From mboxrd@z Thu Jan 1 00:00:00 1970 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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id AD257C3600C for ; Thu, 3 Apr 2025 14:11:28 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id D87F4280006; Thu, 3 Apr 2025 10:11:26 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id D3973280001; Thu, 3 Apr 2025 10:11:26 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id C022C280006; Thu, 3 Apr 2025 10:11:26 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0010.hostedemail.com [216.40.44.10]) by kanga.kvack.org (Postfix) with ESMTP id A13DE280001 for ; Thu, 3 Apr 2025 10:11:26 -0400 (EDT) Received: from smtpin26.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay05.hostedemail.com (Postfix) with ESMTP id 78D1656A8C for ; Thu, 3 Apr 2025 14:11:27 +0000 (UTC) X-FDA: 83292920214.26.A0A3BAD Received: from smtp-out2.suse.de (smtp-out2.suse.de [195.135.223.131]) by imf09.hostedemail.com (Postfix) with ESMTP id D4F1C140004 for ; Thu, 3 Apr 2025 14:11:24 +0000 (UTC) Authentication-Results: imf09.hostedemail.com; dkim=pass header.d=suse.cz header.s=susede2_rsa header.b=2l64JBxQ; dkim=pass header.d=suse.cz header.s=susede2_ed25519 header.b="kuc3/WQF"; dkim=pass header.d=suse.cz header.s=susede2_rsa header.b=2l64JBxQ; dkim=pass header.d=suse.cz header.s=susede2_ed25519 header.b="kuc3/WQF"; dmarc=none; spf=pass (imf09.hostedemail.com: domain of vbabka@suse.cz designates 195.135.223.131 as permitted sender) smtp.mailfrom=vbabka@suse.cz ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1743689485; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=IpKQJ1DZO4HDvv1M1OG+goh5mFQUpBNjEB6oS1DI/0Q=; b=cunStw9NmI8U88bjk/EhqDZ++BNwKSzz+lzUjUwV6GRbJo6IltEJ4j2TG0WqURwX8BFH25 cg5+x22m7KO22DxGsLFzDuhMa3sTrSqWC70KPGWtoYoawWUzL5MH7ZKb89dBUAeApkpVuD k3kpZpP2A8MwCqIPbPrFsbQTDXypjLA= ARC-Authentication-Results: i=1; imf09.hostedemail.com; dkim=pass header.d=suse.cz header.s=susede2_rsa header.b=2l64JBxQ; dkim=pass header.d=suse.cz header.s=susede2_ed25519 header.b="kuc3/WQF"; dkim=pass header.d=suse.cz header.s=susede2_rsa header.b=2l64JBxQ; dkim=pass header.d=suse.cz header.s=susede2_ed25519 header.b="kuc3/WQF"; dmarc=none; spf=pass (imf09.hostedemail.com: domain of vbabka@suse.cz designates 195.135.223.131 as permitted sender) smtp.mailfrom=vbabka@suse.cz ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1743689485; a=rsa-sha256; cv=none; b=MffYh6mDUTew7SRyNvbWQXo+R8UsIaE+7mc7Iq7DEv6zSWH6srPD2Di7BEzGK/l+Uq9UMU Iu1CEd+WPXp75rvyoXbR5VPaKJVv8N/r315CP8QzQ9foZeqrbg/nMQXX48r2RuwyCCvs7s /2Pm8eC8DEGAW+KiPCxjw3LIGoL29UY= Received: from imap1.dmz-prg2.suse.org (unknown [10.150.64.97]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by smtp-out2.suse.de (Postfix) with ESMTPS id 0CC531F390; Thu, 3 Apr 2025 14:11:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.cz; s=susede2_rsa; t=1743689483; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=IpKQJ1DZO4HDvv1M1OG+goh5mFQUpBNjEB6oS1DI/0Q=; b=2l64JBxQfvX4U/Pp4BW677aGlOZFcFy558f1v4eM7STMGl4vU5EZgf6o/rUzVISL4dTOdM X9WU/TYp6wuEYYRR26b0W2ZbsYy0u4arRo62Zlxs8sHm9kP8yp2UzYqU0SRnkUx+Nclxj7 f/Ye8MhAcsCShLTkVMbXJqFfKB0l1Jc= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.cz; s=susede2_ed25519; t=1743689483; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=IpKQJ1DZO4HDvv1M1OG+goh5mFQUpBNjEB6oS1DI/0Q=; b=kuc3/WQFmJXoAHMkRqgoLcY32DnurrQeMaYlD45gyuqrLCeQQXdZHwfSSHVm2BYzGYXpOW F50N78k+LmAhtQAA== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.cz; s=susede2_rsa; t=1743689483; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=IpKQJ1DZO4HDvv1M1OG+goh5mFQUpBNjEB6oS1DI/0Q=; b=2l64JBxQfvX4U/Pp4BW677aGlOZFcFy558f1v4eM7STMGl4vU5EZgf6o/rUzVISL4dTOdM X9WU/TYp6wuEYYRR26b0W2ZbsYy0u4arRo62Zlxs8sHm9kP8yp2UzYqU0SRnkUx+Nclxj7 f/Ye8MhAcsCShLTkVMbXJqFfKB0l1Jc= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.cz; s=susede2_ed25519; t=1743689483; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=IpKQJ1DZO4HDvv1M1OG+goh5mFQUpBNjEB6oS1DI/0Q=; b=kuc3/WQFmJXoAHMkRqgoLcY32DnurrQeMaYlD45gyuqrLCeQQXdZHwfSSHVm2BYzGYXpOW F50N78k+LmAhtQAA== Received: from imap1.dmz-prg2.suse.