summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c7
-rw-r--r--mm/hugetlb.c5
-rw-r--r--mm/memblock.c6
-rw-r--r--mm/memory-failure.c36
-rw-r--r--mm/memremap.c11
-rw-r--r--mm/page_alloc.c8
-rw-r--r--mm/page_owner.c5
-rw-r--r--mm/slab_common.c9
-rw-r--r--mm/slub.c13
-rw-r--r--mm/vmpressure.c20
-rw-r--r--mm/vmscan.c9
-rw-r--r--mm/z3fold.c10
12 files changed, 87 insertions, 52 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index 1e994920e6ff..5ab9c2b22693 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/hugetlb.c b/mm/hugetlb.c
index 6d7296dd11b8..843ee2f8d356 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1084,11 +1084,10 @@ static bool pfn_range_valid_gigantic(struct zone *z,
struct page *page;
for (i = start_pfn; i < end_pfn; i++) {
- if (!pfn_valid(i))
+ page = pfn_to_online_page(i);
+ if (!page)
return false;
- page = pfn_to_page(i);
-
if (page_zone(page) != z)
return false;
diff --git a/mm/memblock.c b/mm/memblock.c
index 7d4f61ae666a..c4b16cae2bc9 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
align = SMP_CACHE_BYTES;
}
- if (end > memblock.current_limit)
- end = memblock.current_limit;
-
again:
found = memblock_find_in_range_node(size, align, start, end, nid,
flags);
@@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal(
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, nid);
+ if (max_addr > memblock.current_limit)
+ max_addr = memblock.current_limit;
+
alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid);
/* retry allocation without lower limit */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7ef849da8278..3151c87dff73 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,
@@ -1253,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags)
if (!sysctl_memory_failure_recovery)
panic("Memory failure on page %lx", pfn);
- if (!pfn_valid(pfn)) {
+ p = pfn_to_online_page(pfn);
+ if (!p) {
+ if (pfn_valid(pfn)) {
+ pgmap = get_dev_pagemap(pfn, NULL);
+ if (pgmap)
+ return memory_failure_dev_pagemap(pfn, flags,
+ pgmap);
+ }
pr_err("Memory failure: %#lx: memory outside kernel control\n",
pfn);
return -ENXIO;
}
- pgmap = get_dev_pagemap(pfn, NULL);
- if (pgmap)
- return memory_failure_dev_pagemap(pfn, flags, pgmap);
-
- p = pfn_to_page(pfn);
if (PageHuge(p))
return memory_failure_hugetlb(pfn, flags);
if (TestSetPageHWPoison(p)) {
diff --git a/mm/memremap.c b/mm/memremap.c
index ed70c4e8e52a..31f1b2953c64 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -104,6 +104,7 @@ static void devm_memremap_pages_release(void *data)
struct dev_pagemap *pgmap = data;
struct device *dev = pgmap->dev;
struct resource *res = &pgmap->res;
+ struct page *first_page;
unsigned long pfn;
int nid;
@@ -112,14 +113,16 @@ static void devm_memremap_pages_release(void *data)
put_page(pfn_to_page(pfn));
dev_pagemap_cleanup(pgmap);
+ /* make sure to access a memmap that was actually initialized */
+ first_page = pfn_to_page(pfn_first(pgmap));
+
/* pages are dead and unused, undo the arch mapping */
- nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
+ nid = page_to_nid(first_page);
mem_hotplug_begin();
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- pfn = PHYS_PFN(res->start);
- __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
- PHYS_PFN(resource_size(res)), NULL);
+ __remove_pages(page_zone(first_page), PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), NULL);
} else {
arch_remove_memory(nid, res->start, resource_size(res),
pgmap_altmap(pgmap));
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c9194959271..bfa5815e59f8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1174,11 +1174,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
- arch_free_page(page, order);
if (want_init_on_free())
kernel_init_free_pages(page, 1 << order);
kernel_poison_pages(page, 1 << order, 0);
+ /*
+ * arch_free_page() can make the page's contents inaccessible. s390
+ * does this. So nothing which can access the page's contents should
+ * happen after this.
