From: Jihan LIN Currently, zcomp uses a per-CPU stream model. This design is restrictive for hardware-accelerated or batched zcomp backends. These backends often need to manage their own resources rather than relying on a generic mutex-protected per-CPU stream for batched operations. Extend the zcomp interface to allow backends to optionally manage their own streams while generic per-CPU streams still remain allocated as a complementary mechanism. Introduce zstrm_mgmt flag to struct zcomp_params. Backends set this flag during zcomp_ops->setup_params() to advertise their capability to manage streams. Add zcomp_ops->{get, put}_stream() to allow zcomp backends to implement their own stream strategies. Modify zcomp_stream_get() to accept a new parameter indicating zcomp-managed streams are preferred, and update zcomp_stream_put() to route a zcomp-managed stream to the backend. If the backends advertise their capability and the caller prefers managed streams, try to get a stream from the backends; otherwise, fall back to the generic per-CPU stream. All existing call sites request the default per-CPU stream to preserve the original behavior. Signed-off-by: Jihan LIN --- drivers/block/zram/zcomp.c | 41 +++++++++++++++++++++++++++++++++++++++-- drivers/block/zram/zcomp.h | 30 ++++++++++++++++++++++++++++-- drivers/block/zram/zram_drv.c | 10 +++++----- 3 files changed, 72 insertions(+), 9 deletions(-) diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index daea592f01c37106b14dca9c6d8727a2240de54b..1b5c8e8f6c6cb78a812320334da0b61391bb38f0 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -84,6 +84,7 @@ static int zcomp_strm_init_percpu(struct zcomp *comp, zcomp_strm_free_percpu(comp, zstrm_pcpu); return -ENOMEM; } + zstrm->zcomp_managed = false; return 0; } @@ -122,7 +123,7 @@ ssize_t zcomp_available_show(const char *comp, char *buf, ssize_t at) return at; } -struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) +static inline struct zcomp_strm *zcomp_stream_pcpu_get(struct zcomp *comp) { for (;;) { struct percpu_zstrm *zstrm_pcpu = raw_cpu_ptr(comp->stream); @@ -144,9 +145,37 @@ struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) } } +struct zcomp_strm *zcomp_stream_get(struct zcomp *comp, enum zstrm_pref pref) +{ + if (comp->params->zstrm_mgmt && pref == ZSTRM_PREFER_MGMT) { + struct managed_zstrm *zstrm_managed = + comp->ops->get_stream(comp->params); + + if (zstrm_managed) { + zstrm_managed->comp = comp; + return &zstrm_managed->strm; + } + } + + return zcomp_stream_pcpu_get(comp); +} + +static inline void zcomp_stream_pcpu_put(struct percpu_zstrm *zstrm) +{ + mutex_unlock(&zstrm->lock); +} + void zcomp_stream_put(struct zcomp_strm *zstrm) { - mutex_unlock(&zstrm_to_pcpu(zstrm)->lock); + if (zstrm->zcomp_managed) { + struct managed_zstrm *zstrm_managed = + zstrm_to_managed(zstrm); + + zstrm_managed->comp->ops->put_stream( + zstrm_managed->comp->params, zstrm_managed); + } else { + zcomp_stream_pcpu_put(zstrm_to_pcpu(zstrm)); + } } int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm, @@ -211,11 +240,19 @@ static int zcomp_init(struct zcomp *comp, struct zcomp_params *params) if (!comp->stream) return -ENOMEM; + params->zstrm_mgmt = false; comp->params = params; ret = comp->ops->setup_params(comp->params); if (ret) goto cleanup; + if (params->zstrm_mgmt && + !(comp->ops->get_stream && comp->ops->put_stream)) { + params->zstrm_mgmt = false; + pr_warn("Missing managed stream ops in %s, managed stream disabled\n", + comp->ops->name); + } + for_each_possible_cpu(cpu) mutex_init(&per_cpu_ptr(comp->stream, cpu)->lock); diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h index 9784bc3f432cf0e22085399b8772b8ba669071de..3543e7e4d2b3b1344bb191b321bcdd69f67031f6 100644 --- a/drivers/block/zram/zcomp.h +++ b/drivers/block/zram/zcomp.h @@ -24,6 +24,7 @@ struct zcomp_params { union { struct deflate_params deflate; }; + bool zstrm_mgmt; void *drv_data; }; @@ -31,13 +32,14 @@ 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 or managed by the backend. */ struct