From nobody Tue Nov 26 12:40:02 2024 Received: from out30-97.freemail.mail.aliyun.com (out30-97.freemail.mail.aliyun.com [115.124.30.97]) (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 D489415DBB3 for ; Fri, 18 Oct 2024 03:00:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.97 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729220447; cv=none; b=aPTM/y+RhXbNY0qp7LQz8x/yY5OlaQCRabyr4humOXIJAuEDvazom1GMNJT7HAeBcAmHVJjFP6Ij0C3BwBLrBLFqr/NmDUYbXf/CYLK0nS3At46ILoOEeGa8zl2kpWAV7A7MEksCqs3w/1Zu1dKA0JSXniebYGMAaNjWEGDWhOI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729220447; c=relaxed/simple; bh=fGpK3d66SdoBUTnXPeubhKKC12+CIKZi3TlVUcLOx08=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=toFLw1xx8C3oUGyR2laiqpkY1kDudrXxbd8BuBXMJLvjFIcqcuxOBfpwdAUC9GMXOEA8N96ZwZ1PRHpzoGR99E7FRBZp5BS31KM/os+ODXIhJUrWuOtOQXtvMpOM3XZE/N5EZv2VlrWalRtSZG4ZmSEwaovhj9OxsglYVmsy0fQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=Pa7+cn4T; arc=none smtp.client-ip=115.124.30.97 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="Pa7+cn4T" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1729220436; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=Ynn20XvNY9Nu0PNOg+bwufz+Xr8j8cPFzYmz1b4byuY=; b=Pa7+cn4THX4U9JjAB2qOQuuQ1czUmA+Ra61mHIap4D/2PFN3RXuhE9lFQqQopafmCflDLDqY/rYZlax9sNIgsPmP6juDi5mHXNVSs9F4Ui0ArRaKO/5tCuLHK4R3WRFo++q1O5TVA1yWJzAIGmgwPbRnSu8DO92dxhtekUs41ew= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WHMZWVd_1729220435 cluster:ay36) by smtp.aliyun-inc.com; Fri, 18 Oct 2024 11:00:36 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, shy828301@gmail.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH v2 1/2] mm: shmem: update iocb->ki_pos directly to simplify tmpfs read logic Date: Fri, 18 Oct 2024 11:00:27 +0800 Message-Id: X-Mailer: git-send-email 2.39.3 In-Reply-To: References: 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" Use iocb->ki_pos to check if the read bytes exceeds the file size and to calculate the bytes to be read can help simplify the code logic. Meanwhile, this is also a preparation for improving tmpfs large folios read performace in the following patch. Signed-off-by: Baolin Wang --- mm/shmem.c | 35 +++++++++++------------------------ 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 66eae800ffab..93642aa8d1aa 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3106,27 +3106,19 @@ static ssize_t shmem_file_read_iter(struct kiocb *i= ocb, struct iov_iter *to) unsigned long offset; int error =3D 0; ssize_t retval =3D 0; - loff_t *ppos =3D &iocb->ki_pos; =20 - index =3D *ppos >> PAGE_SHIFT; - offset =3D *ppos & ~PAGE_MASK; + offset =3D iocb->ki_pos & ~PAGE_MASK; =20 for (;;) { struct folio *folio =3D NULL; struct page *page =3D NULL; - pgoff_t end_index; unsigned long nr, ret; - loff_t i_size =3D i_size_read(inode); + loff_t end_offset, i_size =3D i_size_read(inode); =20 - end_index =3D i_size >> PAGE_SHIFT; - if (index > end_index) + if (unlikely(iocb->ki_pos >=3D i_size)) break; - if (index =3D=3D end_index) { - nr =3D i_size & ~PAGE_MASK; - if (nr <=3D offset) - break; - } =20 + index =3D iocb->ki_pos >> PAGE_SHIFT; error =3D shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error =3D=3D -EINVAL) @@ -3148,18 +3140,14 @@ static ssize_t shmem_file_read_iter(struct kiocb *i= ocb, struct iov_iter *to) * We must evaluate after, since reads (unlike writes) * are called without i_rwsem protection against truncate */ - nr =3D PAGE_SIZE; i_size =3D i_size_read(inode); - end_index =3D i_size >> PAGE_SHIFT; - if (index =3D=3D end_index) { - nr =3D i_size & ~PAGE_MASK; - if (nr <=3D offset) { - if (folio) - folio_put(folio); - break; - } + if (unlikely(iocb->ki_pos >=3D i_size)) { + if (folio) + folio_put(folio); + break; } - nr -=3D offset; + end_offset =3D min_t(loff_t, i_size, iocb->ki_pos + to->count); + nr =3D min_t(loff_t, end_offset - iocb->ki_pos, PAGE_SIZE - offset); =20 if (folio) { /* @@ -3199,8 +3187,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *ioc= b, struct iov_iter *to) =20 retval +=3D ret; offset +=3D ret; - index +=3D offset >> PAGE_SHIFT; offset &=3D ~PAGE_MASK; + iocb->ki_pos +=3D ret; =20 if (!iov_iter_count(to)) break; @@ -3211,7 +3199,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *ioc= b, struct iov_iter *to) cond_resched(); } =20 - *ppos =3D ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } --=20 2.39.3 From nobody Tue Nov 26 12:40:02 2024 Received: from out30-100.freemail.mail.aliyun.com (out30-100.freemail.mail.aliyun.com [115.124.30.100]) (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 D27A51607A4 for ; Fri, 18 Oct 2024 03:00:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.100 