aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c98
-rw-r--r--mm/filemap_xip.c7
-rw-r--r--mm/hugetlb.c33
-rw-r--r--mm/mmap.c3
-rw-r--r--mm/nommu.c8
-rw-r--r--mm/page-writeback.c7
-rw-r--r--mm/page_alloc.c78
-rw-r--r--mm/rmap.c1
-rw-r--r--mm/slab.c93
-rw-r--r--mm/slub.c1050
-rw-r--r--mm/sparse.c12
-rw-r--r--mm/swap.c2
-rw-r--r--mm/truncate.c3
-rw-r--r--mm/vmalloc.c7
-rw-r--r--mm/vmscan.c10
-rw-r--r--mm/vmstat.c95
16 files changed, 849 insertions, 658 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 5631d6b2a62..7b48b2ad00e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -750,6 +750,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
read_unlock_irq(&mapping->tree_lock);
return i;
}
+EXPORT_SYMBOL(find_get_pages_contig);
/**
* find_get_pages_tag - find and return pages that match @tag
@@ -778,6 +779,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
read_unlock_irq(&mapping->tree_lock);
return ret;
}
+EXPORT_SYMBOL(find_get_pages_tag);
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
@@ -1110,6 +1112,45 @@ success:
return size;
}
+/*
+ * Performs necessary checks before doing a write
+ * @iov: io vector request
+ * @nr_segs: number of segments in the iovec
+ * @count: number of bytes to write
+ * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
+ *
+ * Adjust number of segments and amount of bytes to write (nr_segs should be
+ * properly initialized first). Returns appropriate error code that caller
+ * should return or zero in case that write should be allowed.
+ */
+int generic_segment_checks(const struct iovec *iov,
+ unsigned long *nr_segs, size_t *count, int access_flags)
+{
+ unsigned long seg;
+ size_t cnt = 0;
+ for (seg = 0; seg < *nr_segs; seg++) {
+ const struct iovec *iv = &iov[seg];
+
+ /*
+ * If any segment has a negative length, or the cumulative
+ * length ever wraps negative then return -EINVAL.
+ */
+ cnt += iv->iov_len;
+ if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
+ return -EINVAL;
+ if (access_ok(access_flags, iv->iov_base, iv->iov_len))
+ continue;
+ if (seg == 0)
+ return -EFAULT;
+ *nr_segs = seg;
+ cnt -= iv->iov_len; /* This segment is no good */
+ break;
+ }
+ *count = cnt;
+ return 0;
+}
+EXPORT_SYMBOL(generic_segment_checks);
+
/**
* generic_file_aio_read - generic filesystem read routine
* @iocb: kernel I/O control block
@@ -1131,24 +1172,9 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
loff_t *ppos = &iocb->ki_pos;
count = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- count += iv->iov_len;
- if (unlikely((ssize_t)(count|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- nr_segs = seg;
- count -= iv->iov_len; /* This segment is no good */
- break;
- }
+ retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+ if (retval)
+ return retval;
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
@@ -1758,7 +1784,7 @@ struct page *read_cache_page_async(struct address_space *mapping,
retry:
page = __read_cache_page(mapping, index, filler, data);
if (IS_ERR(page))
- goto out;
+ return page;
mark_page_accessed(page);
if (PageUptodate(page))
goto out;
@@ -1776,9 +1802,9 @@ retry:
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
- page = ERR_PTR(err);
+ return ERR_PTR(err);
}
- out:
+out:
mark_page_accessed(page);
return page;
}
@@ -2218,30 +2244,14 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
- unsigned long seg;
loff_t pos;
ssize_t written;
ssize_t err;
ocount = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- ocount += iv->iov_len;
- if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- nr_segs = seg;
- ocount -= iv->iov_len; /* This segment is no good */
- break;
- }
+ err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
+ if (err)
+ return err;
count = ocount;
pos = *ppos;
@@ -2301,10 +2311,10 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
* semantics.
*/
endbyte = pos + written_buffered - written - 1;
- err = do_sync_file_range(file, pos, endbyte,
- SYNC_FILE_RANGE_WAIT_BEFORE|
- SYNC_FILE_RANGE_WRITE|
- SYNC_FILE_RANGE_WAIT_AFTER);
+ err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
+ SYNC_FILE_RANGE_WAIT_BEFORE|
+ SYNC_FILE_RANGE_WRITE|
+ SYNC_FILE_RANGE_WAIT_AFTER);
if (err == 0) {
written = written_buffered;
invalidate_mapping_pages(mapping,
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index cbb335813ec..1b49dab9b25 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -434,7 +434,6 @@ xip_truncate_page(struct address_space *mapping, loff_t from)
unsigned blocksize;
unsigned length;
struct page *page;
- void *kaddr;
BUG_ON(!mapping->a_ops->get_xip_page);
@@ -458,11 +457,7 @@ xip_truncate_page(struct address_space *mapping, loff_t from)
else
return PTR_ERR(page);
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- kunmap_atomic(kaddr, KM_USER0);
-
- flush_dcache_page(page);
+ zero_user_page(page, offset, length, KM_USER0);
return 0;
}
EXPORT_SYMBOL_GPL(xip_truncate_page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 36db012b38d..eb7180db303 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -140,6 +140,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
return page;
fail:
+ if (vma->vm_flags & VM_MAYSHARE)
+ resv_huge_pages++;
spin_unlock(&hugetlb_lock);
return NULL;
}
@@ -172,6 +174,17 @@ static int __init hugetlb_setup(char *s)
}
__setup("hugepages=", hugetlb_setup);
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+ int node;
+ unsigned int nr = 0;
+
+ for_each_node_mask(node, cpuset_current_mems_allowed)
+ nr += array[node];
+
+ return nr;
+}
+
#ifdef CONFIG_SYSCTL
static void update_and_free_page(struct page *page)
{
@@ -817,6 +830,26 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
chg = region_chg(&inode->i_mapping->private_list, from, to);
if (chg < 0)
return chg;
+ /*
+ * When cpuset is configured, it breaks the strict hugetlb page
+ * reservation as the accounting is done on a global variable. Such
+ * reservation is completely rubbish in the presence of cpuset because
+ * the reservation is not checked against page availability for the
+ * current cpuset. Application can still potentially OOM'ed by kernel
+ * with lack of free htlb page in cpuset that the task is in.
+ * Attempt to enforce strict accounting with cpuset is almost
+ * impossible (or too ugly) because cpuset is too fluid that
+ * task or memory node can be dynamically moved between cpusets.
+ *
+ * The change of semantics for shared hugetlb mapping with cpuset is
+ * undesirable. However, in order to preserve some of the semantics,
+ * we fall back to check against current free page availability as
+ * a best attempt and hopefully to minimize the impact of changing
+ * semantics that cpuset has.
+ */
+ if (chg > cpuset_mems_nr(free_huge_pages_node))
+ return -ENOMEM;
+
ret = hugetlb_acct_memory(chg);
if (ret < 0)
return ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 52646d61ff6..68b9ad2ef1d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1366,7 +1366,6 @@ unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
- unsigned long ret;
unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long);
@@ -1721,7 +1720,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
/*
* Split a vma into two pieces at address 'addr', a new vma is allocated
- * either for the first part or the the tail.
+ * either for the first part or the tail.
*/
int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long addr, int new_below)
diff --git a/mm/nommu.c b/mm/nommu.c
index 1f60194d9b9..2b16b00a5b1 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -262,6 +262,14 @@ void vunmap(void *addr)
}
/*
+ * Implement a stub for vmalloc_sync_all() if the architecture chose not to
+ * have one.
+ */
+void __attribute__((weak)) vmalloc_sync_all(void)
+{
+}
+
+/*
* sys_brk() for the most part doesn't need the global kernel
* lock, except when an application is doing something nasty
* like trying to un-brk an area that has already been mapped
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 029dfad5a23..63cd88840eb 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -683,12 +683,7 @@ retry:
}
ret = (*writepage)(page, wbc);
- if (ret) {
- if (ret == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else
- set_bit(AS_EIO, &mapping->flags);
- }
+ mapping_set_error(mapping, ret);
if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
unlock_page(page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 59164313167..f9b5d6d5f4d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -103,7 +103,7 @@ int min_free_kbytes = 1024;
unsigned long __meminitdata nr_kernel_pages;
unsigned long __meminitdata nr_all_pages;
-static unsigned long __initdata dma_reserve;
+static unsigned long __meminitdata dma_reserve;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
@@ -126,10 +126,10 @@ static unsigned long __initdata dma_reserve;
#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];
+ struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS];
+ int __meminitdata nr_nodemap_entries;
+ unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
+ unsigned long __meminitdata 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];
@@ -691,43 +691,26 @@ static void __init setup_nr_node_ids(void) {}
#ifdef CONFIG_NUMA
/*
- * Called from the slab reaper to drain pagesets on a particular node that
- * belongs to the currently executing processor.
+ * Called from the vmstat counter updater to drain pagesets of this
+ * currently executing processor on remote nodes after they have
+ * expired.
+ *
* Note that this function must be called with the thread pinned to
* a single processor.
