zram: rework writeback target selection strategy

Writeback suffers from the same problem as recompression did before -
target slot selection for writeback is just a simple iteration over
zram->table entries (stored pages) which selects suboptimal targets for
writeback.  This is especially problematic for writeback, because we
uncompress objects before writeback so each of them takes 4K out of
limited writeback storage.  For example, when we take a 48 bytes slot and
store it as a 4K object to writeback device we only save 48 bytes of
memory (release from zsmalloc pool).  We naturally want to pick the
largest objects for writeback, because then each writeback will release
the largest amount of memory.

This patch applies the same solution and strategy as for recompression
target selection: pp control (post-process) with 16 buckets of candidate
pp slots.  Slots are assigned to pp buckets based on sizes - the larger
the slot the higher the group index.  This gives us sorted by size lists
of candidate slots (in linear time), so that among post-processing
candidate slots we always select the largest ones first and maximize the
memory saving.

TEST
====

A very simple demonstration: zram is configured with a writeback device.
A limited writeback (wb_limit 2500 pages) is performed then, with a log of
sizes of slots that were written back.  You can see that patched zram
selects slots for recompression in significantly different manner, which
leads to higher memory savings (see column #2 of mm_stat output).

BASE
----

*** initial state of zram device
/sys/block/zram0/mm_stat
1750327296 619765836 631902208        0 631902208        1        0    34278    34278

*** writeback idle wb_limit 2500
/sys/block/zram0/mm_stat
1750327296 617622333 631578624        0 631902208        1        0    34278    34278

Sizes of selected objects for writeback:
... 193 349 46 46 46 46 852 1002 543 162 107 49 34 34 34 ...

PATCHED
-------

*** initial state of zram device
/sys/block/zram0/mm_stat
1750319104 619760957 631992320        0 631992320        1        0    34278    34278

*** writeback idle wb_limit 2500
/sys/block/zram0/mm_stat
1750319104 612672056 626135040        0 631992320        1        0    34278    34278

Sizes of selected objects for writeback:
... 3667 3580 3581 3580 3581 3581 3581 3231 3211 3203 3231 3246 ...

Note, pp-slots are not strictly sorted, there is a PP_BUCKET_SIZE_RANGE
variation of sizes within particular bucket.

Link: https://lkml.kernel.org/r/20240917021020.883356-5-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f57ffb92016675cd3f8ea62a9780f0587c84c113..42f7195b80cb910b6e40ebe6796726aa7cc3c807 100644 (file)
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -184,7 +184,7 @@ static void zram_accessed(struct zram *zram, u32 index)
 #endif
 }
 
-#ifdef CONFIG_ZRAM_MULTI_COMP
+#if defined CONFIG_ZRAM_WRITEBACK || defined CONFIG_ZRAM_MULTI_COMP
 struct zram_pp_slot {
        unsigned long           index;
        struct list_head        entry;
@@ -681,11 +681,57 @@ static void read_from_bdev_async(struct zram *zram, struct page *page,
 #define IDLE_WRITEBACK                 (1<<1)
 #define INCOMPRESSIBLE_WRITEBACK       (1<<2)
 
