diff options
Diffstat (limited to 'drivers/dma')
| -rw-r--r-- | drivers/dma/Kconfig | 15 | ||||
| -rw-r--r-- | drivers/dma/Makefile | 1 | ||||
| -rw-r--r-- | drivers/dma/bcm-sba-raid.c | 1785 | ||||
| -rw-r--r-- | drivers/dma/dw/Kconfig | 7 | ||||
| -rw-r--r-- | drivers/dma/dw/core.c | 332 | ||||
| -rw-r--r-- | drivers/dma/dw/platform.c | 6 | ||||
| -rw-r--r-- | drivers/dma/dw/regs.h | 50 | ||||
| -rw-r--r-- | drivers/dma/fsl_raid.c | 2 | ||||
| -rw-r--r-- | drivers/dma/fsldma.c | 5 | ||||
| -rw-r--r-- | drivers/dma/fsldma.h | 4 | ||||
| -rw-r--r-- | drivers/dma/imx-dma.c | 7 | ||||
| -rw-r--r-- | drivers/dma/imx-sdma.c | 27 | ||||
| -rw-r--r-- | drivers/dma/ioat/dca.c | 8 | ||||
| -rw-r--r-- | drivers/dma/qcom/hidma.c | 22 | ||||
| -rw-r--r-- | drivers/dma/qcom/hidma.h | 1 | ||||
| -rw-r--r-- | drivers/dma/qcom/hidma_mgmt.c | 47 | ||||
| -rw-r--r-- | drivers/dma/ste_dma40.c | 5 | ||||
| -rw-r--r-- | drivers/dma/tegra20-apb-dma.c | 50 | ||||
| -rw-r--r-- | drivers/dma/xilinx/zynqmp_dma.c | 3 |
19 files changed, 1930 insertions, 447 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 24e8597b2c3e..686ae67d7e2a 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -99,6 +99,21 @@ config AXI_DMAC controller is often used in Analog Device's reference designs for FPGA platforms. +config BCM_SBA_RAID + tristate "Broadcom SBA RAID engine support" + depends on ARM64 || COMPILE_TEST + depends on MAILBOX && RAID6_PQ + select DMA_ENGINE + select DMA_ENGINE_RAID + select ASYNC_TX_DISABLE_XOR_VAL_DMA + select ASYNC_TX_DISABLE_PQ_VAL_DMA + default ARCH_BCM_IPROC + help + Enable support for Broadcom SBA RAID Engine. The SBA RAID + engine is available on most of the Broadcom iProc SoCs. It + has the capability to offload memcpy, xor and pq computation + for raid5/6. + config COH901318 bool "ST-Ericsson COH901318 DMA support" select DMA_ENGINE diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 0b723e94d9e6..d12ab2985ed1 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o +obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c new file mode 100644 index 000000000000..e41bbc7cb094 --- /dev/null +++ b/drivers/dma/bcm-sba-raid.c @@ -0,0 +1,1785 @@ +/* + * Copyright (C) 2017 Broadcom + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Broadcom SBA RAID Driver + * + * The Broadcom stream buffer accelerator (SBA) provides offloading + * capabilities for RAID operations. The SBA offload engine is accessible + * via Broadcom SoC specific ring manager. Two or more offload engines + * can share same Broadcom SoC specific ring manager due to this Broadcom + * SoC specific ring manager driver is implemented as a mailbox controller + * driver and offload engine drivers are implemented as mallbox clients. + * + * Typically, Broadcom SoC specific ring manager will implement larger + * number of hardware rings over one or more SBA hardware devices. By + * design, the internal buffer size of SBA hardware device is limited + * but all offload operations supported by SBA can be broken down into + * multiple small size requests and executed parallely on multiple SBA + * hardware devices for achieving high through-put. + * + * The Broadcom SBA RAID driver does not require any register programming + * except submitting request to SBA hardware device via mailbox channels. + * This driver implements a DMA device with one DMA channel using a set + * of mailbox channels provided by Broadcom SoC specific ring manager + * driver. To exploit parallelism (as described above), all DMA request + * coming to SBA RAID DMA channel are broken down to smaller requests + * and submitted to multiple mailbox channels in round-robin fashion. + * For having more SBA DMA channels, we can create more SBA device nodes + * in Broadcom SoC specific DTS based on number of hardware rings supported + * by Broadcom SoC ring manager. + */ + +#include <linux/bitops.h> +#include <linux/dma-mapping.h> +#include <linux/dmaengine.h> +#include <linux/list.h> +#include <linux/mailbox_client.h> +#include <linux/mailbox/brcm-message.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/slab.h> +#include <linux/raid/pq.h> + +#include "dmaengine.h" + +/* SBA command related defines */ +#define SBA_TYPE_SHIFT 48 +#define SBA_TYPE_MASK GENMASK(1, 0) +#define SBA_TYPE_A 0x0 +#define SBA_TYPE_B 0x2 +#define SBA_TYPE_C 0x3 +#define SBA_USER_DEF_SHIFT 32 +#define SBA_USER_DEF_MASK GENMASK(15, 0) +#define SBA_R_MDATA_SHIFT 24 +#define SBA_R_MDATA_MASK GENMASK(7, 0) +#define SBA_C_MDATA_MS_SHIFT 18 +#define SBA_C_MDATA_MS_MASK GENMASK(1, 0) +#define SBA_INT_SHIFT 17 +#define SBA_INT_MASK BIT(0) +#define SBA_RESP_SHIFT 16 +#define SBA_RESP_MASK BIT(0) +#define SBA_C_MDATA_SHIFT 8 +#define SBA_C_MDATA_MASK GENMASK(7, 0) +#define SBA_C_MDATA_BNUMx_SHIFT(__bnum) (2 * (__bnum)) +#define SBA_C_MDATA_BNUMx_MASK GENMASK(1, 0) +#define SBA_C_MDATA_DNUM_SHIFT 5 +#define SBA_C_MDATA_DNUM_MASK GENMASK(4, 0) +#define SBA_C_MDATA_LS(__v) ((__v) & 0xff) +#define SBA_C_MDATA_MS(__v) (((__v) >> 8) & 0x3) +#define SBA_CMD_SHIFT 0 +#define SBA_CMD_MASK GENMASK(3, 0) +#define SBA_CMD_ZERO_BUFFER 0x4 +#define SBA_CMD_ZERO_ALL_BUFFERS 0x8 +#define SBA_CMD_LOAD_BUFFER 0x9 +#define SBA_CMD_XOR 0xa +#define SBA_CMD_GALOIS_XOR 0xb +#define SBA_CMD_WRITE_BUFFER 0xc +#define SBA_CMD_GALOIS 0xe + +/* Driver helper macros */ +#define to_sba_request(tx) \ + container_of(tx, struct sba_request, tx) +#define to_sba_device(dchan) \ + container_of(dchan, struct sba_device, dma_chan) + +enum sba_request_state { + SBA_REQUEST_STATE_FREE = 1, + SBA_REQUEST_STATE_ALLOCED = 2, + SBA_REQUEST_STATE_PENDING = 3, + SBA_REQUEST_STATE_ACTIVE = 4, + SBA_REQUEST_STATE_RECEIVED = 5, + SBA_REQUEST_STATE_COMPLETED = 6, + SBA_REQUEST_STATE_ABORTED = 7, +}; + +struct sba_request { + /* Global state */ + struct list_head node; + struct sba_device *sba; + enum sba_request_state state; + bool fence; + /* Chained requests management */ + struct sba_request *first; + struct list_head next; + unsigned int next_count; + atomic_t next_pending_count; + /* BRCM message data */ + void *resp; + dma_addr_t resp_dma; + struct brcm_sba_command *cmds; + struct brcm_message msg; + struct dma_async_tx_descriptor tx; +}; + +enum sba_version { + SBA_VER_1 = 0, + SBA_VER_2 +}; + +struct sba_device { + /* Underlying device */ + struct device *dev; + /* DT configuration parameters */ + enum sba_version ver; + /* Derived configuration parameters */ + u32 max_req; + u32 hw_buf_size; + u32 hw_resp_size; + u32 max_pq_coefs; + u32 max_pq_srcs; + u32 max_cmd_per_req; + u32 max_xor_srcs; + u32 max_resp_pool_size; + u32 max_cmds_pool_size; + /* Maibox client and Mailbox channels */ + struct mbox_client client; + int mchans_count; + atomic_t mchans_current; + struct mbox_chan **mchans; + struct device *mbox_dev; + /* DMA device and DMA channel */ + struct dma_device dma_dev; + struct dma_chan dma_chan; + /* DMA channel resources */ + void *resp_base; + dma_addr_t resp_dma_base; + void *cmds_base; + dma_addr_t cmds_dma_base; + spinlock_t reqs_lock; + struct sba_request *reqs; + bool reqs_fence; + struct list_head reqs_alloc_list; + struct list_head reqs_pending_list; + struct list_head reqs_active_list; + struct list_head reqs_received_list; + struct list_head reqs_completed_list; + struct list_head reqs_aborted_list; + struct list_head reqs_free_list; + int reqs_free_count; +}; + +/* ====== SBA command helper routines ===== */ + +static inline u64 __pure sba_cmd_enc(u64 cmd, u32 val, u32 shift, u32 mask) +{ + cmd &= ~((u64)mask << shift); + cmd |= ((u64)(val & mask) << shift); + return cmd; +} + +static inline u32 __pure sba_cmd_load_c_mdata(u32 b0) +{ + return b0 & SBA_C_MDATA_BNUMx_MASK; +} + +static inline u32 __pure sba_cmd_write_c_mdata(u32 b0) +{ + return b0 & SBA_C_MDATA_BNUMx_MASK; +} + +static inline u32 __pure sba_cmd_xor_c_mdata(u32 b1, u32 b0) +{ + return (b0 & SBA_C_MDATA_BNUMx_MASK) | + ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1)); +} + +static inline u32 __pure sba_cmd_pq_c_mdata(u32 d, u32 b1, u32 b0) +{ + return (b0 & SBA_C_MDATA_BNUMx_MASK) | + ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1)) | + ((d & SBA_C_MDATA_DNUM_MASK) << SBA_C_MDATA_DNUM_SHIFT); +} + +/* ====== Channel resource management routines ===== */ + +static struct sba_request *sba_alloc_request(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req = NULL; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + req = list_first_entry_or_null(&sba->reqs_free_list, + struct sba_request, node); + if (req) { + list_move_tail(&req->node, &sba->reqs_alloc_list); + req->state = SBA_REQUEST_STATE_ALLOCED; + req->fence = false; + req->first = req; + INIT_LIST_HEAD(&req->next); + req->next_count = 1; + atomic_set(&req->next_pending_count, 1); + + sba->reqs_free_count--; + + dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan); + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); + + return req; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_pending_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_PENDING; + list_move_tail(&req->node, &sba->reqs_pending_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; +} + +/* Note: Must be called with sba->reqs_lock held */ +static bool _sba_active_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + if (sba->reqs_fence) + return false; + req->state = SBA_REQUEST_STATE_ACTIVE; + list_move_tail(&req->node, &sba->reqs_active_list); + if (req->fence) + sba->reqs_fence = true; + return true; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_abort_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_ABORTED; + list_move_tail(&req->node, &sba->reqs_aborted_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_free_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_FREE; + list_move_tail(&req->node, &sba->reqs_free_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + sba->reqs_free_count++; +} + +static void sba_received_request(struct sba_request *req) +{ + unsigned long flags; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + req->state = SBA_REQUEST_STATE_RECEIVED; + list_move_tail(&req->node, &sba->reqs_received_list); + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_complete_chained_requests(struct sba_request *req) +{ + unsigned long flags; + struct sba_request *nreq; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + req->state = SBA_REQUEST_STATE_COMPLETED; + list_move_tail(&req->node, &sba->reqs_completed_list); + list_for_each_entry(nreq, &req->next, next) { + nreq->state = SBA_REQUEST_STATE_COMPLETED; + list_move_tail(&nreq->node, &sba->reqs_completed_list); + } + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_free_chained_requests(struct sba_request *req) +{ + unsigned long flags; + struct sba_request *nreq; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + _sba_free_request(sba, req); + list_for_each_entry(nreq, &req->next, next) + _sba_free_request(sba, nreq); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_chain_request(struct sba_request *first, + struct sba_request *req) +{ + unsigned long flags; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + list_add_tail(&req->next, &first->next); + req->first = first; + first->next_count++; + atomic_set(&first->next_pending_count, first->next_count); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_cleanup_nonpending_requests(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req, *req1; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Freeup all alloced request */ + list_for_each_entry_safe(req, req1, &sba->reqs_alloc_list, node) + _sba_free_request(sba, req); + + /* Freeup all received request */ + list_for_each_entry_safe(req, req1, &sba->reqs_received_list, node) + _sba_free_request(sba, req); + + /* Freeup all completed request */ + list_for_each_entry_safe(req, req1, &sba->reqs_completed_list, node) + _sba_free_request(sba, req); + + /* Set all active requests as aborted */ + list_for_each_entry_safe(req, req1, &sba->reqs_active_list, node) + _sba_abort_request(sba, req); + + /* + * Note: We expect that aborted request will be eventually + * freed by sba_receive_message() + */ + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_cleanup_pending_requests(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req, *req1; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Freeup all pending request */ + list_for_each_entry_safe(req, req1, &sba->reqs_pending_list, node) + _sba_free_request(sba, req); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +/* ====== DMAENGINE callbacks ===== */ + +static void sba_free_chan_resources(struct dma_chan *dchan) +{ + /* + * Channel resources are pre-alloced so we just free-up + * whatever we can so that we can re-use pre-alloced + * channel resources next time. + */ + sba_cleanup_nonpending_requests(to_sba_device(dchan)); +} + +static int sba_device_terminate_all(struct dma_chan *dchan) +{ + /* Cleanup all pending requests */ + sba_cleanup_pending_requests(to_sba_device(dchan)); + + return 0; +} + +static int sba_send_mbox_request(struct sba_device *sba, + struct sba_request *req) +{ + int mchans_idx, ret = 0; + + /* Select mailbox channel in round-robin fashion */ + mchans_idx = atomic_inc_return(&sba->mchans_current); + mchans_idx = mchans_idx % sba->mchans_count; + + /* Send message for the request */ + req->msg.error = 0; + ret = mbox_send_message(sba->mchans[mchans_idx], &req->msg); + if (ret < 0) { + dev_err(sba->dev, "send message failed with error %d", ret); + return ret; + } + ret = req->msg.error; + if (ret < 0) { + dev_err(sba->dev, "message error %d", ret); + return ret; + } + + return 0; +} + +static void sba_issue_pending(struct dma_chan *dchan) +{ + int ret; + unsigned long flags; + struct sba_request *req, *req1; + struct sba_device *sba = to_sba_device(dchan); + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Process all pending request */ + list_for_each_entry_safe(req, req1, &sba->reqs_pending_list, node) { + /* Try to make request active */ + if (!_sba_active_request(sba, req)) + break; + + /* Send request to mailbox channel */ + spin_unlock_irqrestore(&sba->reqs_lock, flags); + ret = sba_send_mbox_request(sba, req); + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* If something went wrong then keep request pending */ + if (ret < 0) { + _sba_pending_request(sba, req); + break; + } + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static dma_cookie_t sba_tx_submit(struct dma_async_tx_descriptor *tx) +{ + unsigned long flags; + dma_cookie_t cookie; + struct sba_device *sba; + struct sba_request *req, *nreq; + + if (unlikely(!tx)) + return -EINVAL; + + sba = to_sba_device(tx->chan); + req = to_sba_request(tx); + + /* Assign cookie and mark all chained requests pending */ + spin_lock_irqsave(&sba->reqs_lock, flags); + cookie = dma_cookie_assign(tx); + _sba_pending_request(sba, req); + list_for_each_entry(nreq, &req->next, next) + _sba_pending_request(sba, nreq); + spin_unlock_irqrestore(&sba->reqs_lock, flags); + + return cookie; +} + +static enum dma_status sba_tx_status(struct dma_chan *dchan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + int mchan_idx; + enum dma_status ret; + struct sba_device *sba = to_sba_device(dchan); + + for (mchan_idx = 0; mchan_idx < sba->mchans_count; mchan_idx++) + mbox_client_peek_data(sba->mchans[mchan_idx]); + + ret = dma_cookie_status(dchan, cookie, txstate); + if (ret == DMA_COMPLETE) + return ret; + + return dma_cookie_status(dchan, cookie, txstate); +} + +static void sba_fillup_interrupt_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg) +{ + u64 cmd; + u32 c_mdata; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load dummy data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = req->resp_dma; + cmdsp->data_len = req->sba->hw_resp_size; + cmdsp++; + + /* Type-A command to write buf0 to dummy location */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = req->resp_dma; + cmdsp->data_len = req->sba->hw_resp_size; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_interrupt(struct dma_chan *dchan, unsigned long flags) +{ + struct sba_request *req = NULL; + struct sba_device *sba = to_sba_device(dchan); + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + + /* + * Force fence so that no requests are submitted + * until DMA callback for this request is invoked. + */ + req->fence = true; + + /* Fillup request message */ + sba_fillup_interrupt_msg(req, req->cmds, &req->msg); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return &req->tx; +} + +static void sba_fillup_memcpy_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t dst, dma_addr_t src) +{ + u64 cmd; + u32 c_mdata; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = dst + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +static struct sba_request * +sba_prep_dma_memcpy_req(struct sba_device *sba, + dma_addr_t off, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request message */ + sba_fillup_memcpy_msg(req, req->cmds, &req->msg, + off, len, dst, src); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + size_t req_len; + dma_addr_t off = 0; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + req = sba_prep_dma_memcpy_req(sba, off, dst, src, + req_len, flags); + if (!req) { + if (first) + sba_free_chained_requests(first); + return NULL; + } + + if (first) + sba_chain_request(first, req); + else + first = req; + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; +} + +static void sba_fillup_xor_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t dst, dma_addr_t *src, u32 src_cnt) +{ + u64 cmd; + u32 c_mdata; + unsigned int i; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[0] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Type-B commands to xor data with buf0 and put it back in buf0 */ + for (i = 1; i < src_cnt; i++) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[i] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = dst + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_xor_req(struct sba_device *sba, + dma_addr_t off, dma_addr_t dst, dma_addr_t *src, + u32 src_cnt, size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request message */ + sba_fillup_xor_msg(req, req->cmds, &req->msg, + off, len, dst, src, src_cnt); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_xor(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t *src, + u32 src_cnt, size_t len, unsigned long flags) +{ + size_t req_len; + dma_addr_t off = 0; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Sanity checks */ + if (unlikely(src_cnt > sba->max_xor_srcs)) + return NULL; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + req = sba_prep_dma_xor_req(sba, off, dst, src, src_cnt, + req_len, flags); + if (!req) { + if (first) + sba_free_chained_requests(first); + return NULL; + } + + if (first) + sba_chain_request(first, req); + else + first = req; + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; +} + +static void sba_fillup_pq_msg(struct sba_request *req, + bool pq_continue, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t *dst_p, dma_addr_t *dst_q, + const u8 *scf, dma_addr_t *src, u32 src_cnt) +{ + u64 cmd; + u32 c_mdata; + unsigned int i; + struct brcm_sba_command *cmdsp = cmds; + + if (pq_continue) { + /* Type-B command to load old P into buf0 */ + if (dst_p) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-B command to load old Q into buf1 */ + if (dst_q) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + } else { + /* Type-A command to zero all buffers */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + } + + /* Type-B commands for generate P onto buf0 and Q onto buf1 */ + for (i = 0; i < src_cnt; i++) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(raid6_gflog[scf[i]], 1, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[i] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + if (dst_p) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf1 */ + if (dst_q) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_pq_req(struct sba_device *sba, dma_addr_t off, + dma_addr_t *dst_p, dma_addr_t *dst_q, dma_addr_t *src, + u32 src_cnt, const u8 *scf, size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request messages */ + sba_fillup_pq_msg(req, dmaf_continue(flags), + req->cmds, &req->msg, + off, len, dst_p, dst_q, scf, src, src_cnt); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static void sba_fillup_pq_single_msg(struct sba_request *req, + bool pq_continue, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t *dst_p, dma_addr_t *dst_q, + dma_addr_t src, u8 scf) +{ + u64 cmd; + u32 c_mdata; + u8 pos, dpos = raid6_gflog[scf]; + struct brcm_sba_command *cmdsp = cmds; + + if (!dst_p) + goto skip_p; + + if (pq_continue) { + /* Type-B command to load old P into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* + * Type-B commands to xor data with buf0 and put it + * back in buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } else { + /* Type-B command to load old P into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + +skip_p: + if (!dst_q) + goto skip_q; + + /* Type-A command to zero all buffers */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + + if (dpos == 255) + goto skip_q_computation; + pos = (dpos < req->sba->max_pq_coefs) ? + dpos : (req->sba->max_pq_coefs - 1); + + /* + * Type-B command to generate initial Q from data + * and store output into buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(pos, 0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + dpos -= pos; + + /* Multiple Type-A command to generate final Q */ + while (dpos) { + pos = (dpos < req->sba->max_pq_coefs) ? + dpos : (req->sba->max_pq_coefs - 1); + + /* + * Type-A command to generate Q with buf0 and + * buf1 store result in buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(pos, 0, 1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + + dpos -= pos; + } + +skip_q_computation: + if (pq_continue) { + /* + * Type-B command to XOR previous output with + * buf0 and write it into buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + +skip_q: + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_pq_single_req(struct sba_device *sba, dma_addr_t off, + dma_addr_t *dst_p, dma_addr_t *dst_q, + dma_addr_t src, u8 scf, size_t len, + unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request messages */ + sba_fillup_pq_single_msg(req, dmaf_continue(flags), + req->cmds, &req->msg, off, len, + dst_p, dst_q, src, scf); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_pq(struct dma_chan *dchan, dma_addr_t *dst, dma_addr_t *src, + u32 src_cnt, const u8 *scf, size_t len, unsigned long flags) +{ + u32 i, dst_q_index; + size_t req_len; + bool slow = false; + dma_addr_t off = 0; + dma_addr_t *dst_p = NULL, *dst_q = NULL; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Sanity checks */ + if (unlikely(src_cnt > sba->max_pq_srcs)) + return NULL; + for (i = 0; i < src_cnt; i++) + if (sba->max_pq_coefs <= raid6_gflog[scf[i]]) + slow = true; + + /* Figure-out P and Q destination addresses */ + if (!(flags & DMA_PREP_PQ_DISABLE_P)) + dst_p = &dst[0]; + if (!