From patchwork Wed May 8 13:33:55 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 13658787 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 3FDBEC04FFE for ; Wed, 8 May 2024 13:37:08 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:Content-Type: Content-Transfer-Encoding:MIME-Version:Message-ID:Date:Subject:CC:To:From: Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From:Resent-Sender :Resent-To:Resent-Cc:Resent-Message-ID:In-Reply-To:References:List-Owner; bh=p7Vn+DPI1/d0t/hWEsP0N7QjuPAGZAk4QsEVvY4slg4=; b=0nZLNxgzDtC8aKFhtcGYf6N+IT fqSwgvIi0ZWayRkAa9AWKZHhlOS+/zlUmxqpLCDo5dHPEo01d+/1IMPLhbIXQBeC7wid5XWDKz46G N6yNrjebdsZygi5OFj3PnF8MdOPuBb4ui2y3eZ0c7fj/d5lyf9H6EKsC5r6rEbytdD3OssHQYq3p/ 0XBzwaXuCPKd68B3rSZsOnuGuntgXUqA9olc+rV25jMBZhtib9I9ROp64JSbteAHEnuQRDQzm+BDF dzTTuien6oWZaSAkziwn8LVwyjNDLxGEkuwzpBscrMIc5Lclrgm4epZASxR2nQpqvHHkA2uC73Bf2 8VXGIVRA==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.97.1 #2 (Red Hat Linux)) id 1s4hTl-0000000FfDi-47u2; Wed, 08 May 2024 13:37:05 +0000 Received: from szxga08-in.huawei.com ([45.249.212.255]) by bombadil.infradead.org with esmtps (Exim 4.97.1 #2 (Red Hat Linux)) id 1s4hTc-0000000Ff4m-0QNZ; Wed, 08 May 2024 13:37:03 +0000 Received: from mail.maildlp.com (unknown [172.19.162.254]) by szxga08-in.huawei.com (SkyGuard) with ESMTP id 4VZGLM3sXnz1RCcJ; Wed, 8 May 2024 21:33:15 +0800 (CST) Received: from dggpemm500005.china.huawei.com (unknown [7.185.36.74]) by mail.maildlp.com (Postfix) with ESMTPS id 787D41800B8; Wed, 8 May 2024 21:36:35 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.35; Wed, 8 May 2024 21:36:35 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Alexander Duyck , Matthias Brugger , AngeloGioacchino Del Regno , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , , , Subject: [PATCH net-next v3 00/13] First try to replace page_frag with page_frag_cache Date: Wed, 8 May 2024 21:33:55 +0800 Message-ID: <20240508133408.54708-1-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 MIME-Version: 1.0 X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems702-chm.china.huawei.com (10.3.19.179) To dggpemm500005.china.huawei.com (7.185.36.74) X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20240508_063656_487828_0838C636 X-CRM114-Status: GOOD ( 21.24 ) X-BeenThere: linux-mediatek@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Linux-mediatek" Errors-To: linux-mediatek-bounces+linux-mediatek=archiver.kernel.org@lists.infradead.org After [1], there are still two implementations for page frag: 1. mm/page_alloc.c: net stack seems to be using it in the rx part with 'struct page_frag_cache' and the main API being page_frag_alloc_align(). 2. net/core/sock.c: net stack seems to be using it in the tx part with 'struct page_frag' and the main API being skb_page_frag_refill(). This patchset tries to unfiy the page frag implementation by replacing page_frag with page_frag_cache for sk_page_frag() first. net_high_order_alloc_disable_key for the implementation in net/core/sock.c doesn't seems matter that much now have have pcp support for high-order pages in commit 44042b449872 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists"). As the related change is mostly related to networking, so targeting the net-next. And will try to replace the rest of page_frag in the follow patchset. After this patchset: 1. Unify the page frag implementation by taking the best out of two the existing implementations: we are able to save some space for the 'page_frag_cache' API user, and avoid 'get_page()' for the old 'page_frag' API user. 2. Future bugfix and performance can be done in one place, hence improving maintainability of page_frag's implementation. Kernel Image changing: Linux Kernel total | text data bss ------------------------------------------------------ after 44893035 | 27084547 17042328 766160 before 44896899 | 27088459 17042280 766160 delta -3864 | -3912 +48 +0 Performance validation: 1. Using micro-benchmark ko added in patch 1 to test aligned and non-aligned API performance impact for the existing users, there is no notiable performance degradation. Instead we have some minor performance boot for both aligned and non-aligned API after this patchset as below. 