+static int scan_slots_for_writeback(struct zram *zram, u32 mode,
+                                   unsigned long nr_pages,
+                                   unsigned long index,
+                                   struct zram_pp_ctl *ctl)
+{
+       struct zram_pp_slot *pps = NULL;
+
+       for (; nr_pages != 0; index++, nr_pages--) {
+               if (!pps)
+                       pps = kmalloc(sizeof(*pps), GFP_KERNEL);
+               if (!pps)
+                       return -ENOMEM;
+
+               INIT_LIST_HEAD(&pps->entry);
+
+               zram_slot_lock(zram, index);
+               if (!zram_allocated(zram, index))
+                       goto next;
+
+               if (zram_test_flag(zram, index, ZRAM_WB) ||
+                   zram_test_flag(zram, index, ZRAM_SAME))
+                       goto next;
+
+               if (mode & IDLE_WRITEBACK &&
+                   !zram_test_flag(zram, index, ZRAM_IDLE))
+                       goto next;
+               if (mode & HUGE_WRITEBACK &&
+                   !zram_test_flag(zram, index, ZRAM_HUGE))
+                       goto next;
+               if (mode & INCOMPRESSIBLE_WRITEBACK &&
+                   !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
+                       goto next;
+
+               pps->index = index;
+               place_pp_slot(zram, ctl, pps);
+               pps = NULL;
+next:
+               zram_slot_unlock(zram, index);
+       }
+
+       kfree(pps);
+       return 0;
+}
+
 static ssize_t writeback_store(struct device *dev,
                struct device_attribute *attr, const char *buf, size_t len)
 {
        struct zram *zram = dev_to_zram(dev);
        unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+       struct zram_pp_ctl *ctl = NULL;
+       struct zram_pp_slot *pps;
        unsigned long index = 0;
        struct bio bio;
        struct bio_vec bio_vec;
@@ -737,7 +783,15 @@ static ssize_t writeback_store(struct device *dev,
                goto release_init_lock;
        }
 
-       for (; nr_pages != 0; index++, nr_pages--) {
+       ctl = init_pp_ctl();
+       if (!ctl) {
+               ret = -ENOMEM;
+               goto release_init_lock;
+       }
+
+       scan_slots_for_writeback(zram, mode, nr_pages, index, ctl);
+
+       while ((pps = select_pp_slot(ctl))) {
                spin_lock(&zram->wb_limit_lock);
                if (zram->wb_limit_enable && !zram->bd_wb_limit) {
                        spin_unlock(&zram->wb_limit_lock);
@@ -754,25 +808,10 @@ static ssize_t writeback_store(struct device *dev,
                        }
                }
 
+               index = pps->index;
                zram_slot_lock(zram, index);
-               if (!zram_allocated(zram, index))
-                       goto next;
-
-               if (zram_test_flag(zram, index, ZRAM_WB) ||
-                               zram_test_flag(zram, index, ZRAM_SAME) ||
-                               zram_test_flag(zram, index, ZRAM_UNDER_WB))
-                       goto next;
-
-               if (mode & IDLE_WRITEBACK &&
-                   !zram_test_flag(zram, index, ZRAM_IDLE))
-                       goto next;
-               if (mode & HUGE_WRITEBACK &&
-                   !zram_test_flag(zram, index, ZRAM_HUGE))
-                       goto next;
-               if (mode & INCOMPRESSIBLE_WRITEBACK &&
-                   !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
+               if (!zram_test_flag(zram, index, ZRAM_PP_SLOT))
                        goto next;
-
                /*
                 * Clearing ZRAM_UNDER_WB is duty of caller.
                 * IOW, zram_free_page never clear it.
@@ -786,6 +825,8 @@ static ssize_t writeback_store(struct device *dev,
                        zram_clear_flag(zram, index, ZRAM_UNDER_WB);
                        zram_clear_flag(zram, index, ZRAM_IDLE);
                        zram_slot_unlock(zram, index);
+
+                       release_pp_slot(zram, pps);
                        continue;
                }
 
@@ -804,6 +845,8 @@ static ssize_t writeback_store(struct device *dev,
                        zram_clear_flag(zram, index, ZRAM_UNDER_WB);
                        zram_clear_flag(zram, index, ZRAM_IDLE);
                        zram_slot_unlock(zram, index);
+
+                       release_pp_slot(zram, pps);
                        /*
                         * BIO errors are not fatal, we continue and simply
                         * attempt to writeback the remaining objects (pages).
@@ -846,12 +889,14 @@ static ssize_t writeback_store(struct device *dev,
                spin_unlock(&zram->wb_limit_lock);
 next:
                zram_slot_unlock(zram, index);
+               release_pp_slot(zram, pps);
        }
 
        if (blk_idx)
                free_block_bdev(zram, blk_idx);
        __free_page(page);
 release_init_lock:
+       release_pp_ctl(zram, ctl);
        atomic_set(&zram->pp_in_progress, 0);
        up_read(&zram->init_lock);