Merge branch 'akpm' (incoming from Andrew)
Merge misc fixes from Andrew Morton:
"13 fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
agp: info leak in agpioc_info_wrap()
fs/affs/super.c: bugfix / double free
fanotify: fix -EOVERFLOW with large files on 64-bit
slub: use sysfs'es release mechanism for kmem_cache
revert "mm: vmscan: do not swap anon pages just because free+file is low"
autofs: fix lockref lookup
mm: filemap: update find_get_pages_tag() to deal with shadow entries
mm/compaction: make isolate_freepages start at pageblock boundary
MAINTAINERS: zswap/zbud: change maintainer email address
mm/page-writeback.c: fix divide by zero in pos_ratio_polynom
hugetlb: ensure hugepage access is denied if hugepages are not supported
slub: fix memcg_propagate_slab_attrs
drivers/rtc/rtc-pcf8523.c: fix month definition
diff --git a/MAINTAINERS b/MAINTAINERS
index 7578deb..51ebb77 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9960,7 +9960,7 @@
F: drivers/net/hamradio/z8530.h
ZBUD COMPRESSED PAGE ALLOCATOR
-M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+M: Seth Jennings <sjennings@variantweb.net>
L: linux-mm@kvack.org
S: Maintained
F: mm/zbud.c
@@ -10005,7 +10005,7 @@
F: include/linux/zsmalloc.h
ZSWAP COMPRESSED SWAP CACHING
-M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+M: Seth Jennings <sjennings@variantweb.net>
L: linux-mm@kvack.org
S: Maintained
F: mm/zswap.c
diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index 8121b4c..b297033 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -730,6 +730,7 @@
agp_copy_info(agp_bridge, &kerninfo);
+ memset(&userinfo, 0, sizeof(userinfo));
userinfo.version.major = kerninfo.version.major;
userinfo.version.minor = kerninfo.version.minor;
userinfo.bridge_id = kerninfo.device->vendor |
diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c
index 5c8f822..4cdb64b 100644
--- a/drivers/rtc/rtc-pcf8523.c
+++ b/drivers/rtc/rtc-pcf8523.c
@@ -206,7 +206,7 @@
tm->tm_hour = bcd2bin(regs[2] & 0x3f);
tm->tm_mday = bcd2bin(regs[3] & 0x3f);
tm->tm_wday = regs[4] & 0x7;
- tm->tm_mon = bcd2bin(regs[5] & 0x1f);
+ tm->tm_mon = bcd2bin(regs[5] & 0x1f) - 1;
tm->tm_year = bcd2bin(regs[6]) + 100;
return rtc_valid_tm(tm);
@@ -229,7 +229,7 @@
regs[3] = bin2bcd(tm->tm_hour);
regs[4] = bin2bcd(tm->tm_mday);
regs[5] = tm->tm_wday;
- regs[6] = bin2bcd(tm->tm_mon);
+ regs[6] = bin2bcd(tm->tm_mon + 1);
regs[7] = bin2bcd(tm->tm_year - 100);
msg.addr = client->addr;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 6d589f2..895ac7d 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -340,8 +340,6 @@
&blocksize,&sbi->s_prefix,
sbi->s_volume, &mount_flags)) {
printk(KERN_ERR "AFFS: Error parsing options\n");
- kfree(sbi->s_prefix);
- kfree(sbi);
return -EINVAL;
}
/* N.B. after this point s_prefix must be released */
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 2caf36a..cc87c1a 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -179,7 +179,7 @@
spin_lock(&active->d_lock);
/* Already gone? */
- if (!d_count(active))
+ if ((int) d_count(active) <= 0)
goto next;
qstr = &active->d_name;
@@ -230,7 +230,7 @@
spin_lock(&expiring->d_lock);
- /* Bad luck, we've already been dentry_iput */
+ /* We've already been dentry_iput or unlinked */
if (!expiring->d_inode)
goto next;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 2040275..e19d4c0 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1030,6 +1030,11 @@
int error;
int i;
+ if (!hugepages_supported()) {
+ pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n");
+ return -ENOTSUPP;
+ }
+
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
return error;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 4e565c8..732648b 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,8 @@
}
group->overflow_event = &oevent->fse;
+ if (force_o_largefile())
+ event_f_flags |= O_LARGEFILE;
group->fanotify_data.f_flags = event_f_flags;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
spin_lock_init(&group->fanotify_data.access_lock);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b337cf..b65166d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -412,6 +412,16 @@
return &mm->page_table_lock;
}
+static inline bool hugepages_supported(void)
+{
+ /*
