From patchwork Thu Dec 27 13:10:58 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Shun-Chih.Yu" X-Patchwork-Id: 10743665 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 AE58B13B5 for ; Thu, 27 Dec 2018 13:11:29 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 923A328399 for ; Thu, 27 Dec 2018 13:11:29 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 81F412883B; Thu, 27 Dec 2018 13:11:29 +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,UNPARSEABLE_RELAY 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 BD13C28399 for ; Thu, 27 Dec 2018 13:11:27 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730608AbeL0NL1 (ORCPT ); Thu, 27 Dec 2018 08:11:27 -0500 Received: from mailgw02.mediatek.com ([210.61.82.184]:63191 "EHLO mailgw02.mediatek.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1726761AbeL0NL1 (ORCPT ); Thu, 27 Dec 2018 08:11:27 -0500 X-UUID: f42e99caf0054483a9833d983027da9b-20181227 X-UUID: f42e99caf0054483a9833d983027da9b-20181227 Received: from mtkcas08.mediatek.inc [(172.21.101.126)] by mailgw02.mediatek.com (envelope-from ) (mhqrelay.mediatek.com ESMTP with TLS) with ESMTP id 1186146640; Thu, 27 Dec 2018 21:11:14 +0800 Received: from mtkcas07.mediatek.inc (172.21.101.84) by mtkmbs02n2.mediatek.inc (172.21.101.101) with Microsoft SMTP Server (TLS) id 15.0.1395.4; Thu, 27 Dec 2018 21:11:11 +0800 Received: from mtkswgap22.mediatek.inc (172.21.77.33) by mtkcas07.mediatek.inc (172.21.101.73) with Microsoft SMTP Server id 15.0.1395.4 via Frontend Transport; Thu, 27 Dec 2018 21:11:11 +0800 From: To: Sean Wang , Vinod Koul , Rob Herring , Matthias Brugger , Dan Williams CC: , , , , , , Shun-Chih Yu Subject: [PATCH 2/2] dmaengine: mediatek: Add MediaTek Command-Queue DMA controller for MT6765 SoC Date: Thu, 27 Dec 2018 21:10:58 +0800 Message-ID: <1545916258-18218-3-git-send-email-shun-chih.yu@mediatek.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1545916258-18218-1-git-send-email-shun-chih.yu@mediatek.com> References: <1545916258-18218-1-git-send-email-shun-chih.yu@mediatek.com> MIME-Version: 1.0 X-TM-SNTS-SMTP: 94B4895B616C9E693442831859A19FFA1C5778DA4A6FB69EA721D33A6A365A722000:8 X-MTK: N Sender: dmaengine-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: dmaengine@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Shun-Chih Yu MediaTek Command-Queue DMA controller (CQDMA) on MT6765 SoC is dedicated to memory-to-memory transfer through queue based descriptor management. There are only 3 physical channels inside CQDMA, while the driver is extended to support 32 virtual channels for multiple dma users to issue dma requests onto the CQDMA simultaneously. Change-Id: I1e8d116c5ecbbc49190ffc925cb59a0d035d886b Signed-off-by: Shun-Chih Yu Reviewed-by: Vinod Koul Reviewed-by: ..., same goes for Acked-by and Tested-by: ... etc --- drivers/dma/mediatek/Kconfig | 12 + drivers/dma/mediatek/Makefile | 1 + drivers/dma/mediatek/mtk-cqdma.c | 867 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 880 insertions(+) create mode 100644 drivers/dma/mediatek/mtk-cqdma.c diff --git a/drivers/dma/mediatek/Kconfig b/drivers/dma/mediatek/Kconfig index 27bac0b..4a1582d 100644 --- a/drivers/dma/mediatek/Kconfig +++ b/drivers/dma/mediatek/Kconfig @@ -11,3 +11,15 @@ config MTK_HSDMA This controller provides the channels which is dedicated to