* [PATCH RFC 0/3] zram: avoid copying spanning LZ4 objects before decompression
@ 2026-11-21 17:09 Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 1/3] zram: allow backends to decompress from two input buffers Xueyuan Chen
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Xueyuan Chen @ 2026-11-21 17:09 UTC (permalink / raw)
To: Minchan Kim, Sergey Senozhatsky, Jens Axboe
Cc: linux-kernel, linux-block, Xueyuan Chen
When a compressed object spans two zsmalloc pages, zram copies it into
a contiguous buffer before decompression. This series lets the LZ4 and
LZ4HC backends decode dictionary-free blocks directly from the two
fragments.
I measured the time to swap in 1 GiB of synthetic data on arm64 with
4 KiB pages. Each page started with pseudorandom data of one of 16
lengths, followed by zeros. On this workload, 32.6% of compressed
reads spanned two pages with LZ4 and 34.4% with LZ4HC.
The table shows median swap-in times over seven pairs. The last two
columns summarize the percentage change within each pair.
Codec Workers Baseline (ms) Patched (ms) Median Range
LZ4 1 1403.81 1344.45 -4.21% -4.64% to -1.61%
LZ4 8 222.57 216.36 -2.73% -4.19% to -1.97%
LZ4HC 1 1403.35 1336.99 -4.74% -5.07% to -2.90%
LZ4HC 8 222.10 215.77 -3.16% -4.39% to -1.27%
These timings include both skipping the copy and switching decoders.
I used Codex to help implement this series.
Do you think the swap-in improvement justifies maintaining a second
LZ4 decoder?
Assisted-by: LLM
Signed-off-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
---
Xueyuan Chen (3):
zram: allow backends to decompress from two input buffers
lib/lz4: add safe decompression from two input buffers
zram: use split-input decompression for LZ4 and LZ4HC
drivers/block/zram/backend_lz4.c | 1 +
drivers/block/zram/backend_lz4.h | 19 +++++
drivers/block/zram/backend_lz4hc.c | 2 +
drivers/block/zram/zcomp.c | 28 +++++++
drivers/block/zram/zcomp.h | 8 ++
include/linux/lz4.h | 18 ++++
lib/lz4/lz4_decompress.c | 163 +++++++++++++++++++++++++++++++++++++
7 files changed, 239 insertions(+)
---
base-commit: b95f8bb86713c860ce8536d22a988b949b884d5f
--
Best regards,
Xueyuan
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH RFC 1/3] zram: allow backends to decompress from two input buffers
2026-11-21 17:09 [PATCH RFC 0/3] zram: avoid copying spanning LZ4 objects before decompression Xueyuan Chen
@ 2026-11-21 17:09 ` Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 2/3] lib/lz4: add safe decompression " Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 3/3] zram: use split-input decompression for LZ4 and LZ4HC Xueyuan Chen
2 siblings, 0 replies; 4+ messages in thread
From: Xueyuan Chen @ 2026-11-21 17:09 UTC (permalink / raw)
To: Minchan Kim, Sergey Senozhatsky, Jens Axboe
Cc: linux-kernel, linux-block, Xueyuan Chen
Let backends decompress a spanning zsmalloc object directly from its
two scatterlist entries. Keep both fragments mapped for the call.
Use the linear path if the callback is absent or returns -EOPNOTSUPP
before writing output. Propagate other errors.
Signed-off-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
---
drivers/block/zram/zcomp.c | 28 ++++++++++++++++++++++++++++
drivers/block/zram/zcomp.h | 8 ++++++++
2 files changed, 36 insertions(+)
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 028e2f0f587e..265108b9f332 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -159,6 +159,28 @@ int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
return ret;
}
+static int zcomp_decompress_split(struct zcomp *comp, struct zcomp_strm *zstrm,
+ struct scatterlist *sg, void *dst)
+{
+ struct scatterlist *next = sg_next(sg);
+ /* Each entry from the zsmalloc read path fits within one page. */
+ void *first = kmap_local_page(sg_page(sg));
+ void *second = kmap_local_page(sg_page(next));
+ struct zcomp_req head = {
+ .src = first + sg->offset,
+ .src_len = sg->length,
+ .dst = dst,
+ .dst_len = PAGE_SIZE,
+ };
+ int ret;
+
+ ret = comp->ops->decompress_split(comp->params, &zstrm->ctx, &head,
+ second + next->offset, next->length);
+ kunmap_local(second);
+ kunmap_local(first);
+ return ret;
+}
+
int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm,
struct scatterlist *sg, unsigned int src_len, void *dst)
{
@@ -177,6 +199,12 @@ int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm,
src = kmap_local_page(sg_page(sg));
req.src = src + sg->offset;
} else {
+ if (comp->ops->decompress_split) {
+ ret = zcomp_decompress_split(comp, zstrm, sg, dst);
+ if (ret != -EOPNOTSUPP)
+ return ret;
+ }
+
/* the object spans two pages, linearize it into local copy */
sg_copy_to_buffer(sg, 2, zstrm->local_copy, src_len);
req.src = zstrm->local_copy;
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index f38fd31f9e4e..92a93630aead 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -61,6 +61,14 @@ struct zcomp_ops {
struct zcomp_req *req);
int (*decompress)(struct zcomp_params *params, struct zcomp_ctx *ctx,
struct zcomp_req *req);
+ /*
+ * Decode one block from head->src and tail into head->dst. The input
+ * mappings are valid during the call. Return 0 for a complete output
+ * or -EOPNOTSUPP before writing output to request a linear retry.
