From f3ef9ead31ae995251b420ac98398bd7545bf4e1 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 25 Sep 2006 16:24:57 -0700 Subject: [PATCH] do not free non slab allocated per_cpu_pageset Stops panic associated with attempting to free a non slab-allocated per_cpu_pageset. Signed-off-by: David Rientjes Acked-by: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3b5358a0561f..8a52ba9fe693 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1845,8 +1845,10 @@ static inline void free_zone_pagesets(int cpu) for_each_zone(zone) { struct per_cpu_pageset *pset = zone_pcp(zone, cpu); + /* Free per_cpu_pageset if it is slab allocated */ + if (pset != &boot_pageset[cpu]) + kfree(pset); zone_pcp(zone, cpu) = NULL; - kfree(pset); } } -- cgit From 725d704ecaca4a43f067092c140d4f3271cf2856 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Mon, 25 Sep 2006 23:30:55 -0700 Subject: [PATCH] mm: VM_BUG_ON Introduce a VM_BUG_ON, which is turned on with CONFIG_DEBUG_VM. Use this in the lightweight, inline refcounting functions; PageLRU and PageActive checks in vmscan, because they're pretty well confined to vmscan. And in page allocate/free fastpaths which can be the hottest parts of the kernel for kbuilds. Unlike BUG_ON, VM_BUG_ON must not be used to execute statements with side-effects, and should not be used outside core mm code. Signed-off-by: Nick Piggin Cc: Hugh Dickins Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 +++++++++- mm/internal.h | 4 ++-- mm/page_alloc.c | 23 +++++++++++------------ mm/swap.c | 12 ++++++------ mm/vmscan.c | 16 ++++++++-------- 5 files changed, 36 insertions(+), 29 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 224178a000d2..7d20b25c58fc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -278,6 +278,12 @@ struct page { */ #include +#ifdef CONFIG_DEBUG_VM +#define VM_BUG_ON(cond) BUG_ON(cond) +#else +#define VM_BUG_ON(condition) do { } while(0) +#endif + /* * Methods to modify the page usage count. * @@ -297,7 +303,7 @@ struct page { */ static inline int put_page_testzero(struct page *page) { - BUG_ON(atomic_read(&page->_count) == 0); + VM_BUG_ON(atomic_read(&page->_count) == 0); return atomic_dec_and_test(&page->_count); } @@ -307,6 +313,7 @@ static inline int put_page_testzero(struct page *page) */ static inline int get_page_unless_zero(struct page *page) { + VM_BUG_ON(PageCompound(page)); return atomic_inc_not_zero(&page->_count); } @@ -323,6 +330,7 @@ static inline void get_page(struct page *page) { if (unlikely(PageCompound(page))) page = (struct page *)page_private(page); + VM_BUG_ON(atomic_read(&page->_count) == 0); atomic_inc(&page->_count); } diff --git a/mm/internal.h b/mm/internal.h index d20e3cc4aef0..d527b80b292f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -24,8 +24,8 @@ static inline void set_page_count(struct page *page, int v) */ static inline void set_page_refcounted(struct page *page) { - BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page); - BUG_ON(atomic_read(&page->_count)); + VM_BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page); + VM_BUG_ON(atomic_read(&page->_count)); set_page_count(page, 1); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8a52ba9fe693..4b33878e9488 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -127,7 +127,6 @@ static int bad_range(struct zone *zone, struct page *page) return 0; } - #else static inline int bad_range(struct zone *zone, struct page *page) { @@ -218,12 +217,12 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) { int i; - BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM); + VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM); /* * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO * and __GFP_HIGHMEM from hard or soft interrupt context. */ - BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); + VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); for (i = 0; i < (1 << order); i++) clear_highpage(page + i); } @@ -347,8 +346,8 @@ static inline void __free_one_page(struct page *page, page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - BUG_ON(page_idx & (order_size - 1)); - BUG_ON(bad_range(zone, page)); + VM_BUG_ON(page_idx & (order_size - 1)); + VM_BUG_ON(bad_range(zone, page)); zone->free_pages += order_size; while (order < MAX_ORDER-1) { @@ -421,7 +420,7 @@ static void free_pages_bulk(struct zone *zone, int count, while (count--) { struct page *page; - BUG_ON(list_empty(list)); + VM_BUG_ON(list_empty(list)); page = list_entry(list->prev, struct page, lru); /* have to delete it as __free_one_page list manipulates */ list_del(&page->lru); @@ -512,7 +511,7 @@ static inline void expand(struct zone *zone, struct page *page, area--; high--; size >>= 1; - BUG_ON(bad_range(zone, &page[size])); + VM_BUG_ON(bad_range(zone, &page[size])); list_add(&page[size].lru, &area->free_list); area->nr_free++; set_page_order(&page[size], high); @@ -761,8 +760,8 @@ void split_page(struct page *page, unsigned int order) { int i; - BUG_ON(PageCompound(page)); - BUG_ON(!page_count(page)); + VM_BUG_ON(PageCompound(page)); + VM_BUG_ON(!page_count(page)); for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); } @@ -809,7 +808,7 @@ again: local_irq_restore(flags); put_cpu(); - BUG_ON(bad_range(zone, page)); + VM_BUG_ON(bad_range(zone, page)); if (prep_new_page(page, order, gfp_flags)) goto again; return page; @@ -1083,7 +1082,7 @@ fastcall unsigned long get_zeroed_page(gfp_t gfp_mask) * get_zeroed_page() returns a 32-bit address, which cannot represent * a highmem page */ - BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); + VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); page = alloc_pages(gfp_mask | __GFP_ZERO, 0); if (page) @@ -1116,7 +1115,7 @@ EXPORT_SYMBOL(__free_pages); fastcall void free_pages(unsigned long addr, unsigned int order) { if (addr != 0) { - BUG_ON(!virt_addr_valid((void *)addr)); + VM_BUG_ON(!virt_addr_valid((void *)addr)); __free_pages(virt_to_page((void *)addr), order); } } diff --git a/mm/swap.c b/mm/swap.c index 687686a61f7c..600235e43704 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -233,7 +233,7 @@ void fastcall __page_cache_release(struct page *page) struct zone *zone = page_zone(page); spin_lock_irqsave(&zone->lru_lock, flags); - BUG_ON(!PageLRU(page)); + VM_BUG_ON(!PageLRU(page)); __ClearPageLRU(page); del_page_from_lru(zone, page); spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -284,7 +284,7 @@ void release_pages(struct page **pages, int nr, int cold) zone = pagezone; spin_lock_irq(&zone->lru_lock); } - BUG_ON(!PageLRU(page)); + VM_BUG_ON(!PageLRU(page)); __ClearPageLRU(page); del_page_from_lru(zone, page); } @@ -337,7 +337,7 @@ void __pagevec_release_nonlru(struct pagevec *pvec) for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); if (put_page_testzero(page)) pagevec_add(&pages_to_free, page); } @@ -364,7 +364,7 @@ void __pagevec_lru_add(struct pagevec *pvec) zone = pagezone; spin_lock_irq(&zone->lru_lock); } - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); SetPageLRU(page); add_page_to_inactive_list(zone, page); } @@ -391,9 +391,9 @@ void __pagevec_lru_add_active(struct pagevec *pvec) zone = pagezone; spin_lock_irq(&zone->lru_lock); } - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); SetPageLRU(page); - BUG_ON(PageActive(page)); + VM_BUG_ON(PageActive(page)); SetPageActive(page); add_page_to_active_list(zone, page); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5d4c4d02254d..41a3da3d6ccc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -440,7 +440,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (TestSetPageLocked(page)) goto keep; - BUG_ON(PageActive(page)); + VM_BUG_ON(PageActive(page)); sc->nr_scanned++; @@ -564,7 +564,7 @@ keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); } list_splice(&ret_pages, page_list); if (pagevec_count(&freed_pvec)) @@ -603,7 +603,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); - BUG_ON(!PageLRU(page)); + VM_BUG_ON(!PageLRU(page)); list_del(&page->lru); target = src; @@ -674,7 +674,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, */ while (!list_empty(&page_list)) { page = lru_to_page(&page_list); - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); SetPageLRU(page); list_del(&page->lru); if (PageActive(page)) @@ -797,9 +797,9 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, while (!list_empty(&l_inactive)) { page = lru_to_page(&l_inactive); prefetchw_prev_lru_page(page, &l_inactive, flags); - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); SetPageLRU(page); - BUG_ON(!PageActive(page)); + VM_BUG_ON(!PageActive(page)); ClearPageActive(page); list_move(&page->lru, &zone->inactive_list); @@ -827,9 +827,9 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, while (!list_empty(&l_active)) { page = lru_to_page(&l_active); prefetchw_prev_lru_page(page, &l_active, flags); - BUG_ON(PageLRU(page)); + VM_BUG_ON(PageLRU(page)); SetPageLRU(page); - BUG_ON(!PageActive(page)); + VM_BUG_ON(!PageActive(page)); list_move(&page->lru, &zone->active_list); pgmoved++; if (!pagevec_add(&pvec, page)) { -- cgit From 182e8e237349e7b6354f45aee4780b6423fd6a50 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:10 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: make display of highmem counters conditional on CONFIG_HIGHMEM Do not display HIGHMEM memory sizes if CONFIG_HIGHMEM is not set. Make HIGHMEM dependent texts and make display of highmem counters optional Some texts are depending on CONFIG_HIGHMEM. Remove those strings and remove the display of highmem counter values if CONFIG_HIGHMEM is not set. [akpm@osdl.org: remove some ifdefs] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 4 ++++ fs/proc/proc_misc.c | 4 ++++ mm/page_alloc.c | 4 ---- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index e9b0957f15d1..e09f5c2c11ee 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -54,10 +54,12 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf) "Node %d MemUsed: %8lu kB\n" "Node %d Active: %8lu kB\n" "Node %d Inactive: %8lu kB\n" +#ifdef CONFIG_HIGHMEM "Node %d HighTotal: %8lu kB\n" "Node %d HighFree: %8lu kB\n" "Node %d LowTotal: %8lu kB\n" "Node %d LowFree: %8lu kB\n" +#endif "Node %d Dirty: %8lu kB\n" "Node %d Writeback: %8lu kB\n" "Node %d FilePages: %8lu kB\n" @@ -72,10 +74,12 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf) nid, K(i.totalram - i.freeram), nid, K(active), nid, K(inactive), +#ifdef CONFIG_HIGHMEM nid, K(i.totalhigh), nid, K(i.freehigh), nid, K(i.totalram - i.totalhigh), nid, K(i.freeram - i.freehigh), +#endif nid, K(node_page_state(nid, NR_FILE_DIRTY)), nid, K(node_page_state(nid, NR_WRITEBACK)), nid, K(node_page_state(nid, NR_FILE_PAGES)), diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 942156225447..caa0a51560a0 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -157,10 +157,12 @@ static int meminfo_read_proc(char *page, char **start, off_t off, "SwapCached: %8lu kB\n" "Active: %8lu kB\n" "Inactive: %8lu kB\n" +#ifdef CONFIG_HIGHMEM "HighTotal: %8lu kB\n" "HighFree: %8lu kB\n" "LowTotal: %8lu kB\n" "LowFree: %8lu kB\n" +#endif "SwapTotal: %8lu kB\n" "SwapFree: %8lu kB\n" "Dirty: %8lu kB\n" @@ -183,10 +185,12 @@ static int meminfo_read_proc(char *page, char **start, off_t off, K(total_swapcache_pages), K(active), K(inactive), +#ifdef CONFIG_HIGHMEM K(i.totalhigh), K(i.freehigh), K(i.totalram-i.totalhigh), K(i.freeram-i.freehigh), +#endif K(i.totalswap), K(i.freeswap), K(global_page_state(NR_FILE_DIRTY)), diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4b33878e9488..e26491cb5a27 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1281,10 +1281,6 @@ void show_free_areas(void) get_zone_counts(&active, &inactive, &free); - printk("Free pages: %11ukB (%ukB HighMem)\n", - K(nr_free_pages()), - K(nr_free_highpages())); - printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu " "unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n", active, -- cgit From c1f60a5a419cc60aff27daffb150f5a3a3a79ef4 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:11 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: move HIGHMEM counters into highmem.c/.h Move totalhigh_pages and nr_free_highpages() into highmem.c/.h Move the totalhigh_pages definition into highmem.c/.h. Move the nr_free_highpages function into highmem.c [yoichi_yuasa@tripeaks.co.jp: build fix] Signed-off-by: Christoph Lameter Signed-off-by: Yoichi Yuasa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/sgi-ip27/ip27-memory.c | 1 + arch/um/kernel/mem.c | 2 ++ include/linux/highmem.h | 3 +++ include/linux/swap.h | 1 - mm/highmem.c | 13 +++++++++++++ mm/page_alloc.c | 15 --------------- mm/shmem.c | 1 + 7 files changed, 20 insertions(+), 16 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 59bfc0fc3f45..16e5682b01f1 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 61280167c560..b39e624c3291 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -79,8 +79,10 @@ void mem_init(void) /* this will put all low memory onto the freelists */ totalram_pages = free_all_bootmem(); +#ifdef CONFIG_HIGHMEM totalhigh_pages = highmem >> PAGE_SHIFT; totalram_pages += totalhigh_pages; +#endif num_physpages = totalram_pages; max_pfn = totalram_pages; printk(KERN_INFO "Memory: %luk available\n", diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 42620e723abb..fd7d12daa94f 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -24,11 +24,14 @@ static inline void flush_kernel_dcache_page(struct page *page) /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); +extern unsigned long totalhigh_pages; #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } +#define totalhigh_pages 0 + #ifndef ARCH_HAS_KMAP static inline void *kmap(struct page *page) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 5e59184c9096..34a6bc3e6cf3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -162,7 +162,6 @@ extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct * /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; -extern unsigned long totalhigh_pages; extern unsigned long totalreserve_pages; extern long nr_swap_pages; extern unsigned int nr_free_pages(void); diff --git a/mm/highmem.c b/mm/highmem.c index 9b2a5403c447..ee5519b176ee 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -46,6 +46,19 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) */ #ifdef CONFIG_HIGHMEM +unsigned long totalhigh_pages __read_mostly; + +unsigned int nr_free_highpages (void) +{ + pg_data_t *pgdat; + unsigned int pages = 0; + + for_each_online_pgdat(pgdat) + pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages; + + return pages; +} + static int pkmap_count[LAST_PKMAP]; static unsigned int last_pkmap_nr; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e26491cb5a27..5cde54695cfb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -51,7 +51,6 @@ EXPORT_SYMBOL(node_online_map); nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL; EXPORT_SYMBOL(node_possible_map); unsigned long totalram_pages __read_mostly; -unsigned long totalhigh_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; long nr_swap_pages; int percpu_pagelist_fraction; @@ -1185,20 +1184,6 @@ unsigned int nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER)); } - -#ifdef CONFIG_HIGHMEM -unsigned int nr_free_highpages (void) -{ - pg_data_t *pgdat; - unsigned int pages = 0; - - for_each_online_pgdat(pgdat) - pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages; - - return pages; -} -#endif - #ifdef CONFIG_NUMA static void show_node(struct zone *zone) { diff --git a/mm/shmem.c b/mm/shmem.c index db21c51531ca..8631be45b40d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include -- cgit From 98d2b0ebda72fc39cdefd3720d50b9b3ce409085 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:12 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: page allocator ZONE_HIGHMEM cleanup page allocator ZONE_HIGHMEM fixups 1. We do not need to do an #ifdef in si_meminfo since both counters in use are zero if !CONFIG_HIGHMEM. 2. Add #ifdef in si_meminfo_node instead to avoid referencing zone information for ZONE_HIGHMEM if we do not have HIGHMEM (may not be there after the following patches). 