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 X-Spam-Level: X-Spam-Status: No, score=-15.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 20887C433B4 for ; Thu, 15 Apr 2021 18:08:49 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E525E611CD for ; Thu, 15 Apr 2021 18:08:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234575AbhDOSJK (ORCPT ); Thu, 15 Apr 2021 14:09:10 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:46498 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234574AbhDOSJI (ORCPT ); Thu, 15 Apr 2021 14:09:08 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1618510124; h=from:from: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; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=Fpz0dHtykwvnxZ3bRpNA5WDF5pXKuGF6qTFY9SaJdRedz594z2g1FmaN7nIWc9Hrv2no+h UT3tkmlE3T3iZY6k96dovgQcl57m3PmSd1ZfyTokhrD77yxTJiKJ8zviyF31FJx+HEvHUQ 610VkESylR0ETuT09B1SGdWuK+PRp4c= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-287-OE96HVLmORK72ygKyf7eRg-1; Thu, 15 Apr 2021 14:08:39 -0400 X-MC-Unique: OE96HVLmORK72ygKyf7eRg-1 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 73FD610054F6; Thu, 15 Apr 2021 18:08:37 +0000 (UTC) Received: from carbon (unknown [10.36.110.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8013D13487; Thu, 15 Apr 2021 18:08:33 +0000 (UTC) Date: Thu, 15 Apr 2021 20:08:32 +0200 From: Jesper Dangaard Brouer To: David Laight Cc: 'Matthew Wilcox' , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "netdev@vger.kernel.org" , "linuxppc-dev@lists.ozlabs.org" , "linux-arm-kernel@lists.infradead.org" , "linux-mips@vger.kernel.org" , Ilias Apalodimas , Matteo Croce , Grygorii Strashko , Arnd Bergmann , "Christoph Hellwig" , brouer@redhat.com Subject: Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems Message-ID: <20210415200832.32796445@carbon> In-Reply-To: References: <20210410205246.507048-1-willy@infradead.org> <20210410205246.507048-2-willy@infradead.org> <20210411114307.5087f958@carbon> <20210411103318.GC2531743@casper.infradead.org> <20210412011532.GG2531743@casper.infradead.org> <20210414101044.19da09df@carbon> <20210414115052.GS2531743@casper.infradead.org> <20210414211322.3799afd4@carbon> <20210414213556.GY2531743@casper.infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.79 on 10.5.11.12 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 14 Apr 2021 21:56:39 +0000 David Laight wrote: > From: Matthew Wilcox > > Sent: 14 April 2021 22:36 > > > > On Wed, Apr 14, 2021 at 09:13:22PM +0200, Jesper Dangaard Brouer wrote: > > > (If others want to reproduce). First I could not reproduce on ARM32. > > > Then I found out that enabling CONFIG_XEN on ARCH=arm was needed to > > > cause the issue by enabling CONFIG_ARCH_DMA_ADDR_T_64BIT. > > > > hmmm ... you should be able to provoke it by enabling ARM_LPAE, > > which selects PHYS_ADDR_T_64BIT, and > > > > config ARCH_DMA_ADDR_T_64BIT > > def_bool 64BIT || PHYS_ADDR_T_64BIT > > > > > struct page { > > > long unsigned int flags; /* 0 4 */ > > > > > > /* XXX 4 bytes hole, try to pack */ > > > > > > union { > > > struct { > > > struct list_head lru; /* 8 8 */ > > > struct address_space * mapping; /* 16 4 */ > > > long unsigned int index; /* 20 4 */ > > > long unsigned int private; /* 24 4 */ > > > }; /* 8 20 */ > > > struct { > > > dma_addr_t dma_addr > > Adding __packed here will remove the 4 byte hole before the union > and the compiler seems clever enough to know that anything following > a 'long' must also be 'long' aligned. Played with __packed in below patch, and I can confirm it seems to work. > So you don't get anything horrid like byte accesses. > On 64bit dma_addr will remain 64bit aligned. > On arm32 dma_addr will be 32bit aligned - but forcing two 32bit access > won't make any difference. See below patch. Where I swap32 the dma address to satisfy page->compound having bit zero cleared. (It is the simplest fix I could