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 B3AC5CDB483 for ; Tue, 17 Oct 2023 12:06:07 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id A710580038; Tue, 17 Oct 2023 08:06:06 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id A03178D000C; Tue, 17 Oct 2023 08:06:06 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 8C08680038; Tue, 17 Oct 2023 08:06:06 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id 752818D000C for ; Tue, 17 Oct 2023 08:06:06 -0400 (EDT) Received: from smtpin15.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay05.hostedemail.com (Postfix) with ESMTP id 2076D41055 for ; Tue, 17 Oct 2023 12:06:06 +0000 (UTC) X-FDA: 81354825132.15.BB7992D Received: from mail-lf1-f52.google.com (mail-lf1-f52.google.com [209.85.167.52]) by imf19.hostedemail.com (Postfix) with ESMTP id 0FB3B1A000F for ; Tue, 17 Oct 2023 12:06:03 +0000 (UTC) Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=linaro.org header.s=google header.b=w3RQxVRl; dmarc=pass (policy=none) header.from=linaro.org; spf=pass (imf19.hostedemail.com: domain of ilias.apalodimas@linaro.org designates 209.85.167.52 as permitted sender) smtp.mailfrom=ilias.apalodimas@linaro.org ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1697544364; 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: in-reply-to:in-reply-to:references:references:dkim-signature; bh=F2LiefjmydOc/s+4bbm5g3/KwA64gaexFwMtR595sLY=; b=JA4BYmtLDvtccmtHbNbJFqEJFEaDTAgZhmUrX8/Hdvtl2Iu/KBhepCO3sO3nvrXashYQow 9xqb6pSMMGtr7MNQL57KfmGZYW7xYMXnWpZ0CIuLdNZX/69ykFR0g7Uw/tcr3EYahX/tYd EqAxNQPQ4b3cA+SUMxkchUeLL77QqHs= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=linaro.org header.s=google header.b=w3RQxVRl; dmarc=pass (policy=none) header.from=linaro.org; spf=pass (imf19.hostedemail.com: domain of ilias.apalodimas@linaro.org designates 209.85.167.52 as permitted sender) smtp.mailfrom=ilias.apalodimas@linaro.org ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1697544364; a=rsa-sha256; cv=none; b=cpgqytQ2OCfwQbadNvMgEuu/wIkEZjQvUPdi6tPkvT7x2dYDCqD9ovYk7BLNzkp4KX1cHH yzfRkHr9docfXL0Vc7InZBRkudqv7LsTGSkB5qE2utbKAccCjflSkpAL8Cv4MwCnxjZby2 33dh/k2ZoMFSpyeRvKWxKF0M3/+KE0k= Received: by mail-lf1-f52.google.com with SMTP id 2adb3069b0e04-507b18cf2e1so2413276e87.3 for ; Tue, 17 Oct 2023 05:06:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1697544362; x=1698149162; darn=kvack.org; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=F2LiefjmydOc/s+4bbm5g3/KwA64gaexFwMtR595sLY=; b=w3RQxVRloFPMJ7zkBWqowm4rYjTBGCzy3l2swXGdp/3qw6r6NWXrMichcINs2+FhLD kfuUEb1xUJtutLmCI4La6Tfa6Ajt5wwK9GGv5P+Q4NzfSLpmahC7SoJDj2TjKNBOLPSK 9347aBYtmWRGh5beZrk+q7/acbnB4LDl0d5DfISrxgfC4EPnNVfUvnDyI9VGT5FPKwzE uf+VRfh2Z5RFw2n/EOp17LeNirAtdMzy3JV5i/gFWn5Xy9INY/7Wgc2M/1NLymVhD2uA eMNf8R0/WIyogUbP19Kd7J+4zc/vaXUkIiINrlNIE/7JMXeaOaUIKJPKJjENjKTgbWwv 7/qQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1697544362; x=1698149162; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=F2LiefjmydOc/s+4bbm5g3/KwA64gaexFwMtR595sLY=; b=fSfu1XyZON/loj1jR1hyaX5Ro0nPsbfq6OarGKkJyolHvCIHsFbx2+0ANJxVZlZHYV AcwoMOMgRAZ3cIZ5tiLPEkpfbwWW5gDj0RUL6fYBdkSg8HGWzzwQf4/th0nQsWqcYuxc KMXvHMsv22Spy2q+ylIClxdzTkkpkZS3xnkSKQ6Ju0R6UX/IMxKwCK5ete2JpQ7t+CSp nLDEuAdNAYze7kDJRjbPQR9BXTp9B8mKI+2qRZ1xJe+3y+M441BTK2A3INCHx+G1AfGi UJUtAFuAXuBHzTm/EesiDq3RADob6+FtH0O8290QeryAoLV2abKJHwBuaNeUrXT6cKMY 0cUQ== X-Gm-Message-State: AOJu0YxYuf4Y4ed2C1Shrt3b4TsM6HLCHH/GczUzGgZH1Bt52hkBJBPK c8ggvw7/zHbInn7o6YtOFmSJTdN2GNTTXn21Bz06Vw== X-Google-Smtp-Source: AGHT+IFMqOpKXeVm5wQEu1wQc2ahJgY3GpGzx9xtnGWa1rdPL9mOWo1HMM86F15GHUu8XJ1zSKpFg0MTkMehSMher/k= X-Received: by 2002:a05:6512:48c3:b0:507:9aec:3014 with SMTP id er3-20020a05651248c300b005079aec3014mr1727172lfb.26.1697544361990; Tue, 17 Oct 2023 05:06:01 -0700 (PDT) MIME-Version: 1.0 References: <20231013064827.61135-1-linyunsheng@huawei.com> <20231013064827.61135-2-linyunsheng@huawei.com> In-Reply-To: <20231013064827.61135-2-linyunsheng@huawei.com> From: Ilias Apalodimas Date: Tue, 17 Oct 2023 15:05:25 +0300 Message-ID: Subject: Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA To: Yunsheng Lin Cc: davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Alexander Lobakin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Guillaume Tucker , Matthew Wilcox , Linux-MM , Jesper Dangaard Brouer , Eric Dumazet Content-Type: multipart/alternative; boundary="000000000000aff45a0607e8581c" X-Rspamd-Queue-Id: 0FB3B1A000F X-Rspam-User: X-Rspamd-Server: rspam05 X-Stat-Signature: d38q9xfofa4u61f9b6njgsz9mu5bhih9 X-HE-Tag: 1697544363-617626 X-HE-Meta: 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 9kMSOkOv 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 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: --000000000000aff45a0607e8581c Content-Type: text/plain; charset="UTF-8" Hi Yunsheng, Apologies for the late reply. On Fri, 13 Oct 2023 at 09:47, Yunsheng Lin wrote: > Currently page_pool_alloc_frag() is not supported in 32-bit > arch with 64-bit DMA because of the overlap issue between > pp_frag_count and dma_addr_upper in 'struct page' for those > arches, which seems to be quite common, see [1], which means > driver may need to handle it when using fragment API. > > It is assumed that the combination of the above arch with an > address space >16TB does not exist, as all those arches have > 64b equivalent, it seems logical to use the 64b version for a > system with a large address space. It is also assumed that dma > address is page aligned when we are dma mapping a page aligned > buffer, see [2]. > > That means we're storing 12 bits of 0 at the lower end for a > dma address, we can reuse those bits for the above arches to > support 32b+12b, which is 16TB of memory. > > If we make a wrong assumption, a warning is emitted so that > user can report to us. > > 1. > https://lore.kernel.org/all/20211117075652.58299-1-linyunsheng@huawei.com/ > 2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/ > > Tested-by: Alexander Lobakin > Signed-off-by: Jakub Kicinski > Signed-off-by: Yunsheng Lin > CC: Lorenzo Bianconi > CC: Alexander Duyck > CC: Liang Chen > CC: Alexander Lobakin > CC: Guillaume Tucker > CC: Matthew Wilcox > CC: Linux-MM > --- > include/linux/mm_types.h | 13 +------------ > include/net/page_pool/helpers.h | 20 ++++++++++++++------ > net/core/page_pool.c | 14 +++++++++----- > 3 files changed, 24 insertions(+), 23 deletions(-) > > diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h > index 36c5b43999e6..74b49c4c7a52 100644 > --- a/include/linux/mm_types.h > +++ b/include/linux/mm_types.h > @@ -125,18 +125,7 @@ struct page { > struct page_pool *pp; > unsigned long _pp_mapping_pad; > unsigned long dma_addr; > - union { > - /** > - * dma_addr_upper: might require a 64-bit > - * value on 32-bit architectures. > - */ > - unsigned long dma_addr_upper; > - /** > - * For frag page support, not supported in > - * 32-bit architectures with 64-bit DMA. > - */ > - atomic_long_t pp_frag_count; > - }; > + atomic_long_t pp_frag_count; > }; > struct { /* Tail pages of compound page */ > unsigned long compound_head; /* Bit zero is set > */ > diff --git a/include/net/page_pool/helpers.h > b/include/net/page_pool/helpers.h > index 8e7751464ff5..8f64adf86f5b 100644 > --- a/include/net/page_pool/helpers.h > +++ b/include/net/page_pool/helpers.h > @@ -197,7 +197,7 @@ static inline void page_pool_recycle_direct(struct > page_pool *pool, > page_pool_put_full_page(pool, page, true); > } > > -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ > +#define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA \ > (sizeof(dma_addr_t) > sizeof(unsigned long)) > > /** > @@ -211,17 +211,25 @@ static inline dma_addr_t > page_pool_get_dma_addr(struct page *page) > { > dma_addr_t ret = page->dma_addr; > > - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) > - ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; > + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) > + ret <<= PAGE_SHIFT; > > return ret; > } > > -static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t > addr) > +static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t > addr) > { > + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { > + page->dma_addr = addr >> PAGE_SHIFT; > + > + /* We assume page alignment to shave off bottom bits, > + * if this "compression" doesn't work we need to drop. > + */ > + return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; > + } > + > page->dma_addr = addr; > - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) > - page->dma_addr_upper = upper_32_bits(addr); > + return false; > } > > static inline bool page_pool_put(struct page_pool *pool) > diff --git a/net/core/page_pool.c b/net/core/page_pool.c > index 77cb75e63aca..8a9868ea5067 100644 > --- a/net/core/page_pool.c > +++ b/net/core/page_pool.c > @@ -211,10 +211,6 @@ static int page_pool_init(struct page_pool *pool, > */ > } > > - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && > - pool->p.flags & PP_FLAG_PAGE_FRAG) > - return -EINVAL; > - > #ifdef CONFIG_PAGE_POOL_STATS > pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); > if (!pool->recycle_stats) > @@ -359,12 +355,20 @@ static bool page_pool_dma_map(struct page_pool > *pool, struct page *page) > if (dma_mapping_error(pool->p.dev, dma)) > return false; > > - page_pool_set_dma_addr(page, dma); > + if (page_pool_set_dma_addr(page, dma)) > + goto unmap_failed; > > if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) > page_pool_dma_sync_for_device(pool, page, pool->p.max_len); > > return true; > + > +unmap_failed: > + WARN_ON_ONCE("unexpected DMA address, please report to netdev@"); > + dma_unmap_page_attrs(pool->p.dev, dma, > + PAGE_SIZE << pool->p.order, pool->p.dma_dir, > + DMA_ATTR_SKIP_CPU_SYNC | > DMA_ATTR_WEAK_ORDERING); > + return false; > } > > static void page_pool_set_pp_info(struct page_pool *pool, > -- > 2.33.0 > That looks fine wrt what we discussed with Jakub, Acked-by: Ilias Apalodimas --000000000000aff45a0607e8581c Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Yunsheng,