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by imap1.dmz-prg2.suse.org (Postfix) with ESMTPS id E55081392A; Thu, 3 Apr 2025 14:11:22 +0000 (UTC) Received: from dovecot-director2.suse.de ([2a07:de40:b281:106:10:150:64:167]) by imap1.dmz-prg2.suse.org with ESMTPSA id gOGZNwqX7mePUAAAD6G6ig (envelope-from ); Thu, 03 Apr 2025 14:11:22 +0000 Message-ID: <81ffcfee-8f18-4392-a9ce-ff3f60f7b5b1@suse.cz> Date: Thu, 3 Apr 2025 16:11:22 +0200 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH RFC v3 2/8] slab: add opt-in caching layer of percpu sheaves Content-Language: en-US To: Harry Yoo Cc: Suren Baghdasaryan , "Liam R. Howlett" , Christoph Lameter , David Rientjes , Roman Gushchin , Uladzislau Rezki , linux-mm@kvack.org, linux-kernel@vger.kernel.org, rcu@vger.kernel.org, maple-tree@lists.infradead.org References: <20250317-slub-percpu-caches-v3-0-9d9884d8b643@suse.cz> <20250317-slub-percpu-caches-v3-2-9d9884d8b643@suse.cz> From: Vlastimil Babka In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Rspamd-Server: rspam11 X-Rspamd-Queue-Id: D4F1C140004 X-Stat-Signature: 1nb6r5ij7qckamrj8qpdpu6feucd43m4 X-Rspam-User: X-HE-Tag: 1743689484-880299 X-HE-Meta: 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 +iNujeXl 0S044uW3PM6G6Vnp3gaW73tp/Hyw7aucPAW9mFoVon6zpj45JuTHGittdqcGX1+/6LhLX1Amxjx9TG8TtQy8J0lvoUsA/bSHHGh68BKWyacyiEXQrKZWNgZVKwN42FJsPOVT0x5qyc6y1lQl+18vderU7fvfg4+di4t6qjGmUePuBbzMSkR59ueBhfU2bkEnuc4UF5GiLUkW8RbbDx666jj9HGh8GqPBmOlLk+9RSCkJAK/IFt75YE1VN1cP+OcVw83Bin7PGeIxylSeg9Qk9GejSPqjyRL3jg6wq X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: On 4/3/25 10:31, Harry Yoo wrote: >> +/* >> + * Bulk free objects to the percpu sheaves. >> + * Unlike free_to_pcs() this includes the calls to all necessary hooks >> + * and the fallback to freeing to slab pages. >> + */ >> +static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p) >> +{ > > [...snip...] > >> +next_batch: >> + if (!localtry_trylock(&s->cpu_sheaves->lock)) >> + goto fallback; >> + >> + pcs = this_cpu_ptr(s->cpu_sheaves); >> + >> + if (unlikely(pcs->main->size == s->sheaf_capacity)) { >> + >> + struct slab_sheaf *empty; >> + >> + if (!pcs->spare) { >> + empty = barn_get_empty_sheaf(pcs->barn); >> + if (empty) { >> + pcs->spare = pcs->main; >> + pcs->main = empty; >> + goto do_free; >> + } >> + goto no_empty; > > Maybe a silly question, but if neither of alloc_from_pcs_bulk() or > free_to_pcs_bulk() allocates empty sheaves (and sometimes put empty or full > sheaves in the barn), you should expect usually sheaves not to be in the barn > when using bulk interfces? Hm maybe, but with patch 5/8 it becomes cheap to check? And there might be caches mixing both bulk and individual allocs? But maybe I should at least add the free sheaf alloc with GFP_NOWAIT attempt to bulk free? Can't recall if I missed it intentionally or forgot. >> -static void >> -init_kmem_cache_node(struct kmem_cache_node *n) >> +static bool >> +init_kmem_cache_node(struct kmem_cache_node *n, struct node_barn *barn) >> { > > Why is the return type bool, when it always succeeds? I guess leftover from earlier versions. Will fix. >> @@ -5421,20 +6295,27 @@ static int init_kmem_cache_nodes(struct kmem_cache *s) >> >> for_each_node_mask(node, slab_nodes) { >> struct kmem_cache_node *n; >> + struct node_barn *barn = NULL; >> >> if (slab_state == DOWN) { >> early_kmem_cache_node_alloc(node); >> continue; >> } >> + >> + if (s->cpu_sheaves) { >> + barn = kmalloc_node(sizeof(*barn), GFP_KERNEL, node); >> + >> + if (!barn) >> + return 0; >> + } >> + >> n = kmem_cache_alloc_node(kmem_cache_node, >> GFP_KERNEL, node); >> - >> - if (!n) { >> - free_kmem_cache_nodes(s); >> + if (!n) >> return 0; >> - } > > Looks like it's leaking the barn > if the allocation of kmem_cache_node fails? Oops right, will add kfree(barn) before return 0; > >> - init_kmem_cache_node(n); >> + init_kmem_cache_node(n, barn); >> + >> s->node[node] = n; >> } >> return 1; >> @@ -6005,12 +6891,24 @@ static int slab_mem_going_online_callback(void *arg) >> */ >> mutex_lock(&slab_mutex); >> list_for_each_entry(s, &slab_caches, list) { >> + struct node_barn *barn = NULL; >> + >> /* >> * The structure may already exist if the node was previously >> * onlined and offlined. >> */ >> if (get_node(s, nid)) >> continue; >> + >> + if (s->cpu_sheaves) { >> + barn = kmalloc_node(sizeof(*barn), GFP_KERNEL, nid); >> + >> + if (!barn) { >> + ret = -ENOMEM; >> + goto out; >> + } >> + } >> + > > Ditto. > > Otherwise looks good to me :) Thanks a lot!