From 9614634fe6a138fd8ae044950700d2af8d203f97 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 3 Jul 2006 00:24:13 -0700 Subject: [PATCH] ZVC/zone_reclaim: Leave 1% of unmapped pagecache pages for file I/O It turns out that it is advantageous to leave a small portion of unmapped file backed pages if all of a zone's pages (or almost all pages) are allocated and so the page allocator has to go off-node. This allows recently used file I/O buffers to stay on the node and reduces the times that zone reclaim is invoked if file I/O occurs when we run out of memory in a zone. The problem is that zone reclaim runs too frequently when the page cache is used for file I/O (read write and therefore unmapped pages!) alone and we have almost all pages of the zone allocated. Zone reclaim may remove 32 unmapped pages. File I/O will use these pages for the next read/write requests and the unmapped pages increase. After the zone has filled up again zone reclaim will remove it again after only 32 pages. This cycle is too inefficient and there are potentially too many zone reclaim cycles. With the 1% boundary we may still remove all unmapped pages for file I/O in zone reclaim pass. However. it will take a large number of read and writes to get back to 1% again where we trigger zone reclaim again. The zone reclaim 2.6.16/17 does not show this behavior because we have a 30 second timeout. [akpm@osdl.org: rename the /proc file and the variable] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 22 ++++++++++++++++++++++ mm/vmscan.c | 27 ++++++++++++++------------- 2 files changed, 36 insertions(+), 13 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3e792a583f3b..54a4f5375bba 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2005,6 +2005,10 @@ 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) + / 100; +#endif zone->name = zone_names[j]; spin_lock_init(&zone->lock); spin_lock_init(&zone->lru_lock); @@ -2298,6 +2302,24 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, return 0; } +#ifdef CONFIG_NUMA +int sysctl_min_unmapped_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_unmapped_ratio = (zone->present_pages * + sysctl_min_unmapped_ratio) / 100; + return 0; +} +#endif + /* * lowmem_reserve_ratio_sysctl_handler - just a wrapper around * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve() diff --git a/mm/vmscan.c b/mm/vmscan.c index ff2ebe9458a3..5d4c4d02254d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1503,10 +1503,6 @@ module_init(kswapd_init) * * If non-zero call zone_reclaim when the number of free pages falls below * the watermarks. - * - * In the future we may add flags to the mode. However, the page allocator - * should only have to check that zone_reclaim_mode != 0 before calling - * zone_reclaim(). */ int zone_reclaim_mode __read_mostly; @@ -1523,6 +1519,12 @@ int zone_reclaim_mode __read_mostly; */ #define ZONE_RECLAIM_PRIORITY 4 +/* + * Percentage of pages in a zone that must be unmapped for zone_reclaim to + * occur. + */ +int sysctl_min_unmapped_ratio = 1; + /* * Try to free up some pages from this zone through reclaim. */ @@ -1590,18 +1592,17 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) int node_id; /* - * Do not reclaim if there are not enough reclaimable pages in this - * zone that would satify this allocations. + * Zone reclaim reclaims unmapped file backed pages. * - * All unmapped pagecache pages are reclaimable. - * - * Both counters may be temporarily off a bit so we use - * SWAP_CLUSTER_MAX as the boundary. It may also be good to - * leave a few frequently used unmapped pagecache pages around. + * A small portion of unmapped file backed pages is needed for + * file I/O otherwise pages read by file I/O will be immediately + * thrown out if the zone is overallocated. So we do not reclaim + * if less than a specified percentage of the zone is used by + * unmapped file backed pages. */ if (zone_page_state(zone, NR_FILE_PAGES) - - zone_page_state(zone, NR_FILE_MAPPED) < SWAP_CLUSTER_MAX) - return 0; + zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_ratio) + return 0; /* * Avoid concurrent zone reclaims, do not reclaim in a zone that does -- cgit v1.2.2 From 9a11b49a805665e13a56aa067afaf81d43ec1514 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Jul 2006 00:24:33 -0700 Subject: [PATCH] lockdep: better lock debugging Generic lock debugging: - generalized lock debugging framework. For example, a bug in one lock subsystem turns off debugging in all lock subsystems. - got rid of the caller address passing (__IP__/__IP_DECL__/etc.) from the mutex/rtmutex debugging code: it caused way too much prototype hackery, and lockdep will give the same information anyway. - ability to do silent tests - check lock freeing in vfree too. - more finegrained debugging options, to allow distributions to turn off more expensive debugging features. There's