The patch titled Subject: mm: zswap: function ordering: compress & decompress functions has been added to the -mm mm-unstable branch. Its filename is mm-zswap-function-ordering-compress-decompress-functions.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-zswap-function-ordering-compress-decompress-functions.patch This patch will later appear in the mm-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 the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Johannes Weiner <hannes@xxxxxxxxxxx> Subject: mm: zswap: function ordering: compress & decompress functions Date: Mon, 29 Jan 2024 20:36:53 -0500 Writeback needs to decompress. Move the (de)compression API above what will be the consolidated shrinking/writeback code. Link: https://lkml.kernel.org/r/20240130014208.565554-18-hannes@xxxxxxxxxxx Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx> Cc: Nhat Pham <nphamcs@xxxxxxxxx> Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/zswap.c | 207 +++++++++++++++++++++++++-------------------------- 1 file changed, 105 insertions(+), 102 deletions(-) --- a/mm/zswap.c~mm-zswap-function-ordering-compress-decompress-functions +++ a/mm/zswap.c @@ -993,6 +993,111 @@ static void zswap_invalidate_entry(struc } /********************************* +* compressed storage functions +**********************************/ +static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) +{ + struct crypto_acomp_ctx *acomp_ctx; + struct scatterlist input, output; + unsigned int dlen = PAGE_SIZE; + unsigned long handle; + struct zpool *zpool; + char *buf; + gfp_t gfp; + int ret; + u8 *dst; + + acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); + + mutex_lock(&acomp_ctx->mutex); + + dst = acomp_ctx->buffer; + sg_init_table(&input, 1); + sg_set_page(&input, &folio->page, PAGE_SIZE, 0); + + /* + * We need PAGE_SIZE * 2 here since there maybe over-compression case, + * and hardware-accelerators may won't check the dst buffer size, so + * giving the dst buffer with enough length to avoid buffer overflow. + */ + sg_init_one(&output, dst, PAGE_SIZE * 2); + acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen); + + /* + * it maybe looks a little bit silly that we send an asynchronous request, + * then wait for its completion synchronously. This makes the process look + * synchronous in fact. + * Theoretically, acomp supports users send multiple acomp requests in one + * acomp instance, then get those requests done simultaneously. but in this + * case, zswap actually does store and load page by page, there is no + * existing method to send the second page before the first page is done + * in one thread doing zwap. + * but in different threads running on different cpu, we have different + * acomp instance, so multiple threads can do (de)compression in parallel. + */ + ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); + dlen = acomp_ctx->req->dlen; + if (ret) { + zswap_reject_compress_fail++; + goto unlock; + } + + zpool = zswap_find_zpool(entry); + gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; + if (zpool_malloc_support_movable(zpool)) + gfp |= __GFP_HIGHMEM | __GFP_MOVABLE; + ret = zpool_malloc(zpool, dlen, gfp, &handle); + if (ret == -ENOSPC) { + zswap_reject_compress_poor++; + goto unlock; + } + if (ret) { + zswap_reject_alloc_fail++; + goto unlock; + } + + buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO); + memcpy(buf, dst, dlen); + zpool_unmap_handle(zpool, handle); + + entry->handle = handle; + entry->length = dlen; + +unlock: + mutex_unlock(&acomp_ctx->mutex); + return ret == 0; +} + +static void zswap_decompress(struct zswap_entry *entry, struct page *page) +{ + struct zpool *zpool = zswap_find_zpool(entry); + struct scatterlist input, output; + struct crypto_acomp_ctx *acomp_ctx; + u8 *src; + + acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + + src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); + if (!zpool_can_sleep_mapped(zpool)) { + memcpy(acomp_ctx->buffer, src, entry->length); + src = acomp_ctx->buffer; + zpool_unmap_handle(zpool, entry->handle); + } + + sg_init_one(&input, src, entry->length); + sg_init_table(&output, 1); + sg_set_page(&output, page, PAGE_SIZE, 0); + acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); + BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); + BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); + mutex_unlock(&acomp_ctx->mutex); + + if (zpool_can_sleep_mapped(zpool)) + zpool_unmap_handle(zpool, entry->handle); +} + +/********************************* * shrinker