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729220448; cv=none; b=ibC96x6Z4Z9NtbqP/ArJ6vajbhtNXIIrEyiEGljtz70mDwGET4mDGidgFCFXmBu/woboPC3xsde5VhyUjAJjOJroTud4TwjpvjDVveseSNgPyoQ809KOh+6wdMzfq7IaXz+CiI9tankT6FUa3aNJqHXtJ10yLdQkfIew0mMeO2A= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729220448; c=relaxed/simple; bh=Y3c1W9Gibs9aUiNJwJ9qhHit2umjgziyg8++LNN6140=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=pRWhASv4lNwRPWCgWiCtnBShZWP7mG5dmHM8UzK9TnsteaPz5EtfCXXtSERvKXxMETyBYOK+uRdA5kR7QLabD3uwH/ffhJEz0mFSiqXOBH8w7RgrxpWDvNDFT4vQn6Cpv7S/8GL9GFharAX+jy0emhUeKMZy0hoSJUGnYQ6iuac= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=e3T2xx1h; arc=none smtp.client-ip=115.124.30.100 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="e3T2xx1h" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1729220437; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=ZL+DuJ+RP/aBC8VbvHjJ2i2qhBXaPyZwPwmHC2i5Ozk=; b=e3T2xx1hFmunyeuiIHLvsNZipxS3GpW7M+65XqNmcSNxcNmN4ib6zKrDOP/zVC/cM7vOctKe2N0eu/GHozWprOPyScw3necBXGl3rhbrqLe6FVndSymYpWJMprRyrs7jIE3K5WPPlDIgnB4I6QtnTKyFbT9KrPWboNIBdfdRG9M= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WHMdEgo_1729220436 cluster:ay36) by smtp.aliyun-inc.com; Fri, 18 Oct 2024 11:00:36 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, shy828301@gmail.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH v2 2/2] mm: shmem: improve the tmpfs large folio read performance Date: Fri, 18 Oct 2024 11:00:28 +0800 Message-Id: <2129a21a5b9f77d3bb7ddec152c009ce7c5653c4.1729218573.git.baolin.wang@linux.alibaba.com> X-Mailer: git-send-email 2.39.3 In-Reply-To: References: 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" The tmpfs has already supported the PMD-sized large folios, but the tmpfs read operation still performs copying at the PAGE SIZE granularity, which is unreasonable. This patch changes to copy data at the folio granularity, which can improve the read performance, as well as changing to use folio related functions. Moreoever, if a large folio has a subpage that is hwpoisoned, it will still fallback to page granularity copying. Use 'fio bs=3D64k' to read a 1G tmpfs file populated with 2M THPs, and I can see about 20% performance improvement, and no regression with bs=3D4k. Before the patch: READ: bw=3D10.0GiB/s After the patch: READ: bw=3D12.0GiB/s Signed-off-by: Baolin Wang --- mm/shmem.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 93642aa8d1aa..cbefd9801f6b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3107,13 +3107,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *i= ocb, struct iov_iter *to) int error =3D 0; ssize_t retval =3D 0; =20 - offset =3D iocb->ki_pos & ~PAGE_MASK; - for (;;) { struct folio *folio =3D NULL; struct page *page =3D NULL; unsigned long nr, ret; loff_t end_offset, i_size =3D i_size_read(inode); + bool fallback_page_copy =3D false; + size_t fsize; =20 if (unlikely(iocb->ki_pos >=3D i_size)) break; @@ -3134,6 +3134,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *io= cb, struct iov_iter *to) error =3D -EIO; break; } + + if (folio_test_large(folio) && + folio_test_has_hwpoisoned(folio)) + fallback_page_copy =3D true; } =20 /* @@ -3147,7 +3151,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *io= cb, struct iov_iter *to) break; } end_offset =3D min_t(loff_t, i_size, iocb->ki_pos + to->count); - nr =3D min_t(loff_t, end_offset - iocb->ki_pos, PAGE_SIZE - offset); + if (folio && likely(!fallback_page_copy)) + fsize =3D folio_size(folio); + else + fsize =3D PAGE_SIZE; + offset =3D iocb->ki_pos & (fsize - 1); + nr =3D min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); =20 if (folio) { /* @@ -3155,10 +3164,15 @@ static ssize_t shmem_file_read_iter(struct kiocb *i= ocb, struct iov_iter *to) * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ - if (mapping_writably_mapped(mapping)) - flush_dcache_page(page); + if (mapping_writably_mapped(mapping)) { + if (likely(!fallback_page_copy)) + flush_dcache_folio(folio); + else + flush_dcache_page(page); + } + /* - * Mark the page accessed if we read the beginning. + * Mark the folio accessed if we read the beginning. */ if (!offset) folio_mark_accessed(folio); @@ -3166,9 +3180,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *io= cb, struct iov_iter *to) * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ - ret =3D copy_page_to_iter(page, offset, nr, to); + if (likely(!fallback_page_copy)) + ret =3D copy_folio_to_iter(folio, offset, nr, to); + else + ret =3D copy_page_to_iter(page, offset, nr, to); folio_put(folio); - } else if (user_backed_iter(to)) { /* * Copy to user tends to be so well optimized, but @@ -3186,8 +3202,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *ioc= b, struct iov_iter *to) } =20 retval +=3D ret; - offset +=3D ret; - offset &=3D ~PAGE_MASK; iocb->ki_pos +=3D ret; =20 if (!iov_iter_count(to)) --=20 2.39.3