+ */
+ int (*decompress_split)(struct zcomp_params *params, struct zcomp_ctx *ctx,
+ const struct zcomp_req *head,
+ const void *tail, size_t tail_len);
int (*create_ctx)(struct zcomp_params *params, struct zcomp_ctx *ctx);
void (*destroy_ctx)(struct zcomp_ctx *ctx);
--
2.47.3
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH RFC 2/3] lib/lz4: add safe decompression from two input buffers
2026-11-21 17:09 [PATCH RFC 0/3] zram: avoid copying spanning LZ4 objects before decompression Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 1/3] zram: allow backends to decompress from two input buffers Xueyuan Chen
@ 2026-11-21 17:09 ` Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 3/3] zram: use split-input decompression for LZ4 and LZ4HC Xueyuan Chen
2 siblings, 0 replies; 4+ messages in thread
From: Xueyuan Chen @ 2026-11-21 17:09 UTC (permalink / raw)
To: Minchan Kim, Sergey Senozhatsky, Jens Axboe
Cc: linux-kernel, linux-block, Xueyuan Chen
LZ4_decompress_generic() assumes contiguous input. Its wide literal
loads can cross the boundary between independently mapped fragments.
Add a dictionary-free block decoder that reads from two buffers and
handles literals, lengths and offsets that cross the split.
Signed-off-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
---
include/linux/lz4.h | 18 ++++++
lib/lz4/lz4_decompress.c | 163 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 181 insertions(+)
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index ad6042a718b5..3b6217bd9a9b 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -292,6 +292,24 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize);
int LZ4_decompress_safe(const char *source, char *dest, int compressedSize,
int maxDecompressedSize);
+/**
+ * LZ4_decompress_safe_split() - Decode a single block from two buffers
+ * @first: address of the first input fragment
+ * @first_len: bytes in the first input fragment
+ * @second: address of the second input fragment
+ * @second_len: bytes in the second input fragment
+ * @dst: output buffer, disjoint from the input buffers
+ * @capacity: bytes available in the output buffer
+ *
+ * The fragments, in order, contain one dictionary-free LZ4 block.
+ * Their addresses need not be adjacent. An empty fragment may be NULL.
+ *
+ * Return: the decoded size, or -EINVAL on error.
