diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/filemap.c | 3 | ||||
| -rw-r--r-- | mm/page-writeback.c | 2 | ||||
| -rw-r--r-- | mm/page_alloc.c | 2 | ||||
| -rw-r--r-- | mm/percpu.c | 10 | ||||
| -rw-r--r-- | mm/rmap.c | 2 | ||||
| -rw-r--r-- | mm/shmem.c | 9 | ||||
| -rw-r--r-- | mm/slab.c | 76 | ||||
| -rw-r--r-- | mm/slob.c | 5 | ||||
| -rw-r--r-- | mm/slub.c | 70 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 2 | ||||
| -rw-r--r-- | mm/swapfile.c | 7 | ||||
| -rw-r--r-- | mm/util.c | 21 | ||||
| -rw-r--r-- | mm/vmstat.c | 151 |
13 files changed, 183 insertions, 177 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 6b9aee20f242..ca389394fa2a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -102,9 +102,6 @@ * ->inode_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * - * ->task->proc_lock - * ->dcache_lock (proc_pid_lookup) - * * (code doesn't rely on that order, so you could switch it around) * ->tasklist_lock (memory_failure, collect_procs_ao) * ->i_mmap_lock diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b4edfe7ce06c..b5d8a1f820a0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -404,7 +404,7 @@ unsigned long determine_dirtyable_memory(void) * - vm.dirty_background_ratio or vm.dirty_background_bytes * - vm.dirty_ratio or vm.dirty_bytes * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and - * runtime tasks. + * real-time tasks. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ff7e15872398..826ba6922e84 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4014,7 +4014,7 @@ static void __init setup_usemap(struct pglist_data *pgdat, zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); } #else -static void inline setup_usemap(struct pglist_data *pgdat, +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ diff --git a/mm/percpu.c b/mm/percpu.c index 02ba91230b99..3f930018aa60 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -258,7 +258,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, /* * (Un)populated page region iterators. Iterate over (un)populated - * page regions betwen @start and @end in @chunk. @rs and @re should + * page regions between @start and @end in @chunk. @rs and @re should * be integer variables and will be set to start and end page index of * the current region. */ @@ -293,12 +293,8 @@ static void *pcpu_mem_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - else { - void *ptr = vmalloc(size); - if (ptr) - memset(ptr, 0, size); - return ptr; - } + else + return vzalloc(size); } /** diff --git a/mm/rmap.c b/mm/rmap.c index 1a8bf76bfd03..c95d2ba27a0b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -94,7 +94,7 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, but if - * if not we either need to find an adjacent mapping that we + * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. diff --git a/mm/shmem.c b/mm/shmem.c index 47fdeeb9d636..5ee67c990602 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2415,13 +2415,20 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) return &p->vfs_inode; } +static void shmem_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + INIT_LIST_HEAD(&inode->i_dentry); + kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); +} + static void shmem_destroy_inode(struct inode *inode) { if ((inode->i_mode & S_IFMT) == S_IFREG) { /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } - kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); + call_rcu(&inode->i_rcu, shmem_i_callback); } static void init_once(void *foo) diff --git a/mm/slab.c b/mm/slab.c index b1e40dafbab3..264037449f08 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -829,12 +829,12 @@ static void init_reap_node(int cpu) static void next_reap_node(void) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); - __get_cpu_var(slab_reap_node) = node; + __this_cpu_write(slab_reap_node, node); } #else @@ -1012,7 +1012,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, */ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); if (l3->alien) { struct array_cache *ac = l3->alien[node]; @@ -1293,7 +1293,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, * anything expensive but will only modify reap_work * and reschedule the timer. */ - cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu)); + cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu)); /* Now the cache_reaper is guaranteed to be not running. */ per_cpu(slab_reap_work, cpu).work.func = NULL; break; @@ -2781,7 +2781,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, /* * Map pages beginning at addr to the given cache and slab. This is required * for the slab allocator to be able to lookup the cache and slab of a - * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging. + * virtual address for kfree, ksize, and slab debugging. */ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, void *addr) @@ -3653,42 +3653,19 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) +void * +kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags) { - return __cache_alloc(cachep, flags, __builtin_return_address(0)); -} -EXPORT_SYMBOL(kmem_cache_alloc_notrace); -#endif + void *ret; -/** - * kmem_ptr_validate - check if an untrusted pointer might be a slab entry. - * @cachep: the cache we're checking against - * @ptr: pointer to validate - * - * This verifies that the untrusted pointer looks sane; - * it is _not_ a