From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934491AbbCPU2x (ORCPT ); Mon, 16 Mar 2015 16:28:53 -0400 Received: from mga03.intel.com ([134.134.136.65]:6197 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934210AbbCPU2q (ORCPT ); Mon, 16 Mar 2015 16:28:46 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,411,1422950400"; d="scan'208";a="692973833" Subject: [RFC PATCH 7/7] block: base support for pfn i/o From: Dan Williams To: linux-kernel@vger.kernel.org Cc: axboe@kernel.dk, hch@infradead.org, riel@redhat.com, linux-nvdimm@ml01.01.org, linux-raid@vger.kernel.org, mgorman@suse.de, linux-fsdevel@vger.kernel.org Date: Mon, 16 Mar 2015 16:26:04 -0400 Message-ID: <20150316202604.33102.12999.stgit@dwillia2-desk3.amr.corp.intel.com> In-Reply-To: <20150316201640.33102.33761.stgit@dwillia2-desk3.amr.corp.intel.com> References: <20150316201640.33102.33761.stgit@dwillia2-desk3.amr.corp.intel.com> User-Agent: StGit/0.17.1-8-g92dd MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Allow block device drivers to opt-in to receiving bio(s) where the bio_vec(s) point to memory that is not backed by struct page entries. When a driver opts in it asserts that it will use the pfn version of the dma mapping routines and does not use pfn_to_page() in its submission path. TODO: add kmap_pfn() and kmap_atomic_pfn() for drivers that want to touch bio_vec buffers with the cpu prior to submission to a low-level-device-driver. Signed-off-by: Dan Williams --- block/bio.c | 48 ++++++++++++++++++++++++++++++++++++++------- block/blk-core.c | 5 +++++ include/linux/blk_types.h | 1 + include/linux/blkdev.h | 2 ++ 4 files changed, 48 insertions(+), 8 deletions(-) diff --git a/block/bio.c b/block/bio.c index 3d494e85e16d..091c0071e360 100644 --- a/block/bio.c +++ b/block/bio.c @@ -568,6 +568,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_rw = bio_src->bi_rw; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; + bio->bi_flags |= bio_src->bi_flags & (1 << BIO_PFN); } EXPORT_SYMBOL(__bio_clone_fast); @@ -659,6 +660,8 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, goto integrity_clone; } + bio->bi_flags |= bio_src->bi_flags & (1 << BIO_PFN); + bio_for_each_segment(bv, bio_src, iter) bio->bi_io_vec[bio->bi_vcnt++] = bv; @@ -700,9 +703,9 @@ int bio_get_nr_vecs(struct block_device *bdev) } EXPORT_SYMBOL(bio_get_nr_vecs); -static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page - *page, unsigned int len, unsigned int offset, - unsigned int max_sectors) +static int __bio_add_pfn(struct request_queue *q, struct bio *bio, + __pfn_t pfn, unsigned int len, unsigned int offset, + unsigned int max_sectors) { int retried_segments = 0; struct bio_vec *bvec; @@ -724,7 +727,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page if (bio->bi_vcnt > 0) { struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (page == bvec_page(prev) && + if (pfn.pfn == prev->bv_pfn.pfn && offset == prev->bv_offset + prev->bv_len) { unsigned int prev_bv_len = prev->bv_len; prev->bv_len += len; @@ -769,7 +772,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page * cannot add the page */ bvec = &bio->bi_io_vec[bio->bi_vcnt]; - bvec_set_page(bvec, page); + bvec->bv_pfn = pfn; bvec->bv_len = len; bvec->bv_offset = offset; bio->bi_vcnt++; @@ -819,7 +822,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page return len; failed: - bvec_set_page(bvec, NULL); + bvec->bv_pfn.pfn = 0; bvec->bv_len = 0; bvec->bv_offset = 0; bio->bi_vcnt--; @@ -846,7 +849,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { - return __bio_add_page(q, bio, page, len, offset, + return __bio_add_pfn(q, bio, page_to_pfn_typed(page), len, offset, queue_max_hw_sectors(q)); } EXPORT_SYMBOL(bio_add_pc_page); @@ -873,10 +876,39 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len, if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size) max_sectors = len >> 9; - return __bio_add_page(q, bio, page, len, offset, max_sectors); + return __bio_add_pfn(q, bio, page_to_pfn_typed(page), len, offset, + max_sectors); } EXPORT_SYMBOL(bio_add_page); +/** + * bio_add_pfn - attempt to add pfn to bio + * @bio: destination bio + * @pfn: pfn to add + * @len: vec entry length + * @offset: vec entry offset + * + * Identical to bio_add_page() except this variant flags the bio as + * not have struct page backing. A given request_queue must assert + * that it is prepared to handle this constraint before bio(s) + * flagged in the manner can be passed. + */ +int bio_add_pfn(struct bio *bio, __pfn_t pfn, unsigned int len, + unsigned int offset) +{ + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + unsigned int max_sectors; + + if (!blk_queue_pfn(q)) + return 0; + set_bit(BIO_PFN, &bio->bi_flags); + max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size) + max_sectors = len >> 9; + + return __bio_add_pfn(q, bio, pfn, len, offset, max_sectors); +} + struct submit_bio_ret { struct completion event; int error; diff --git a/block/blk-core.c b/block/blk-core.c index 7830ce00cbf5..8bafb4c87c96 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1843,6 +1843,11 @@ generic_make_request_checks(struct bio *bio) goto end_io; } + if (bio_flagged(bio, BIO_PFN) && !blk_queue_pfn(q)) { + err = -EOPNOTSUPP; + goto end_io; + } + /* * Various block parts want %current->io_context and lazy ioc * allocation ends up trading a lot of pain for a small amount of diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 7f63fa3e4fda..653bb4fd0706 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -140,6 +140,7 @@ struct bio { #define BIO_NULL_MAPPED 8 /* contains invalid user pages */ #define BIO_QUIET 9 /* Make BIO Quiet */ #define BIO_SNAP_STABLE 10 /* bio data must be snapshotted during write */ +#define BIO_PFN 11 /* bio_vec references memory without struct page */ /* * Flags starting here get preserved by bio_reset() - this includes diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7f9a516f24de..e17ecefba80a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -513,6 +513,7 @@ struct request_queue { #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ #define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ #define QUEUE_FLAG_SG_GAPS 22 /* queue doesn't support SG gaps */ +#define QUEUE_FLAG_PFN 23 /* queue supports pfn-only bio_vec(s) */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -594,6 +595,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_pfn(q) test_bit(QUEUE_FLAG_PFN, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_stackable(q) \