summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig1
-rw-r--r--mm/backing-dev.c3
-rw-r--r--mm/filemap.c9
-rw-r--r--mm/gup.c3
-rw-r--r--mm/huge_memory.c5
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/migrate.c20
-rw-r--r--mm/mmap.c87
-rw-r--r--mm/oom_kill.c81
-rw-r--r--mm/page-writeback.c18
-rw-r--r--mm/rmap.c3
-rw-r--r--mm/sparse.c2
-rw-r--r--mm/vmscan.c21
-rw-r--r--mm/vmstat.c6
-rw-r--r--mm/z3fold.c42
15 files changed, 208 insertions, 95 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index d5004d82a1d6..e14c01513bfd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -636,6 +636,7 @@ config DEFERRED_STRUCT_PAGE_INIT
default n
depends on NO_BOOTMEM
depends on !FLATMEM
+ depends on !NEED_PER_CPU_KM
help
Ordinarily all struct pages are initialised during early boot in a
single thread. On very large machines this can take a considerable
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 023190c69dce..7441bd93b732 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -115,6 +115,7 @@ static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
bdi, &bdi_debug_stats_fops);
if (!bdi->debug_stats) {
debugfs_remove(bdi->debug_dir);
+ bdi->debug_dir = NULL;
return -ENOMEM;
}
@@ -383,7 +384,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
* the barrier provided by test_and_clear_bit() above.
*/
smp_wmb();
- clear_bit(WB_shutting_down, &wb->state);
+ clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
diff --git a/mm/filemap.c b/mm/filemap.c
index 9276bdb2343c..0604cb02e6f3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -786,7 +786,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
@@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page,
return error;
}
- error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
if (error) {
if (!huge)
mem_cgroup_cancel_charge(page, memcg, false);
@@ -1585,8 +1585,7 @@ no_page:
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, offset,
- gfp_mask & GFP_RECLAIM_MASK);
+ err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (unlikely(err)) {
put_page(page);
page = NULL;
@@ -2387,7 +2386,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
if (!page)
return -ENOMEM;
- ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
+ ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
diff --git a/mm/gup.c b/mm/gup.c
index 76af4cfeaf68..541904a7c60f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
if (vm_flags & (VM_IO | VM_PFNMAP))
return -EFAULT;
+ if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+ return -EFAULT;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 14ed6ee5e02f..a3a1815f8e11 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2925,7 +2925,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
pmde = maybe_pmd_mkwrite(pmde, vma);
flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
- page_add_anon_rmap(new, vma, mmun_start, true);
+ if (PageAnon(new))
+ page_add_anon_rmap(new, vma, mmun_start, true);
+ else
+ page_add_file_rmap(new, true);
set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
if (vma->vm_flags & VM_LOCKED)
mlock_vma_page(new);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e074f7c637aa..2bd3df3d101a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2192,7 +2192,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
{
struct memcg_kmem_cache_create_work *cw;
- cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
+ cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
if (!cw)
return;
diff --git a/mm/migrate.c b/mm/migrate.c
index f65dd69e1fd1..8c0af0f7cab1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -472,7 +472,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
pslot = radix_tree_lookup_slot(&mapping->i_pages,
page_index(page));
- expected_count += 1 + page_has_private(page);
+ expected_count += hpage_nr_pages(page) + page_has_private(page);
if (page_count(page) != expected_count ||
radix_tree_deref_slot_protected(pslot,
&mapping->i_pages.xa_lock) != page) {
@@ -505,7 +505,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
*/
newpage->index = page->index;
newpage->mapping = page->mapping;
- get_page(newpage); /* add cache reference */
+ page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
if (PageSwapBacked(page)) {
__SetPageSwapBacked(newpage);
if (PageSwapCache(page)) {
@@ -524,13 +524,24 @@ int migrate_page_move_mapping(struct address_space *mapping,