Apologies for the late reply.


On Fri, 13 Oct 2023 at 09:47, Yunsheng Lin <linyunsheng@huawei.com> wrote:
Currently page_pool_alloc_frag() is= not supported in 32-bit
arch with 64-bit DMA because of the overlap issue between
pp_frag_count and dma_addr_upper in 'struct page' for those
arches, which seems to be quite common, see [1], which means
driver may need to handle it when using fragment API.

It is assumed that the combination of the above arch with an
address space >16TB does not exist, as all those arches have
64b equivalent, it seems logical to use the 64b version for a
system with a large address space. It is also assumed that dma
address is page aligned when we are dma mapping a page aligned
buffer, see [2].

That means we're storing 12 bits of 0 at the lower end for a
dma address, we can reuse those bits for the above arches to
support 32b+12b, which is 16TB of memory.

If we make a wrong assumption, a warning is emitted so that
user can report to us.

1. https://lore.kernel.org= /all/20211117075652.58299-1-linyunsheng@huawei.com/
2. https://lore.kernel.org/all/202308= 18145145.4b357c89@kernel.org/

Tested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
CC: Lorenzo Bianconi <lorenzo@kernel.org>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Liang Chen <liangchen.linux@gmail.com>
CC: Alexander Lobakin <aleksander.lobakin@intel.com>
CC: Guillaume Tucker <guillaume.tucker@collabora.com>
CC: Matthew Wilcox <willy@infradead.org>
CC: Linux-MM <li= nux-mm@kvack.org>
---
=C2=A0include/linux/mm_types.h=C2=A0 =C2=A0 =C2=A0 =C2=A0 | 13 +-----------= -
=C2=A0include/net/page_pool/helpers.h | 20 ++++++++++++++------
=C2=A0net/core/page_pool.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 | 14 ++= +++++++-----
=C2=A03 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 36c5b43999e6..74b49c4c7a52 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -125,18 +125,7 @@ struct page {
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 struct page_pool *pp;
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 unsigned long _pp_mapping_pad;
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 unsigned long dma_addr;
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0union {
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0/**
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 * dma_addr_upper: might require a 64= -bit
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 * value on 32-bit architectures.
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 */
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0unsigned long dma_addr_upper;
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0/**
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 * For frag page support, not support= ed in
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 * 32-bit architectures with 64-bit D= MA.
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 */
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0atomic_long_t pp_frag_count;
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0};
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0atomic_long_t pp_frag_count;
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 };
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 struct {=C2=A0 =C2= =A0 =C2=A0 =C2=A0 /* Tail pages of compound page */
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 unsigned long compound_head;=C2=A0 =C2=A0 /* Bit zero is set */<= br> diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helper= s.h
index 8e7751464ff5..8f64adf86f5b 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -197,7 +197,7 @@ static inline void page_pool_recycle_direct(struct page= _pool *pool,
=C2=A0 =C2=A0 =C2=A0 =C2=A0 page_pool_put_full_page(pool, page, true);
=C2=A0}