functions **********************************/ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, @@ -1317,108 +1422,6 @@ resched: zswap_pool_put(pool); } -static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) -{ - struct crypto_acomp_ctx *acomp_ctx; - struct scatterlist input, output; - unsigned int dlen = PAGE_SIZE; - unsigned long handle; - struct zpool *zpool; - char *buf; - gfp_t gfp; - int ret; - u8 *dst; - - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - - dst = acomp_ctx->buffer; - sg_init_table(&input, 1); - sg_set_page(&input, &folio->page, PAGE_SIZE, 0); - - /* - * We need PAGE_SIZE * 2 here since there maybe over-compression case, - * and hardware-accelerators may won't check the dst buffer size, so - * giving the dst buffer with enough length to avoid buffer overflow. - */ - sg_init_one(&output, dst, PAGE_SIZE * 2); - acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen); - - /* - * it maybe looks a little bit silly that we send an asynchronous request, - * then wait for its completion synchronously. This makes the process look - * synchronous in fact. - * Theoretically, acomp supports users send multiple acomp requests in one - * acomp instance, then get those requests done simultaneously. but in this - * case, zswap actually does store and load page by page, there is no - * existing method to send the second page before the first page is done - * in one thread doing zwap. - * but in different threads running on different cpu, we have different - * acomp instance, so multiple threads can do (de)compression in parallel. - */ - ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); - dlen = acomp_ctx->req->dlen; - if (ret) { - zswap_reject_compress_fail++; - goto unlock; - } - - zpool = zswap_find_zpool(entry); - gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - if (zpool_malloc_support_movable(zpool)) - gfp |= __GFP_HIGHMEM | __GFP_MOVABLE; - ret = zpool_malloc(zpool, dlen, gfp, &handle); - if (ret == -ENOSPC) { - zswap_reject_compress_poor++; - goto unlock; - } - if (ret) { - zswap_reject_alloc_fail++; - goto unlock; - } - - buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO); - memcpy(buf, dst, dlen); - zpool_unmap_handle(zpool, handle); - - entry->handle = handle; - entry->length = dlen; - -unlock: - mutex_unlock(&acomp_ctx->mutex); - return ret == 0; -} - -static void zswap_decompress(struct zswap_entry *entry, struct page *page) -{ - struct zpool *zpool = zswap_find_zpool(entry); - struct scatterlist input, output; - struct crypto_acomp_ctx *acomp_ctx; - u8 *src; - - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - - src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); - if (!zpool_can_sleep_mapped(zpool)) { - memcpy(acomp_ctx->buffer, src, entry->length); - src = acomp_ctx->buffer; - zpool_unmap_handle(zpool, entry->handle); - } - - sg_init_one(&input, src, entry->length); - sg_init_table(&output, 1); - sg_set_page(&output, page, PAGE_SIZE, 0); - acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); - BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); - BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); - - if (zpool_can_sleep_mapped(zpool)) - zpool_unmap_handle(zpool, entry->handle); -} - /********************************* * writeback code **********************************/ _ Patches currently in -mm which might be from hannes@xxxxxxxxxxx are mm-zswap-fix-objcg-use-after-free-in-entry-destruction.patch mm-zswap-rename-zswap_free_entry-to-zswap_entry_free.patch mm-zswap-inline-and-remove-zswap_entry_find_get.patch mm-zswap-move-zswap_invalidate_entry-to-related-functions.patch mm-zswap-warn-when-referencing-a-dead-entry.patch mm-zswap-clean-up-zswap_entry_put.patch mm-zswap-rename-__zswap_load-to-zswap_decompress.patch mm-zswap-break-out-zwap_compress.patch mm-zswap-further-cleanup-zswap_store.patch mm-zswap-simplify-zswap_invalidate.patch mm-zswap-function-ordering-pool-alloc-free.patch mm-zswap-function-ordering-pool-refcounting.patch mm-zswap-function-ordering-zswap_pools.patch mm-zswap-function-ordering-pool-params.patch mm-zswap-function-ordering-public-lru-api.patch mm-zswap-function-ordering-move-entry-sections-out-of-lru-section.patch mm-zswap-function-ordering-move-entry-section-out-of-tree-section.patch mm-zswap-function-ordering-compress-decompress-functions.patch mm-zswap-function-ordering-per-cpu-compression-infra.patch mm-zswap-function-ordering-writeback.patch mm-zswap-function-ordering-shrink_memcg_cb.patch