+ */
+int LZ4_decompress_safe_split(const u8 *first, size_t first_len,
+ const u8 *second, size_t second_len,
+ u8 *dst, int capacity);
+
/**
* LZ4_decompress_safe_partial() - Decompress a block of size 'compressedSize'
* at position 'source' into buffer 'dest'
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 3a2cd9acada4..548197faa3e3 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -39,6 +39,11 @@
#include <linux/kernel.h>
#include <linux/unaligned.h>
+#ifndef STATIC
+#include <linux/errno.h>
+#include <linux/limits.h>
+#endif
+
/*-*****************************
* Decompression functions
*******************************/
@@ -705,6 +710,164 @@ int LZ4_decompress_fast_usingDict(const char *source, char *dest,
}
#ifndef STATIC
+struct lz4_split_input {
+ const u8 *first;
+ const u8 *second;
+ size_t split;
+ size_t size;
+ size_t pos;
+};
+
+static __always_inline size_t
+lz4_split_input_left(const struct lz4_split_input *in)
+{
+ return in->size - in->pos;
+}
+
+static __always_inline int lz4_split_get_byte(struct lz4_split_input *in)
+{
+ size_t pos = in->pos;
+
+ if (unlikely(pos == in->size))
+ return -1;
+ in->pos++;
+ if (pos < in->split)
+ return in->first[pos];
+ return in->second[pos - in->split];
+}
+
+/* The caller has checked that two bytes remain in the block. */
+static __always_inline int lz4_split_get_offset(struct lz4_split_input *in)
+{
+ size_t pos = in->pos;
+
+ in->pos += 2;
+ if (pos >= in->split)
+ return get_unaligned_le16(in->second + (pos - in->split));
+ if (in->split - pos >= 2)
+ return get_unaligned_le16(in->first + pos);
+ return in->first[pos] | (in->second[0] << 8);
+}
+
+static __always_inline bool
+lz4_split_copy_literals(struct lz4_split_input *in, u8 *dst, size_t len)
+{
+ size_t pos = in->pos;
+
+ if (unlikely(len > lz4_split_input_left(in)))
+ return false;
+ if (!len)
+ return true;
+ if (pos < in->split) {
+ size_t n = min(len, in->split - pos);
+
+ memcpy(dst, in->first + pos, n);
+ pos += n;
+ dst += n;
+ len -= n;
+ }
+ if (len)
+ memcpy(dst, in->second + (pos - in->split), len);
+ in->pos = pos + len;
+ return true;
+}
+
+/* The decoder has checked the lookbehind distance and output capacity. */
+static __always_inline void
+lz4_split_copy_match(u8 *dst, size_t distance, size_t len)
+{
+ size_t copied = min(distance, len);
+
+ if (distance == 1) {
+ memset(dst, dst[-1], len);
+ return;
+ }
+
+ memcpy(dst, dst - distance, copied);
+ /* Reuse the period already written, keeping each copy disjoint. */
+ while (len - copied > copied) {
+ memcpy(dst + copied, dst, copied);
+ copied *= 2;
+ }
+ if (copied < len)
+ memcpy(dst + copied, dst, len - copied);
+}
+
+static __always_inline int
+lz4_split_read_length(struct lz4_split_input *in, int length, int limit)
+{
+ int byte;
+
+ if (length > limit)
+ return -EINVAL;
+ if (length < RUN_MASK)
+ return length;
+
+ do {
+ byte = lz4_split_get_byte(in);
+ if (byte < 0 || byte > limit - length)
+ return -EINVAL;
+ length += byte;
+ } while (byte == 255);
+ return length;
+}
+
+int LZ4_decompress_safe_split(const u8 *first, size_t first_len,
+ const u8 *second, size_t second_len,
+ u8 *dst, int capacity)
+{
+ struct lz4_split_input in = {
+ .first = first,
+ .second = second,
+ .split = first_len,
+ };
+ int written = 0, min_last_literals = 0;
+
+ if (capacity < 0 || !dst || (!first && first_len) ||
+ (!second && second_len) || first_len > SIZE_MAX - second_len)
+ return -EINVAL;
+ in.size = first_len + second_len;
+
+ for (;;) {
+ int token, literal, distance, match;
+
+ token = lz4_split_get_byte(&in);
+ if (token < 0)
+ return -EINVAL;
+ literal = lz4_split_read_length(&in, token >> ML_BITS,
+ capacity - written);
+ if (literal < 0 ||
+ !lz4_split_copy_literals(&in, dst + written, literal))
+ return -EINVAL;
+ written += literal;
+ if (!lz4_split_input_left(&in))
+ return literal >= min_last_literals ? written : -EINVAL;
+
+ /* A match must leave room for the final literal sequence. */
+ if (lz4_split_input_left(&in) < 2 + 1 + LASTLITERALS ||
+ capacity - written < MFLIMIT)
+ return -EINVAL;
+
+ distance = lz4_split_get_offset(&in);
+ if (!distance || distance > written)
+ return -EINVAL;
+ match = lz4_split_read_length(&in, token & ML_MASK,
+ capacity - written - MINMATCH -
+ LASTLITERALS);
+ if (match < 0)
+ return -EINVAL;
+ match += MINMATCH;
+ lz4_split_copy_match(dst + written, distance, match);
+ written += match;
+ /*
+ * Leave at least LASTLITERALS bytes and end at least MFLIMIT
+ * bytes past the start of the last match.