memory-to-memory transfer to offload from CPU through ring- based descriptor management. + +config MTK_CQDMA + tristate "MediaTek Command-Queue DMA controller support" + depends on ARCH_MEDIATEK || COMPILE_TEST + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Enable support for Command-Queue DMA controller on MediaTek + SoCs. + + This controller provides the channels which is dedicated to + memory-to-memory transfer to offload from CPU. diff --git a/drivers/dma/mediatek/Makefile b/drivers/dma/mediatek/Makefile index 6e778f8..41bb381 100644 --- a/drivers/dma/mediatek/Makefile +++ b/drivers/dma/mediatek/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_MTK_HSDMA) += mtk-hsdma.o +obj-$(CONFIG_MTK_CQDMA) += mtk-cqdma.o diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c new file mode 100644 index 0000000..304eb0a --- /dev/null +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -0,0 +1,867 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018-2019 MediaTek Inc. + +/* + * Driver for MediaTek Command-Queue DMA Controller + * + * Author: Shun-Chih Yu + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../virt-dma.h" + +#define MTK_CQDMA_USEC_POLL 10 +#define MTK_CQDMA_TIMEOUT_POLL 1000 +#define MTK_CQDMA_DMA_BUSWIDTHS BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) +#define MTK_CQDMA_ALIGN_SIZE 1 + +/* The default number of virtual channel */ +#define MTK_CQDMA_NR_VCHANS 32 + +/* The default number of physical channel */ +#define MTK_CQDMA_NR_PCHANS 3 + +/* Registers for underlying dma manipulation */ +#define MTK_CQDMA_INT_FLAG 0x0 +#define MTK_CQDMA_INT_EN 0x4 +#define MTK_CQDMA_EN 0x8 +#define MTK_CQDMA_RESET 0xc +#define MTK_CQDMA_FLUSH 0x14 +#define MTK_CQDMA_SRC 0x1c +#define MTK_CQDMA_DST 0x20 +#define MTK_CQDMA_LEN1 0x24 +#define MTK_CQDMA_LEN2 0x28 +#define MTK_CQDMA_SRC2 0x60 +#define MTK_CQDMA_DST2 0x64 + +/* Registers setting */ +#define MTK_CQDMA_EN_BIT BIT(0) +#define MTK_CQDMA_INT_FLAG_BIT BIT(0) +#define MTK_CQDMA_INT_EN_BIT BIT(0) +#define MTK_CQDMA_FLUSH_BIT BIT(0) + +#define MTK_CQDMA_WARM_RST_BIT BIT(0) +#define MTK_CQDMA_HARD_RST_BIT BIT(1) + +#define MTK_CQDMA_MAX_LEN GENMASK(27, 0) +#define MTK_CQDMA_ADDR_LIMIT GENMASK(31, 0) +#define MTK_CQDMA_ADDR2_SHFIT (32) + +/** + * struct mtk_cqdma_vdesc - The struct holding info describing virtual + * descriptor (CVD) + * @vd: An instance for struct virt_dma_desc + * @len: The total data size device wants to move + * @dest: The destination address device wants to move to + * @src: The source address device wants to move from + * @ch: The pointer to the corresponding dma channel + * @node: To build linked-list for PC queue + */ +struct mtk_cqdma_vdesc { + struct virt_dma_desc vd; + size_t len; + dma_addr_t dest; + dma_addr_t src; + struct dma_chan *ch; + + /* protected by pc.lock */ + struct list_head node; +}; + +/** + * struct mtk_cqdma_pchan - The struct holding info describing physical + * channel (PC) + * @queue: Queue for the CVDs issued to this PC + * @base: The mapped register I/O base of this PC + * @irq: The IRQ that this PC are using + * @refcnt: Track how many VCs are using this PC + * @lock: Lock protect agaisting multiple VCs access PC + */ +struct mtk_cqdma_pchan { + struct list_head queue; + void __iomem *base; + u32 irq; + refcount_t refcnt; + + /* lock to protect