From 0db478c2e26f1e6428ee86d11d7401a75fadd677 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Tue, 25 Aug 2026 15:06:01 -0700 Subject: [PATCH] crypto: zstd - Avoid redundant cstream initialization zstd_compress() initializes the shared workspace as a CStream before entering the walk loop. If the first source and destination fragments each span the whole request it then hands off to zstd_compress_one(), which initializes that same ctx->wksp as a CCtx, discarding the CStream setup without having compressed a byte. zswap always takes this one-shot path when storing, so every page it stores paid for both. Neither is cheap: zstd_init_cstream() redoes the cwksp layout, zeroes the ZSTD_CCtx, probes for BMI2 through ZSTD_cpuid(), then resets the session and parameters and replays ten validated ZSTD_CCtx_setParameter() calls. Defer the CStream initialization to the first walk iteration that needs it, guarded by a flag because that iteration can be reached more than once. The first inner iteration either takes the one-shot path and returns or initializes the CStream, so the trailing zstd_end_stream() cannot pick up the stale context left in ctx->cctx by an earlier request. Unlike the old call site the new one runs with the walk's fragments mapped, so it has to release them before failing. For a 4 KB crypto_acomp benchmark for compression, twelve runs of nine 30K operation rounds, on the bare-metal host the median per-round mean request time fell from 52,283 ns to 51,038 ns (2.4%). In the one-vCPU KVM guest it fell from 16,675 ns to 15,050 ns (9.8%). The larger improvement in guest is because of the pair of CPUID instructions in ZSTD_cpuid() that the removed initialization runs. Signed-off-by: Usama Arif Signed-off-by: Herbert Xu --- crypto/zstd.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/crypto/zstd.c b/crypto/zstd.c index 556f5d2bdd5f..d64472f3e11e 100644 --- a/crypto/zstd.c +++ b/crypto/zstd.c @@ -96,6 +96,7 @@ static int zstd_compress_one(struct acomp_req *req, struct zstd_ctx *ctx, static int zstd_compress(struct acomp_req *req) { + bool stream_initialized = false; struct crypto_acomp_stream *s; unsigned int pos, scur, dcur; unsigned int total_out = 0; @@ -115,12 +116,6 @@ static int zstd_compress(struct acomp_req *req) if (ret) goto out; - ctx->cctx = zstd_init_cstream(&ctx->params, 0, ctx->wksp, ctx->wksp_size); - if (!ctx->cctx) { - ret = -EINVAL; - goto out; - } - do { dcur = acomp_walk_next_dst(&walk); if (!dcur) { @@ -142,6 +137,19 @@ static int zstd_compress(struct acomp_req *req) goto out; } + if (!stream_initialized) { + ctx->cctx = zstd_init_cstream(&ctx->params, 0, + ctx->wksp, ctx->wksp_size); + if (!ctx->cctx) { + /* Release in the reverse of the map order. */ + acomp_walk_done_src(&walk, 0); + acomp_walk_done_dst(&walk, 0); + ret = -EINVAL; + goto out; + } + stream_initialized = true; + } + if (scur) { inbuf.pos = 0; inbuf.src = walk.src.virt.addr;