+ */
+ min_last_literals = max(LASTLITERALS, MFLIMIT - match);
+ }
+}
+EXPORT_SYMBOL_GPL(LZ4_decompress_safe_split);
+
EXPORT_SYMBOL(LZ4_decompress_safe);
EXPORT_SYMBOL(LZ4_decompress_safe_partial);
EXPORT_SYMBOL(LZ4_decompress_fast);
--
2.47.3
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH RFC 3/3] zram: use split-input decompression for LZ4 and LZ4HC
2026-11-21 17:09 [PATCH RFC 0/3] zram: avoid copying spanning LZ4 objects before decompression Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 1/3] zram: allow backends to decompress from two input buffers Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 2/3] lib/lz4: add safe decompression " Xueyuan Chen
@ 2026-11-21 17:09 ` Xueyuan Chen
2 siblings, 0 replies; 4+ messages in thread
From: Xueyuan Chen @ 2026-11-21 17:09 UTC (permalink / raw)
To: Minchan Kim, Sergey Senozhatsky, Jens Axboe
Cc: linux-kernel, linux-block, Xueyuan Chen
Use the split decoder for dictionary-free LZ4 and LZ4HC blocks.
Keep dictionary-backed reads on the linear path and require the
split decoder to produce a full page.
Signed-off-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
---
drivers/block/zram/backend_lz4.c | 1 +
drivers/block/zram/backend_lz4.h | 19 +++++++++++++++++++
drivers/block/zram/backend_lz4hc.c | 2 ++
3 files changed, 22 insertions(+)
diff --git a/drivers/block/zram/backend_lz4.c b/drivers/block/zram/backend_lz4.c
index 1e4ad31d39a6..2cf8ff656f13 100644
--- a/drivers/block/zram/backend_lz4.c
+++ b/drivers/block/zram/backend_lz4.c
@@ -150,6 +150,7 @@ static int lz4_decompress(struct zcomp_params *params, struct zcomp_ctx *ctx,
const struct zcomp_ops backend_lz4 = {
.compress = lz4_compress,
.decompress = lz4_decompress,
+ .decompress_split = lz4_decompress_split,
.create_ctx = lz4_create,
.destroy_ctx = lz4_destroy,
.setup_params = lz4_setup_params,
diff --git a/drivers/block/zram/backend_lz4.h b/drivers/block/zram/backend_lz4.h
index c11fa602a703..6c1736ea1a87 100644
--- a/drivers/block/zram/backend_lz4.h
+++ b/drivers/block/zram/backend_lz4.h
@@ -3,8 +3,27 @@
#ifndef __BACKEND_LZ4_H__
#define __BACKEND_LZ4_H__
+#include <linux/errno.h>
+#include <linux/lz4.h>
+
#include "zcomp.h"
+static inline int lz4_decompress_split(struct zcomp_params *params,
+ struct zcomp_ctx *ctx,
+ const struct zcomp_req *head,
+ const void *tail, size_t tail_len)
+{
+ int decoded;
+
+ if (params->dict_sz)
+ return -EOPNOTSUPP;
+ decoded = LZ4_decompress_safe_split(head->src, head->src_len, tail,
+ tail_len, head->dst, head->dst_len);
+ if (decoded < 0)
+ return decoded;
+ return decoded == head->dst_len ? 0 : -EINVAL;
+}
+
extern const struct zcomp_ops backend_lz4;
#endif /* __BACKEND_LZ4_H__ */
diff --git a/drivers/block/zram/backend_lz4hc.c b/drivers/block/zram/backend_lz4hc.c
index d8aa01bb258f..56a6eecf8d67 100644
--- a/drivers/block/zram/backend_lz4hc.c
+++ b/drivers/block/zram/backend_lz4hc.c
@@ -7,6 +7,7 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
+#include "backend_lz4.h"
#include "backend_lz4hc.h"
struct lz4hc_ctx {
@@ -134,6 +135,7 @@ static int lz4hc_decompress(struct zcomp_params *params, struct zcomp_ctx *ctx,
const struct zcomp_ops backend_lz4hc = {
.compress = lz4hc_compress,
.decompress = lz4hc_decompress,
+ .decompress_split = lz4_decompress_split,
.create_ctx = lz4hc_create,
.destroy_ctx = lz4hc_destroy,
.setup_params = lz4hc_setup_params,
--
2.47.3
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-11-21 17:09 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-21 17:09 [PATCH RFC 0/3] zram: avoid copying spanning LZ4 objects before decompression Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 1/3] zram: allow backends to decompress from two input buffers Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 2/3] lib/lz4: add safe decompression " Xueyuan Chen
2026-11-21 17:09 ` [PATCH RFC 3/3] zram: use split-input decompression for LZ4 and LZ4HC Xueyuan Chen
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®