+ * Some platform decide whether they support huge pages at boot
+ * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
+ * there is no such support
+ */
+ return HPAGE_SHIFT != 0;
+}
+
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index f2f7398..d82abd4 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -101,4 +101,13 @@
struct kmem_cache_node *node[MAX_NUMNODES];
};
+#ifdef CONFIG_SYSFS
+#define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_remove(struct kmem_cache *);
+#else
+static inline void sysfs_slab_remove(struct kmem_cache *s)
+{
+}
+#endif
+
#endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/compaction.c b/mm/compaction.c
index 37f9762..627dc2e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -671,16 +671,20 @@
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+ unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
/*
* Initialise the free scanner. The starting point is where we last
- * scanned from (or the end of the zone if starting). The low point
- * is the end of the pageblock the migration scanner is using.
+ * successfully isolated from, zone-cached value, or the end of the
+ * zone when isolating for the first time. We need this aligned to
+ * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+ * in the for loop.
+ * The low boundary is the end of the pageblock the migration scanner
+ * is using.
*/
- pfn = cc->free_pfn;
+ pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
@@ -700,6 +704,7 @@
for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
+ unsigned long end_pfn;
/*
* This can iterate a massively long zone without finding any
@@ -734,13 +739,10 @@
isolated = 0;
/*
- * As pfn may not start aligned, pfn+pageblock_nr_page
- * may cross a MAX_ORDER_NR_PAGES boundary and miss
- * a pfn_valid check. Ensure isolate_freepages_block()
- * only scans within a pageblock
+ * Take care when isolating in last pageblock of a zone which
+ * ends in the middle of a pageblock.
*/
- end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
- end_pfn = min(end_pfn, z_end_pfn);
+ end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
isolated = isolate_freepages_block(cc, pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
diff --git a/mm/filemap.c b/mm/filemap.c
index 5020b28..000a220 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -906,8 +906,8 @@
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*/
@@ -928,9 +928,9 @@
if (radix_tree_deref_retry(page))
goto repeat;
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so return it without
- * attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto out;
}
@@ -983,8 +983,8 @@
* page cache page, it is returned locked and with an increased
* refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*
@@ -1099,8 +1099,8 @@
* with ascending indexes. There may be holes in the indices due to
* not-present pages.
*
- * Any shadow entries of evicted pages are included in the returned
- * array.
+ * Any shadow entries of evicted pages, or swap entries from
+ * shmem/tmpfs, are included in the returned array.
*
* find_get_entries() returns the number of pages and shadow entries
* which were found.
@@ -1128,9 +1128,9 @@
if (radix_tree_deref_retry(page))
goto restart;
/*
- * Otherwise, we must be storing a swap entry
- * here as an exceptional entry: so return it
- * without attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto export;
}
@@ -1198,9 +1198,9 @@
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so skip over it -
- * we only reach this from invalidate_mapping_pages().
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Skip
+ * over it.
*/
continue;
}
@@ -1265,9 +1265,9 @@
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so stop looking for
- * contiguous pages.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Stop
+ * looking for contiguous pages.
*/
break;
}
@@ -1341,10 +1341,17 @@
goto restart;
}
/*
- * This function is never used on a shmem/tmpfs
- * mapping, so a swap entry won't be found here.
+ * A shadow entry of a recently evicted page.
+ *
+ * Those entries should never be tagged, but
+ * this tree walk is lockless and the tags are
+ * looked up in bulk, one radix tree node at a
+ * time, so there is a sizable window for page
+ * reclaim to evict a page we saw tagged.