2. Use the below netcat test case, we also have some minor performance boot for repalcing 'page_frag' with 'page_frag_cache' after this patchset. server: nc -l -k 1234 > /dev/null client: perf stat -r 30 -- head -c 51200000000 /dev/zero | nc -N 127.0.0.1 1234 In order to avoid performance noise as much as possible, the testing is done in system without any other laod and have enough iterations to prove the data is stable enogh, complete log for testing is below: *After* this patchset: Performance counter stats for 'insmod ./page_frag_test.ko' (200 runs): 17.959047 task-clock (msec) # 0.001 CPUs utilized ( +- 0.16% ) 7 context-switches # 0.371 K/sec ( +- 0.52% ) 1 cpu-migrations # 0.037 K/sec ( +- 5.25% ) 84 page-faults # 0.005 M/sec ( +- 0.10% ) 46630340 cycles # 2.596 GHz ( +- 0.16% ) 60991298 instructions # 1.31 insn per cycle ( +- 0.03% ) 14778609 branches # 822.906 M/sec ( +- 0.03% ) 21461 branch-misses # 0.15% of all branches ( +- 0.35% ) 25.071309168 seconds time elapsed ( +- 0.42% ) Performance counter stats for 'insmod ./page_frag_test.ko test_align=1' (200 runs): 17.518324 task-clock (msec) # 0.001 CPUs utilized ( +- 0.22% ) 7 context-switches # 0.397 K/sec ( +- 0.22% ) 0 cpu-migrations # 0.014 K/sec ( +- 12.78% ) 84 page-faults # 0.005 M/sec ( +- 0.10% ) 45494458 cycles # 2.597 GHz ( +- 0.22% ) 61059177 instructions # 1.34 insn per cycle ( +- 0.02% ) 14792330 branches # 844.392 M/sec ( +- 0.02% ) 21132 branch-misses # 0.14% of all branches ( +- 0.17% ) 26.156288028 seconds time elapsed ( +- 0.41% ) perf stat -r 30 -- head -c 51200000000 /dev/zero | nc -N 127.0.0.1 1234 Performance counter stats for 'head -c 51200000000 /dev/zero' (30 runs): 107793.53 msec task-clock # 0.881 CPUs utilized ( +- 0.36% ) 380421 context-switches # 3.529 K/sec ( +- 0.32% ) 374 cpu-migrations # 3.470 /sec ( +- 1.31% ) 74 page-faults # 0.686 /sec ( +- 0.28% ) 92758718093 cycles # 0.861 GHz ( +- 0.48% ) (69.47%) 7035559641 stalled-cycles-frontend # 7.58% frontend cycles idle ( +- 1.19% ) (69.65%) 33668082825 stalled-cycles-backend # 36.30% backend cycles idle ( +- 0.84% ) (70.18%) 52424770535 instructions # 0.57 insn per cycle # 0.64 stalled cycles per insn ( +- 0.26% ) (61.93%) 13240874953 branches # 122.836 M/sec ( +- 0.40% ) (60.36%) 208178019 branch-misses # 1.57% of all branches ( +- 0.65% ) (68.42%) 122.294 +- 0.402 seconds time elapsed ( +- 0.33% ) *Before* this patchset: Performance counter stats for 'insmod ./page_frag_test_frag_page_v3_org.ko' (200 runs): 17.878013 task-clock (msec) # 0.001 CPUs utilized ( +- 0.02% ) 7 context-switches # 0.384 K/sec ( +- 0.37% ) 0 cpu-migrations # 0.002 K/sec ( +- 34.73% ) 83 page-faults # 0.005 M/sec ( +- 0.11% ) 46428731 cycles # 2.597 GHz ( +- 0.02% ) 61080812 instructions # 1.32 insn per cycle ( +- 0.01% ) 14802110 branches # 827.951 M/sec ( +- 0.01% ) 33011 branch-misses # 0.22% of all branches ( +- 0.10% ) 26.923903379 seconds time elapsed ( +- 0.32% ) Performance counter stats for 'insmod ./page_frag_test_frag_page_v3_org.ko test_align=1' (200 runs): 17.579978 task-clock (msec) # 0.001 CPUs utilized ( +- 0.05% ) 7 context-switches # 0.393 K/sec ( +- 0.31% ) 0 cpu-migrations # 0.014 K/sec ( +- 12.96% ) 83 page-faults # 0.005 M/sec ( +- 0.10% ) 45649145 cycles # 2.597 GHz ( +- 0.05% ) 60999424 instructions # 1.34 insn per cycle ( +- 0.03% ) 14778647 branches # 840.652 M/sec ( +- 0.03% ) 33148 branch-misses # 0.22% of all branches ( +- 0.11% ) 27.454413570 seconds time elapsed ( +- 0.48% ) perf stat -r 30 -- head -c 51200000000 /dev/zero | nc -N 127.0.0.1 1234 Performance counter stats for 'head -c 51200000000 /dev/zero' (30 runs): 110198.93 msec task-clock # 0.884 CPUs utilized ( +- 0.83% ) 387680 context-switches # 3.518 K/sec ( +- 0.85% ) 366 cpu-migrations # 3.321 /sec ( +- 11.38% ) 74 page-faults # 0.672 /sec ( +- 0.27% ) 92978008685 cycles # 0.844 GHz ( +- 0.49% ) (64.93%) 7339938950 stalled-cycles-frontend # 7.89% frontend cycles idle ( +- 1.48% ) (67.15%) 34783792329 stalled-cycles-backend # 37.41% backend cycles idle ( +- 1.52% ) (68.96%) 51704527141 instructions # 0.56 insn per cycle # 0.67 stalled cycles per insn ( +- 0.37% ) (68.28%) 12865503633 branches # 116.748 M/sec ( +- 0.88% ) (66.11%) 212414695 branch-misses # 1.65% of all branches ( +- 0.45% ) (64.57%) 124.664 +- 0.990 seconds time elapsed ( +- 0.79% ) Note, ipv4-udp, ipv6-tcp and ipv6-udp is also tested with the below script: nc -u -l -k 1234 > /dev/null perf stat -r 4 -- head -c 51200000000 /dev/zero | nc -N -u 127.0.0.1 1234 nc -l6 -k 1234 > /dev/null perf stat -r 4 -- head -c 51200000000 /dev/zero | nc -N ::1 1234 nc -l6 -k -u 1234 > /dev/null perf stat -r 4 -- head -c 51200000000 /dev/zero | nc -u -N ::1 1234 CC: Alexander Duyck Change log: v3: 1. Use new layout for 'struct page_frag_cache' as the discussion with Alexander and other sugeestions from Alexander. 2. Add probe API to address Mat' comment about mptcp use case. 3. Some doc updating according to Bagas' suggestion. v2: 1. reorder test module to patch 1. 2. split doc and maintainer updating to two patches. 3. refactor the page_frag before moving. 4. fix a type and 'static' warning in test module. 5. add a patch for xtensa arch to enable using get_order() in BUILD_BUG_ON(). 6. Add test case and performance data for the socket code. Yunsheng Lin (13): mm: page_frag: add a test module for page_frag xtensa: remove the get_order() implementation mm: page_frag: use free_unref_page() to free page fragment mm: move the page fragment allocator from page_alloc into its own file mm: page_frag: use initial zero offset for page_frag_alloc_align() mm: page_frag: add '_va' suffix to page_frag API mm: page_frag: avoid caller accessing 'page_frag_cache' directly mm: page_frag: reuse existing space for 'size' and 'pfmemalloc' net: introduce the skb_copy_to_va_nocache() helper mm: page_frag: introduce prepare/probe/commit API net: replace page_frag with page_frag_cache mm: page_frag: update documentation for page_frag mm: page_frag: add a entry in MAINTAINERS for page_frag Documentation/mm/page_frags.rst | 156 ++++++- MAINTAINERS | 11 + arch/xtensa/include/asm/page.h | 18 - .../chelsio/inline_crypto/chtls/chtls.h | 3 - .../chelsio/inline_crypto/chtls/chtls_io.c | 100 ++--- .../chelsio/inline_crypto/chtls/chtls_main.c | 3 - drivers/net/ethernet/google/gve/gve_rx.c | 4 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.h | 2 +- drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 4 +- .../marvell/octeontx2/nic/otx2_common.c | 2 +- drivers/net/ethernet/mediatek/mtk_wed_wo.c | 4 +- drivers/net/tun.c | 28 +- drivers/nvme/host/tcp.c | 8 +- drivers/nvme/target/tcp.c | 22 +- drivers/vhost/net.c | 8 +- include/linux/gfp.h | 22 - include/linux/mm_types.h | 18 - include/linux/page_frag_cache.h | 278 +++++++++++++ include/linux/sched.h | 4 +- include/linux/skbuff.h | 3 +- include/net/sock.h | 29 +- kernel/bpf/cpumap.c | 2 +- kernel/exit.c | 3 +- kernel/fork.c | 3 +- mm/Kconfig.debug | 8 + mm/Makefile | 2 + mm/page_alloc.c | 136 ------- mm/page_frag_cache.c | 337 ++++++++++++++++ mm/page_frag_test.c | 379 ++++++++++++++++++ net/core/skbuff.c | 56 +-- net/core/skmsg.c | 22 +- net/core/sock.c | 46 ++- net/core/xdp.c | 2 +- net/ipv4/ip_output.c | 33 +- net/ipv4/tcp.c | 35 +- net/ipv4/tcp_output.c | 28 +- net/ipv6/ip6_output.c | 33 +- net/kcm/kcmsock.c | 30 +- net/mptcp/protocol.c | 70 ++-- net/rxrpc/conn_object.c | 4 +- net/rxrpc/local_object.c | 4 +- net/rxrpc/txbuf.c | 15 +- net/sched/em_meta.c | 2 +- net/sunrpc/svcsock.c | 12 +- net/tls/tls_device.c | 139 ++++--- 47 files changed, 1576 insertions(+), 556 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c create mode 100644 mm/page_frag_test.c