}
radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+ if (PageTransHuge(page)) {
+ int i;
+ int index = page_index(page);
+
+ for (i = 1; i < HPAGE_PMD_NR; i++) {
+ pslot = radix_tree_lookup_slot(&mapping->i_pages,
+ index + i);
+ radix_tree_replace_slot(&mapping->i_pages, pslot,
+ newpage + i);
+ }
+ }
/*
* Drop cache reference from old page by unfreezing
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - 1);
+ page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
xa_unlock(&mapping->i_pages);
/* Leave irq disabled to prevent preemption while updating stats */
@@ -1622,6 +1633,9 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
current_node = NUMA_NO_NODE;
}
out_flush:
+ if (list_empty(&pagelist))
+ return err;
+
/* Make sure we do not overwrite the existing error */
err1 = do_move_pages_to_node(mm, &pagelist, current_node);
if (!err1)
diff --git a/mm/mmap.c b/mm/mmap.c
index 188f195883b9..78e14facdb6e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -100,11 +100,20 @@ pgprot_t protection_map[16] __ro_after_init = {
__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};
+#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ return prot;
+}
+#endif
+
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
- return __pgprot(pgprot_val(protection_map[vm_flags &
+ pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
pgprot_val(arch_vm_get_page_prot(vm_flags)));
+
+ return arch_filter_pgprot(ret);
}
EXPORT_SYMBOL(vm_get_page_prot);
@@ -1315,6 +1324,35 @@ static inline int mlock_future_check(struct mm_struct *mm,
return 0;
}
+static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
+{
+ if (S_ISREG(inode->i_mode))
+ return inode->i_sb->s_maxbytes;
+
+ if (S_ISBLK(inode->i_mode))
+ return MAX_LFS_FILESIZE;
+
+ /* Special "we do even unsigned file positions" case */
+ if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+ return 0;
+
+ /* Yes, random drivers might want more. But I'm tired of buggy drivers */
+ return ULONG_MAX;
+}
+
+static inline bool file_mmap_ok(struct file *file, struct inode *inode,
+ unsigned long pgoff, unsigned long len)
+{
+ u64 maxsize = file_mmap_size_max(file, inode);
+
+ if (maxsize && len > maxsize)
+ return false;
+ maxsize -= len;
+ if (pgoff > maxsize >> PAGE_SHIFT)
+ return false;
+ return true;
+}
+
/*
* The caller must hold down_write(&current->mm->mmap_sem).
*/
@@ -1400,6 +1438,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
struct inode *inode = file_inode(file);
unsigned long flags_mask;
+ if (!file_mmap_ok(file, inode, pgoff, len))
+ return -EOVERFLOW;
+
flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
switch (flags & MAP_TYPE) {
@@ -3015,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm)
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
+ if (unlikely(mm_is_oom_victim(mm))) {
+ /*
+ * Manually reap the mm to free as much memory as possible.
+ * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
+ * this mm from further consideration. Taking mm->mmap_sem for
+ * write after setting MMF_OOM_SKIP will guarantee that the oom
+ * reaper will not run on this mm again after mmap_sem is
+ * dropped.
+ *
+ * Nothing can be holding mm->mmap_sem here and the above call
+ * to mmu_notifier_release(mm) ensures mmu notifier callbacks in
+ * __oom_reap_task_mm() will not block.
+ *
+ * This needs to be done before calling munlock_vma_pages_all(),
+ * which clears VM_LOCKED, otherwise the oom reaper cannot
+ * reliably test it.
+ */
+ mutex_lock(&oom_lock);
+ __oom_reap_task_mm(mm);
+ mutex_unlock(&oom_lock);
+
+ set_bit(MMF_OOM_SKIP, &mm->flags);
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ }
+
if (mm->locked_vm) {
vma = mm->mmap;
while (vma) {
@@ -3036,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm)
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
-
- if (unlikely(mm_is_oom_victim(mm))) {
- /*
- * Wait for oom_reap_task() to stop working on this
- * mm. Because MMF_OOM_SKIP is already set before
- * calling down_read(), oom_reap_task() will not run
- * on this "mm" post up_write().
- *
- * mm_is_oom_victim() cannot be set from under us
- * either because victim->mm is already set to NULL
- * under task_lock before calling mmput and oom_mm is
- * set not NULL by the OOM killer only if victim->mm
- * is found not NULL while holding the task_lock.