(flags & DMA_PREP_PQ_DISABLE_Q)) + dst_q = &dst[1]; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + if (slow) { + dst_q_index = src_cnt; + + if (dst_q) { + for (i = 0; i < src_cnt; i++) { + if (*dst_q == src[i]) { + dst_q_index = i; + break; + } + } + } + + if (dst_q_index < src_cnt) { + i = dst_q_index; + req = sba_prep_dma_pq_single_req(sba, + off, dst_p, dst_q, src[i], scf[i], + req_len, flags | DMA_PREP_FENCE); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + + flags |= DMA_PREP_CONTINUE; + } + + for (i = 0; i < src_cnt; i++) { + if (dst_q_index == i) + continue; + + req = sba_prep_dma_pq_single_req(sba, + off, dst_p, dst_q, src[i], scf[i], + req_len, flags | DMA_PREP_FENCE); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + + flags |= DMA_PREP_CONTINUE; + } + } else { + req = sba_prep_dma_pq_req(sba, off, + dst_p, dst_q, src, src_cnt, + scf, req_len, flags); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + } + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; + +fail: + if (first) + sba_free_chained_requests(first); + return NULL; +} + +/* ====== Mailbox callbacks ===== */ + +static void sba_dma_tx_actions(struct sba_request *req) +{ + struct dma_async_tx_descriptor *tx = &req->tx; + + WARN_ON(tx->cookie < 0); + + if (tx->cookie > 0) { + dma_cookie_complete(tx); + + /* + * Call the callback (must not sleep or submit new + * operations to this channel) + */ + if (tx->callback) + tx->callback(tx->callback_param); + + dma_descriptor_unmap(tx); + } + + /* Run dependent operations */ + dma_run_dependencies(tx); + + /* If waiting for 'ack' then move to completed list */ + if (!async_tx_test_ack(&req->tx)) + sba_complete_chained_requests(req); + else + sba_free_chained_requests(req); +} + +static void sba_receive_message(struct mbox_client *cl, void *msg) +{ + unsigned long flags; + struct brcm_message *m = msg; + struct sba_request *req = m->ctx, *req1; + struct sba_device *sba = req->sba; + + /* Error count if message has error */ + if (m->error < 0) + dev_err(sba->dev, "%s got message with error %d", + dma_chan_name(&sba->dma_chan), m->error); + + /* Mark request as received */ + sba_received_request(req); + + /* Wait for all chained requests to be completed */ + if (atomic_dec_return(&req->first->next_pending_count)) + goto done; + + /* Point to first request */ + req = req->first; + + /* Update request */ + if (req->state == SBA_REQUEST_STATE_RECEIVED) + sba_dma_tx_actions(req); + else + sba_free_chained_requests(req); + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Re-check all completed request waiting for 'ack' */ + list_for_each_entry_safe(req, req1, &sba->reqs_completed_list, node) { + spin_unlock_irqrestore(&sba->reqs_lock, flags); + sba_dma_tx_actions(req); + spin_lock_irqsave(&sba->reqs_lock, flags); + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); + +done: + /* Try to submit pending request */ + sba_issue_pending(&sba->dma_chan); +} + +/* ====== Platform driver routines ===== */ + +static int sba_prealloc_channel_resources(struct sba_device *sba) +{ + int i, j, p, ret = 0; + struct sba_request *req = NULL; + + sba->resp_base = dma_alloc_coherent(sba->dma_dev.dev, + sba->max_resp_pool_size, + &sba->resp_dma_base, GFP_KERNEL); + if (!sba->resp_base) + return -ENOMEM; + + sba->cmds_base = dma_alloc_coherent(sba->dma_dev.dev, + sba->max_cmds_pool_size, + &sba->cmds_dma_base, GFP_KERNEL); + if (!sba->cmds_base) { + ret = -ENOMEM; + goto fail_free_resp_pool; + } + + spin_lock_init(&sba->reqs_lock); + sba->reqs_fence = false; + INIT_LIST_HEAD(&sba->reqs_alloc_list); + INIT_LIST_HEAD(&sba->reqs_pending_list); + INIT_LIST_HEAD(&sba->reqs_active_list); + INIT_LIST_HEAD(&sba->reqs_received_list); + INIT_LIST_HEAD(&sba->reqs_completed_list); + INIT_LIST_HEAD(&sba->reqs_aborted_list); + INIT_LIST_HEAD(&sba->reqs_free_list); + + sba->reqs = devm_kcalloc(sba->dev, sba->max_req, + sizeof(*req), GFP_KERNEL); + if (!sba->reqs) { + ret = -ENOMEM; + goto fail_free_cmds_pool; + } + + for (i = 0, p = 0; i < sba->max_req; i++) { + req = &sba->reqs[i]; + INIT_LIST_HEAD(&req->node); + req->sba = sba; + req->state = SBA_REQUEST_STATE_FREE; + INIT_LIST_HEAD(&req->next); + req->next_count = 1; + atomic_set(&req->next_pending_count, 0); + req->fence = false; + req->resp = sba->resp_base + p; + req->resp_dma = sba->resp_dma_base + p; + p += sba->hw_resp_size; + req->cmds = devm_kcalloc(sba->dev, sba->max_cmd_per_req, + sizeof(*req->cmds), GFP_KERNEL); + if (!req->cmds) { + ret = -ENOMEM; + goto fail_free_cmds_pool; + } + for (j = 0; j < sba->max_cmd_per_req; j++) { + req->cmds[j].cmd = 0; + req->cmds[j].cmd_dma = sba->cmds_base + + (i * sba->max_cmd_per_req + j) * sizeof(u64); + req->cmds[j].cmd_dma_addr = sba->cmds_dma_base + + (i * sba->max_cmd_per_req + j) * sizeof(u64); + req->cmds[j].flags = 0; + } + memset(&req->msg, 0, sizeof(req->msg)); + dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan); + req->tx.tx_submit = sba_tx_submit; + req->tx.phys = req->resp_dma; + list_add_tail(&req->node, &sba->reqs_free_list); + } + + sba->reqs_free_count = sba->max_req; + + return 0; + +fail_free_cmds_pool: + dma_free_coherent(sba->dma_dev.dev, + sba->max_cmds_pool_size, + sba->cmds_base, sba->cmds_dma_base); +fail_free_resp_pool: + dma_free_coherent(sba->dma_dev.dev, + sba->max_resp_pool_size, + sba->resp_base, sba->resp_dma_base); + return ret; +} + +static void sba_freeup_channel_resources(struct sba_device *sba) +{ + dmaengine_terminate_all(&sba->dma_chan); + dma_free_coherent(sba->dma_dev.dev, sba->max_cmds_pool_size, + sba->cmds_base, sba->cmds_dma_base); + dma_free_coherent(sba->dma_dev.dev, sba->max_resp_pool_size, + sba->resp_base, sba->resp_dma_base); + sba->resp_base = NULL; + sba->resp_dma_base = 0; +} + +static int sba_async_register(struct sba_device *sba) +{ + int ret; + struct dma_device *dma_dev = &sba->dma_dev; + + /* Initialize DMA channel cookie */ + sba->dma_chan.device = dma_dev; + dma_cookie_init(&sba->dma_chan); + + /* Initialize DMA device capability mask */ + dma_cap_zero(dma_dev->cap_mask); + dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask); + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + dma_cap_set(DMA_XOR, dma_dev->cap_mask); + dma_cap_set(DMA_PQ, dma_dev->cap_mask); + + /* + * Set mailbox channel device as the base device of + * our dma_device because the actual memory accesses + * will be done by mailbox controller + */ + dma_dev->dev = sba->mbox_dev; + + /* Set base prep routines */ + dma_dev->device_free_chan_resources = sba_free_chan_resources; + dma_dev->device_terminate_all = sba_device_terminate_all; + dma_dev->device_issue_pending = sba_issue_pending; + dma_dev->device_tx_status = sba_tx_status; + + /* Set interrupt routine */ + if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask)) + dma_dev->device_prep_dma_interrupt = sba_prep_dma_interrupt; + + /* Set memcpy routine */ + if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) + dma_dev->device_prep_dma_memcpy = sba_prep_dma_memcpy; + + /* Set xor routine and capability */ + if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_xor = sba_prep_dma_xor; + dma_dev->max_xor = sba->max_xor_srcs; + } + + /* Set pq routine and capability */ + if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_pq = sba_prep_dma_pq; + dma_set_maxpq(dma_dev, sba->max_pq_srcs, 0); + } + + /* Initialize DMA device channel list */ + INIT_LIST_HEAD(&dma_dev->channels); + list_add_tail(&sba->dma_chan.device_node, &dma_dev->channels); + + /* Register with Linux async DMA framework*/ + ret = dma_async_device_register(dma_dev); + if (ret) { + dev_err(sba->dev, "async device register error %d", ret); + return ret; + } + + dev_info(sba->dev, "%s capabilities: %s%s%s%s\n", + dma_chan_name(&sba->dma_chan), + dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "interrupt " : "", + dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "memcpy " : "", + dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "", + dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : ""); + + return 0; +} + +static int sba_probe(struct platform_device *pdev) +{ + int i, ret = 0, mchans_count; + struct sba_device *sba; + struct platform_device *mbox_pdev; + struct of_phandle_args args; + + /* Allocate main SBA struct */ + sba = devm_kzalloc(&pdev->dev, sizeof(*sba), GFP_KERNEL); + if (!sba) + return -ENOMEM; + + sba->dev = &pdev->dev; + platform_set_drvdata(pdev, sba); + + /* Determine SBA version from DT compatible string */ + if (of_device_is_compatible(sba->dev->of_node, "brcm,iproc-sba")) + sba->ver = SBA_VER_1; + else if (of_device_is_compatible(sba->dev->of_node, + "brcm,iproc-sba-v2")) + sba->ver = SBA_VER_2; + else + return -ENODEV; + + /* Derived Configuration parameters */ + switch (sba->ver) { + case SBA_VER_1: + sba->max_req = 1024; + sba->hw_buf_size = 4096; + sba->hw_resp_size = 8; + sba->max_pq_coefs = 6; + sba->max_pq_srcs = 6; + break; + case SBA_VER_2: + sba->max_req = 1024; + sba->hw_buf_size = 4096; + sba->hw_resp_size = 8; + sba->max_pq_coefs = 30; + /* + * We can support max_pq_srcs == max_pq_coefs because + * we are limited by number of SBA commands that we can + * fit in one message for underlying ring manager HW. + */ + sba->max_pq_srcs = 12; + break; + default: + return -EINVAL; + } + sba->max_cmd_per_req = sba->max_pq_srcs + 3; + sba->max_xor_srcs = sba->max_cmd_per_req - 1; + sba->max_resp_pool_size = sba->max_req * sba->hw_resp_size; + sba->max_cmds_pool_size = sba->max_req * + sba->max_cmd_per_req * sizeof(u64); + + /* Setup mailbox client */ + sba->client.dev = &pdev->dev; + sba->client.rx_callback = sba_receive_message; + sba->client.tx_block = false; + sba->client.knows_txdone = false; + sba->client.tx_tout = 0; + + /* Number of channels equals number of mailbox channels */ + ret = of_count_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells"); + if (ret <= 0) + return -ENODEV; + mchans_count = ret; + sba->mchans_count = 0; + atomic_set(&sba->mchans_current, 0); + + /* Allocate mailbox channel array */ + sba->mchans = devm_kcalloc(&pdev->dev, sba->mchans_count, + sizeof(*sba->mchans), GFP_KERNEL); + if (!sba->mchans) + return -ENOMEM; + + /* Request mailbox channels */ + for (i = 0; i < mchans_count; i++) { + sba->mchans[i] = mbox_request_channel(&sba->client, i); + if (IS_ERR(sba->mchans[i])) { + ret = PTR_ERR(sba->mchans[i]); + goto fail_free_mchans; + } + sba->mchans_count++; + } + + /* Find-out underlying mailbox device */ + ret = of_parse_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells", 0, &args); + if (ret) + goto fail_free_mchans; + mbox_pdev = of_find_device_by_node(args.np); + of_node_put(args.np); + if (!mbox_pdev) { + ret = -ENODEV; + goto fail_free_mchans; + } + sba->mbox_dev = &mbox_pdev->dev; + + /* All mailbox channels should be of same ring manager device */ + for (i = 1; i < mchans_count; i++) { + ret = of_parse_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells", i, &args); + if (ret) + goto fail_free_mchans; + mbox_pdev = of_find_device_by_node(args.np); + of_node_put(args.np); + if (sba->mbox_dev != &mbox_pdev->dev) { + ret = -EINVAL; + goto fail_free_mchans; + } + } + + /* Register DMA device with linux async framework */ + ret = sba_async_register(sba); + if (ret) + goto fail_free_mchans; + + /* Prealloc channel resource */ + ret = sba_prealloc_channel_resources(sba); + if (ret) + goto fail_async_dev_unreg; + + /* Print device info */ + dev_info(sba->dev, "%s using SBAv%d and %d mailbox channels", + dma_chan_name(&sba->dma_chan), sba->ver+1, + sba->mchans_count); + + return 0; + +fail_async_dev_unreg: + dma_async_device_unregister(&sba->dma_dev); +fail_free_mchans: + for (i = 0; i < sba->mchans_count; i++) + mbox_free_channel(sba->mchans[i]); + return ret; +} + +static int sba_remove(struct platform_device *pdev) +{ + int i; + struct sba_device *sba = platform_get_drvdata(pdev); + + sba_freeup_channel_resources(sba); + + dma_async_device_unregister(&sba->dma_dev); + + for (i = 0; i < sba->mchans_count; i++) + mbox_free_channel(sba->mchans[i]); + + return 0; +} + +static const struct of_device_id sba_of_match[] = { + { .compatible = "brcm,iproc-sba", }, + { .compatible = "brcm,iproc-sba-v2", }, + {}, +}; +MODULE_DEVICE_TABLE(of, sba_of_match); + +static struct platform_driver sba_driver = { + .probe = sba_probe, + .remove = sba_remove, + .driver = { + .name = "bcm-sba-raid", + .of_match_table = sba_of_match, + }, +}; +module_platform_driver(sba_driver); + +MODULE_DESCRIPTION("Broadcom SBA RAID driver"); +MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index 5a37b9fcf40d..04b9728c1d26 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -6,17 +6,12 @@ config DW_DMAC_CORE tristate select DMA_ENGINE -config DW_DMAC_BIG_ENDIAN_IO - bool - config DW_DMAC tristate "Synopsys DesignWare AHB DMA platform driver" select DW_DMAC_CORE - select DW_DMAC_BIG_ENDIAN_IO if AVR32 - default y if CPU_AT32AP7000 help Support the Synopsys DesignWare AHB DMA controller. This - can be integrated in chips such as the Atmel AT32ap7000. + can be integrated in chips such as the Intel Cherrytrail. config DW_DMAC_PCI tristate "Synopsys DesignWare AHB DMA PCI driver" diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index e500950dad82..f43e6dafe446 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -561,92 +561,14 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc) dwc_descriptor_complete(dwc, bad_desc, true); } -/* --------------------- Cyclic DMA API extensions -------------------- */ - -dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - return channel_readl(dwc, SAR); -} -EXPORT_SYMBOL(dw_dma_get_src_addr); - -dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - return channel_readl(dwc, DAR); -} -EXPORT_SYMBOL(dw_dma_get_dst_addr); - -/* Called with dwc->lock held and all DMAC interrupts disabled */ -static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, - u32 status_block, u32 status_err, u32 status_xfer) -{ - unsigned long flags; - - if (status_block & dwc->mask) { - void (*callback)(void *param); - void *callback_param; - - dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n", - channel_readl(dwc, LLP)); - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - - callback = dwc->cdesc->period_callback; - callback_param = dwc->cdesc->period_callback_param; - - if (callback) - callback(callback_param); - } - - /* - * Error and transfer complete are highly unlikely, and will most - * likely be due to a configuration error by the user. - */ - if (unlikely(status_err & dwc->mask) || - unlikely(status_xfer & dwc->mask)) { - unsigned int i; - - dev_err(chan2dev(&dwc->chan), - "cyclic DMA unexpected %s interrupt, stopping DMA transfer\n", - status_xfer ? "xfer" : "error"); - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_dump_chan_regs(dwc); - - dwc_chan_disable(dw, dwc); - - /* Make sure DMA does not restart by loading a new list */ - channel_writel(dwc, LLP, 0); - channel_writel(dwc, CTL_LO, 0); - channel_writel(dwc, CTL_HI, 0); - - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - for (i = 0; i < dwc->cdesc->periods; i++) - dwc_dump_lli(dwc, dwc->cdesc->desc[i]); - - spin_unlock_irqrestore(&dwc->lock, flags); - } - - /* Re-enable interrupts */ - channel_set_bit(dw, MASK.BLOCK, dwc->mask); -} - -/* ------------------------------------------------------------------------- */ - static void dw_dma_tasklet(unsigned long data) { struct dw_dma *dw = (struct dw_dma *)data; struct dw_dma_chan *dwc; - u32 status_block; u32 status_xfer; u32 status_err; unsigned int i; - status_block = dma_readl(dw, RAW.BLOCK); status_xfer = dma_readl(dw, RAW.XFER); status_err = dma_readl(dw, RAW.ERROR); @@ -655,8 +577,7 @@ static void dw_dma_tasklet(unsigned long data) for (i = 0; i < dw->dma.chancnt; i++) { dwc = &dw->chan[i]; if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) - dwc_handle_cyclic(dw, dwc, status_block, status_err, - status_xfer); + dev_vdbg(dw->dma.dev, "Cyclic xfer is not implemented\n"); else if (status_err & (1 << i)) dwc_handle_error(dw, dwc); else if (status_xfer & (1 << i)) @@ -1264,255 +1185,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan) dev_vdbg(chan2dev(chan), "%s: done\n", __func__); } -/* --------------------- Cyclic DMA API extensions -------------------- */ - -/** - * dw_dma_cyclic_start - start the cyclic DMA transfer - * @chan: the DMA channel to start - * - * Must be called with soft interrupts disabled. Returns zero on success or - * -errno on failure. - */ -int dw_dma_cyclic_start(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(chan->device); - unsigned long flags; - - if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { - dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n"); - return -ENODEV; - } - - spin_lock_irqsave(&dwc->lock, flags); - - /* Enable interrupts to perform cyclic transfer */ - channel_set_bit(dw, MASK.BLOCK, dwc->mask); - - dwc_dostart(dwc, dwc->cdesc->desc[0]); - - spin_unlock_irqrestore(&dwc->lock, flags); - - return 0; -} -EXPORT_SYMBOL(dw_dma_cyclic_start); - -/** - * dw_dma_cyclic_stop - stop the cyclic DMA transfer - * @chan: the DMA channel to stop - * - * Must be called with soft interrupts disabled. - */ -void dw_dma_cyclic_stop(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - unsigned long flags; - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_chan_disable(dw, dwc); - - spin_unlock_irqrestore(&dwc->lock, flags); -} -EXPORT_SYMBOL(dw_dma_cyclic_stop); - -/** - * dw_dma_cyclic_prep - prepare the cyclic DMA transfer - * @chan: the DMA channel to prepare - * @buf_addr: physical DMA address where the buffer starts - * @buf_len: total number of bytes for the entire buffer - * @period_len: number of bytes for each period - * @direction: transfer direction, to or from device - * - * Must be called before trying to start the transfer. Returns a valid struct - * dw_cyclic_desc if successful or an ERR_PTR(-errno) if not successful. - */ -struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, - dma_addr_t buf_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dma_slave_config *sconfig = &dwc->dma_sconfig; - struct dw_cyclic_desc *cdesc; - struct dw_cyclic_desc *retval = NULL; - struct dw_desc *desc; - struct dw_desc *last = NULL; - u8 lms = DWC_LLP_LMS(dwc->dws.m_master); - unsigned long was_cyclic; - unsigned int reg_width; - unsigned int periods; - unsigned int i; - unsigned long flags; - - spin_lock_irqsave(&dwc->lock, flags); - if (dwc->nollp) { - spin_unlock_irqrestore(&dwc->lock, flags); - dev_dbg(chan2dev(&dwc->chan), - "channel doesn't support LLP transfers\n"); - return ERR_PTR(-EINVAL); - } - - if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) { - spin_unlock_irqrestore(&dwc->lock, flags); - dev_dbg(chan2dev(&dwc->chan), - "queue and/or active list are not empty\n"); - return ERR_PTR(-EBUSY); - } - - was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags); - spin_unlock_irqrestore(&dwc->lock, flags); - if (was_cyclic) { - dev_dbg(chan2dev(&dwc->chan), - "channel already prepared for cyclic DMA\n"); - return ERR_PTR(-EBUSY); - } - - retval = ERR_PTR(-EINVAL); - - if (unlikely(!is_slave_direction(direction))) - goto out_err; - - dwc->direction = direction; - - if (direction == DMA_MEM_TO_DEV) - reg_width = __ffs(sconfig->dst_addr_width); - else - reg_width = __ffs(sconfig->src_addr_width); - - periods = buf_len / period_len; - - /* Check for too big/unaligned periods and unaligned DMA buffer. */ - if (period_len > (dwc->block_size << reg_width)) - goto out_err; - if (unlikely(period_len & ((1 << reg_width) - 1))) - goto out_err; - if (unlikely(buf_addr & ((1 << reg_width) - 1))) - goto out_err; - - retval = ERR_PTR(-ENOMEM); - - cdesc = kzalloc(sizeof(struct dw_cyclic_desc), GFP_KERNEL); - if (!cdesc) - goto out_err; - - cdesc->desc = kzalloc(sizeof(struct dw_desc *) * periods, GFP_KERNEL); - if (!cdesc->desc) - goto out_err_alloc; - - for (i = 0; i < periods; i++) { - desc = dwc_desc_get(dwc); - if (!desc) - goto out_err_desc_get; - - switch (direction) { - case DMA_MEM_TO_DEV: - lli_write(desc, dar, sconfig->dst_addr); - lli_write(desc, sar, buf_addr + period_len * i); - lli_write(desc, ctllo, (DWC_DEFAULT_CTLLO(chan) - | DWC_CTLL_DST_WIDTH(reg_width) - | DWC_CTLL_SRC_WIDTH(reg_width) - | DWC_CTLL_DST_FIX - | DWC_CTLL_SRC_INC - | DWC_CTLL_INT_EN)); - - lli_set(desc, ctllo, sconfig->device_fc ? - DWC_CTLL_FC(DW_DMA_FC_P_M2P) : - DWC_CTLL_FC(DW_DMA_FC_D_M2P)); - - break; - case DMA_DEV_TO_MEM: - lli_write(desc, dar, buf_addr + period_len * i); - lli_write(desc, sar, sconfig->src_addr); - lli_write(desc, ctllo, (DWC_DEFAULT_CTLLO(chan) - | DWC_CTLL_SRC_WIDTH(reg_width) - | DWC_CTLL_DST_WIDTH(reg_width) - | DWC_CTLL_DST_INC - | DWC_CTLL_SRC_FIX - | DWC_CTLL_INT_EN)); - - lli_set(desc, ctllo, sconfig->device_fc ? - DWC_CTLL_FC(DW_DMA_FC_P_P2M) : - DWC_CTLL_FC(DW_DMA_FC_D_P2M)); - - break; - default: - break; - } - - lli_write(desc, ctlhi, period_len >> reg_width); - cdesc->desc[i] = desc; - - if (last) - lli_write(last, llp, desc->txd.phys | lms); - - last = desc; - } - - /* Let's make a cyclic list */ - lli_write(last, llp, cdesc->desc[0]->txd.phys | lms); - - dev_dbg(chan2dev(&dwc->chan), - "cyclic prepared buf %pad len %zu period %zu periods %d\n", - &buf_addr, buf_len, period_len, periods); - - cdesc->periods = periods; - dwc->cdesc = cdesc; - - return cdesc; - -out_err_desc_get: - while (i--) - dwc_desc_put(dwc, cdesc->desc[i]); -out_err_alloc: - kfree(cdesc); -out_err: - clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); - return (struct dw_cyclic_desc *)retval; -} -EXPORT_SYMBOL(dw_dma_cyclic_prep); - -/** - * dw_dma_cyclic_free - free a prepared cyclic DMA transfer - * @chan: the DMA channel to free - */ -void dw_dma_cyclic_free(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - struct dw_cyclic_desc *cdesc = dwc->cdesc; - unsigned int i; - unsigned long flags; - - dev_dbg(chan2dev(&dwc->chan), "%s\n", __func__); - - if (!cdesc) - return; - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_chan_disable(dw, dwc); - - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - spin_unlock_irqrestore(&dwc->lock, flags); - - for (i = 0; i < cdesc->periods; i++) - dwc_desc_put(dwc, cdesc->desc[i]); - - kfree(cdesc->desc); - kfree(cdesc); - - dwc->cdesc = NULL; - - clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); -} -EXPORT_SYMBOL(dw_dma_cyclic_free); - -/*----------------------------------------------------------------------*/ - int dw_dma_probe(struct dw_dma_chip *chip) { struct dw_dma_platform_data *pdata; @@ -1642,7 +1314,7 @@ int dw_dma_probe(struct dw_dma_chip *chip) if (autocfg) { unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1; void __iomem *addr = &__dw_regs(dw)->DWC_PARAMS[r]; - unsigned int dwc_params = dma_readl_native(addr); + unsigned int dwc_params = readl(addr); dev_dbg(chip->dev, "DWC_PARAMS[%d]: 0x%08x\n", i, dwc_params); diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index c639c60b825a..bc31fe802061 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -306,8 +306,12 @@ static int dw_resume_early(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct dw_dma_chip *chip = platform_get_drvdata(pdev); + int ret; + + ret = clk_prepare_enable(chip->clk); + if (ret) + return ret; - clk_prepare_enable(chip->clk); return dw_dma_enable(chip); } diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h index 32a328721c88..09e7dfdbb790 100644 --- a/drivers/dma/dw/regs.h +++ b/drivers/dma/dw/regs.h @@ -116,20 +116,6 @@ struct dw_dma_regs { DW_REG(GLOBAL_CFG); }; -/* - * Big endian I/O access when reading and writing to the DMA controller - * registers. This is needed on some platforms, like the Atmel AVR32 - * architecture. - */ - -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -#define dma_readl_native ioread32be -#define dma_writel_native iowrite32be -#else -#define dma_readl_native readl -#define dma_writel_native writel -#endif - /* Bitfields in DW_PARAMS */ #define DW_PARAMS_NR_CHAN 8 /* number of channels */ #define DW_PARAMS_NR_MASTER 11 /* number of AHB masters */ @@ -280,7 +266,6 @@ struct dw_dma_chan { unsigned long flags; struct list_head active_list; struct list_head queue; - struct dw_cyclic_desc *cdesc; unsigned int descs_allocated; @@ -302,9 +287,9 @@ __dwc_regs(struct dw_dma_chan *dwc) } #define channel_readl(dwc, name) \ - dma_readl_native(&(__dwc_regs(dwc)->name)) + readl(&(__dwc_regs(dwc)->name)) #define channel_writel(dwc, name, val) \ - dma_writel_native((val), &(__dwc_regs(dwc)->name)) + writel((val), &(__dwc_regs(dwc)->name)) static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan) { @@ -333,9 +318,9 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw) } #define dma_readl(dw, name) \ - dma_readl_native(&(__dw_regs(dw)->name)) + readl(&(__dw_regs(dw)->name)) #define dma_writel(dw, name, val) \ - dma_writel_native((val), &(__dw_regs(dw)->name)) + writel((val), &(__dw_regs(dw)->name)) #define idma32_readq(dw, name) \ hi_lo_readq(&(__dw_regs(dw)->name)) @@ -352,43 +337,30 @@ static inline struct dw_dma *to_dw_dma(struct dma_device *ddev) return container_of(ddev, struct dw_dma, dma); } -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -typedef __be32 __dw32; -#else -typedef __le32 __dw32; -#endif - /* LLI == Linked List Item; a.k.a. DMA block descriptor */ struct dw_lli { /* values that are not changed by hardware */ - __dw32 sar; - __dw32 dar; - __dw32 llp; /* chain to next lli */ - __dw32 ctllo; + __le32 sar; + __le32 dar; + __le32 llp; /* chain to next lli */ + __le32 ctllo; /* values that may get written back: */ - __dw32 ctlhi; + __le32 ctlhi; /* sstat and dstat can snapshot peripheral register state. * silicon config may discard either or both... */ - __dw32 sstat; - __dw32 dstat; + __le32 sstat; + __le32 dstat; }; struct dw_desc { /* FIRST values the hardware uses */ struct dw_lli lli; -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -#define lli_set(d, reg, v) ((d)->lli.reg |= cpu_to_be32(v)) -#define lli_clear(d, reg, v) ((d)->lli.reg &= ~cpu_to_be32(v)) -#define lli_read(d, reg) be32_to_cpu((d)->lli.reg) -#define lli_write(d, reg, v) ((d)->lli.reg = cpu_to_be32(v)) -#else #define lli_set(d, reg, v) ((d)->lli.reg |= cpu_to_le32(v)) #define lli_clear(d, reg, v) ((d)->lli.reg &= ~cpu_to_le32(v)) #define lli_read(d, reg) le32_to_cpu((d)->lli.reg) #define lli_write(d, reg, v) ((d)->lli.reg = cpu_to_le32(v)) -#endif /* THEN values for driver housekeeping */ struct list_head desc_node; diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c index 90d29f90acfb..493dc6c59d1d 100644 --- a/drivers/dma/fsl_raid.c +++ b/drivers/dma/fsl_raid.c @@ -877,7 +877,7 @@ static int fsl_re_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id fsl_re_ids[] = { +static const struct of_device_id fsl_re_ids[] = { { .compatible = "fsl,raideng-v1.0", }, {} }; diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 51c75bf2b9b6..3b8b752ede2d 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -269,6 +269,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size) case 2: case 4: case 8: + mode &= ~FSL_DMA_MR_SAHTS_MASK; mode |= FSL_DMA_MR_SAHE | (__ilog2(size) << 14); break; } @@ -301,6 +302,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size) case 2: case 4: case 8: + mode &= ~FSL_DMA_MR_DAHTS_MASK; mode |= FSL_DMA_MR_DAHE | (__ilog2(size) << 16); break; } @@ -327,7 +329,8 @@ static void fsl_chan_set_request_count(struct fsldma_chan *chan, int size) BUG_ON(size > 1024); mode = get_mr(chan); - mode |= (__ilog2(size) << 24) & 0x0f000000; + mode &= ~FSL_DMA_MR_BWC_MASK; + mode |= (__ilog2(size) << 24) & FSL_DMA_MR_BWC_MASK; set_mr(chan, mode); } diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index 31bffccdcc75..4787d485dd76 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -36,6 +36,10 @@ #define FSL_DMA_MR_DAHE 0x00002000 #define FSL_DMA_MR_SAHE 0x00001000 +#define FSL_DMA_MR_SAHTS_MASK 0x0000C000 +#define FSL_DMA_MR_DAHTS_MASK 0x00030000 +#define FSL_DMA_MR_BWC_MASK 0x0f000000 + /* * Bandwidth/pause control determines how many bytes a given * channel is allowed to transfer before the DMA engine pauses diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index ab0fb804fb1e..f681df8f0ed3 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -888,7 +888,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic( sg_init_table(imxdmac->sg_list, periods); for (i = 0; i < periods; i++) { - imxdmac->sg_list[i].page_link = 0; + sg_assign_page(&imxdmac->sg_list[i], NULL); imxdmac->sg_list[i].offset = 0; imxdmac->sg_list[i].dma_address = dma_addr; sg_dma_len(&imxdmac->sg_list[i]) = period_len; @@ -896,10 +896,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic( } /* close the loop */ - imxdmac->sg_list[periods].offset = 0; - sg_dma_len(&imxdmac->sg_list[periods]) = 0; - imxdmac->sg_list[periods].page_link = - ((unsigned long)imxdmac->sg_list | 0x01) & ~0x02; + sg_chain(imxdmac->sg_list, periods + 1, imxdmac->sg_list); desc->type = IMXDMA_DESC_CYCLIC; desc->sg = imxdmac->sg_list; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 085993cb2ccc..a67ec1bdc4e0 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1323,7 +1323,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( } if (period_len > 0xffff) { - dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %d > %d\n", + dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %zu > %d\n", channel, period_len, 0xffff); goto err_out; } @@ -1347,7 +1347,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( if (i + 1 == num_periods) param |= BD_WRAP; - dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n", + dev_dbg(sdma->dev, "entry %d: count: %zu dma: %#llx %s%s\n", i, period_len, (u64)dma_addr, param & BD_WRAP ? "wrap" : "", param & BD_INTR ? " intr" : ""); @@ -1755,19 +1755,26 @@ static int sdma_probe(struct platform_device *pdev) if (IS_ERR(sdma->clk_ahb)) return PTR_ERR(sdma->clk_ahb); - clk_prepare(sdma->clk_ipg); - clk_prepare(sdma->clk_ahb); + ret = clk_prepare(sdma->clk_ipg); + if (ret) + return ret; + + ret = clk_prepare(sdma->clk_ahb); + if (ret) + goto err_clk; ret = devm_request_irq(&pdev->dev, irq, sdma_int_handler, 0, "sdma", sdma); if (ret) - return ret; + goto err_irq; sdma->irq = irq; sdma->script_addrs = kzalloc(sizeof(*sdma->script_addrs), GFP_KERNEL); - if (!sdma->script_addrs) - return -ENOMEM; + if (!sdma->script_addrs) { + ret = -ENOMEM; + goto err_irq; + } /* initially no scripts available */ saddr_arr = (s32 *)sdma->script_addrs; @@ -1882,6 +1889,10 @@ err_register: dma_async_device_unregister(&sdma->dma_device); err_init: kfree(sdma->script_addrs); +err_irq: + clk_unprepare(sdma->clk_ahb); +err_clk: + clk_unprepare(sdma->clk_ipg); return ret; } @@ -1893,6 +1904,8 @@ static int sdma_remove(struct platform_device *pdev) devm_free_irq(&pdev->dev, sdma->irq, sdma); dma_async_device_unregister(&sdma->dma_device); kfree(sdma->script_addrs); + clk_unprepare(sdma->clk_ahb); + clk_unprepare(sdma->clk_ipg); /* Kill the tasklet */ for (i = 0; i < MAX_DMA_CHANNELS; i++) { struct sdma_channel *sdmac = &sdma->channel[i]; diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 0b9b6b07db9e..eab2fdda29ec 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -336,10 +336,10 @@ struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase) } if (dca3_tag_map_invalid(ioatdca->tag_map)) { - WARN_TAINT_ONCE(1, TAINT_FIRMWARE_WORKAROUND, - "%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n", - dev_driver_string(&pdev->dev), - dev_name(&pdev->dev)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + pr_warn_once("%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n", + dev_driver_string(&pdev->dev), + dev_name(&pdev->dev)); free_dca_provider(dca); return NULL; } diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c index 5072a7d306d4..34fb6afd229b 100644 --- a/drivers/dma/qcom/hidma.c +++ b/drivers/dma/qcom/hidma.c @@ -1,7 +1,7 @@ /* * Qualcomm Technologies HIDMA DMA engine interface * - * Copyright (c) 2015-2016, The Linux Foundation. All rights reserved. + * Copyright (c) 2015-2017, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -210,6 +210,7 @@ static int hidma_chan_init(struct hidma_dev *dmadev, u32 dma_sig) INIT_LIST_HEAD(&mchan->prepared); INIT_LIST_HEAD(&mchan->active); INIT_LIST_HEAD(&mchan->completed); + INIT_LIST_HEAD(&mchan->queued); spin_lock_init(&mchan->lock); list_add_tail(&mchan->chan.device_node, &ddev->channels); @@ -230,9 +231,15 @@ static void hidma_issue_pending(struct dma_chan *dmach) struct hidma_chan *mchan = to_hidma_chan(dmach); struct hidma_dev *dmadev = mchan->dmadev; unsigned long flags; + struct hidma_desc *qdesc, *next; int status; spin_lock_irqsave(&mchan->lock, flags); + list_for_each_entry_safe(qdesc, next, &mchan->queued, node) { + hidma_ll_queue_request(dmadev->lldev, qdesc->tre_ch); + list_move_tail(&qdesc->node, &mchan->active); + } + if (!mchan->running) { struct hidma_desc *desc = list_first_entry(&mchan->active, struct hidma_desc, @@ -315,17 +322,18 @@ static dma_cookie_t hidma_tx_submit(struct dma_async_tx_descriptor *txd) pm_runtime_put_autosuspend(dmadev->ddev.dev); return -ENODEV; } + pm_runtime_mark_last_busy(dmadev->ddev.dev); + pm_runtime_put_autosuspend(dmadev->ddev.dev); mdesc = container_of(txd, struct hidma_desc, desc); spin_lock_irqsave(&mchan->lock, irqflags); - /* Move descriptor to active */ - list_move_tail(&mdesc->node, &mchan->active); + /* Move descriptor to queued */ + list_move_tail(&mdesc->node, &mchan->queued); /* Update cookie */ cookie = dma_cookie_assign(txd); - hidma_ll_queue_request(dmadev->lldev, mdesc->tre_ch); spin_unlock_irqrestore(&mchan->lock, irqflags); return cookie; @@ -431,6 +439,7 @@ static int hidma_terminate_channel(struct dma_chan *chan) list_splice_init(&mchan->active, &list); list_splice_init(&mchan->prepared, &list); list_splice_init(&mchan->completed, &list); + list_splice_init(&mchan->queued, &list); spin_unlock_irqrestore(&mchan->lock, irqflags); /* this suspends the existing transfer */ @@ -795,8 +804,11 @@ static int hidma_probe(struct platform_device *pdev) device_property_read_u32(&pdev->dev, "desc-count", &dmadev->nr_descriptors); - if (!dmadev->nr_descriptors && nr_desc_prm) + if (nr_desc_prm) { + dev_info(&pdev->dev, "overriding number of descriptors as %d\n", + nr_desc_prm); dmadev->nr_descriptors = nr_desc_prm; + } if (!dmadev->nr_descriptors) dmadev->nr_descriptors = HIDMA_NR_DEFAULT_DESC; diff --git a/drivers/dma/qcom/hidma.h b/drivers/dma/qcom/hidma.h index c7d014235c32..41e0aa283828 100644 --- a/drivers/dma/qcom/hidma.h +++ b/drivers/dma/qcom/hidma.h @@ -104,6 +104,7 @@ struct hidma_chan { struct dma_chan chan; struct list_head free; struct list_head prepared; + struct list_head queued; struct list_head active; struct list_head completed; diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c index f847d32cc4b5..5a0991bc4787 100644 --- a/drivers/dma/qcom/hidma_mgmt.c +++ b/drivers/dma/qcom/hidma_mgmt.c @@ -1,7 +1,7 @@ /* * Qualcomm Technologies HIDMA DMA engine Management interface * - * Copyright (c) 2015-2016, The Linux Foundation. All rights reserved. + * Copyright (c) 2015-2017, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -49,6 +49,26 @@ #define HIDMA_AUTOSUSPEND_TIMEOUT 2000 #define HIDMA_MAX_CHANNEL_WEIGHT 15 +static unsigned int max_write_request; +module_param(max_write_request, uint, 0644); +MODULE_PARM_DESC(max_write_request, + "maximum write burst (default: ACPI/DT value)"); + +static unsigned int max_read_request; +module_param(max_read_request, uint, 0644); +MODULE_PARM_DESC(max_read_request, + "maximum read burst (default: ACPI/DT value)"); + +static unsigned int max_wr_xactions; +module_param(max_wr_xactions, uint, 0644); +MODULE_PARM_DESC(max_wr_xactions, + "maximum number of write transactions (default: ACPI/DT value)"); + +static unsigned int max_rd_xactions; +module_param(max_rd_xactions, uint, 0644); +MODULE_PARM_DESC(max_rd_xactions, + "maximum number of read transactions (default: ACPI/DT value)"); + int hidma_mgmt_setup(struct hidma_mgmt_dev *mgmtdev) { unsigned int i; @@ -207,12 +227,25 @@ static int hidma_mgmt_probe(struct platform_device *pdev) goto out; } + if (max_write_request) { + dev_info(&pdev->dev, "overriding max-write-burst-bytes: %d\n", + max_write_request); + mgmtdev->max_write_request = max_write_request; + } else + max_write_request = mgmtdev->max_write_request; + rc = device_property_read_u32(&pdev->dev, "max-read-burst-bytes", &mgmtdev->max_read_request); if (rc) { dev_err(&pdev->dev, "max-read-burst-bytes missing\n"); goto out; } + if (max_read_request) { + dev_info(&pdev->dev, "overriding max-read-burst-bytes: %d\n", + max_read_request); + mgmtdev->max_read_request = max_read_request; + } else + max_read_request = mgmtdev->max_read_request; rc = device_property_read_u32(&pdev->dev, "max-write-transactions", &mgmtdev->max_wr_xactions); @@ -220,6 +253,12 @@ static int hidma_mgmt_probe(struct platform_device *pdev) dev_err(&pdev->dev, "max-write-transactions missing\n"); goto out; } + if (max_wr_xactions) { + dev_info(&pdev->dev, "overriding max-write-transactions: %d\n", + max_wr_xactions); + mgmtdev->max_wr_xactions = max_wr_xactions; + } else + max_wr_xactions = mgmtdev->max_wr_xactions; rc = device_property_read_u32(&pdev->dev, "max-read-transactions", &mgmtdev->max_rd_xactions); @@ -227,6 +266,12 @@ static int hidma_mgmt_probe(struct platform_device *pdev) dev_err(&pdev->dev, "max-read-transactions missing\n"); goto out; } + if (max_rd_xactions) { + dev_info(&pdev->dev, "overriding max-read-transactions: %d\n", + max_rd_xactions); + mgmtdev->max_rd_xactions = max_rd_xactions; + } else + max_rd_xactions = mgmtdev->max_rd_xactions; mgmtdev->priority = devm_kcalloc(&pdev->dev, mgmtdev->dma_channels, diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index a6620b671d1d..c3052fbfd092 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -2528,10 +2528,7 @@ dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr, dma_addr += period_len; } - sg[periods].offset = 0; - sg_dma_len(&sg[periods]) = 0; - sg[periods].page_link = - ((unsigned long)sg | 0x01) & ~0x02; + sg_chain(sg, periods + 1, sg); txd = d40_prep_sg(chan, sg, sg, periods, direction, DMA_PREP_INTERRUPT); diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 3722b9d8d9fe..b9d75a54c896 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -1494,35 +1494,7 @@ static int tegra_dma_remove(struct platform_device *pdev) static int tegra_dma_runtime_suspend(struct device *dev) { struct tegra_dma *tdma = dev_get_drvdata(dev); - - clk_disable_unprepare(tdma->dma_clk); - return 0; -} - -static int tegra_dma_runtime_resume(struct device *dev) -{ - struct tegra_dma *tdma = dev_get_drvdata(dev); - int ret; - - ret = clk_prepare_enable(tdma->dma_clk); - if (ret < 0) { - dev_err(dev, "clk_enable failed: %d\n", ret); - return ret; - } - return 0; -} - -#ifdef CONFIG_PM_SLEEP -static int tegra_dma_pm_suspend(struct device *dev) -{ - struct tegra_dma *tdma = dev_get_drvdata(dev); int i; - int ret; - - /* Enable clock before accessing register */ - ret = pm_runtime_get_sync(dev); - if (ret < 0) - return ret; tdma->reg_gen = tdma_read(tdma, TEGRA_APBDMA_GENERAL); for (i = 0; i < tdma->chip_data->nr_channels; i++) { @@ -1543,21 +1515,21 @@ static int tegra_dma_pm_suspend(struct device *dev) TEGRA_APBDMA_CHAN_WCOUNT); } - /* Disable clock */ - pm_runtime_put(dev); + clk_disable_unprepare(tdma->dma_clk); + return 0; } -static int tegra_dma_pm_resume(struct device *dev) +static int tegra_dma_runtime_resume(struct device *dev) { struct tegra_dma *tdma = dev_get_drvdata(dev); - int i; - int ret; + int i, ret; - /* Enable clock before accessing register */ - ret = pm_runtime_get_sync(dev); - if (ret < 0) + ret = clk_prepare_enable(tdma->dma_clk); + if (ret < 0) { + dev_err(dev, "clk_enable failed: %d\n", ret); return ret; + } tdma_write(tdma, TEGRA_APBDMA_GENERAL, tdma->reg_gen); tdma_write(tdma, TEGRA_APBDMA_CONTROL, 0); @@ -1582,16 +1554,14 @@ static int tegra_dma_pm_resume(struct device *dev) (ch_reg->csr & ~TEGRA_APBDMA_CSR_ENB)); } - /* Disable clock */ - pm_runtime_put(dev); return 0; } -#endif static const struct dev_pm_ops tegra_dma_dev_pm_ops = { SET_RUNTIME_PM_OPS(tegra_dma_runtime_suspend, tegra_dma_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(tegra_dma_pm_suspend, tegra_dma_pm_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static const struct of_device_id tegra_dma_of_match[] = { diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index 6d221e5c72ee..47f64192d2fd 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -794,9 +794,6 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy( chan = to_chan(dchan); - if (len > ZYNQMP_DMA_MAX_TRANS_LEN) - return NULL; - desc_cnt = DIV_ROUND_UP(len, ZYNQMP_DMA_MAX_TRANS_LEN); spin_lock_bh(&chan->lock); |