guarantee that the pointer is actually - * part of the slab cache in question, but it at least - * validates that the pointer can be dereferenced and - * looks half-way sane. - * - * Currently only used for dentry validation. - */ -int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr) -{ - unsigned long size = cachep->buffer_size; - struct page *page; + ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); - if (unlikely(!kern_ptr_validate(ptr, size))) - goto out; - page = virt_to_page(ptr); - if (unlikely(!PageSlab(page))) - goto out; - if (unlikely(page_get_cache(page) != cachep)) - goto out; - return 1; -out: - return 0; + trace_kmalloc(_RET_IP_, ret, + size, slab_buffer_size(cachep), flags); + return ret; } +EXPORT_SYMBOL(kmem_cache_alloc_trace); +#endif #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) @@ -3705,31 +3682,32 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) EXPORT_SYMBOL(kmem_cache_alloc_node); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid) +void *kmem_cache_alloc_node_trace(size_t size, + struct kmem_cache *cachep, + gfp_t flags, + int nodeid) { - return __cache_alloc_node(cachep, flags, nodeid, + void *ret; + + ret = __cache_alloc_node(cachep, flags, nodeid, __builtin_return_address(0)); + trace_kmalloc_node(_RET_IP_, ret, + size, slab_buffer_size(cachep), + flags, nodeid); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif static __always_inline void * __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; - void *ret; cachep = kmem_find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = kmem_cache_alloc_node_notrace(cachep, flags, node); - - trace_kmalloc_node((unsigned long) caller, ret, - size, cachep->buffer_size, flags, node); - - return ret; + return kmem_cache_alloc_node_trace(size, cachep, flags, node); } #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING) diff --git a/mm/slob.c b/mm/slob.c index 617b6d6c42c7..3588eaaef726 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -678,11 +678,6 @@ int kmem_cache_shrink(struct kmem_cache *d) } EXPORT_SYMBOL(kmem_cache_shrink); -int kmem_ptr_validate(struct kmem_cache *a, const void *b) -{ - return 0; -} - static unsigned int slob_ready __read_mostly; int slab_is_available(void) diff --git a/mm/slub.c b/mm/slub.c index bec0e355fbad..008cd743a36a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -28,6 +28,8 @@ #include <linux/math64.h> #include <linux/fault-inject.h> +#include <trace/events/kmem.h> + /* * Lock order: * 1. slab_lock(page) @@ -1774,11 +1776,21 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { - return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_notrace); +EXPORT_SYMBOL(kmem_cache_alloc_trace); + +void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = kmalloc_order(size, flags, order); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order_trace); #endif #ifdef CONFIG_NUMA @@ -1794,13 +1806,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) EXPORT_SYMBOL(kmem_cache_alloc_node); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, +void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node) + int node, size_t size) { - return slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, + size, s->size, gfpflags, node); + return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif #endif @@ -1917,17 +1933,6 @@ void kmem_cache_free(struct kmem_cache *s, void *x) } EXPORT_SYMBOL(kmem_cache_free); -/* Figure out on which slab page the object resides */ -static struct page *get_object_page(const void *x) -{ - struct page *page = virt_to_head_page(x); - - if (!PageSlab(page)) - return NULL; - - return page; -} - /* * Object placement in a slab is made very easy because we always start at * offset 0. If we tune the size of the object to the alignment then we can @@ -2386,35 +2391,6 @@ error: } /* - * Check if a given pointer is valid - */ -int kmem_ptr_validate(struct kmem_cache *s, const void *object) -{ - struct page *page; - - if (!kern_ptr_validate(object, s->size)) - return 0; - - page = get_object_page(object); - - if (!page || s != page->slab) - /* No slab or wrong slab */ - return 0; - - if (!check_valid_pointer(s, page, object)) - return 0; - - /* - * We could also check if the object is on the slabs freelist. - * But this would be too expensive and it seems that the main - * purpose of kmem_ptr_valid() is to check if the object belongs - * to a certain slab. - */ - return 1; -} -EXPORT_SYMBOL(kmem_ptr_validate); - -/* * Determine the size of a slab object */ unsigned int kmem_cache_size(struct kmem_cache *s) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 29d6cbffb283..64b984091edb 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -9,7 +9,7 @@ * * However, virtual mappings need a page table and TLBs. Many Linux * architectures already map their physical space using 1-1 mappings - * via TLBs. For those arches the virtual memmory map is essentially + * via TLBs. For those arches the virtual memory map is essentially * for free if we use the same page size as the 1-1 mappings. In that * case the overhead consists of a few additional pages that are * allocated to create a view of memory for vmemmap. diff --git a/mm/swapfile.c b/mm/swapfile.c index 67ddaaf98c74..b6adcfbf6f48 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1677,7 +1677,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, p->old_block_size); - bd_release(bdev); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { mutex_lock(&inode->i_mutex); inode->i_flags &= ~S_SWAPFILE; @@ -1939,7 +1939,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -EINVAL; if (S_ISBLK(inode->i_mode)) { bdev = I_BDEV(inode); - error = bd_claim(bdev, sys_swapon); + error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, + sys_swapon); if (error < 0) { bdev = NULL; error = -EINVAL; @@ -2136,7 +2137,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) bad_swap: if (bdev) { set_blocksize(bdev, p->old_block_size); - bd_release(bdev); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } destroy_swap_extents(p); swap_cgroup_swapoff(type); diff --git a/mm/util.c b/mm/util.c index 73dac81e9f78..f126975ef23e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -186,27 +186,6 @@ void kzfree(const void *p) } EXPORT_SYMBOL(kzfree); -int kern_ptr_validate(const void *ptr, unsigned long size) -{ - unsigned long addr = (unsigned long)ptr; - unsigned long min_addr = PAGE_OFFSET; - unsigned long align_mask = sizeof(void *) - 1; - - if (unlikely(addr < min_addr)) - goto out; - if (unlikely(addr > (unsigned long)high_memory - size)) - goto out; - if (unlikely(addr & align_mask)) - goto out; - if (unlikely(!kern_addr_valid(addr))) - goto out; - if (unlikely(!kern_addr_valid(addr + size - 1))) - goto out; - return 1; -out: - return 0; -} - /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate diff --git a/mm/vmstat.c b/mm/vmstat.c index 8f62f17ee1c7..312d728976f1 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -167,36 +167,24 @@ static void refresh_zone_stat_thresholds(void) void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; long x; + long t; + + x = delta + __this_cpu_read(*p); - x = delta + *p; + t = __this_cpu_read(pcp->stat_threshold); - if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) { + if (unlikely(x > t || x < -t)) { zone_page_state_add(x, zone, item); x = 0; } - *p = x; + __this_cpu_write(*p, x); } EXPORT_SYMBOL(__mod_zone_page_state); /* - * For an unknown interrupt state - */ -void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_zone_page_state(zone, item, delta); - local_irq_restore(flags); -} -EXPORT_SYMBOL(mod_zone_page_state); - -/* * Optimized increment and decrement functions. * * These are only for a single page and therefore can take a struct page * @@ -221,16 +209,17 @@ EXPORT_SYMBOL(mod_zone_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - (*p)++; + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; - if (unlikely(*p > pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; - - zone_page_state_add(*p + overstep, zone, item); - *p = -overstep; + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); } } @@ -242,16 +231,17 @@ EXPORT_SYMBOL(__inc_zone_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; - - (*p)--; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - if (unlikely(*p < - pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; - zone_page_state_add(*p - overstep, zone, item); - *p = overstep; + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); } } @@ -261,6 +251,92 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item) } EXPORT_SYMBOL(__dec_zone_page_state); +#ifdef CONFIG_CMPXCHG_LOCAL +/* + * If we have cmpxchg_local support then we do not need to incur the overhead + * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. + * + * mod_state() modifies the zone counter state through atomic per cpu + * operations. + * + * Overstep mode specifies how overstep should handled: + * 0 No overstepping + * 1 Overstepping half of threshold + * -1 Overstepping minus half of threshold +*/ +static inline void mod_state(struct zone *zone, + enum zone_stat_item item, int delta, int overstep_mode) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + long o, n, t, z; + + do { + z = 0; /* overflow to zone counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the following + * will apply the threshold again and therefore bring the + * counter under the threshold. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (n > t || n < -t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to zone counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + zone_page_state_add(z, zone, item); +} + +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + mod_state(zone, item, delta, 0); +} +EXPORT_SYMBOL(mod_zone_page_state); + +void inc_zone_state(struct zone *zone, enum zone_stat_item item) +{ + mod_state(zone, item, 1, 1); +} + +void inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_zone_page_state); + +void dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_zone_page_state); +#else +/* + * Use interrupt disable to serialize counter updates + */ +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_zone_page_state(zone, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_zone_page_state); + void inc_zone_state(struct zone *zone, enum zone_stat_item item) { unsigned long flags; @@ -291,6 +367,7 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); +#endif /* * Update the zone counters for one cpu. @@ -1033,7 +1110,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: - cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu)); + cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); per_cpu(vmstat_work, cpu).work.func = NULL; break; case CPU_DOWN_FAILED: |