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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 48B7CC32771 for ; Wed, 28 Sep 2022 17:40:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:In-Reply-To:Content-Type: MIME-Version:References:Message-ID:Subject:Cc:To:From:Date:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=huGelRfYV4xfgZxXlge2ASn7B961mrjAW1M47mxW1tA=; b=WBztHJcuOWyg56AHab/OvupB/Z rwRfGsbwoWGxpuUryywE1DxP38GtFPiLLyaw3zFnl188bQtxrT6PQi/lypp05A/5M7KNqPsSokWRV mIDgEK1xwyIC/lhzihLYGNwoGb6aeMJOktxB0hk5QEUBHH5b0Bt9APPm8dGIr9Hk/UXhZYl78SHPp 99gxvuAlQlrtVnvWnafOk/Hm4MKNY/u57uNTK5Y5f4OJp5Iu6UYASiWar2s3gak6b1Kkukqyijo9r yrENmtOJYLk8npwaGzKNUbR5fkznwGhZh9cc1ffc8My9bpiBDkMsUIihtgh2ydzZjO7KtqXJrq6gx 6Kauf2+w==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1odb38-00HQDu-6y; Wed, 28 Sep 2022 17:40:46 +0000 Received: from verein.lst.de ([213.95.11.211]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1odb34-00HQDD-VX for linux-nvme@lists.infradead.org; Wed, 28 Sep 2022 17:40:44 +0000 Received: by verein.lst.de (Postfix, from userid 2407) id 8233B68BEB; Wed, 28 Sep 2022 19:40:39 +0200 (CEST) Date: Wed, 28 Sep 2022 19:40:39 +0200 From: Christoph Hellwig To: Kanchan Joshi Cc: axboe@kernel.dk, hch@lst.de, kbusch@kernel.org, io-uring@vger.kernel.org, linux-nvme@lists.infradead.org, linux-block@vger.kernel.org, gost.dev@samsung.com, Anuj Gupta Subject: Re: [PATCH for-next v10 6/7] block: extend functionality to map bvec iterator Message-ID: <20220928174039.GD17153@lst.de> References: <20220927173610.7794-1-joshi.k@samsung.com> <20220927173610.7794-7-joshi.k@samsung.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20220927173610.7794-7-joshi.k@samsung.com> User-Agent: Mutt/1.5.17 (2007-11-01) X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20220928_104043_327960_083AF00E X-CRM114-Status: GOOD ( 25.99 ) X-BeenThere: linux-nvme@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Linux-nvme" Errors-To: linux-nvme-bounces+linux-nvme=archiver.kernel.org@lists.infradead.org On Tue, Sep 27, 2022 at 11:06:09PM +0530, Kanchan Joshi wrote: > Extend blk_rq_map_user_iov so that it can handle bvec iterator. > It maps the pages from bvec iterator into a bio and place the bio into > request. > > This helper will be used by nvme for uring-passthrough path when IO is > done using pre-mapped buffers. Can we avoid duplicating some of the checks? Something like the below incremental patch. Note that this now also allows the copy path for all kinds of iov_iters, but as the copy from/to iter code is safe and the sanity check was just or the map path that should be fine. It's best split into a prep patch, though. --- diff --git a/block/blk-map.c b/block/blk-map.c index a1aa8dacb02bc..c51de30767403 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -549,26 +549,16 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio) EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ -static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter, - bool *copy) +static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { struct request_queue *q = rq->q; - size_t nr_iter, nr_segs, i; - struct bio *bio = NULL; - struct bio_vec *bv, *bvecs, *bvprvp = NULL; + size_t nr_iter = iov_iter_count(iter); + size_t nr_segs = iter->nr_segs; + struct bio_vec *bvecs, *bvprvp = NULL; struct queue_limits *lim = &q->limits; unsigned int nsegs = 0, bytes = 0; - unsigned long align = q->dma_pad_mask | queue_dma_alignment(q); - - /* see if we need to copy pages due to any weird situation */ - if (blk_queue_may_bounce(q)) - goto out_copy; - else if (iov_iter_alignment(iter) & align) - goto out_copy; - /* virt-alignment gap is checked anyway down, so avoid extra loop here */ - - nr_iter = iov_iter_count(iter); - nr_segs = iter->nr_segs; + struct bio *bio; + size_t i; if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q)) return -EINVAL; @@ -586,14 +576,15 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter, /* loop to perform a bunch of sanity checks */ bvecs = (struct bio_vec *)iter->bvec; for (i = 0; i < nr_segs; i++) { - bv = &bvecs[i]; + struct bio_vec *bv = &bvecs[i]; + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, fallback to copy. */ if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) { bio_map_put(bio); - goto out_copy; + return -EREMOTEIO; } /* check full condition */ if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len) @@ -611,9 +602,6 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter, put_bio: bio_map_put(bio); return -EINVAL; -out_copy: - *copy = true; - return 0; } /** @@ -635,33 +623,35 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - bool copy = false; + bool copy = false, map_bvec = false; unsigned long align = q->dma_pad_mask | queue_dma_alignment(q); struct bio *bio = NULL; struct iov_iter i; int ret = -EINVAL; - if (iov_iter_is_bvec(iter)) { - ret = blk_rq_map_user_bvec(rq, iter, ©); - if (ret != 0) - goto fail; - if (copy) - goto do_copy; - return ret; - } - if (!iter_is_iovec(iter)) - goto fail; - if (map_data) copy = true; else if (blk_queue_may_bounce(q)) copy = true; else if (iov_iter_alignment(iter) & align) copy = true; + else if (iov_iter_is_bvec(iter)) + map_bvec = true; + else if (!iter_is_iovec(iter)) + copy = true; else if (queue_virt_boundary(q)) copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter); -do_copy: + if (map_bvec) { + ret = blk_rq_map_user_bvec(rq, iter); + if (!ret) + return 0; + if (ret != -EREMOTEIO) + goto fail; + /* fall back to copying the data on limits mismatches */ + copy = true; + } + i = *iter; do { if (copy)