- */
- set_bit(MMF_OOM_SKIP, &mm->flags);
- down_write(&mm->mmap_sem);
- up_write(&mm->mmap_sem);
- }
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb, 0, -1);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ff992fa8760a..8ba6cb88cf58 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
return false;
}
-
#ifdef CONFIG_MMU
/*
* OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);
-static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+void __oom_reap_task_mm(struct mm_struct *mm)
{
- struct mmu_gather tlb;
struct vm_area_struct *vma;
+
+ /*
+ * Tell all users of get_user/copy_from_user etc... that the content
+ * is no longer stable. No barriers really needed because unmapping
+ * should imply barriers already and the reader would hit a page fault
+ * if it stumbled over a reaped memory.
+ */
+ set_bit(MMF_UNSTABLE, &mm->flags);
+
+ for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+ if (!can_madv_dontneed_vma(vma))
+ continue;
+
+ /*
+ * Only anonymous pages have a good chance to be dropped
+ * without additional steps which we cannot afford as we
+ * are OOM already.
+ *
+ * We do not even care about fs backed pages because all
+ * which are reclaimable have already been reclaimed and
+ * we do not want to block exit_mmap by keeping mm ref
+ * count elevated without a good reason.
+ */
+ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+ const unsigned long start = vma->vm_start;
+ const unsigned long end = vma->vm_end;
+ struct mmu_gather tlb;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ unmap_page_range(&tlb, vma, start, end, NULL);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+ }
+ }
+}
+
+static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
bool ret = true;
/*
* We have to make sure to not race with the victim exit path
* and cause premature new oom victim selection:
- * __oom_reap_task_mm exit_mm
+ * oom_reap_task_mm exit_mm
* mmget_not_zero
* mmput
* atomic_dec_and_test
@@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
trace_start_task_reaping(tsk->pid);
- /*
- * Tell all users of get_user/copy_from_user etc... that the content
- * is no longer stable. No barriers really needed because unmapping
- * should imply barriers already and the reader would hit a page fault
- * if it stumbled over a reaped memory.
- */
- set_bit(MMF_UNSTABLE, &mm->flags);
-
- for (vma = mm->mmap ; vma; vma = vma->vm_next) {
- if (!can_madv_dontneed_vma(vma))
- continue;
+ __oom_reap_task_mm(mm);
- /*
- * Only anonymous pages have a good chance to be dropped
- * without additional steps which we cannot afford as we
- * are OOM already.
- *
- * We do not even care about fs backed pages because all
- * which are reclaimable have already been reclaimed and
- * we do not want to block exit_mmap by keeping mm ref
- * count elevated without a good reason.
- */
- if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
- const unsigned long start = vma->vm_start;
- const unsigned long end = vma->vm_end;
-
- tlb_gather_mmu(&tlb, mm, start, end);
- mmu_notifier_invalidate_range_start(mm, start, end);
- unmap_page_range(&tlb, vma, start, end, NULL);
- mmu_notifier_invalidate_range_end(mm, start, end);
- tlb_finish_mmu(&tlb, start, end);
- }
- }
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk)
struct mm_struct *mm = tsk->signal->oom_mm;
/* Retry the down_read_trylock(mmap_sem) a few times */
- while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
+ while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
if (attempts <= MAX_OOM_REAP_RETRIES ||
test_bit(MMF_OOM_SKIP, &mm->flags))
goto done;
-
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5c1a3279e63f..337c6afb3345 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
current->nr_dirtied--;
dec_node_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
}
}
EXPORT_SYMBOL(account_page_redirty);
@@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page)
if (mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
lock_page_memcg(page);
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page))
account_page_cleaned(page, mapping, wb);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
unlock_page_memcg(page);
} else {
ClearPageDirty(page);
@@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
/*
* Yes, Virginia, this is indeed insane.
@@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page)
* always locked coming in here, so we get the desired
* exclusion.
*/
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page)) {
dec_lruvec_page_state(page, NR_FILE_DIRTY);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
return TestClearPageDirty(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index f0dd4e4565bc..8d5337fed37b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1374,9 +1374,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (!pvmw.pte && (flags & TTU_MIGRATION)) {
VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
- if (!PageAnon(page))
- continue;
-
set_pmd_migration_entry(&pvmw, page);
continue;
}
diff --git a/mm/sparse.c b/mm/sparse.c
index 62eef264a7bd..73dc2fcc0eab 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ unsigned long section_nr = pfn_to_section_nr(pfn);
struct mem_section *ms;
/*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8b920ce3ae02..9b697323a88c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -303,7 +303,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
/*
* Add a shrinker callback to be called from the vm.