no separate 'held mutexes' list anymore - but there's a 'held locks' stack within lockdep, which unifies deadlock detection across all lock classes. (this is independent of the lockdep validation stuff - lockdep first checks whether we are holding a lock already) Here are the current debugging options: CONFIG_DEBUG_MUTEXES=y CONFIG_DEBUG_LOCK_ALLOC=y which do: config DEBUG_MUTEXES bool "Mutex debugging, basic checks" config DEBUG_LOCK_ALLOC bool "Detect incorrect freeing of live mutexes" Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 35f8553f893a..7b450798b458 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -330,6 +330,8 @@ void __vunmap(void *addr, int deallocate_pages) return; } + debug_check_no_locks_freed(addr, area->size); + if (deallocate_pages) { int i; -- cgit v1.2.2 From e4d919188554a77c798a267e098059bc9aa39726 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Jul 2006 00:24:34 -0700 Subject: [PATCH] lockdep: locking init debugging improvement Locking init improvement: - introduce and use __SPIN_LOCK_UNLOCKED for array initializations, to pass in the name string of locks, used by debugging Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/swap_state.c b/mm/swap_state.c index fccbd9bba77b..5f7cf2a4cb55 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -38,7 +38,7 @@ static struct backing_dev_info swap_backing_dev_info = { struct address_space swapper_space = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .tree_lock = RW_LOCK_UNLOCKED, + .tree_lock = __RW_LOCK_UNLOCKED(swapper_space.tree_lock), .a_ops = &swap_aops, .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear), .backing_dev_info = &swap_backing_dev_info, -- cgit v1.2.2 From f20dc5f7c1adf1c4b68b7672d6f2002cb824e636 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Jul 2006 00:25:08 -0700 Subject: [PATCH] lockdep: annotate mm Teach special (recursive) locking code to the lock validator. Has no effect on non-lockdep kernels. Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- mm/mremap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 7e2a4b1580e3..c1e14c9e67e4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -503,7 +503,7 @@ again: return -ENOMEM; src_pte = pte_offset_map_nested(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); - spin_lock(src_ptl); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); do { /* diff --git a/mm/mremap.c b/mm/mremap.c index 1903bdf65e42..7c15cf3373ad 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -97,7 +97,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_pte = pte_offset_map_nested(new_pmd, new_addr); new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) - spin_lock(new_ptl); + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { -- cgit v1.2.2 From 2b2d5493e10051694ae3a57ea6a153e3cb4d4488 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Jul 2006 00:25:28 -0700 Subject: [PATCH] lockdep: annotate SLAB code Teach special (recursive) locking code to the lock validator. Has no effect on non-lockdep kernels. Fix initialize-locks-via-memcpy assumptions. Effects on non-lockdep kernels: the subclass nesting parameter is passed into cache_free_alien() and __cache_free(), and turns one internal kmem_cache_free() call into an open-coded __cache_free() call. Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Cc: Pekka Enberg Cc: Christoph Lameter Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 48 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index 3936af344542..85c2e03098a7 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1021,7 +1021,8 @@ static void drain_alien_cache(struct kmem_cache *cachep, } } -static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp, + int nesting) { struct slab *slabp = virt_to_slab(objp); int nodeid = slabp->nodeid; @@ -1039,7 +1040,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) STATS_INC_NODEFREES(cachep); if (l3->alien && l3->alien[nodeid]) { alien = l3->alien[nodeid]; - spin_lock(&alien->lock); + spin_lock_nested(&alien->lock, nesting); if (unlikely(alien->avail == alien->limit)) { STATS_INC_ACOVERFLOW(cachep); __drain_alien_cache(cachep, alien, nodeid); @@ -1068,7 +1069,8 @@ static inline void free_alien_cache(struct array_cache **ac_ptr) { } -static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp, + int nesting) { return 0; } @@ -1272,6 +1274,11 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, local_irq_disable(); memcpy(ptr, list, sizeof(struct kmem_list3)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->list_lock); + MAKE_ALL_LISTS(cachep, ptr, nodeid); cachep->nodelists[nodeid] = ptr; local_irq_enable(); @@ -1398,7 +1405,7 @@ void __init kmem_cache_init(void) } /* 4) Replace the bootstrap head arrays */ { - void *ptr; + struct array_cache *ptr; ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); @@ -1406,6 +1413,11 @@ void __init