From patchwork Wed Aug 17 11:25:00 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Mark Brown X-Patchwork-Id: 9285619 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 35086600CB for ; Wed, 17 Aug 2016 11:25:35 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 28D9C28816 for ; Wed, 17 Aug 2016 11:25:35 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 1D6182882C; Wed, 17 Aug 2016 11:25:35 +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=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=unavailable 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 8870E28816 for ; Wed, 17 Aug 2016 11:25:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752364AbcHQLZK (ORCPT ); Wed, 17 Aug 2016 07:25:10 -0400 Received: from mezzanine.sirena.org.uk ([106.187.55.193]:49698 "EHLO mezzanine.sirena.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751688AbcHQLZK (ORCPT ); Wed, 17 Aug 2016 07:25:10 -0400 Received: from debutante.sirena.org.uk ([2a01:348:6:8808:fab::3] helo=debutante) by mezzanine.sirena.org.uk with esmtpsa (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.84_2) (envelope-from ) id 1bZyxz-0003Rj-B5; Wed, 17 Aug 2016 11:25:05 +0000 Received: from broonie by debutante with local (Exim 4.87) (envelope-from ) id 1bZyxw-00067T-DB; Wed, 17 Aug 2016 12:25:00 +0100 From: Mark Brown To: Vignesh R Cc: Mark Brown , Mark Brown , linux-spi@vger.kernel.org, linux-kernel@vger.kernel.org, linux-omap@vger.kernel.org In-Reply-To: <20160817095237.13101-3-vigneshr@ti.com> Message-Id: Date: Wed, 17 Aug 2016 12:25:00 +0100 X-SA-Exim-Connect-IP: 2a01:348:6:8808:fab::3 X-SA-Exim-Mail-From: broonie@sirena.org.uk Subject: Applied "spi: spi-ti-qspi: Add DMA support for QSPI mmap read" to the spi tree X-SA-Exim-Version: 4.2.1 (built Mon, 26 Dec 2011 16:24:06 +0000) X-SA-Exim-Scanned: No (on mezzanine.sirena.org.uk); Unknown failure Sender: linux-omap-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-omap@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The patch spi: spi-ti-qspi: Add DMA support for QSPI mmap read has been applied to the spi tree at git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark From 5720ec0a6d2605930934f3f154b048e8be3d8a40 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 17 Aug 2016 15:22:37 +0530 Subject: [PATCH] spi: spi-ti-qspi: Add DMA support for QSPI mmap read Use mem-to-mem DMA to read from flash when reading in mmap mode. This gives improved read performance and reduces CPU load. With this patch the raw-read throughput is ~16MB/s on DRA74 EVM. And CPU load is <20%. UBIFS read throughput ~13 MB/s. Signed-off-by: Vignesh R Signed-off-by: Mark Brown --- drivers/spi/spi-ti-qspi.c | 139 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 122 insertions(+), 17 deletions(-) diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index ac0b072815a3..caeac66a3977 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -41,6 +41,8 @@ struct ti_qspi_regs { }; struct ti_qspi { + struct completion transfer_complete; + /* list synchronization */ struct mutex list_lock; @@ -54,6 +56,9 @@ struct ti_qspi { struct ti_qspi_regs ctx_reg; + dma_addr_t mmap_phys_base; + struct dma_chan *rx_chan; + u32 spi_max_frequency; u32 cmd; u32 dc; @@ -379,6 +384,72 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t, return 0; } +static void ti_qspi_dma_callback(void *param) +{ + struct ti_qspi *qspi = param; + + complete(&qspi->transfer_complete); +} + +static int ti_qspi_dma_xfer(struct ti_qspi *qspi, dma_addr_t dma_dst, + dma_addr_t dma_src, size_t len) +{ + struct dma_chan *chan = qspi->rx_chan; + struct dma_device *dma_dev = chan->device; + dma_cookie_t cookie; + enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT; + struct dma_async_tx_descriptor *tx; + int ret; + + tx = dma_dev->device_prep_dma_memcpy(chan, dma_dst, dma_src, + len, flags); + if (!tx) { + dev_err(qspi->dev, "device_prep_dma_memcpy error\n"); + return -EIO; + } + + tx->callback = ti_qspi_dma_callback; + tx->callback_param = qspi; + cookie = tx->tx_submit(tx); + + ret = dma_submit_error(cookie); + if (ret) { + dev_err(qspi->dev, "dma_submit_error %d\n", cookie); + return -EIO; + } + + dma_async_issue_pending(chan); + ret = wait_for_completion_timeout(&qspi->transfer_complete, + msecs_to_jiffies(len)); + if (ret <= 0) { + dmaengine_terminate_sync(chan); + dev_err(qspi->dev, "DMA wait_for_completion_timeout\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int ti_qspi_dma_xfer_sg(struct ti_qspi *qspi, struct sg_table rx_sg, + loff_t from) +{ + struct scatterlist *sg; + dma_addr_t dma_src = qspi->mmap_phys_base + from; + dma_addr_t dma_dst; + int i, len, ret; + + for_each_sg(rx_sg.sgl, sg, rx_sg.nents, i) { + dma_dst = sg_dma_address(sg); + len = sg_dma_len(sg); + ret = ti_qspi_dma_xfer(qspi, dma_dst, dma_src, len); + if (ret) + return ret; + dma_src += len; + } + + return 0; +} + static void ti_qspi_enable_memory_map(struct spi_device *spi) { struct ti_qspi *qspi = spi_master_get_devdata(spi->master); @@ -426,7 +497,7 @@ static void ti_qspi_setup_mmap_read(struct spi_device *spi, QSPI_SPI_SETUP_REG(spi->chip_select)); } -static int ti_qspi_spi_flash_read(struct spi_device *spi, +static int ti_qspi_spi_flash_read(struct spi_device *spi, struct spi_flash_read_message *msg) { struct ti_qspi *qspi = spi_master_get_devdata(spi->master); @@ -437,9 +508,23 @@ static int ti_qspi_spi_flash_read(struct spi_device *spi, if (!qspi->mmap_enabled) ti_qspi_enable_memory_map(spi); ti_qspi_setup_mmap_read(spi, msg); - memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len); + + if (qspi->rx_chan) { + if (msg->cur_msg_mapped) { + ret = ti_qspi_dma_xfer_sg(qspi, msg->rx_sg, msg->from); + if (ret) + goto err_unlock; + } else { + dev_err(qspi->dev, "Invalid address for DMA\n"); + ret = -EIO; + goto err_unlock; + } + } else { + memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len); + } msg->retlen = msg->len; +err_unlock: mutex_unlock(&qspi->list_lock); return ret; @@ -536,6 +621,7 @@ static int ti_qspi_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; u32 max_freq; int ret = 0, num_cs, irq; + dma_cap_mask_t mask; master = spi_alloc_master(&pdev->dev, sizeof(*qspi)); if (!master) @@ -550,6 +636,7 @@ static int ti_qspi_probe(struct platform_device *pdev) master->dev.of_node = pdev->dev.of_node; master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8); + master->spi_flash_read = ti_qspi_spi_flash_read; if (!of_property_read_u32(np, "num-cs", &num_cs)) master->num_chipselect = num_cs; @@ -592,17 +679,6 @@ static int ti_qspi_probe(struct platform_device *pdev) goto free_master; } - if (res_mmap) { - qspi->mmap_base = devm_ioremap_resource(&pdev->dev, - res_mmap); - master->spi_flash_read = ti_qspi_spi_flash_read; - if (IS_ERR(qspi->mmap_base)) { - dev_err(&pdev->dev, - "falling back to PIO mode\n"); - master->spi_flash_read = NULL; - } - } - qspi->mmap_enabled = false; if (of_property_read_bool(np, "syscon-chipselects")) { qspi->ctrl_base = @@ -633,11 +709,37 @@ static int ti_qspi_probe(struct platform_device *pdev) if (!of_property_read_u32(np, "spi-max-frequency", &max_freq)) qspi->spi_max_frequency = max_freq; - ret = devm_spi_register_master(&pdev->dev, master); - if (ret) - goto free_master; + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); - return 0; + qspi->rx_chan = dma_request_chan_by_mask(&mask); + if (!qspi->rx_chan) { + dev_err(qspi->dev, + "No Rx DMA available, trying mmap mode\n"); + ret = 0; + goto no_dma; + } + master->dma_rx = qspi->rx_chan; + init_completion(&qspi->transfer_complete); + if (res_mmap) + qspi->mmap_phys_base = (dma_addr_t)res_mmap->start; + +no_dma: + if (!qspi->rx_chan && res_mmap) { + qspi->mmap_base = devm_ioremap_resource(&pdev->dev, res_mmap); + if (IS_ERR(qspi->mmap_base)) { + dev_info(&pdev->dev, + "mmap failed with error %ld using PIO mode\n", + PTR_ERR(qspi->mmap_base)); + qspi->mmap_base = NULL; + master->spi_flash_read = NULL; + } + } + qspi->mmap_enabled = false; + + ret = devm_spi_register_master(&pdev->dev, master); + if (!ret) + return 0; free_master: spi_master_put(master); @@ -656,6 +758,9 @@ static int ti_qspi_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); + if (qspi->rx_chan) + dma_release_channel(qspi->rx_chan); + return 0; }