From patchwork Mon Dec 24 22:32:23 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Saleem, Shiraz" X-Patchwork-Id: 10742481 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8C4676C5 for ; Mon, 24 Dec 2018 22:32:44 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 7D85D28A00 for ; Mon, 24 Dec 2018 22:32:44 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 7218728A3D; Mon, 24 Dec 2018 22:32:44 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 8EB7B28A00 for ; Mon, 24 Dec 2018 22:32:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1725822AbeLXWcm (ORCPT ); Mon, 24 Dec 2018 17:32:42 -0500 Received: from mga04.intel.com ([192.55.52.120]:63659 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725788AbeLXWcm (ORCPT ); Mon, 24 Dec 2018 17:32:42 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 24 Dec 2018 14:32:41 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,394,1539673200"; d="scan'208";a="286217048" Received: from ssaleem-mobl4.amr.corp.intel.com ([10.255.230.58]) by orsmga005.jf.intel.com with ESMTP; 24 Dec 2018 14:32:40 -0800 From: Shiraz Saleem To: dledford@redhat.com, jgg@ziepe.ca Cc: linux-rdma@vger.kernel.org, Shiraz Saleem Subject: [PATCH rdma-next 2/6] RDMA/umem: Add API to find best driver supported page size in an MR Date: Mon, 24 Dec 2018 16:32:23 -0600 Message-Id: <20181224223227.18016-3-shiraz.saleem@intel.com> X-Mailer: git-send-email 2.8.3 In-Reply-To: <20181224223227.18016-1-shiraz.saleem@intel.com> References: <20181224223227.18016-1-shiraz.saleem@intel.com> Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This helper iterates through the SG list to find the best page size to use from a bitmap of HW supported page sizes. Drivers that support multiple page sizes, but not mixed pages in an MR can use this API. Suggested-by: Jason Gunthorpe Reviewed-by: Michael J. Ruhl Signed-off-by: Shiraz Saleem --- drivers/infiniband/core/umem.c | 86 ++++++++++++++++++++++++++++++++++++++++++ include/rdma/ib_umem.h | 9 +++++ 2 files changed, 95 insertions(+) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 64bacc5..b2f2d75 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -119,6 +119,92 @@ static void ib_umem_add_sg_table(struct scatterlist **cur, } /** + * ib_umem_find_pg_bit - Find the page bit to use for phyaddr + * + * @phyaddr: Physical address after DMA translation + * @supported_pgsz: bitmask of HW supported page sizes + */ +static unsigned int ib_umem_find_pg_bit(unsigned long phyaddr, + unsigned long supported_pgsz) +{ + unsigned long num_zeroes; + unsigned long pgsz; + + /* Trailing zero bits in the address */ + num_zeroes = __ffs(phyaddr); + + /* Find page bit such that phyaddr is aligned to the highest supported + * HW page size + */ + pgsz = supported_pgsz & (BIT_ULL(num_zeroes + 1) - 1); + if (!pgsz) + return __ffs(supported_pgsz); + + return (fls64(pgsz) - 1); +} + +/** + * ib_umem_find_single_pg_size - Find best HW page size to use for this MR + * @umem: umem struct + * @supported_pgsz: bitmask of HW supported page sizes + * @uvirt_addr: user-space virtual MR base address + * + * This helper is intended for HW that support multiple page + * sizes but can do only a single page size in an MR. + */ +unsigned long ib_umem_find_single_pg_size(struct ib_umem *umem, + unsigned long supported_pgsz, + unsigned long uvirt_addr) +{ + struct scatterlist *sg; + unsigned int pg_bit_sg, min_pg_bit, best_pg_bit; + int i; + + if (!supported_pgsz) + return 0; + + min_pg_bit = __ffs(supported_pgsz); + best_pg_bit = fls64(supported_pgsz) - 1; + + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + unsigned long dma_addr_start, dma_addr_end; + + dma_addr_start = sg_dma_address(sg); + dma_addr_end = sg_dma_address(sg) + sg_dma_len(sg); + if (!i) { + pg_bit_sg = ib_umem_find_pg_bit(dma_addr_end, supported_pgsz); + + /* The start offset of the MR into a first _large_ page + * should line up exactly for the user-space virtual buf + * and physical buffer, in order to upgrade the page bit + */ + if (pg_bit_sg > PAGE_SHIFT) { + unsigned int uvirt_pg_bit; + + uvirt_pg_bit = ib_umem_find_pg_bit(uvirt_addr + sg_dma_len(sg), + supported_pgsz); + pg_bit_sg = min_t(unsigned int, uvirt_pg_bit, pg_bit_sg); + } + } else if (i == (umem->nmap - 1)) { + /* last SGE: Does not matter if MR ends at an + * unaligned offset. + */ + pg_bit_sg = ib_umem_find_pg_bit(dma_addr_start, supported_pgsz); + } else { + pg_bit_sg = ib_umem_find_pg_bit(dma_addr_start, + supported_pgsz & (BIT_ULL(__ffs(sg_dma_len(sg)) + 1) - 1)); + } + + best_pg_bit = min_t(unsigned int, best_pg_bit, pg_bit_sg); + if (best_pg_bit == min_pg_bit) + break; + } + + return BIT_ULL(best_pg_bit); +} +EXPORT_SYMBOL(ib_umem_find_single_pg_size); + +/** * ib_umem_get - Pin and DMA map userspace memory. * * If access flags indicate ODP memory, avoid pinning. Instead, stores diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 5d3755e..3e8e1ed 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -86,6 +86,9 @@ void ib_umem_release(struct ib_umem *umem); int ib_umem_page_count(struct ib_umem *umem); int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, size_t length); +unsigned long ib_umem_find_single_pg_size(struct ib_umem *umem, + unsigned long supported_pgsz, + unsigned long uvirt_addr); #else /* CONFIG_INFINIBAND_USER_MEM */ @@ -102,6 +105,12 @@ static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offs size_t length) { return -EINVAL; } +static inline int ib_umem_find_single_pg_size(struct ib_umem *umem, + unsigned long supported_pgsz, + unsigned long uvirt_addr) { + return -EINVAL; +} + #endif /* CONFIG_INFINIBAND_USER_MEM */ #endif /* IB_UMEM_H */