@@ -6,7 +6,7 @@
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/sched.h>
-#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
#include <linux/crypto.h>
#include <linux/vmalloc.h>
@@ -109,13 +109,29 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
{
- local_lock(&comp->stream->lock);
- return this_cpu_ptr(comp->stream);
+ for (;;) {
+ struct zcomp_strm *zstrm = raw_cpu_ptr(comp->stream);
+
+ /*
+ * Inspired by zswap
+ *
+ * stream is returned with ->mutex locked which prevents
+ * cpu_dead() from releasing this stream under us, however
+ * there is still a race window between raw_cpu_ptr() and
+ * mutex_lock(), during which we could have been migrated
+ * from a CPU that has already destroyed its stream. If
+ * so then unlock and re-try on the current CPU.
+ */
+ mutex_lock(&zstrm->lock);
+ if (likely(zstrm->buffer))
+ return zstrm;
+ mutex_unlock(&zstrm->lock);
+ }
}
-void zcomp_stream_put(struct zcomp *comp)
+void zcomp_stream_put(struct zcomp_strm *zstrm)
{
- local_unlock(&comp->stream->lock);
+ mutex_unlock(&zstrm->lock);
}
int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
@@ -151,12 +167,9 @@ int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm,
int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
{
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
- struct zcomp_strm *zstrm;
+ struct zcomp_strm *zstrm = per_cpu_ptr(comp->stream, cpu);
int ret;
- zstrm = per_cpu_ptr(comp->stream, cpu);
- local_lock_init(&zstrm->lock);
-
ret = zcomp_strm_init(comp, zstrm);
if (ret)
pr_err("Can't allocate a compression stream\n");
@@ -166,16 +179,17 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
- struct zcomp_strm *zstrm;
+ struct zcomp_strm *zstrm = per_cpu_ptr(comp->stream, cpu);
- zstrm = per_cpu_ptr(comp->stream, cpu);
+ mutex_lock(&zstrm->lock);
zcomp_strm_free(comp, zstrm);
+ mutex_unlock(&zstrm->lock);
return 0;
}
static int zcomp_init(struct zcomp *comp, struct zcomp_params *params)
{
- int ret;
+ int ret, cpu;
comp->stream = alloc_percpu(struct zcomp_strm);
if (!comp->stream)
@@ -186,6 +200,9 @@ static int zcomp_init(struct zcomp *comp, struct zcomp_params *params)
if (ret)
goto cleanup;
+ for_each_possible_cpu(cpu)
+ mutex_init(&per_cpu_ptr(comp->stream, cpu)->lock);
+
ret = cpuhp_state_add_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
if (ret < 0)
goto cleanup;
@@ -3,7 +3,7 @@
#ifndef _ZCOMP_H_
#define _ZCOMP_H_
-#include <linux/local_lock.h>
+#include <linux/mutex.h>
#define ZCOMP_PARAM_NO_LEVEL INT_MIN
@@ -31,7 +31,7 @@ struct zcomp_ctx {
};
struct zcomp_strm {
- local_lock_t lock;
+ struct mutex lock;
/* compression buffer */
void *buffer;
struct zcomp_ctx ctx;
@@ -77,7 +77,7 @@ struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params);
void zcomp_destroy(struct zcomp *comp);
struct zcomp_strm *zcomp_stream_get(struct zcomp *comp);
-void zcomp_stream_put(struct zcomp *comp);
+void zcomp_stream_put(struct zcomp_strm *zstrm);
int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
const void *src, unsigned int *dst_len);
@@ -1650,7 +1650,7 @@ static int read_compressed_page(struct zram *zram, struct page *page, u32 index)
ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, dst);
kunmap_local(dst);
zs_unmap_object(zram->mem_pool, handle);
- zcomp_stream_put(zram->comps[prio]);
+ zcomp_stream_put(zstrm);
return ret;
}
@@ -1811,14 +1811,14 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
kunmap_local(mem);
if (unlikely(ret)) {
- zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+ zcomp_stream_put(zstrm);
pr_err("Compression failed! err=%d\n", ret);
zs_free(zram->mem_pool, handle);
return ret;
}
if (comp_len >= huge_class_size) {
- zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+ zcomp_stream_put(zstrm);
return write_incompressible_page(zram, page, index);
}
@@ -1842,7 +1842,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (IS_ERR_VALUE(handle)) {
- zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+ zcomp_stream_put(zstrm);
atomic64_inc(&zram->stats.writestall);
handle = zs_malloc(zram->mem_pool, comp_len,
GFP_NOIO | __GFP_HIGHMEM |
@@ -1854,7 +1854,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
}
if (!zram_can_store_page(zram)) {
- zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+ zcomp_stream_put(zstrm);
zs_free(zram->mem_pool, handle);
return -ENOMEM;
}
@@ -1862,7 +1862,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
memcpy(dst, zstrm->buffer, comp_len);
- zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+ zcomp_stream_put(zstrm);
zs_unmap_object(zram->mem_pool, handle);
zram_slot_lock(zram, index);
@@ -2021,7 +2021,7 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
kunmap_local(src);
if (ret) {
- zcomp_stream_put(zram->comps[prio]);
+ zcomp_stream_put(zstrm);
return ret;
}
@@ -2031,7 +2031,7 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
/* Continue until we make progress */
if (class_index_new >= class_index_old ||
(threshold && comp_len_new >= threshold)) {
- zcomp_stream_put(zram->comps[prio]);
+ zcomp_stream_put(zstrm);
continue;
}
@@ -2089,13 +2089,13 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page,
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (IS_ERR_VALUE(handle_new)) {
- zcomp_stream_put(zram->comps[prio]);
+ zcomp_stream_put(zstrm);
return PTR_ERR((void *)handle_new);
}
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]);
+ zcomp_stream_put(zstrm);
zs_unmap_object(zram->mem_pool, handle_new);
Currently, per-CPU stream access is done from a non-preemptible (atomic) section, which imposes the same atomicity requirements on compression backends as entry spin-lock, and makes it impossible to use algorithms that can schedule/wait/sleep during compression and decompression. Switch to preemptible per-CPU model, similar to the one used in zswap. Instead of a per-CPU local lock, each stream carries a mutex which is locked throughout entire time zram uses it for compression or decompression, so that cpu-dead event waits for zram to stop using a particular per-CPU stream and release it. Suggested-by: Yosry Ahmed <yosry.ahmed@linux.dev> Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org> --- drivers/block/zram/zcomp.c | 41 +++++++++++++++++++++++++---------- drivers/block/zram/zcomp.h | 6 ++--- drivers/block/zram/zram_drv.c | 20 ++++++++--------- 3 files changed, 42 insertions(+), 25 deletions(-)