3. Replace the use of ZONE_HIGHMEM with MAX_NR_ZONES in build_zonelists_node 4. build_zonelists_node: Remove BUG_ON for ZONE_HIGHMEM. Zone will be optional soon and thus BUG_ON cannot be triggered anymore. 5. init_free_area_core: Replace a use of ZONE_HIGHMEM with NR_MAX_ZONES. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5cde54695cfb..13c102b95c57 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1199,13 +1199,8 @@ void si_meminfo(struct sysinfo *val) val->sharedram = 0; val->freeram = nr_free_pages(); val->bufferram = nr_blockdev_pages(); -#ifdef CONFIG_HIGHMEM val->totalhigh = totalhigh_pages; val->freehigh = nr_free_highpages(); -#else - val->totalhigh = 0; - val->freehigh = 0; -#endif val->mem_unit = PAGE_SIZE; } @@ -1218,8 +1213,13 @@ void si_meminfo_node(struct sysinfo *val, int nid) val->totalram = pgdat->node_present_pages; val->freeram = nr_free_pages_pgdat(pgdat); +#ifdef CONFIG_HIGHMEM val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages; val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages; +#else + val->totalhigh = 0; + val->freehigh = 0; +#endif val->mem_unit = PAGE_SIZE; } #endif @@ -1344,14 +1344,11 @@ static int __meminit build_zonelists_node(pg_data_t *pgdat, { struct zone *zone; - BUG_ON(zone_type > ZONE_HIGHMEM); + BUG_ON(zone_type >= MAX_NR_ZONES); do { zone = pgdat->node_zones + zone_type; if (populated_zone(zone)) { -#ifndef CONFIG_HIGHMEM - BUG_ON(zone_type > ZONE_NORMAL); -#endif zonelist->zones[nr_zones++] = zone; check_highest_zone(zone_type); } @@ -1981,7 +1978,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, if (zholes_size) realsize -= zholes_size[j]; - if (j < ZONE_HIGHMEM) + if (!is_highmem_idx(j)) nr_kernel_pages += realsize; nr_all_pages += realsize; -- cgit From 2f1b6248682f8b39ca3c7e549dfc216d26c4109b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:13 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: use enum to define zones, reformat and comment Use enum for zones and reformat zones dependent information Add comments explaning the use of zones and add a zones_t type for zone numbers. Line up information that will be #ifdefd by the following patches. [akpm@osdl.org: comment cleanups] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++--- include/linux/mmzone.h | 66 +++++++++++++++++++++++++++++++++++--------------- mm/page_alloc.c | 24 +++++++++++++----- 3 files changed, 69 insertions(+), 28 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 45678b036955..2db4229a0066 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -470,7 +470,7 @@ void split_page(struct page *page, unsigned int order); #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define ZONETABLE_MASK ((1UL << ZONETABLE_SHIFT) - 1) -static inline unsigned long page_zonenum(struct page *page) +static inline enum zone_type page_zonenum(struct page *page) { return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } @@ -499,11 +499,12 @@ static inline unsigned long page_to_section(struct page *page) return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } -static inline void set_page_zone(struct page *page, unsigned long zone) +static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } + static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); @@ -515,7 +516,7 @@ static inline void set_page_section(struct page *page, unsigned long section) page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } -static inline void set_page_links(struct page *page, unsigned long zone, +static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f45163c528e8..03a5a6eb0ffa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -88,14 +88,53 @@ struct per_cpu_pageset { #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)]) #endif -#define ZONE_DMA 0 -#define ZONE_DMA32 1 -#define ZONE_NORMAL 2 -#define ZONE_HIGHMEM 3 +enum zone_type { + /* + * ZONE_DMA is used when there are devices that are not able + * to do DMA to all of addressable memory (ZONE_NORMAL). Then we + * carve out the portion of memory that is needed for these devices. + * The range is arch specific. + * + * Some examples + * + * Architecture Limit + * --------------------------- + * parisc, ia64, sparc <4G + * s390 <2G + * arm26 <48M + * arm Various + * alpha Unlimited or 0-16MB. + * + * i386, x86_64 and multiple other arches + * <16M. + */ + ZONE_DMA, + /* + * x86_64 needs two ZONE_DMAs because it supports devices that are + * only able to do DMA to the lower 16M but also 32 bit devices that + * can only do DMA areas below 4G. + */ + ZONE_DMA32, + /* + * Normal addressable memory is in ZONE_NORMAL. DMA operations can be + * performed on pages in ZONE_NORMAL if the DMA devices support + * transfers to all addressable memory. + */ + ZONE_NORMAL, + /* + * A memory area that is only addressable by the kernel through + * mapping portions into its own address space. This is for example + * used by i386 to allow the kernel to address the memory beyond + * 900MB. The kernel will set up special mappings (page + * table entries on i386) for each page that the kernel needs to + * access. + */ + ZONE_HIGHMEM, -#define MAX_NR_ZONES 4 /* Sync this with ZONES_SHIFT */ -#define ZONES_SHIFT 2 /* ceil(log2(MAX_NR_ZONES)) */ + MAX_NR_ZONES +}; +#define ZONES_SHIFT 2 /* ceil(log2(MAX_NR_ZONES)) */ /* * When a memory allocation must conform to specific limitations (such @@ -126,16 +165,6 @@ struct per_cpu_pageset { /* #define GFP_ZONETYPES (GFP_ZONEMASK + 1) */ /* Non-loner */ #define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ -/* - * On machines where it is needed (eg PCs) we divide physical memory - * into multiple physical zones. On a 32bit PC we have 4 zones: - * - * ZONE_DMA < 16 MB ISA DMA capable memory - * ZONE_DMA32 0 MB Empty - * ZONE_NORMAL 16-896 MB direct mapped by the kernel - * ZONE_HIGHMEM > 896 MB only page cache and user processes - */ - struct zone { /* Fields commonly accessed by the page allocator */ unsigned long free_pages; @@ -266,7 +295,6 @@ struct zone { char *name; } ____cacheline_internodealigned_in_smp; - /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -373,12 +401,12 @@ static inline int populated_zone(struct zone *zone) return (!!zone->present_pages); } -static inline int is_highmem_idx(int idx) +static inline int is_highmem_idx(enum zone_type idx) { return (idx == ZONE_HIGHMEM); } -static inline int is_normal_idx(int idx) +static inline int is_normal_idx(enum zone_type idx) { return (idx == ZONE_NORMAL); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 13c102b95c57..2410a3cb1c53 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -68,7 +68,11 @@ static void __free_pages_ok(struct page *page, unsigned int order); * TBD: should special case ZONE_DMA32 machines here - in those we normally * don't need any ZONE_NORMAL reservation */ -int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 256, 32 }; +int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { + 256, + 256, + 32 +}; EXPORT_SYMBOL(totalram_pages); @@ -79,7 +83,13 @@ EXPORT_SYMBOL(totalram_pages); struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly; EXPORT_SYMBOL(zone_table); -static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem" }; +static char *zone_names[MAX_NR_ZONES] = { + "DMA", + "DMA32", + "Normal", + "HighMem" +}; + int min_free_kbytes = 1024; unsigned long __meminitdata nr_kernel_pages; @@ -1487,7 +1497,9 @@ static void __meminit build_zonelists(pg_data_t *pgdat) static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, j, k, node, local_node; + int i, node, local_node; + enum zone_type k; + enum zone_type j; local_node = pgdat->node_id; for (i = 0; i < GFP_ZONETYPES; i++) { @@ -1675,8 +1687,8 @@ void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, } #define ZONETABLE_INDEX(x, zone_nr) ((x << ZONES_SHIFT) | zone_nr) -void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, - unsigned long size) +void zonetable_add(struct zone *zone, int nid, enum zone_type zid, + unsigned long pfn, unsigned long size) { unsigned long snum = pfn_to_section_nr(pfn); unsigned long end = pfn_to_section_nr(pfn + size); @@ -1960,7 +1972,7 @@ __meminit int init_currently_empty_zone(struct zone *zone, static void __meminit free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { - unsigned long j; + enum zone_type j; int nid = pgdat->node_id; unsigned long zone_start_pfn = pgdat->node_start_pfn; int ret; -- cgit From fb0e7942bdcbbd2f90e61cb4cfa4fa892a873f8a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:13 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: make ZONE_DMA32 optional Make ZONE_DMA32 optional - Add #ifdefs around ZONE_DMA32 specific code and definitions. - Add CONFIG_ZONE_DMA32 config option and use that for x86_64 that alone needs this zone. - Remove the use of CONFIG_DMA_IS_DMA32 and CONFIG_DMA_IS_NORMAL for ia64 and fix up the way per node ZVCs are calculated. - Fall back to prior GFP_ZONEMASK of 0x03 if there is no DMA32 zone. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/Kconfig | 9 --------- arch/x86_64/Kconfig | 4 ++++ include/linux/gfp.h | 2 +- include/linux/mmzone.h | 16 +++++++++++++--- include/linux/vmstat.h | 4 +--- mm/page_alloc.c | 6 ++++++ 6 files changed, 25 insertions(+), 16 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index db274da7dba1..f521f2f60a78 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -66,15 +66,6 @@ config IA64_UNCACHED_ALLOCATOR bool select GENERIC_ALLOCATOR -config DMA_IS_DMA32 - bool - default y - -config DMA_IS_NORMAL - bool - depends on IA64_SGI_SN2 - default y - config AUDIT_ARCH bool default y diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 6cd4878625f1..581ce9af0ec8 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -24,6 +24,10 @@ config X86 bool default y +config ZONE_DMA32 + bool + default y + config LOCKDEP_SUPPORT bool default y diff --git a/include/linux/gfp.h b/include/linux/gfp.h index cc9e60844484..14610b56c132 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -13,7 +13,7 @@ struct vm_area_struct; /* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low three bits) */ #define __GFP_DMA ((__force gfp_t)0x01u) #define __GFP_HIGHMEM ((__force gfp_t)0x02u) -#ifdef CONFIG_DMA_IS_DMA32 +#ifndef CONFIG_ZONE_DMA32 #define __GFP_DMA32 ((__force gfp_t)0x01) /* ZONE_DMA is ZONE_DMA32 */ #elif BITS_PER_LONG < 64 #define __GFP_DMA32 ((__force gfp_t)0x00) /* ZONE_NORMAL is ZONE_DMA32 */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 03a5a6eb0ffa..adae3c915938 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -109,12 +109,14 @@ enum zone_type { * <16M. */ ZONE_DMA, +#ifdef CONFIG_ZONE_DMA32 /* * x86_64 needs two ZONE_DMAs because it supports devices that are * only able to do DMA to the lower 16M but also 32 bit devices that * can only do DMA areas below 4G. */ ZONE_DMA32, +#endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support @@ -161,9 +163,13 @@ enum zone_type { * * NOTE! Make sure this matches the zones in */ -#define GFP_ZONEMASK 0x07 -/* #define GFP_ZONETYPES (GFP_ZONEMASK + 1) */ /* Non-loner */ -#define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ +#define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ + +#ifdef CONFIG_ZONE_DMA32 +#define GFP_ZONEMASK 0x07 +#else +#define GFP_ZONEMASK 0x03 +#endif struct zone { /* Fields commonly accessed by the page allocator */ @@ -429,7 +435,11 @@ static inline int is_normal(struct zone *zone) static inline int is_dma32(struct zone *zone) { +#ifdef CONFIG_ZONE_DMA32 return zone == zone->zone_pgdat->node_zones + ZONE_DMA32; +#else + return 0; +#endif } static inline int is_dma(struct zone *zone) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 2d9b1b60798a..9c6e62c56ec2 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -124,12 +124,10 @@ static inline unsigned long node_page_state(int node, struct zone *zones = NODE_DATA(node)->node_zones; return -#ifndef CONFIG_DMA_IS_NORMAL -#if !defined(CONFIG_DMA_IS_DMA32) && BITS_PER_LONG >= 64 +#ifdef CONFIG_ZONE_DMA32 zone_page_state(&zones[ZONE_DMA32], item) + #endif zone_page_state(&zones[ZONE_NORMAL], item) + -#endif #ifdef CONFIG_HIGHMEM zone_page_state(&zones[ZONE_HIGHMEM], item) + #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2410a3cb1c53..5b5cbb5e1816 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -70,7 +70,9 @@ static void __free_pages_ok(struct page *page, unsigned int order); */ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, +#ifdef CONFIG_ZONE_DMA32 256, +#endif 32 }; @@ -85,7 +87,9 @@ EXPORT_SYMBOL(zone_table); static char *zone_names[MAX_NR_ZONES] = { "DMA", +#ifdef CONFIG_ZONE_DMA32 "DMA32", +#endif "Normal", "HighMem" }; @@ -1373,8 +1377,10 @@ static inline int highest_zone(int zone_bits) int res = ZONE_NORMAL; if (zone_bits & (__force int)__GFP_HIGHMEM) res = ZONE_HIGHMEM; +#ifdef CONFIG_ZONE_DMA32 if (zone_bits & (__force int)__GFP_DMA32) res = ZONE_DMA32; +#endif if (zone_bits & (__force int)__GFP_DMA) res = ZONE_DMA; return res; -- cgit From e53ef38d05dd59ed281a35590e4a5b64d8ff4c52 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:14 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: make ZONE_HIGHMEM optional Make ZONE_HIGHMEM optional - ifdef out code and definitions related to CONFIG_HIGHMEM - __GFP_HIGHMEM falls back to normal allocations if there is no ZONE_HIGHMEM - GFP_ZONEMASK becomes 0x01 if there is no DMA32 and no HIGHMEM zone. [jdike@addtoit.com: build fix] Signed-off-by: Jeff Dike Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/mem.c | 2 ++ include/linux/gfp.h | 18 ++++++++++-------- include/linux/mmzone.h | 36 +++++++++++++++++++++++++++++++++--- mm/page_alloc.c | 6 ++++++ 4 files changed, 51 insertions(+), 11 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index b39e624c3291..b1cd5c6e468b 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -226,7 +226,9 @@ void paging_init(void) for(i=0;i> PAGE_SHIFT) - (uml_physmem >> PAGE_SHIFT); +#ifdef CONFIG_HIGHMEM zones_size[ZONE_HIGHMEM] = highmem >> PAGE_SHIFT; +#endif free_area_init(zones_size); /* diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 14610b56c132..2a2153ebfe0b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -9,17 +9,19 @@ struct vm_area_struct; /* * GFP bitmasks.. + * + * Zone modifiers (see linux/mmzone.h - low three bits) + * + * These may be masked by GFP_ZONEMASK to make allocations with this bit + * set fall back to ZONE_NORMAL. + * + * Do not put any conditional on these. If necessary modify the definitions + * without the underscores and use the consistently. The definitions here may + * be used in bit comparisons. */ -/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low three bits) */ #define __GFP_DMA ((__force gfp_t)0x01u) #define __GFP_HIGHMEM ((__force gfp_t)0x02u) -#ifndef CONFIG_ZONE_DMA32 -#define __GFP_DMA32 ((__force gfp_t)0x01) /* ZONE_DMA is ZONE_DMA32 */ -#elif BITS_PER_LONG < 64 -#define __GFP_DMA32 ((__force gfp_t)0x00) /* ZONE_NORMAL is ZONE_DMA32 */ -#else -#define __GFP_DMA32 ((__force gfp_t)0x04) /* Has own ZONE_DMA32 */ -#endif +#define __GFP_DMA32 ((__force gfp_t)0x04u) /* * Action modifiers - doesn't change the zoning diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index adae3c915938..76d33e688593 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -123,6 +123,7 @@ enum zone_type { * transfers to all addressable memory. */ ZONE_NORMAL, +#ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example @@ -132,11 +133,10 @@ enum zone_type { * access. */ ZONE_HIGHMEM, - +#endif MAX_NR_ZONES }; -#define ZONES_SHIFT 2 /* ceil(log2(MAX_NR_ZONES)) */ /* * When a memory allocation must conform to specific limitations (such @@ -163,12 +163,34 @@ enum zone_type { * * NOTE! Make sure this matches the zones in */ -#define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ #ifdef CONFIG_ZONE_DMA32 + +#ifdef CONFIG_HIGHMEM +#define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ #define GFP_ZONEMASK 0x07 +#define ZONES_SHIFT 2 /* ceil(log2(MAX_NR_ZONES)) */ #else +#define GFP_ZONETYPES ((0x07 + 1) / 2 + 1) /* Loner */ +/* Mask __GFP_HIGHMEM */ +#define GFP_ZONEMASK 0x05 +#define ZONES_SHIFT 2 +#endif + +#else +#ifdef CONFIG_HIGHMEM + #define GFP_ZONEMASK 0x03 +#define ZONES_SHIFT 2 +#define GFP_ZONETYPES 3 + +#else + +#define GFP_ZONEMASK 0x01 +#define ZONES_SHIFT 1 +#define GFP_ZONETYPES 2 + +#endif #endif struct zone { @@ -409,7 +431,11 @@ static inline int populated_zone(struct zone *zone) static inline int is_highmem_idx(enum zone_type idx) { +#ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM); +#else + return 0; +#endif } static inline int is_normal_idx(enum zone_type idx) @@ -425,7 +451,11 @@ static inline int is_normal_idx(enum zone_type idx) */ static inline int is_highmem(struct zone *zone) { +#ifdef CONFIG_HIGHMEM return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM; +#else + return 0; +#endif } static inline int is_normal(struct zone *zone) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5b5cbb5e1816..6c7c2dd1b3ed 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -73,7 +73,9 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { #ifdef CONFIG_ZONE_DMA32 256, #endif +#ifdef CONFIG_HIGHMEM 32 +#endif }; EXPORT_SYMBOL(totalram_pages); @@ -91,7 +93,9 @@ static char *zone_names[MAX_NR_ZONES] = { "DMA32", #endif "Normal", +#ifdef CONFIG_HIGHMEM "HighMem" +#endif }; int min_free_kbytes = 1024; @@ -1375,8 +1379,10 @@ static int __meminit build_zonelists_node(pg_data_t *pgdat, static inline int highest_zone(int zone_bits) { int res = ZONE_NORMAL; +#ifdef CONFIG_HIGHMEM if (zone_bits & (__force int)__GFP_HIGHMEM) res = ZONE_HIGHMEM; +#endif #ifdef CONFIG_ZONE_DMA32 if (zone_bits & (__force int)__GFP_DMA32) res = ZONE_DMA32; -- cgit From 4e4785bcf0c8503224fa6c17d8e0228de781bff6 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:17 -0700 Subject: [PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone() yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter Signed-off-by: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 15 +++++++++++++++ mm/mempolicy.c | 2 +- mm/page_alloc.c | 16 ---------------- 3 files changed, 16 insertions(+), 17 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2a2153ebfe0b..a0992d392d79 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -85,6 +85,21 @@ static inline int gfp_zone(gfp_t gfp) return zone; } +static inline enum zone_type highest_zone(gfp_t flags) +{ + if (flags & __GFP_DMA) + return ZONE_DMA; +#ifdef CONFIG_ZONE_DMA32 + if (flags & __GFP_DMA32) + return ZONE_DMA32; +#endif +#ifdef CONFIG_HIGHMEM + if (flags & __GFP_HIGHMEM) + return ZONE_HIGHMEM; +#endif + return ZONE_NORMAL; +} + /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a9963ceddd65..9870624d72a6 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1096,7 +1096,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy) case MPOL_BIND: /* Lower zones don't get a policy applied */ /* Careful: current->mems_allowed might have moved */ - if (gfp_zone(gfp) >= policy_zone) + if (highest_zone(gfp) >= policy_zone) if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist)) return policy->v.zonelist; /*FALL THROUGH*/ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6c7c2dd1b3ed..25f39865e324 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1376,22 +1376,6 @@ static int __meminit build_zonelists_node(pg_data_t *pgdat, return nr_zones; } -static inline int highest_zone(int zone_bits) -{ - int res = ZONE_NORMAL; -#ifdef CONFIG_HIGHMEM - if (zone_bits & (__force int)__GFP_HIGHMEM) - res = ZONE_HIGHMEM; -#endif -#ifdef CONFIG_ZONE_DMA32 - if (zone_bits & (__force int)__GFP_DMA32) - res = ZONE_DMA32; -#endif - if (zone_bits & (__force int)__GFP_DMA) - res = ZONE_DMA; - return res; -} - #ifdef CONFIG_NUMA #define MAX_NODE_LOAD (num_online_nodes()) static int __meminitdata node_load[MAX_NUMNODES]; -- cgit From 2f6726e54a9410e2e4cee864947c05e954051916 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:18 -0700 Subject: [PATCH] Apply type enum zone_type After we have done this we can now do some typing cleanup. The memory policy layer keeps a policy_zone that specifies the zone that gets memory policies applied. This variable can now be of type enum zone_type. The check_highest_zone function and the build_zonelists funnctionm must then also take a enum zone_type parameter. Plus there are a number of loops over zones that also should use zone_type. We run into some troubles at some points with functions that need a zone_type variable to become -1. Fix that up. [pj@sgi.com: fix set_mempolicy() crash] Signed-off-by: Christoph Lameter Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ++-- mm/mempolicy.c | 11 ++++++++--- mm/page_alloc.c | 27 +++++++++++++++++---------- 3 files changed, 27 insertions(+), 15 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 72440f0a443d..09f0f575ddff 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -162,9 +162,9 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr); extern unsigned slab_node(struct mempolicy *policy); -extern int policy_zone; +extern enum zone_type policy_zone; -static inline void check_highest_zone(int k) +static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone) policy_zone = k; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9870624d72a6..7da4142ce960 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -105,7 +105,7 @@ static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ -int policy_zone = ZONE_DMA; +enum zone_type policy_zone = ZONE_DMA; struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ @@ -137,7 +137,8 @@ static int mpol_check_policy(int mode, nodemask_t *nodes) static struct zonelist *bind_zonelist(nodemask_t *nodes) { struct zonelist *zl; - int num, max, nd, k; + int num, max, nd; + enum zone_type k; max = 1 + MAX_NR_ZONES * nodes_weight(*nodes); zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL); @@ -148,12 +149,16 @@ static struct zonelist *bind_zonelist(nodemask_t *nodes) lower zones etc. Avoid empty zones because the memory allocator doesn't like them. If you implement node hot removal you have to fix that. */ - for (k = policy_zone; k >= 0; k--) { + k = policy_zone; + while (1) { for_each_node_mask(nd, *nodes) { struct zone *z = &NODE_DATA(nd)->node_zones[k]; if (z->present_pages > 0) zl->zones[num++] = z; } + if (k == 0) + break; + k--; } zl->zones[num] = NULL; return zl; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 25f39865e324..9c44b9a39d30 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -637,7 +637,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, */ void drain_node_pages(int nodeid) { - int i, z; + int i; + enum zone_type z; unsigned long flags; for (z = 0; z < MAX_NR_ZONES; z++) { @@ -1158,7 +1159,8 @@ EXPORT_SYMBOL(nr_free_pages); #ifdef CONFIG_NUMA unsigned int nr_free_pages_pgdat(pg_data_t *pgdat) { - unsigned int i, sum = 0; + unsigned int sum = 0; + enum zone_type i; for (i = 0; i < MAX_NR_ZONES; i++) sum += pgdat->node_zones[i].free_pages; @@ -1358,21 +1360,22 @@ void show_free_areas(void) * Add all populated zones of a node to the zonelist. */ static int __meminit build_zonelists_node(pg_data_t *pgdat, - struct zonelist *zonelist, int nr_zones, int zone_type) + struct zonelist *zonelist, int nr_zones, enum zone_type zone_type) { struct zone *zone; BUG_ON(zone_type >= MAX_NR_ZONES); + zone_type++; do { + zone_type--; zone = pgdat->node_zones + zone_type; if (populated_zone(zone)) { zonelist->zones[nr_zones++] = zone; check_highest_zone(zone_type); } - zone_type--; - } while (zone_type >= 0); + } while (zone_type); return nr_zones; } @@ -1441,10 +1444,11 @@ static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, j, k, node, local_node; + int i, j, node, local_node; int prev_node, load; struct zonelist *zonelist; nodemask_t used_mask; + enum zone_type k; /* initialize zonelists */ for (i = 0; i < GFP_ZONETYPES; i++) { @@ -1628,7 +1632,7 @@ static void __init calculate_zone_totalpages(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { unsigned long realtotalpages, totalpages = 0; - int i; + enum zone_type i; for (i = 0; i < MAX_NR_ZONES; i++) totalpages += zones_size[i]; @@ -2116,7 +2120,7 @@ static void calculate_totalreserve_pages(void) { struct pglist_data *pgdat; unsigned long reserve_pages = 0; - int i, j; + enum zone_type i, j; for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { @@ -2149,7 +2153,7 @@ static void calculate_totalreserve_pages(void) static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - int j, idx; + enum zone_type j, idx; for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { @@ -2158,9 +2162,12 @@ static void setup_per_zone_lowmem_reserve(void) zone->lowmem_reserve[j] = 0; - for (idx = j-1; idx >= 0; idx--) { + idx = j; + while (idx) { struct zone *lower_zone; + idx--; + if (sysctl_lowmem_reserve_ratio[idx] < 1) sysctl_lowmem_reserve_ratio[idx] = 1; -- cgit From 19655d3487001d7df0e10e9cbfc27c758b77c2b5 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:19 -0700 Subject: [PATCH] linearly index zone->node_zonelists[] I wonder why we need this bitmask indexing into zone->node_zonelists[]? We always start with the highest zone and then include all lower zones if we build zonelists. Are there really cases where we need allocation from ZONE_DMA or ZONE_HIGHMEM but not ZONE_NORMAL? It seems that the current implementation of highest_zone() makes that already impossible. If we go linear on the index then gfp_zone() == highest_zone() and a lot of definitions fall by the wayside. We can now revert back to the use of gfp_zone() in mempolicy.c ;-) Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 +----------- include/linux/mmzone.h | 52 +++++--------------------------------------------- mm/mempolicy.c | 2 +- mm/page_alloc.c | 27 +++++++++++--------------- 4 files changed, 18 insertions(+), 75 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a0992d392d79..63ab88a36f39 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -12,9 +12,6 @@ struct vm_area_struct; * * Zone modifiers (see linux/mmzone.h - low three bits) * - * These may be masked by GFP_ZONEMASK to make allocations with this bit - * set fall back to ZONE_NORMAL. - * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use the consistently. The definitions here may * be used in bit comparisons. @@ -78,14 +75,7 @@ struct vm_area_struct; #define GFP_DMA32 __GFP_DMA32 -static inline int gfp_zone(gfp_t gfp) -{ - int zone = GFP_ZONEMASK & (__force int) gfp; - BUG_ON(zone >= GFP_ZONETYPES); - return zone; -} - -static inline enum zone_type highest_zone(gfp_t flags) +static inline enum zone_type gfp_zone(gfp_t flags) { if (flags & __GFP_DMA) return ZONE_DMA; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 76d33e688593..7fe317164b73 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -137,60 +137,18 @@ enum zone_type { MAX_NR_ZONES }; - /* * When a memory allocation must conform to specific limitations (such * as being suitable for DMA) the caller will pass in hints to the * allocator in the gfp_mask, in the zone modifier bits. These bits * are used to select a priority ordered list of memory zones which - * match the requested limits. GFP_ZONEMASK defines which bits within - * the gfp_mask should be considered as zone modifiers. Each valid - * combination of the zone modifier bits has a corresponding list - * of zones (in node_zonelists). Thus for two zone modifiers there - * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will - * be 8 (2 ** 3) zonelists. GFP_ZONETYPES defines the number of possible - * combinations of zone modifiers in "zone modifier space". - * - * As an optimisation any zone modifier bits which are only valid when - * no other zone modifier bits are set (loners) should be placed in - * the highest order bits of this field. This allows us to reduce the - * extent of the zonelists thus saving space. For example in the case - * of three zone modifier bits, we could require up to eight zonelists. - * If the left most zone modifier is a "loner" then the highest valid - * zonelist would be four allowing us to allocate only five zonelists. - * Use the first form for GFP_ZONETYPES when the left most bit is not - * a "loner", otherwise use the second. - * - * NOTE! Make sure this matches the zones in + * match the requested limits. See gfp_zone() in include/linux/gfp.h */ -#ifdef CONFIG_ZONE_DMA32 - -#ifdef CONFIG_HIGHMEM -#define GFP_ZONETYPES ((GFP_ZONEMASK + 1) / 2 + 1) /* Loner */ -#define GFP_ZONEMASK 0x07 -#define ZONES_SHIFT 2 /* ceil(log2(MAX_NR_ZONES)) */ -#else -#define GFP_ZONETYPES ((0x07 + 1) / 2 + 1) /* Loner */ -/* Mask __GFP_HIGHMEM */ -#define GFP_ZONEMASK 0x05 -#define ZONES_SHIFT 2 -#endif - -#else -#ifdef CONFIG_HIGHMEM - -#define GFP_ZONEMASK 0x03 -#define ZONES_SHIFT 2 -#define GFP_ZONETYPES 3 - +#if !defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_HIGHMEM) +#define ZONES_SHIFT 1 #else - -#define GFP_ZONEMASK 0x01 -#define ZONES_SHIFT 1 -#define GFP_ZONETYPES 2 - -#endif +#define ZONES_SHIFT 2 #endif struct zone { @@ -360,7 +318,7 @@ struct zonelist { struct bootmem_data; typedef struct pglist_data { struct zone node_zones[MAX_NR_ZONES]; - struct zonelist node_zonelists[GFP_ZONETYPES]; + struct zonelist node_zonelists[MAX_NR_ZONES]; int nr_zones; #ifdef CONFIG_FLAT_NODE_MEM_MAP struct page *node_mem_map; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7da4142ce960..c3429a710ab1 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1101,7 +1101,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy) case MPOL_BIND: /* Lower zones don't get a policy applied */ /* Careful: current->mems_allowed might have moved */ - if (highest_zone(gfp) >= policy_zone) + if (gfp_zone(gfp) >= policy_zone) if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist)) return policy->v.zonelist; /*FALL THROUGH*/ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9c44b9a39d30..208a6b03aa78 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1444,14 +1444,14 @@ static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, j, node, local_node; + int j, node, local_node; + enum zone_type i; int prev_node, load; struct zonelist *zonelist; nodemask_t used_mask; - enum zone_type k; /* initialize zonelists */ - for (i = 0; i < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { zonelist = pgdat->node_zonelists + i; zonelist->zones[0] = NULL; } @@ -1481,13 +1481,11 @@ static void __meminit build_zonelists(pg_data_t *pgdat) node_load[node] += load; prev_node = node; load--; - for (i = 0; i < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { zonelist = pgdat->node_zonelists + i; for (j = 0; zonelist->zones[j] != NULL; j++); - k = highest_zone(i); - - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); zonelist->zones[j] = NULL; } } @@ -1497,19 +1495,16 @@ static void __meminit build_zonelists(pg_data_t *pgdat) static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, node, local_node; - enum zone_type k; - enum zone_type j; + int node, local_node; + enum zone_type i,j; local_node = pgdat->node_id; - for (i = 0; i < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { struct zonelist *zonelist; zonelist = pgdat->node_zonelists + i; - j = 0; - k = highest_zone(i); - j = build_zonelists_node(pgdat, zonelist, j, k); + j = build_zonelists_node(pgdat, zonelist, 0, i); /* * Now we build the zonelist so that it contains the zones * of all the other nodes. @@ -1521,12 +1516,12 @@ static void __meminit build_zonelists(pg_data_t *pgdat) for (node = local_node + 1; node < MAX_NUMNODES; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); } for (node = 0; node < local_node; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); } zonelist->zones[j] = NULL; -- cgit From 9b819d204cf602eab1a53a9ec4b8d2ca51e02a1d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:40 -0700 Subject: [PATCH] Add __GFP_THISNODE to avoid fallback to other nodes and ignore cpuset/memory policy restrictions Add a new gfp flag __GFP_THISNODE to avoid fallback to other nodes. This flag is essential if a kernel component requires memory to be located on a certain node. It will be needed for alloc_pages_node() to force allocation on the indicated node and for alloc_pages() to force allocation on the current node. Signed-off-by: Christoph Lameter Cc: Andy Whitcroft Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 3 ++- kernel/cpuset.c | 2 +- mm/mempolicy.c | 2 +- mm/page_alloc.c | 3 +++ 4 files changed, 7 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 63ab88a36f39..0eda5b6dedbd 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -45,6 +45,7 @@ struct vm_area_struct; #define __GFP_ZERO ((__force gfp_t)0x8000u)/* Return zeroed page on success */ #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */ #define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */ +#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */ #define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) @@ -53,7 +54,7 @@ struct vm_area_struct; #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \ __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \ - __GFP_NOMEMALLOC|__GFP_HARDWALL) + __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE) /* This equals 0, but use constants in case they ever change */ #define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4ea6f0dc2fc5..76940361273e 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2316,7 +2316,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) const struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ - if (in_interrupt()) + if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; node = z->zone_pgdat->node_id; might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index c3429a710ab1..8002e1faccda 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1290,7 +1290,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) if ((gfp & __GFP_WAIT) && !in_interrupt()) cpuset_update_task_memory_state(); - if (!pol || in_interrupt()) + if (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; if (pol->policy == MPOL_INTERLEAVE) return alloc_page_interleave(gfp, order, interleave_nodes(pol)); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 208a6b03aa78..ea498788af53 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -893,6 +893,9 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ do { + if (unlikely((gfp_mask & __GFP_THISNODE) && + (*z)->zone_pgdat != zonelist->zones[0]->zone_pgdat)) + break; if ((alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed(*z, gfp_mask)) continue; -- cgit From 1192d526412b1b8ccb1493064cea06efc12c772b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:45 -0700 Subject: [PATCH] Cleanup: Add zone pointer to get_page_from_freelist There are frequent references to *z in get_page_from_freelist. Add an explicit zone variable that can be used in all these places. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ea498788af53..e8a71657ac4a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -887,35 +887,37 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, struct zone **z = zonelist->zones; struct page *page = NULL; int classzone_idx = zone_idx(*z); + struct zone *zone; /* * Go through the zonelist once, looking for a zone with enough free. * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ do { + zone = *z; if (unlikely((gfp_mask & __GFP_THISNODE) && - (*z)->zone_pgdat != zonelist->zones[0]->zone_pgdat)) + zone->zone_pgdat != zonelist->zones[0]->zone_pgdat)) break; if ((alloc_flags & ALLOC_CPUSET) && - !cpuset_zone_allowed(*z, gfp_mask)) + !cpuset_zone_allowed(zone, gfp_mask)) continue; if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { unsigned long mark; if (alloc_flags & ALLOC_WMARK_MIN) - mark = (*z)->pages_min; + mark = zone->pages_min; else if (alloc_flags & ALLOC_WMARK_LOW) - mark = (*z)->pages_low; + mark = zone->pages_low; else - mark = (*z)->pages_high; - if (!zone_watermark_ok(*z, order, mark, + mark = zone->pages_high; + if (!zone_watermark_ok(zone , order, mark, classzone_idx, alloc_flags)) if (!zone_reclaim_mode || - !zone_reclaim(*z, gfp_mask, order)) + !zone_reclaim(zone, gfp_mask, order)) continue; } - page = buffered_rmqueue(zonelist, *z, order, gfp_mask); + page = buffered_rmqueue(zonelist, zone, order, gfp_mask); if (page) { break; } -- cgit From 006d22d9bbb7e66279ba5cc4556b54eeaf8fd556 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:48 -0700 Subject: [PATCH] Optimize free_one_page Free one_page currently adds the page to a fake list and calls free_page_bulk. Fee_page_bulk takes it off again and then calles __free_one_page. Make free_one_page go directly to __free_one_page. Saves list on / off and a temporary list in free_one_page for higher ordered pages. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e8a71657ac4a..cc6483047567 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -448,9 +448,11 @@ static void free_pages_bulk(struct zone *zone, int count, static void free_one_page(struct zone *zone, struct page *page, int order) { - LIST_HEAD(list); - list_add(&page->lru, &list); - free_pages_bulk(zone, 1, &list, order); + spin_lock(&zone->lock); + zone->all_unreclaimable = 0; + zone->pages_scanned = 0; + __free_one_page(page, zone ,order); + spin_unlock(&zone->lock); } static void __free_pages_ok(struct page *page, unsigned int order) -- cgit From 39bbcb8f88154c4ac9853baf3f1134af4c987517 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:49 -0700 Subject: [PATCH] mm: do not check unpopulated zones for draining and counter updates If a zone is unpopulated then we do not need to check for pages that are to be drained and also not for vm counters that may need to be updated. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 5 ++++- mm/vmstat.c | 3 +++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cc6483047567..f7ea020c23ea 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -633,7 +633,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, #ifdef CONFIG_NUMA /* * Called from the slab reaper to drain pagesets on a particular node that - * belong to the currently executing processor. + * belongs to the currently executing processor. * Note that this function must be called with the thread pinned to * a single processor. */ @@ -647,6 +647,9 @@ void drain_node_pages(int nodeid) struct zone *zone = NODE_DATA(nodeid)->node_zones + z; struct per_cpu_pageset *pset; + if (!populated_zone(zone)) + continue; + pset = zone_pcp(zone, smp_processor_id()); for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) { struct per_cpu_pages *pcp; diff --git a/mm/vmstat.c b/mm/vmstat.c index 04a9093f649e..968c0072e19a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -321,6 +321,9 @@ void refresh_cpu_vm_stats(int cpu) for_each_zone(zone) { struct per_cpu_pageset *pcp; + if (!populated_zone(zone)) + continue; + pcp = zone_pcp(zone, cpu); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) -- cgit From 8417bba4b151346ed475fcc923693c9e3be89063 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:51 -0700 Subject: [PATCH] Replace min_unmapped_ratio by min_unmapped_pages in struct zone *_pages is a better description of the role of the variable. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7fe317164b73..a703527e2b45 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -169,7 +169,7 @@ struct zone { /* * zone reclaim becomes active if more unmapped pages exist. */ - unsigned long min_unmapped_ratio; + unsigned long min_unmapped_pages; struct per_cpu_pageset *pageset[NR_CPUS]; #else struct per_cpu_pageset pageset[NR_CPUS]; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f7ea020c23ea..5da6bc4e0a6b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2002,7 +2002,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->spanned_pages = size; zone->present_pages = realsize; #ifdef CONFIG_NUMA - zone->min_unmapped_ratio = (realsize*sysctl_min_unmapped_ratio) + zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) / 100; #endif zone->name = zone_names[j]; @@ -2313,7 +2313,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_unmapped_ratio = (zone->present_pages * + zone->min_unmapped_pages = (zone->present_pages * sysctl_min_unmapped_ratio) / 100; return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 8f35d7d585cb..5154c25e8440 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1618,7 +1618,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * unmapped file backed pages. */ if (zone_page_state(zone, NR_FILE_PAGES) - - zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_ratio) + zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages) return 0; /* -- cgit From 972d1a7b140569084439a81265a0f15b74e924e0 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:51 -0700 Subject: [PATCH] ZVC: Support NR_SLAB_RECLAIMABLE / NR_SLAB_UNRECLAIMABLE Remove the atomic counter for slab_reclaim_pages and replace the counter and NR_SLAB with two ZVC counter that account for unreclaimable and reclaimable slab pages: NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE. Change the check in vmscan.c to refer to to NR_SLAB_RECLAIMABLE. The intend seems to be to check for slab pages that could be freed. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/mm/pgtable.c | 4 +++- drivers/base/node.c | 9 +++++++-- fs/proc/proc_misc.c | 7 ++++++- include/linux/mmzone.h | 3 ++- include/linux/slab.h | 2 -- mm/mmap.c | 2 +- mm/nommu.c | 2 +- mm/page_alloc.c | 3 ++- mm/slab.c | 24 +++++++++++------------- mm/slob.c | 4 ---- mm/vmscan.c | 2 +- mm/vmstat.c | 3 ++- 12 files changed, 36 insertions(+), 29 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c index bd98768d8764..a9f4910a22f8 100644 --- a/arch/i386/mm/pgtable.c +++ b/arch/i386/mm/pgtable.c @@ -60,7 +60,9 @@ void show_mem(void) printk(KERN_INFO "%lu pages writeback\n", global_page_state(NR_WRITEBACK)); printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED)); - printk(KERN_INFO "%lu pages slab\n", global_page_state(NR_SLAB)); + printk(KERN_INFO "%lu pages slab\n", + global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)); printk(KERN_INFO "%lu pages pagetables\n", global_page_state(NR_PAGETABLE)); } diff --git a/drivers/base/node.c b/drivers/base/node.c index e09f5c2c11ee..001e6f6b9c1b 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -68,7 +68,9 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf) "Node %d PageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" - "Node %d Slab: %8lu kB\n", + "Node %d Slab: %8lu kB\n" + "Node %d SReclaimable: %8lu kB\n" + "Node %d SUnreclaim: %8lu kB\n", nid, K(i.totalram), nid, K(i.freeram), nid, K(i.totalram - i.freeram), @@ -88,7 +90,10 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf) nid, K(node_page_state(nid, NR_PAGETABLE)), nid, K(node_page_state(nid, NR_UNSTABLE_NFS)), nid, K(node_page_state(nid, NR_BOUNCE)), - nid, K(node_page_state(nid, NR_SLAB))); + nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) + + node_page_state(nid, NR_SLAB_UNRECLAIMABLE)), + nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)), + nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))); n += hugetlb_report_node_meminfo(nid, buf + n); return n; } diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index caa0a51560a0..5bbd60896050 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -170,6 +170,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off, "AnonPages: %8lu kB\n" "Mapped: %8lu kB\n" "Slab: %8lu kB\n" + "SReclaimable: %8lu kB\n" + "SUnreclaim: %8lu kB\n" "PageTables: %8lu kB\n" "NFS_Unstable: %8lu kB\n" "Bounce: %8lu kB\n" @@ -197,7 +199,10 @@ static int meminfo_read_proc(char *page, char **start, off_t off, K(global_page_state(NR_WRITEBACK)), K(global_page_state(NR_ANON_PAGES)), K(global_page_state(NR_FILE_MAPPED)), - K(global_page_state(NR_SLAB)), + K(global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)), + K(global_page_state(NR_SLAB_RECLAIMABLE)), + K(global_page_state(NR_SLAB_UNRECLAIMABLE)), K(global_page_state(NR_PAGETABLE)), K(global_page_state(NR_UNSTABLE_NFS)), K(global_page_state(NR_BOUNCE)), diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a703527e2b45..08c41b9f92e0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -51,7 +51,8 @@ enum zone_stat_item { NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, - NR_SLAB, /* Pages used by slab allocator */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_FILE_DIRTY, NR_WRITEBACK, diff --git a/include/linux/slab.h b/include/linux/slab.h index 2f6bef6a98c9..66d6eb78d1c6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -284,8 +284,6 @@ extern kmem_cache_t *fs_cachep; extern kmem_cache_t *sighand_cachep; extern kmem_cache_t *bio_cachep; -extern atomic_t slab_reclaim_pages; - #endif /* __KERNEL__ */ #endif /* _LINUX_SLAB_H */ diff --git a/mm/mmap.c b/mm/mmap.c index 8507ee9cd573..eea8eefd51a8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -116,7 +116,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin) * which are reclaimable, under pressure. The dentry * cache and most inode caches should fall into this */ - free += atomic_read(&slab_reclaim_pages); + free += global_page_state(NR_SLAB_RECLAIMABLE); /* * Leave the last 3% for root diff --git a/mm/nommu.c b/mm/nommu.c index c576df71e3bb..d99dea31e443 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1133,7 +1133,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin) * which are reclaimable, under pressure. The dentry * cache and most inode caches should fall into this */ - free += atomic_read(&slab_reclaim_pages); + free += global_page_state(NR_SLAB_RECLAIMABLE); /* * Leave the last 3% for root diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5da6bc4e0a6b..47e98423b30d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1304,7 +1304,8 @@ void show_free_areas(void) global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), nr_free_pages(), - global_page_state(NR_SLAB), + global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE), global_page_state(NR_FILE_MAPPED), global_page_state(NR_PAGETABLE)); diff --git a/mm/slab.c b/mm/slab.c index 13b5050f84cc..7a48eb1a60c8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -735,14 +735,6 @@ static inline void init_lock_keys(void) static DEFINE_MUTEX(cache_chain_mutex); static struct list_head cache_chain; -/* - * vm_enough_memory() looks at this to determine how many slab-allocated pages - * are possibly freeable under pressure - * - * SLAB_RECLAIM_ACCOUNT turns this on per-slab - */ -atomic_t slab_reclaim_pages; - /* * chicken and egg problem: delay the per-cpu array allocation * until the general caches are up. @@ -1580,8 +1572,11 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_add(nr_pages, &slab_reclaim_pages); - add_zone_page_state(page_zone(page), NR_SLAB, nr_pages); + add_zone_page_state(page_zone(page), + NR_SLAB_RECLAIMABLE, nr_pages); + else + add_zone_page_state(page_zone(page), + NR_SLAB_UNRECLAIMABLE, nr_pages); for (i = 0; i < nr_pages; i++) __SetPageSlab(page + i); return page_address(page); @@ -1596,7 +1591,12 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) struct page *page = virt_to_page(addr); const unsigned long nr_freed = i; - sub_zone_page_state(page_zone(page), NR_SLAB, nr_freed); + if (cachep->flags & SLAB_RECLAIM_ACCOUNT) + sub_zone_page_state(page_zone(page), + NR_SLAB_RECLAIMABLE, nr_freed); + else + sub_zone_page_state(page_zone(page), + NR_SLAB_UNRECLAIMABLE, nr_freed); while (i--) { BUG_ON(!PageSlab(page)); __ClearPageSlab(page); @@ -1605,8 +1605,6 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; free_pages((unsigned long)addr, cachep->gfporder); - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_sub(1 << cachep->gfporder, &slab_reclaim_pages); } static void kmem_rcu_free(struct rcu_head *head) diff --git a/mm/slob.c b/mm/slob.c index 4c28a421b270..20188627347c 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -339,7 +339,3 @@ void kmem_cache_init(void) mod_timer(&slob_timer, jiffies + HZ); } - -atomic_t slab_reclaim_pages = ATOMIC_INIT(0); -EXPORT_SYMBOL(slab_reclaim_pages); - diff --git a/mm/vmscan.c b/mm/vmscan.c index 5154c25e8440..349797ba4bac 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1378,7 +1378,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) for_each_zone(zone) lru_pages += zone->nr_active + zone->nr_inactive; - nr_slab = global_page_state(NR_SLAB); + nr_slab = global_page_state(NR_SLAB_RECLAIMABLE); /* If slab caches are huge, it's better to hit them first */ while (nr_slab >= lru_pages) { reclaim_state.reclaimed_slab = 0; diff --git a/mm/vmstat.c b/mm/vmstat.c index 968c0072e19a..490d8c1a0ded 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -458,7 +458,8 @@ static char *vmstat_text[] = { "nr_anon_pages", "nr_mapped", "nr_file_pages", - "nr_slab", + "nr_slab_reclaimable", + "nr_slab_unreclaimable", "nr_page_table_pages", "nr_dirty", "nr_writeback", -- cgit From 0ff38490c836dc379ff7ec45b10a15a662f4e5f6 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:52 -0700 Subject: [PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 27 +++++++++++++++------ include/linux/mmzone.h | 3 +++ include/linux/swap.h | 1 + include/linux/sysctl.h | 1 + kernel/sysctl.c | 11 +++++++++ mm/page_alloc.c | 17 +++++++++++++ mm/vmscan.c | 58 +++++++++++++++++++++++++++++---------------- 7 files changed, 90 insertions(+), 28 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 7cee90223d3a..20d0d797f539 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -29,6 +29,7 @@ Currently, these files are in /proc/sys/vm: - drop-caches - zone_reclaim_mode - min_unmapped_ratio +- min_slab_ratio - panic_on_oom ============================================================== @@ -138,7 +139,6 @@ This is value ORed together of 1 = Zone reclaim on 2 = Zone reclaim writes dirty pages out 4 = Zone reclaim swaps pages -8 = Also do a global slab reclaim pass zone_reclaim_mode is set during bootup to 1 if it is determined that pages from remote zones will cause a measurable performance reduction. The @@ -162,18 +162,13 @@ Allowing regular swap effectively restricts allocations to the local node unless explicitly overridden by memory policies or cpuset configurations. -It may be advisable to allow slab reclaim if the system makes heavy -use of files and builds up large slab caches. However, the slab -shrink operation is global, may take a long time and free slabs -in all nodes of the system. - ============================================================= min_unmapped_ratio: This is available only on NUMA kernels. -A percentage of the file backed pages in each zone. Zone reclaim will only +A percentage of the total pages in each zone. Zone reclaim will only occur if more than this percentage of pages are file backed and unmapped. This is to insure that a minimal amount of local pages is still available for file I/O even if the node is overallocated. @@ -182,6 +177,24 @@ The default is 1 percent. ============================================================= +min_slab_ratio: + +This is available only on NUMA kernels. + +A percentage of the total pages in each zone. On Zone reclaim +(fallback from the local zone occurs) slabs will be reclaimed if more +than this percentage of pages in a zone are reclaimable slab pages. +This insures that the slab growth stays under control even in NUMA +systems that rarely perform global reclaim. + +The default is 5 percent. + +Note that slab reclaim is triggered in a per zone / node fashion. +The process of reclaiming slab memory is currently not node specific +and may not be fast. + +============================================================= + panic_on_oom This enables or disables panic on out-of-memory feature. If this is set to 1, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 08c41b9f92e0..3693f1a52788 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -171,6 +171,7 @@ struct zone { * zone reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; + unsigned long min_slab_pages; struct per_cpu_pageset *pageset[NR_CPUS]; #else struct per_cpu_pageset pageset[NR_CPUS]; @@ -448,6 +449,8 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file void __user *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, + struct file *, void __user *, size_t *, loff_t *); #include /* Returns the number of the current Node. */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 32db06c8ffe0..a2f5ad7c2d2e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -193,6 +193,7 @@ extern long vm_total_pages; #ifdef CONFIG_NUMA extern int zone_reclaim_mode; extern int sysctl_min_unmapped_ratio; +extern int sysctl_min_slab_ratio; extern int zone_reclaim(struct zone *, gfp_t, unsigned int); #else #define zone_reclaim_mode 0 diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 736ed917a4f8..eca555781d05 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -191,6 +191,7 @@ enum VM_MIN_UNMAPPED=32, /* Set min percent of unmapped pages */ VM_PANIC_ON_OOM=33, /* panic at out-of-memory */ VM_VDSO_ENABLED=34, /* map VDSO into new processes? */ + VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */ }; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 362a0cc37138..fd43c3e6786b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -943,6 +943,17 @@ static ctl_table vm_table[] = { .extra1 = &zero, .extra2 = &one_hundred, }, + { + .ctl_name = VM_MIN_SLAB, + .procname = "min_slab_ratio", + .data = &sysctl_min_slab_ratio, + .maxlen = sizeof(sysctl_min_slab_ratio), + .mode = 0644, + .proc_handler = &sysctl_min_slab_ratio_sysctl_handler, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, #endif #ifdef CONFIG_X86_32 { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 47e98423b30d..cf913bdd433e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2005,6 +2005,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, #ifdef CONFIG_NUMA zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) / 100; + zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; spin_lock_init(&zone->lock); @@ -2318,6 +2319,22 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, sysctl_min_unmapped_ratio) / 100; return 0; } + +int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) +{ + struct zone *zone; + int rc; + + rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + if (rc) + return rc; + + for_each_zone(zone) + zone->min_slab_pages = (zone->present_pages * + sysctl_min_slab_ratio) / 100; + return 0; +} #endif /* diff --git a/mm/vmscan.c b/mm/vmscan.c index 349797ba4bac..089e943c4d38 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1527,7 +1527,6 @@ int zone_reclaim_mode __read_mostly; #define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ #define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */ -#define RECLAIM_SLAB (1<<3) /* Do a global slab shrink if the zone is out of memory */ /* * Priority for ZONE_RECLAIM. This determines the fraction of pages @@ -1542,6 +1541,12 @@ int zone_reclaim_mode __read_mostly; */ int sysctl_min_unmapped_ratio = 1; +/* + * If the number of slab pages in a zone grows beyond this percentage then + * slab reclaim needs to occur. + */ +int sysctl_min_slab_ratio = 5; + /* * Try to free up some pages from this zone through reclaim. */ @@ -1573,29 +1578,37 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - /* - * Free memory by calling shrink zone with increasing priorities - * until we have enough memory freed. - */ - priority = ZONE_RECLAIM_PRIORITY; - do { - nr_reclaimed += shrink_zone(priority, zone, &sc); - priority--; - } while (priority >= 0 && nr_reclaimed < nr_pages); + if (zone_page_state(zone, NR_FILE_PAGES) - + zone_page_state(zone, NR_FILE_MAPPED) > + zone->min_unmapped_pages) { + /* + * Free memory by calling shrink zone with increasing + * priorities until we have enough memory freed. + */ + priority = ZONE_RECLAIM_PRIORITY; + do { + nr_reclaimed += shrink_zone(priority, zone, &sc); + priority--; + } while (priority >= 0 && nr_reclaimed < nr_pages); + } - if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) { + if (zone_page_state(zone, NR_SLAB_RECLAIMABLE) > zone->min_slab_pages) { /* * shrink_slab() does not currently allow us to determine how - * many pages were freed in this zone. So we just shake the slab - * a bit and then go off node for this particular allocation - * despite possibly having freed enough memory to allocate in - * this zone. If we freed local memory then the next - * allocations will be local again. + * many pages were freed in this zone. So we take the current + * number of slab pages and shake the slab until it is reduced + * by the same nr_pages that we used for reclaiming unmapped + * pages. * - * shrink_slab will free memory on all zones and may take - * a long time. + * Note that shrink_slab will free memory on all zones and may + * take a long time. */ - shrink_slab(sc.nr_scanned, gfp_mask, order); + unsigned long limit = zone_page_state(zone, + NR_SLAB_RECLAIMABLE) - nr_pages; + + while (shrink_slab(sc.nr_scanned, gfp_mask, order) && + zone_page_state(zone, NR_SLAB_RECLAIMABLE) > limit) + ; } p->reclaim_state = NULL; @@ -1609,7 +1622,8 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) int node_id; /* - * Zone reclaim reclaims unmapped file backed pages. + * Zone reclaim reclaims unmapped file backed pages and + * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately @@ -1618,7 +1632,9 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * unmapped file backed pages. */ if (zone_page_state(zone, NR_FILE_PAGES) - - zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages) + zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages + && zone_page_state(zone, NR_SLAB_RECLAIMABLE) + <= zone->min_slab_pages) return 0; /* -- cgit From 89fa30242facca249aead2aac03c4c69764f911c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:55 -0700 Subject: [PATCH] NUMA: Add zone_to_nid function There are many places where we need to determine the node of a zone. Currently we use a difficult to read sequence of pointer dereferencing. Put that into an inline function and use throughout VM. Maybe we can find a way to optimize the lookup in the future. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/mm/discontig.c | 2 +- arch/parisc/mm/init.c | 2 +- include/linux/mm.h | 7 ++++++- kernel/cpuset.c | 4 ++-- mm/hugetlb.c | 2 +- mm/mempolicy.c | 6 +++--- mm/oom_kill.c | 3 +-- mm/page_alloc.c | 2 +- mm/vmscan.c | 2 +- 9 files changed, 17 insertions(+), 13 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 07c300f93764..fb5d8b747de4 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -422,7 +422,7 @@ void __init set_highmem_pages_init(int bad_ppro) zone_end_pfn = zone_start_pfn + zone->spanned_pages; printk("Initializing %s for node %d (%08lx:%08lx)\n", - zone->name, zone->zone_pgdat->node_id, + zone->name, zone_to_nid(zone), zone_start_pfn, zone_end_pfn); for (node_pfn = zone_start_pfn; node_pfn < zone_end_pfn; node_pfn++) { diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index c7329615ef94..25ad28d63e88 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -551,7 +551,7 @@ void show_mem(void) printk("Zone list for zone %d on node %d: ", j, i); for (k = 0; zl->zones[k] != NULL; k++) - printk("[%d/%s] ", zl->zones[k]->zone_pgdat->node_id, zl->zones[k]->name); + printk("[%d/%s] ", zone_to_nid(zl->zones[k]), zl->zones[k]->name); printk("\n"); } } diff --git a/include/linux/mm.h b/include/linux/mm.h index f2018775b995..856f0ee7e84a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -499,12 +499,17 @@ static inline struct zone *page_zone(struct page *page) return zone_table[page_zone_id(page)]; } +static inline unsigned long zone_to_nid(struct zone *zone) +{ + return zone->zone_pgdat->node_id; +} + static inline unsigned long page_to_nid(struct page *page) { if (FLAGS_HAS_NODE) return (page->flags >> NODES_PGSHIFT) & NODES_MASK; else - return page_zone(page)->zone_pgdat->node_id; + return zone_to_nid(page_zone(page)); } static inline unsigned long page_to_section(struct page *page) { diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 76940361273e..cff41511269f 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2245,7 +2245,7 @@ int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) int i; for (i = 0; zl->zones[i]; i++) { - int nid = zl->zones[i]->zone_pgdat->node_id; + int nid = zone_to_nid(zl->zones[i]); if (node_isset(nid, current->mems_allowed)) return 1; @@ -2318,7 +2318,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; - node = z->zone_pgdat->node_id; + node = zone_to_nid(z); might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); if (node_isset(node, current->mems_allowed)) return 1; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3aceadce1a76..7c7d03dbf73d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -72,7 +72,7 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma, struct zone **z; for (z = zonelist->zones; *z; z++) { - nid = (*z)->zone_pgdat->node_id; + nid = zone_to_nid(*z); if (cpuset_zone_allowed(*z, GFP_HIGHUSER) && !list_empty(&hugepage_freelists[nid])) break; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8002e1faccda..38f89650bc84 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -487,7 +487,7 @@ static void get_zonemask(struct mempolicy *p, nodemask_t *nodes) switch (p->policy) { case MPOL_BIND: for (i = 0; p->v.zonelist->zones[i]; i++) - node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id, + node_set(zone_to_nid(p->v.zonelist->zones[i]), *nodes); break; case MPOL_DEFAULT: @@ -1145,7 +1145,7 @@ unsigned slab_node(struct mempolicy *policy) * Follow bind policy behavior and start allocation at the * first node. */ - return policy->v.zonelist->zones[0]->zone_pgdat->node_id; + return zone_to_nid(policy->v.zonelist->zones[0]); case MPOL_PREFERRED: if (policy->v.preferred_node >= 0) @@ -1649,7 +1649,7 @@ void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) nodes_clear(nodes); for (z = pol->v.zonelist->zones; *z; z++) - node_set((*z)->zone_pgdat->node_id, nodes); + node_set(zone_to_nid(*z), nodes); nodes_remap(tmp, nodes, *mpolmask, *newmask); nodes = tmp; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f1c0ef1fd21f..bada3d03119f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -177,8 +177,7 @@ static inline int constrained_alloc(struct zonelist *zonelist, gfp_t gfp_mask) for (z = zonelist->zones; *z; z++) if (cpuset_zone_allowed(*z, gfp_mask)) - node_clear((*z)->zone_pgdat->node_id, - nodes); + node_clear(zone_to_nid(*z), nodes); else return CONSTRAINT_CPUSET; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cf913bdd433e..51070b6d593f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1217,7 +1217,7 @@ unsigned int nr_free_pagecache_pages(void) #ifdef CONFIG_NUMA static void show_node(struct zone *zone) { - printk("Node %d ", zone->zone_pgdat->node_id); + printk("Node %ld ", zone_to_nid(zone)); } #else #define show_node(zone) do { } while (0) diff --git a/mm/vmscan.c b/mm/vmscan.c index b950f193816e..87779dda4ec6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1661,7 +1661,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * over remote processors and spread off node memory allocations * as wide as possible. */ - node_id = zone->zone_pgdat->node_id; + node_id = zone_to_nid(zone); mask = node_to_cpumask(node_id); if (!cpus_empty(mask) && node_id != numa_node_id()) return 0; -- cgit From f623f0db8e6aa86a37be86167e4ff478821a9f4f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 25 Sep 2006 23:32:49 -0700 Subject: [PATCH] swsusp: Fix mark_free_pages Clean up mm/page_alloc.c#mark_free_pages() and make it avoid clearing PageNosaveFree for PageNosave pages. This allows us to get rid of an ugly hack in kernel/power/snapshot.c#copy_data_pages(). Additionally, the page-copying loop in copy_data_pages() is moved to an inline function. Signed-off-by: Rafael J. Wysocki Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/snapshot.c | 27 +++++++++++++-------------- mm/page_alloc.c | 24 ++++++++++++++++-------- 2 files changed, 29 insertions(+), 22 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 81fe8de9e604..4afb7900002b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -208,37 +208,36 @@ unsigned int count_data_pages(void) return n; } +static inline void copy_data_page(long *dst, long *src) +{ + int n; + + /* copy_page and memcpy are not usable for copying task structs. */ + for (n = PAGE_SIZE / sizeof(long); n; n--) + *dst++ = *src++; +} + static void copy_data_pages(struct pbe *pblist) { struct zone *zone; unsigned long pfn, max_zone_pfn; - struct pbe *pbe, *p; + struct pbe *pbe; pbe = pblist; for_each_zone (zone) { if (is_highmem(zone)) continue; mark_free_pages(zone); - /* This is necessary for swsusp_free() */ - for_each_pb_page (p, pblist) - SetPageNosaveFree(virt_to_page(p)); - for_each_pbe (p, pblist) - SetPageNosaveFree(virt_to_page(p->address)); max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { struct page *page = saveable_page(pfn); if (page) { - long *src, *dst; - int n; + void *ptr = page_address(page); BUG_ON(!pbe); - pbe->orig_address = (unsigned long)page_address(page); - /* copy_page and memcpy are not usable for copying task structs. */ - dst = (long *)pbe->address; - src = (long *)pbe->orig_address; - for (n = PAGE_SIZE / sizeof(long); n; n--) - *dst++ = *src++; + copy_data_page((void *)pbe->address, ptr); + pbe->orig_address = (unsigned long)ptr; pbe = pbe->next; } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 51070b6d593f..9810f0a60db7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -694,7 +694,8 @@ static void __drain_pages(unsigned int cpu) void mark_free_pages(struct zone *zone) { - unsigned long zone_pfn, flags; + unsigned long pfn, max_zone_pfn; + unsigned long flags; int order; struct list_head *curr; @@ -702,18 +703,25 @@ void mark_free_pages(struct zone *zone) return; spin_lock_irqsave(&zone->lock, flags); - for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) - ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn)); + + max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (pfn_valid(pfn)) { + struct page *page = pfn_to_page(pfn); + + if (!PageNosave(page)) + ClearPageNosaveFree(page); + } for (order = MAX_ORDER - 1; order >= 0; --order) list_for_each(curr, &zone->free_area[order].free_list) { - unsigned long start_pfn, i; + unsigned long i; - start_pfn = page_to_pfn(list_entry(curr, struct page, lru)); + pfn = page_to_pfn(list_entry(curr, struct page, lru)); + for (i = 0; i < (1UL << order); i++) + SetPageNosaveFree(pfn_to_page(pfn + i)); + } - for (i=0; i < (1<lock, flags); } -- cgit From c713216deebd95d2b0ab38fef8bb2361c0180c2d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:43 -0700 Subject: [PATCH] Introduce mechanism for registering active regions of memory At a basic level, architectures define structures to record where active ranges of page frames are located. Once located, the code to calculate zone sizes and holes in each architecture is very similar. Some of this zone and hole sizing code is difficult to read for no good reason. This set of patches eliminates the similar-looking architecture-specific code. The patches introduce a mechanism where architectures register where the active ranges of page frames are with add_active_range(). When all areas have been discovered, free_area_init_nodes() is called to initialise the pgdat and zones. The zone sizes and holes are then calculated in an architecture independent manner. Patch 1 introduces the mechanism for registering and initialising PFN ranges Patch 2 changes ppc to use the mechanism - 139 arch-specific LOC removed Patch 3 changes x86 to use the mechanism - 136 arch-specific LOC removed Patch 4 changes x86_64 to use the mechanism - 74 arch-specific LOC removed Patch 5 changes ia64 to use the mechanism - 52 arch-specific LOC removed Patch 6 accounts for mem_map as a memory hole as the pages are not reclaimable. It adjusts the watermarks slightly Tony Luck has successfully tested for ia64 on Itanium with tiger_defconfig, gensparse_defconfig and defconfig. Bob Picco has also tested and debugged on IA64. Jack Steiner successfully boot tested on a mammoth SGI IA64-based machine. These were on patches against 2.6.17-rc1 and release 3 of these patches but there have been no ia64-changes since release 3. There are differences in the zone sizes for x86_64 as the arch-specific code for x86_64 accounts the kernel image and the starting mem_maps as memory holes but the architecture-independent code accounts the memory as present. The big benefit of this set of patches is a sizable reduction of architecture-specific code, some of which is very hairy. There should be a greater reduction when other architectures use the same mechanisms for zone and hole sizing but I lack the hardware to test on. Additional credit; Dave Hansen for the initial suggestion and comments on early patches Andy Whitcroft for reviewing early versions and catching numerous errors Tony Luck for testing and debugging on IA64 Bob Picco for fixing bugs related to pfn registration, reviewing a number of patch revisions, providing a number of suggestions on future direction and testing heavily Jack Steiner and Robin Holt for testing on IA64 and clarifying issues related to memory holes Yasunori for testing on IA64 Andi Kleen for reviewing and feeding back about x86_64 Christian Kujau for providing valuable information related to ACPI problems on x86_64 and testing potential fixes This patch: Define the structure to represent an active range of page frames within a node in an architecture independent manner. Architectures are expected to register active ranges of PFNs using add_active_range(nid, start_pfn, end_pfn) and call free_area_init_nodes() passing the PFNs of the end of each zone. Signed-off-by: Mel Gorman Signed-off-by: Bob Picco Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 47 +++++ include/linux/mmzone.h | 10 +- mm/page_alloc.c | 552 ++++++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 584 insertions(+), 25 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 856f0ee7e84a..c0402da7cce0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -937,6 +937,53 @@ extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, pg_data_t *pgdat, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/* + * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its + * zones, allocate the backing mem_map and account for memory holes in a more + * architecture independent manner. This is a substitute for creating the + * zone_sizes[] and zholes_size[] arrays and passing them to + * free_area_init_node() + * + * An architecture is expected to register range of page frames backed by + * physical memory with add_active_range() before calling + * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * usage, an architecture is expected to do something like + * + * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, + * max_highmem_pfn}; + * for_each_valid_physical_page_range() + * add_active_range(node_id, start_pfn, end_pfn) + * free_area_init_nodes(max_zone_pfns); + * + * If the architecture guarantees that there are no holes in the ranges + * registered with add_active_range(), free_bootmem_active_regions() + * will call free_bootmem_node() for each registered physical page range. + * Similarly sparse_memory_present_with_active_regions() calls + * memory_present() for each range when SPARSEMEM is enabled. + * + * See mm/page_alloc.c for more information on each function exposed by + * CONFIG_ARCH_POPULATES_NODE_MAP + */ +extern void free_area_init_nodes(unsigned long *max_zone_pfn); +extern void add_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn); +extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn, + unsigned long new_end_pfn); +extern void remove_all_active_ranges(void); +extern unsigned long absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn); +extern void get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn); +extern unsigned long find_min_pfn_with_active_regions(void); +extern unsigned long find_max_pfn_with_active_regions(void); +extern void free_bootmem_with_active_regions(int nid, + unsigned long max_low_pfn); +extern void sparse_memory_present_with_active_regions(int nid); +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +extern int early_pfn_to_nid(unsigned long pfn); +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long); extern void setup_per_zone_pages_min(void); extern void mem_init(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3693f1a52788..7fa1cbe9fa7a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -305,6 +305,13 @@ struct zonelist { struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited }; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +struct node_active_region { + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +}; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ /* * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM @@ -518,7 +525,8 @@ extern struct zone *next_zone(struct zone *zone); #endif -#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ + !defined(CONFIG_ARCH_POPULATES_NODE_MAP) #define early_pfn_to_nid(nid) (0UL) #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9810f0a60db7..26c9939857fa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -37,6 +37,8 @@ #include #include #include +#include +#include #include #include @@ -103,6 +105,33 @@ int min_free_kbytes = 1024; unsigned long __meminitdata nr_kernel_pages; unsigned long __meminitdata nr_all_pages; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + /* + * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct + * ranges of memory (RAM) that may be registered with add_active_range(). + * Ranges passed to add_active_range() will be merged if possible + * so the number of times add_active_range() can be called is + * related to the number of nodes and the number of holes + */ + #ifdef CONFIG_MAX_ACTIVE_REGIONS + /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ + #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS + #else + #if MAX_NUMNODES >= 32 + /* If there can be many nodes, allow up to 50 holes per node */ + #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) + #else + /* By default, allow up to 256 distinct regions */ + #define MAX_ACTIVE_REGIONS 256 + #endif + #endif + + struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS]; + int __initdata nr_nodemap_entries; + unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; + unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { @@ -1642,25 +1671,6 @@ static inline unsigned long wait_table_bits(unsigned long size) #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) -static void __init calculate_zone_totalpages(struct pglist_data *pgdat, - unsigned long *zones_size, unsigned long *zholes_size) -{ - unsigned long realtotalpages, totalpages = 0; - enum zone_type i; - - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zones_size[i]; - pgdat->node_spanned_pages = totalpages; - - realtotalpages = totalpages; - if (zholes_size) - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= zholes_size[i]; - pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); -} - - /* * Initially all pages are reserved - free ones are freed * up by free_all_bootmem() once the early boot process is @@ -1977,6 +1987,272 @@ __meminit int init_currently_empty_zone(struct zone *zone, return 0; } +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/* + * Basic iterator support. Return the first range of PFNs for a node + * Note: nid == MAX_NUMNODES returns first region regardless of node + */ +static int __init first_active_region_index_in_nid(int nid) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) + if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) + return i; + + return -1; +} + +/* + * Basic iterator support. Return the next active range of PFNs for a node + * Note: nid == MAX_NUMNODES returns next region regardles of node + */ +static int __init next_active_region_index_in_nid(int index, int nid) +{ + for (index = index + 1; index < nr_nodemap_entries; index++) + if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) + return index; + + return -1; +} + +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + * Architectures may implement their own version but if add_active_range() + * was used and there are no special requirements, this is a convenient + * alternative + */ +int __init early_pfn_to_nid(unsigned long pfn) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) { + unsigned long start_pfn = early_node_map[i].start_pfn; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (start_pfn <= pfn && pfn < end_pfn) + return early_node_map[i].nid; + } + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +/* Basic iterator support to walk early_node_map[] */ +#define for_each_active_range_index_in_nid(i, nid) \ + for (i = first_active_region_index_in_nid(nid); i != -1; \ + i = next_active_region_index_in_nid(i, nid)) + +/** + * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed + * @max_low_pfn: The highest PFN that till be passed to free_bootmem_node + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * this function may be used instead of calling free_bootmem() manually. + */ +void __init free_bootmem_with_active_regions(int nid, + unsigned long max_low_pfn) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) { + unsigned long size_pages = 0; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (early_node_map[i].start_pfn >= max_low_pfn) + continue; + + if (end_pfn > max_low_pfn) + end_pfn = max_low_pfn; + + size_pages = end_pfn - early_node_map[i].start_pfn; + free_bootmem_node(NODE_DATA(early_node_map[i].nid), + PFN_PHYS(early_node_map[i].start_pfn), + size_pages << PAGE_SHIFT); + } +} + +/** + * sparse_memory_present_with_active_regions - Call memory_present for each active range + * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * this function may be used instead of calling memory_present() manually. + */ +void __init sparse_memory_present_with_active_regions(int nid) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) + memory_present(early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); +} + +/** + * get_pfn_range_for_nid - Return the start and end page frames for a node + * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned + * @start_pfn: Passed by reference. On return, it will have the node start_pfn + * @end_pfn: Passed by reference. On return, it will have the node end_pfn + * + * It returns the start and end page frame of a node based on information + * provided by an arch calling add_active_range(). If called for a node + * with no available memory, a warning is printed and the start and end + * PFNs will be 0 + */ +void __init get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + int i; + *start_pfn = -1UL; + *end_pfn = 0; + + for_each_active_range_index_in_nid(i, nid) { + *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); + *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + } + + if (*start_pfn == -1UL) { + printk(KERN_WARNING "Node %u active with no memory\n", nid); + *start_pfn = 0; + } +} + +/* + * Return the number of pages a zone spans in a node, including holes + * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() + */ +unsigned long __init zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + /* Get the start and end of the node and zone */ + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; + zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; + + /* Check that this node has pages within the zone's required range */ + if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn) + return 0; + + /* Move the zone boundaries inside the node if necessary */ + zone_end_pfn = min(zone_end_pfn, node_end_pfn); + zone_start_pfn = max(zone_start_pfn, node_start_pfn); + + /* Return the spanned pages */ + return zone_end_pfn - zone_start_pfn; +} + +/* + * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, + * then all holes in the requested range will be accounted for + */ +unsigned long __init __absent_pages_in_range(int nid, + unsigned long range_start_pfn, + unsigned long range_end_pfn) +{ + int i = 0; + unsigned long prev_end_pfn = 0, hole_pages = 0; + unsigned long start_pfn; + + /* Find the end_pfn of the first active range of pfns in the node */ + i = first_active_region_index_in_nid(nid); + if (i == -1) + return 0; + + prev_end_pfn = early_node_map[i].start_pfn; + + /* Find all holes for the zone within the node */ + for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { + + /* No need to continue if prev_end_pfn is outside the zone */ + if (prev_end_pfn >= range_end_pfn) + break; + + /* Make sure the end of the zone is not within the hole */ + start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); + prev_end_pfn = max(prev_end_pfn, range_start_pfn); + + /* Update the hole size cound and move on */ + if (start_pfn > range_start_pfn) { + BUG_ON(prev_end_pfn > start_pfn); + hole_pages += start_pfn - prev_end_pfn; + } + prev_end_pfn = early_node_map[i].end_pfn; + } + + return