PC */ + spinlock_t lock; +}; + +/** + * struct mtk_cqdma_vchan - The struct holding info describing virtual + * channel (VC) + * @vc: An instance for struct virt_dma_chan + * @pc: The pointer to the underlying PC + * @issue_completion: The wait for all issued descriptors completited + * @issue_synchronize: Bool indicating channel synchronization starts + */ +struct mtk_cqdma_vchan { + struct virt_dma_chan vc; + struct mtk_cqdma_pchan *pc; + struct completion issue_completion; + bool issue_synchronize; + /* protected by vc.lock */ +}; + +/** + * struct mtk_cqdma_device - The struct holding info describing CQDMA + * device + * @ddev: An instance for struct dma_device + * @clk: The clock that device internal is using + * @dma_requests: The number of VCs the device supports to + * @dma_channels: The number of PCs the device supports to + * @vc: The pointer to all available VCs + * @pc: The pointer to all the underlying PCs + */ +struct mtk_cqdma_device { + struct dma_device ddev; + struct clk *clk; + + u32 dma_requests; + u32 dma_channels; + struct mtk_cqdma_vchan *vc; + struct mtk_cqdma_pchan **pc; +}; + +static struct mtk_cqdma_device *to_cqdma_dev(struct dma_chan *chan) +{ + return container_of(chan->device, struct mtk_cqdma_device, ddev); +} + +static struct mtk_cqdma_vchan *to_cqdma_vchan(struct dma_chan *chan) +{ + return container_of(chan, struct mtk_cqdma_vchan, vc.chan); +} + +static struct mtk_cqdma_vdesc *to_cqdma_vdesc(struct virt_dma_desc *vd) +{ + return container_of(vd, struct mtk_cqdma_vdesc, vd); +} + +static struct device *cqdma2dev(struct mtk_cqdma_device *cqdma) +{ + return cqdma->ddev.dev; +} + +static u32 mtk_dma_read(struct mtk_cqdma_pchan *pc, u32 reg) +{ + return readl(pc->base + reg); +} + +static void mtk_dma_write(struct mtk_cqdma_pchan *pc, u32 reg, u32 val) +{ + writel_relaxed(val, pc->base + reg); +} + +static void mtk_dma_rmw(struct mtk_cqdma_pchan *pc, u32 reg, + u32 mask, u32 set) +{ + u32 val; + + val = mtk_dma_read(pc, reg); + val &= ~mask; + val |= set; + mtk_dma_write(pc, reg, val); +} + +static void mtk_dma_set(struct mtk_cqdma_pchan *pc, u32 reg, u32 val) +{ + mtk_dma_rmw(pc, reg, 0, val); +} + +static void mtk_dma_clr(struct mtk_cqdma_pchan *pc, u32 reg, u32 val) +{ + mtk_dma_rmw(pc, reg, val, 0); +} + +static void mtk_cqdma_vdesc_free(struct virt_dma_desc *vd) +{ + kfree(to_cqdma_vdesc(vd)); +} + +static int mtk_cqdma_poll_engine_done(struct mtk_cqdma_pchan *pc, bool atomic) +{ + u32 status = 0; + + if (!atomic) + return readl_poll_timeout(pc->base + MTK_CQDMA_EN, + status, + !(status & MTK_CQDMA_EN_BIT), + MTK_CQDMA_USEC_POLL, + MTK_CQDMA_TIMEOUT_POLL); + + return readl_poll_timeout_atomic(pc->base + MTK_CQDMA_EN, + status, + !(status & MTK_CQDMA_EN_BIT), + MTK_CQDMA_USEC_POLL, + MTK_CQDMA_TIMEOUT_POLL); +} + +static int mtk_cqdma_hard_reset(struct mtk_cqdma_pchan *pc) +{ + mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT); + mtk_dma_clr(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT); + + return mtk_cqdma_poll_engine_done(pc, false); +} + +static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc, + struct mtk_cqdma_vdesc *cvd) +{ + /* wait for the previous transaction done */ + if (mtk_cqdma_poll_engine_done(pc, true) < 0) + dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), + "cqdma wait transaction