come up with). [PATCH] page_pool: handling 32-bit archs with 64-bit dma_addr_t From: Jesper Dangaard Brouer Workaround for storing 64-bit DMA-addr on 32-bit machines in struct page. The page->dma_addr share area with page->compound_head which use bit zero to mark compound pages. This is okay, as DMA-addr are aligned pointers which have bit zero cleared. In the 32-bit case, page->compound_head is 32-bit. Thus, when dma_addr_t is 64-bit it will be located in top 32-bit. Solve by swapping dma_addr 32-bit segments. Signed-off-by: Jesper Dangaard Brouer --- include/linux/mm_types.h | 2 +- include/linux/types.h | 1 + include/net/page_pool.h | 21 ++++++++++++++++++++- net/core/page_pool.c | 8 +++++--- 4 files changed, 27 insertions(+), 5 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..27406e3b1e1b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -100,7 +100,7 @@ struct page { * @dma_addr: might require a 64-bit value even on * 32-bit architectures. */ - dma_addr_t dma_addr; + dma_addr_t dma_addr __packed; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..65fd5d630016 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -141,6 +141,7 @@ typedef u64 blkcnt_t; */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; +//typedef u64 __attribute__((aligned(sizeof(void *)))) dma_addr_t; #else typedef u32 dma_addr_t; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b5b195305346..c2329088665c 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -196,9 +196,28 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +static inline +dma_addr_t page_pool_dma_addr_read(dma_addr_t dma_addr) +{ + /* Workaround for storing 64-bit DMA-addr on 32-bit machines in struct + * page. The page->dma_addr share area with page->compound_head which + * use bit zero to mark compound pages. This is okay, as DMA-addr are + * aligned pointers which have bit zero cleared. + * + * In the 32-bit case, page->compound_head is 32-bit. Thus, when + * dma_addr_t is 64-bit it will be located in top 32-bit. Solve by + * swapping dma_addr 32-bit segments. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (sizeof(long unsigned int) == 4) /* 32-bit system */ + dma_addr = (dma_addr << 32) | (dma_addr >> 32); +#endif + return dma_addr; +} + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + return page_pool_dma_addr_read(page->dma_addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ad8b0707af04..813598ea23f6 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma = page_pool_dma_addr_read(page->dma_addr); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); return NULL; } - page->dma_addr = dma; + page->dma_addr = page_pool_dma_addr_read(dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -294,7 +296,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_dma_addr_read(page->dma_addr); /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer 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 X-Spam-Level: X-Spam-Status: No, score=-15.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 206C2C433B4 for ; Thu, 15 Apr 2021 18:08:46 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 709C360249 for ; Thu, 15 Apr 2021 18:08:45 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 709C360249 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 007FF6B0070; Thu, 15 Apr 2021 14:08:45 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id EFC236B0071; Thu, 15 Apr 2021 14:08:44 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id D4E266B0072; Thu, 15 Apr 2021 14:08:44 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0030.hostedemail.com [216.40.44.30]) by kanga.kvack.org (Postfix) with ESMTP id B35B16B0070 for ; Thu, 15 Apr 2021 14:08:44 -0400 (EDT) Received: from smtpin04.