From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=91.218.175.165 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794203789; b=zjCc1Hj8SarneCq0vR2zJFI4evhE6oUYdY9e7MYaA9bmA//UVRYCkON0DY2BlH/wZ7UM CNonroh1WAr1OOhBjnfI9XJIoPIH02PuBykrTUKHi4O/P3ppy/RKlrFCYXysDegwFHrEm y3g8maNXlwSrCRJFaIowmgddv7U5NZgsZeibB9p+27mb/SbyHg0p4o6fDXad/A+IANvSP zxk5Q82t6n3rLAB6DRtAJRbFesW+aqMVmHJKDCFksV50/4m1INazffo/jCYUnml6irtS3 BSgeIdHuHv+x+29oMo2vaZoRKjO8lu0KNy1uUfB49ng86sy+DROXb2OR5ME3EEN2OcA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794203789; h=DMARC-Filter:X-Envelope-To:DKIM-Signature:X-Envelope-To:Received: X-Mizu-Trace-ID:X-Migadu-Flow:From:To:Cc:Subject:Date:Message-ID: X-Mailer:In-Reply-To:References:MIME-Version:Content-type: Content-Transfer-Encoding; bh=cBPK2bWCIiA35KexCp977hu0u4JhPWx94qijTZF4Drw=; b=eyZZ5pvJHvQDy5ckfyVgT9G8qS+U3ZgGQ4SXRqwIlLtaGerLsuKtoXqtxaDtdkKk5IbD DlOTjVMJDQS861hWV9l232Lrh/wySJT9arGLCcjnDVpnG0MCOkUctDyC9F9LMn94zkoHU nWKR4EyEYEU57DayOIKaRYxRA9g+bajdCfjcNhNEamT7F4FQWZUpZVSyePKVmKOoQUWiv IkAdDX8hh+Lfu6A9iI0WQdBoLppeVM8t/G93T+rAyFDd+H473wNFKoce6wPWMC75x+eun 43jcG7cwGxU5gS8LYsG1U/9L6qsEZLXUeKbHdDs2j8FiB3e9yjyFIw/w6dc8tjJT9IA== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b="lUKae8B/"; arc=none smtp.remote-ip=91.218.175.165 Received: from mta0.migadu.com (out-165.mta0.migadu.com [91.218.175.165]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DD6F8606A321 for ; Mon, 9 Nov 2026 05:56:28 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org DD6F8606A321 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key, unprotected) header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=lUKae8B/ X-Envelope-To: linux-kernel@vger.kernel.org DKIM-Signature: a=rsa-sha256; bh=Cu449HxZRkFE3StVJpRmbTVf00lAahvBFPbJvlhsIco=; c=simple/simple; d=linux.dev; h=from:to:subject:date:message-id:mime-version:content-type; s=key1; t=1794203787; v=1; x=1794808587; b=lUKae8B/DlS4DBPXOqay/pn6wFDHYSYdtxFjFILwjJRJZ+fSX61q0xm9bddOQLHd7NgYzr9X 2tz2n6VBltaLFeysUW8f/CtEtv2PktQauKKPyia1N3IkVc9OMzE3zNS2w+8RevnsfDfDvnpmb/y VqpOpJGg17/VWzh7uvij3nn8= X-Envelope-To: linux-kernel@vger.kernel.org Received: by mta10.migadu.com with ESMTPS id 11e07ec0317c68cf; Mon, 09 Nov 2026 05:56:26 +0000 X-Mizu-Trace-ID: 11e07ec0317c68cf X-Migadu-Flow: FLOW_OUT From: Baoquan He To: linux-mm@kvack.org Cc: akpm@linux-foundation.org, david@kernel.org, chrisl@kernel.org, kasong@tencent.com, nphamcs@gmail.com, baohua@kernel.org, youngjun.park@lge.com, corbet@lwn.net, hannes@cmpxchg.org, chengming.zhou@linux.dev, kunwu.chan@gmail.com, klarasmodin@gmail.com, linux-kernel@vger.kernel.org, Baoquan He Subject: [PATCH v5 07/19] mm, swap: refactor swapoff and add xswap_destroy Date: Mon, 9 Nov 2026 13:54:43 +0800 Message-ID: <20261109055455.536925-8-baoquan.he@linux.dev> X-Mailer: git-send-email 2.54.0 In-Reply-To: <20261109055455.536925-1-baoquan.he@linux.dev> References: <20261109055455.536925-1-baoquan.he@linux.dev> X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-type: text/plain Content-Transfer-Encoding: 8bit From: Baoquan He Extract __swapoff() from sys_swapoff() so the teardown logic can be shared, and make it work for file-less devices. Add xswap_destroy() to tear down a file-less xswap device by swap type, exposed via /sys/kernel/mm/xswap/destroy. Writing a swap type tears down that device; it requires CAP_SYS_ADMIN. Signed-off-by: Baoquan He --- mm/swapfile.c | 127 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 109 insertions(+), 18 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index 616adbb298e7..3f2b863f7dd7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -86,6 +86,7 @@ static void xswap_unmap_clusters(struct swap_info_struct *si, static int xswap_mapped_end(pte_t *pte, unsigned long addr, void *data); static int xswap_create(int prio); +static int xswap_destroy(int type); static ssize_t xswap_create_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -116,8 +117,35 @@ static ssize_t xswap_create_store(struct kobject *kobj, static struct kobj_attribute xswap_create_attr = __ATTR(create, 0200, NULL, xswap_create_store); +static ssize_t