*/
-int register_shrinker(struct shrinker *shrinker)
+int prealloc_shrinker(struct shrinker *shrinker)
{
size_t size = sizeof(*shrinker->nr_deferred);
@@ -313,10 +313,29 @@ int register_shrinker(struct shrinker *shrinker)
shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
if (!shrinker->nr_deferred)
return -ENOMEM;
+ return 0;
+}
+
+void free_prealloced_shrinker(struct shrinker *shrinker)
+{
+ kfree(shrinker->nr_deferred);
+ shrinker->nr_deferred = NULL;
+}
+void register_shrinker_prepared(struct shrinker *shrinker)
+{
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
+}
+
+int register_shrinker(struct shrinker *shrinker)
+{
+ int err = prealloc_shrinker(shrinker);
+
+ if (err)
+ return err;
+ register_shrinker_prepared(shrinker);
return 0;
}
EXPORT_SYMBOL(register_shrinker);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 536332e988b8..a2b9518980ce 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = {
"nr_vmscan_immediate_reclaim",
"nr_dirtied",
"nr_written",
- "nr_indirectly_reclaimable",
+ "", /* nr_indirectly_reclaimable */
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
@@ -1740,6 +1740,10 @@ static int vmstat_show(struct seq_file *m, void *arg)
unsigned long *l = arg;
unsigned long off = l - (unsigned long *)m->private;
+ /* Skip hidden vmstat items. */
+ if (*vmstat_text[off] == '\0')
+ return 0;
+
seq_puts(m, vmstat_text[off]);
seq_put_decimal_ull(m, " ", *l);
seq_putc(m, '\n');
diff --git a/mm/z3fold.c b/mm/z3fold.c
index c0bca6153b95..4b366d181f35 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
PAGE_HEADLESS = 0,
MIDDLE_CHUNK_MAPPED,
NEEDS_COMPACTING,
- PAGE_STALE
+ PAGE_STALE,
+ UNDER_RECLAIM
};
/*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page,
clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
clear_bit(NEEDS_COMPACTING, &page->private);
clear_bit(PAGE_STALE, &page->private);
+ clear_bit(UNDER_RECLAIM, &page->private);
spin_lock_init(&zhdr->page_lock);
kref_init(&zhdr->refcount);
@@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
atomic64_dec(&pool->pages_nr);
return;
}
+ if (test_bit(UNDER_RECLAIM, &page->private)) {
+ z3fold_page_unlock(zhdr);
+ return;
+ }
if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
z3fold_page_unlock(zhdr);
return;
@@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
kref_get(&zhdr->refcount);
list_del_init(&zhdr->buddy);
zhdr->cpu = -1;
+ set_bit(UNDER_RECLAIM, &page->private);
+ break;
}
list_del_init(&page->lru);
@@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
goto next;
}
next:
- spin_lock(&pool->lock);
if (test_bit(PAGE_HEADLESS, &page->private)) {
if (ret == 0) {
- spin_unlock(&pool->lock);
free_z3fold_page(page);
return 0;
}
- } else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
- atomic64_dec(&pool->pages_nr);
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
+ spin_unlock(&pool->lock);
+ } else {
+ z3fold_page_lock(zhdr);
+ clear_bit(UNDER_RECLAIM, &page->private);
+ if (kref_put(&zhdr->refcount,
+ release_z3fold_page_locked)) {
+ atomic64_dec(&pool->pages_nr);
+ return 0;
+ }
+ /*
+ * if we are here, the page is still not completely
+ * free. Take the global pool lock then to be able
+ * to add it back to the lru list
+ */
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
spin_unlock(&pool->lock);
- return 0;
+ z3fold_page_unlock(zhdr);
}
- /*
- * Add to the beginning of LRU.
- * Pool lock has to be kept here to ensure the page has
- * not already been released
- */
- list_add(&page->lru, &pool->lru);
+ /* We started off locked to we need to lock the pool back */
+ spin_lock(&pool->lock);
}
spin_unlock(&pool->lock);
return -EAGAIN;
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-06-03 07:15:54 +0000