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id 45F054DDD for ; Thu, 15 Apr 2021 18:08:44 +0000 (UTC) X-FDA: 78035386968.04.B94E1FA Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [216.205.24.124]) by imf21.hostedemail.com (Postfix) with ESMTP id CBD6EE000125 for ; Thu, 15 Apr 2021 18:08:41 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1618510123; h=from:from: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; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=QSYQT6m+6tAbDxoq57MEa4kiRgrkvLlZxUf/Hd1EM2K8EJ/+dTmdMtnnG5npdsT/Q9MZTd ph0a47Sj7d2tJxJ1+JQDJtBwNHgDqtBXZdmeNIZr0MsQ5zSnAdemvb4A38+SvHShwA8+nW 4yQwHnl4RFTmtOnDNyFwtn+jKw+11AM= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-287-OE96HVLmORK72ygKyf7eRg-1; Thu, 15 Apr 2021 14:08:39 -0400 X-MC-Unique: OE96HVLmORK72ygKyf7eRg-1 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 73FD610054F6; Thu, 15 Apr 2021 18:08:37 +0000 (UTC) Received: from carbon (unknown [10.36.110.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8013D13487; Thu, 15 Apr 2021 18:08:33 +0000 (UTC) Date: Thu, 15 Apr 2021 20:08:32 +0200 From: Jesper Dangaard Brouer To: David Laight Cc: 'Matthew Wilcox' , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "netdev@vger.kernel.org" , "linuxppc-dev@lists.ozlabs.org" , "linux-arm-kernel@lists.infradead.org" , "linux-mips@vger.kernel.org" , Ilias Apalodimas , Matteo Croce , Grygorii Strashko , Arnd Bergmann , "Christoph Hellwig" , brouer@redhat.com Subject: Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems Message-ID: <20210415200832.32796445@carbon> In-Reply-To: References: <20210410205246.507048-1-willy@infradead.org> <20210410205246.507048-2-willy@infradead.org> <20210411114307.5087f958@carbon> <20210411103318.GC2531743@casper.infradead.org> <20210412011532.GG2531743@casper.infradead.org> <20210414101044.19da09df@carbon> <20210414115052.GS2531743@casper.infradead.org> <20210414211322.3799afd4@carbon> <20210414213556.GY2531743@casper.infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.79 on 10.5.11.12 X-Rspamd-Queue-Id: CBD6EE000125 X-Stat-Signature: inkupuzjkykazoed5zfnxdjqtjaorygj X-Rspamd-Server: rspam02 Received-SPF: none (redhat.com>: No applicable sender policy available) receiver=imf21; identity=mailfrom; envelope-from=""; helo=us-smtp-delivery-124.mimecast.com; client-ip=216.205.24.124 X-HE-DKIM-Result: pass/pass X-HE-Tag: 1618510121-834762 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: On Wed, 14 Apr 2021 21:56:39 +0000 David Laight wrote: > From: Matthew Wilcox > > Sent: 14 April 2021 22:36 > > > > On Wed, Apr 14, 2021 at 09:13:22PM +0200, Jesper Dangaard Brouer wrote: > > > (If others want to reproduce). First I could not reproduce on ARM32. > > > Then I found out that enabling CONFIG_XEN on ARCH=arm was needed to > > > cause the issue by enabling CONFIG_ARCH_DMA_ADDR_T_64BIT. > > > > hmmm ... you should be able to provoke it by enabling ARM_LPAE, > > which selects PHYS_ADDR_T_64BIT, and > > > > config ARCH_DMA_ADDR_T_64BIT > > def_bool 64BIT || PHYS_ADDR_T_64BIT > > > > > struct page { > > > long unsigned int flags; /* 0 4 */ > > > > > > /* XXX 4 bytes hole, try to pack */ > > > > > > union { > > > struct { > > > struct list_head lru; /* 8 8 */ > > > struct address_space * mapping; /* 16 4 */ > > > long unsigned int index; /* 20 4 */ > > > long unsigned int private; /* 24 4 */ > > > }; /* 8 20 */ > > > struct { > > > dma_addr_t dma_addr > > Adding __packed here will remove the 4 byte hole before the union > and the compiler seems clever enough to know that anything following > a 'long' must also be 'long' aligned. Played with __packed in below patch, and I can confirm it seems to work. > So you don't get anything horrid like byte accesses. > On 64bit dma_addr will remain 64bit aligned. > On arm32 dma_addr will be 32bit aligned - but forcing two 32bit access > won't make any difference. See below patch. Where I swap32 the dma address to satisfy page->compound having bit zero cleared. (It is the simplest fix I could come up with). [PATCH] page_pool: handling 32-bit archs with 64-bit dma_addr_t From: Jesper Dangaard Brouer Workaround for storing 64-bit DMA-addr on 32-bit machines in struct page. The page->dma_addr share area with page->compound_head which use bit zero to mark compound pages. This is okay, as DMA-addr are aligned pointers which have bit zero cleared. In the 32-bit case, page->compound_head is 32-bit. Thus, when dma_addr_t is 64-bit it will be located in top 32-bit. Solve by swapping dma_addr 32-bit segments. Signed-off-by: Jesper Dangaard Brouer --- include/linux/mm_types.h | 2 +- include/linux/types.h | 1 + include/net/page_pool.h | 21 ++++++++++++++++++++- net/core/page_pool.c | 8 +++++--- 4 files changed, 27 insertions(+), 5 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..27406e3b1e1b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -100,7 +100,7 @@ struct page { * @dma_addr: might require a 64-bit value even on * 32-bit architectures. */ - dma_addr_t dma_addr; + dma_addr_t dma_addr __packed; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..65fd5d630016 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -141,6 +141,7 @@ typedef u64 blkcnt_t; */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; +//typedef u64 __attribute__((aligned(sizeof(void *)))) dma_addr_t; #else typedef u32 dma_addr_t; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b5b195305346..c2329088665c 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -196,9 +196,28 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +static inline +dma_addr_t page_pool_dma_addr_read(dma_addr_t dma_addr) +{ + /* Workaround for storing 64-bit DMA-addr on 32-bit machines in struct + * page. The page->dma_addr share area with page->compound_head which + * use bit zero to mark compound pages. This is okay, as DMA-addr are + * aligned pointers which have bit zero cleared. + * + * In the 32-bit case, page->compound_head is 32-bit. Thus, when + * dma_addr_t is 64-bit it will be located in top 32-bit. Solve by + * swapping dma_addr 32-bit segments. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (sizeof(long unsigned int) == 4) /* 32-bit system */ + dma_addr = (dma_addr << 32) | (dma_addr >> 32); +#endif + return dma_addr; +} + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + return page_pool_dma_addr_read(page->dma_addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ad8b0707af04..813598ea23f6 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma = page_pool_dma_addr_read(page->dma_addr); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); return NULL; } - page->dma_addr = dma; + page->dma_addr = page_pool_dma_addr_read(dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -294,7 +296,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_dma_addr_read(page->dma_addr); /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer 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 X-Spam-Level: X-Spam-Status: No, score=-13.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6A38EC433ED for ; Thu, 15 Apr 2021 18:09:46 +0000 (UTC) Received: from lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id C96F4611CD for ; Thu, 15 Apr 2021 18:09:45 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C96F4611CD Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=linuxppc-dev-bounces+linuxppc-dev=archiver.kernel.org@lists.ozlabs.org Received: from boromir.ozlabs.org (localhost [IPv6:::1]) by lists.ozlabs.org (Postfix) with ESMTP id 4FLnRr29qpz30FX for ; Fri, 16 Apr 2021 04:09:44 +1000 (AEST) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=YwiFKYOJ; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=YwiFKYOJ; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=redhat.com (client-ip=216.205.24.124; helo=us-smtp-delivery-124.mimecast.com; envelope-from=brouer@redhat.com; receiver=) Authentication-Results: lists.ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=YwiFKYOJ; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=YwiFKYOJ; dkim-atps=neutral Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [216.205.24.