-#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT=C2=A0 =C2=A0 =C2=A0 =C2=A0 \
+#define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA=C2=A0 =C2=A0 \
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 (sizeof(dma_addr_t)= > sizeof(unsigned long))

=C2=A0/**
@@ -211,17 +211,25 @@ static inline dma_addr_t page_pool_get_dma_addr(struc= t page *page)
=C2=A0{
=C2=A0 =C2=A0 =C2=A0 =C2=A0 dma_addr_t ret =3D page->dma_addr;

-=C2=A0 =C2=A0 =C2=A0 =C2=A0if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0ret |=3D (dma_addr_= t)page->dma_addr_upper << 16 << 16;
+=C2=A0 =C2=A0 =C2=A0 =C2=A0if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0ret <<=3D PAG= E_SHIFT;

=C2=A0 =C2=A0 =C2=A0 =C2=A0 return ret;
=C2=A0}

-static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t ad= dr)
+static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t ad= dr)
=C2=A0{
+=C2=A0 =C2=A0 =C2=A0 =C2=A0if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0page->dma_addr = =3D addr >> PAGE_SHIFT;
+
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0/* We assume page a= lignment to shave off bottom bits,
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 * if this "co= mpression" doesn't work we need to drop.
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 */
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0return addr !=3D (d= ma_addr_t)page->dma_addr << PAGE_SHIFT;
+=C2=A0 =C2=A0 =C2=A0 =C2=A0}
+
=C2=A0 =C2=A0 =C2=A0 =C2=A0 page->dma_addr =3D addr;
-=C2=A0 =C2=A0 =C2=A0 =C2=A0if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0page->dma_addr_u= pper =3D upper_32_bits(addr);
+=C2=A0 =C2=A0 =C2=A0 =C2=A0return false;
=C2=A0}

=C2=A0static inline bool page_pool_put(struct page_pool *pool)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 77cb75e63aca..8a9868ea5067 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -211,10 +211,6 @@ static int page_pool_init(struct page_pool *pool,
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0*/
=C2=A0 =C2=A0 =C2=A0 =C2=A0 }

-=C2=A0 =C2=A0 =C2=A0 =C2=A0if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&<= br> -=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0pool->p.flags & PP_FLAG_PA= GE_FRAG)
-=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0return -EINVAL;
-
=C2=A0#ifdef CONFIG_PAGE_POOL_STATS
=C2=A0 =C2=A0 =C2=A0 =C2=A0 pool->recycle_stats =3D alloc_percpu(struct = page_pool_recycle_stats);
=C2=A0 =C2=A0 =C2=A0 =C2=A0 if (!pool->recycle_stats)
@@ -359,12 +355,20 @@ static bool page_pool_dma_map(struct page_pool *pool,= struct page *page)
=C2=A0 =C2=A0 =C2=A0 =C2=A0 if (dma_mapping_error(pool->p.dev, dma))
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 return false;

-=C2=A0 =C2=A0 =C2=A0 =C2=A0page_pool_set_dma_addr(page, dma);
+=C2=A0 =C2=A0 =C2=A0 =C2=A0if (page_pool_set_dma_addr(page, dma))
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0goto unmap_failed;<= br>
=C2=A0 =C2=A0 =C2=A0 =C2=A0 if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV= )
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 page_pool_dma_sync_= for_device(pool, page, pool->p.max_len);

=C2=A0 =C2=A0 =C2=A0 =C2=A0 return true;
+
+unmap_failed:
+=C2=A0 =C2=A0 =C2=A0 =C2=A0WARN_ON_ONCE("unexpected DMA address, plea= se report to netdev@");
+=C2=A0 =C2=A0 =C2=A0 =C2=A0dma_unmap_page_attrs(pool->p.dev, dma,
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 PAGE_SIZE << pool->p.order, pool->p.dm= a_dir,
+=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);<= br> +=C2=A0 =C2=A0 =C2=A0 =C2=A0return false;
=C2=A0}

=C2=A0static void page_pool_set_pp_info(struct page_pool *pool,
--
2.33.0

That looks fine wrt what we discussed with J= akub,

Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
--000000000000aff45a0607e8581c--