + + nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); + nr /= sizeof(unsigned long); + + __get_page_state(ret, nr + 1, &mask); +} + +void get_full_page_state(struct page_state *ret) +{ + cpumask_t mask = CPU_MASK_ALL; + + __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask); +} + +unsigned long read_page_state_offset(unsigned long offset) +{ + unsigned long ret = 0; + int cpu; + + for_each_online_cpu(cpu) { + unsigned long in; + + in = (unsigned long)&per_cpu(page_states, cpu) + offset; + ret += *((unsigned long *)in); + } + return ret; +} + +void __mod_page_state_offset(unsigned long offset, unsigned long delta) +{ + void *ptr; + + ptr = &__get_cpu_var(page_states); + *(unsigned long *)(ptr + offset) += delta; +} +EXPORT_SYMBOL(__mod_page_state_offset); + +void mod_page_state_offset(unsigned long offset, unsigned long delta) +{ + unsigned long flags; + void *ptr; + + local_irq_save(flags); + ptr = &__get_cpu_var(page_states); + *(unsigned long *)(ptr + offset) += delta; + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_page_state_offset); + +void __get_zone_counts(unsigned long *active, unsigned long *inactive, + unsigned long *free, struct pglist_data *pgdat) +{ + struct zone *zones = pgdat->node_zones; + int i; + + *active = 0; + *inactive = 0; + *free = 0; + for (i = 0; i < MAX_NR_ZONES; i++) { + *active += zones[i].nr_active; + *inactive += zones[i].nr_inactive; + *free += zones[i].free_pages; + } +} + +void get_zone_counts(unsigned long *active, + unsigned long *inactive, unsigned long *free) +{ + struct pglist_data *pgdat; + + *active = 0; + *inactive = 0; + *free = 0; + for_each_online_pgdat(pgdat) { + unsigned long l, m, n; + __get_zone_counts(&l, &m, &n, pgdat); + *active += l; + *inactive += m; + *free += n; + } +} + +#ifdef CONFIG_PROC_FS + +#include + +static void *frag_start(struct seq_file *m, loff_t *pos) +{ + pg_data_t *pgdat; + loff_t node = *pos; + for (pgdat = first_online_pgdat(); + pgdat && node; + pgdat = next_online_pgdat(pgdat)) + --node; + + return pgdat; +} + +static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + (*pos)++; + return next_online_pgdat(pgdat); +} + +static void frag_stop(struct seq_file *m, void *arg) +{ +} + +/* + * This walks the free areas for each zone. + */ +static int frag_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + int order; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + spin_unlock_irqrestore(&zone->lock, flags); + seq_putc(m, '\n'); + } + return 0; +} + +struct seq_operations fragmentation_op = { + .start = frag_start, + .next = frag_next, + .stop = frag_stop, + .show = frag_show, +}; + +static char *vmstat_text[] = { + "nr_dirty", + "nr_writeback", + "nr_unstable", + "nr_page_table_pages", + "nr_mapped", + "nr_slab", + + "pgpgin", + "pgpgout", + "pswpin", + "pswpout", + + "pgalloc_high", + "pgalloc_normal", + "pgalloc_dma32", + "pgalloc_dma", + + "pgfree", + "pgactivate", + "pgdeactivate", + + "pgfault", + "pgmajfault", + + "pgrefill_high", + "pgrefill_normal", + "pgrefill_dma32", + "pgrefill_dma", + + "pgsteal_high", + "pgsteal_normal", + "pgsteal_dma32", + "pgsteal_dma", + + "pgscan_kswapd_high", + "pgscan_kswapd_normal", + "pgscan_kswapd_dma32", + "pgscan_kswapd_dma", + + "pgscan_direct_high", + "pgscan_direct_normal", + "pgscan_direct_dma32", + "pgscan_direct_dma", + + "pginodesteal", + "slabs_scanned", + "kswapd_steal", + "kswapd_inodesteal", + "pageoutrun", + "allocstall", + + "pgrotated", + "nr_bounce", +}; + +/* + * Output information about zones in @pgdat. + */ +static int zoneinfo_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = arg; + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) { + int i; + + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); + seq_printf(m, + "\n pages free %lu" + "\n min %lu" + "\n low %lu" + "\n high %lu" + "\n active %lu" + "\n inactive %lu" + "\n scanned %lu (a: %lu i: %lu)" + "\n spanned %lu" + "\n present %lu", + zone->free_pages, + zone->pages_min, + zone->pages_low, + zone->pages_high, + zone->nr_active, + zone->nr_inactive, + zone->pages_scanned, + zone->nr_scan_active, zone->nr_scan_inactive, + zone->spanned_pages, + zone->present_pages); + seq_printf(m, + "\n protection: (%lu", + zone->lowmem_reserve[0]); + for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) + seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, + ")" + "\n pagesets"); + for_each_online_cpu(i) { + struct per_cpu_pageset *pageset; + int j; + + pageset = zone_pcp(zone, i); + for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { + if (pageset->pcp[j].count) + break; + } + if (j == ARRAY_SIZE(pageset->pcp)) + continue; + for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { + seq_printf(m, + "\n cpu: %i pcp: %i" + "\n count: %i" + "\n high: %i" + "\n batch: %i", + i, j, + pageset->pcp[j].count, + pageset->pcp[j].high, + pageset->pcp[j].batch); + } +#ifdef CONFIG_NUMA + seq_printf(m, + "\n numa_hit: %lu" + "\n numa_miss: %lu" + "\n numa_foreign: %lu" + "\n interleave_hit: %lu" + "\n local_node: %lu" + "\n other_node: %lu", + pageset->numa_hit, + pageset->numa_miss, + pageset->numa_foreign, + pageset->interleave_hit, + pageset->local_node, + pageset->other_node); +#endif + } + seq_printf(m, + "\n all_unreclaimable: %u" + "\n prev_priority: %i" + "\n temp_priority: %i" + "\n start_pfn: %lu", + zone->all_unreclaimable, + zone->prev_priority, + zone->temp_priority, + zone->zone_start_pfn); + spin_unlock_irqrestore(&zone->lock, flags); + seq_putc(m, '\n'); + } + return 0; +} + +struct seq_operations zoneinfo_op = { + .start = frag_start, /* iterate over all zones. The same as in + * fragmentation. */ + .next = frag_next, + .stop = frag_stop, + .show = zoneinfo_show, +}; + +static void *vmstat_start(struct seq_file *m, loff_t *pos) +{ + struct page_state *ps; + + if (*pos >= ARRAY_SIZE(vmstat_text)) + return NULL; + + ps = kmalloc(sizeof(*ps), GFP_KERNEL); + m->private = ps; + if (!ps) + return ERR_PTR(-ENOMEM); + get_full_page_state(ps); + ps->pgpgin /= 2; /* sectors -> kbytes */ + ps->pgpgout /= 2; + return (unsigned long *)ps + *pos; +} + +static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) +{ + (*pos)++; + if (*pos >= ARRAY_SIZE(vmstat_text)) + return NULL; + return (unsigned long *)m->private + *pos; +} + +static int vmstat_show(struct seq_file *m, void *arg) +{ + unsigned long *l = arg; + unsigned long off = l - (unsigned long *)m->private; + + seq_printf(m, "%s %lu\n", vmstat_text[off], *l); + return 0; +} + +static void vmstat_stop(struct seq_file *m, void *arg) +{ + kfree(m->private); + m->private = NULL; +} + +struct seq_operations vmstat_op = { + .start = vmstat_start, + .next = vmstat_next, + .stop = vmstat_stop, + .show = vmstat_show, +}; + +#endif /* CONFIG_PROC_FS */ +