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4FLnRK0tMCz304D for ; Fri, 16 Apr 2021 04:09:15 +1000 (AEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1618510153; h=from:from: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; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=YwiFKYOJYdF2O5OXLTLdIvCDcL3i/DdPXp5qJc4UbDsKMeaO3McKQnV00m1hBlzSRhAHJu nR9QowriUBQfsMte88gkVa/Xz+hPvFQrncBvVebMxA/1fi3NY0E55k/BC2J0rikU2vHnFL z/bG8wDaXc3u7j3UD3sRnzksNgCHvxE= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1618510153; h=from:from: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; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=YwiFKYOJYdF2O5OXLTLdIvCDcL3i/DdPXp5qJc4UbDsKMeaO3McKQnV00m1hBlzSRhAHJu nR9QowriUBQfsMte88gkVa/Xz+hPvFQrncBvVebMxA/1fi3NY0E55k/BC2J0rikU2vHnFL z/bG8wDaXc3u7j3UD3sRnzksNgCHvxE= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-287-OE96HVLmORK72ygKyf7eRg-1; Thu, 15 Apr 2021 14:08:39 -0400 X-MC-Unique: OE96HVLmORK72ygKyf7eRg-1 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 73FD610054F6; Thu, 15 Apr 2021 18:08:37 +0000 (UTC) Received: from carbon (unknown [10.36.110.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8013D13487; Thu, 15 Apr 2021 18:08:33 +0000 (UTC) Date: Thu, 15 Apr 2021 20:08:32 +0200 From: Jesper Dangaard Brouer To: David Laight Subject: Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems Message-ID: <20210415200832.32796445@carbon> In-Reply-To: References: <20210410205246.507048-1-willy@infradead.org> <20210410205246.507048-2-willy@infradead.org> <20210411114307.5087f958@carbon> <20210411103318.GC2531743@casper.infradead.org> <20210412011532.GG2531743@casper.infradead.org> <20210414101044.19da09df@carbon> <20210414115052.GS2531743@casper.infradead.org> <20210414211322.3799afd4@carbon> <20210414213556.GY2531743@casper.infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.79 on 10.5.11.12 X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Arnd Bergmann , Grygorii Strashko , "netdev@vger.kernel.org" , Ilias Apalodimas , "linux-kernel@vger.kernel.org" , 'Matthew Wilcox' , "linux-mips@vger.kernel.org" , "linux-mm@kvack.org" , brouer@redhat.com, Matteo Croce , "linuxppc-dev@lists.ozlabs.org" , Christoph Hellwig , "linux-arm-kernel@lists.infradead.org" Errors-To: linuxppc-dev-bounces+linuxppc-dev=archiver.kernel.org@lists.ozlabs.org Sender: "Linuxppc-dev" On Wed, 14 Apr 2021 21:56:39 +0000 David Laight wrote: > From: Matthew Wilcox > > Sent: 14 April 2021 22:36 > > > > On Wed, Apr 14, 2021 at 09:13:22PM +0200, Jesper Dangaard Brouer wrote: > > > (If others want to reproduce). First I could not reproduce on ARM32. > > > Then I found out that enabling CONFIG_XEN on ARCH=arm was needed to > > > cause the issue by enabling CONFIG_ARCH_DMA_ADDR_T_64BIT. > > > > hmmm ... you should be able to provoke it by enabling ARM_LPAE, > > which selects PHYS_ADDR_T_64BIT, and > > > > config ARCH_DMA_ADDR_T_64BIT > > def_bool 64BIT || PHYS_ADDR_T_64BIT > > > > > struct page { > > > long unsigned int flags; /* 0 4 */ > > > > > > /* XXX 4 bytes hole, try to pack */ > > > > > > union { > > > struct { > > > struct list_head lru; /* 8 8 */ > > > struct address_space * mapping; /* 16 4 */ > > > long unsigned int index; /* 20 4 */ > > > long unsigned int private; /* 24 4 */ > > > }; /* 8 20 */ > > > struct { > > > dma_addr_t dma_addr > > Adding __packed here will remove the 4 byte hole before the union > and the compiler seems clever enough to know that anything following > a 'long' must also be 'long' aligned. Played with __packed in below patch, and I can confirm it seems to work. > So you don't get anything horrid like byte accesses. > On 64bit dma_addr will remain 64bit aligned. > On arm32 dma_addr will be 32bit aligned - but forcing two 32bit access > won't make any difference. See below patch. Where I swap32 