*/
-void drain_node_pages(int nodeid)
+void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
- int i;
- enum zone_type z;
unsigned long flags;
+ int to_drain;
- for (z = 0; z < MAX_NR_ZONES; z++) {
- 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;
-
- pcp = &pset->pcp[i];
- if (pcp->count) {
- int to_drain;
-
- local_irq_save(flags);
- if (pcp->count >= pcp->batch)
- to_drain = pcp->batch;
- else
- to_drain = pcp->count;
- free_pages_bulk(zone, to_drain, &pcp->list, 0);
- pcp->count -= to_drain;
- local_irq_restore(flags);
- }
- }
- }
+ local_irq_save(flags);
+ if (pcp->count >= pcp->batch)
+ to_drain = pcp->batch;
+ else
+ to_drain = pcp->count;
+ free_pages_bulk(zone, to_drain, &pcp->list, 0);
+ pcp->count -= to_drain;
+ local_irq_restore(flags);
}
#endif
@@ -2148,11 +2131,14 @@ static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
if (process_zones(cpu))
ret = NOTIFY_BAD;
break;
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
free_zone_pagesets(cpu);
break;
default:
@@ -2179,7 +2165,7 @@ void __init setup_per_cpu_pageset(void)
#endif
-static __meminit
+static __meminit noinline
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
int i;
@@ -2267,7 +2253,7 @@ __meminit int init_currently_empty_zone(struct zone *zone,
* 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)
+static int __meminit first_active_region_index_in_nid(int nid)
{
int i;
@@ -2282,7 +2268,7 @@ static int __init first_active_region_index_in_nid(int nid)
* 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)
+static int __meminit 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)
@@ -2435,7 +2421,7 @@ static void __init account_node_boundary(unsigned int nid,
* 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,
+void __meminit get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn)
{
int i;
@@ -2460,7 +2446,7 @@ void __init get_pfn_range_for_nid(unsigned int nid,
* 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 __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
unsigned long *ignored)
{
@@ -2488,7 +2474,7 @@ unsigned long __init zone_spanned_pages_in_node(int nid,
* 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 __meminit __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
@@ -2548,7 +2534,7 @@ unsigned long __init absent_pages_in_range(unsigned long start_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 __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_type,
unsigned long *ignored)
{
@@ -2584,7 +2570,7 @@ static inline unsigned long zone_absent_pages_in_node(int nid,
#endif
-static void __init calculate_node_totalpages(struct pglist_data *pgdat,
+static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
unsigned long realtotalpages, totalpages = 0;
@@ -2692,7 +2678,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
}
}
-static void __init alloc_node_mem_map(struct pglist_data *pgdat)
+static void __meminit alloc_node_mem_map(struct pglist_data *pgdat)
{
/* Skip empty nodes */
if (!pgdat->node_spanned_pages)
@@ -3012,7 +2998,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
{
int cpu = (unsigned long)hcpu;
- if (action == CPU_DEAD) {
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
local_irq_disable();
__drain_pages(cpu);
vm_events_fold_cpu(cpu);
diff --git a/mm/rmap.c b/mm/rmap.c
index 75a32be64a2..304f51985c7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -505,6 +505,7 @@ int page_mkclean(struct page *page)
return ret;
}
+EXPORT_SYMBOL_GPL(page_mkclean);
/**
* page_set_anon_rmap - setup new anonymous rmap
diff --git a/mm/slab.c b/mm/slab.c
index 5920a412b37..944b20581f8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -148,10 +148,11 @@
* Usually, the kmalloc caches are cache_line_size() aligned, except when
* DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
- * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that.
- * Note that this flag disables some debug features.
+ * alignment larger than the alignment of a 64-bit integer.
+ * ARCH_KMALLOC_MINALIGN allows that.
+ * Note that increasing this value may disable some debug features.
*/
-#define ARCH_KMALLOC_MINALIGN 0
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
#endif
#ifndef ARCH_SLAB_MINALIGN
@@ -536,19 +537,22 @@ static int obj_size(struct kmem_cache *cachep)
return cachep->obj_size;
}
-static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
+static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
- return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD);
+ return (unsigned long long*) (objp + obj_offset(cachep) -
+ sizeof(unsigned long long));
}
-static unsigned long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
+static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
if (cachep->flags & SLAB_STORE_USER)
- return (unsigned long *)(objp + cachep->buffer_size -
- 2 * BYTES_PER_WORD);
- return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD);
+ return (unsigned long long *)(objp + cachep->buffer_size -
+ sizeof(unsigned long long) -
+ BYTES_PER_WORD);
+ return (unsigned long long *) (objp + cachep->buffer_size -
+ sizeof(unsigned long long));
}
static void **dbg_userword(struct kmem_cache *cachep, void *objp)
@@ -561,8 +565,8 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
#define obj_offset(x) 0
#define obj_size(cachep) (cachep->buffer_size)
-#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long *)NULL;})
-#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long *)NULL;})
+#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
+#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;})
#endif
@@ -924,12 +928,6 @@ static void next_reap_node(void)
{
int node = __get_cpu_var(reap_node);
- /*
- * Also drain per cpu pages on remote zones
- */
- if (node != numa_node_id())
- drain_node_pages(node);
-
node = next_node(node, node_online_map);
if (unlikely(node >= MAX_NUMNODES))
node = first_node(node_online_map);
@@ -1182,8 +1180,11 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
int memsize = sizeof(struct kmem_list3);
switch (action) {
- case CPU_UP_PREPARE:
+ case CPU_LOCK_ACQUIRE:
mutex_lock(&cache_chain_mutex);
+ break;
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
/*
* We need to do this right in the beginning since
* alloc_arraycache's are going to use this list.
@@ -1270,17 +1271,28 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
}
break;
case CPU_ONLINE:
- mutex_unlock(&cache_chain_mutex);
+ case CPU_ONLINE_FROZEN:
start_cpu_timer(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_DOWN_PREPARE:
- mutex_lock(&cache_chain_mutex);
- break;
- case CPU_DOWN_FAILED:
- mutex_unlock(&cache_chain_mutex);
- break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ /*
+ * Shutdown cache reaper. Note that the cache_chain_mutex is
+ * held so that if cache_reap() is invoked it cannot do
+ * anything expensive but will only modify reap_work
+ * and reschedule the timer.
+ */
+ cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+ /* Now the cache_reaper is guaranteed to be not running. */
+ per_cpu(reap_work, cpu).work.func = NULL;
+ break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ start_cpu_timer(cpu);
+ break;
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
/*
* Even if all the cpus of a node are down, we don't free the
* kmem_list3 of any cache. This to avoid a race between
@@ -1292,6 +1304,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
/* fall thru */
#endif
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
struct array_cache *shared;
@@ -1350,6 +1363,8 @@ free_array_cache:
continue;
drain_freelist(cachep, l3, l3->free_objects);
}
+ break;
+ case CPU_LOCK_RELEASE:
mutex_unlock(&cache_chain_mutex);
break;
}
@@ -1776,7 +1791,7 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
char *realobj;
if (cachep->flags & SLAB_RED_ZONE) {
- printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n",
+ printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
*dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
@@ -2239,7 +2254,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
* is greater than BYTES_PER_WORD.
*/
if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
- ralign = BYTES_PER_WORD;
+ ralign = __alignof__(unsigned long long);
/* 2) arch mandated alignment */
if (ralign < ARCH_SLAB_MINALIGN) {
@@ -2250,7 +2265,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
ralign = align;
}
/* disable debug if necessary */
- if (ralign > BYTES_PER_WORD)
+ if (ralign > __alignof__(unsigned long long))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
@@ -2271,8 +2286,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
- cachep->obj_offset += BYTES_PER_WORD;
- size += 2 * BYTES_PER_WORD;
+ cachep->obj_offset += sizeof(unsigned long long);
+ size += 2 * sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
@@ -2833,7 +2848,7 @@ static void kfree_debugcheck(const void *objp)
static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
{
- unsigned long redzone1, redzone2;
+ unsigned long long redzone1, redzone2;
redzone1 = *dbg_redzone1(cache, obj);
redzone2 = *dbg_redzone2(cache, obj);
@@ -2849,7 +2864,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
else
slab_error(cache, "memory outside object was overwritten");
- printk(KERN_ERR "%p: redzone 1:0x%lx, redzone 2:0x%lx.\n",
+ printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n",
obj, redzone1, redzone2);
}
@@ -3065,7 +3080,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
slab_error(cachep, "double free, or memory outside"
" object was overwritten");
printk(KERN_ERR
- "%p: redzone 1:0x%lx, redzone 2:0x%lx\n",
+ "%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
@@ -3738,7 +3753,6 @@ EXPORT_SYMBOL(__kmalloc);
/**
* krealloc - reallocate memory. The contents will remain unchanged.
- *
* @p: object to reallocate memory for.
* @new_size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
@@ -4136,7 +4150,6 @@ next:
check_irq_on();
mutex_unlock(&cache_chain_mutex);
next_reap_node();
- refresh_cpu_vm_stats(smp_processor_id());
out:
/* Set up the next iteration */
schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
@@ -4428,16 +4441,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
static void show_symbol(struct seq_file *m, unsigned long address)
{
#ifdef CONFIG_KALLSYMS
- char *modname;
- const char *name;
unsigned long offset, size;
- char namebuf[KSYM_NAME_LEN+1];
-
- name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+ char modname[MODULE_NAME_LEN + 1], name[KSYM_NAME_LEN + 1];
- if (name) {
+ if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
- if (modname)
+ if (modname[0])
seq_printf(m, " [%s]", modname);
return;
}
diff --git a/mm/slub.c b/mm/slub.c
index 5db3da5a60b..bd2efae02bc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -66,11 +66,11 @@
* SLUB assigns one slab for allocation to each processor.
* Allocations only occur from these slabs called cpu slabs.
*
- * Slabs with free elements are kept on a partial list.
- * There is no list for full slabs. If an object in a full slab is
+ * Slabs with free elements are kept on a partial list and during regular
+ * operations no list for full slabs is used. If an object in a full slab is
* freed then the slab will show up again on the partial lists.
- * Otherwise there is no need to track full slabs unless we have to
- * track full slabs for debugging purposes.
+ * We track full slabs for debugging purposes though because otherwise we
+ * cannot scan all objects.
