summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c7
-rw-r--r--mm/kmemleak.c30
-rw-r--r--mm/memory-failure.c22
-rw-r--r--mm/page_alloc.c6
-rw-r--r--mm/page_ext.c23
-rw-r--r--mm/page_owner.c55
-rw-r--r--mm/slab.c3
-rw-r--r--mm/slub.c35
8 files changed, 101 insertions, 80 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index ce08b39d85d4..672d3c78c6ab 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
/* Ensure the start of the pageblock or zone is online and valid */
block_pfn = pageblock_start_pfn(pfn);
- block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+ block_pfn = max(block_pfn, zone->zone_start_pfn);
+ block_page = pfn_to_online_page(block_pfn);
if (block_page) {
page = block_page;
pfn = block_pfn;
}
/* Ensure the end of the pageblock or zone is online and valid */
- block_pfn += pageblock_nr_pages;
+ block_pfn = pageblock_end_pfn(pfn) - 1;
block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
end_page = pfn_to_online_page(block_pfn);
if (!end_page)
@@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
page += (1 << PAGE_ALLOC_COSTLY_ORDER);
pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
- } while (page < end_page);
+ } while (page <= end_page);
return false;
}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 03a8d84badad..244607663363 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -527,6 +527,16 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
}
/*
+ * Remove an object from the object_tree_root and object_list. Must be called
+ * with the kmemleak_lock held _if_ kmemleak is still enabled.
+ */
+static void __remove_object(struct kmemleak_object *object)
+{
+ rb_erase(&object->rb_node, &object_tree_root);
+ list_del_rcu(&object->object_list);
+}
+
+/*
* Look up an object in the object search tree and remove it from both
* object_tree_root and object_list. The returned object's use_count should be
* at least 1, as initially set by create_object().
@@ -538,10 +548,8 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
write_lock_irqsave(&kmemleak_lock, flags);
object = lookup_object(ptr, alias);
- if (object) {
- rb_erase(&object->rb_node, &object_tree_root);
- list_del_rcu(&object->object_list);
- }
+ if (object)
+ __remove_object(object);
write_unlock_irqrestore(&kmemleak_lock, flags);
return object;
@@ -1834,12 +1842,16 @@ static const struct file_operations kmemleak_fops = {
static void __kmemleak_do_cleanup(void)
{
- struct kmemleak_object *object;
+ struct kmemleak_object *object, *tmp;
- rcu_read_lock();
- list_for_each_entry_rcu(object, &object_list, object_list)
- delete_object_full(object->pointer);
- rcu_read_unlock();
+ /*
+ * Kmemleak has already been disabled, no need for RCU list traversal
+ * or kmemleak_lock held.
+ */
+ list_for_each_entry_safe(object, tmp, &object_list, object_list) {
+ __remove_object(object);
+ __delete_object(object);
+ }
}
/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7ef849da8278..0ae72b6acee7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -199,7 +199,6 @@ struct to_kill {
struct task_struct *tsk;
unsigned long addr;
short size_shift;
- char addr_valid;
};
/*
@@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
}
}
tk->addr = page_address_in_vma(p, vma);
- tk->addr_valid = 1;
if (is_zone_device_page(p))
tk->size_shift = dev_pagemap_mapping_shift(p, vma);
else
tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
/*
- * In theory we don't have to kill when the page was
- * munmaped. But it could be also a mremap. Since that's
- * likely very rare kill anyways just out of paranoia, but use
- * a SIGKILL because the error is not contained anymore.
+ * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+ * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+ * so "tk->size_shift == 0" effectively checks no mapping on
+ * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+ * to a process' address space, it's possible not all N VMAs
+ * contain mappings for the page, but at least one VMA does.
+ * Only deliver SIGBUS with payload derived from the VMA that
+ * has a mapping for the page.
*/
- if (tk->addr == -EFAULT || tk->size_shift == 0) {
+ if (tk->addr == -EFAULT) {
pr_info("Memory failure: Unable to find user space address %lx in %s\n",
page_to_pfn(p), tsk->comm);
- tk->addr_valid = 0;
+ } else if (tk->size_shift == 0) {
+ kfree(tk);
+ return;
}
get_task_struct(tsk);
tk->tsk = tsk;
@@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
* make sure the process doesn't catch the
* signal and then access the memory. Just kill it.
*/
- if (fail || tk->addr_valid == 0) {
+ if (fail || tk->addr == -EFAULT) {
pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
pfn, tk->tsk->comm, tk->tsk->pid);
do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c0b2e0306720..ecc3dbad606b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4473,12 +4473,14 @@ retry_cpuset:
if (page)
goto got_pg;
- if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+ if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
+ !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
/*
* If allocating entire pageblock(s) and compaction
* failed because all zones are below low watermarks
* or is prohibited because it recently failed at this
- * order, fail immediately.
