summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c25
-rw-r--r--mm/gup.c13
-rw-r--r--mm/memcontrol.c12
-rw-r--r--mm/memory.c27
-rw-r--r--mm/mmap.c2
-rw-r--r--mm/page_alloc.c7
-rw-r--r--mm/shmem.c11
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slab_common.c138
-rw-r--r--mm/slub.c24
-rw-r--r--mm/userfaultfd.c29
-rw-r--r--mm/vmalloc.c7
-rw-r--r--mm/vmscan.c24
13 files changed, 211 insertions, 110 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index d62150418b91..60a9cc593e9b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2712,14 +2712,12 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
}
EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
-int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
+int filemap_invalidate_pages(struct address_space *mapping,
+ loff_t pos, loff_t end, bool nowait)
{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- loff_t pos = iocb->ki_pos;
- loff_t end = pos + count - 1;
int ret;
- if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (nowait) {
/* we could block if there are any pages in the range */
if (filemap_range_has_page(mapping, pos, end))
return -EAGAIN;
@@ -2738,6 +2736,15 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
+
+int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
+{
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+ return filemap_invalidate_pages(mapping, iocb->ki_pos,
+ iocb->ki_pos + count - 1,
+ iocb->ki_flags & IOCB_NOWAIT);
+}
EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
/**
@@ -3987,7 +3994,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
ssize_t written = 0;
do {
- struct page *page;
struct folio *folio;
size_t offset; /* Offset into folio */
size_t bytes; /* Bytes to write to folio */
@@ -4017,11 +4023,10 @@ retry:
}
status = a_ops->write_begin(file, mapping, pos, bytes,
- &page, &fsdata);
+ &folio, &fsdata);
if (unlikely(status < 0))
break;
- folio = page_folio(page);
offset = offset_in_folio(folio, pos);
if (bytes > folio_size(folio) - offset)
bytes = folio_size(folio) - offset;
@@ -4033,7 +4038,7 @@ retry:
flush_dcache_folio(folio);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
- page, fsdata);
+ folio, fsdata);
if (unlikely(status != copied)) {
iov_iter_revert(i, copied - max(status, 0L));
if (unlikely(status < 0))
@@ -4231,7 +4236,7 @@ int filemap_invalidate_inode(struct inode *inode, bool flush,
}
/* Wait for writeback to complete on all folios and discard. */
- truncate_inode_pages_range(mapping, start, end);
+ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE);
unlock:
filemap_invalidate_unlock(mapping);
diff --git a/mm/gup.c b/mm/gup.c
index 54d0dc3831fb..02c46ae33028 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -416,6 +416,19 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
EXPORT_SYMBOL(unpin_user_pages);
/**
+ * unpin_user_folio() - release pages of a folio
+ * @folio: pointer to folio to be released
+ * @npages: number of pages of same folio
+ *
+ * Release npages of the folio
+ */
+void unpin_user_folio(struct folio *folio, unsigned long npages)
+{
+ gup_put_folio(folio, npages, FOLL_PIN);
+}
+EXPORT_SYMBOL(unpin_user_folio);
+
+/**
* unpin_folios() - release an array of gup-pinned folios.
* @folios: array of folios to be marked dirty and released.
* @nfolios: number of folios in the @folios array.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f29157288b7d..d563fb515766 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3613,8 +3613,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
memcg1_soft_limit_reset(memcg);
#ifdef CONFIG_ZSWAP
memcg->zswap_max = PAGE_COUNTER_MAX;
- WRITE_ONCE(memcg->zswap_writeback,
- !parent || READ_ONCE(parent->zswap_writeback));
+ WRITE_ONCE(memcg->zswap_writeback, true);
#endif
page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
if (parent) {
@@ -5320,7 +5319,14 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
{
/* if zswap is disabled, do not block pages going to the swapping device */
- return !zswap_is_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
+ if (!zswap_is_enabled())
+ return true;
+
+ for (; memcg; memcg = parent_mem_cgroup(memcg))
+ if (!READ_ONCE(memcg->zswap_writeback))
+ return false;
+
+ return true;
}
static u64 zswap_current_read(struct cgroup_subsys_state *css,
diff --git a/mm/memory.c b/mm/memory.c
index 3c01d68065be..ebfc9768f801 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2632,11 +2632,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
return 0;
}
-/*
- * Variant of remap_pfn_range that does not call track_pfn_remap. The caller
- * must have pre-validated the caching bits of the pgprot_t.
