From: Vivek Goyal Subject: [PATCH v5 1/8] pmem: Add functions for reading/writing page to/from pmem Date: Tue, 18 Feb 2020 16:48:34 -0500 Message-ID: <20200218214841.10076-2-vgoyal@redhat.com> References: <20200218214841.10076-1-vgoyal@redhat.com> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20200218214841.10076-1-vgoyal@redhat.com> Sender: linux-fsdevel-owner@vger.kernel.org To: linux-fsdevel@vger.kernel.org, linux-nvdimm@lists.01.org, hch@infradead.org, dan.j.williams@intel.com Cc: dm-devel@redhat.com, vishal.l.verma@intel.com, vgoyal@redhat.com, Christoph Hellwig List-Id: dm-devel.ids This splits pmem_do_bvec() into pmem_do_read() and pmem_do_write(). pmem_do_write() will be used by pmem zero_page_range() as well. Hence sharing the same code. Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Signed-off-by: Vivek Goyal --- drivers/nvdimm/pmem.c | 86 +++++++++++++++++++++++++------------------ 1 file changed, 50 insertions(+), 36 deletions(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 4eae441f86c9..075b11682192 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -136,9 +136,25 @@ static blk_status_t read_pmem(struct page *page, uns= igned int off, return BLK_STS_OK; } =20 -static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *= page, - unsigned int len, unsigned int off, unsigned int op, - sector_t sector) +static blk_status_t pmem_do_read(struct pmem_device *pmem, + struct page *page, unsigned int page_off, + sector_t sector, unsigned int len) +{ + blk_status_t rc; + phys_addr_t pmem_off =3D sector * 512 + pmem->data_offset; + void *pmem_addr =3D pmem->virt_addr + pmem_off; + + if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) + return BLK_STS_IOERR; + + rc =3D read_pmem(page, page_off, pmem_addr, len); + flush_dcache_page(page); + return rc; +} + +static blk_status_t pmem_do_write(struct pmem_device *pmem, + struct page *page, unsigned int page_off, + sector_t sector, unsigned int len) { blk_status_t rc =3D BLK_STS_OK; bool bad_pmem =3D false; @@ -148,34 +164,25 @@ static blk_status_t pmem_do_bvec(struct pmem_device= *pmem, struct page *page, if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) bad_pmem =3D true; =20 - if (!op_is_write(op)) { - if (unlikely(bad_pmem)) - rc =3D BLK_STS_IOERR; - else { - rc =3D read_pmem(page, off, pmem_addr, len); - flush_dcache_page(page); - } - } else { - /* - * Note that we write the data both before and after - * clearing poison. The write before clear poison - * handles situations where the latest written data is - * preserved and the clear poison operation simply marks - * the address range as valid without changing the data. - * In this case application software can assume that an - * interrupted write will either return the new good - * data or an error. - * - * However, if pmem_clear_poison() leaves the data in an - * indeterminate state we need to perform the write - * after clear poison. - */ - flush_dcache_page(page); - write_pmem(pmem_addr, page, off, len); - if (unlikely(bad_pmem)) { - rc =3D pmem_clear_poison(pmem, pmem_off, len); - write_pmem(pmem_addr, page, off, len); - } + /* + * Note that we write the data both before and after + * clearing poison. The write before clear poison + * handles situations where the latest written data is + * preserved and the clear poison operation simply marks + * the address range as valid without changing the data. + * In this case application software can assume that an + * interrupted write will either return the new good + * data or an error. + * + * However, if pmem_clear_poison() leaves the data in an + * indeterminate state we need to perform the write + * after clear poison. + */ + flush_dcache_page(page); + write_pmem(pmem_addr, page, page_off, len); + if (unlikely(bad_pmem)) { + rc =3D pmem_clear_poison(pmem, pmem_off, len); + write_pmem(pmem_addr, page, page_off, len); } =20 return rc; @@ -197,8 +204,12 @@ static blk_qc_t pmem_make_request(struct request_que= ue *q, struct bio *bio) =20 do_acct =3D nd_iostat_start(bio, &start); bio_for_each_segment(bvec, bio, iter) { - rc =3D pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, - bvec.bv_offset, bio_op(bio), iter.bi_sector); + if (op_is_write(bio_op(bio))) + rc =3D pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset, + iter.bi_sector, bvec.bv_len); + else + rc =3D pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset, + iter.bi_sector, bvec.bv_len); if (rc) { bio->bi_status =3D rc; break; @@ -223,9 +234,12 @@ static int pmem_rw_page(struct block_device *bdev, s= ector_t sector, struct pmem_device *pmem =3D bdev->bd_queue->queuedata; blk_status_t rc; =20 - rc =3D pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE, - 0, op, sector); - + if (op_is_write(op)) + rc =3D pmem_do_write(pmem, page, 0, sector, + hpage_nr_pages(page) * PAGE_SIZE); + else + rc =3D pmem_do_read(pmem, page, 0, sector, + hpage_nr_pages(page) * PAGE_SIZE); /* * The ->rw_page interface is subtle and tricky. The core * retries on any error, so we can only invoke page_endio() in --=20 2.20.1