As of now recompress_slot() is called under slot bucket write-lock,
which is suboptimal as it blocks access to a huge number of entries.
The good news is that recompression, like writeback, makes a local
copy of slot data (we need to decompress it anyway) before
post-processing so we can unlock slot bucket once we have that local
copy.
Unlock the bucket write-lock before recompression loop (secondary
algorithms can be tried out one by one, in order of priority) and
re-acquire it right after the loop.
There is one more potentially costly operation recompress_slot()
does - new zs_handle allocation, which can schedule(). Release
the bucket write-lock before zsmalloc allocation and grab it again
after the allocation.
In both cases, once the bucket lock is re-acquired we examine slot's
ZRAM_PP_SLOT flag to make sure that the slot has not been modified
by a concurrent operation.
Signed-off-by: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
---
drivers/block/zram/zram_drv.c | 53 +++++++++++++++++++++++++----------
1 file changed, 38 insertions(+), 15 deletions(-)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d516f968321e..0413438e4500 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1925,6 +1925,14 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
zram_clear_flag(zram, index, ZRAM_IDLE);
class_index_old = zs_lookup_class_index(zram->mem_pool, comp_len_old);
+
+ /*
+ * Set prio to one past current slot's compression prio, so that
+ * we automatically skip lower priority algorithms.
+ */
+ prio = zram_get_priority(zram, index) + 1;
+ /* Slot data copied out - unlock its bucket */
+ zram_slot_write_unlock(zram, index);
/*
* Iterate the secondary comp algorithms list (in order of priority)
* and try to recompress the page.
@@ -1933,13 +1941,6 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
if (!zram->comps[prio])
continue;
- /*
- * Skip if the object is already re-compressed with a higher
- * priority algorithm (or same algorithm).
- */
- if (prio <= zram_get_priority(zram, index))
- continue;
-
num_recomps++;
zstrm = zcomp_stream_get(zram->comps[prio]);
src = kmap_local_page(page);
@@ -1947,10 +1948,8 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
src, &comp_len_new);
kunmap_local(src);
- if (ret) {
- zcomp_stream_put(zram->comps[prio], zstrm);
- return ret;
- }
+ if (ret)
+ break;
class_index_new = zs_lookup_class_index(zram->mem_pool,
comp_len_new);
@@ -1966,6 +1965,19 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
break;
}
+ zram_slot_write_lock(zram, index);
+ /* Compression error */
+ if (ret) {
+ zcomp_stream_put(zram->comps[prio], zstrm);
+ return ret;
+ }
+
+ /* Slot has been modified concurrently */
+ if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) {
+ zcomp_stream_put(zram->comps[prio], zstrm);
+ return 0;
+ }
+
/*
* We did not try to recompress, e.g. when we have only one
* secondary algorithm and the page is already recompressed
@@ -2003,17 +2015,28 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
if (threshold && comp_len_new >= threshold)
return 0;
- /*
- * If we cannot alloc memory for recompressed object then we bail out
- * and simply keep the old (existing) object in zsmalloc.
- */
+ /* zsmalloc handle allocation can schedule, unlock slot's bucket */
+ zram_slot_write_unlock(zram, index);
handle_new = zs_malloc(zram->mem_pool, comp_len_new,
GFP_NOIO | __GFP_HIGHMEM | __GFP_MOVABLE);
+ zram_slot_write_lock(zram, index);
+
+ /*
+ * If we couldn't allocate memory for recompressed object then bail
+ * out and simply keep the old (existing) object in mempool.
+ */
if (IS_ERR_VALUE(handle_new)) {
zcomp_stream_put(zram->comps[prio], zstrm);
return PTR_ERR((void *)handle_new);
}
+ /* Slot has been modified concurrently */
+ if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) {
+ zcomp_stream_put(zram->comps[prio], zstrm);
+ zs_free(zram->mem_pool, handle_new);
+ return 0;
+ }
+
dst = zs_map_object(zram->mem_pool, handle_new, ZS_MM_WO);
memcpy(dst, zstrm->buffer, comp_len_new);
zcomp_stream_put(zram->comps[prio], zstrm);
--
2.48.0.rc2.279.g1de40edade-goog