- */
-int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
@@ -2689,6 +2685,27 @@ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
return 0;
}
+/*
+ * Variant of remap_pfn_range that does not call track_pfn_remap. The caller
+ * must have pre-validated the caching bits of the pgprot_t.
+ */
+int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+ int error = remap_pfn_range_internal(vma, addr, pfn, size, prot);
+
+ if (!error)
+ return 0;
+
+ /*
+ * A partial pfn range mapping is dangerous: it does not
+ * maintain page reference counts, and callers may free
+ * pages due to the error. So zap it early.
+ */
+ zap_page_range_single(vma, addr, size, NULL);
+ return error;
+}
+
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
diff --git a/mm/mmap.c b/mm/mmap.c
index d0dfc85b209b..6ddb278a5ee8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1229,7 +1229,7 @@ static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
return MAX_LFS_FILESIZE;
/* Special "we do even unsigned file positions" case */
- if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+ if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET)
return 0;
/* Yes, random drivers might want more. But I'm tired of buggy drivers */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c565de8f48e9..91ace8ca97e2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1054,6 +1054,13 @@ __always_inline bool free_pages_prepare(struct page *page,
reset_page_owner(page, order);
page_table_check_free(page, order);
pgalloc_tag_sub(page, 1 << order);
+
+ /*
+ * The page is isolated and accounted for.
+ * Mark the codetag as empty to avoid accounting error
+ * when the page is freed by unpoison_memory().
+ */
+ clear_page_tag_ref(page);
return false;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 5a77acf6ac6a..b875852df51f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2878,7 +2878,7 @@ static const struct inode_operations shmem_short_symlink_operations;
static int
shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
- struct page **pagep, void **fsdata)
+ struct folio **foliop, void **fsdata)
{
struct inode *inode = mapping->host;
struct shmem_inode_info *info = SHMEM_I(inode);
@@ -2899,23 +2899,22 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
if (ret)
return ret;
- *pagep = folio_file_page(folio, index);
- if (PageHWPoison(*pagep)) {
+ if (folio_test_hwpoison(folio) ||
+ (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
folio_unlock(folio);
folio_put(folio);
- *pagep = NULL;
return -EIO;
}
+ *foliop = folio;
return 0;
}
static int
shmem_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+ struct folio *folio, void *fsdata)
{
- struct folio *folio = page_folio(page);
struct inode *inode = mapping->host;
if (pos + copied > inode->i_size)
diff --git a/mm/slab.h b/mm/slab.h
index dcdb56b8e7f5..a6051385186e 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -261,6 +261,8 @@ struct kmem_cache {
unsigned int object_size; /* Object size without metadata */
struct reciprocal_value reciprocal_size;
unsigned int offset; /* Free pointer offset */
+ /* Specific free pointer requested (if not UINT_MAX) */
+ unsigned int rcu_freeptr_offset;
#ifdef CONFIG_SLUB_CPU_PARTIAL
/* Number of per cpu partial objects to keep around */
unsigned int cpu_partial;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 40b582a014b8..95db3702f8d6 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -202,10 +202,10 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
}
static struct kmem_cache *create_cache(const char *name,
- unsigned int object_size, unsigned int align,
- slab_flags_t flags, unsigned int useroffset,
- unsigned int usersize, void (*ctor)(void *),
- struct kmem_cache *root_cache)
+ unsigned int object_size, unsigned int freeptr_offset,
+ unsigned int align, slab_flags_t flags,
+ unsigned int useroffset, unsigned int usersize,
+ void (*ctor)(void *))
{
struct kmem_cache *s;
int err;
@@ -213,6 +213,13 @@ static struct kmem_cache *create_cache(const char *name,
if (WARN_ON(useroffset + usersize > object_size))
useroffset = usersize = 0;
+ /* If a custom freelist pointer is requested make sure it's sane. */
+ err = -EINVAL;
+ if (freeptr_offset != UINT_MAX &&
+ (freeptr_offset >= object_size || !(flags & SLAB_TYPESAFE_BY_RCU) ||
+ !IS_ALIGNED(freeptr_offset, sizeof(freeptr_t))))
+ goto out;
+
err = -ENOMEM;
s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
if (!s)
@@ -220,13 +227,13 @@ static struct kmem_cache *create_cache(const char *name,
s->name = name;
s->size = s->object_size = object_size;
+ s->rcu_freeptr_offset = freeptr_offset;
s->align = align;
s->ctor = ctor;
#ifdef CONFIG_HARDENED_USERCOPY
s->useroffset = useroffset;
s->usersize = usersize;
#endif
-
err = __kmem_cache_create(s, flags);
if (err)
goto out_free_cache;
@@ -241,38 +248,10 @@ out:
return ERR_PTR(err);
}
-/**
- * kmem_cache_create_usercopy - Create a cache with a region suitable
- * for copying to userspace
- * @name: A string which is used in /proc/slabinfo to identify this cache.
- * @size: The size of objects to be created in this cache.
- * @align: The required alignment for the objects.
- * @flags: SLAB flags
- * @useroffset: Usercopy region offset
- * @usersize: Usercopy region size
- * @ctor: A constructor for the objects.
- *
- * Cannot be called within a interrupt, but can be interrupted.
- * The @ctor is run when new pages are allocated by the cache.
- *
- * The flags are
- *
- * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
- * to catch references to uninitialised memory.
- *
- * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
- * for buffer overruns.
- *
- * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
- * cacheline. This can be beneficial if you're counting cycles as closely
- * as davem.
- *
- * Return: a pointer to the cache on success, NULL on failure.
- */
-struct kmem_cache *
-kmem_cache_create_usercopy(const char *name,
- unsigned int size, unsigned int align,
- slab_flags_t flags,
+static struct kmem_cache *
+do_kmem_cache_create_usercopy(const char *name,
+ unsigned int size, unsigned int freeptr_offset,
+ unsigned int align, slab_flags_t flags,
unsigned int useroffset, unsigned int usersize,
void (*ctor)(void *))
{
@@ -332,9 +311,9 @@ kmem_cache_create_usercopy(const char *name,
goto out_unlock;
}
- s = create_cache(cache_name, size,
+ s = create_cache(cache_name, size, freeptr_offset,
calculate_alignment(flags, align, size),
- flags, useroffset, usersize, ctor, NULL);
+ flags, useroffset, usersize, ctor);
if (IS_ERR(s)) {
err = PTR_ERR(s);
kfree_const(cache_name);
@@ -356,6 +335,44 @@ out_unlock:
}
return s;
}
+
+/**
+ * kmem_cache_create_usercopy - Create a cache with a region suitable
+ * for copying to userspace
+ * @name: A string which is used in /proc/slabinfo to identify this cache.
+ * @size: The size of objects to be created in this cache.
+ * @align: The required alignment for the objects.
+ * @flags: SLAB flags
+ * @useroffset: Usercopy region offset
+ * @usersize: Usercopy region size
+ * @ctor: A constructor for the objects.
+ *
+ * Cannot be called within a interrupt, but can be interrupted.
+ * The @ctor is run when new pages are allocated by the cache.
+ *
+ * The flags are
+ *
+ * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
+ * to catch references to uninitialised memory.
+ *
+ * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
+ * for buffer overruns.
+ *
+ * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
+ * cacheline. This can be beneficial if you're counting cycles as closely
+ * as davem.
+ *
+ * Return: a pointer to the cache on success, NULL on failure.
+ */
+struct kmem_cache *
+kmem_cache_create_usercopy(const char *name, unsigned int size,
+ unsigned int align, slab_flags_t flags,
+ unsigned int useroffset, unsigned int usersize,
+ void (*ctor)(void *))
+{
+ return do_kmem_cache_create_usercopy(name, size, UINT_MAX, align, flags,
+ useroffset, usersize, ctor);
+}
EXPORT_SYMBOL(kmem_cache_create_usercopy);
/**
@@ -387,11 +404,50 @@ struct kmem_cache *
kmem_cache_create(const char *name, unsigned int size, unsigned int align,
slab_flags_t flags, void (*ctor)(void *))
{
- return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
- ctor);
+ return do_kmem_cache_create_usercopy(name, size, UINT_MAX, align, flags,
+ 0, 0, ctor);
}
EXPORT_SYMBOL(kmem_cache_create);
+/**
+ * kmem_cache_create_rcu - Create a SLAB_TYPESAFE_BY_RCU cache.
+ * @name: A string which is used in /proc/slabinfo to identify this cache.
+ * @size: The size of objects to be created in this cache.
+ * @freeptr_offset: The offset into the memory to the free pointer
+ * @flags: SLAB flags
+ *
+ * Cannot be called within an interrupt, but can be interrupted.
+ *
+ * See kmem_cache_create() for an explanation of possible @flags.
+ *
+ * By default SLAB_TYPESAFE_BY_RCU caches place the free pointer outside
+ * of the object. This might cause the object to grow in size. Callers
+ * that have a reason to avoid this can specify a custom free pointer
+ * offset in their struct where the free pointer will be placed.
+ *
+ * Note that placing the free pointer inside the object requires the
+ * caller to ensure that no fields are invalidated that are required to
+ * guard against object recycling (See SLAB_TYPESAFE_BY_RCU for
+ * details.).
+ *
+ * Using zero as a value for @freeptr_offset is valid. To request no
+ * offset UINT_MAX must be specified.
+ *
+ * Note that @ctor isn't supported with custom free pointers as a @ctor
+ * requires an external free pointer.
+ *
+ * Return: a pointer to the cache on success, NULL on failure.
+ */
+struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size,
+ unsigned int freeptr_offset,
+ slab_flags_t flags)
+{
+ return do_kmem_cache_create_usercopy(name, size, freeptr_offset, 0,
+ flags | SLAB_TYPESAFE_BY_RCU, 0, 0,
+ NULL);
+}
+EXPORT_SYMBOL(kmem_cache_create_rcu);
+
static struct kmem_cache *kmem_buckets_cache __ro_after_init;
/**
diff --git a/mm/slub.c b/mm/slub.c
index c9d8a2497fd6..be36f1df809c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -466,12 +466,6 @@ static struct workqueue_struct *flushwq;
*******************************************************************/
/*
- * freeptr_t represents a SLUB freelist pointer, which might be encoded
- * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
- */
-typedef struct { unsigned long v; } freeptr_t;
-
-/*
* Returns freelist pointer (ptr). With hardening, this is obfuscated
* with an XOR of the address where the pointer is held and a per-cache
* random number.
@@ -2116,6 +2110,10 @@ alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
if (!mem_alloc_profiling_enabled())
return;
+ /* slab->obj_exts might not be NULL if it was created for MEMCG accounting. */
+ if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
+ return;
+
obj_exts = slab_obj_exts(slab);
if (!obj_exts)
return;
@@ -3921,6 +3919,9 @@ static void *__slab_alloc_node(struct kmem_cache *s,
/*
* If the object has been wiped upon free, make sure it's fully initialized by
* zeroing out freelist pointer.
+ *
+ * Note that we also wipe custom freelist pointers specified via
+ * s->rcu_freeptr_offset.
*/
static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
void *obj)
@@ -5144,6 +5145,12 @@ static void set_cpu_partial(struct kmem_cache *s)
#endif
}
+/* Was a valid freeptr offset requested? */
+static inline bool has_freeptr_offset(const struct kmem_cache *s)
+{
+ return s->rcu_freeptr_offset != UINT_MAX;
+}
+
/*
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
@@ -5189,7 +5196,8 @@ static int calculate_sizes(struct kmem_cache *s)
*/
s->inuse = size;
- if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || s->ctor ||
+ if (((flags & SLAB_TYPESAFE_BY_RCU) && !has_freeptr_offset(s)) ||
+ (flags & SLAB_POISON) || s->ctor ||
((flags & SLAB_RED_ZONE) &&
(s->object_size < sizeof(void *) || slub_debug_orig_size(s)))) {
/*
@@ -5210,6 +5218,8 @@ static int calculate_sizes(struct kmem_cache *s)
*/
s->offset = size;
size += sizeof(void *);
+ } else if ((flags & SLAB_TYPESAFE_BY_RCU) && has_freeptr_offset(s)) {
+ s->offset = s->rcu_freeptr_offset;
} else {
/*
* Store freelist pointer near middle of object to keep
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e54e5c8907fa..acc56c75ba99 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -787,27 +787,30 @@ retry:
}
dst_pmdval = pmdp_get_lockless(dst_pmd);
- /*
- * If the dst_pmd is mapped as THP don't
- * override it and just be strict.