+ */
+ arch_free_page(page, order);
+
if (debug_pagealloc_enabled())
kernel_map_pages(page, 1 << order, 0);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index addcbb2ae4e4..8088ab29bc2d 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -258,7 +258,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
* not matter as the mixed block count will still be correct
*/
for (; pfn < end_pfn; ) {
- if (!pfn_valid(pfn)) {
+ page = pfn_to_online_page(pfn);
+ if (!page) {
pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
continue;
}
@@ -266,13 +267,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
block_end_pfn = min(block_end_pfn, end_pfn);
- page = pfn_to_page(pfn);
pageblock_mt = get_pageblock_migratetype(page);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
+ /* The pageblock is online, no need to recheck. */
page = pfn_to_page(pfn);
if (page_zone(page) != zone)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 807490fe217a..7f492e53a7db 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -178,10 +178,13 @@ static int init_memcg_params(struct kmem_cache *s,
static void destroy_memcg_params(struct kmem_cache *s)
{
- if (is_root_cache(s))
+ if (is_root_cache(s)) {
kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
- else
+ } else {
+ mem_cgroup_put(s->memcg_params.memcg);
+ WRITE_ONCE(s->memcg_params.memcg, NULL);
percpu_ref_exit(&s->memcg_params.refcnt);
+ }
}
static void free_memcg_params(struct rcu_head *rcu)
@@ -253,8 +256,6 @@ static void memcg_unlink_cache(struct kmem_cache *s)
} else {
list_del(&s->memcg_params.children_node);
list_del(&s->memcg_params.kmem_caches_node);
- mem_cgroup_put(s->memcg_params.memcg);
- WRITE_ONCE(s->memcg_params.memcg, NULL);
}
}
#else
diff --git a/mm/slub.c b/mm/slub.c
index 8834563cdb4b..dac41cf0b94a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4836,7 +4836,17 @@ 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;
@@ -4877,7 +4887,6 @@ 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");
}
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index f3b50811497a..4bac22fe1aa2 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
* "hierarchy" or "local").
*
* To be used as memcg event method.
+ *
+ * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could
+ * not be parsed.
*/
int vmpressure_register_event(struct mem_cgroup *memcg,
struct eventfd_ctx *eventfd, const char *args)
@@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
struct vmpressure_event *ev;
enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH;
- enum vmpressure_levels level = -1;
+ enum vmpressure_levels level;
char *spec, *spec_orig;
char *token;
int ret = 0;
@@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
/* Find required level */
token = strsep(&spec, ",");
- level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
- if (level < 0) {
- ret = level;
+ ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
+ if (ret < 0)
goto out;
- }
+ level = ret;
/* Find optional mode */
token = strsep(&spec, ",");
if (token) {
- mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
- if (mode < 0) {
- ret = mode;
+ ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
+ if (ret < 0)
goto out;
- }
+ mode = ret;
}
ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
mutex_lock(&vmpr->events_lock);
list_add(&ev->node, &vmpr->events);
mutex_unlock(&vmpr->events_lock);
+ ret = 0;
out:
kfree(spec_orig);
return ret;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a6c5d0b28321..8d03013b6c59 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -354,12 +354,13 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
*/
unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
{
- unsigned long lru_size;
+ unsigned long lru_size = 0;
int zid;
- if (!mem_cgroup_disabled())
- lru_size = lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
- else
+ if (!mem_cgroup_disabled()) {
+ for (zid = 0; zid < MAX_NR_ZONES; zid++)
+ lru_size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+ } else
lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 05bdf90646e7..6d3d3f698ebb 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
struct z3fold_header *zhdr;
struct page *page;
enum buddy bud;
+ bool page_claimed;
zhdr = handle_to_z3fold_header(handle);
page = virt_to_page(zhdr);
+ page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private);
if (test_bit(PAGE_HEADLESS, &page->private)) {
/* if a headless page is under reclaim, just leave.
@@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
* has not been set before, we release this page
* immediately so we don't care about its value any more.
*/
- if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) {
+ if (!page_claimed) {
spin_lock(&pool->lock);
list_del(&page->lru);
spin_unlock(&pool->lock);
@@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
atomic64_dec(&pool->pages_nr);
return;
}
- if (test_bit(PAGE_CLAIMED, &page->private)) {
+ if (page_claimed) {
+ /* the page has not been claimed by us */
z3fold_page_unlock(zhdr);
return;
}
if (unlikely(PageIsolated(page)) ||
test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
z3fold_page_unlock(zhdr);
+ clear_bit(PAGE_CLAIMED, &page->private);
return;
}
if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) {
@@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
zhdr->cpu = -1;
kref_get(&zhdr->refcount);
do_compact_page(zhdr, true);
+ clear_bit(PAGE_CLAIMED, &page->private);
return;
}
kref_get(&zhdr->refcount);
queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
+ clear_bit(PAGE_CLAIMED, &page->private);
z3fold_page_unlock(zhdr);
}
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-16 13:27:31 +0000