zcomp_ctx { void *context; }; struct zcomp_strm { + bool zcomp_managed; /* compression buffer */ void *buffer; /* local copy of handle memory */ @@ -47,6 +49,11 @@ struct zcomp_strm { struct percpu_zstrm; +struct managed_zstrm { + struct zcomp *comp; + struct zcomp_strm strm; +}; + struct zcomp_req { const unsigned char *src; const size_t src_len; @@ -55,6 +62,11 @@ struct zcomp_req { size_t dst_len; }; +enum zstrm_pref { + ZSTRM_DEFAULT, /* always use the generic per-CPU stream */ + ZSTRM_PREFER_MGMT, /* try managed stream; fallback to per-CPU */ +}; + struct zcomp_ops { int (*compress)(struct zcomp_params *params, struct zcomp_ctx *ctx, struct zcomp_req *req); @@ -67,6 +79,15 @@ struct zcomp_ops { int (*setup_params)(struct zcomp_params *params); void (*release_params)(struct zcomp_params *params); + /* + * get_stream() needs to prepare zstrm->ctx. The backend must ensure + * returned stream has zcomp_managed set and matches the per-cpu + * stream sizing: local_copy >= PAGE_SIZE, buffer >= 2 * PAGE_SIZE. + */ + struct managed_zstrm *(*get_stream)(struct zcomp_params *params); + void (*put_stream)(struct zcomp_params *params, + struct managed_zstrm *zstrm); + const char *name; }; @@ -86,7 +107,7 @@ bool zcomp_available_algorithm(const char *comp); 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); +struct zcomp_strm *zcomp_stream_get(struct zcomp *comp, enum zstrm_pref pref); void zcomp_stream_put(struct zcomp_strm *zstrm); int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm, @@ -94,4 +115,9 @@ int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm, int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm, const void *src, unsigned int src_len, void *dst); +static inline struct managed_zstrm *zstrm_to_managed(struct zcomp_strm *zstrm) +{ + return container_of(zstrm, struct managed_zstrm, strm); +} + #endif /* _ZCOMP_H_ */ diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index bca33403fc8bf872569c63e65af0fe143287eaaf..7be88cfb56adb12fcc1edc6b4d42271044ef71b5 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1377,7 +1377,7 @@ static int decompress_bdev_page(struct zram *zram, struct page *page, u32 index) size = get_slot_size(zram, index); prio = get_slot_comp_priority(zram, index); - zstrm = zcomp_stream_get(zram->comps[prio]); + zstrm = zcomp_stream_get(zram->comps[prio], ZSTRM_DEFAULT); src = kmap_local_page(page); ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, zstrm->local_copy); @@ -2083,7 +2083,7 @@ static int read_compressed_page(struct zram *zram, struct page *page, u32 index) size = get_slot_size(zram, index); prio = get_slot_comp_priority(zram, index); - zstrm = zcomp_stream_get(zram->comps[prio]); + zstrm = zcomp_stream_get(zram->comps[prio], ZSTRM_DEFAULT); src = zs_obj_read_begin(zram->mem_pool, handle, size, zstrm->local_copy); dst = kmap_local_page(page); @@ -2111,7 +2111,7 @@ static int read_from_zspool_raw(struct zram *zram, struct page *page, u32 index) * case if object spans two physical pages. No decompression * takes place here, as we read raw compressed data. */ - zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); + zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP], ZSTRM_DEFAULT); src = zs_obj_read_begin(zram->mem_pool, handle, size, zstrm->local_copy); memcpy_to_page(page, 0, src, size); @@ -2265,7 +2265,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) if (same_filled) return write_same_filled_page(zram, element, index); - zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); + zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP], ZSTRM_DEFAULT); mem = kmap_local_page(page); ret = zcomp_compress(zram->comps[ZRAM_PRIMARY_COMP], zstrm, mem, &comp_len); @@ -2447,7 +2447,7 @@ static int recompress_slot(struct zram *zram, u32 index, struct page *page, if (!zram->comps[prio]) continue; - zstrm = zcomp_stream_get(zram->comps[prio]); + zstrm = zcomp_stream_get(zram->comps[prio], ZSTRM_DEFAULT); src = kmap_local_page(page); ret = zcomp_compress(zram->comps[prio], zstrm, src, &comp_len_new); -- 2.51.0