- */
- if (unlikely(pmd_trans_huge(dst_pmdval))) {
- err = -EEXIST;
- break;
- }
if (unlikely(pmd_none(dst_pmdval)) &&
unlikely(__pte_alloc(dst_mm, dst_pmd))) {
err = -ENOMEM;
break;
}
- /* If an huge pmd materialized from under us fail */
- if (unlikely(pmd_trans_huge(*dst_pmd))) {
+ dst_pmdval = pmdp_get_lockless(dst_pmd);
+ /*
+ * If the dst_pmd is THP don't override it and just be strict.
+ * (This includes the case where the PMD used to be THP and
+ * changed back to none after __pte_alloc().)
+ */
+ if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval) ||
+ pmd_devmap(dst_pmdval))) {
+ err = -EEXIST;
+ break;
+ }
+ if (unlikely(pmd_bad(dst_pmdval))) {
err = -EFAULT;
break;
}
-
- BUG_ON(pmd_none(*dst_pmd));
- BUG_ON(pmd_trans_huge(*dst_pmd));
+ /*
+ * For shmem mappings, khugepaged is allowed to remove page
+ * tables under us; pte_offset_map_lock() will deal with that.
+ */
err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr,
src_addr, flags, &folio);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index af2de36549d6..a0df1e2e155a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2191,6 +2191,7 @@ static void purge_vmap_node(struct work_struct *work)
{
struct vmap_node *vn = container_of(work,
struct vmap_node, purge_work);
+ unsigned long nr_purged_pages = 0;
struct vmap_area *va, *n_va;
LIST_HEAD(local_list);
@@ -2208,7 +2209,7 @@ static void purge_vmap_node(struct work_struct *work)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
- atomic_long_sub(nr, &vmap_lazy_nr);
+ nr_purged_pages += nr;
vn->nr_purged++;
if (is_vn_id_valid(vn_id) && !vn->skip_populate)
@@ -2219,6 +2220,8 @@ static void purge_vmap_node(struct work_struct *work)
list_add(&va->list, &local_list);
}
+ atomic_long_sub(nr_purged_pages, &vmap_lazy_nr);
+
reclaim_list_global(&local_list);
}
@@ -2626,6 +2629,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
vb->dirty_max = 0;
bitmap_set(vb->used_map, 0, (1UL << order));
INIT_LIST_HEAD(&vb->free_list);
+ vb->cpu = raw_smp_processor_id();
xa = addr_to_vb_xa(va->va_start);
vb_idx = addr_to_vb_idx(va->va_start);
@@ -2642,7 +2646,6 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
* integrity together with list_for_each_rcu from read
* side.
*/
- vb->cpu = raw_smp_processor_id();
vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cfa839284b92..bd489c1af228 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1604,25 +1604,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
}
-#ifdef CONFIG_CMA
-/*
- * It is waste of effort to scan and reclaim CMA pages if it is not available
- * for current allocation context. Kswapd can not be enrolled as it can not
- * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL
- */
-static bool skip_cma(struct folio *folio, struct scan_control *sc)
-{
- return !current_is_kswapd() &&
- gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE &&
- folio_migratetype(folio) == MIGRATE_CMA;
-}
-#else
-static bool skip_cma(struct folio *folio, struct scan_control *sc)
-{
- return false;
-}
-#endif
-
/*
* Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
*
@@ -1669,8 +1650,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
nr_pages = folio_nr_pages(folio);
total_scan += nr_pages;
- if (folio_zonenum(folio) > sc->reclaim_idx ||
- skip_cma(folio, sc)) {
+ if (folio_zonenum(folio) > sc->reclaim_idx) {
nr_skipped[folio_zonenum(folio)] += nr_pages;
move_to = &folios_skipped;
goto move;
@@ -4320,7 +4300,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
}
/* ineligible */
- if (zone > sc->reclaim_idx || skip_cma(folio, sc)) {
+ if (zone > sc->reclaim_idx) {
gen = folio_inc_gen(lruvec, folio, false);
list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;