+ zram-use-a-singleton-compression-context-for-recompression.patch added to mm-nonmm-unstable branch

+ zram-use-a-singleton-compression-context-for-recompression.patch added to mm-nonmm-unstable branch

[Andrew Morton]

The patch titled
     Subject: zram: use a singleton compression context for recompression
has been added to the -mm mm-nonmm-unstable branch.  Its filename is
     zram-use-a-singleton-compression-context-for-recompression.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/zram-use-a-singleton-compression-context-for-recompression.patch

This patch will later appear in the mm-nonmm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Subject: zram: use a singleton compression context for recompression
Date: Sun, 25 Oct 2026 11:18:31 +0900

Secondary compressors are only used by recompress_store(), which is
serialized under zram->dev_lock, so we only ever use one secondary
compressor at a time, yet we still allocate them on each CPU, which is
just a plain memory wastage.  However, we do need per-CPU decompressors
in order to support concurrent reads.

Now that Read and Write contexts are split, we can allocate just a
single compression stream (recomp_cstream) for secondary algorithms
instead of per-CPU streams, avoiding unused per-CPU compression
contexts and 2 * PAGE_SIZE buffers.

For example, on an 8-CPU x86_64 system (4K PAGE_SIZE), this saves:
- zstd (level 3, default):        ~700 KB (~100 KB/CPU)
- zstd (levels 12-22, no dict):   ~1.91 MB (~280 KB/CPU)
- zstd (levels 14-22, 110K dict): ~5.33 MB (~780 KB/CPU, lazy)
- deflate (winbits=-11, default): ~1.04 MB (~152 KB/CPU)
- deflate (winbits=15):           ~1.86 MB (~272 KB/CPU)
- lz4hc:                          ~1.84 MB (~269 KB/CPU)

Link: https://lore.kernel.org/20261025021839.1542805-16-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Bo Zhang <zhangbo0325@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Richard Chang <richardycc@google.com>
Cc: Bo Zhang <zhangbo56@xiaomi.com>
Cc: Hillf Danton <hdanton@sina.com>
---

 drivers/block/zram/zcomp.c    |   75 +++++++++++++++++++++++---------
 drivers/block/zram/zcomp.h    |    9 ++-
 drivers/block/zram/zram_drv.c |    5 +-
 3 files changed, 65 insertions(+), 24 deletions(-)

--- a/drivers/block/zram/zcomp.c~zram-use-a-singleton-compression-context-for-recompression
+++ a/drivers/block/zram/zcomp.c
@@ -151,6 +151,11 @@ ssize_t zcomp_available_show(const char
 
 struct zcomp_cstrm *zcomp_cstrm_get(struct zcomp *comp)
 {
+	if (comp->recomp_cstream) {
+		mutex_lock(&comp->recomp_cstream->lock);
+		return comp->recomp_cstream;
+	}
+
 	for (;;) {
 		struct zcomp_cstrm *zstrm = raw_cpu_ptr(comp->cstream);
 
@@ -326,22 +331,25 @@ int zcomp_decompress(struct zcomp *comp,
 int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
-	struct zcomp_cstrm *cstrm;
+	struct zcomp_cstrm *cstrm = NULL;
 	struct zcomp_dstrm *dstrm;
 	int ret;
 
-	cstrm = per_cpu_ptr(comp->cstream, cpu);
-	ret = zcomp_cstrm_init(comp, cstrm);
-	if (ret) {
-		pr_err("Can't allocate a compression stream\n");
-		return ret;
+	if (comp->cstream) {
+		cstrm = per_cpu_ptr(comp->cstream, cpu);
+		ret = zcomp_cstrm_init(comp, cstrm);
+		if (ret) {
+			pr_err("Can't allocate a compression stream\n");
+			return ret;
+		}
 	}
 
 	dstrm = per_cpu_ptr(comp->dstream, cpu);
 	ret = zcomp_dstrm_init(comp, dstrm);
 	if (ret) {
 		pr_err("Can't allocate a decompression stream\n");
-		zcomp_cstrm_free(comp, cstrm);
+		if (cstrm)
+			zcomp_cstrm_free(comp, cstrm);
 		return ret;
 	}
 