*
* Slabs are freed when they become empty. Teardown and setup is
* minimal so we rely on the page allocators per cpu caches for
@@ -87,13 +87,36 @@
* the fast path.
*/
+static inline int SlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ return PageError(page);
+#else
+ return 0;
+#endif
+}
+
+static inline void SetSlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ SetPageError(page);
+#endif
+}
+
+static inline void ClearSlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ ClearPageError(page);
+#endif
+}
+
/*
* Issues still to be resolved:
*
* - The per cpu array is updated for each new slab and and is a remote
* cacheline for most nodes. This could become a bouncing cacheline given
- * enough frequent updates. There are 16 pointers in a cacheline.so at
- * max 16 cpus could compete. Likely okay.
+ * enough frequent updates. There are 16 pointers in a cacheline, so at
+ * max 16 cpus could compete for the cacheline which may be okay.
*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
@@ -137,6 +160,7 @@
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
+
/*
* Set of flags that will prevent slab merging
*/
@@ -157,6 +181,11 @@
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000 /* Poison object */
+/* Not all arches define cache_line_size */
+#ifndef cache_line_size
+#define cache_line_size() L1_CACHE_BYTES
+#endif
+
static int kmem_size = sizeof(struct kmem_cache);
#ifdef CONFIG_SMP
@@ -166,7 +195,7 @@ static struct notifier_block slab_notifier;
static enum {
DOWN, /* No slab functionality available */
PARTIAL, /* kmem_cache_open() works but kmalloc does not */
- UP, /* Everything works */
+ UP, /* Everything works but does not show up in sysfs */
SYSFS /* Sysfs up */
} slab_state = DOWN;
@@ -174,7 +203,19 @@ static enum {
static DECLARE_RWSEM(slub_lock);
LIST_HEAD(slab_caches);
-#ifdef CONFIG_SYSFS
+/*
+ * Tracking user of a slab.
+ */
+struct track {
+ void *addr; /* Called from address */
+ int cpu; /* Was running on cpu */
+ int pid; /* Pid context */
+ unsigned long when; /* When did the operation occur */
+};
+
+enum track_item { TRACK_ALLOC, TRACK_FREE };
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
static void sysfs_slab_remove(struct kmem_cache *);
@@ -202,6 +243,63 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
#endif
}
+static inline int check_valid_pointer(struct kmem_cache *s,
+ struct page *page, const void *object)
+{
+ void *base;
+
+ if (!object)
+ return 1;
+
+ base = page_address(page);
+ if (object < base || object >= base + s->objects * s->size ||
+ (object - base) % s->size) {
+ return 0;
+ }
+
+ return 1;
+}
+
+/*
+ * Slow version of get and set free pointer.
+ *
+ * This version requires touching the cache lines of kmem_cache which
+ * we avoid to do in the fast alloc free paths. There we obtain the offset
+ * from the page struct.
+ */
+static inline void *get_freepointer(struct kmem_cache *s, void *object)
+{
+ return *(void **)(object + s->offset);
+}
+
+static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
+{
+ *(void **)(object + s->offset) = fp;
+}
+
+/* Loop over all objects in a slab */
+#define for_each_object(__p, __s, __addr) \
+ for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+ __p += (__s)->size)
+
+/* Scan freelist */
+#define for_each_free_object(__p, __s, __free) \
+ for (__p = (__free); __p; __p = get_freepointer((__s), __p))
+
+/* Determine object index from a given position */
+static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
+{
+ return (p - addr) / s->size;
+}
+
+#ifdef CONFIG_SLUB_DEBUG
+/*
+ * Debug settings:
+ */
+static int slub_debug;
+
+static char *slub_debug_slabs;
+
/*
* Object debugging
*/
@@ -237,35 +335,6 @@ static void print_section(char *text, u8 *addr, unsigned int length)
}
}
-/*
- * Slow version of get and set free pointer.
- *
- * This requires touching the cache lines of kmem_cache.
- * The offset can also be obtained from the page. In that
- * case it is in the cacheline that we already need to touch.
- */
-static void *get_freepointer(struct kmem_cache *s, void *object)
-{
- return *(void **)(object + s->offset);
-}
-
-static void set_freepointer(struct kmem_cache *s, void *object, void *fp)
-{
- *(void **)(object + s->offset) = fp;
-}
-
-/*
- * Tracking user of a slab.
- */
-struct track {
- void *addr; /* Called from address */
- int cpu; /* Was running on cpu */
- int pid; /* Pid context */
- unsigned long when; /* When did the operation occur */
-};
-
-enum track_item { TRACK_ALLOC, TRACK_FREE };
-
static struct track *get_track(struct kmem_cache *s, void *object,
enum track_item alloc)
{
@@ -400,24 +469,6 @@ static int check_bytes(u8 *start, unsigned int value, unsigned int bytes)
return 1;
}
-
-static int check_valid_pointer(struct kmem_cache *s, struct page *page,
- void *object)
-{
- void *base;
-
- if (!object)
- return 1;
-
- base = page_address(page);
- if (object < base || object >= base + s->objects * s->size ||
- (object - base) % s->size) {
- return 0;
- }
-
- return 1;
-}
-
/*
* Object layout:
*
@@ -425,26 +476,34 @@ static int check_valid_pointer(struct kmem_cache *s, struct page *page,
* Bytes of the object to be managed.
* If the freepointer may overlay the object then the free
* pointer is the first word of the object.
+ *
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
* object + s->objsize
* Padding to reach word boundary. This is also used for Redzoning.
- * Padding is extended to word size if Redzoning is enabled
- * and objsize == inuse.
+ * Padding is extended by another word if Redzoning is enabled and
+ * objsize == inuse.
+ *
* We fill with 0xbb (RED_INACTIVE) for inactive objects and with
* 0xcc (RED_ACTIVE) for objects in use.
*
* object + s->inuse
+ * Meta data starts here.
+ *
* A. Free pointer (if we cannot overwrite object on free)
* B. Tracking data for SLAB_STORE_USER
- * C. Padding to reach required alignment boundary
- * Padding is done using 0x5a (POISON_INUSE)
+ * C. Padding to reach required alignment boundary or at mininum
+ * one word if debuggin is on to be able to detect writes
+ * before the word boundary.
+ *
+ * Padding is done using 0x5a (POISON_INUSE)
*
* object + s->size
+ * Nothing is used beyond s->size.
*
- * If slabcaches are merged then the objsize and inuse boundaries are to
- * be ignored. And therefore no slab options that rely on these boundaries
+ * If slabcaches are merged then the objsize and inuse boundaries are mostly
+ * ignored. And therefore no slab options that rely on these boundaries
* may be used with merged slabcaches.
*/
@@ -570,8 +629,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
/*
* No choice but to zap it and thus loose the remainder
* of the free objects in this slab. May cause
- * another error because the object count maybe
- * wrong now.
+ * another error because the object count is now wrong.
*/
set_freepointer(s, p, NULL);
return 0;
@@ -611,9 +669,8 @@ static int check_slab(struct kmem_cache *s, struct page *page)
}
/*
- * Determine if a certain object on a page is on the freelist and
- * therefore free. Must hold the slab lock for cpu slabs to
- * guarantee that the chains are consistent.
+ * Determine if a certain object on a page is on the freelist. Must hold the
+ * slab lock to guarantee that the chains are in a consistent state.
*/
static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
{
@@ -659,7 +716,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
}
/*
- * Tracking of fully allocated slabs for debugging
+ * Tracking of fully allocated slabs for debugging purposes.
*/
static void add_full(struct kmem_cache_node *n, struct page *page)
{
@@ -710,7 +767,7 @@ bad:
/*
* If this is a slab page then lets do the best we can
* to avoid issues in the future. Marking all objects
- * as used avoids touching the remainder.
+ * as used avoids touching the remaining objects.
*/
printk(KERN_ERR "@@@ SLUB: %s slab 0x%p. Marking all objects used.\n",
s->name, page);
@@ -764,6 +821,113 @@ fail:
return 0;
}
+static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc)
+{
+ if (s->flags & SLAB_TRACE) {
+ printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
+ s->name,
+ alloc ? "alloc" : "free",
+ object, page->inuse,
+ page->freelist);
+
+ if (!alloc)
+ print_section("Object", (void *)object, s->objsize);
+
+ dump_stack();
+ }
+}
+
+static int __init setup_slub_debug(char *str)
+{
+ if (!str || *str != '=')
+ slub_debug = DEBUG_DEFAULT_FLAGS;
+ else {
+ str++;
+ if (*str == 0 || *str == ',')
+ slub_debug = DEBUG_DEFAULT_FLAGS;
+ else
+ for( ;*str && *str != ','; str++)
+ switch (*str) {
+ case 'f' : case 'F' :
+ slub_debug |= SLAB_DEBUG_FREE;
+ break;
+ case 'z' : case 'Z' :
+ slub_debug |= SLAB_RED_ZONE;
+ break;
+ case 'p' : case 'P' :
+ slub_debug |= SLAB_POISON;
+ break;
+ case 'u' : case 'U' :
+ slub_debug |= SLAB_STORE_USER;
+ break;
+ case 't' : case 'T' :
+ slub_debug |= SLAB_TRACE;
+ break;
+ default:
+ printk(KERN_ERR "slub_debug option '%c' "
+ "unknown. skipped\n",*str);
+ }
+ }
+
+ if (*str == ',')
+ slub_debug_slabs = str + 1;
+ return 1;
+}
+
+__setup("slub_debug", setup_slub_debug);
+
+static void kmem_cache_open_debug_check(struct kmem_cache *s)
+{
+ /*
+ * The page->offset field is only 16 bit wide. This is an offset
+ * in units of words from the beginning of an object. If the slab
+ * size is bigger then we cannot move the free pointer behind the
+ * object anymore.