kmem_cache_init(void) BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache); memcpy(ptr, cpu_cache_get(&cache_cache), sizeof(struct arraycache_init)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->lock); + cache_cache.array[smp_processor_id()] = ptr; local_irq_enable(); @@ -1416,6 +1428,11 @@ void __init kmem_cache_init(void) != &initarray_generic.cache); memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep), sizeof(struct arraycache_init)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->lock); + malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] = ptr; local_irq_enable(); @@ -1743,6 +1760,8 @@ static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp) } #endif +static void __cache_free(struct kmem_cache *cachep, void *objp, int nesting); + /** * slab_destroy - destroy and release all objects in a slab * @cachep: cache pointer being destroyed @@ -1766,8 +1785,17 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) call_rcu(&slab_rcu->head, kmem_rcu_free); } else { kmem_freepages(cachep, addr); - if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->slabp_cache, slabp); + if (OFF_SLAB(cachep)) { + unsigned long flags; + + /* + * lockdep: we may nest inside an already held + * ac->lock, so pass in a nesting flag: + */ + local_irq_save(flags); + __cache_free(cachep->slabp_cache, slabp, 1); + local_irq_restore(flags); + } } } @@ -3072,7 +3100,16 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, if (slabp->inuse == 0) { if (l3->free_objects > l3->free_limit) { l3->free_objects -= cachep->num; + /* + * It is safe to drop the lock. The slab is + * no longer linked to the cache. cachep + * cannot disappear - we are using it and + * all destruction of caches must be + * serialized properly by the user. + */ + spin_unlock(&l3->list_lock); slab_destroy(cachep, slabp); + spin_lock(&l3->list_lock); } else { list_add(&slabp->list, &l3->slabs_free); } @@ -3098,7 +3135,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) #endif check_irq_off(); l3 = cachep->nodelists[node]; - spin_lock(&l3->list_lock); + spin_lock_nested(&l3->list_lock, SINGLE_DEPTH_NESTING); if (l3->shared) { struct array_cache *shared_array = l3->shared; int max = shared_array->limit - shared_array->avail; @@ -3141,14 +3178,14 @@ free_done: * Release an obj back to its cache. If the obj has a constructed state, it must * be in this state _before_ it is released. Called with disabled ints. */ -static inline void __cache_free(struct kmem_cache *cachep, void *objp) +static void __cache_free(struct kmem_cache *cachep, void *objp, int nesting) { struct array_cache *ac = cpu_cache_get(cachep); check_irq_off(); objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0)); - if (cache_free_alien(cachep, objp)) + if (cache_free_alien(cachep, objp, nesting)) return; if (likely(ac->avail < ac->limit)) { @@ -3387,7 +3424,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) BUG_ON(virt_to_cache(objp) != cachep); local_irq_save(flags); - __cache_free(cachep, objp); + __cache_free(cachep, objp, 0); local_irq_restore(flags); } EXPORT_SYMBOL(kmem_cache_free); @@ -3412,7 +3449,7 @@ void kfree(const void *objp) kfree_debugcheck(objp); c = virt_to_cache(objp); debug_check_no_locks_freed(objp, obj_size(c)); - __cache_free(c, (void *)objp); + __cache_free(c, (void *)objp, 0); local_irq_restore(flags); } EXPORT_SYMBOL(kfree); -- cgit v1.2.2 From 36c8b586896f60cb91a4fd526233190b34316baf Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Jul 2006 00:25:41 -0700 Subject: [PATCH] sched: cleanup, remove task_t, convert to struct task_struct cleanup: remove task_t and convert all the uses to struct task_struct. I introduced it for the scheduler anno and it was a mistake. Conversion was mostly scripted, the result was reviewed and all secondary whitespace and style impact (if any) was fixed up by hand. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d46ed0f1dc06..b9af136e5cfa 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -225,7 +225,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) * CAP_SYS_RAW_IO set, send SIGTERM instead (but it's unlikely that * we select a process with CAP_SYS_RAW_IO set). */ -static void __oom_kill_task(task_t *p, const char *message) +static void __oom_kill_task(struct task_struct *p, const char *message) { if (p->pid == 1) { WARN_ON(1); @@ -255,10 +255,10 @@ static void __oom_kill_task(task_t *p, const char *message) force_sig(SIGKILL, p); } -static int oom_kill_task(task_t *p, const char *message) +static int oom_kill_task(struct task_struct *p, const char *message) { struct mm_struct *mm; - task_t * g, * q; + struct task_struct *g, *q; mm = p->mm; @@ -316,7 +316,7 @@ static int oom_kill_process(struct task_struct *p, unsigned long points, */ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) { - task_t *p; + struct task_struct *p; unsigned long points = 0; if (printk_ratelimit()) { -- cgit v1.2.2