From nobody Mon Feb 9 05:59:44 2026 Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.15]) (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 054FB331A6A for ; Fri, 30 Jan 2026 15:38:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=192.198.163.15 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769787486; cv=none; b=tLCWQczlkuCGrHXU/O8mSdwayI5vQpJgvVd41a7H5yLPX5Qj5Oya8QBLrDjm7/C6ZTITeKQS42NlSzJana2mM43ttZ2gqta/boJrsXpbrWgQcdKvKrS1qY/YO5+rM9aI2V+rhuPf5l5d2Vd5LkB+2RfSkoWEjOEqJOHJQ2mkkKc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769787486; c=relaxed/simple; bh=XukClm9fljIpYlDSCYiTs15l3rVEQBWBcp4lxswkTpI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=sPnH/pdSEIxMOru/5pnZqZRa3SbspvRyYV07NRE1ycNlLOJuDNEDuWInu3Per9RRXYYWs9imWAYhVvH0CurpwNWAet1EJx+71BlV3BbDsLLBHj4HDGG5TvNDbzH9wQCth4n9tZXs29O55o8qYgPP8y+BpCHzZBgzg3k8ewqlm0M= 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=SHvf7+2I; arc=none smtp.client-ip=192.198.163.15 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="SHvf7+2I" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1769787485; x=1801323485; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=XukClm9fljIpYlDSCYiTs15l3rVEQBWBcp4lxswkTpI=; b=SHvf7+2IUUBx783YdjnzoSQNbGy054+DudCA82l5lrLmvW2OfDvAgO/l UZ/vsuVMhn5OA83cmxQxoSrivC7nVzhDvIKDettA8hvwmCmG8ySn6ECdq lzgCf4wak3Lhxod9KxBUiTP7HPej9VGzNMa7mITv3M5seTkANF0BJlIIu MwS4ifAu3BBLepEQnU0AeDUVk6zRIpiXUUWG/owtwSLEWzm4IsC+ysRqy vIpHB9X2bCS3jt8v6FQghuG7WySSK5vsyfG1NYV/1WjPGqzZfq8MdSmI4 nxD+4L9BWHe4Gx7HErnSuOXUJELTkvwVi8pPfrhlTOt9aw7T4FQ2KctLa w==; X-CSE-ConnectionGUID: /owJ5m85SoqPCgx942/8Ww== X-CSE-MsgGUID: gEeg529cQPKSmaDWpq+t0Q== X-IronPort-AV: E=McAfee;i="6800,10657,11686"; a="71124788" X-IronPort-AV: E=Sophos;i="6.21,263,1763452800"; d="scan'208";a="71124788" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by fmvoesa109.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Jan 2026 07:38:04 -0800 X-CSE-ConnectionGUID: 6N7nEZH/TO2QUHEZtC8fCA== X-CSE-MsgGUID: rEwis8p7Tce3oimMej6sRA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.21,263,1763452800"; d="scan'208";a="208989121" Received: from linux-pnp-server-27.sh.intel.com ([10.239.147.41]) by orviesa007.jf.intel.com with ESMTP; 30 Jan 2026 07:38:00 -0800 From: Tianyou Li To: David Hildenbrand , Oscar Salvador , Mike Rapoport , Wei Yang , Michal Hocko 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 v9 1/2] mm/memory hotplug/unplug: Add online_memory_block_pages() and offline_memory_block_pages() Date: Sat, 31 Jan 2026 00:37:55 +0800 Message-ID: <20260130163756.2674225-2-tianyou.li@intel.com> X-Mailer: git-send-email 2.47.1 In-Reply-To: <20260130163756.2674225-1-tianyou.li@intel.com> References: <20260130163756.2674225-1-tianyou.li@intel.com> 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" Encapsulate the mhp_init_memmap_on_memory() and online_pages() into online_memory_block_pages(). Thus we can further optimize the set_zone_contiguous() to check the whole memory block range, instead of check the zone contiguous in separate range. Correspondingly, encapsulate the mhp_deinit_memmap_on_memory() and offline_pages() into offline_memory_block_pages(). Furthermore, move most of memory_block_online() to the new function mhp_block_online(struct memory_block *block) and correspondingly memory_block_offline() to mhp_block_offline(struct memory_block *block). Tested-by: Yuan Liu Reviewed-by: Yuan Liu Signed-off-by: Tianyou Li --- drivers/base/memory.c | 115 +--------------------------- include/linux/memory_hotplug.h | 13 +--- include/linux/mm.h | 6 ++ mm/memory_hotplug.c | 132 ++++++++++++++++++++++++++++++++- 4 files changed, 141 insertions(+), 125 deletions(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 751f248ca4a8..40f014c5dbb1 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -209,115 +209,6 @@ int memory_notify(enum memory_block_state state, void= *v) return blocking_notifier_call_chain(&memory_chain, state, v); } =20 -#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) -static unsigned long memblk_nr_poison(struct memory_block *mem); -#else -static inline unsigned long memblk_nr_poison(struct memory_block *mem) -{ - return 0; -} -#endif - -/* - * Must acquire mem_hotplug_lock in write mode. - */ -static int memory_block_online(struct memory_block *mem) -{ - unsigned long start_pfn =3D section_nr_to_pfn(mem->start_section_nr); - unsigned long nr_pages =3D PAGES_PER_SECTION * sections_per_block; - unsigned long nr_vmemmap_pages =3D 0; - struct zone *zone; - int ret; - - if (memblk_nr_poison(mem)) - return -EHWPOISON; - - zone =3D zone_for_pfn_range(mem->online_type, mem->nid, mem->group, - start_pfn, nr_pages); - - /* - * Although vmemmap pages have a different lifecycle than the pages - * they describe (they remain until the memory is unplugged), doing - * their initialization and accounting at memory onlining/offlining - * stage helps to keep accounting easier to follow - e.g vmemmaps - * belong to the