the dma address to satisfy page->compound having bit zero cleared. (It is the simplest fix I could come up with). [PATCH] page_pool: handling 32-bit archs with 64-bit dma_addr_t From: Jesper Dangaard Brouer Workaround for storing 64-bit DMA-addr on 32-bit machines in struct page. The page->dma_addr share area with page->compound_head which use bit zero to mark compound pages. This is okay, as DMA-addr are aligned pointers which have bit zero cleared. In the 32-bit case, page->compound_head is 32-bit. Thus, when dma_addr_t is 64-bit it will be located in top 32-bit. Solve by swapping dma_addr 32-bit segments. Signed-off-by: Jesper Dangaard Brouer --- include/linux/mm_types.h | 2 +- include/linux/types.h | 1 + include/net/page_pool.h | 21 ++++++++++++++++++++- net/core/page_pool.c | 8 +++++--- 4 files changed, 27 insertions(+), 5 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..27406e3b1e1b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -100,7 +100,7 @@ struct page { * @dma_addr: might require a 64-bit value even on * 32-bit architectures. */ - dma_addr_t dma_addr; + dma_addr_t dma_addr __packed; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..65fd5d630016 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -141,6 +141,7 @@ typedef u64 blkcnt_t; */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; +//typedef u64 __attribute__((aligned(sizeof(void *)))) dma_addr_t; #else typedef u32 dma_addr_t; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b5b195305346..c2329088665c 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -196,9 +196,28 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +static inline +dma_addr_t page_pool_dma_addr_read(dma_addr_t dma_addr) +{ + /* Workaround for storing 64-bit DMA-addr on 32-bit machines in struct + * page. The page->dma_addr share area with page->compound_head which + * use bit zero to mark compound pages. This is okay, as DMA-addr are + * aligned pointers which have bit zero cleared. + * + * In the 32-bit case, page->compound_head is 32-bit. Thus, when + * dma_addr_t is 64-bit it will be located in top 32-bit. Solve by + * swapping dma_addr 32-bit segments. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (sizeof(long unsigned int) == 4) /* 32-bit system */ + dma_addr = (dma_addr << 32) | (dma_addr >> 32); +#endif + return dma_addr; +} + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + return page_pool_dma_addr_read(page->dma_addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ad8b0707af04..813598ea23f6 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma = page_pool_dma_addr_read(page->dma_addr); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); return NULL; } - page->dma_addr = dma; + page->dma_addr = page_pool_dma_addr_read(dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -294,7 +296,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_dma_addr_read(page->dma_addr); /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer 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 X-Spam-Level: X-Spam-Status: No, score=-13.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8D344C433B4 for ; Thu, 15 Apr 2021 18:10:55 +0000 (UTC) Received: from desiato.infradead.org (desiato.infradead.org [90.155.92.199]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 0EFDE611CD for ; Thu, 15 Apr 2021 18:10:55 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 0EFDE611CD Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=desiato.20200630; h=Sender:Content-Transfer-Encoding :Content-Type:List-Subscribe:List-Help:List-Post:List-Archive: List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To:Message-ID: Subject:Cc:To:From:Date:Reply-To:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=8SG7NPjc+NCMoubTtsL5+GPuqUlXwKKiyUC1CZs3Tdk=; b=SeThvVjc6JNhHoaWV8ejLonJR xPjN4eL4l9ykffNjbEZWWa0NSGYfdYnbVS1B+IWhFF7Z7V+ECkK9YzqYPwTzSRtfQoWlSQes4j9nM