@@ -354,10 +362,12 @@ int zcomp_cpu_dead(unsigned int cpu, str
 	struct zcomp_cstrm *cstrm;
 	struct zcomp_dstrm *dstrm;
 
-	cstrm = per_cpu_ptr(comp->cstream, cpu);
-	mutex_lock(&cstrm->lock);
-	zcomp_cstrm_free(comp, cstrm);
-	mutex_unlock(&cstrm->lock);
+	if (comp->cstream) {
+		cstrm = per_cpu_ptr(comp->cstream, cpu);
+		mutex_lock(&cstrm->lock);
+		zcomp_cstrm_free(comp, cstrm);
+		mutex_unlock(&cstrm->lock);
+	}
 
 	dstrm = per_cpu_ptr(comp->dstream, cpu);
 	down_write(&dstrm->lock);
@@ -367,7 +377,8 @@ int zcomp_cpu_dead(unsigned int cpu, str
 	return 0;
 }
 
-static int zcomp_init(struct zcomp *comp, struct zcomp_params *params)
+static int zcomp_init(struct zcomp *comp, struct zcomp_params *params,
+		      bool recomp)
 {
 	int ret, cpu;
 
@@ -376,10 +387,28 @@ static int zcomp_init(struct zcomp *comp
 	if (ret)
 		goto cleanup;
 
-	comp->cstream = alloc_percpu(struct zcomp_cstrm);
-	if (!comp->cstream) {
-		ret = -ENOMEM;
-		goto cleanup;
+	if (recomp) {
+		comp->recomp_cstream = kzalloc_obj(*comp->recomp_cstream);
+		if (!comp->recomp_cstream) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+		mutex_init(&comp->recomp_cstream->lock);
+		ret = zcomp_cstrm_init(comp, comp->recomp_cstream);
+		if (ret) {
+			/* zcomp_cstrm_init() cleans up after itself */
+			kfree(comp->recomp_cstream);
+			comp->recomp_cstream = NULL;
+			goto cleanup;
+		}
+	} else {
+		comp->cstream = alloc_percpu(struct zcomp_cstrm);
+		if (!comp->cstream) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+		for_each_possible_cpu(cpu)
+			mutex_init(&per_cpu_ptr(comp->cstream, cpu)->lock);
 	}
 
 	comp->dstream = alloc_percpu(struct zcomp_dstrm);
@@ -393,7 +422,6 @@ static int zcomp_init(struct zcomp *comp
 	for_each_possible_cpu(cpu) {
 		struct zcomp_dstrm *zstrm = per_cpu_ptr(comp->dstream, cpu);
 
-		mutex_init(&per_cpu_ptr(comp->cstream, cpu)->lock);
 		init_rwsem(&zstrm->lock);
 		mutex_init(&zstrm->excl_lock);
 	}
@@ -405,6 +433,10 @@ static int zcomp_init(struct zcomp *comp
 	return 0;
 
 cleanup:
+	if (comp->recomp_cstream) {
+		zcomp_cstrm_free(comp, comp->recomp_cstream);
+		kfree(comp->recomp_cstream);
+	}
 	comp->ops->release_params(comp->params);
 	free_percpu(comp->dstream);
 	free_percpu(comp->cstream);
@@ -414,13 +446,18 @@ cleanup:
 void zcomp_destroy(struct zcomp *comp)
 {
 	cpuhp_state_remove_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
+	if (comp->recomp_cstream) {
+		zcomp_cstrm_free(comp, comp->recomp_cstream);
+		kfree(comp->recomp_cstream);
+	}
 	comp->ops->release_params(comp->params);
 	free_percpu(comp->dstream);
 	free_percpu(comp->cstream);
 	kfree(comp);
 }
 
-struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params)
+struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params,
+			   bool recomp)
 {
 	struct zcomp *comp;
 	int error;
@@ -443,7 +480,7 @@ struct zcomp *zcomp_create(const char *a
 		return ERR_PTR(-EINVAL);
 	}
 
-	error = zcomp_init(comp, params);
+	error = zcomp_init(comp, params, recomp);
 	if (error) {
 		kfree(comp);
 		return ERR_PTR(error);
--- a/drivers/block/zram/zcomp.h~zram-use-a-singleton-compression-context-for-recompression
+++ a/drivers/block/zram/zcomp.h
@@ -40,7 +40,8 @@ struct zcomp_params {
 /*
  * Run-time driver context - scratch buffers, etc. It is modified during
  * request execution (compression/decompression), cannot be shared, so
- * it's in per-CPU area.
+ * it's in per-CPU area (except for recompression, which uses a single
+ * per-device compression stream).
  */
 struct zcomp_ctx {
 	void *context;
@@ -95,9 +96,10 @@ struct zcomp_ops {
 
 /* dynamic per-device compression frontend */
 struct zcomp {
-	struct zcomp_cstrm __percpu *cstream;
 	struct zcomp_dstrm __percpu *dstream;
 	wait_queue_head_t dstrm_waitq;
+	struct zcomp_cstrm __percpu *cstream;
+	struct zcomp_cstrm *recomp_cstream;
 	const struct zcomp_ops *ops;
 	struct zcomp_params *params;
 	struct hlist_node node;
@@ -108,7 +110,8 @@ int zcomp_cpu_dead(unsigned int cpu, str
 ssize_t zcomp_available_show(const char *comp, char *buf, ssize_t at);
 const char *zcomp_lookup_backend_name(const char *comp);
 
-struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params);
+struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params,
+			   bool recomp);
 void zcomp_destroy(struct zcomp *comp);
 
 struct zcomp_cstrm *zcomp_cstrm_get(struct zcomp *comp);
--- a/drivers/block/zram/zram_drv.c~zram-use-a-singleton-compression-context-for-recompression
+++ a/drivers/block/zram/zram_drv.c
@@ -2526,7 +2526,7 @@ static int recompress_slot(struct zram *
 	}
 
 	/*
-	 * We are holding per-CPU stream mutex and entry lock so better
+	 * We are holding compression stream mutex and entry lock so better
 	 * avoid direct reclaim.  Allocation error is not fatal since
 	 * we still have the old object in the mem_pool.
 	 *
@@ -2920,7 +2920,8 @@ static ssize_t disksize_store(struct dev
 			continue;
 
 		comp = zcomp_create(zram->comp_algs[prio],
-				    &zram->params[prio]);
+				    &zram->params[prio],
+				    prio != ZRAM_PRIMARY_COMP);
 		if (IS_ERR(comp)) {
 			pr_err("Cannot initialise %s compressing backend\n",
 			       zram->comp_algs[prio]);
_

Patches currently in -mm which might be from senozhatsky@chromium.org are

zram-prefix-backends-printk-s.patch
zram-remove-debugfs-entry-on-init-failure.patch
zram-reset-writeback-state-in-zram_reset_device.patch
zram-move-mark_slot_accessed-under-existing-slot-lock-sections.patch
zram-remove-stale-warn_on-from-zram_read_page.patch
zram-zstd-do-not-allocate-empty-c-d-dictionaries.patch
zram-lz4hc-pre-initialize-dictionary-stream-in-setup_params.patch
zram-lz4-use-lz4_decompress_safe_usingdict.patch
zram-lz4hc-use-lz4_decompress_safe_usingdict.patch
zram-zstd-do-not-use-kvzalloc-for-zstd-allocations.patch
zram-split-zcomp-into-separate-r-w-streams.patch
zram-introduce-shared-decompression-streams.patch
zram-allocate-bounce-buffer-for-spanning-objects.patch
zram-borrow-idle-decompression-streams-in-exclusive-mode.patch
zram-use-a-singleton-compression-context-for-recompression.patch