timeout\n"); + + /* warm reset the dma engine for the new transaction */ + mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_WARM_RST_BIT); + if (mtk_cqdma_poll_engine_done(pc, true) < 0) + dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), + "cqdma warm reset timeout\n"); + + /* setup the source */ + mtk_dma_set(pc, MTK_CQDMA_SRC, cvd->src & MTK_CQDMA_ADDR_LIMIT); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + mtk_dma_set(pc, MTK_CQDMA_SRC2, cvd->src >> MTK_CQDMA_ADDR2_SHFIT); +#else + mtk_dma_set(pc, MTK_CQDMA_SRC2, 0); +#endif + + /* setup the destination */ + mtk_dma_set(pc, MTK_CQDMA_DST, cvd->dest & MTK_CQDMA_ADDR_LIMIT); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT); +#else + mtk_dma_set(pc, MTK_CQDMA_SRC2, 0); +#endif + + /* setup the length */ + mtk_dma_set(pc, MTK_CQDMA_LEN1, + (cvd->len < MTK_CQDMA_MAX_LEN) ? + cvd->len : MTK_CQDMA_MAX_LEN); + + /* start dma engine */ + mtk_dma_set(pc, MTK_CQDMA_EN, MTK_CQDMA_EN_BIT); +} + +static void mtk_cqdma_issue_vchan_pending(struct mtk_cqdma_vchan *cvc) +{ + struct virt_dma_desc *vd, *vd2; + struct mtk_cqdma_pchan *pc = cvc->pc; + struct mtk_cqdma_vdesc *cvd; + bool trigger_engine = false; + + lockdep_assert_held(&cvc->vc.lock); + lockdep_assert_held(&pc->lock); + + list_for_each_entry_safe(vd, vd2, &cvc->vc.desc_issued, node) { + /* need to trigger dma engine if PC's queue is empty */ + if (list_empty(&pc->queue)) + trigger_engine = true; + + cvd = to_cqdma_vdesc(vd); + + /* add VD into PC's queue */ + list_add_tail(&cvd->node, &pc->queue); + + /* start the dma engine */ + if (trigger_engine) + mtk_cqdma_start(pc, cvd); + + /* remove VD from list desc_issued */ + list_del(&vd->node); + } +} + +/* + * return true if this VC is active, + * meaning that there are VDs under processing by the PC + */ +static bool mtk_cqdma_is_vchan_active(struct mtk_cqdma_vchan *cvc) +{ + struct mtk_cqdma_vdesc *cvd; + + list_for_each_entry(cvd, &cvc->pc->queue, node) + if (cvc == to_cqdma_vchan(cvd->ch)) + return true; + + return false; +} + +/* + * return the pointer of the CVD that is just consumed by the PC + */ +static void mtk_cqdma_consume_work_queue(struct mtk_cqdma_pchan *pc) +{ + struct mtk_cqdma_vchan *cvc; + struct mtk_cqdma_vdesc *cvd; + size_t tlen; + + /* consume a CVD from PC's queue */ + cvd = list_first_entry_or_null(&pc->queue, + struct mtk_cqdma_vdesc, node); + if (unlikely(!cvd)) + return; + + cvc = to_cqdma_vchan(cvd->ch); + + tlen = (cvd->len < MTK_CQDMA_MAX_LEN) ? cvd->len : MTK_CQDMA_MAX_LEN; + cvd->len -= tlen; + cvd->src += tlen; + cvd->dest += tlen; + + /* check whether the CVD completed */ + if (!cvd->len) { + /* delete CVD from PC's queue */ + list_del(&cvd->node); + + spin_lock(&cvc->vc.lock); + + /* add the VD into list desc_completed */ + vchan_cookie_complete(&cvd->vd); + + /* setup completion if this VC is under synchronization */ + if (cvc->issue_synchronize && !mtk_cqdma_is_vchan_active(cvc)) { + complete(&cvc->issue_completion); + cvc->issue_synchronize = false; + } + + spin_unlock(&cvc->vc.lock); + } + + /* iterate on the next CVD if the current CVD completed */ + if (!cvd->len) + cvd = list_first_entry_or_null(&pc->queue, + struct mtk_cqdma_vdesc, node); + + /* start the next transaction */ + if (cvd) + mtk_cqdma_start(pc, cvd); +} + +static irqreturn_t mtk_cqdma_irq(int