+ * order, fail immediately unless the allocator has
+ * requested compaction and reclaim retry.
*
* Reclaim is
* - potentially very expensive because zones are far
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 5f5769c7db3b..4ade843ff588 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = {
#endif
};
+unsigned long page_ext_size = sizeof(struct page_ext);
+
static unsigned long total_usage;
-static unsigned long extra_mem;
static bool __init invoke_need_callbacks(void)
{
@@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void)
for (i = 0; i < entries; i++) {
if (page_ext_ops[i]->need && page_ext_ops[i]->need()) {
- page_ext_ops[i]->offset = sizeof(struct page_ext) +
- extra_mem;
- extra_mem += page_ext_ops[i]->size;
+ page_ext_ops[i]->offset = page_ext_size;
+ page_ext_size += page_ext_ops[i]->size;
need = true;
}
}
@@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void)
}
}
-static unsigned long get_entry_size(void)
-{
- return sizeof(struct page_ext) + extra_mem;
-}
-
static inline struct page_ext *get_entry(void *base, unsigned long index)
{
- return base + get_entry_size() * index;
+ return base + page_ext_size * index;
}
#if !defined(CONFIG_SPARSEMEM)
@@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid)
!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
nr_pages += MAX_ORDER_NR_PAGES;
- table_size = get_entry_size() * nr_pages;
+ table_size = page_ext_size * nr_pages;
base = memblock_alloc_try_nid(
table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
if (section->page_ext)
return 0;
- table_size = get_entry_size() * PAGES_PER_SECTION;
+ table_size = page_ext_size * PAGES_PER_SECTION;
base = alloc_page_ext(table_size, nid);
/*
@@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
* we need to apply a mask.
*/
pfn &= PAGE_SECTION_MASK;
- section->page_ext = (void *)base - get_entry_size() * pfn;
+ section->page_ext = (void *)base - page_ext_size * pfn;
total_usage += table_size;
return 0;
}
@@ -267,7 +262,7 @@ static void free_page_ext(void *addr)
struct page *page = virt_to_page(addr);
size_t table_size;
- table_size = get_entry_size() * PAGES_PER_SECTION;
+ table_size = page_ext_size * PAGES_PER_SECTION;
BUG_ON(PageReserved(page));
kmemleak_free(addr);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index dee931184788..e327bcd0380e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -24,12 +24,10 @@ struct page_owner {
short last_migrate_reason;
gfp_t gfp_mask;
depot_stack_handle_t handle;
-#ifdef CONFIG_DEBUG_PAGEALLOC
depot_stack_handle_t free_handle;
-#endif
};
-static bool page_owner_disabled = true;
+static bool page_owner_enabled = false;
DEFINE_STATIC_KEY_FALSE(page_owner_inited);
static depot_stack_handle_t dummy_handle;
@@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf)
return -EINVAL;
if (strcmp(buf, "on") == 0)
- page_owner_disabled = false;
+ page_owner_enabled = true;
return 0;
}
@@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param);
static bool need_page_owner(void)
{
- if (page_owner_disabled)
- return false;
-
- return true;
+ return page_owner_enabled;
}
static __always_inline depot_stack_handle_t create_dummy_stack(void)
@@ -84,7 +79,7 @@ static noinline void register_early_stack(void)
static void init_page_owner(void)
{
- if (page_owner_disabled)
+ if (!page_owner_enabled)
return;
register_dummy_stack();
@@ -148,25 +143,19 @@ void __reset_page_owner(struct page *page, unsigned int order)
{
int i;
struct page_ext *page_ext;
-#ifdef CONFIG_DEBUG_PAGEALLOC
depot_stack_handle_t handle = 0;
struct page_owner *page_owner;
- if (debug_pagealloc_enabled())
- handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
-#endif
+ handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
+ page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
for (i = 0; i < (1 << order); i++) {
- page_ext = lookup_page_ext(page + i);
- if (unlikely(!page_ext))
- continue;
- __clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
-#ifdef CONFIG_DEBUG_PAGEALLOC
- if (debug_pagealloc_enabled()) {
- page_owner = get_page_owner(page_ext);
- page_owner->free_handle = handle;
- }
-#endif
+ __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+ page_owner = get_page_owner(page_ext);
+ page_owner->free_handle = handle;
+ page_ext = page_ext_next(page_ext);
}
}
@@ -184,9 +173,9 @@ static inline void __set_page_owner_handle(struct page *page,
page_owner->gfp_mask = gfp_mask;
page_owner->last_migrate_reason = -1;
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
- __set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
+ __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
- page_ext = lookup_page_ext(page + i);
+ page_ext = page_ext_next(page_ext);
}
}
@@ -224,12 +213,10 @@ void __split_page_owner(struct page *page, unsigned int order)
if (unlikely(!page_ext))
return;
- page_owner = get_page_owner(page_ext);
- page_owner->order = 0;
- for (i = 1; i < (1 << order); i++) {
- page_ext = lookup_page_ext(page + i);
+ for (i = 0; i < (1 << order); i++) {
page_owner = get_page_owner(page_ext);
page_owner->order = 0;
+ page_ext = page_ext_next(page_ext);
}
}
@@ -260,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
* the new page, which will be freed.
