From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: [PATCH 11/18] block: implement bio helper to add iter bvec pages to bio Date: Wed, 30 Jan 2019 14:55:33 -0700 Message-ID: <20190130215540.20871-12-axboe@kernel.dk> References: <20190130215540.20871-1-axboe@kernel.dk> Return-path: In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk> Sender: owner-linux-aio@kvack.org To: linux-aio@kvack.org, linux-block@vger.kernel.org, linux-api@vger.kernel.org Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com, jannh@google.com, Jens Axboe List-Id: linux-api@vger.kernel.org For an ITER_BVEC, we can just iterate the iov and add the pages to the bio directly. This requires that the caller doesn't releases the pages on IO completion, we add a BIO_NO_PAGE_REF flag for that. The current two callers of bio_iov_iter_get_pages() are updated to check if they need to release pages on completion. This makes them work with bvecs that contain kernel mapped pages already. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 59 ++++++++++++++++++++++++++++++++------- fs/block_dev.c | 5 ++-- fs/iomap.c | 5 ++-- include/linux/blk_types.h | 1 + 4 files changed, 56 insertions(+), 14 deletions(-) diff --git a/block/bio.c b/block/bio.c index 4db1008309ed..330df572cfb8 100644 --- a/block/bio.c +++ b/block/bio.c @@ -828,6 +828,23 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) +{ + const struct bio_vec *bv = iter->bvec; + unsigned int len; + size_t size; + + len = min_t(size_t, bv->bv_len, iter->count); + size = bio_add_page(bio, bv->bv_page, len, + bv->bv_offset + iter->iov_offset); + if (size == len) { + iov_iter_advance(iter, size); + return 0; + } + + return -EINVAL; +} + #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** @@ -876,23 +893,43 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) } /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to - * @iter: iov iterator describing the region to be mapped + * @iter: iov iterator describing the region to be added + * + * This takes either an iterator pointing to user memory, or one pointing to + * kernel pages (BVEC iterator). If we're adding user pages, we pin them and + * map them into the kernel. On IO completion, the caller should put those + * pages. If we're adding kernel pages, we just have to add the pages to the + * bio directly. We don't grab an extra reference to those pages (the user + * should already have that), and we don't put the page on IO completion. + * The caller needs to check if the bio is flagged BIO_NO_PAGE_REF on IO + * completion. If it isn't, then pages should be released. * - * Pins pages from *iter and appends them to @bio's bvec array. The - * pages will have to be released using put_page() when done. * The function tries, but does not guarantee, to pin as many pages as - * fit into the bio, or are requested in *iter, whatever is smaller. - * If MM encounters an error pinning the requested pages, it stops. - * Error is returned only if 0 pages could be pinned. + * fit into the bio, or are requested in *iter, whatever is smaller. If + * MM encounters an error pinning the requested pages, it stops. Error + * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { + const bool is_bvec = iov_iter_is_bvec(iter); unsigned short orig_vcnt = bio->bi_vcnt; + /* + * If this is a BVEC iter, then the pages are kernel pages. Don't + * release them on IO completion. + */ + if (is_bvec) + bio_set_flag(bio, BIO_NO_PAGE_REF); + do { - int ret = __bio_iov_iter_get_pages(bio, iter); + int ret; + + if (is_bvec) + ret = __bio_iov_bvec_add_pages(bio, iter); + else + ret = __bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) return bio->bi_vcnt > orig_vcnt ? 0 : ret; @@ -1634,7 +1671,8 @@ static void bio_dirty_fn(struct work_struct *work) next = bio->bi_private; bio_set_pages_dirty(bio); - bio_release_pages(bio); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_release_pages(bio); bio_put(bio); } } @@ -1650,7 +1688,8 @@ void bio_check_pages_dirty(struct bio *bio) goto defer; } - bio_release_pages(bio); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_release_pages(bio); bio_put(bio); return; defer: diff --git a/fs/block_dev.c b/fs/block_dev.c index 392e2bfb636f..051ab41d1c61 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -338,8 +338,9 @@ static void blkdev_bio_end_io(struct bio *bio) struct bio_vec *bvec; int