zsmalloc: introduce some helper functions

Patch series "zsmalloc: remove bit_spin_lock", v2.

zsmalloc uses bit_spin_lock to minimize space overhead since it's zpage
granularity lock.  However, it causes zsmalloc non-working under
PREEMPT_RT as well as adding too much complication.

This patchset tries to replace the bit_spin_lock with per-pool rwlock.
It also removes unnecessary zspage isolation logic from class, which was
the other part too much complication added into zsmalloc.

Last patch changes the get_cpu_var to local_lock to make it work in
PREEMPT_RT.

This patch (of 9):

get_zspage_mapping returns fullness as well as class_idx.  However, the
fullness is usually not used since it could be stale in some contexts.
It causes misleading as well as unnecessary instructions so this patch
introduces zspage_class.

obj_to_location also produces page and index but we don't need always
the index, either so this patch introduces obj_to_page.

Link: https://lkml.kernel.org/r/20211115185909.3949505-1-minchan@kernel.org
Link: https://lkml.kernel.org/r/20211115185909.3949505-2-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 0d3b65939016c38b7d77fd79b2d8180a65d33a9a..dfa58511fa5b53fdf2146f19720995680d019332 100644 (file)
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -517,6 +517,12 @@ static void get_zspage_mapping(struct zspage *zspage,
        *class_idx = zspage->class;
 }
 
+static struct size_class *zspage_class(struct zs_pool *pool,
+                                            struct zspage *zspage)
+{
+       return pool->size_class[zspage->class];
+}
+
 static void set_zspage_mapping(struct zspage *zspage,
                                unsigned int class_idx,
                                enum fullness_group fullness)
@@ -844,6 +850,12 @@ static void obj_to_location(unsigned long obj, struct page **page,
        *obj_idx = (obj & OBJ_INDEX_MASK);
 }
 
+static void obj_to_page(unsigned long obj, struct page **page)
+{
+       obj >>= OBJ_TAG_BITS;
+       *page = pfn_to_page(obj >> OBJ_INDEX_BITS);
+}
+
 /**
  * location_to_obj - get obj value encoded from (<page>, <obj_idx>)
  * @page: page object resides in zspage
@@ -1246,8 +1258,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
        unsigned long obj, off;
        unsigned int obj_idx;
 
-       unsigned int class_idx;
-       enum fullness_group fg;
        struct size_class *class;
        struct mapping_area *area;
        struct page *pages[2];
@@ -1270,8 +1280,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
        /* migration cannot move any subpage in this zspage */
        migrate_read_lock(zspage);
 
-       get_zspage_mapping(zspage, &class_idx, &fg);
-       class = pool->size_class[class_idx];
+       class = zspage_class(pool, zspage);
        off = (class->size * obj_idx) & ~PAGE_MASK;
 
        area = &get_cpu_var(zs_map_area);
@@ -1304,16 +1313,13 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
        unsigned long obj, off;
        unsigned int obj_idx;
 
-       unsigned int class_idx;
-       enum fullness_group fg;
        struct size_class *class;
        struct mapping_area *area;
 
        obj = handle_to_obj(handle);
        obj_to_location(obj, &page, &obj_idx);
        zspage = get_zspage(page);
-       get_zspage_mapping(zspage, &class_idx, &fg);
-       class = pool->size_class[class_idx];
+       class = zspage_class(pool, zspage);
        off = (class->size * obj_idx) & ~PAGE_MASK;
 
        area = this_cpu_ptr(&zs_map_area);
@@ -1491,8 +1497,6 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
        struct zspage *zspage;
        struct page *f_page;
        unsigned long obj;
-       unsigned int f_objidx;
-       int class_idx;
        struct size_class *class;
        enum fullness_group fullness;
        bool isolated;
@@ -1502,13 +1506,11 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 
        pin_tag(handle);
        obj = handle_to_obj(handle);
-       obj_to_location(obj, &f_page, &f_objidx);
+       obj_to_page(obj, &f_page);
        zspage = get_zspage(f_page);
 
        migrate_read_lock(zspage);
-
-       get_zspage_mapping(zspage, &class_idx, &fullness);
-       class = pool->size_class[class_idx];
+       class = zspage_class(pool, zspage);
 
        spin_lock(&class->lock);
        obj_free(class, obj);
@@ -1866,8 +1868,6 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 {
        struct zs_pool *pool;
        struct size_class *class;
-       int class_idx;
-       enum fullness_group fullness;
        struct zspage *zspage;
        struct address_space *mapping;
 
@@ -1880,15 +1880,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 
        zspage = get_zspage(page);
 
-       /*
-        * Without class lock, fullness could be stale while class_idx is okay
-        * because class_idx is constant unless page is freed so we should get
-        * fullness again under class lock.
-        */
-       get_zspage_mapping(zspage, &class_idx, &fullness);
        mapping = page_mapping(page);
        pool = mapping->private_data;
-       class = pool->size_class[class_idx];
+
+       class = zspage_class(pool, zspage);
 
        spin_lock(&class->lock);
        if (get_zspage_inuse(zspage) == 0) {
@@ -1907,6 +1902,9 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
         * size_class to prevent further object allocation from the zspage.
         */
        if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
+               enum fullness_group fullness;
+               unsigned int class_idx;
+
                get_zspage_mapping(zspage, &class_idx, &fullness);
                atomic_long_inc(&pool->isolated_pages);
                remove_zspage(class, zspage, fullness);
@@ -1923,8 +1921,6 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
 {
        struct zs_pool *pool;
        struct size_class *class;
-       int class_idx;
-       enum fullness_group fullness;
        struct zspage *zspage;
        struct page *dummy;
        void *s_addr, *d_addr, *addr;
@@ -1949,9 +1945,8 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
 
        /* Concurrent compactor cannot migrate any subpage in zspage */
        migrate_write_lock(zspage);
-       get_zspage_mapping(zspage, &class_idx, &fullness);
        pool = mapping->private_data;
-       class = pool->size_class[class_idx];
+       class = zspage_class(pool, zspage);
        offset = get_first_obj_offset(page);
 
        spin_lock(&class->lock);
@@ -2049,8 +2044,6 @@ static void zs_page_putback(struct page *page)
 {
        struct zs_pool *pool;
        struct size_class *class;
-       int class_idx;
-       enum fullness_group fg;
        struct address_space *mapping;
        struct zspage *zspage;
 
@@ -2058,10 +2051,9 @@ static void zs_page_putback(struct page *page)
        VM_BUG_ON_PAGE(!PageIsolated(page), page);
 
        zspage = get_zspage(page);
-       get_zspage_mapping(zspage, &class_idx, &fg);
        mapping = page_mapping(page);
        pool = mapping->private_data;
-       class = pool->size_class[class_idx];
+       class = zspage_class(pool, zspage);
 
        spin_lock(&class->lock);
        dec_zspage_isolation(zspage);