+ *
+ * On 32 bit platforms the limit is 256k. On 64bit platforms
+ * the limit is 512k.
+ *
+ * Debugging or ctor/dtors may create a need to move the free
+ * pointer. Fail if this happens.
+ */
+ if (s->size >= 65535 * sizeof(void *)) {
+ BUG_ON(s->flags & (SLAB_RED_ZONE | SLAB_POISON |
+ SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
+ BUG_ON(s->ctor || s->dtor);
+ }
+ else
+ /*
+ * Enable debugging if selected on the kernel commandline.
+ */
+ if (slub_debug && (!slub_debug_slabs ||
+ strncmp(slub_debug_slabs, s->name,
+ strlen(slub_debug_slabs)) == 0))
+ s->flags |= slub_debug;
+}
+#else
+
+static inline int alloc_object_checks(struct kmem_cache *s,
+ struct page *page, void *object) { return 0; }
+
+static inline int free_object_checks(struct kmem_cache *s,
+ struct page *page, void *object) { return 0; }
+
+static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
+static inline void remove_full(struct kmem_cache *s, struct page *page) {}
+static inline void trace(struct kmem_cache *s, struct page *page,
+ void *object, int alloc) {}
+static inline void init_object(struct kmem_cache *s,
+ void *object, int active) {}
+static inline void init_tracking(struct kmem_cache *s, void *object) {}
+static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
+ { return 1; }
+static inline int check_object(struct kmem_cache *s, struct page *page,
+ void *object, int active) { return 1; }
+static inline void set_track(struct kmem_cache *s, void *object,
+ enum track_item alloc, void *addr) {}
+static inline void kmem_cache_open_debug_check(struct kmem_cache *s) {}
+#define slub_debug 0
+#endif
/*
* Slab allocation and freeing
*/
@@ -797,7 +961,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
static void setup_object(struct kmem_cache *s, struct page *page,
void *object)
{
- if (PageError(page)) {
+ if (SlabDebug(page)) {
init_object(s, object, 0);
init_tracking(s, object);
}
@@ -832,7 +996,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
page->flags |= 1 << PG_slab;
if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
SLAB_STORE_USER | SLAB_TRACE))
- page->flags |= 1 << PG_error;
+ SetSlabDebug(page);
start = page_address(page);
end = start + s->objects * s->size;
@@ -841,7 +1005,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
memset(start, POISON_INUSE, PAGE_SIZE << s->order);
last = start;
- for (p = start + s->size; p < end; p += s->size) {
+ for_each_object(p, s, start) {
setup_object(s, page, last);
set_freepointer(s, last, p);
last = p;
@@ -861,13 +1025,11 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
{
int pages = 1 << s->order;
- if (unlikely(PageError(page) || s->dtor)) {
- void *start = page_address(page);
- void *end = start + (pages << PAGE_SHIFT);
+ if (unlikely(SlabDebug(page) || s->dtor)) {
void *p;
slab_pad_check(s, page);
- for (p = start; p <= end - s->size; p += s->size) {
+ for_each_object(p, s, page_address(page)) {
if (s->dtor)
s->dtor(p, s, 0);
check_object(s, page, p, 0);
@@ -910,7 +1072,8 @@ static void discard_slab(struct kmem_cache *s, struct page *page)
atomic_long_dec(&n->nr_slabs);
reset_page_mapcount(page);
- page->flags &= ~(1 << PG_slab | 1 << PG_error);
+ ClearSlabDebug(page);
+ __ClearPageSlab(page);
free_slab(s, page);
}
@@ -966,9 +1129,9 @@ static void remove_partial(struct kmem_cache *s,
}
/*
- * Lock page and remove it from the partial list
+ * Lock slab and remove from the partial list.
*
- * Must hold list_lock
+ * Must hold list_lock.
*/
static int lock_and_del_slab(struct kmem_cache_node *n, struct page *page)
{
@@ -981,7 +1144,7 @@ static int lock_and_del_slab(struct kmem_cache_node *n, struct page *page)
}
/*
- * Try to get a partial slab from a specific node
+ * Try to allocate a partial slab from a specific node.
*/
static struct page *get_partial_node(struct kmem_cache_node *n)
{
@@ -990,7 +1153,8 @@ static struct page *get_partial_node(struct kmem_cache_node *n)
/*
* Racy check. If we mistakenly see no partial slabs then we
* just allocate an empty slab. If we mistakenly try to get a
- * partial slab then get_partials() will return NULL.
+ * partial slab and there is none available then get_partials()
+ * will return NULL.
*/
if (!n || !n->nr_partial)
return NULL;
@@ -1006,8 +1170,7 @@ out:
}
/*
- * Get a page from somewhere. Search in increasing NUMA
- * distances.
+ * Get a page from somewhere. Search in increasing NUMA distances.
*/
static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
{
@@ -1017,24 +1180,22 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
struct page *page;
/*
- * The defrag ratio allows to configure the tradeoffs between
- * inter node defragmentation and node local allocations.
- * A lower defrag_ratio increases the tendency to do local
- * allocations instead of scanning throught the partial
- * lists on other nodes.
- *
- * If defrag_ratio is set to 0 then kmalloc() always
- * returns node local objects. If its higher then kmalloc()
- * may return off node objects in order to avoid fragmentation.
+ * The defrag ratio allows a configuration of the tradeoffs between
+ * inter node defragmentation and node local allocations. A lower
+ * defrag_ratio increases the tendency to do local allocations
+ * instead of attempting to obtain partial slabs from other nodes.
*
- * A higher ratio means slabs may be taken from other nodes
- * thus reducing the number of partial slabs on those nodes.
+ * If the defrag_ratio is set to 0 then kmalloc() always
+ * returns node local objects. If the ratio is higher then kmalloc()
+ * may return off node objects because partial slabs are obtained
+ * from other nodes and filled up.
*
* If /sys/slab/xx/defrag_ratio is set to 100 (which makes
- * defrag_ratio = 1000) then every (well almost) allocation
- * will first attempt to defrag slab caches on other nodes. This
- * means scanning over all nodes to look for partial slabs which
- * may be a bit expensive to do on every slab allocation.
+ * defrag_ratio = 1000) then every (well almost) allocation will
+ * first attempt to defrag slab caches on other nodes. This means
+ * scanning over all nodes to look for partial slabs which may be
+ * expensive if we do it every time we are trying to find a slab
+ * with available objects.
*/
if (!s->defrag_ratio || get_cycles() % 1024 > s->defrag_ratio)
return NULL;
@@ -1087,18 +1248,19 @@ static void putback_slab(struct kmem_cache *s, struct page *page)
if (page->freelist)
add_partial(n, page);
- else if (PageError(page) && (s->flags & SLAB_STORE_USER))
+ else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
add_full(n, page);
slab_unlock(page);
} else {
if (n->nr_partial < MIN_PARTIAL) {
/*
- * Adding an empty page to the partial slabs in order
- * to avoid page allocator overhead. This page needs to
- * come after all the others that are not fully empty
- * in order to make sure that we do maximum
- * defragmentation.
+ * Adding an empty slab to the partial slabs in order
+ * to avoid page allocator overhead. This slab needs
+ * to come after the other slabs with objects in
+ * order to fill them up. That way the size of the
+ * partial list stays small. kmem_cache_shrink can
+ * reclaim empty slabs from the partial list.
*/
add_partial_tail(n, page);
slab_unlock(page);
@@ -1166,11 +1328,11 @@ static void flush_all(struct kmem_cache *s)
* 1. The page struct
* 2. The first cacheline of the object to be allocated.
*
- * The only cache lines that are read (apart from code) is the
+ * The only other cache lines that are read (apart from code) is the
* per cpu array in the kmem_cache struct.
*
* Fastpath is not possible if we need to get a new slab or have
- * debugging enabled (which means all slabs are marked with PageError)
+ * debugging enabled (which means all slabs are marked with SlabDebug)
*/
static void *slab_alloc(struct kmem_cache *s,
gfp_t gfpflags, int node, void *addr)
@@ -1193,7 +1355,7 @@ redo:
object = page->freelist;
if (unlikely(!object))
goto another_slab;
- if (unlikely(PageError(page)))
+ if (unlikely(SlabDebug(page)))
goto debug;
have_object:
@@ -1220,9 +1382,11 @@ have_slab:
cpu = smp_processor_id();
if (s->cpu_slab[cpu]) {
/*
- * Someone else populated the cpu_slab while we enabled
- * interrupts, or we have got scheduled on another cpu.
- * The page may not be on the requested node.
+ * Someone else populated the cpu_slab while we
+ * enabled interrupts, or we have gotten scheduled
+ * on another cpu. The page may not be on the
+ * requested node even if __GFP_THISNODE was
+ * specified. So we need to recheck.
*/
if (node == -1 ||
page_to_nid(s->cpu_slab[cpu]) == node) {
@@ -1235,7 +1399,7 @@ have_slab:
slab_lock(page);
goto redo;
}
- /* Dump the current slab */
+ /* New slab does not fit our expectations */
flush_slab(s, s->cpu_slab[cpu], cpu);
}
slab_lock(page);
@@ -1248,12 +1412,7 @@ debug:
goto another_slab;
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s alloc 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- dump_stack();
- }
+ trace(s, page, object, 1);
init_object(s, object, 1);
goto have_object;
}
@@ -1276,7 +1435,8 @@ EXPORT_SYMBOL(kmem_cache_alloc_node);
* The fastpath only writes the cacheline of the page struct and the first
* cacheline of the object.
*
- * No special cachelines need to be read
+ * We read the cpu_slab cacheline to check if the slab is the per cpu
+ * slab for this processor.