irq, void *devid) +{ + struct mtk_cqdma_device *cqdma = devid; + irqreturn_t ret = IRQ_NONE; + u32 i; + + /* clear interrupt flags for each PC */ + for (i = 0; i < cqdma->dma_channels; ++i) { + spin_lock(&cqdma->pc[i]->lock); + if (mtk_dma_read(cqdma->pc[i], + MTK_CQDMA_INT_FLAG) & MTK_CQDMA_INT_FLAG_BIT) { + /* clear interrupt */ + mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_FLAG, + MTK_CQDMA_INT_FLAG_BIT); + + mtk_cqdma_consume_work_queue(cqdma->pc[i]); + + ret = IRQ_HANDLED; + } + spin_unlock(&cqdma->pc[i]->lock); + } + + return ret; +} + +static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c, + dma_cookie_t cookie) +{ + struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); + struct virt_dma_desc *vd; + unsigned long flags; + + spin_lock_irqsave(&cvc->pc->lock, flags); + list_for_each_entry(vd, &cvc->pc->queue, node) + if (vd->tx.cookie == cookie) { + spin_unlock_irqrestore(&cvc->pc->lock, flags); + return vd; + } + spin_unlock_irqrestore(&cvc->pc->lock, flags); + + list_for_each_entry(vd, &cvc->vc.desc_issued, node) + if (vd->tx.cookie == cookie) + return vd; + + return NULL; +} + +static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); + struct mtk_cqdma_vdesc *cvd; + struct virt_dma_desc *vd; + enum dma_status ret; + unsigned long flags; + size_t bytes = 0; + + ret = dma_cookie_status(c, cookie, txstate); + if (ret == DMA_COMPLETE || !txstate) + return ret; + + spin_lock_irqsave(&cvc->vc.lock, flags); + vd = mtk_cqdma_find_active_desc(c, cookie); + spin_unlock_irqrestore(&cvc->vc.lock, flags); + + if (vd) { + cvd = to_cqdma_vdesc(vd); + bytes = cvd->len; + } + + dma_set_residue(txstate, bytes); + + return ret; +} + +static void mtk_cqdma_issue_pending(struct dma_chan *c) +{ + struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); + unsigned long pc_flags; + unsigned long vc_flags; + + /* acquire PC's lock before VS's lock for lock dependency in ISR */ + spin_lock_irqsave(&cvc->pc->lock, pc_flags); + spin_lock_irqsave(&cvc->vc.lock, vc_flags); + + if (vchan_issue_pending(&cvc->vc)) + mtk_cqdma_issue_vchan_pending(cvc); + + spin_unlock_irqrestore(&cvc->vc.lock, vc_flags); + spin_unlock_irqrestore(&cvc->pc->lock, pc_flags); +} + +static struct dma_async_tx_descriptor * +mtk_cqdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, + dma_addr_t src, size_t len, unsigned long flags) +{ + struct mtk_cqdma_vdesc *cvd; + + cvd = kzalloc(sizeof(*cvd), GFP_NOWAIT); + if (!cvd) + return NULL; + + /* setup dma channel */ + cvd->ch = c; + + /* setup sourece, destination, and length */ + cvd->len = len; + cvd->src = src; + cvd->dest = dest; + + return vchan_tx_prep(to_virt_chan(c), &cvd->vd, flags); +} + +static void mtk_cqdma_free_inactive_desc(struct dma_chan *c) +{ + struct virt_dma_chan *vc = to_virt_chan(c); + unsigned long flags; + LIST_HEAD(head); + + /* + * set desc_allocated, desc_submitted, + * and desc_issued as the candicates to be freed + */ + spin_lock_irqsave(&vc->lock, flags); + list_splice_tail_init(&vc->desc_allocated, &head); + list_splice_tail_init(&vc->desc_submitted, &head); + list_splice_tail_init(&vc->desc_issued, &head); + spin_unlock_irqrestore(&vc->lock, flags); + + /* free descriptor lists */ + vchan_dma_desc_free_list(vc, &head); +} + +static void mtk_cqdma_free_active_desc(struct dma_chan *c) +{ + struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); + bool sync_needed = false; + unsigned long pc_flags; + unsigned long vc_flags; + + /* acquire PC's lock first due to lock dependency in dma ISR */ + spin_lock_irqsave(&cvc->pc->lock, pc_flags); + spin_lock_irqsave(&cvc->vc.lock, vc_flags); + + /* synchronization is required if this VC is active */ + if (mtk_cqdma_is_vchan_active(cvc)) { + cvc->issue_synchronize = true; + sync_needed = true; + } + + spin_unlock_irqrestore(&cvc->vc.lock, vc_flags); + spin_unlock_irqrestore(&cvc->pc->lock, pc_flags); + + /* waiting for the completion of this VC */ + if (sync_needed) + wait_for_completion(&cvc->issue_completion); + + /* free all descriptors in list desc_completed */ + vchan_synchronize(&cvc->vc); + + WARN_ONCE(!list_empty(&cvc->vc.desc_completed), + "Desc pending still in list desc_completed\n"); +} + +static int mtk_cqdma_terminate_all(struct dma_chan *c) +{ + /* free descriptors not processed yet by hardware */ + mtk_cqdma_free_inactive_desc(c); + + /* free descriptors being processed by hardware */ + mtk_cqdma_free_active_desc(c); + + return 0; +} + +static int mtk_cqdma_alloc_chan_resources(struct dma_chan *c) +{ + struct mtk_cqdma_device *cqdma = to_cqdma_dev(c); + struct mtk_cqdma_vchan *vc = to_cqdma_vchan(c); + struct mtk_cqdma_pchan *pc = NULL; + u32 i, min_refcnt = U32_MAX, refcnt; + unsigned long flags; + + /* allocate PC with the minimum refcount */ + for (i = 0; i < cqdma->dma_channels; ++i) { + refcnt = refcount_read(&cqdma->pc[i]->refcnt); + if (refcnt < min_refcnt) { + pc = cqdma->pc[i]; + min_refcnt = refcnt; + } + } + + if (!pc) + return -ENOSPC; + + spin_lock_irqsave(&pc->lock, flags); + + if (!refcount_read(&pc->refcnt)) { + /* allocate PC when the refcount is zero */ + mtk_cqdma_hard_reset(pc); + + /* enable interrupt for this PC */ + mtk_dma_set(pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT); + + /* + * refcount_inc would complain increment on 0; use-after-free. + * Thus, we need to explicitly set it as 1 initially. + */ + refcount_set(&pc->refcnt, 1); + } else { + refcount_inc(&pc->refcnt); + } + + spin_unlock_irqrestore(&pc->lock, flags); + + vc->pc = pc; + + return 0; +} + +static void mtk_cqdma_free_chan_resources(struct dma_chan *c) +{ + struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); + unsigned long flags; + + /* free all descriptors in all lists on the VC */ + mtk_cqdma_terminate_all(c); + + spin_lock_irqsave(&cvc->pc->lock, flags); + + /* PC is not freed until there is no VC mapped to it */ + if (refcount_dec_and_test(&cvc->pc->refcnt)) { + /* start the flush operation and stop the engine */ + mtk_dma_set(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT); + + /* wait for the completion of flush operation */ + if (mtk_cqdma_poll_engine_done(cvc->pc, false) < 0) + dev_err(cqdma2dev(to_cqdma_dev(c)), + "cqdma flush timeout\n"); + + /* clear the flush bit and interrupt flag */ + mtk_dma_clr(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT); + mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_FLAG, + MTK_CQDMA_INT_FLAG_BIT); + + /* disable interrupt for this PC */ + mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT); + } + + spin_unlock_irqrestore(&cvc->pc->lock, flags); +} + +static int mtk_cqdma_hw_init(struct mtk_cqdma_device *cqdma) +{ + unsigned