i; - bio_for_each_segment_all(bvec, bio, i) - put_page(bvec->bv_page); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_for_each_segment_all(bvec, bio, i) + put_page(bvec->bv_page); bio_put(bio); } } diff --git a/fs/iomap.c b/fs/iomap.c index 4ee50b76b4a1..e5c48a0b20e0 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1582,8 +1582,9 @@ static void iomap_dio_bio_end_io(struct bio *bio) struct bio_vec *bvec; int i; - bio_for_each_segment_all(bvec, bio, i) - put_page(bvec->bv_page); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_for_each_segment_all(bvec, bio, i) + put_page(bvec->bv_page); bio_put(bio); } } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d66bf5f32610..791fee35df88 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -215,6 +215,7 @@ struct bio { /* * bio flags */ +#define BIO_NO_PAGE_REF 0 /* don't put release vec pages */ #define BIO_SEG_VALID 1 /* bi_phys_segments valid */ #define BIO_CLONED 2 /* doesn't own data */ #define BIO_BOUNCED 3 /* bio is a bounce bio */ -- 2.17.1 -- To unsubscribe, send a message with 'unsubscribe linux-aio' in the body to majordomo@kvack.org. For more info on Linux AIO, see: http://www.kvack.org/aio/ Don't email: aart@kvack.org 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=-9.0 required=3.0 tests=DKIMWL_WL_MED,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT 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 26060C282D7 for ; Wed, 30 Jan 2019 23:26:03 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C0FC720882 for ; Wed, 30 Jan 2019 23:26:02 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20150623.gappssmtp.com header.i=@kernel-dk.20150623.gappssmtp.com header.b="RS1ICGx9" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726967AbfA3X0C (ORCPT ); Wed, 30 Jan 2019 18:26:02 -0500 Received: from mail-io1-f65.google.com ([209.85.166.65]:41863 "EHLO mail-io1-f65.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725768AbfA3X0C (ORCPT ); Wed, 30 Jan 2019 18:26:02 -0500 Received: by mail-io1-f65.google.com with SMTP id s22so1061158ioc.8 for ; Wed, 30 Jan 2019 15:26:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=BK66d+c011HKx58tvLlznS+PEC6KSjdwHKShIT6KD+A=; b=RS1ICGx9eCd+DVjixkhcbXZI22u6/fF01cB9L7GaiFtH8FT4g8XRzYeU96GUwP25xV H8Hn++L0YQ//tDaSaCryo+g4iryG+iOQ4ne6RrC5yo1Q7k/7qx/5vW9BTGfdcXlw+KMw 4sc6wH2xzQPQVE+Vs7a+zIFKC+vrZWDJdQ7epbA3jdb/Dxqr3h7yNBd8Ubgk5BQdw0KX GJRysyfVU+C8tWCv4SSFfCMbYff8n9KkRkUrs32g4DmN51CL4CeTvKBz4oqjiG4E5YdX rrWfdLNykcpk7mBWy3iMpt0jWpYaRTt9nxFNRC94YeJiimWRGrO6XT/cGuwsrCfPR4V0 HTow== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=BK66d+c011HKx58tvLlznS+PEC6KSjdwHKShIT6KD+A=; b=dhGSz7F+O1qd5yXUvjDDucZfEqoPlWiO8cUHkdja+Pk9tTPBpzTpg5rQ3SN+FRVYl8 +6dfleadPO4TJksp8+rPypSwkbN5BGu6GpcHHoiskRLSzTbRrj+v1+rwAef/R7ZS8zoH pjphMA2MppyGMnEw1mnMJpFBYHAeLpG8rHWiT/UCaXJBS9Ffz148sWxRAlkEClMpIvDU 5pBSV3FXgV1Zw2QgR9YB+7EfFwUt7esfP0k3nbgZf/ZBLRSYhloaRB9nYLPCXQV0ryAJ 3EAk2YjrBEr/K+eHobynMogQDcE2eagwTePnsY4oNoWeFB4CwldZOr4ehGf+H9gBCMrU VK/A== X-Gm-Message-State: AHQUAubW//pysx/G+6k26VTpq5C9MxNaf3q9iMZVwFvDlJuHEmU7QDKG X8HyPUGmir04Ftdt055nUf/LYXZaf1M= X-Google-Smtp-Source: ALg8bN7hufXf4vXAcwJdfG/hHVJfxGju0rHqadMcKEIMBQ3YA4mFfQZFqFsAp/YnR0xCkvTCurDxxQ== X-Received: by 2002:a6b:92d7:: with SMTP id u206mr19879481iod.174.1548885364102; Wed, 30 Jan 2019 13:56:04 -0800 (PST) Received: from localhost.localdomain ([216.160.245.98]) by smtp.gmail.com with ESMTPSA id 189sm1805081itw.33.2019.01.30.13.56.02 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 30 Jan 2019 13:56:03 -0800 (PST) From: Jens Axboe To: linux-aio@kvack.org, linux-block@vger.kernel.org, linux-api@vger.kernel.org Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com, jannh@google.com, Jens Axboe Subject: [PATCH 11/18] block: implement bio helper to add iter bvec pages to bio Date: Wed, 30 Jan 2019 14:55:33 -0700 Message-Id: <20190130215540.20871-12-axboe@kernel.dk> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk> References: <20190130215540.20871-1-axboe@kernel.dk> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org For an ITER_BVEC, we can just iterate the iov and add the pages to the bio directly. This requires that the caller doesn't releases the pages on IO completion, we add a BIO_NO_PAGE_REF flag for that. The current two callers of bio_iov_iter_get_pages() are updated to check if they need to release pages on completion. This makes them work with bvecs that contain kernel mapped pages already. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 59 ++++++++++++++++++++++++++++++++------- fs/block_dev.c | 5 ++-- fs/iomap.c | 5 ++-- include/linux/blk_types.h | 1 + 4 files changed, 56 insertions(+), 14 deletions(-) diff --git a/block/bio.c b/block/bio.c index 4db1008309ed..330df572cfb8 100644 --- a/block/bio.c +++ b/block/bio.c @@ -828,6 +828,23 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) +{ + const struct bio_vec *bv = iter->bvec; + unsigned int len; + size_t size; + + len = min_t(size_t, bv->bv_len, iter->count); + size = bio_add_page(bio, bv->bv_page, len, + bv->bv_offset + iter->iov_offset); + if (size == len) { + iov_iter_advance(iter, size); + return 0; + } + + return -EINVAL; +} + #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** @@ -876,23 +893,43 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) } /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to - * @iter: iov iterator describing the region to be mapped + * @iter: iov iterator describing the region to be added + * + * This takes either an iterator pointing to user memory, or one pointing to + * kernel pages (BVEC iterator). If we're adding user pages, we pin them and + * map them into the kernel. On IO completion, the caller should put those + * pages. If we're adding kernel pages, we just have to add the pages to the + * bio directly. We don't grab an extra reference to those pages (the user + * should already have that), and we don't put the page on IO completion. + * The caller needs to check if the bio is flagged BIO_NO_PAGE_REF on IO + * completion. If it isn't, then pages should be released. * - * Pins pages from *iter and appends them to @bio's bvec array. The - * pages will have to be released using put_page() when done. * The function tries, but does not guarantee, to pin as many pages as - * fit into the bio, or are requested in *iter, whatever is smaller. - * If MM encounters an error pinning the requested pages, it stops. - * Error is returned only if 0 pages could be pinned. + * fit into the bio, or are requested in *iter, whatever is smaller. If + * MM encounters an error pinning the requested pages, it stops. Error + * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { + const bool is_bvec = iov_iter_is_bvec(iter); unsigned short orig_vcnt = bio->bi_vcnt; + /* + * If this is a BVEC iter, then the pages are kernel pages. Don't + * release them on IO completion. + */ + if (is_bvec) + bio_set_flag(bio, BIO_NO_PAGE_REF); + do { - int ret = __bio_iov_iter_get_pages(bio, iter); + int ret; + + if (is_bvec) + ret = __bio_iov_bvec_add_pages(bio, iter); + else + ret = __bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) return bio->bi_vcnt > orig_vcnt ? 0 : ret; @@ -1634,7 +1671,8 @@ static void bio_dirty_fn(struct work_struct *work) next = bio->bi_private; bio_set_pages_dirty(bio); - bio_release_pages(bio); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_release_pages(bio); bio_put(bio); } } @@ -1650,7 +1688,8 @@ void bio_check_pages_dirty(struct bio *bio) goto defer; } - bio_release_pages(bio); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_release_pages(bio); bio_put(bio); return; defer: diff --git a/fs/block_dev.c b/fs/block_dev.c index 392e2bfb636f..051ab41d1c61 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -338,8 +338,9 @@ static void blkdev_bio_end_io(struct bio *bio) struct bio_vec *bvec; int i; - bio_for_each_segment_all(bvec, bio, i) - put_page(bvec->bv_page); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_for_each_segment_all(bvec, bio, i) + put_page(bvec->bv_page); bio_put(bio); } } diff --git a/fs/iomap.c b/fs/iomap.c index 4ee50b76b4a1..e5c48a0b20e0 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1582,8 +1582,9 @@ static void iomap_dio_bio_end_io(struct bio *bio) struct bio_vec *bvec; int i; - bio_for_each_segment_all(bvec, bio, i) - put_page(bvec->bv_page); + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + bio_for_each_segment_all(bvec, bio, i) + put_page(bvec->bv_page); bio_put(bio); } } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d66bf5f32610..791fee35df88 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -215,6 +215,7 @@ struct bio { /* * bio flags */ +#define BIO_NO_PAGE_REF 0 /* don't put release vec pages */ #define BIO_SEG_VALID 1 /* bi_phys_segments valid */ #define BIO_CLONED 2 /* doesn't own data */ #define BIO_BOUNCED 3 /* bio is a bounce bio */ -- 2.17.1