*/
static void slab_free(struct kmem_cache *s, struct page *page,
void *x, void *addr)
@@ -1288,7 +1448,7 @@ static void slab_free(struct kmem_cache *s, struct page *page,
local_irq_save(flags);
slab_lock(page);
- if (unlikely(PageError(page)))
+ if (unlikely(SlabDebug(page)))
goto debug;
checks_ok:
prior = object[page->offset] = page->freelist;
@@ -1321,7 +1481,7 @@ out_unlock:
slab_empty:
if (prior)
/*
- * Slab on the partial list.
+ * Slab still on the partial list.
*/
remove_partial(s, page);
@@ -1337,13 +1497,7 @@ debug:
remove_full(s, page);
if (s->flags & SLAB_STORE_USER)
set_track(s, x, TRACK_FREE, addr);
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s free 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- print_section("Object", (void *)object, s->objsize);
- dump_stack();
- }
+ trace(s, page, object, 0);
init_object(s, object, 0);
goto checks_ok;
}
@@ -1370,22 +1524,16 @@ static struct page *get_object_page(const void *x)
}
/*
- * kmem_cache_open produces objects aligned at "size" and the first object
- * is placed at offset 0 in the slab (We have no metainformation on the
- * slab, all slabs are in essence "off slab").
- *
- * In order to get the desired alignment one just needs to align the
- * size.
+ * 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
+ * get the required alignment by putting one properly sized object after
+ * another.
*
* Notice that the allocation order determines the sizes of the per cpu
* caches. Each processor has always one slab available for allocations.
* Increasing the allocation order reduces the number of times that slabs
- * must be moved on and off the partial lists and therefore may influence
+ * must be moved on and off the partial lists and is therefore a factor in
* locking overhead.
- *
- * The offset is used to relocate the free list link in each object. It is
- * therefore possible to move the free list link behind the object. This
- * is necessary for RCU to work properly and also useful for debugging.
*/
/*
@@ -1396,76 +1544,110 @@ static struct page *get_object_page(const void *x)
*/
static int slub_min_order;
static int slub_max_order = DEFAULT_MAX_ORDER;
-
-/*
- * Minimum number of objects per slab. This is necessary in order to
- * reduce locking overhead. Similar to the queue size in SLAB.
- */
static int slub_min_objects = DEFAULT_MIN_OBJECTS;
/*
* Merge control. If this is set then no merging of slab caches will occur.
+ * (Could be removed. This was introduced to pacify the merge skeptics.)
*/
static int slub_nomerge;
/*
- * Debug settings:
- */
-static int slub_debug;
-
-static char *slub_debug_slabs;
-
-/*
* Calculate the order of allocation given an slab object size.
*
- * The order of allocation has significant impact on other elements
- * of the system. Generally order 0 allocations should be preferred
- * since they do not cause fragmentation in the page allocator. Larger
- * objects may have problems with order 0 because there may be too much
- * space left unused in a slab. We go to a higher order if more than 1/8th
- * of the slab would be wasted.
+ * The order of allocation has significant impact on performance and other
+ * system components. Generally order 0 allocations should be preferred since
+ * order 0 does not cause fragmentation in the page allocator. Larger objects
+ * be problematic to put into order 0 slabs because there may be too much
+ * unused space left. We go to a higher order if more than 1/8th of the slab
+ * would be wasted.
*
- * In order to reach satisfactory performance we must ensure that
- * a minimum number of objects is in one slab. Otherwise we may
- * generate too much activity on the partial lists. This is less a
- * concern for large slabs though. slub_max_order specifies the order
- * where we begin to stop considering the number of objects in a slab.
+ * In order to reach satisfactory performance we must ensure that a minimum
+ * number of objects is in one slab. Otherwise we may generate too much
+ * activity on the partial lists which requires taking the list_lock. This is
+ * less a concern for large slabs though which are rarely used.
*
- * Higher order allocations also allow the placement of more objects
- * in a slab and thereby reduce object handling overhead. If the user
- * has requested a higher mininum order then we start with that one
- * instead of zero.
+ * slub_max_order specifies the order where we begin to stop considering the
+ * number of objects in a slab as critical. If we reach slub_max_order then
+ * we try to keep the page order as low as possible. So we accept more waste
+ * of space in favor of a small page order.
+ *
+ * Higher order allocations also allow the placement of more objects in a
+ * slab and thereby reduce object handling overhead. If the user has
+ * requested a higher mininum order then we start with that one instead of
+ * the smallest order which will fit the object.
*/
-static int calculate_order(int size)
+static inline int slab_order(int size, int min_objects,
+ int max_order, int fract_leftover)
{
int order;
int rem;
- for (order = max(slub_min_order, fls(size - 1) - PAGE_SHIFT);
- order < MAX_ORDER; order++) {
- unsigned long slab_size = PAGE_SIZE << order;
+ for (order = max(slub_min_order,
+ fls(min_objects * size - 1) - PAGE_SHIFT);
+ order <= max_order; order++) {
- if (slub_max_order > order &&
- slab_size < slub_min_objects * size)
- continue;
+ unsigned long slab_size = PAGE_SIZE << order;
- if (slab_size < size)
+ if (slab_size < min_objects * size)
continue;
rem = slab_size % size;
- if (rem <= (PAGE_SIZE << order) / 8)
+ if (rem <= slab_size / fract_leftover)
break;
}
- if (order >= MAX_ORDER)
- return -E2BIG;
+
return order;
}
+static inline int calculate_order(int size)
+{
+ int order;
+ int min_objects;
+ int fraction;
+
+ /*
+ * Attempt to find best configuration for a slab. This
+ * works by first attempting to generate a layout with
+ * the best configuration and backing off gradually.
+ *
+ * First we reduce the acceptable waste in a slab. Then
+ * we reduce the minimum objects required in a slab.
+ */
+ min_objects = slub_min_objects;
+ while (min_objects > 1) {
+ fraction = 8;
+ while (fraction >= 4) {
+ order = slab_order(size, min_objects,
+ slub_max_order, fraction);
+ if (order <= slub_max_order)
+ return order;
+ fraction /= 2;
+ }
+ min_objects /= 2;
+ }
+
+ /*
+ * We were unable to place multiple objects in a slab. Now
+ * lets see if we can place a single object there.
+ */
+ order = slab_order(size, 1, slub_max_order, 1);
+ if (order <= slub_max_order)
+ return order;
+
+ /*
+ * Doh this slab cannot be placed using slub_max_order.
+ */
+ order = slab_order(size, 1, MAX_ORDER, 1);
+ if (order <= MAX_ORDER)
+ return order;
+ return -ENOSYS;
+}
+
/*
- * Function to figure out which alignment to use from the
- * various ways of specifying it.
+ * Figure out what the alignment of the objects will be.
*/
static unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size)
@@ -1480,8 +1662,8 @@ static unsigned long calculate_alignment(unsigned long flags,
* then use it.
*/
if ((flags & SLAB_HWCACHE_ALIGN) &&
- size > L1_CACHE_BYTES / 2)
- return max_t(unsigned long, align, L1_CACHE_BYTES);
+ size > cache_line_size() / 2)
+ return max_t(unsigned long, align, cache_line_size());
if (align < ARCH_SLAB_MINALIGN)
return ARCH_SLAB_MINALIGN;
@@ -1619,22 +1801,23 @@ static int calculate_sizes(struct kmem_cache *s)
*/
size = ALIGN(size, sizeof(void *));
+#ifdef CONFIG_SLUB_DEBUG
/*
- * If we are redzoning then check if there is some space between the
+ * If we are Redzoning then check if there is some space between the
* end of the object and the free pointer. If not then add an
- * additional word, so that we can establish a redzone between
- * the object and the freepointer to be able to check for overwrites.
+ * additional word to have some bytes to store Redzone information.
*/
if ((flags & SLAB_RED_ZONE) && size == s->objsize)
size += sizeof(void *);
+#endif
/*
- * With that we have determined how much of the slab is in actual
- * use by the object. This is the potential offset to the free
- * pointer.
+ * With that we have determined the number of bytes in actual use
+ * by the object. This is the potential offset to the free pointer.
*/
s->inuse = size;
+#ifdef CONFIG_SLUB_DEBUG
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
s->ctor || s->dtor)) {
/*
@@ -1656,7 +1839,7 @@ static int calculate_sizes(struct kmem_cache *s)
*/
size += 2 * sizeof(struct track);
- if (flags & DEBUG_DEFAULT_FLAGS)
+ if (flags & SLAB_RED_ZONE)
/*
* Add some empty padding so that we can catch
* overwrites from earlier objects rather than let
@@ -1665,10 +1848,12 @@ static int calculate_sizes(struct kmem_cache *s)
* of the object.
*/
size += sizeof(void *);
+#endif
+
/*
* Determine the alignment based on various parameters that the
- * user specified (this is unecessarily complex due to the attempt
- * to be compatible with SLAB. Should be cleaned up some day).
+ * user specified and the dynamic determination of cache line size
+ * on bootup.
*/
align = calculate_alignment(flags, align, s->objsize);
@@ -1700,23 +1885,6 @@ static int calculate_sizes(struct kmem_cache *s)
}
-static int __init finish_bootstrap(void)
-{
- struct list_head *h;
- int err;
-
- slab_state = SYSFS;
-
- list_for_each(h, &slab_caches) {
- struct kmem_cache *s =
- container_of(h, struct kmem_cache, list);
-
- err = sysfs_slab_add(s);
- BUG_ON(err);
- }
- return 0;
-}
-
static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
const char *name, size_t size,
size_t align, unsigned long flags,
@@ -1730,32 +1898,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
s->objsize = size;
s->flags = flags;
s->align = align;
-
- /*
- * The page->offset field is only 16 bit wide. This is an offset
- * in units of words from the beginning of an object. If the slab
- * size is bigger then we cannot move the free pointer behind the
- * object anymore.
