From nobody Mon Dec 1 20:57:15 2025 Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.16]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 254F430C631 for ; Mon, 1 Dec 2025 12:24:24 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=192.198.163.16 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764591868; cv=none; b=d9HaoCgsRhouo3r91BVj0JREHT5oChT9q3T+F9HyR8yIS2eofmDrC1cu7EqqLG7LGc0HH2UCgUWrERdXbRXCErMGbr/tWhbIkQL2X3r/0aHPpZb/6AkIfJ8PnLLioYVO24rj2VLeVMp5nfWYymMXFTr6dQmfOk3FozGhf0uJd3Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764591868; c=relaxed/simple; bh=8hCebE/6vQVoeJdDj2t2yEVh2qzS8Dr/Tb3OeINOkq4=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=NLgWAfNRL/OgvJz66OPsakn82PDQjQN7PbYKyre+jZKElJ125YIIWPIIeqxKaucYE+rftmDl8QTWXdwPynqly+RntCXcIQ5mPxoSTdNz37ujLZEKJAi/f5/AyPbZGE+jnz/zMSPgXJ3XONfu8LoB3Y1TgdleDc/Mv9XVAQw4CaM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Qt0NEjzb; arc=none smtp.client-ip=192.198.163.16 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Qt0NEjzb" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1764591865; x=1796127865; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=8hCebE/6vQVoeJdDj2t2yEVh2qzS8Dr/Tb3OeINOkq4=; b=Qt0NEjzb+GKqb9HQLd6Y/GfAnVmzTP+D02yk3Qb2eDX7JSK+KDvap8JP b/Qs0pK4H3xT3x8XIaV3oYhjxYxf04DIcnkeIp8hAFuIKz61y57Bb3gts 6hyj45vbJDV2zhAPabS+RiaqsAi2P8l3vptUbxj0tZz3tj3wP46BxQ+bP 3yU2hci7ipu+wxumkLsfUmh0WkaG5dbCjP3HCae2E+dcraLx1sEadQNxC z2PkSmd0hFocQL0mR843fsDUnLPpQ82Mwu6AADqxeJKgf31dxtpPoESY9 VV3igRvSp8hqmM0pyy+C/f9Poh9iOO7TVzfB9amSiJXk06+Tv//zxLr8R w==; X-CSE-ConnectionGUID: uQ+uOhbfQumaWwhESB31RA== X-CSE-MsgGUID: pGSdUnmORhSx/MCt2G9KZg== X-IronPort-AV: E=McAfee;i="6800,10657,11629"; a="54082918" X-IronPort-AV: E=Sophos;i="6.20,240,1758610800"; d="scan'208";a="54082918" Received: from orviesa003.jf.intel.com ([10.64.159.143]) by fmvoesa110.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Dec 2025 04:24:24 -0800 X-CSE-ConnectionGUID: KM/s3vX5Qd6l5flq2FXcVw== X-CSE-MsgGUID: ZvPnrSJdS0CzA9N6etrHkg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.20,240,1758610800"; d="scan'208";a="198266533" Received: from linux-pnp-server-27.sh.intel.com ([10.239.147.41]) by orviesa003.jf.intel.com with ESMTP; 01 Dec 2025 04:24:20 -0800 From: Tianyou Li To: David Hildenbrand , Oscar Salvador , Mike Rapoport , Wei Yang Cc: linux-mm@kvack.org, Yong Hu , Nanhai Zou , Yuan Liu , Tim Chen , Qiuxu Zhuo , Yu C Chen , Pan Deng , Tianyou Li , Chen Zhang , linux-kernel@vger.kernel.org Subject: [PATCH v4] mm/memory hotplug/unplug: Optimize zone->contiguous update when changes pfn range Date: Mon, 1 Dec 2025 21:22:16 +0800 Message-ID: <20251201132216.1636924-1-tianyou.li@intel.com> X-Mailer: git-send-email 2.47.1 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" When invoke move_pfn_range_to_zone or remove_pfn_range_from_zone, it will update the zone->contiguous by checking the new zone's pfn range from the beginning to the end, regardless the previous state of the old zone. When the zone's pfn range is large, the cost of traversing the pfn range to update the zone->contiguous could be significant. Add fast paths to quickly detect cases where zone is definitely not contiguous without scanning the new zone. The cases are: when the new range did not overlap with previous range, the contiguous should be false; if the new range adjacent with the previous range, just need to check the new range; if the new added pages could not fill the hole of previous zone, the contiguous should be false. The following test cases of memory hotplug for a VM [1], tested in the environment [2], show that this optimization can significantly reduce the memory hotplug time [3]. +----------------+------+---------------+--------------+----------------+ | | Size | Time (before) | Time (after) | Time Reduction | | +------+---------------+--------------+----------------+ | Plug Memory | 256G | 10s | 2s | 80% | | +------+---------------+--------------+----------------+ | | 512G | 33s | 6s | 81% | +----------------+------+---------------+--------------+----------------+ +----------------+------+---------------+--------------+----------------+ | | Size | Time (before) | Time (after) | Time Reduction | | +------+---------------+--------------+----------------+ | Unplug Memory | 256G | 10s | 2s | 