+ *
+ * Skip over it.
*/
- BUG();
+ continue;
}
if (!page_cache_get_speculative(page))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2461929..c82290b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1981,11 +1981,7 @@
{
int i;
- /* Some platform decide whether they support huge pages at boot
- * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
- * there is no such support
- */
- if (HPAGE_SHIFT == 0)
+ if (!hugepages_supported())
return 0;
if (!size_to_hstate(default_hstate_size)) {
@@ -2112,6 +2108,9 @@
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->max_huge_pages;
if (write && h->order >= MAX_ORDER)
@@ -2165,6 +2164,9 @@
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->nr_overcommit_huge_pages;
if (write && h->order >= MAX_ORDER)
@@ -2190,6 +2192,8 @@
void hugetlb_report_meminfo(struct seq_file *m)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return;
seq_printf(m,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
@@ -2206,6 +2210,8 @@
int hugetlb_report_node_meminfo(int nid, char *buf)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return 0;
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
"Node %d HugePages_Free: %5u\n"
@@ -2220,6 +2226,9 @@
struct hstate *h;
int nid;
+ if (!hugepages_supported())
+ return;
+
for_each_node_state(nid, N_MEMORY)
for_each_hstate(h)
pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 29501f0..c47dffd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6686,16 +6686,20 @@
pgoff = pte_to_pgoff(ptent);
/* page is moved even if it's not RSS of this task(page-faulted). */
- page = find_get_page(mapping, pgoff);
-
#ifdef CONFIG_SWAP
/* shmem/tmpfs may report page out on swap: account for that too. */
- if (radix_tree_exceptional_entry(page)) {
- swp_entry_t swap = radix_to_swp_entry(page);
- if (do_swap_account)
- *entry = swap;
- page = find_get_page(swap_address_space(swap), swap.val);
- }
+ if (shmem_mapping(mapping)) {
+ page = find_get_entry(mapping, pgoff);
+ if (radix_tree_exceptional_entry(page)) {
+ swp_entry_t swp = radix_to_swp_entry(page);
+ if (do_swap_account)
+ *entry = swp;
+ page = find_get_page(swap_address_space(swp), swp.val);
+ }
+ } else
+ page = find_get_page(mapping, pgoff);
+#else
+ page = find_get_page(mapping, pgoff);
#endif
return page;
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ef41349..a4317da 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -593,14 +593,14 @@
* (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
* => fast response on large errors; small oscillation near setpoint
*/
-static inline long long pos_ratio_polynom(unsigned long setpoint,
+static long long pos_ratio_polynom(unsigned long setpoint,
unsigned long dirty,
unsigned long limit)
{
long long pos_ratio;
long x;
- x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+ x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
limit - setpoint + 1);
pos_ratio = x;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -842,7 +842,7 @@
x_intercept = bdi_setpoint + span;
if (bdi_dirty < x_intercept - span / 4) {
- pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+ pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
x_intercept - bdi_setpoint + 1);
} else
pos_ratio /= 4;
diff --git a/mm/slab.h b/mm/slab.h
index 3045316..6bd4c35 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -91,6 +91,7 @@
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
int __kmem_cache_shutdown(struct kmem_cache *);
+void slab_kmem_cache_release(struct kmem_cache *);
struct seq_file;
struct file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f3cfccf..102cc6f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -323,6 +323,12 @@
}
#endif /* CONFIG_MEMCG_KMEM */
+void slab_kmem_cache_release(struct kmem_cache *s)
+{
+ kfree(s->name);
+ kmem_cache_free(kmem_cache, s);
+}
+
void kmem_cache_destroy(struct kmem_cache *s)
{
get_online_cpus();
@@ -352,8 +358,11 @@
rcu_barrier();
memcg_free_cache_params(s);
- kfree(s->name);
- kmem_cache_free(kmem_cache, s);
+#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_remove(s);
+#else
+ slab_kmem_cache_release(s);
+#endif
goto out_put_cpus;
out_unlock:
diff --git a/mm/slub.c b/mm/slub.c
index 5e234f1..2b1ce69 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -210,14 +210,11 @@
#ifdef CONFIG_SYSFS
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 *);
static void memcg_propagate_slab_attrs(struct kmem_cache *s);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
-
static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
#endif
@@ -3238,24 +3235,7 @@
int __kmem_cache_shutdown(struct kmem_cache *s)
{
- int rc = kmem_cache_close(s);
-
- if (!rc) {
- /*
- * Since slab_attr_store may take the slab_mutex, we should
- * release the lock while removing the sysfs entry in order to
- * avoid a deadlock. Because this is pretty much the last
- * operation we do and the lock will be released shortly after
- * that in slab_common.c, we could just move sysfs_slab_remove
- * to a later point in common code. We should do that when we
- * have a common sysfs framework for all allocators.