- *
- * On 32 bit platforms the limit is 256k. On 64bit platforms
- * the limit is 512k.
- *
- * Debugging or ctor/dtors may create a need to move the free
- * pointer. Fail if this happens.
- */
- if (s->size >= 65535 * sizeof(void *)) {
- BUG_ON(flags & (SLAB_RED_ZONE | SLAB_POISON |
- SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
- BUG_ON(ctor || dtor);
- }
- else
- /*
- * Enable debugging if selected on the kernel commandline.
- */
- if (slub_debug && (!slub_debug_slabs ||
- strncmp(slub_debug_slabs, name,
- strlen(slub_debug_slabs)) == 0))
- s->flags |= slub_debug;
+ kmem_cache_open_debug_check(s);
if (!calculate_sizes(s))
goto error;
@@ -1783,7 +1926,6 @@ EXPORT_SYMBOL(kmem_cache_open);
int kmem_ptr_validate(struct kmem_cache *s, const void *object)
{
struct page * page;
- void *addr;
page = get_object_page(object);
@@ -1791,13 +1933,7 @@ int kmem_ptr_validate(struct kmem_cache *s, const void *object)
/* No slab or wrong slab */
return 0;
- addr = page_address(page);
- if (object < addr || object >= addr + s->objects * s->size)
- /* Out of bounds */
- return 0;
-
- if ((object - addr) % s->size)
- /* Improperly aligned */
+ if (!check_valid_pointer(s, page, object))
return 0;
/*
@@ -1826,7 +1962,8 @@ const char *kmem_cache_name(struct kmem_cache *s)
EXPORT_SYMBOL(kmem_cache_name);
/*
- * Attempt to free all slabs on a node
+ * Attempt to free all slabs on a node. Return the number of slabs we
+ * were unable to free.
*/
static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
struct list_head *list)
@@ -1847,7 +1984,7 @@ static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
}
/*
- * Release all resources used by slab cache
+ * Release all resources used by a slab cache.
*/
static int kmem_cache_close(struct kmem_cache *s)
{
@@ -1932,45 +2069,6 @@ static int __init setup_slub_nomerge(char *str)
__setup("slub_nomerge", setup_slub_nomerge);
-static int __init setup_slub_debug(char *str)
-{
- if (!str || *str != '=')
- slub_debug = DEBUG_DEFAULT_FLAGS;
- else {
- str++;
- if (*str == 0 || *str == ',')
- slub_debug = DEBUG_DEFAULT_FLAGS;
- else
- for( ;*str && *str != ','; str++)
- switch (*str) {
- case 'f' : case 'F' :
- slub_debug |= SLAB_DEBUG_FREE;
- break;
- case 'z' : case 'Z' :
- slub_debug |= SLAB_RED_ZONE;
- break;
- case 'p' : case 'P' :
- slub_debug |= SLAB_POISON;
- break;
- case 'u' : case 'U' :
- slub_debug |= SLAB_STORE_USER;
- break;
- case 't' : case 'T' :
- slub_debug |= SLAB_TRACE;
- break;
- default:
- printk(KERN_ERR "slub_debug option '%c' "
- "unknown. skipped\n",*str);
- }
- }
-
- if (*str == ',')
- slub_debug_slabs = str + 1;
- return 1;
-}
-
-__setup("slub_debug", setup_slub_debug);
-
static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
const char *name, int size, gfp_t gfp_flags)
{
@@ -2108,13 +2206,14 @@ void kfree(const void *x)
EXPORT_SYMBOL(kfree);
/*
- * kmem_cache_shrink removes empty slabs from the partial lists
- * and then sorts the partially allocated slabs by the number
- * of items in use. The slabs with the most items in use
- * come first. New allocations will remove these from the
- * partial list because they are full. The slabs with the
- * least items are placed last. If it happens that the objects
- * are freed then the page can be returned to the page allocator.
+ * kmem_cache_shrink removes empty slabs from the partial lists and sorts
+ * the remaining slabs by the number of items in use. The slabs with the
+ * most items in use come first. New allocations will then fill those up
+ * and thus they can be removed from the partial lists.
+ *
+ * The slabs with the least items are placed last. This results in them
+ * being allocated from last increasing the chance that the last objects
+ * are freed in them.
*/
int kmem_cache_shrink(struct kmem_cache *s)
{
@@ -2143,12 +2242,10 @@ int kmem_cache_shrink(struct kmem_cache *s)
spin_lock_irqsave(&n->list_lock, flags);
/*
- * Build lists indexed by the items in use in
- * each slab or free slabs if empty.
+ * Build lists indexed by the items in use in each slab.
*
- * Note that concurrent frees may occur while
- * we hold the list_lock. page->inuse here is
- * the upper limit.
+ * Note that concurrent frees may occur while we hold the
+ * list_lock. page->inuse here is the upper limit.
*/
list_for_each_entry_safe(page, t, &n->partial, lru) {
if (!page->inuse && slab_trylock(page)) {
@@ -2172,8 +2269,8 @@ int kmem_cache_shrink(struct kmem_cache *s)
goto out;
/*
- * Rebuild the partial list with the slabs filled up
- * most first and the least used slabs at the end.
+ * Rebuild the partial list with the slabs filled up most
+ * first and the least used slabs at the end.
*/
for (i = s->objects - 1; i >= 0; i--)
list_splice(slabs_by_inuse + i, n->partial.prev);
@@ -2189,7 +2286,6 @@ EXPORT_SYMBOL(kmem_cache_shrink);
/**
* krealloc - reallocate memory. The contents will remain unchanged.
- *
* @p: object to reallocate memory for.
* @new_size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
@@ -2201,9 +2297,8 @@ EXPORT_SYMBOL(kmem_cache_shrink);
*/
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
- struct kmem_cache *new_cache;
void *ret;
- struct page *page;
+ size_t ks;
if (unlikely(!p))
return kmalloc(new_size, flags);
@@ -2213,19 +2308,13 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags)
return NULL;
}
- page = virt_to_head_page(p);
-
- new_cache = get_slab(new_size, flags);
-
- /*
- * If new size fits in the current cache, bail out.
- */
- if (likely(page->slab == new_cache))
+ ks = ksize(p);
+ if (ks >= new_size)
return (void *)p;
ret = kmalloc(new_size, flags);
if (ret) {
- memcpy(ret, p, min(new_size, ksize(p)));
+ memcpy(ret, p, min(new_size, ks));
kfree(p);
}
return ret;
@@ -2243,7 +2332,7 @@ void __init kmem_cache_init(void)
#ifdef CONFIG_NUMA
/*
* Must first have the slab cache available for the allocations of the
- * struct kmalloc_cache_node's. There is special bootstrap code in
+ * struct kmem_cache_node's. There is special bootstrap code in
* kmem_cache_open for slab_state == DOWN.
*/
create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
@@ -2280,7 +2369,7 @@ void __init kmem_cache_init(void)
printk(KERN_INFO "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
" Processors=%d, Nodes=%d\n",
- KMALLOC_SHIFT_HIGH, L1_CACHE_BYTES,
+ KMALLOC_SHIFT_HIGH, cache_line_size(),
slub_min_order, slub_max_order, slub_min_objects,
nr_cpu_ids, nr_node_ids);
}
@@ -2415,8 +2504,8 @@ static void for_all_slabs(void (*func)(struct kmem_cache *, int), int cpu)
}
/*
- * Use the cpu notifier to insure that the slab are flushed
- * when necessary.
+ * Use the cpu notifier to insure that the cpu slabs are flushed when
+ * necessary.
*/
static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
@@ -2425,7 +2514,9 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
for_all_slabs(__flush_cpu_slab, cpu);
break;
default:
@@ -2439,153 +2530,6 @@ static struct notifier_block __cpuinitdata slab_notifier =
#endif
-#ifdef CONFIG_NUMA
-
-/*****************************************************************
- * Generic reaper used to support the page allocator
- * (the cpu slabs are reaped by a per slab workqueue).
- *
- * Maybe move this to the page allocator?
- ****************************************************************/
-
-static DEFINE_PER_CPU(unsigned long, reap_node);
-
-static void init_reap_node(int cpu)
-{
- int node;
-
- node = next_node(cpu_to_node(cpu), node_online_map);
- if (node == MAX_NUMNODES)
- node = first_node(node_online_map);
-
- __get_cpu_var(reap_node) = node;
-}
-
-static void next_reap_node(void)
-{
- int node = __get_cpu_var(reap_node);
-
- /*
- * Also drain per cpu pages on remote zones
- */
- if (node != numa_node_id())
- drain_node_pages(node);
-
- node = next_node(node, node_online_map);
- if (unlikely(node >= MAX_NUMNODES))
- node = first_node(node_online_map);
- __get_cpu_var(reap_node) = node;
-}
-#else
-#define init_reap_node(cpu) do { } while (0)
-#define next_reap_node(void) do { } while (0)
-#endif
-
-#define REAPTIMEOUT_CPUC (2*HZ)
-
-#ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
-
-static void cache_reap(struct work_struct *unused)
-{
- next_reap_node();
- refresh_cpu_vm_stats(smp_processor_id());
- schedule_delayed_work(&__get_cpu_var(reap_work),
- REAPTIMEOUT_CPUC);
-}
-
-static void __devinit start_cpu_timer(int cpu)
-{
- struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
-
- /*
- * When this gets called from do_initcalls via cpucache_init(),
- * init_workqueues() has already run, so keventd will be setup
- * at that time.