long flags; + int err; + u32 i; + + pm_runtime_enable(cqdma2dev(cqdma)); + pm_runtime_get_sync(cqdma2dev(cqdma)); + + err = clk_prepare_enable(cqdma->clk); + + if (err) { + pm_runtime_put_sync(cqdma2dev(cqdma)); + pm_runtime_disable(cqdma2dev(cqdma)); + return err; + } + + /* reset all PCs */ + for (i = 0; i < cqdma->dma_channels; ++i) { + spin_lock_irqsave(&cqdma->pc[i]->lock, flags); + if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0) { + dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n"); + spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags); + + clk_disable_unprepare(cqdma->clk); + pm_runtime_put_sync(cqdma2dev(cqdma)); + pm_runtime_disable(cqdma2dev(cqdma)); + return -EINVAL; + } + spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags); + } + + return 0; +} + +static void mtk_cqdma_hw_deinit(struct mtk_cqdma_device *cqdma) +{ + unsigned long flags; + u32 i; + + /* reset all PCs */ + for (i = 0; i < cqdma->dma_channels; ++i) { + spin_lock_irqsave(&cqdma->pc[i]->lock, flags); + if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0) + dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n"); + spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags); + } + + clk_disable_unprepare(cqdma->clk); + + pm_runtime_put_sync(cqdma2dev(cqdma)); + pm_runtime_disable(cqdma2dev(cqdma)); +} + +static const struct of_device_id mtk_cqdma_match[] = { + { .compatible = "mediatek,mt6765-cqdma" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, mtk_cqdma_match); + +static int mtk_cqdma_probe(struct platform_device *pdev) +{ + struct mtk_cqdma_device *cqdma; + struct mtk_cqdma_vchan *vc; + struct dma_device *dd; + struct resource *res; + int err; + u32 i; + + cqdma = devm_kzalloc(&pdev->dev, sizeof(*cqdma), GFP_KERNEL); + if (!cqdma) + return -ENOMEM; + + dd = &cqdma->ddev; + + cqdma->clk = devm_clk_get(&pdev->dev, "cqdma"); + if (IS_ERR(cqdma->clk)) { + dev_err(&pdev->dev, "No clock for %s\n", + dev_name(&pdev->dev)); + return PTR_ERR(cqdma->clk); + } + + dma_cap_set(DMA_MEMCPY, dd->cap_mask); + + dd->copy_align = MTK_CQDMA_ALIGN_SIZE; + dd->device_alloc_chan_resources = mtk_cqdma_alloc_chan_resources; + dd->device_free_chan_resources = mtk_cqdma_free_chan_resources; + dd->device_tx_status = mtk_cqdma_tx_status; + dd->device_issue_pending = mtk_cqdma_issue_pending; + dd->device_prep_dma_memcpy = mtk_cqdma_prep_dma_memcpy; + dd->device_terminate_all = mtk_cqdma_terminate_all; + dd->src_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS; + dd->dst_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS; + dd->directions = BIT(DMA_MEM_TO_MEM); + dd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + dd->dev = &pdev->dev; + INIT_LIST_HEAD(&dd->channels); + + if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node, + "dma-requests", + &cqdma->dma_requests)) { + dev_dbg(&pdev->dev, + "Using %u as missing dma-requests property\n", + MTK_CQDMA_NR_VCHANS); + + cqdma->dma_requests = MTK_CQDMA_NR_VCHANS; + } + + if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node, + "dma-channels", + &cqdma->dma_channels)) { + dev_dbg(&pdev->dev, + "Using %u as missing dma-channels property\n", + MTK_CQDMA_NR_PCHANS); + + cqdma->dma_channels = MTK_CQDMA_NR_PCHANS; + } + + cqdma->pc = devm_kcalloc(&pdev->dev, cqdma->dma_channels, + sizeof(*cqdma->pc), GFP_KERNEL); + if (!cqdma->pc) + return -ENOMEM; + + /* initialization for PCs */ + for (i = 0; i < cqdma->dma_channels; ++i) { + cqdma->pc[i] = devm_kcalloc(&pdev->dev, 1, + sizeof(**cqdma->pc), GFP_KERNEL); + if (!cqdma->pc[i]) + return -ENOMEM; + + INIT_LIST_HEAD(&cqdma->pc[i]->queue); + spin_lock_init(&cqdma->pc[i]->lock); + refcount_set(&cqdma->pc[i]->refcnt, 0); + + res = platform_get_resource(pdev, IORESOURCE_MEM, i); + if (!res) { + dev_err(&pdev->dev, "No mem resource for %s\n", + dev_name(&pdev->dev)); + return -EINVAL; + } + + cqdma->pc[i]->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(cqdma->pc[i]->base)) + return PTR_ERR(cqdma->pc[i]->base); + + /* allocate IRQ resource */ + res = platform_get_resource(pdev, IORESOURCE_IRQ, i); + if (!res) { + dev_err(&pdev->dev, "No irq resource for %s\n", + dev_name(&pdev->dev)); + return -EINVAL; + } + cqdma->pc[i]->irq = res->start; + + err = devm_request_irq(&pdev->dev, cqdma->pc[i]->irq, + mtk_cqdma_irq, 0, dev_name(&pdev->dev), + cqdma); + if (err) { + dev_err(&pdev->dev, + "request_irq failed with err %d\n", err); + return -EINVAL; + } + } + + /* allocate resource for VCs */ + cqdma->vc = devm_kcalloc(&pdev->dev, cqdma->dma_requests, + sizeof(*cqdma->vc), GFP_KERNEL); + if (!cqdma->vc) + return -ENOMEM; + + for (i = 0; i < cqdma->dma_requests; i++) { + vc = &cqdma->vc[i]; + vc->vc.desc_free = mtk_cqdma_vdesc_free; + vchan_init(&vc->vc, dd); + init_completion(&vc->issue_completion); + } + + err = dma_async_device_register(dd); + if (err) + return err; + + err = of_dma_controller_register(pdev->dev.of_node, + of_dma_xlate_by_chan_id, cqdma); + if (err) { + dev_err(&pdev->dev, + "MediaTek CQDMA OF registration failed %d\n", err); + goto err_unregister; + } + + err = mtk_cqdma_hw_init(cqdma); + if (err) { + dev_err(&pdev->dev, + "MediaTek CQDMA HW initialization failed %d\n", err); + goto err_unregister; + } + + platform_set_drvdata(pdev, cqdma); + + dev_dbg(&pdev->dev, "MediaTek CQDMA driver registered\n"); + + return 0; + +err_unregister: + dma_async_device_unregister(dd); + + return err; +} + +static int mtk_cqdma_remove(struct platform_device *pdev) +{ + struct mtk_cqdma_device *cqdma = platform_get_drvdata(pdev); + struct mtk_cqdma_vchan *vc; + unsigned long flags; + int i; + + /* kill VC task */ + for (i = 0; i < cqdma->dma_requests; i++) { + vc = &cqdma->vc[i]; + + list_del(&vc->vc.chan.device_node); + tasklet_kill(&vc->vc.task); + } + + /* disable interrupt */ + for (i = 0; i < cqdma->dma_channels; i++) { + spin_lock_irqsave(&cqdma->pc[i]->lock, flags); + mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_EN, + MTK_CQDMA_INT_EN_BIT); + spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags); + + /* Waits for any pending IRQ handlers to complete */ + synchronize_irq(cqdma->pc[i]->irq); + } + + /* disable hardware */ + mtk_cqdma_hw_deinit(cqdma); + + dma_async_device_unregister(&cqdma->ddev); + of_dma_controller_free(pdev->dev.of_node); + + return 0; +} + +static struct platform_driver mtk_cqdma_driver = { + .probe = mtk_cqdma_probe, + .remove = mtk_cqdma_remove, + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = mtk_cqdma_match, + }, +}; +module_platform_driver(mtk_cqdma_driver); + +MODULE_DESCRIPTION("MediaTek CQDMA Controller Driver"); +MODULE_AUTHOR("Shun-Chih Yu "); +MODULE_LICENSE("GPL v2");