*/
__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
- __set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags);
+ __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
}
void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -320,7 +307,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
if (unlikely(!page_ext))
continue;
- if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
continue;
page_owner = get_page_owner(page_ext);
@@ -435,7 +422,7 @@ void __dump_page_owner(struct page *page)
return;
}
- if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+ if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
pr_alert("page_owner tracks the page as allocated\n");
else
pr_alert("page_owner tracks the page as freed\n");
@@ -451,7 +438,6 @@ void __dump_page_owner(struct page *page)
stack_trace_print(entries, nr_entries, 0);
}
-#ifdef CONFIG_DEBUG_PAGEALLOC
handle = READ_ONCE(page_owner->free_handle);
if (!handle) {
pr_alert("page_owner free stack trace missing\n");
@@ -460,7 +446,6 @@ void __dump_page_owner(struct page *page)
pr_alert("page last free stack trace:\n");
stack_trace_print(entries, nr_entries, 0);
}
-#endif
if (page_owner->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
@@ -527,7 +512,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
* Although we do have the info about past allocation of free
* pages, it's not relevant for current memory usage.
*/
- if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
continue;
page_owner = get_page_owner(page_ext);
diff --git a/mm/slab.c b/mm/slab.c
index 9df370558e5d..66e5d8032bae 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
/**
* __ksize -- Uninstrumented ksize.
+ * @objp: pointer to the object
*
* Unlike ksize(), __ksize() is uninstrumented, and does not provide the same
* safety checks as ksize() with KASAN instrumentation enabled.
+ *
+ * Return: size of the actual memory used by @objp in bytes
*/
size_t __ksize(const void *objp)
{
diff --git a/mm/slub.c b/mm/slub.c
index 3d63ae320d31..b25c807a111f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2672,6 +2672,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
}
/*
+ * If the object has been wiped upon free, make sure it's fully initialized by
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+ void *obj)
+{
+ if (unlikely(slab_want_init_on_free(s)) && obj)
+ memset((void *)((char *)obj + s->offset), 0, sizeof(void *));
+}
+
+/*
* Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
* have the fastpath folded into their functions. So no function call
* overhead for requests that can be satisfied on the fastpath.
@@ -2759,12 +2770,8 @@ redo:
prefetch_freepointer(s, next_object);
stat(s, ALLOC_FASTPATH);
}
- /*
- * If the object has been wiped upon free, make sure it's fully
- * initialized by zeroing out freelist pointer.
- */
- if (unlikely(slab_want_init_on_free(s)) && object)
- memset(object + s->offset, 0, sizeof(void *));
+
+ maybe_wipe_obj_freeptr(s, object);
if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
memset(object, 0, s->object_size);
@@ -3178,10 +3185,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
goto error;
c = this_cpu_ptr(s->cpu_slab);
+ maybe_wipe_obj_freeptr(s, p[i]);
+
continue; /* goto for-loop */
}
c->freelist = get_freepointer(s, object);
p[i] = object;
+ maybe_wipe_obj_freeptr(s, p[i]);
}
c->tid = next_tid(c->tid);
local_irq_enable();
@@ -4846,7 +4856,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
}
}
- get_online_mems();
+ /*
+ * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex"
+ * already held which will conflict with an existing lock order:
+ *
+ * mem_hotplug_lock->slab_mutex->kernfs_mutex
+ *
+ * We don't really need mem_hotplug_lock (to hold off
+ * slab_mem_going_offline_callback) here because slab's memory hot
+ * unplug code doesn't destroy the kmem_cache->node[] data.
+ */
+
#ifdef CONFIG_SLUB_DEBUG
if (flags & SO_ALL) {
struct kmem_cache_node *n;
@@ -4887,7 +4907,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
x += sprintf(buf + x, " N%d=%lu",
node, nodes[node]);
#endif
- put_online_mems();
kfree(nodes);
return x + sprintf(buf + x, "\n");
}
OpenPOWER on IntegriCloud