- */
- if (keventd_up() && reap_work->work.func == NULL) {
- init_reap_node(cpu);
- INIT_DELAYED_WORK(reap_work, cache_reap);
- schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
- }
-}
-
-static int __init cpucache_init(void)
-{
- int cpu;
-
- /*
- * Register the timers that drain pcp pages and update vm statistics
- */
- for_each_online_cpu(cpu)
- start_cpu_timer(cpu);
- return 0;
-}
-__initcall(cpucache_init);
-#endif
-
-#ifdef SLUB_RESILIENCY_TEST
-static unsigned long validate_slab_cache(struct kmem_cache *s);
-
-static void resiliency_test(void)
-{
- u8 *p;
-
- printk(KERN_ERR "SLUB resiliency testing\n");
- printk(KERN_ERR "-----------------------\n");
- printk(KERN_ERR "A. Corruption after allocation\n");
-
- p = kzalloc(16, GFP_KERNEL);
- p[16] = 0x12;
- printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
- " 0x12->0x%p\n\n", p + 16);
-
- validate_slab_cache(kmalloc_caches + 4);
-
- /* Hmmm... The next two are dangerous */
- p = kzalloc(32, GFP_KERNEL);
- p[32 + sizeof(void *)] = 0x34;
- printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
- " 0x34 -> -0x%p\n", p);
- printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
-
- validate_slab_cache(kmalloc_caches + 5);
- p = kzalloc(64, GFP_KERNEL);
- p += 64 + (get_cycles() & 0xff) * sizeof(void *);
- *p = 0x56;
- printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
- p);
- printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
- validate_slab_cache(kmalloc_caches + 6);
-
- printk(KERN_ERR "\nB. Corruption after free\n");
- p = kzalloc(128, GFP_KERNEL);
- kfree(p);
- *p = 0x78;
- printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 7);
-
- p = kzalloc(256, GFP_KERNEL);
- kfree(p);
- p[50] = 0x9a;
- printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 8);
-
- p = kzalloc(512, GFP_KERNEL);
- kfree(p);
- p[512] = 0xab;
- printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 9);
-}
-#else
-static void resiliency_test(void) {};
-#endif
-
-/*
- * These are not as efficient as kmalloc for the non debug case.
- * We do not have the page struct available so we have to touch one
- * cacheline in struct kmem_cache to check slab flags.
- */
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
{
struct kmem_cache *s = get_slab(size, gfpflags);
@@ -2607,13 +2551,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
return slab_alloc(s, gfpflags, node, caller);
}
-#ifdef CONFIG_SYSFS
-
+#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
static int validate_slab(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);
- unsigned long map[BITS_TO_LONGS(s->objects)];
+ DECLARE_BITMAP(map, s->objects);
if (!check_slab(s, page) ||
!on_freelist(s, page, NULL))
@@ -2622,14 +2565,14 @@ static int validate_slab(struct kmem_cache *s, struct page *page)
/* Now we know that a valid freelist exists */
bitmap_zero(map, s->objects);
- for(p = page->freelist; p; p = get_freepointer(s, p)) {
- set_bit((p - addr) / s->size, map);
+ for_each_free_object(p, s, page->freelist) {
+ set_bit(slab_index(p, s, addr), map);
if (!check_object(s, page, p, 0))
return 0;
}
- for(p = addr; p < addr + s->objects * s->size; p += s->size)
- if (!test_bit((p - addr) / s->size, map))
+ for_each_object(p, s, addr)
+ if (!test_bit(slab_index(p, s, addr), map))
if (!check_object(s, page, p, 1))
return 0;
return 1;
@@ -2645,12 +2588,12 @@ static void validate_slab_slab(struct kmem_cache *s, struct page *page)
s->name, page);
if (s->flags & DEBUG_DEFAULT_FLAGS) {
- if (!PageError(page))
- printk(KERN_ERR "SLUB %s: PageError not set "
+ if (!SlabDebug(page))
+ printk(KERN_ERR "SLUB %s: SlabDebug not set "
"on slab 0x%p\n", s->name, page);
} else {
- if (PageError(page))
- printk(KERN_ERR "SLUB %s: PageError set on "
+ if (SlabDebug(page))
+ printk(KERN_ERR "SLUB %s: SlabDebug set on "
"slab 0x%p\n", s->name, page);
}
}
@@ -2702,14 +2645,76 @@ static unsigned long validate_slab_cache(struct kmem_cache *s)
return count;
}
+#ifdef SLUB_RESILIENCY_TEST
+static void resiliency_test(void)
+{
+ u8 *p;
+
+ printk(KERN_ERR "SLUB resiliency testing\n");
+ printk(KERN_ERR "-----------------------\n");
+ printk(KERN_ERR "A. Corruption after allocation\n");
+
+ p = kzalloc(16, GFP_KERNEL);
+ p[16] = 0x12;
+ printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
+ " 0x12->0x%p\n\n", p + 16);
+
+ validate_slab_cache(kmalloc_caches + 4);
+
+ /* Hmmm... The next two are dangerous */
+ p = kzalloc(32, GFP_KERNEL);
+ p[32 + sizeof(void *)] = 0x34;
+ printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
+ " 0x34 -> -0x%p\n", p);
+ printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
+
+ validate_slab_cache(kmalloc_caches + 5);
+ p = kzalloc(64, GFP_KERNEL);
+ p += 64 + (get_cycles() & 0xff) * sizeof(void *);
+ *p = 0x56;
+ printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
+ p);
+ printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
+ validate_slab_cache(kmalloc_caches + 6);
+
+ printk(KERN_ERR "\nB. Corruption after free\n");
+ p = kzalloc(128, GFP_KERNEL);
+ kfree(p);
+ *p = 0x78;
+ printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 7);
+
+ p = kzalloc(256, GFP_KERNEL);
+ kfree(p);
+ p[50] = 0x9a;
+ printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 8);
+
+ p = kzalloc(512, GFP_KERNEL);
+ kfree(p);
+ p[512] = 0xab;
+ printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 9);
+}
+#else
+static void resiliency_test(void) {};
+#endif
+
/*
- * Generate lists of locations where slabcache objects are allocated
+ * Generate lists of code addresses where slabcache objects are allocated
* and freed.
*/
struct location {
unsigned long count;
void *addr;
+ long long sum_time;
+ long min_time;
+ long max_time;
+ long min_pid;
+ long max_pid;
+ cpumask_t cpus;
+ nodemask_t nodes;
};
struct loc_track {
@@ -2750,11 +2755,12 @@ static int alloc_loc_track(struct loc_track *t, unsigned long max)
}
static int add_location(struct loc_track *t, struct kmem_cache *s,
- void *addr)
+ const struct track *track)
{
long start, end, pos;
struct location *l;
void *caddr;
+ unsigned long age = jiffies - track->when;
start = -1;
end = t->count;
@@ -2770,19 +2776,36 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
break;
caddr = t->loc[pos].addr;
- if (addr == caddr) {
- t->loc[pos].count++;
+ if (track->addr == caddr) {
+
+ l = &t->loc[pos];
+ l->count++;
+ if (track->when) {
+ l->sum_time += age;
+ if (age < l->min_time)
+ l->min_time = age;
+ if (age > l->max_time)
+ l->max_time = age;
+
+ if (track->pid < l->min_pid)
+ l->min_pid = track->pid;
+ if (track->pid > l->max_pid)
+ l->max_pid = track->pid;
+
+ cpu_set(track->cpu, l->cpus);
+ }
+ node_set(page_to_nid(virt_to_page(track)), l->nodes);
return 1;
}
- if (addr < caddr)
+ if (track->addr < caddr)
end = pos;
else
start = pos;
}
/*
- * Not found. Insert new tracking element
+ * Not found. Insert new tracking element.