xswap_destroy_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long type; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + err = kstrtoul(buf, 0, &type); + if (err) + return err; + if (type >= MAX_SWAPFILES) + return -EINVAL; + + err = xswap_destroy(type); + if (err) + return err; + + return count; +} + +static struct kobj_attribute xswap_destroy_attr = __ATTR(destroy, 0200, NULL, + xswap_destroy_store); + static struct attribute *xswap_attrs[] = { &xswap_create_attr.attr, + &xswap_destroy_attr.attr, NULL, }; @@ -3365,13 +3393,14 @@ static void flush_percpu_swap_cluster(struct swap_info_struct *si) } } +static int swap_info_remove(struct swap_info_struct *p); +static int __swapoff(struct swap_info_struct *p); SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; - struct file *swap_file, *victim; + struct file *victim; struct address_space *mapping; - struct inode *inode; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) @@ -3388,7 +3417,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) { + if (p->swap_file && p->swap_file->f_mapping == mapping) { found = 1; break; } @@ -3407,20 +3436,50 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } - if (!security_vm_enough_memory_mm(current->mm, p->pages)) - vm_unacct_memory(p->pages); - else { - err = -ENOMEM; + err = swap_info_remove(p); + if (err) { spin_unlock(&swap_lock); goto out_dput; } + spin_unlock(&swap_lock); + + err = __swapoff(p); + +out_dput: + filp_close(victim, NULL); + return err; +} + +/* + * Drop @p from the avail and active lists and undo its accounting. The + * caller must hold swap_lock and have checked that @p is WRITEOK and not + * pinned for hibernation. + * + * Returns 0, or -ENOMEM with swap_lock still held. + */ +static int swap_info_remove(struct swap_info_struct *p) +{ + if (!security_vm_enough_memory_mm(current->mm, p->pages)) + vm_unacct_memory(p->pages); + else + return -ENOMEM; + spin_lock(&p->lock); del_from_avail_list(p, true); plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); - spin_unlock(&swap_lock); + return 0; +} + +/* Common swap teardown after list removal; shared by sys_swapoff() and + * xswap_destroy(). + */ +static int __swapoff(struct swap_info_struct *p) +{ + struct file *swap_file = NULL; + int err; wait_for_allocation(p); @@ -3431,7 +3490,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); - goto out_dput; + return err; } /* @@ -3471,15 +3530,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) kfree(p->global_cluster); p->global_cluster = NULL; free_swap_cluster_info(p); + /* + * The device is off swap_active_head and no longer WRITEOK, so no + * reader can observe these; clearing them here needs no lock. + */ p->max = 0; p->cluster_info = NULL; - inode = mapping->host; + if (swap_file) { + struct inode *inode = swap_file->f_mapping->host; - inode_lock(inode); - inode->i_flags &= ~S_SWAPFILE; - inode_unlock(inode); - filp_close(swap_file, NULL); + inode_lock(inode); + inode->i_flags &= ~S_SWAPFILE; + inode_unlock(inode); + filp_close(swap_file, NULL); + } /* * Clear the SWP_USED flag after all resources are freed so that swapon @@ -3490,13 +3555,10 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->flags = 0; spin_unlock(&swap_lock); - err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); -out_dput: - filp_close(victim, NULL); - return err; + return 0; } #ifdef CONFIG_PROC_FS @@ -4269,6 +4331,35 @@ static int xswap_create(int prio) spin_unlock(&swap_lock); return error; } + +/* Tear down a file-less xswap device by its swap type. */ +static int xswap_destroy(int type) +{ + struct swap_info_struct *p; + int err; + + p = swap_type_to_info(type); + if (!p) + return -EINVAL; + + spin_lock(&swap_lock); + if (!(p->flags & SWP_WRITEOK) || !(p->flags & SWP_XSWAP)) { + spin_unlock(&swap_lock); + return -EINVAL; + } + /* Refuse swapoff while the device is pinned for hibernation */ + if (p->flags & SWP_HIBERNATION) { + spin_unlock(&swap_lock); + return -EBUSY; + } + + err = swap_info_remove(p); + spin_unlock(&swap_lock); + if (err) + return err; + + return __swapoff(p); +} #endif /* CONFIG_XSWAP */ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) -- 2.54.0