same zone as the memory they backed. - */ - if (mem->altmap) - nr_vmemmap_pages =3D mem->altmap->free; - - mem_hotplug_begin(); - if (nr_vmemmap_pages) { - ret =3D mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); - if (ret) - goto out; - } - - ret =3D online_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages, zone, mem->group); - if (ret) { - if (nr_vmemmap_pages) - mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - goto out; - } - - /* - * Account once onlining succeeded. If the zone was unpopulated, it is - * now already properly populated. - */ - if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), mem->group, - nr_vmemmap_pages); - - mem->zone =3D zone; -out: - mem_hotplug_done(); - return ret; -} - -/* - * Must acquire mem_hotplug_lock in write mode. - */ -static int memory_block_offline(struct memory_block *mem) -{ - unsigned long start_pfn =3D section_nr_to_pfn(mem->start_section_nr); - unsigned long nr_pages =3D PAGES_PER_SECTION * sections_per_block; - unsigned long nr_vmemmap_pages =3D 0; - int ret; - - if (!mem->zone) - return -EINVAL; - - /* - * Unaccount before offlining, such that unpopulated zone and kthreads - * can properly be torn down in offline_pages(). - */ - if (mem->altmap) - nr_vmemmap_pages =3D mem->altmap->free; - - mem_hotplug_begin(); - if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), mem->group, - -nr_vmemmap_pages); - - ret =3D offline_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages, mem->zone, mem->group); - if (ret) { - /* offline_pages() failed. Account back. */ - if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), - mem->group, nr_vmemmap_pages); - goto out; - } - - if (nr_vmemmap_pages) - mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - - mem->zone =3D NULL; -out: - mem_hotplug_done(); - return ret; -} - /* * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is * OK to have direct references to sparsemem variables in here. @@ -329,10 +220,10 @@ memory_block_action(struct memory_block *mem, unsigne= d long action) =20 switch (action) { case MEM_ONLINE: - ret =3D memory_block_online(mem); + ret =3D mhp_block_online(mem); break; case MEM_OFFLINE: - ret =3D memory_block_offline(mem); + ret =3D mhp_block_offline(mem); break; default: WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: " @@ -1243,7 +1134,7 @@ void memblk_nr_poison_sub(unsigned long pfn, long i) atomic_long_sub(i, &mem->nr_hwpoison); } =20 -static unsigned long memblk_nr_poison(struct memory_block *mem) +unsigned long memblk_nr_poison(struct memory_block *mem) { return atomic_long_read(&mem->nr_hwpoison); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index f2f16cdd73ee..8783a11da464 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -12,6 +12,7 @@ struct zone; struct pglist_data; struct mem_section; struct memory_group; +struct memory_block; struct resource; struct vmem_altmap; struct dev_pagemap; @@ -106,11 +107,7 @@ extern void adjust_present_page_count(struct page *pag= e, struct memory_group *group, long nr_pages); /* VM interface that may be used by firmware interface */ -extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_p= ages, - struct zone *zone); -extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long n= r_pages); -extern int online_pages(unsigned long pfn, unsigned long nr_pages, - struct zone *zone, struct memory_group *group); +extern int mhp_block_online(struct memory_block *block); extern unsigned long __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); =20 @@ -261,8 +258,7 @@ static inline void pgdat_resize_init(struct pglist_data= *pgdat) {} #ifdef CONFIG_MEMORY_HOTREMOVE =20 extern void try_offline_node(int nid); -extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct zone *zone, struct memory_group *group); +extern int mhp_block_offline(struct memory_block *block); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -270,8 +266,7 @@ extern int offline_and_remove_memory(u64 start, u64 siz= e); #else static inline void try_offline_node(int nid) {} =20 -static inline int offline_pages(unsigned long start_pfn, unsigned long nr_= pages, - struct zone *zone, struct memory_group *group) +static inline int mhp_block_offline(struct memory_block *block) { return -EINVAL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 6f959d8ca4b4..967605d95131 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4377,6 +4377,7 @@ static inline void num_poisoned_pages_sub(unsigned lo= ng pfn, long i) #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); +extern unsigned long memblk_nr_poison(struct memory_block *mem); #else static inline void memblk_nr_poison_inc(unsigned long pfn) { @@ -4385,6 +4386,11 @@ static inline void memblk_nr_poison_inc(unsigned lon= g pfn) static inline void memblk_nr_poison_sub(unsigned long pfn, long i) { } + +static inline unsigned long memblk_nr_poison(struct memory_block *mem) +{ + return 0; +} #endif =20 #ifndef arch_memory_failure diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c8f492b5daf0..62d6bc8ea2dd 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1085,7 +1085,7 @@ void adjust_present_page_count(struct page *page, str= uct memory_group *group, group->present_kernel_pages +=3D nr_pages; } =20 -int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, +static int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_p= ages, struct zone *zone) { unsigned long end_pfn =3D pfn + nr_pages; @@ -1116,7 +1116,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsi= gned long nr_pages, return ret; } =20 -void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) +static void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long n= r_pages) { unsigned long end_pfn =3D pfn + nr_pages; =20 @@ -1139,7 +1139,7 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, u= nsigned long nr_pages) /* * Must be called with mem_hotplug_lock in write mode. */ -int online_pages(unsigned long pfn, unsigned long nr_pages, +static int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { struct memory_notify mem_arg =3D { @@ -1254,6 +1254,74 @@ int online_pages(unsigned long pfn, unsigned long nr= _pages, return ret; } =20 +static int online_memory_block_pages(unsigned long start_pfn, unsigned lon= g nr_pages, + unsigned long nr_vmemmap_pages, struct zone *zone, + struct memory_group *group) +{ + int ret; + + if (nr_vmemmap_pages) { + ret =3D mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); + if (ret) + return ret; + } + + ret =3D online_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages, zone, group); + if (ret) { + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + return ret; + } + + /* + * Account once onlining succeeded. If the zone was unpopulated, it is + * now already properly populated. + */ + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), group, + nr_vmemmap_pages); + + return ret; +} + +/* + * Must acquire mem_hotplug_lock in write mode. + */ +int mhp_block_online(struct memory_block *mem) +{ + unsigned long start_pfn =3D section_nr_to_pfn(mem->start_section_nr); + unsigned long nr_pages =3D PAGES_PER_SECTION * sections_per_block; + unsigned long nr_vmemmap_pages =3D 0; + struct zone *zone; + int ret; + + if (memblk_nr_poison(mem)) + return -EHWPOISON; + + zone =3D zone_for_pfn_range(mem->online_type, mem->nid, mem->group, + start_pfn, nr_pages); + + /* + * Although vmemmap pages have a different lifecycle than the pages + * they describe (they remain until the memory is unplugged), doing + * their initialization and accounting at memory onlining/offlining + * stage helps to keep accounting easier to follow - e.g vmemmaps + * belong to the same zone as the memory they backed. + */ + if (mem->altmap) + nr_vmemmap_pages =3D mem->altmap->free; + + mem_hotplug_begin(); + ret =3D online_memory_block_pages(start_pfn, nr_pages, nr_vmemmap_pages, + zone, mem->group); + if (!ret) + mem->zone =3D zone; + mem_hotplug_done(); + + return ret; +} + /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG = */ static pg_data_t *hotadd_init_pgdat(int nid) { @@ -1896,7 +1964,7 @@ static int count_system_ram_pages_cb(unsigned long st= art_pfn, /* * Must be called with mem_hotplug_lock in write mode. */ -int offline_pages(unsigned long start_pfn, unsigned long nr_pages, +static int offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { unsigned long pfn, managed_pages, system_ram_pages =3D 0; @@ -2101,6 +2169,62 @@ int offline_pages(unsigned long start_pfn, unsigned = long nr_pages, return ret; } =20 +static int offline_memory_block_pages(unsigned long start_pfn, + unsigned long nr_pages, unsigned long nr_vmemmap_pages, + struct zone *zone, struct memory_group *group) +{ + int ret; + + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), group, + -nr_vmemmap_pages); + + ret =3D offline_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages, zone, group); + if (ret) { + /* offline_pages() failed. Account back. */ + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), + group, nr_vmemmap_pages); + return ret; + } + + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + + return ret; +} + +/* + * Must acquire mem_hotplug_lock in write mode. + */ +int mhp_block_offline(struct memory_block *mem) +{ + unsigned long start_pfn =3D section_nr_to_pfn(mem->start_section_nr); + unsigned long nr_pages =3D PAGES_PER_SECTION * sections_per_block; + unsigned long nr_vmemmap_pages =3D 0; + int ret; + + if (!mem->zone) + return -EINVAL; + + /* + * Unaccount before offlining, such that unpopulated zone and kthreads + * can properly be torn down in offline_pages(). + */ + if (mem->altmap) + nr_vmemmap_pages =3D mem->altmap->free; + + mem_hotplug_begin(); + ret =3D offline_memory_block_pages(start_pfn, nr_pages, nr_vmemmap_pages, + mem->zone, mem->group); + if (!ret) + mem->zone =3D NULL; + mem_hotplug_done(); + + return ret; +} + static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int *nid =3D arg; --=20 2.47.1