*/
if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max))
return 0;
@@ -2793,7 +2816,16 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
(t->count - pos) * sizeof(struct location));
t->count++;
l->count = 1;
- l->addr = addr;
+ l->addr = track->addr;
+ l->sum_time = age;
+ l->min_time = age;
+ l->max_time = age;
+ l->min_pid = track->pid;
+ l->max_pid = track->pid;
+ cpus_clear(l->cpus);
+ cpu_set(track->cpu, l->cpus);
+ nodes_clear(l->nodes);
+ node_set(page_to_nid(virt_to_page(track)), l->nodes);
return 1;
}
@@ -2801,19 +2833,16 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
- unsigned long map[BITS_TO_LONGS(s->objects)];
+ DECLARE_BITMAP(map, s->objects);
void *p;
bitmap_zero(map, s->objects);
- for (p = page->freelist; p; p = get_freepointer(s, p))
- set_bit((p - addr) / s->size, map);
-
- for (p = addr; p < addr + s->objects * s->size; p += s->size)
- if (!test_bit((p - addr) / s->size, map)) {
- void *addr = get_track(s, p, alloc)->addr;
+ for_each_free_object(p, s, page->freelist)
+ set_bit(slab_index(p, s, addr), map);
- add_location(t, s, addr);
- }
+ for_each_object(p, s, addr)
+ if (!test_bit(slab_index(p, s, addr), map))
+ add_location(t, s, get_track(s, p, alloc));
}
static int list_locations(struct kmem_cache *s, char *buf,
@@ -2847,15 +2876,47 @@ static int list_locations(struct kmem_cache *s, char *buf,
}
for (i = 0; i < t.count; i++) {
- void *addr = t.loc[i].addr;
+ struct location *l = &t.loc[i];
if (n > PAGE_SIZE - 100)
break;
- n += sprintf(buf + n, "%7ld ", t.loc[i].count);
- if (addr)
- n += sprint_symbol(buf + n, (unsigned long)t.loc[i].addr);
+ n += sprintf(buf + n, "%7ld ", l->count);
+
+ if (l->addr)
+ n += sprint_symbol(buf + n, (unsigned long)l->addr);
else
n += sprintf(buf + n, "<not-available>");
+
+ if (l->sum_time != l->min_time) {
+ unsigned long remainder;
+
+ n += sprintf(buf + n, " age=%ld/%ld/%ld",
+ l->min_time,
+ div_long_long_rem(l->sum_time, l->count, &remainder),
+ l->max_time);
+ } else
+ n += sprintf(buf + n, " age=%ld",
+ l->min_time);
+
+ if (l->min_pid != l->max_pid)
+ n += sprintf(buf + n, " pid=%ld-%ld",
+ l->min_pid, l->max_pid);
+ else
+ n += sprintf(buf + n, " pid=%ld",
+ l->min_pid);
+
+ if (num_online_cpus() > 1 && !cpus_empty(l->cpus)) {
+ n += sprintf(buf + n, " cpus=");
+ n += cpulist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ l->cpus);
+ }
+
+ if (num_online_nodes() > 1 && !nodes_empty(l->nodes)) {
+ n += sprintf(buf + n, " nodes=");
+ n += nodelist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ l->nodes);
+ }
+
n += sprintf(buf + n, "\n");
}
@@ -3491,6 +3552,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
static int __init slab_sysfs_init(void)
{
+ struct list_head *h;
int err;
err = subsystem_register(&slab_subsys);
@@ -3499,7 +3561,15 @@ static int __init slab_sysfs_init(void)
return -ENOSYS;
}
- finish_bootstrap();
+ slab_state = SYSFS;
+
+ list_for_each(h, &slab_caches) {
+ struct kmem_cache *s =
+ container_of(h, struct kmem_cache, list);
+
+ err = sysfs_slab_add(s);
+ BUG_ON(err);
+ }
while (alias_list) {
struct saved_alias *al = alias_list;
@@ -3515,6 +3585,4 @@ static int __init slab_sysfs_init(void)
}
__initcall(slab_sysfs_init);
-#else
-__initcall(finish_bootstrap);
#endif
diff --git a/mm/sparse.c b/mm/sparse.c
index 893e5621c24..6f3fff907bc 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -44,7 +44,7 @@ EXPORT_SYMBOL(page_to_nid);
#endif
#ifdef CONFIG_SPARSEMEM_EXTREME
-static struct mem_section *sparse_index_alloc(int nid)
+static struct mem_section noinline *sparse_index_alloc(int nid)
{
struct mem_section *section = NULL;
unsigned long array_size = SECTIONS_PER_ROOT *
@@ -61,7 +61,7 @@ static struct mem_section *sparse_index_alloc(int nid)
return section;
}
-static int sparse_index_init(unsigned long section_nr, int nid)
+static int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
static DEFINE_SPINLOCK(index_init_lock);
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
@@ -138,7 +138,7 @@ static inline int sparse_early_nid(struct mem_section *section)
}
/* Record a memory area against a node. */
-void memory_present(int nid, unsigned long start, unsigned long end)
+void __init memory_present(int nid, unsigned long start, unsigned long end)
{
unsigned long pfn;
@@ -197,7 +197,7 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
-static int sparse_init_one_section(struct mem_section *ms,
+static int __meminit sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map)
{
if (!valid_section(ms))
@@ -209,7 +209,7 @@ static int sparse_init_one_section(struct mem_section *ms,
return 1;
}
-static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
+static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
{
struct page *map;
struct mem_section *ms = __nr_to_section(pnum);
@@ -288,6 +288,7 @@ void __init sparse_init(void)
}
}
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* returns the number of sections whose mem_maps were properly
* set. If this is <=0, then that means that the passed-in
@@ -327,3 +328,4 @@ out:
__kfree_section_memmap(memmap, nr_pages);
return ret;
}
+#endif
diff --git a/mm/swap.c b/mm/swap.c
index 218c52a24a2..d3cb966fe99 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -488,7 +488,7 @@ static int cpu_swap_callback(struct notifier_block *nfb,
long *committed;
committed = &per_cpu(committed_space, (long)hcpu);
- if (action == CPU_DEAD) {
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
atomic_add(*committed, &vm_committed_space);
*committed = 0;
__lru_add_drain((long)hcpu);
diff --git a/mm/truncate.c b/mm/truncate.c
index 0f4b6d18ab0..4fbe1a2da5f 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -12,6 +12,7 @@
#include <linux/swap.h>
#include <linux/module.h>
#include <linux/pagemap.h>
+#include <linux/highmem.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/buffer_head.h> /* grr. try_to_release_page,
@@ -46,7 +47,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
static inline void truncate_partial_page(struct page *page, unsigned partial)
{
- memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
+ zero_user_page(page, partial, PAGE_CACHE_SIZE - partial, KM_USER0);
if (PagePrivate(page))
do_invalidatepage(page, partial);
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cb5aabda704..faa2a521dea 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -755,3 +755,10 @@ out_einval_locked:
}
EXPORT_SYMBOL(remap_vmalloc_range);
+/*
+ * Implement a stub for vmalloc_sync_all() if the architecture chose not to
+ * have one.
+ */
+void __attribute__((weak)) vmalloc_sync_all(void)
+{
+}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 56651a10c36..1be5a6376ef 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -284,12 +284,8 @@ static void handle_write_error(struct address_space *mapping,
struct page *page, int error)
{
lock_page(page);
- if (page_mapping(page) == mapping) {
- if (error == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else
- set_bit(AS_EIO, &mapping->flags);
- }
+ if (page_mapping(page) == mapping)
+ mapping_set_error(mapping, error);
unlock_page(page);
}
@@ -1532,7 +1528,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
pg_data_t *pgdat;
cpumask_t mask;
- if (action == CPU_ONLINE) {
+ if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
for_each_online_pgdat(pgdat) {
mask = node_to_cpumask(pgdat->node_id);
if (any_online_cpu(mask) != NR_CPUS)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6c488d6ac42..9832d9a41d8 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -281,6 +281,17 @@ EXPORT_SYMBOL(dec_zone_page_state);
/*
* Update the zone counters for one cpu.
+ *
+ * Note that refresh_cpu_vm_stats strives to only access
+ * node local memory. The per cpu pagesets on remote zones are placed
+ * in the memory local to the processor using that pageset. So the
+ * loop over all zones will access a series of cachelines local to
+ * the processor.
+ *
+ * The call to zone_page_state_add updates the cachelines with the
+ * statistics in the remote zone struct as well as the global cachelines
+ * with the global counters. These could cause remote node cache line
+ * bouncing and will have to be only done when necessary.
*/
void refresh_cpu_vm_stats(int cpu)
{
@@ -289,21 +300,54 @@ void refresh_cpu_vm_stats(int cpu)
unsigned long flags;
for_each_zone(zone) {
- struct per_cpu_pageset *pcp;
+ struct per_cpu_pageset *p;
if (!populated_zone(zone))
continue;
- pcp = zone_pcp(zone, cpu);
+ p = zone_pcp(zone, cpu);
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (pcp->vm_stat_diff[i]) {
+ if (p->vm_stat_diff[i]) {
local_irq_save(flags);
- zone_page_state_add(pcp->vm_stat_diff[i],
+ zone_page_state_add(p->vm_stat_diff[i],
zone, i);
- pcp->vm_stat_diff[i] = 0;
+ p->vm_stat_diff[i] = 0;
+#ifdef CONFIG_NUMA
+ /* 3 seconds idle till flush */
+ p->expire = 3;
+#endif
local_irq_restore(flags);
}
+#ifdef CONFIG_NUMA
+ /*
+ * Deal with draining the remote pageset of this
+ * processor
+ *
+ * Check if there are pages remaining in this pageset
+ * if not then there is nothing to expire.
+ */
+ if (!p->expire || (!p->pcp[0].count && !p->pcp[1].count))
+ continue;
+
+ /*
+ * We never drain zones local to this processor.
+ */
+ if (zone_to_nid(zone) == numa_node_id()) {
+ p->expire = 0;
+ continue;
+ }
+
+ p->expire--;
+ if (p->expire)
+ continue;
+
+ if (p->pcp[0].count)
+ drain_zone_pages(zone, p->pcp + 0);
+
+ if (p->pcp[1].count)
+ drain_zone_pages(zone, p->pcp + 1);
+#endif
}
}
@@ -640,6 +684,24 @@ const struct seq_operations vmstat_op = {
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
+int sysctl_stat_interval __read_mostly = HZ;
+
+static void vmstat_update(struct work_struct *w)
+{
+ refresh_cpu_vm_stats(smp_processor_id());
+ schedule_delayed_work(&__get_cpu_var(vmstat_work),
+ sysctl_stat_interval);
+}
+
+static void __devinit start_cpu_timer(int cpu)
+{
+ struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+
+ INIT_DELAYED_WORK(vmstat_work, vmstat_update);
+ schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+}
+
/*
* Use the cpu notifier to insure that the thresholds are recalculated
* when necessary.
@@ -648,10 +710,24 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
+ long cpu = (long)hcpu;
+
switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_CANCELED:
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ start_cpu_timer(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu));
+ per_cpu(vmstat_work, cpu).work.func = NULL;
+ break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ start_cpu_timer(cpu);
+ break;
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
refresh_zone_stat_thresholds();
break;
default:
@@ -665,8 +741,13 @@ static struct notifier_block __cpuinitdata vmstat_notifier =
int __init setup_vmstat(void)
{
+ int cpu;
+
refresh_zone_stat_thresholds();
register_cpu_notifier(&vmstat_notifier);
+
+ for_each_online_cpu(cpu)
+ start_cpu_timer(cpu);
return 0;
}
module_init(setup_vmstat)
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2024-11-22 19:17:24 +0000