hole_pages; +} + +/** + * absent_pages_in_range - Return number of page frames in holes within a range + * @start_pfn: The start PFN to start searching for holes + * @end_pfn: The end PFN to stop searching for holes + * + * It returns the number of pages frames in memory holes within a range + */ +unsigned long __init absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn) +{ + return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); +} + +/* Return the number of page frames in holes in a zone on a node */ +unsigned long __init zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + return __absent_pages_in_range(nid, + arch_zone_lowest_possible_pfn[zone_type], + arch_zone_highest_possible_pfn[zone_type]); +} +#else +static inline unsigned long zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zones_size) +{ + return zones_size[zone_type]; +} + +static inline unsigned long zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zholes_size) +{ + if (!zholes_size) + return 0; + + return zholes_size[zone_type]; +} +#endif + +static void __init calculate_node_totalpages(struct pglist_data *pgdat, + unsigned long *zones_size, unsigned long *zholes_size) +{ + unsigned long realtotalpages, totalpages = 0; + enum zone_type i; + + for (i = 0; i < MAX_NR_ZONES; i++) + totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, + zones_size); + pgdat->node_spanned_pages = totalpages; + + realtotalpages = totalpages; + for (i = 0; i < MAX_NR_ZONES; i++) + realtotalpages -= + zone_absent_pages_in_node(pgdat->node_id, i, + zholes_size); + pgdat->node_present_pages = realtotalpages; + printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, + realtotalpages); +} + /* * Set up the zone data structures: * - mark all pages reserved @@ -2000,9 +2276,9 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize; - realsize = size = zones_size[j]; - if (zholes_size) - realsize -= zholes_size[j]; + size = zone_spanned_pages_in_node(nid, j, zones_size); + realsize = size - zone_absent_pages_in_node(nid, j, + zholes_size); if (!is_highmem_idx(j)) nr_kernel_pages += realsize; @@ -2073,8 +2349,13 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) /* * With no DISCONTIG, the global mem_map is just set as node 0's */ - if (pgdat == NODE_DATA(0)) + if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + if (page_to_pfn(mem_map) != pgdat->node_start_pfn) + mem_map -= pgdat->node_start_pfn; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + } #endif #endif /* CONFIG_FLAT_NODE_MEM_MAP */ } @@ -2085,13 +2366,236 @@ void __meminit free_area_init_node(int nid, struct pglist_data *pgdat, { pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - calculate_zone_totalpages(pgdat, zones_size, zholes_size); + calculate_node_totalpages(pgdat, zones_size, zholes_size); alloc_node_mem_map(pgdat); free_area_init_core(pgdat, zones_size, zholes_size); } +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/** + * add_active_range - Register a range of PFNs backed by physical memory + * @nid: The node ID the range resides on + * @start_pfn: The start PFN of the available physical memory + * @end_pfn: The end PFN of the available physical memory + * + * These ranges are stored in an early_node_map[] and later used by + * free_area_init_nodes() to calculate zone sizes and holes. If the + * range spans a memory hole, it is up to the architecture to ensure + * the memory is not freed by the bootmem allocator. If possible + * the range being registered will be merged with existing ranges. + */ +void __init add_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn) +{ + int i; + + printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) " + "%d entries of %d used\n", + nid, start_pfn, end_pfn, + nr_nodemap_entries, MAX_ACTIVE_REGIONS); + + /* Merge with existing active regions if possible */ + for (i = 0; i < nr_nodemap_entries; i++) { + if (early_node_map[i].nid != nid) + continue; + + /* Skip if an existing region covers this new one */ + if (start_pfn >= early_node_map[i].start_pfn && + end_pfn <= early_node_map[i].end_pfn) + return; + + /* Merge forward if suitable */ + if (start_pfn <= early_node_map[i].end_pfn && + end_pfn > early_node_map[i].end_pfn) { + early_node_map[i].end_pfn = end_pfn; + return; + } + + /* Merge backward if suitable */ + if (start_pfn < early_node_map[i].end_pfn && + end_pfn >= early_node_map[i].start_pfn) { + early_node_map[i].start_pfn = start_pfn; + return; + } + } + + /* Check that early_node_map is large enough */ + if (i >= MAX_ACTIVE_REGIONS) { + printk(KERN_CRIT "More than %d memory regions, truncating\n", + MAX_ACTIVE_REGIONS); + return; + } + + early_node_map[i].nid = nid; + early_node_map[i].start_pfn = start_pfn; + early_node_map[i].end_pfn = end_pfn; + nr_nodemap_entries = i + 1; +} + +/** + * shrink_active_range - Shrink an existing registered range of PFNs + * @nid: The node id the range is on that should be shrunk + * @old_end_pfn: The old end PFN of the range + * @new_end_pfn: The new PFN of the range + * + * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. + * The map is kept at the end physical page range that has already been + * registered with add_active_range(). This function allows an arch to shrink + * an existing registered range. + */ +void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn, + unsigned long new_end_pfn) +{ + int i; + + /* Find the old active region end and shrink */ + for_each_active_range_index_in_nid(i, nid) + if (early_node_map[i].end_pfn == old_end_pfn) { + early_node_map[i].end_pfn = new_end_pfn; + break; + } +} + +/** + * remove_all_active_ranges - Remove all currently registered regions + * During discovery, it may be found that a table like SRAT is invalid + * and an alternative discovery method must be used. This function removes + * all currently registered regions. + */ +void __init remove_all_active_ranges() +{ + memset(early_node_map, 0, sizeof(early_node_map)); + nr_nodemap_entries = 0; +} + +/* Compare two active node_active_regions */ +static int __init cmp_node_active_region(const void *a, const void *b) +{ + struct node_active_region *arange = (struct node_active_region *)a; + struct node_active_region *brange = (struct node_active_region *)b; + + /* Done this way to avoid overflows */ + if (arange->start_pfn > brange->start_pfn) + return 1; + if (arange->start_pfn < brange->start_pfn) + return -1; + + return 0; +} + +/* sort the node_map by start_pfn */ +static void __init sort_node_map(void) +{ + sort(early_node_map, (size_t)nr_nodemap_entries, + sizeof(struct node_active_region), + cmp_node_active_region, NULL); +} + +/* Find the lowest pfn for a node. This depends on a sorted early_node_map */ +unsigned long __init find_min_pfn_for_node(unsigned long nid) +{ + int i; + + /* Assuming a sorted map, the first range found has the starting pfn */ + for_each_active_range_index_in_nid(i, nid) + return early_node_map[i].start_pfn; + + printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid); + return 0; +} + +/** + * find_min_pfn_with_active_regions - Find the minimum PFN registered + * + * It returns the minimum PFN based on information provided via + * add_active_range() + */ +unsigned long __init find_min_pfn_with_active_regions(void) +{ + return find_min_pfn_for_node(MAX_NUMNODES); +} + +/** + * find_max_pfn_with_active_regions - Find the maximum PFN registered + * + * It returns the maximum PFN based on information provided via + * add_active_range() + */ +unsigned long __init find_max_pfn_with_active_regions(void) +{ + int i; + unsigned long max_pfn = 0; + + for (i = 0; i < nr_nodemap_entries; i++) + max_pfn = max(max_pfn, early_node_map[i].end_pfn); + + return max_pfn; +} + +/** + * free_area_init_nodes - Initialise all pg_data_t and zone data + * @arch_max_dma_pfn: The maximum PFN usable for ZONE_DMA + * @arch_max_dma32_pfn: The maximum PFN usable for ZONE_DMA32 + * @arch_max_low_pfn: The maximum PFN usable for ZONE_NORMAL + * @arch_max_high_pfn: The maximum PFN usable for ZONE_HIGHMEM + * + * This will call free_area_init_node() for each active node in the system. + * Using the page ranges provided by add_active_range(), the size of each + * zone in each node and their holes is calculated. If the maximum PFN + * between two adjacent zones match, it is assumed that the zone is empty. + * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed + * that arch_max_dma32_pfn has no pages. It is also assumed that a zone + * starts where the previous one ended. For example, ZONE_DMA32 starts + * at arch_max_dma_pfn. + */ +void __init free_area_init_nodes(unsigned long *max_zone_pfn) +{ + unsigned long nid; + enum zone_type i; + + /* Record where the zone boundaries are */ + memset(arch_zone_lowest_possible_pfn, 0, + sizeof(arch_zone_lowest_possible_pfn)); + memset(arch_zone_highest_possible_pfn, 0, + sizeof(arch_zone_highest_possible_pfn)); + arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions(); + arch_zone_highest_possible_pfn[0] = max_zone_pfn[0]; + for (i = 1; i < MAX_NR_ZONES; i++) { + arch_zone_lowest_possible_pfn[i] = + arch_zone_highest_possible_pfn[i-1]; + arch_zone_highest_possible_pfn[i] = + max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]); + } + + /* Regions in the early_node_map can be in any order */ + sort_node_map(); + + /* Print out the zone ranges */ + printk("Zone PFN ranges:\n"); + for (i = 0; i < MAX_NR_ZONES; i++) + printk(" %-8s %8lu -> %8lu\n", + zone_names[i], + arch_zone_lowest_possible_pfn[i], + arch_zone_highest_possible_pfn[i]); + + /* Print out the early_node_map[] */ + printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); + for (i = 0; i < nr_nodemap_entries; i++) + printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); + + /* Initialise every node */ + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + free_area_init_node(nid, pgdat, NULL, + find_min_pfn_for_node(nid), NULL); + } +} +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + #ifndef CONFIG_NEED_MULTIPLE_NODES static bootmem_data_t contig_bootmem_data; struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data }; -- cgit From 0e0b864e069c52a7b3e4a7da56e29b03a012fd75 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:56 -0700 Subject: [PATCH] Account for memmap and optionally the kernel image as holes The x86_64 code accounted for memmap and some portions of the the DMA zone as holes. This was because those areas would never be reclaimed and accounting for them as memory affects min watermarks. This patch will account for the memmap as a memory hole. Architectures may optionally use set_dma_reserve() if they wish to account for a portion of memory in ZONE_DMA as a hole. Signed-off-by: Mel Gorman Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86_64/mm/init.c | 4 +++- include/linux/mm.h | 1 + mm/page_alloc.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 63 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index 47928399e38a..3e16fe08150e 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -655,8 +655,10 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) #else reserve_bootmem(phys, len); #endif - if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) + if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { dma_reserve += len / PAGE_SIZE; + set_dma_reserve(dma_reserve); + } } int kern_addr_valid(unsigned long addr) diff --git a/include/linux/mm.h b/include/linux/mm.h index c0402da7cce0..22936e1fcdf2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -984,6 +984,7 @@ extern void sparse_memory_present_with_active_regions(int nid); extern int early_pfn_to_nid(unsigned long pfn); #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long); extern void setup_per_zone_pages_min(void); extern void mem_init(void); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 26c9939857fa..8d9a1eb9fbba 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -104,6 +104,7 @@ int min_free_kbytes = 1024; unsigned long __meminitdata nr_kernel_pages; unsigned long __meminitdata nr_all_pages; +static unsigned long __initdata dma_reserve; #ifdef CONFIG_ARCH_POPULATES_NODE_MAP /* @@ -2213,6 +2214,20 @@ unsigned long __init zone_absent_pages_in_node(int nid, arch_zone_lowest_possible_pfn[zone_type], arch_zone_highest_possible_pfn[zone_type]); } + +/* Return the zone index a PFN is in */ +int memmap_zone_idx(struct page *lmem_map) +{ + int i; + unsigned long phys_addr = virt_to_phys(lmem_map); + unsigned long pfn = phys_addr >> PAGE_SHIFT; + + for (i = 0; i < MAX_NR_ZONES; i++) + if (pfn < arch_zone_highest_possible_pfn[i]) + break; + + return i; +} #else static inline unsigned long zone_spanned_pages_in_node(int nid, unsigned long zone_type, @@ -2230,6 +2245,11 @@ static inline unsigned long zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } + +static inline int memmap_zone_idx(struct page *lmem_map) +{ + return MAX_NR_ZONES; +} #endif static void __init calculate_node_totalpages(struct pglist_data *pgdat, @@ -2274,12 +2294,35 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize; + unsigned long size, realsize, memmap_pages; size = zone_spanned_pages_in_node(nid, j, zones_size); realsize = size - zone_absent_pages_in_node(nid, j, zholes_size); + /* + * Adjust realsize so that it accounts for how much memory + * is used by this zone for memmap. This affects the watermark + * and per-cpu initialisations + */ + memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT; + if (realsize >= memmap_pages) { + realsize -= memmap_pages; + printk(KERN_DEBUG + " %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); + } else + printk(KERN_WARNING + " %s zone: %lu pages exceeds realsize %lu\n", + zone_names[j], memmap_pages, realsize); + + /* Account for reserved DMA pages */ + if (j == ZONE_DMA && realsize > dma_reserve) { + realsize -= dma_reserve; + printk(KERN_DEBUG " DMA zone: %lu pages reserved\n", + dma_reserve); + } + if (!is_highmem_idx(j)) nr_kernel_pages += realsize; nr_all_pages += realsize; @@ -2596,6 +2639,21 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) } #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +/** + * set_dma_reserve - Account the specified number of pages reserved in ZONE_DMA + * @new_dma_reserve - The number of pages to mark reserved + * + * The per-cpu batchsize and zone watermarks are determined by present_pages. + * In the DMA zone, a significant percentage may be consumed by kernel image + * and other unfreeable allocations which can skew the watermarks badly. This + * function may optionally be used to account for unfreeable pages in + * ZONE_DMA. The effect will be lower watermarks and smaller per-cpu batchsize + */ +void __init set_dma_reserve(unsigned long new_dma_reserve) +{ + dma_reserve = new_dma_reserve; +} + #ifndef CONFIG_NEED_MULTIPLE_NODES static bootmem_data_t contig_bootmem_data; struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data }; -- cgit From 9c7cd6877cf8db15269163deda69392263124c1e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:58 -0700 Subject: [PATCH] Account for holes that are outside the range of physical memory absent_pages_in_range() made the assumption that users of the API would not care about holes beyound the end of physical memory. This was not the case. This patch will account for ranges outside of physical memory as holes correctly. Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86_64/mm/srat.c | 4 +++- mm/page_alloc.c | 22 +++++++++++++++++++--- 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 7b50bb1caabe..db1b2e11cf8f 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -227,7 +227,9 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end) /* This check might be a bit too strict, but I'm keeping it for now. */ if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) { - printk(KERN_ERR "SRAT: Hotplug area has existing memory\n"); + printk(KERN_ERR + "SRAT: Hotplug area %lu -> %lu has existing memory\n", + s_pfn, e_pfn); return -1; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8d9a1eb9fbba..75133e1dc4b1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2168,6 +2168,10 @@ unsigned long __init __absent_pages_in_range(int nid, if (i == -1) return 0; + /* Account for ranges before physical memory on this node */ + if (early_node_map[i].start_pfn > range_start_pfn) + hole_pages = early_node_map[i].start_pfn - range_start_pfn; + prev_end_pfn = early_node_map[i].start_pfn; /* Find all holes for the zone within the node */ @@ -2189,6 +2193,11 @@ unsigned long __init __absent_pages_in_range(int nid, prev_end_pfn = early_node_map[i].end_pfn; } + /* Account for ranges past physical memory on this node */ + if (range_end_pfn > prev_end_pfn) + hole_pages = range_end_pfn - + max(range_start_pfn, prev_end_pfn); + return hole_pages; } @@ -2210,9 +2219,16 @@ unsigned long __init zone_absent_pages_in_node(int nid, unsigned long zone_type, unsigned long *ignored) { - return __absent_pages_in_range(nid, - arch_zone_lowest_possible_pfn[zone_type], - arch_zone_highest_possible_pfn[zone_type]); + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], + node_start_pfn); + zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], + node_end_pfn); + + return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } /* Return the zone index a PFN is in */ -- cgit From fb01439c5b778d5974a488c5d4fe85e6d0e18a68 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:59 -0700 Subject: [PATCH] Allow an arch to expand node boundaries Arch-independent zone-sizing determines the size of a node (pgdat->node_spanned_pages) based on the physical memory that was registered by the architecture. However, when CONFIG_MEMORY_HOTPLUG_RESERVE is set, the architecture expects that the spanned_pages will be much larger and that mem_map will be allocated that is used lated on memory hot-add. This patch allows an architecture that sets CONFIG_MEMORY_HOTPLUG_RESERVE to call push_node_boundaries() which will set the node beginning and end to at *least* the requested boundary. Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86_64/mm/srat.c | 2 ++ include/linux/mm.h | 2 ++ mm/page_alloc.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 71 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index db1b2e11cf8f..f8c04d6935c9 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -324,6 +324,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) nd->start, nd->end); e820_register_active_regions(node, nd->start >> PAGE_SHIFT, nd->end >> PAGE_SHIFT); + push_node_boundaries(node, nd->start >> PAGE_SHIFT, + nd->end >> PAGE_SHIFT); #ifdef RESERVE_HOTADD if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 22936e1fcdf2..9d046db31e76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -970,6 +970,8 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn, unsigned long new_end_pfn); +extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn); extern void remove_all_active_ranges(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 75133e1dc4b1..acbf58f8a1b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -131,6 +131,10 @@ static unsigned long __initdata dma_reserve; int __initdata nr_nodemap_entries; unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES]; + unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES]; +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ #ifdef CONFIG_DEBUG_VM @@ -2094,6 +2098,62 @@ void __init sparse_memory_present_with_active_regions(int nid) early_node_map[i].end_pfn); } +/** + * push_node_boundaries - Push node boundaries to at least the requested boundary + * @nid: The nid of the node to push the boundary for + * @start_pfn: The start pfn of the node + * @end_pfn: The end pfn of the node + * + * In reserve-based hot-add, mem_map is allocated that is unused until hotadd + * time. Specifically, on x86_64, SRAT will report ranges that can potentially + * be hotplugged even though no physical memory exists. This function allows + * an arch to push out the node boundaries so mem_map is allocated that can + * be used later. + */ +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) +{ + printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n", + nid, start_pfn, end_pfn); + + /* Initialise the boundary for this node if necessary */ + if (node_boundary_end_pfn[nid] == 0) + node_boundary_start_pfn[nid] = -1UL; + + /* Update the boundaries */ + if (node_boundary_start_pfn[nid] > start_pfn) + node_boundary_start_pfn[nid] = start_pfn; + if (node_boundary_end_pfn[nid] < end_pfn) + node_boundary_end_pfn[nid] = end_pfn; +} + +/* If necessary, push the node boundary out for reserve hotadd */ +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n", + nid, *start_pfn, *end_pfn); + + /* Return if boundary information has not been provided */ + if (node_boundary_end_pfn[nid] == 0) + return; + + /* Check the boundaries and update if necessary */ + if (node_boundary_start_pfn[nid] < *start_pfn) + *start_pfn = node_boundary_start_pfn[nid]; + if (node_boundary_end_pfn[nid] > *end_pfn) + *end_pfn = node_boundary_end_pfn[nid]; +} +#else +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) {} + +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) {} +#endif + + /** * get_pfn_range_for_nid - Return the start and end page frames for a node * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned @@ -2121,6 +2181,9 @@ void __init get_pfn_range_for_nid(unsigned int nid, printk(KERN_WARNING "Node %u active with no memory\n", nid); *start_pfn = 0; } + + /* Push the node boundaries out if requested */ + account_node_boundary(nid, start_pfn, end_pfn); } /* @@ -2527,6 +2590,10 @@ void __init remove_all_active_ranges() { memset(early_node_map, 0, sizeof(early_node_map)); nr_nodemap_entries = 0; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn)); + memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn)); +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ } /* Compare two active node_active_regions */ -- cgit From c72419138fa34e1bc1f1c6fa54ee77df55a05ed0 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Wed, 27 Sep 2006 01:50:05 -0700 Subject: [PATCH] Condense output of show_free_areas() On larger systems, the amount of output dumped on the console when you do SysRq-M is beyond insane. This patch is trying to reduce it somewhat as even with the smaller NUMA systems that have hit the desktop this seems to be a fair thing to do. The philosophy I have taken is as follows: 1) If a zone is empty, don't tell, we don't need yet another line telling us so. The information is available since one can look up the fact how many zones were initialized in the first place. 2) Put as much information on a line is possible, if it can be done in one line, rahter than two, then do it in one. I tried to format the temperature stuff for easy reading. Change show_free_areas() to not print lines for empty zones. If no zone output is printed, the zone is empty. This reduces the number of lines dumped to the console in sysrq on a large system by several thousand lines. Change the zone temperature printouts to use one line per CPU instead of two lines (one hot, one cold). On a 1024 CPU, 1024 node system, this reduces the console output by over a million lines of output. While this is a bigger problem on large NUMA systems, it is also applicable to smaller desktop sized and mid range NUMA systems. Old format: Mem-info: Node 0 DMA per-cpu: cpu 0 hot: high 42, batch 7 used:24 cpu 0 cold: high 14, batch 3 used:1 cpu 1 hot: high 42, batch 7 used:34 cpu 1 cold: high 14, batch 3 used:0 cpu 2 hot: high 42, batch 7 used:0 cpu 2 cold: high 14, batch 3 used:0 cpu 3 hot: high 42, batch 7 used:0 cpu 3 cold: high 14, batch 3 used:0 cpu 4 hot: high 42, batch 7 used:0 cpu 4 cold: high 14, batch 3 used:0 cpu 5 hot: high 42, batch 7 used:0 cpu 5 cold: high 14, batch 3 used:0 cpu 6 hot: high 42, batch 7 used:0 cpu 6 cold: high 14, batch 3 used:0 cpu 7 hot: high 42, batch 7 used:0 cpu 7 cold: high 14, batch 3 used:0 Node 0 DMA32 per-cpu: empty Node 0 Normal per-cpu: empty Node 0 HighMem per-cpu: empty Node 1 DMA per-cpu: [snip] Free pages: 5410688kB (0kB HighMem) Active:9536 inactive:4261 dirty:6 writeback:0 unstable:0 free:338168 slab:1931 mapped:1900 pagetables:208 Node 0 DMA free:1676304kB min:3264kB low:4080kB high:4896kB active:128048kB inactive:61568kB present:1970880kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 0 DMA32 free:0kB min:0kB low:0kB high:0kB active:0kB inactive:0kB present:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 0 Normal free:0kB min:0kB low:0kB high:0kB active:0kB inactive:0kB present:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 0 HighMem free:0kB min:512kB low:512kB high:512kB active:0kB inactive:0kB present:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 1 DMA free:1951728kB min:3280kB low:4096kB high:4912kB active:5632kB inactive:1504kB present:1982464kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 .... New format: Mem-info: Node 0 DMA per-cpu: CPU 0: Hot: hi: 42, btch: 7 usd: 41 Cold: hi: 14, btch: 3 usd: 2 CPU 1: Hot: hi: 42, btch: 7 usd: 40 Cold: hi: 14, btch: 3 usd: 1 CPU 2: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 CPU 3: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 CPU 4: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 CPU 5: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 CPU 6: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 CPU 7: Hot: hi: 42, btch: 7 usd: 0 Cold: hi: 14, btch: 3 usd: 0 Node 1 DMA per-cpu: [snip] Free pages: 5411088kB (0kB HighMem) Active:9558 inactive:4233 dirty:6 writeback:0 unstable:0 free:338193 slab:1942 mapped:1918 pagetables:208 Node 0 DMA free:1677648kB min:3264kB low:4080kB high:4896kB active:129296kB inactive:58864kB present:1970880kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 1 DMA free:1948448kB min:3280kB low:4096kB high:4912kB active:6864kB inactive:3536kB present:1982464kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Signed-off-by: Jes Sorensen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index acbf58f8a1b7..8a6418b0d2c5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1305,34 +1305,30 @@ void si_meminfo_node(struct sysinfo *val, int nid) */ void show_free_areas(void) { - int cpu, temperature; + int cpu; unsigned long active; unsigned long inactive; unsigned long free; struct zone *zone; for_each_zone(zone) { - show_node(zone); - printk("%s per-cpu:", zone->name); - - if (!populated_zone(zone)) { - printk(" empty\n"); + if (!populated_zone(zone)) continue; - } else - printk("\n"); + + show_node(zone); + printk("%s per-cpu:\n", zone->name); for_each_online_cpu(cpu) { struct per_cpu_pageset *pageset; pageset = zone_pcp(zone, cpu); - for (temperature = 0; temperature < 2; temperature++) - printk("cpu %d %s: high %d, batch %d used:%d\n", - cpu, - temperature ? "cold" : "hot", - pageset->pcp[temperature].high, - pageset->pcp[temperature].batch, - pageset->pcp[temperature].count); + printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d " + "Cold: hi:%5d, btch:%4d usd:%4d\n", + cpu, pageset->pcp[0].high, + pageset->pcp[0].batch, pageset->pcp[0].count, + pageset->pcp[1].high, pageset->pcp[1].batch, + pageset->pcp[1].count); } } @@ -1354,6 +1350,9 @@ void show_free_areas(void) for_each_zone(zone) { int i; + if (!populated_zone(zone)) + continue; + show_node(zone); printk("%s" " free:%lukB" @@ -1386,12 +1385,11 @@ void show_free_areas(void) for_each_zone(zone) { unsigned long nr[MAX_ORDER], flags, order, total = 0; + if (!populated_zone(zone)) + continue; + show_node(zone); printk("%s: ", zone->name); - if (!populated_zone(zone)) { - printk("empty\n"); - continue; - } spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { -- cgit From 08e0f6a9705376732fd3bc9bf8ba97a6b5211eb1 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:06 -0700 Subject: [PATCH] Add NUMA_BUILD definition in kernel.h to avoid #ifdef CONFIG_NUMA The NUMA_BUILD constant is always available and will be set to 1 on NUMA_BUILDs. That way checks valid only under CONFIG_NUMA can easily be done without #ifdef CONFIG_NUMA F.e. if (NUMA_BUILD && ) { ... } [akpm: not a thing we'd normally do, but CONFIG_NUMA is special: it is causing ifdef explosion in core kernel, so let's see if this is a comfortable way in whcih to control that] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 +++++++ mm/page_alloc.c | 12 +++++------- 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 4fa373bb18ac..4d00988dad03 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -350,4 +350,11 @@ struct sysinfo { /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) +/* This helps us to avoid #ifdef CONFIG_NUMA */ +#ifdef CONFIG_NUMA +#define NUMA_BUILD 1 +#else +#define NUMA_BUILD 0 +#endif + #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8a6418b0d2c5..4c76188b1681 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -942,7 +942,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, */ do { zone = *z; - if (unlikely((gfp_mask & __GFP_THISNODE) && + if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) && zone->zone_pgdat != zonelist->zones[0]->zone_pgdat)) break; if ((alloc_flags & ALLOC_CPUSET) && @@ -1256,14 +1256,12 @@ unsigned int nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER)); } -#ifdef CONFIG_NUMA -static void show_node(struct zone *zone) + +static inline void show_node(struct zone *zone) { - printk("Node %ld ", zone_to_nid(zone)); + if (NUMA_BUILD) + printk("Node %ld ", zone_to_nid(zone)); } -#else -#define show_node(zone) do { } while (0) -#endif void si_meminfo(struct sysinfo *val) { -- cgit From d5f541ed6e31518508c688912e7464facf253c87 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:08 -0700 Subject: [PATCH] Add node to zone for the NUMA case Add the node in order to optimize zone_to_nid. Signed-off-by: Christoph Lameter Acked-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++++- include/linux/mmzone.h | 1 + mm/page_alloc.c | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7477fb59c4f2..8e433bbc6e7e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -446,7 +446,11 @@ static inline struct zone *page_zone(struct page *page) static inline unsigned long zone_to_nid(struct zone *zone) { - return zone->zone_pgdat->node_id; +#ifdef CONFIG_NUMA + return zone->node; +#else + return 0; +#endif } static inline unsigned long page_to_nid(struct page *page) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 562cf7a8f3ee..59855b8718a0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -168,6 +168,7 @@ struct zone { unsigned long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA + int node; /* * zone reclaim becomes active if more unmapped pages exist. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4c76188b1681..d0432e44f77d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2405,6 +2405,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->spanned_pages = size; zone->present_pages = realsize; #ifdef CONFIG_NUMA + zone->node = nid; zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) / 100; zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100; -- cgit From 66a550308b8e4cbaba185d0326cb05d1bd758101 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:09 -0700 Subject: [PATCH] Do not allocate pagesets for unpopulated zones. We do not need to allocate pagesets for unpopulated zones. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d0432e44f77d..490aee1f2ce8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1829,6 +1829,9 @@ static int __cpuinit process_zones(int cpu) for_each_zone(zone) { + if (!populated_zone(zone)) + continue; + zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset), GFP_KERNEL, cpu_to_node(cpu)); if (!zone_pcp(zone, cpu)) -- cgit From 423b41d773abe443bb546ce91361192073b96f88 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 27 Sep 2006 01:50:12 -0700 Subject: [PATCH] mm/page_alloc: use NULL instead of 0 for ptr Use NULL instead of 0 for pointer value, eliminate sparse warnings. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 490aee1f2ce8..4f59d90b81e6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1591,7 +1591,7 @@ static int __meminit __build_all_zonelists(void *dummy) void __meminit build_all_zonelists(void) { if (system_state == SYSTEM_BOOTING) { - __build_all_zonelists(0); + __build_all_zonelists(NULL); cpuset_init_current_mems_allowed(); } else { /* we have to stop all cpus to guaranntee there is no user -- cgit