The patch titled
Subject: shmem: split huge pages beyond i_size under memory pressure
has been added to the -mm tree. Its filename is
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: shmem: split huge pages beyond i_size under memory pressure
Even if user asked to allocate huge pages always (huge=always), we
should be able to free up some memory by splitting pages which are
partly byound i_size if memory presure comes or once we hit limit on
filesystem size (-o size=).
In order to do this we maintain per-superblock list of inodes, which
potentially have huge pages on the border of file size.
Per-fs shrinker can reclaim memory by splitting such pages.
If we hit -ENOSPC during shmem_getpage_gfp(), we try to split a page to
free up space on the filesystem and retry allocation if it succeed.
Link: http://lkml.kernel.org/r/1465297246-98985-32-git-send-email-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Jerome Marchand <jmarchan@xxxxxxxxxx>
Cc: Yang Shi <yang.shi@xxxxxxxxxx>
Cc: Sasha Levin <sasha.levin@xxxxxxxxxx>
Cc: Andres Lagar-Cavilla <andreslc@xxxxxxxxxx>
Cc: Ning Qu <quning@xxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/shmem_fs.h | 6 +
mm/shmem.c | 175 +++++++++++++++++++++++++++++++++++++
2 files changed, 180 insertions(+), 1 deletion(-)
diff -puN include/linux/shmem_fs.h~shmem-split-huge-pages-beyond-i_size-under-memory-pressure include/linux/shmem_fs.h
--- a/include/linux/shmem_fs.h~shmem-split-huge-pages-beyond-i_size-under-memory-pressure
+++ a/include/linux/shmem_fs.h
@@ -16,8 +16,9 @@ struct shmem_inode_info {
unsigned long flags;
unsigned long alloced; /* data pages alloced to file */
unsigned long swapped; /* subtotal assigned to swap */
- struct shared_policy policy; /* NUMA memory alloc policy */
+ struct list_head shrinklist; /* shrinkable hpage inodes */
struct list_head swaplist; /* chain of maybes on swap */
+ struct shared_policy policy; /* NUMA memory alloc policy */
struct simple_xattrs xattrs; /* list of xattrs */
struct inode vfs_inode;
};
@@ -33,6 +34,9 @@ struct shmem_sb_info {
kuid_t uid; /* Mount uid for root directory */
kgid_t gid; /* Mount gid for root directory */
struct mempolicy *mpol; /* default memory policy for mappings */
+ spinlock_t shrinklist_lock; /* Protects shrinklist */
+ struct list_head shrinklist; /* List of shinkable inodes */
+ unsigned long shrinklist_len; /* Length of shrinklist */
};
static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
diff -puN mm/shmem.c~shmem-split-huge-pages-beyond-i_size-under-memory-pressure mm/shmem.c
--- a/mm/shmem.c~shmem-split-huge-pages-beyond-i_size-under-memory-pressure
+++ a/mm/shmem.c
@@ -188,6 +188,7 @@ static const struct inode_operations shm
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static const struct vm_operations_struct shmem_vm_ops;
+static struct file_system_type shmem_fs_type;
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
@@ -406,10 +407,122 @@ static const char *shmem_format_huge(int
}
}
+static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
+ struct shrink_control *sc, unsigned long nr_to_split)
+{
+ LIST_HEAD(list), *pos, *next;
+ struct inode *inode;
+ struct shmem_inode_info *info;
+ struct page *page;
+ unsigned long batch = sc ? sc->nr_to_scan : 128;
+ int removed = 0, split = 0;
+
+ if (list_empty(&sbinfo->shrinklist))
+ return SHRINK_STOP;
+
+ spin_lock(&sbinfo->shrinklist_lock);
+ list_for_each_safe(pos, next, &sbinfo->shrinklist) {
+ info = list_entry(pos, struct shmem_inode_info, shrinklist);
+
+ /* pin the inode */
+ inode = igrab(&info->vfs_inode);
+
+ /* inode is about to be evicted */
+ if (!inode) {
+ list_del_init(&info->shrinklist);
+ removed++;
+ goto next;
+ }
+
+ /* Check if there's anything to gain */
+ if (round_up(inode->i_size, PAGE_SIZE) ==
+ round_up(inode->i_size, HPAGE_PMD_SIZE)) {
+ list_del_init(&info->shrinklist);
+ removed++;
+ iput(inode);
+ goto next;
+ }
+
+ list_move(&info->shrinklist, &list);
+next:
+ if (!--batch)
+ break;
+ }
+ spin_unlock(&sbinfo->shrinklist_lock);
+
+ list_for_each_safe(pos, next, &list) {
+ int ret;
+
+ info = list_entry(pos, struct shmem_inode_info, shrinklist);
+ inode = &info->vfs_inode;
+
+ if (nr_to_split && split >= nr_to_split) {
+ iput(inode);
+ continue;
+ }
+
+ page = find_lock_page(inode->i_mapping,
+ (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
+ if (!page)
+ goto drop;
+
+ if (!PageTransHuge(page)) {
+ unlock_page(page);
+ put_page(page);
+ goto drop;
+ }
+
+ ret = split_huge_page(page);
+ unlock_page(page);
+ put_page(page);
+
+ if (ret) {
+ /* split failed: leave it on the list */
+ iput(inode);
+ continue;
+ }
+
+ split++;
+drop:
+ list_del_init(&info->shrinklist);
+ removed++;
+ iput(inode);
+ }
+
+ spin_lock(&sbinfo->shrinklist_lock);
+ list_splice_tail(&list, &sbinfo->shrinklist);
+ sbinfo->shrinklist_len -= removed;
+ spin_unlock(&sbinfo->shrinklist_lock);
+
+ return split;
+}
+
+static long shmem_unused_huge_scan(struct super_block *sb,
+ struct shrink_control *sc)
+{
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+
+ if (!READ_ONCE(sbinfo->shrinklist_len))
+ return SHRINK_STOP;
+
+ return shmem_unused_huge_shrink(sbinfo, sc, 0);
+}
+
+static long shmem_unused_huge_count(struct super_block *sb,
+ struct shrink_control *sc)
+{
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+ return READ_ONCE(sbinfo->shrinklist_len);
+}
#else /* !CONFIG_TRANSPARENT_HUGE_PAGECACHE */
#define shmem_huge SHMEM_HUGE_DENY
+static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
+ struct shrink_control *sc, unsigned long nr_to_split)
+{
+ return 0;
+}
#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
/*
@@ -843,6 +956,7 @@ static int shmem_setattr(struct dentry *
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
+ struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
error = inode_change_ok(inode, attr);
@@ -878,6 +992,20 @@ static int shmem_setattr(struct dentry *
if (oldsize > holebegin)
unmap_mapping_range(inode->i_mapping,
holebegin, 0, 1);
+
+ /*
+ * Part of the huge page can be beyond i_size: subject
+ * to shrink under memory pressure.
+ */
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
+ spin_lock(&sbinfo->shrinklist_lock);
+ if (list_empty(&info->shrinklist)) {
+ list_add_tail(&info->shrinklist,
+ &sbinfo->shrinklist);
+ sbinfo->shrinklist_len++;
+ }
+ spin_unlock(&sbinfo->shrinklist_lock);
+ }
}
}
@@ -890,11 +1018,20 @@ static int shmem_setattr(struct dentry *
static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
+ struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (inode->i_mapping->a_ops == &shmem_aops) {
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
shmem_truncate_range(inode, 0, (loff_t)-1);
+ if (!list_empty(&info->shrinklist)) {
+ spin_lock(&sbinfo->shrinklist_lock);
+ if (!list_empty(&info->shrinklist)) {
+ list_del_init(&info->shrinklist);
+ sbinfo->shrinklist_len--;
+ }
+ spin_unlock(&sbinfo->shrinklist_lock);
+ }
if (!list_empty(&info->swaplist)) {
mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
@@ -1563,8 +1700,23 @@ alloc_nohuge: page = shmem_alloc_and_ac
index, false);
}
if (IS_ERR(page)) {
+ int retry = 5;
error = PTR_ERR(page);
page = NULL;
+ if (error != -ENOSPC)
+ goto failed;
+ /*
+ * Try to reclaim some spece by splitting a huge page
+ * beyond i_size on the filesystem.
+ */
+ while (retry--) {
+ int ret;
+ ret = shmem_unused_huge_shrink(sbinfo, NULL, 1);
+ if (ret == SHRINK_STOP)
+ break;
+ if (ret)
+ goto alloc_nohuge;
+ }
goto failed;
}
@@ -1603,6 +1755,22 @@ alloc_nohuge: page = shmem_alloc_and_ac
spin_unlock_irq(&info->lock);
alloced = true;
+ if (PageTransHuge(page) &&
+ DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) <
+ hindex + HPAGE_PMD_NR - 1) {
+ /*
+ * Part of the huge page is beyond i_size: subject
+ * to shrink under memory pressure.
+ */
+ spin_lock(&sbinfo->shrinklist_lock);
+ if (list_empty(&info->shrinklist)) {
+ list_add_tail(&info->shrinklist,
+ &sbinfo->shrinklist);
+ sbinfo->shrinklist_len++;
+ }
+ spin_unlock(&sbinfo->shrinklist_lock);
+ }
+
/*
* Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
*/
@@ -1920,6 +2088,7 @@ static struct inode *shmem_get_inode(str
spin_lock_init(&info->lock);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
+ INIT_LIST_HEAD(&info->shrinklist);
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
@@ -3516,6 +3685,8 @@ int shmem_fill_super(struct super_block
if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
goto failed;
sbinfo->free_inodes = sbinfo->max_inodes;
+ spin_lock_init(&sbinfo->shrinklist_lock);
+ INIT_LIST_HEAD(&sbinfo->shrinklist);
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = PAGE_SIZE;
@@ -3678,6 +3849,10 @@ static const struct super_operations shm
.evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+ .nr_cached_objects = shmem_unused_huge_count,
+ .free_cached_objects = shmem_unused_huge_scan,
+#endif
};
static const struct vm_operations_struct shmem_vm_ops = {
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.patch
a.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