- */
- mutex_unlock(&slab_mutex);
- sysfs_slab_remove(s);
- mutex_lock(&slab_mutex);
- }
-
- return rc;
+ return kmem_cache_close(s);
}
/********************************************************************
@@ -5071,15 +5051,18 @@
#ifdef CONFIG_MEMCG_KMEM
int i;
char *buffer = NULL;
+ struct kmem_cache *root_cache;
- if (!is_root_cache(s))
+ if (is_root_cache(s))
return;
+ root_cache = s->memcg_params->root_cache;
+
/*
* This mean this cache had no attribute written. Therefore, no point
* in copying default values around
*/
- if (!s->max_attr_size)
+ if (!root_cache->max_attr_size)
return;
for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
@@ -5101,7 +5084,7 @@
*/
if (buffer)
buf = buffer;
- else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+ else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
buf = mbuf;
else {
buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5110,7 +5093,7 @@
buf = buffer;
}
- attr->show(s->memcg_params->root_cache, buf);
+ attr->show(root_cache, buf);
attr->store(s, buf, strlen(buf));
}
@@ -5119,6 +5102,11 @@
#endif
}
+static void kmem_cache_release(struct kobject *k)
+{
+ slab_kmem_cache_release(to_slab(k));
+}
+
static const struct sysfs_ops slab_sysfs_ops = {
.show = slab_attr_show,
.store = slab_attr_store,
@@ -5126,6 +5114,7 @@
static struct kobj_type slab_ktype = {
.sysfs_ops = &slab_sysfs_ops,
+ .release = kmem_cache_release,
};
static int uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -5252,7 +5241,7 @@
goto out;
}
-static void sysfs_slab_remove(struct kmem_cache *s)
+void sysfs_slab_remove(struct kmem_cache *s)
{
if (slab_state < FULL)
/*
diff --git a/mm/truncate.c b/mm/truncate.c
index e5cc39a..6a78c81 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -484,14 +484,6 @@
unsigned long count = 0;
int i;
- /*
- * Note: this function may get called on a shmem/tmpfs mapping:
- * pagevec_lookup() might then return 0 prematurely (because it
- * got a gangful of swap entries); but it's hardly worth worrying
- * about - it can rarely have anything to free from such a mapping
- * (most pages are dirty), and already skips over any difficulties.
- */
-
pagevec_init(&pvec, 0);
while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3f56c8d..32c661d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1916,6 +1916,24 @@
get_lru_size(lruvec, LRU_INACTIVE_FILE);
/*
+ * Prevent the reclaimer from falling into the cache trap: as
+ * cache pages start out inactive, every cache fault will tip
+ * the scan balance towards the file LRU. And as the file LRU
+ * shrinks, so does the window for rotation from references.
+ * This means we have a runaway feedback loop where a tiny
+ * thrashing file LRU becomes infinitely more attractive than
+ * anon pages. Try to detect this based on file LRU size.
+ */
+ if (global_reclaim(sc)) {
+ unsigned long free = zone_page_state(zone, NR_FREE_PAGES);
+
+ if (unlikely(file + free <= high_wmark_pages(zone))) {
+ scan_balance = SCAN_ANON;
+ goto out;
+ }
+ }
+
+ /*
* There is enough inactive page cache, do not reclaim
* anything from the anonymous working set right now.
*/