80% | | +------+---------------+--------------+----------------+ | | 512G | 34s | 6s | 82% | +----------------+------+---------------+--------------+----------------+ [1] Qemu commands to hotplug 256G/512G memory for a VM: object_add memory-backend-ram,id=3Dhotmem0,size=3D256G/512G,share=3Don device_add virtio-mem-pci,id=3Dvmem1,memdev=3Dhotmem0,bus=3Dport1 qom-set vmem1 requested-size 256G/512G (Plug Memory) qom-set vmem1 requested-size 0G (Unplug Memory) [2] Hardware : Intel Icelake server Guest Kernel : v6.18-rc2 Qemu : v9.0.0 Launch VM : qemu-system-x86_64 -accel kvm -cpu host \ -drive file=3D./Centos10_cloud.qcow2,format=3Dqcow2,if=3Dvirtio \ -drive file=3D./seed.img,format=3Draw,if=3Dvirtio \ -smp 3,cores=3D3,threads=3D1,sockets=3D1,maxcpus=3D3 \ -m 2G,slots=3D10,maxmem=3D2052472M \ -device pcie-root-port,id=3Dport1,bus=3Dpcie.0,slot=3D1,multifunction= =3Don \ -device pcie-root-port,id=3Dport2,bus=3Dpcie.0,slot=3D2 \ -nographic -machine q35 \ -nic user,hostfwd=3Dtcp::3000-:22 Guest kernel auto-onlines newly added memory blocks: echo online > /sys/devices/system/memory/auto_online_blocks [3] The time from typing the QEMU commands in [1] to when the output of 'grep MemTotal /proc/meminfo' on Guest reflects that all hotplugged memory is recognized. Reported-by: Nanhai Zou Reported-by: Chen Zhang Tested-by: Yuan Liu Reviewed-by: Tim Chen Reviewed-by: Qiuxu Zhuo Reviewed-by: Yu C Chen Reviewed-by: Pan Deng Reviewed-by: Nanhai Zou Reviewed-by: Yuan Liu Signed-off-by: Tianyou Li --- mm/internal.h | 8 ++++- mm/memory_hotplug.c | 79 ++++++++++++++++++++++++++++++++++++++++++--- mm/mm_init.c | 36 +++++++++++++-------- 3 files changed, 103 insertions(+), 20 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 1561fc2ff5b8..a94928520a55 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -730,7 +730,13 @@ static inline struct page *pageblock_pfn_to_page(unsig= ned long start_pfn, return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } =20 -void set_zone_contiguous(struct zone *zone); +enum zone_contiguous_state { + CONTIGUOUS_DEFINITELY_NOT =3D 0, + CONTIGUOUS_DEFINITELY =3D 1, + CONTIGUOUS_UNDETERMINED =3D 2, +}; + +void set_zone_contiguous(struct zone *zone, enum zone_contiguous_state sta= te); bool pfn_range_intersects_zones(int nid, unsigned long start_pfn, unsigned long nr_pages); =20 diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0be83039c3b5..b74e558ce822 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -544,6 +544,32 @@ static void update_pgdat_span(struct pglist_data *pgda= t) pgdat->node_spanned_pages =3D node_end_pfn - node_start_pfn; } =20 +static enum zone_contiguous_state __meminit clear_zone_contiguous_for_shri= nking( + struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) +{ + const unsigned long end_pfn =3D start_pfn + nr_pages; + enum zone_contiguous_state result =3D CONTIGUOUS_UNDETERMINED; + + /* + * If the removed pfn range inside the original zone span, the contiguous + * property is surely false. + */ + if (start_pfn > zone->zone_start_pfn && end_pfn < zone_end_pfn(zone)) + result =3D CONTIGUOUS_DEFINITELY_NOT; + + /* + * If the removed pfn range is at the beginning or end of the + * original zone span, the contiguous property is preserved when + * the original zone is contiguous. + */ + else if (start_pfn =3D=3D zone->zone_start_pfn || end_pfn =3D=3D zone_end= _pfn(zone)) + result =3D zone->contiguous ? + CONTIGUOUS_DEFINITELY : CONTIGUOUS_UNDETERMINED; + + clear_zone_contiguous(zone); + return result; +} + void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) @@ -551,6 +577,7 @@ void remove_pfn_range_from_zone(struct zone *zone, const unsigned long end_pfn =3D start_pfn + nr_pages; struct pglist_data *pgdat =3D zone->zone_pgdat; unsigned long pfn, cur_nr_pages; + enum zone_contiguous_state contiguous_state =3D CONTIGUOUS_UNDETERMINED; =20 /* Poison struct pages because they are now uninitialized again. */ for (pfn =3D start_pfn; pfn < end_pfn; pfn +=3D cur_nr_pages) { @@ -571,12 +598,13 @@ void remove_pfn_range_from_zone(struct zone *zone, if (zone_is_zone_device(zone)) return; =20 - clear_zone_contiguous(zone); + contiguous_state =3D clear_zone_contiguous_for_shrinking( + zone, start_pfn, nr_pages); =20 shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); =20 - set_zone_contiguous(zone); + set_zone_contiguous(zone, contiguous_state); } =20 /** @@ -736,6 +764,47 @@ static inline void section_taint_zone_device(unsigned = long pfn) } #endif =20 +static enum zone_contiguous_state __meminit clear_zone_contiguous_for_grow= ing( + struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) +{ + const unsigned long end_pfn =3D start_pfn + nr_pages; + enum zone_contiguous_state result =3D CONTIGUOUS_UNDETERMINED; + + /* + * Given the moved pfn range's contiguous property is always true, + * under the conditional of empty zone, the contiguous property should + * be true. + */ + if (zone_is_empty(zone)) + result =3D CONTIGUOUS_DEFINITELY; + + /* + * If the moved pfn range does not intersect with the original zone span, + * the contiguous property is surely false. + */ + else if (end_pfn < zone->zone_start_pfn || start_pfn > zone_end_pfn(zone)) + result =3D CONTIGUOUS_DEFINITELY_NOT; + + /* + * If the moved pfn range is adjacent to the original zone span, given + * the moved pfn range's contiguous property is always true, the zone's + * contiguous property inherited from the original value. + */ + else if (end_pfn =3D=3D zone->zone_start_pfn || start_pfn =3D=3D zone_end= _pfn(zone)) + result =3D zone->contiguous ? + CONTIGUOUS_DEFINITELY : CONTIGUOUS_DEFINITELY_NOT; + + /* + * If the original zone's hole larger than the moved pages in the range, + * the contiguous property is surely false. + */ + else if (nr_pages < (zone->spanned_pages - zone->present_pages)) + result =3D CONTIGUOUS_DEFINITELY_NOT; + + clear_zone_contiguous(zone); + return result; +} + /* * Associate the pfn range with the given zone, initializing the memmaps * and resizing the pgdat/zone data to span the added pages. After this @@ -752,8 +821,8 @@ void move_pfn_range_to_zone(struct zone *zone, unsigned= long start_pfn, { struct pglist_data *pgdat =3D zone->zone_pgdat; int nid =3D pgdat->node_id; - - clear_zone_contiguous(zone); + const enum zone_contiguous_state contiguous_state =3D + clear_zone_contiguous_for_growing(zone, start_pfn, nr_pages); =20 if (zone_is_empty(zone)) init_currently_empty_zone(zone, start_pfn, nr_pages); @@ -783,7 +852,7 @@ void move_pfn_range_to_zone(struct zone *zone, unsigned= long start_pfn, MEMINIT_HOTPLUG, altmap, migratetype, isolate_pageblock); =20 - set_zone_contiguous(zone); + set_zone_contiguous(zone, contiguous_state); } =20 struct auto_movable_stats { diff --git a/mm/mm_init.c b/mm/mm_init.c index 7712d887b696..06db3fcf7f95 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2263,26 +2263,34 @@ void __init init_cma_pageblock(struct page *page) } #endif =20 -void set_zone_contiguous(struct zone *zone) +void set_zone_contiguous(struct zone *zone, enum zone_contiguous_state sta= te) { unsigned long block_start_pfn =3D zone->zone_start_pfn; unsigned long block_end_pfn; =20 - block_end_pfn =3D pageblock_end_pfn(block_start_pfn); - for (; block_start_pfn < zone_end_pfn(zone); - block_start_pfn =3D block_end_pfn, - block_end_pfn +=3D pageblock_nr_pages) { + if (state =3D=3D CONTIGUOUS_DEFINITELY) { + zone->contiguous =3D true; + return; + } else if (state =3D=3D CONTIGUOUS_DEFINITELY_NOT) { + // zone contiguous has already cleared as false, just return. + return; + } else if (state =3D=3D CONTIGUOUS_UNDETERMINED) { + block_end_pfn =3D pageblock_end_pfn(block_start_pfn); + for (; block_start_pfn < zone_end_pfn(zone); + block_start_pfn =3D block_end_pfn, + block_end_pfn +=3D pageblock_nr_pages) { =20 - block_end_pfn =3D min(block_end_pfn, zone_end_pfn(zone)); + block_end_pfn =3D min(block_end_pfn, zone_end_pfn(zone)); =20 - if (!__pageblock_pfn_to_page(block_start_pfn, - block_end_pfn, zone)) - return; - cond_resched(); - } + if (!__pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, zone)) + return; + cond_resched(); + } =20 - /* We confirm that there is no hole */ - zone->contiguous =3D true; + /* We confirm that there is no hole */ + zone->contiguous =3D true; + } } =20 /* @@ -2348,7 +2356,7 @@ void __init page_alloc_init_late(void) shuffle_free_memory(NODE_DATA(nid)); =20 for_each_populated_zone(zone) - set_zone_contiguous(zone); + set_zone_contiguous(zone, CONTIGUOUS_UNDETERMINED); =20 /* Initialize page ext after all struct pages are initialized. */ if (deferred_struct_pages) --=20 2.47.1