ZMZp2X5kUqgeI4kELABjHUWyr1y3S/0fO+H86TsiZrz3GC4GxSJV9LFlJ/OFlT7Ww9xXNAiqUDECc Ooe8vRnYc4mdIxiHVHcNPtY6cMMJ+zVHBL1UwrU1Cx9ZK308SzXjS5pW6ofRAXydQ2aEixfKEhJWh O+Gy3c4PLL7uIzNhpFTRipuyrL7jK1VpCFy6azIfVbXQCk9N+HdnJnZQuswkt9ZDxbA7P3AAgfVv6 jTulhzTNA==; Received: from localhost ([::1] helo=desiato.infradead.org) by desiato.infradead.org with esmtp (Exim 4.94 #2 (Red Hat Linux)) id 1lX6QB-00GwZI-My; Thu, 15 Apr 2021 18:08:55 +0000 Received: from bombadil.infradead.org ([2607:7c80:54:e::133]) by desiato.infradead.org with esmtps (Exim 4.94 #2 (Red Hat Linux)) id 1lX6Q6-00GwYq-K3 for linux-arm-kernel@desiato.infradead.org; Thu, 15 Apr 2021 18:08:51 +0000 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=bombadil.20210309; h=Content-Transfer-Encoding: Content-Type:MIME-Version:References:In-Reply-To:Message-ID:Subject:Cc:To: From:Date:Sender:Reply-To:Content-ID:Content-Description; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=BsIF1Usu3qtqAA0HeudVRP0XTE MrTjqhZc6xU6/zjcJkgbdzmc8GkYWjpyW10cwbXqqpe/cKygt0n9F3KSVsw9uZPPdUU0OLT2itsRQ e+K6VsRpmitnUT8Ji6Oio9GKlP0FUfRj6at3v57p+vc0sycKWjOY67qKf6tkADGPIBe7PVr9cRtxC 4J1i5j/2MTcu73P857Q+pPCb+acwMDp/Zja8qbiNx1nevJAEmWZx1guZAr+5FuNWcoE4oj8cBw9Od 9LRBDUwVtbLfQl3EAu5/Ho2lMZ/cscZHj0pvR5tmaI61Zo9UJvDAYnwTBXNuq2KdxuGe5YyE0SDJM kZPN6hbA==; Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]) by bombadil.infradead.org with esmtps (Exim 4.94 #2 (Red Hat Linux)) id 1lX6Q3-008ndr-D9 for linux-arm-kernel@lists.infradead.org; Thu, 15 Apr 2021 18:08:49 +0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1618510124; h=from:from: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; bh=CFSW/xx6h8VP0E9MM0SVm+J+UNt/2rTNWHWvDh7sIOU=; b=Fpz0dHtykwvnxZ3bRpNA5WDF5pXKuGF6qTFY9SaJdRedz594z2g1FmaN7nIWc9Hrv2no+h UT3tkmlE3T3iZY6k96dovgQcl57m3PmSd1ZfyTokhrD77yxTJiKJ8zviyF31FJx+HEvHUQ 610VkESylR0ETuT09B1SGdWuK+PRp4c= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-287-OE96HVLmORK72ygKyf7eRg-1; Thu, 15 Apr 2021 14:08:39 -0400 X-MC-Unique: OE96HVLmORK72ygKyf7eRg-1 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 73FD610054F6; Thu, 15 Apr 2021 18:08:37 +0000 (UTC) Received: from carbon (unknown [10.36.110.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8013D13487; Thu, 15 Apr 2021 18:08:33 +0000 (UTC) Date: Thu, 15 Apr 2021 20:08:32 +0200 From: Jesper Dangaard Brouer To: David Laight Cc: 'Matthew Wilcox' , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "netdev@vger.kernel.org" , "linuxppc-dev@lists.ozlabs.org" , "linux-arm-kernel@lists.infradead.org" , "linux-mips@vger.kernel.org" , Ilias Apalodimas , Matteo Croce , Grygorii Strashko , Arnd Bergmann , "Christoph Hellwig" , brouer@redhat.com Subject: Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems Message-ID: <20210415200832.32796445@carbon> In-Reply-To: References: <20210410205246.507048-1-willy@infradead.org> <20210410205246.507048-2-willy@infradead.org> <20210411114307.5087f958@carbon> <20210411103318.GC2531743@casper.infradead.org> <20210412011532.GG2531743@casper.infradead.org> <20210414101044.19da09df@carbon> <20210414115052.GS2531743@casper.infradead.org> <20210414211322.3799afd4@carbon> <20210414213556.GY2531743@casper.infradead.org> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.12 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20210415_110847_537427_B8C4D164 X-CRM114-Status: GOOD ( 34.79 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org On Wed, 14 Apr 2021 21:56:39 +0000 David Laight wrote: > From: Matthew Wilcox > > Sent: 14 April 2021 22:36 > > > > On Wed, Apr 14, 2021 at 09:13:22PM +0200, Jesper Dangaard Brouer wrote: > > > (If others want to reproduce). First I could not reproduce on ARM32. > > > Then I found out that enabling CONFIG_XEN on ARCH=arm was needed to > > > cause the issue by enabling CONFIG_ARCH_DMA_ADDR_T_64BIT. > > > > hmmm ... you should be able to provoke it by enabling ARM_LPAE, > > which selects PHYS_ADDR_T_64BIT, and > > > > config ARCH_DMA_ADDR_T_64BIT > > def_bool 64BIT || PHYS_ADDR_T_64BIT > > > > > struct page { > > > long unsigned int flags; /* 0 4 */ > > > > > > /* XXX 4 bytes hole, try to pack */ > > > > > > union { > > > struct { > > > struct list_head lru; /* 8 8 */ > > > struct address_space * mapping; /* 16 4 */ > > > long unsigned int index; /* 20 4 */ > > > long unsigned int private; /* 24 4 */ > > > }; /* 8 20 */ > > > struct { > > > dma_addr_t dma_addr > > Adding __packed here will remove the 4 byte hole before the union > and the compiler seems clever enough to know that anything following > a 'long' must also be 'long' aligned. Played with __packed in below patch, and I can confirm it seems to work. > So you don't get anything horrid like byte accesses. > On 64bit dma_addr will remain 64bit aligned. > On arm32 dma_addr will be 32bit aligned - but forcing two 32bit access > won't make any difference. See below patch. Where I swap32 the dma address to satisfy page->compound having bit zero cleared. (It is the simplest fix I could come up with). [PATCH] page_pool: handling 32-bit archs with 64-bit dma_addr_t From: Jesper Dangaard Brouer Workaround for storing 64-bit DMA-addr on 32-bit machines in struct page. The page->dma_addr share area with page->compound_head which use bit zero to mark compound pages. This is okay, as DMA-addr are aligned pointers which have bit zero cleared. In the 32-bit case, page->compound_head is 32-bit. Thus, when dma_addr_t is 64-bit it will be located in top 32-bit. Solve by swapping dma_addr 32-bit segments. Signed-off-by: Jesper Dangaard Brouer --- include/linux/mm_types.h | 2 +- include/linux/types.h | 1 + include/net/page_pool.h | 21 ++++++++++++++++++++- net/core/page_pool.c | 8 +++++--- 4 files changed, 27 insertions(+), 5 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..27406e3b1e1b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -100,7 +100,7 @@ struct page { * @dma_addr: might require a 64-bit value even on * 32-bit architectures. */ - dma_addr_t dma_addr; + dma_addr_t dma_addr __packed; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..65fd5d630016 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -141,6 +141,7 @@ typedef u64 blkcnt_t; */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; +//typedef u64 __attribute__((aligned(sizeof(void *)))) dma_addr_t; #else typedef u32 dma_addr_t; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b5b195305346..c2329088665c 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -196,9 +196,28 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +static inline +dma_addr_t page_pool_dma_addr_read(dma_addr_t dma_addr) +{ + /* Workaround for storing 64-bit DMA-addr on 32-bit machines in struct + * page. The page->dma_addr share area with page->compound_head which + * use bit zero to mark compound pages. This is okay, as DMA-addr are + * aligned pointers which have bit zero cleared. + * + * In the 32-bit case, page->compound_head is 32-bit. Thus, when + * dma_addr_t is 64-bit it will be located in top 32-bit. Solve by + * swapping dma_addr 32-bit segments. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (sizeof(long unsigned int) == 4) /* 32-bit system */ + dma_addr = (dma_addr << 32) | (dma_addr >> 32); +#endif + return dma_addr; +} + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + return page_pool_dma_addr_read(page->dma_addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ad8b0707af04..813598ea23f6 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma = page_pool_dma_addr_read(page->dma_addr); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); return NULL; } - page->dma_addr = dma; + page->dma_addr = page_pool_dma_addr_read(dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -294,7 +296,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_dma_addr_read(page->dma_addr); /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel