提交 a487b670 编写于 作者: L Linus Torvalds

Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (97 commits)
  md: raid-1/10: fix RW bits manipulation
  md: remove unnecessary memset from multipath.
  md: report device as congested when suspended
  md: Improve name of threads created by md_register_thread
  md: remove sparse warnings about lock context.
  md: remove sparse waring "symbol xxx shadows an earlier one"
  async_tx/raid6: add missing dma_unmap calls to the async fail case
  ioat3: fix uninitialized var warnings
  drivers/dma/ioat/dma_v2.c: fix warnings
  raid6test: fix stack overflow
  ioat2: clarify ring size limits
  md/raid6: cleanup ops_run_compute6_2
  md/raid6: eliminate BUG_ON with side effect
  dca: module load should not be an error message
  ioat: driver version 4.0
  dca: registering requesters in multiple dca domains
  async_tx: remove HIGHMEM64G restriction
  dmaengine: sh: Add Support SuperH DMA Engine driver
  dmaengine: Move all map_sg/unmap_sg for slave channel to its client
  fsldma: Add DMA_SLAVE support
  ...
......@@ -54,20 +54,23 @@ features surfaced as a result:
3.1 General format of the API:
struct dma_async_tx_descriptor *
async_<operation>(<op specific parameters>,
enum async_tx_flags flags,
struct dma_async_tx_descriptor *dependency,
dma_async_tx_callback callback_routine,
void *callback_parameter);
async_<operation>(<op specific parameters>, struct async_submit ctl *submit)
3.2 Supported operations:
memcpy - memory copy between a source and a destination buffer
memset - fill a destination buffer with a byte value
xor - xor a series of source buffers and write the result to a
destination buffer
xor_zero_sum - xor a series of source buffers and set a flag if the
result is zero. The implementation attempts to prevent
writes to memory
memcpy - memory copy between a source and a destination buffer
memset - fill a destination buffer with a byte value
xor - xor a series of source buffers and write the result to a
destination buffer
xor_val - xor a series of source buffers and set a flag if the
result is zero. The implementation attempts to prevent
writes to memory
pq - generate the p+q (raid6 syndrome) from a series of source buffers
pq_val - validate that a p and or q buffer are in sync with a given series of
sources
datap - (raid6_datap_recov) recover a raid6 data block and the p block
from the given sources
2data - (raid6_2data_recov) recover 2 raid6 data blocks from the given
sources
3.3 Descriptor management:
The return value is non-NULL and points to a 'descriptor' when the operation
......@@ -80,8 +83,8 @@ acknowledged by the application before the offload engine driver is allowed to
recycle (or free) the descriptor. A descriptor can be acked by one of the
following methods:
1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted
2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent
descriptor of a new operation.
2/ submitting an unacknowledged descriptor as a dependency to another
async_tx call will implicitly set the acknowledged state.
3/ calling async_tx_ack() on the descriptor.
3.4 When does the operation execute?
......@@ -119,30 +122,42 @@ of an operation.
Perform a xor->copy->xor operation where each operation depends on the
result from the previous operation:
void complete_xor_copy_xor(void *param)
void callback(void *param)
{
printk("complete\n");
struct completion *cmp = param;
complete(cmp);
}
int run_xor_copy_xor(struct page **xor_srcs,
int xor_src_cnt,
struct page *xor_dest,
size_t xor_len,
struct page *copy_src,
struct page *copy_dest,
size_t copy_len)
void run_xor_copy_xor(struct page **xor_srcs,
int xor_src_cnt,
struct page *xor_dest,
size_t xor_len,
struct page *copy_src,
struct page *copy_dest,
size_t copy_len)
{
struct dma_async_tx_descriptor *tx;
addr_conv_t addr_conv[xor_src_cnt];
struct async_submit_ctl submit;
addr_conv_t addr_conv[NDISKS];
struct completion cmp;
init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL,
addr_conv);
tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit)
tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL);
tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len,
ASYNC_TX_DEP_ACK, tx, NULL, NULL);
tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK,
tx, complete_xor_copy_xor, NULL);
submit->depend_tx = tx;
tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, &submit);
init_completion(&cmp);
init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx,
callback, &cmp, addr_conv);
tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit);
async_tx_issue_pending_all();
wait_for_completion(&cmp);
}
See include/linux/async_tx.h for more information on the flags. See the
......
......@@ -187,11 +187,74 @@ union iop3xx_desc {
void *ptr;
};
/* No support for p+q operations */
static inline int
iop_chan_pq_slot_count(size_t len, int src_cnt, int *slots_per_op)
{
BUG();
return 0;
}
static inline void
iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
unsigned long flags)
{
BUG();
}
static inline void
iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
{
BUG();
}
static inline void
iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
dma_addr_t addr, unsigned char coef)
{
BUG();
}
static inline int
iop_chan_pq_zero_sum_slot_count(size_t len, int src_cnt, int *slots_per_op)
{
BUG();
return 0;
}
static inline void
iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
unsigned long flags)
{
BUG();
}
static inline void
iop_desc_set_pq_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
{
BUG();
}
#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
static inline void
iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
dma_addr_t *src)
{
BUG();
}
static inline int iop_adma_get_max_xor(void)
{
return 32;
}
static inline int iop_adma_get_max_pq(void)
{
BUG();
return 0;
}
static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
{
int id = chan->device->id;
......@@ -332,6 +395,11 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
return slot_cnt;
}
static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
{
return 0;
}
static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
{
......@@ -349,6 +417,14 @@ static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
return 0;
}
static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
{
BUG();
return 0;
}
static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
{
......@@ -756,13 +832,14 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
hw_desc->src[0] = val;
}
static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
static inline enum sum_check_flags
iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
{
struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
struct iop3xx_aau_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
iop_paranoia(!(desc_ctrl.tx_complete && desc_ctrl.zero_result_en));
return desc_ctrl.zero_result_err;
return desc_ctrl.zero_result_err << SUM_CHECK_P;
}
static inline void iop_chan_append(struct iop_adma_chan *chan)
......
......@@ -86,6 +86,7 @@ struct iop_adma_chan {
* @idx: pool index
* @unmap_src_cnt: number of xor sources
* @unmap_len: transaction bytecount
* @tx_list: list of descriptors that are associated with one operation
* @async_tx: support for the async_tx api
* @group_list: list of slots that make up a multi-descriptor transaction
* for example transfer lengths larger than the supported hw max
......@@ -102,10 +103,12 @@ struct iop_adma_desc_slot {
u16 idx;
u16 unmap_src_cnt;
size_t unmap_len;
struct list_head tx_list;
struct dma_async_tx_descriptor async_tx;
union {
u32 *xor_check_result;
u32 *crc32_result;
u32 *pq_check_result;
};
};
......
......@@ -150,6 +150,8 @@ static inline int iop_adma_get_max_xor(void)
return 16;
}
#define iop_adma_get_max_pq iop_adma_get_max_xor
static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
{
return __raw_readl(ADMA_ADAR(chan));
......@@ -211,7 +213,10 @@ iop_chan_xor_slot_count(size_t len, int src_cnt, int *slots_per_op)
#define IOP_ADMA_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
#define IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
#define IOP_ADMA_XOR_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
#define IOP_ADMA_PQ_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
#define iop_chan_zero_sum_slot_count(l, s, o) iop_chan_xor_slot_count(l, s, o)
#define iop_chan_pq_slot_count iop_chan_xor_slot_count
#define iop_chan_pq_zero_sum_slot_count iop_chan_xor_slot_count
static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
......@@ -220,6 +225,13 @@ static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
return hw_desc->dest_addr;
}
static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
return hw_desc->q_dest_addr;
}
static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
{
......@@ -319,6 +331,58 @@ iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
return 1;
}
static inline void
iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
unsigned long flags)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
union {
u32 value;
struct iop13xx_adma_desc_ctrl field;
} u_desc_ctrl;
u_desc_ctrl.value = 0;
u_desc_ctrl.field.src_select = src_cnt - 1;
u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
u_desc_ctrl.field.pq_xfer_en = 1;
u_desc_ctrl.field.p_xfer_dis = !!(flags & DMA_PREP_PQ_DISABLE_P);
u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
hw_desc->desc_ctrl = u_desc_ctrl.value;
}
static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
union {
u32 value;
struct iop13xx_adma_desc_ctrl field;
} u_desc_ctrl;
u_desc_ctrl.value = hw_desc->desc_ctrl;
return u_desc_ctrl.field.pq_xfer_en;
}
static inline void
iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
unsigned long flags)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
union {
u32 value;
struct iop13xx_adma_desc_ctrl field;
} u_desc_ctrl;
u_desc_ctrl.value = 0;
u_desc_ctrl.field.src_select = src_cnt - 1;
u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
u_desc_ctrl.field.zero_result = 1;
u_desc_ctrl.field.status_write_back_en = 1;
u_desc_ctrl.field.pq_xfer_en = 1;
u_desc_ctrl.field.p_xfer_dis = !!(flags & DMA_PREP_PQ_DISABLE_P);
u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
hw_desc->desc_ctrl = u_desc_ctrl.value;
}
static inline void iop_desc_set_byte_count(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan,
u32 byte_count)
......@@ -351,6 +415,7 @@ iop_desc_set_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
}
}
#define iop_desc_set_pq_zero_sum_byte_count iop_desc_set_zero_sum_byte_count
static inline void iop_desc_set_dest_addr(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan,
......@@ -361,6 +426,16 @@ static inline void iop_desc_set_dest_addr(struct iop_adma_desc_slot *desc,
hw_desc->upper_dest_addr = 0;
}
static inline void
iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
hw_desc->dest_addr = addr[0];
hw_desc->q_dest_addr = addr[1];
hw_desc->upper_dest_addr = 0;
}
static inline void iop_desc_set_memcpy_src_addr(struct iop_adma_desc_slot *desc,
dma_addr_t addr)
{
......@@ -388,6 +463,29 @@ static inline void iop_desc_set_xor_src_addr(struct iop_adma_desc_slot *desc,
} while (slot_cnt);
}
static inline void
iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
dma_addr_t addr, unsigned char coef)
{
int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc, *iter;
struct iop13xx_adma_src *src;
int i = 0;
do {
iter = iop_hw_desc_slot_idx(hw_desc, i);
src = &iter->src[src_idx];
src->src_addr = addr;
src->pq_upper_src_addr = 0;
src->pq_dmlt = coef;
slot_cnt -= slots_per_op;
if (slot_cnt) {
i += slots_per_op;
addr += IOP_ADMA_PQ_MAX_BYTE_COUNT;
}
} while (slot_cnt);
}
static inline void
iop_desc_init_interrupt(struct iop_adma_desc_slot *desc,
struct iop_adma_chan *chan)
......@@ -399,6 +497,15 @@ iop_desc_init_interrupt(struct iop_adma_desc_slot *desc,
}
#define iop_desc_set_zero_sum_src_addr iop_desc_set_xor_src_addr
#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
static inline void
iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
dma_addr_t *src)
{
iop_desc_set_xor_src_addr(desc, pq_idx, src[pq_idx]);
iop_desc_set_xor_src_addr(desc, pq_idx+1, src[pq_idx+1]);
}
static inline void iop_desc_set_next_desc(struct iop_adma_desc_slot *desc,
u32 next_desc_addr)
......@@ -428,18 +535,20 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
hw_desc->block_fill_data = val;
}
static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
static inline enum sum_check_flags
iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
{
struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
struct iop13xx_adma_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
struct iop13xx_adma_byte_count byte_count = hw_desc->byte_count_field;
enum sum_check_flags flags;
BUG_ON(!(byte_count.tx_complete && desc_ctrl.zero_result));
if (desc_ctrl.pq_xfer_en)
return byte_count.zero_result_err_q;
else
return byte_count.zero_result_err;
flags = byte_count.zero_result_err_q << SUM_CHECK_Q;
flags |= byte_count.zero_result_err << SUM_CHECK_P;
return flags;
}
static inline void iop_chan_append(struct iop_adma_chan *chan)
......
......@@ -477,10 +477,8 @@ void __init iop13xx_platform_init(void)
plat_data = &iop13xx_adma_0_data;
dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
dma_cap_set(DMA_XOR, plat_data->cap_mask);
dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
break;
case IOP13XX_INIT_ADMA_1:
......@@ -489,10 +487,8 @@ void __init iop13xx_platform_init(void)
plat_data = &iop13xx_adma_1_data;
dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
dma_cap_set(DMA_XOR, plat_data->cap_mask);
dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
break;
case IOP13XX_INIT_ADMA_2:
......@@ -501,14 +497,11 @@ void __init iop13xx_platform_init(void)
plat_data = &iop13xx_adma_2_data;
dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
dma_cap_set(DMA_XOR, plat_data->cap_mask);
dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
dma_cap_set(DMA_PQ_XOR, plat_data->cap_mask);
dma_cap_set(DMA_PQ_UPDATE, plat_data->cap_mask);
dma_cap_set(DMA_PQ_ZERO_SUM, plat_data->cap_mask);
dma_cap_set(DMA_PQ, plat_data->cap_mask);
dma_cap_set(DMA_PQ_VAL, plat_data->cap_mask);
break;
}
}
......
......@@ -179,7 +179,6 @@ static int __init iop3xx_adma_cap_init(void)
dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask);
#else
dma_cap_set(DMA_MEMCPY, iop3xx_dma_0_data.cap_mask);
dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_0_data.cap_mask);
dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask);
#endif
......@@ -188,7 +187,6 @@ static int __init iop3xx_adma_cap_init(void)
dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask);
#else
dma_cap_set(DMA_MEMCPY, iop3xx_dma_1_data.cap_mask);
dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_1_data.cap_mask);
dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask);
#endif
......@@ -198,7 +196,7 @@ static int __init iop3xx_adma_cap_init(void)
dma_cap_set(DMA_INTERRUPT, iop3xx_aau_data.cap_mask);
#else
dma_cap_set(DMA_XOR, iop3xx_aau_data.cap_mask);
dma_cap_set(DMA_ZERO_SUM, iop3xx_aau_data.cap_mask);
dma_cap_set(DMA_XOR_VAL, iop3xx_aau_data.cap_mask);
dma_cap_set(DMA_MEMSET, iop3xx_aau_data.cap_mask);
dma_cap_set(DMA_INTERRUPT, iop3xx_aau_data.cap_mask);
#endif
......
/*
* Freescale MPC83XX / MPC85XX DMA Controller
*
* Copyright (c) 2009 Ira W. Snyder <iws@ovro.caltech.edu>
*
* This file is licensed under the terms of the GNU General Public License
* version 2. This program is licensed "as is" without any warranty of any
* kind, whether express or implied.
*/
#ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
#define __ARCH_POWERPC_ASM_FSLDMA_H__
#include <linux/dmaengine.h>
/*
* Definitions for the Freescale DMA controller's DMA_SLAVE implemention
*
* The Freescale DMA_SLAVE implementation was designed to handle many-to-many
* transfers. An example usage would be an accelerated copy between two
* scatterlists. Another example use would be an accelerated copy from
* multiple non-contiguous device buffers into a single scatterlist.
*
* A DMA_SLAVE transaction is defined by a struct fsl_dma_slave. This
* structure contains a list of hardware addresses that should be copied
* to/from the scatterlist passed into device_prep_slave_sg(). The structure
* also has some fields to enable hardware-specific features.
*/
/**
* struct fsl_dma_hw_addr
* @entry: linked list entry
* @address: the hardware address
* @length: length to transfer
*
* Holds a single physical hardware address / length pair for use
* with the DMAEngine DMA_SLAVE API.
*/
struct fsl_dma_hw_addr {
struct list_head entry;
dma_addr_t address;
size_t length;
};
/**
* struct fsl_dma_slave
* @addresses: a linked list of struct fsl_dma_hw_addr structures
* @request_count: value for DMA request count
* @src_loop_size: setup and enable constant source-address DMA transfers
* @dst_loop_size: setup and enable constant destination address DMA transfers
* @external_start: enable externally started DMA transfers
* @external_pause: enable externally paused DMA transfers
*
* Holds a list of address / length pairs for use with the DMAEngine
* DMA_SLAVE API implementation for the Freescale DMA controller.
*/
struct fsl_dma_slave {
/* List of hardware address/length pairs */
struct list_head addresses;
/* Support for extra controller features */
unsigned int request_count;
unsigned int src_loop_size;
unsigned int dst_loop_size;
bool external_start;
bool external_pause;
};
/**
* fsl_dma_slave_append - add an address/length pair to a struct fsl_dma_slave
* @slave: the &struct fsl_dma_slave to add to
* @address: the hardware address to add
* @length: the length of bytes to transfer from @address
*
* Add a hardware address/length pair to a struct fsl_dma_slave. Returns 0 on
* success, -ERRNO otherwise.
*/
static inline int fsl_dma_slave_append(struct fsl_dma_slave *slave,
dma_addr_t address, size_t length)
{
struct fsl_dma_hw_addr *addr;
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (!addr)
return -ENOMEM;
INIT_LIST_HEAD(&addr->entry);
addr->address = address;
addr->length = length;
list_add_tail(&addr->entry, &slave->addresses);
return 0;
}
/**
* fsl_dma_slave_free - free a struct fsl_dma_slave
* @slave: the struct fsl_dma_slave to free
*
* Free a struct fsl_dma_slave and all associated address/length pairs
*/
static inline void fsl_dma_slave_free(struct fsl_dma_slave *slave)
{
struct fsl_dma_hw_addr *addr, *tmp;
if (slave) {
list_for_each_entry_safe(addr, tmp, &slave->addresses, entry) {
list_del(&addr->entry);
kfree(addr);
}
kfree(slave);
}
}
/**
* fsl_dma_slave_alloc - allocate a struct fsl_dma_slave
* @gfp: the flags to pass to kmalloc when allocating this structure
*
* Allocate a struct fsl_dma_slave for use by the DMA_SLAVE API. Returns a new
* struct fsl_dma_slave on success, or NULL on failure.
*/
static inline struct fsl_dma_slave *fsl_dma_slave_alloc(gfp_t gfp)
{
struct fsl_dma_slave *slave;
slave = kzalloc(sizeof(*slave), gfp);
if (!slave)
return NULL;
INIT_LIST_HEAD(&slave->addresses);
return slave;
}
#endif /* __ARCH_POWERPC_ASM_FSLDMA_H__ */
menu "DMA support"
config SH_DMA_API
bool
config SH_DMA
bool "SuperH on-chip DMA controller (DMAC) support"
depends on CPU_SH3 || CPU_SH4
select SH_DMA_API
default n
config SH_DMA_IRQ_MULTI
......@@ -19,6 +16,15 @@ config SH_DMA_IRQ_MULTI
CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785 || \
CPU_SUBTYPE_SH7760
config SH_DMA_API
depends on SH_DMA
bool "SuperH DMA API support"
default n
help
SH_DMA_API always enabled DMA API of used SuperH.
If you want to use DMA ENGINE, you must not enable this.
Please enable DMA_ENGINE and SH_DMAE.
config NR_ONCHIP_DMA_CHANNELS
int
depends on SH_DMA
......
......@@ -2,8 +2,7 @@
# Makefile for the SuperH DMA specific kernel interface routines under Linux.
#
obj-$(CONFIG_SH_DMA_API) += dma-api.o dma-sysfs.o
obj-$(CONFIG_SH_DMA) += dma-sh.o
obj-$(CONFIG_SH_DMA_API) += dma-sh.o dma-api.o dma-sysfs.o
obj-$(CONFIG_PVR2_DMA) += dma-pvr2.o
obj-$(CONFIG_G2_DMA) += dma-g2.o
obj-$(CONFIG_SH_DMABRG) += dmabrg.o
......@@ -116,4 +116,17 @@ static u32 dma_base_addr[] __maybe_unused = {
#define CHCR 0x0C
#define DMAOR 0x40
/*
* for dma engine
*
* SuperH DMA mode
*/
#define SHDMA_MIX_IRQ (1 << 1)
#define SHDMA_DMAOR1 (1 << 2)
#define SHDMA_DMAE1 (1 << 3)
struct sh_dmae_pdata {
unsigned int mode;
};
#endif /* __DMA_SH_H */
......@@ -14,3 +14,12 @@ config ASYNC_MEMSET
tristate
select ASYNC_CORE
config ASYNC_PQ
tristate
select ASYNC_CORE
config ASYNC_RAID6_RECOV
tristate
select ASYNC_CORE
select ASYNC_PQ
......@@ -2,3 +2,6 @@ obj-$(CONFIG_ASYNC_CORE) += async_tx.o
obj-$(CONFIG_ASYNC_MEMCPY) += async_memcpy.o
obj-$(CONFIG_ASYNC_MEMSET) += async_memset.o
obj-$(CONFIG_ASYNC_XOR) += async_xor.o
obj-$(CONFIG_ASYNC_PQ) += async_pq.o
obj-$(CONFIG_ASYNC_RAID6_RECOV) += async_raid6_recov.o
obj-$(CONFIG_ASYNC_RAID6_TEST) += raid6test.o
......@@ -33,28 +33,31 @@
* async_memcpy - attempt to copy memory with a dma engine.
* @dest: destination page
* @src: src page
* @offset: offset in pages to start transaction
* @dest_offset: offset into 'dest' to start transaction
* @src_offset: offset into 'src' to start transaction
* @len: length in bytes
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK,
* @depend_tx: memcpy depends on the result of this transaction
* @cb_fn: function to call when the memcpy completes
* @cb_param: parameter to pass to the callback routine
* @submit: submission / completion modifiers
*
* honored flags: ASYNC_TX_ACK
*/
struct dma_async_tx_descriptor *
async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
unsigned int src_offset, size_t len, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
unsigned int src_offset, size_t len,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMCPY,
struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMCPY,
&dest, 1, &src, 1, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
if (device) {
if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
dma_addr_t dma_dest, dma_src;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
unsigned long dma_prep_flags = 0;
if (submit->cb_fn)
dma_prep_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_prep_flags |= DMA_PREP_FENCE;
dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
DMA_FROM_DEVICE);
......@@ -67,13 +70,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
if (tx) {
pr_debug("%s: (async) len: %zu\n", __func__, len);
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
async_tx_submit(chan, tx, submit);
} else {
void *dest_buf, *src_buf;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
/* wait for any prerequisite operations */
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
dest_buf = kmap_atomic(dest, KM_USER0) + dest_offset;
src_buf = kmap_atomic(src, KM_USER1) + src_offset;
......@@ -83,26 +86,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
kunmap_atomic(dest_buf, KM_USER0);
kunmap_atomic(src_buf, KM_USER1);
async_tx_sync_epilog(cb_fn, cb_param);
async_tx_sync_epilog(submit);
}
return tx;
}
EXPORT_SYMBOL_GPL(async_memcpy);
static int __init async_memcpy_init(void)
{
return 0;
}
static void __exit async_memcpy_exit(void)
{
do { } while (0);
}
module_init(async_memcpy_init);
module_exit(async_memcpy_exit);
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("asynchronous memcpy api");
MODULE_LICENSE("GPL");
......@@ -35,26 +35,26 @@
* @val: fill value
* @offset: offset in pages to start transaction
* @len: length in bytes
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: memset depends on the result of this transaction
* @cb_fn: function to call when the memcpy completes
* @cb_param: parameter to pass to the callback routine
*
* honored flags: ASYNC_TX_ACK
*/
struct dma_async_tx_descriptor *
async_memset(struct page *dest, int val, unsigned int offset,
size_t len, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
async_memset(struct page *dest, int val, unsigned int offset, size_t len,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMSET,
struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMSET,
&dest, 1, NULL, 0, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
if (device) {
if (device && is_dma_fill_aligned(device, offset, 0, len)) {
dma_addr_t dma_dest;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
unsigned long dma_prep_flags = 0;
if (submit->cb_fn)
dma_prep_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_prep_flags |= DMA_PREP_FENCE;
dma_dest = dma_map_page(device->dev, dest, offset, len,
DMA_FROM_DEVICE);
......@@ -64,38 +64,25 @@ async_memset(struct page *dest, int val, unsigned int offset,
if (tx) {
pr_debug("%s: (async) len: %zu\n", __func__, len);
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
async_tx_submit(chan, tx, submit);
} else { /* run the memset synchronously */
void *dest_buf;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
dest_buf = (void *) (((char *) page_address(dest)) + offset);
dest_buf = page_address(dest) + offset;
/* wait for any prerequisite operations */
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
memset(dest_buf, val, len);
async_tx_sync_epilog(cb_fn, cb_param);
async_tx_sync_epilog(submit);
}
return tx;
}
EXPORT_SYMBOL_GPL(async_memset);
static int __init async_memset_init(void)
{
return 0;
}
static void __exit async_memset_exit(void)
{
do { } while (0);
}
module_init(async_memset_init);
module_exit(async_memset_exit);
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("asynchronous memset api");
MODULE_LICENSE("GPL");
/*
* Copyright(c) 2007 Yuri Tikhonov <yur@emcraft.com>
* Copyright(c) 2009 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc., 59
* Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* The full GNU General Public License is included in this distribution in the
* file called COPYING.
*/
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/dma-mapping.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
/**
* scribble - space to hold throwaway P buffer for synchronous gen_syndrome
*/
static struct page *scribble;
static bool is_raid6_zero_block(struct page *p)
{
return p == (void *) raid6_empty_zero_page;
}
/* the struct page *blocks[] parameter passed to async_gen_syndrome()
* and async_syndrome_val() contains the 'P' destination address at
* blocks[disks-2] and the 'Q' destination address at blocks[disks-1]
*
* note: these are macros as they are used as lvalues
*/
#define P(b, d) (b[d-2])
#define Q(b, d) (b[d-1])
/**
* do_async_gen_syndrome - asynchronously calculate P and/or Q
*/
static __async_inline struct dma_async_tx_descriptor *
do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
const unsigned char *scfs, unsigned int offset, int disks,
size_t len, dma_addr_t *dma_src,
struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct dma_device *dma = chan->device;
enum dma_ctrl_flags dma_flags = 0;
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
dma_async_tx_callback cb_param_orig = submit->cb_param;
int src_cnt = disks - 2;
unsigned char coefs[src_cnt];
unsigned short pq_src_cnt;
dma_addr_t dma_dest[2];
int src_off = 0;
int idx;
int i;
/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
if (P(blocks, disks))
dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
len, DMA_BIDIRECTIONAL);
else
dma_flags |= DMA_PREP_PQ_DISABLE_P;
if (Q(blocks, disks))
dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
len, DMA_BIDIRECTIONAL);
else
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
/* convert source addresses being careful to collapse 'empty'
* sources and update the coefficients accordingly
*/
for (i = 0, idx = 0; i < src_cnt; i++) {
if (is_raid6_zero_block(blocks[i]))
continue;
dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
DMA_TO_DEVICE);
coefs[idx] = scfs[i];
idx++;
}
src_cnt = idx;
while (src_cnt > 0) {
submit->flags = flags_orig;
pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
/* if we are submitting additional pqs, leave the chain open,
* clear the callback parameters, and leave the destination
* buffers mapped
*/
if (src_cnt > pq_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
if (cb_fn_orig)
dma_flags |= DMA_PREP_INTERRUPT;
}
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward
* progress in case they can not provide a descriptor
*/
for (;;) {
tx = dma->device_prep_dma_pq(chan, dma_dest,
&dma_src[src_off],
pq_src_cnt,
&coefs[src_off], len,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
/* drop completed sources */
src_cnt -= pq_src_cnt;
src_off += pq_src_cnt;
dma_flags |= DMA_PREP_CONTINUE;
}
return tx;
}
/**
* do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
*/
static void
do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
size_t len, struct async_submit_ctl *submit)
{
void **srcs;
int i;
if (submit->scribble)
srcs = submit->scribble;
else
srcs = (void **) blocks;
for (i = 0; i < disks; i++) {
if (is_raid6_zero_block(blocks[i])) {
BUG_ON(i > disks - 3); /* P or Q can't be zero */
srcs[i] = blocks[i];
} else
srcs[i] = page_address(blocks[i]) + offset;
}
raid6_call.gen_syndrome(disks, len, srcs);
async_tx_sync_epilog(submit);
}
/**
* async_gen_syndrome - asynchronously calculate a raid6 syndrome
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
* @offset: common offset into each block (src and dest) to start transaction
* @disks: number of blocks (including missing P or Q, see below)
* @len: length of operation in bytes
* @submit: submission/completion modifiers
*
* General note: This routine assumes a field of GF(2^8) with a
* primitive polynomial of 0x11d and a generator of {02}.
*
* 'disks' note: callers can optionally omit either P or Q (but not
* both) from the calculation by setting blocks[disks-2] or
* blocks[disks-1] to NULL. When P or Q is omitted 'len' must be <=
* PAGE_SIZE as a temporary buffer of this size is used in the
* synchronous path. 'disks' always accounts for both destination
* buffers.
*
* 'blocks' note: if submit->scribble is NULL then the contents of
* 'blocks' may be overridden
*/
struct dma_async_tx_descriptor *
async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
size_t len, struct async_submit_ctl *submit)
{
int src_cnt = disks - 2;
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&P(blocks, disks), 2,
blocks, src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
dma_addr_t *dma_src = NULL;
BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) blocks;
if (dma_src && device &&
(src_cnt <= dma_maxpq(device, 0) ||
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {
/* run the p+q asynchronously */
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
disks, len, dma_src, submit);
}
/* run the pq synchronously */
pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
if (!P(blocks, disks)) {
P(blocks, disks) = scribble;
BUG_ON(len + offset > PAGE_SIZE);
}
if (!Q(blocks, disks)) {
Q(blocks, disks) = scribble;
BUG_ON(len + offset > PAGE_SIZE);
}
do_sync_gen_syndrome(blocks, offset, disks, len, submit);
return NULL;
}
EXPORT_SYMBOL_GPL(async_gen_syndrome);
/**
* async_syndrome_val - asynchronously validate a raid6 syndrome
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
* @offset: common offset into each block (src and dest) to start transaction
* @disks: number of blocks (including missing P or Q, see below)
* @len: length of operation in bytes
* @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
* @spare: temporary result buffer for the synchronous case
* @submit: submission / completion modifiers
*
* The same notes from async_gen_syndrome apply to the 'blocks',
* and 'disks' parameters of this routine. The synchronous path
* requires a temporary result buffer and submit->scribble to be
* specified.
*/
struct dma_async_tx_descriptor *
async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
size_t len, enum sum_check_flags *pqres, struct page *spare,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL,
NULL, 0, blocks, disks,
len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
dma_addr_t *dma_src = NULL;
BUG_ON(disks < 4);
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) blocks;
if (dma_src && device && disks <= dma_maxpq(device, 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {
struct device *dev = device->dev;
dma_addr_t *pq = &dma_src[disks-2];
int i;
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
if (!P(blocks, disks))
dma_flags |= DMA_PREP_PQ_DISABLE_P;
if (!Q(blocks, disks))
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
for (i = 0; i < disks; i++)
if (likely(blocks[i])) {
BUG_ON(is_raid6_zero_block(blocks[i]));
dma_src[i] = dma_map_page(dev, blocks[i],
offset, len,
DMA_TO_DEVICE);
}
for (;;) {
tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
disks - 2,
raid6_gfexp,
len, pqres,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
async_tx_submit(chan, tx, submit);
return tx;
} else {
struct page *p_src = P(blocks, disks);
struct page *q_src = Q(blocks, disks);
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *scribble = submit->scribble;
void *cb_param_orig = submit->cb_param;
void *p, *q, *s;
pr_debug("%s: (sync) disks: %d len: %zu\n",
__func__, disks, len);
/* caller must provide a temporary result buffer and
* allow the input parameters to be preserved
*/
BUG_ON(!spare || !scribble);
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
/* recompute p and/or q into the temporary buffer and then
* check to see the result matches the current value
*/
tx = NULL;
*pqres = 0;
if (p_src) {
init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
NULL, NULL, scribble);
tx = async_xor(spare, blocks, offset, disks-2, len, submit);
async_tx_quiesce(&tx);
p = page_address(p_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
}
if (q_src) {
P(blocks, disks) = NULL;
Q(blocks, disks) = spare;
init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
tx = async_gen_syndrome(blocks, offset, disks, len, submit);
async_tx_quiesce(&tx);
q = page_address(q_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
}
/* restore P, Q and submit */
P(blocks, disks) = p_src;
Q(blocks, disks) = q_src;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
submit->flags = flags_orig;
async_tx_sync_epilog(submit);
return NULL;
}
}
EXPORT_SYMBOL_GPL(async_syndrome_val);
static int __init async_pq_init(void)
{
scribble = alloc_page(GFP_KERNEL);
if (scribble)
return 0;
pr_err("%s: failed to allocate required spare page\n", __func__);
return -ENOMEM;
}
static void __exit async_pq_exit(void)
{
put_page(scribble);
}
module_init(async_pq_init);
module_exit(async_pq_exit);
MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation");
MODULE_LICENSE("GPL");
/*
* Asynchronous RAID-6 recovery calculations ASYNC_TX API.
* Copyright(c) 2009 Intel Corporation
*
* based on raid6recov.c:
* Copyright 2002 H. Peter Anvin
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc., 51
* Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*
*/
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/dma-mapping.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
static struct dma_async_tx_descriptor *
async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
size_t len, struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, srcs, 2, len);
struct dma_device *dma = chan ? chan->device : NULL;
const u8 *amul, *bmul;
u8 ax, bx;
u8 *a, *b, *c;
if (dma) {
dma_addr_t dma_dest[2];
dma_addr_t dma_src[2];
struct device *dev = dma->dev;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef,
len, dma_flags);
if (tx) {
async_tx_submit(chan, tx, submit);
return tx;
}
/* could not get a descriptor, unmap and fall through to
* the synchronous path
*/
dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
dma_unmap_page(dev, dma_src[1], len, DMA_TO_DEVICE);
}
/* run the operation synchronously */
async_tx_quiesce(&submit->depend_tx);
amul = raid6_gfmul[coef[0]];
bmul = raid6_gfmul[coef[1]];
a = page_address(srcs[0]);
b = page_address(srcs[1]);
c = page_address(dest);
while (len--) {
ax = amul[*a++];
bx = bmul[*b++];
*c++ = ax ^ bx;
}
return NULL;
}
static struct dma_async_tx_descriptor *
async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, &src, 1, len);
struct dma_device *dma = chan ? chan->device : NULL;
const u8 *qmul; /* Q multiplier table */
u8 *d, *s;
if (dma) {
dma_addr_t dma_dest[2];
dma_addr_t dma_src[1];
struct device *dev = dma->dev;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef,
len, dma_flags);
if (tx) {
async_tx_submit(chan, tx, submit);
return tx;
}
/* could not get a descriptor, unmap and fall through to
* the synchronous path
*/
dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
}
/* no channel available, or failed to allocate a descriptor, so
* perform the operation synchronously
*/
async_tx_quiesce(&submit->depend_tx);
qmul = raid6_gfmul[coef];
d = page_address(dest);
s = page_address(src);
while (len--)
*d++ = qmul[*s++];
return NULL;
}
static struct dma_async_tx_descriptor *
__2data_recov_4(size_t bytes, int faila, int failb, struct page **blocks,
struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *a, *b;
struct page *srcs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
void *cb_param = submit->cb_param;
void *scribble = submit->scribble;
p = blocks[4-2];
q = blocks[4-1];
a = blocks[faila];
b = blocks[failb];
/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = p;
srcs[1] = q;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_sum_product(b, srcs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = p;
srcs[1] = b;
init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
cb_param, scribble);
tx = async_xor(a, srcs, 0, 2, bytes, submit);
return tx;
}
static struct dma_async_tx_descriptor *
__2data_recov_5(size_t bytes, int faila, int failb, struct page **blocks,
struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *g, *dp, *dq;
struct page *srcs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
void *cb_param = submit->cb_param;
void *scribble = submit->scribble;
int uninitialized_var(good);
int i;
for (i = 0; i < 3; i++) {
if (i == faila || i == failb)
continue;
else {
good = i;
break;
}
}
BUG_ON(i >= 3);
p = blocks[5-2];
q = blocks[5-1];
g = blocks[good];
/* Compute syndrome with zero for the missing data pages
* Use the dead data pages as temporary storage for delta p and
* delta q
*/
dp = blocks[faila];
dq = blocks[failb];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_memcpy(dp, g, 0, 0, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
/* compute P + Pxy */
srcs[0] = dp;
srcs[1] = p;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
tx = async_xor(dp, srcs, 0, 2, bytes, submit);
/* compute Q + Qxy */
srcs[0] = dq;
srcs[1] = q;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
tx = async_xor(dq, srcs, 0, 2, bytes, submit);
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = dp;
srcs[1] = dq;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_sum_product(dq, srcs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = dp;
srcs[1] = dq;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
tx = async_xor(dp, srcs, 0, 2, bytes, submit);
return tx;
}
static struct dma_async_tx_descriptor *
__2data_recov_n(int disks, size_t bytes, int faila, int failb,
struct page **blocks, struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *dp, *dq;
struct page *srcs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
void *cb_param = submit->cb_param;
void *scribble = submit->scribble;
p = blocks[disks-2];
q = blocks[disks-1];
/* Compute syndrome with zero for the missing data pages
* Use the dead data pages as temporary storage for
* delta p and delta q
*/
dp = blocks[faila];
blocks[faila] = (void *)raid6_empty_zero_page;
blocks[disks-2] = dp;
dq = blocks[failb];
blocks[failb] = (void *)raid6_empty_zero_page;
blocks[disks-1] = dq;
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
/* Restore pointer table */
blocks[faila] = dp;
blocks[failb] = dq;
blocks[disks-2] = p;
blocks[disks-1] = q;
/* compute P + Pxy */
srcs[0] = dp;
srcs[1] = p;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
tx = async_xor(dp, srcs, 0, 2, bytes, submit);
/* compute Q + Qxy */
srcs[0] = dq;
srcs[1] = q;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
tx = async_xor(dq, srcs, 0, 2, bytes, submit);
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = dp;
srcs[1] = dq;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_sum_product(dq, srcs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = dp;
srcs[1] = dq;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
tx = async_xor(dp, srcs, 0, 2, bytes, submit);
return tx;
}
/**
* async_raid6_2data_recov - asynchronously calculate two missing data blocks
* @disks: number of disks in the RAID-6 array
* @bytes: block size
* @faila: first failed drive index
* @failb: second failed drive index
* @blocks: array of source pointers where the last two entries are p and q
* @submit: submission/completion modifiers
*/
struct dma_async_tx_descriptor *
async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
struct page **blocks, struct async_submit_ctl *submit)
{
BUG_ON(faila == failb);
if (failb < faila)
swap(faila, failb);
pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
/* we need to preserve the contents of 'blocks' for the async
* case, so punt to synchronous if a scribble buffer is not available
*/
if (!submit->scribble) {
void **ptrs = (void **) blocks;
int i;
async_tx_quiesce(&submit->depend_tx);
for (i = 0; i < disks; i++)
ptrs[i] = page_address(blocks[i]);
raid6_2data_recov(disks, bytes, faila, failb, ptrs);
async_tx_sync_epilog(submit);
return NULL;
}
switch (disks) {
case 4:
/* dma devices do not uniformly understand a zero source pq
* operation (in contrast to the synchronous case), so
* explicitly handle the 4 disk special case
*/
return __2data_recov_4(bytes, faila, failb, blocks, submit);
case 5:
/* dma devices do not uniformly understand a single
* source pq operation (in contrast to the synchronous
* case), so explicitly handle the 5 disk special case
*/
return __2data_recov_5(bytes, faila, failb, blocks, submit);
default:
return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
}
}
EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
/**
* async_raid6_datap_recov - asynchronously calculate a data and the 'p' block
* @disks: number of disks in the RAID-6 array
* @bytes: block size
* @faila: failed drive index
* @blocks: array of source pointers where the last two entries are p and q
* @submit: submission/completion modifiers
*/
struct dma_async_tx_descriptor *
async_raid6_datap_recov(int disks, size_t bytes, int faila,
struct page **blocks, struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *dq;
u8 coef;
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
void *cb_param = submit->cb_param;
void *scribble = submit->scribble;
struct page *srcs[2];
pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
/* we need to preserve the contents of 'blocks' for the async
* case, so punt to synchronous if a scribble buffer is not available
*/
if (!scribble) {
void **ptrs = (void **) blocks;
int i;
async_tx_quiesce(&submit->depend_tx);
for (i = 0; i < disks; i++)
ptrs[i] = page_address(blocks[i]);
raid6_datap_recov(disks, bytes, faila, ptrs);
async_tx_sync_epilog(submit);
return NULL;
}
p = blocks[disks-2];
q = blocks[disks-1];
/* Compute syndrome with zero for the missing data page
* Use the dead data page as temporary storage for delta q
*/
dq = blocks[faila];
blocks[faila] = (void *)raid6_empty_zero_page;
blocks[disks-1] = dq;
/* in the 4 disk case we only need to perform a single source
* multiplication
*/
if (disks == 4) {
int good = faila == 0 ? 1 : 0;
struct page *g = blocks[good];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
tx = async_memcpy(p, g, 0, 0, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
} else {
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
}
/* Restore pointer table */
blocks[faila] = dq;
blocks[disks-1] = q;
/* calculate g^{-faila} */
coef = raid6_gfinv[raid6_gfexp[faila]];
srcs[0] = dq;
srcs[1] = q;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
tx = async_xor(dq, srcs, 0, 2, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
tx = async_mult(dq, dq, coef, bytes, submit);
srcs[0] = p;
srcs[1] = dq;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
tx = async_xor(p, srcs, 0, 2, bytes, submit);
return tx;
}
EXPORT_SYMBOL_GPL(async_raid6_datap_recov);
MODULE_AUTHOR("Dan Williams <dan.j.williams@intel.com>");
MODULE_DESCRIPTION("asynchronous RAID-6 recovery api");
MODULE_LICENSE("GPL");
......@@ -42,16 +42,21 @@ static void __exit async_tx_exit(void)
async_dmaengine_put();
}
module_init(async_tx_init);
module_exit(async_tx_exit);
/**
* __async_tx_find_channel - find a channel to carry out the operation or let
* the transaction execute synchronously
* @depend_tx: transaction dependency
* @submit: transaction dependency and submission modifiers
* @tx_type: transaction type
*/
struct dma_chan *
__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
enum dma_transaction_type tx_type)
__async_tx_find_channel(struct async_submit_ctl *submit,
enum dma_transaction_type tx_type)
{
struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
/* see if we can keep the chain on one channel */
if (depend_tx &&
dma_has_cap(tx_type, depend_tx->chan->device->cap_mask))
......@@ -59,17 +64,6 @@ __async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
return async_dma_find_channel(tx_type);
}
EXPORT_SYMBOL_GPL(__async_tx_find_channel);
#else
static int __init async_tx_init(void)
{
printk(KERN_INFO "async_tx: api initialized (sync-only)\n");
return 0;
}
static void __exit async_tx_exit(void)
{
do { } while (0);
}
#endif
......@@ -83,10 +77,14 @@ static void
async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
struct dma_async_tx_descriptor *tx)
{
struct dma_chan *chan;
struct dma_device *device;
struct dma_chan *chan = depend_tx->chan;
struct dma_device *device = chan->device;
struct dma_async_tx_descriptor *intr_tx = (void *) ~0;
#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH
BUG();
#endif
/* first check to see if we can still append to depend_tx */
spin_lock_bh(&depend_tx->lock);
if (depend_tx->parent && depend_tx->chan == tx->chan) {
......@@ -96,11 +94,11 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
}
spin_unlock_bh(&depend_tx->lock);
if (!intr_tx)
/* attached dependency, flush the parent channel */
if (!intr_tx) {
device->device_issue_pending(chan);
return;
chan = depend_tx->chan;
device = chan->device;
}
/* see if we can schedule an interrupt
* otherwise poll for completion
......@@ -134,6 +132,7 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
intr_tx->tx_submit(intr_tx);
async_tx_ack(intr_tx);
}
device->device_issue_pending(chan);
} else {
if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR)
panic("%s: DMA_ERROR waiting for depend_tx\n",
......@@ -144,13 +143,14 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
/**
* submit_disposition - while holding depend_tx->lock we must avoid submitting
* new operations to prevent a circular locking dependency with
* drivers that already hold a channel lock when calling
* async_tx_run_dependencies.
* submit_disposition - flags for routing an incoming operation
* @ASYNC_TX_SUBMITTED: we were able to append the new operation under the lock
* @ASYNC_TX_CHANNEL_SWITCH: when the lock is dropped schedule a channel switch
* @ASYNC_TX_DIRECT_SUBMIT: when the lock is dropped submit directly
*
* while holding depend_tx->lock we must avoid submitting new operations
* to prevent a circular locking dependency with drivers that already
* hold a channel lock when calling async_tx_run_dependencies.
*/
enum submit_disposition {
ASYNC_TX_SUBMITTED,
......@@ -160,11 +160,12 @@ enum submit_disposition {
void
async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
struct async_submit_ctl *submit)
{
tx->callback = cb_fn;
tx->callback_param = cb_param;
struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
tx->callback = submit->cb_fn;
tx->callback_param = submit->cb_param;
if (depend_tx) {
enum submit_disposition s;
......@@ -220,30 +221,29 @@ async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
tx->tx_submit(tx);
}
if (flags & ASYNC_TX_ACK)
if (submit->flags & ASYNC_TX_ACK)
async_tx_ack(tx);
if (depend_tx && (flags & ASYNC_TX_DEP_ACK))
if (depend_tx)
async_tx_ack(depend_tx);
}
EXPORT_SYMBOL_GPL(async_tx_submit);
/**
* async_trigger_callback - schedules the callback function to be run after
* any dependent operations have been completed.
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: 'callback' requires the completion of this transaction
* @cb_fn: function to call after depend_tx completes
* @cb_param: parameter to pass to the callback routine
* async_trigger_callback - schedules the callback function to be run
* @submit: submission and completion parameters
*
* honored flags: ASYNC_TX_ACK
*
* The callback is run after any dependent operations have completed.
*/
struct dma_async_tx_descriptor *
async_trigger_callback(enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
async_trigger_callback(struct async_submit_ctl *submit)
{
struct dma_chan *chan;
struct dma_device *device;
struct dma_async_tx_descriptor *tx;
struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
if (depend_tx) {
chan = depend_tx->chan;
......@@ -262,14 +262,14 @@ async_trigger_callback(enum async_tx_flags flags,
if (tx) {
pr_debug("%s: (async)\n", __func__);
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
async_tx_submit(chan, tx, submit);
} else {
pr_debug("%s: (sync)\n", __func__);
/* wait for any prerequisite operations */
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
async_tx_sync_epilog(cb_fn, cb_param);
async_tx_sync_epilog(submit);
}
return tx;
......@@ -295,9 +295,6 @@ void async_tx_quiesce(struct dma_async_tx_descriptor **tx)
}
EXPORT_SYMBOL_GPL(async_tx_quiesce);
module_init(async_tx_init);
module_exit(async_tx_exit);
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("Asynchronous Bulk Memory Transactions API");
MODULE_LICENSE("GPL");
......@@ -33,19 +33,16 @@
/* do_async_xor - dma map the pages and perform the xor with an engine */
static __async_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len,
enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
struct async_submit_ctl *submit)
{
struct dma_device *dma = chan->device;
dma_addr_t *dma_src = (dma_addr_t *) src_list;
struct dma_async_tx_descriptor *tx = NULL;
int src_off = 0;
int i;
dma_async_tx_callback _cb_fn;
void *_cb_param;
enum async_tx_flags async_flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *cb_param_orig = submit->cb_param;
enum async_tx_flags flags_orig = submit->flags;
enum dma_ctrl_flags dma_flags;
int xor_src_cnt;
dma_addr_t dma_dest;
......@@ -63,25 +60,27 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
}
while (src_cnt) {
async_flags = flags;
submit->flags = flags_orig;
dma_flags = 0;
xor_src_cnt = min(src_cnt, dma->max_xor);
xor_src_cnt = min(src_cnt, (int)dma->max_xor);
/* if we are submitting additional xors, leave the chain open,
* clear the callback parameters, and leave the destination
* buffer mapped
*/
if (src_cnt > xor_src_cnt) {
async_flags &= ~ASYNC_TX_ACK;
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
_cb_fn = NULL;
_cb_param = NULL;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
_cb_fn = cb_fn;
_cb_param = cb_param;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
}
if (_cb_fn)
if (submit->cb_fn)
dma_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward progress
* in case they can not provide a descriptor
......@@ -90,7 +89,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
xor_src_cnt, len, dma_flags);
if (unlikely(!tx))
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
/* spin wait for the preceeding transactions to complete */
while (unlikely(!tx)) {
......@@ -101,11 +100,8 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
dma_flags);
}
async_tx_submit(chan, tx, async_flags, depend_tx, _cb_fn,
_cb_param);
depend_tx = tx;
flags |= ASYNC_TX_DEP_ACK;
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
if (src_cnt > xor_src_cnt) {
/* drop completed sources */
......@@ -124,23 +120,27 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
static void
do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, enum async_tx_flags flags,
dma_async_tx_callback cb_fn, void *cb_param)
int src_cnt, size_t len, struct async_submit_ctl *submit)
{
int i;
int xor_src_cnt;
int src_off = 0;
void *dest_buf;
void **srcs = (void **) src_list;
void **srcs;
if (submit->scribble)
srcs = submit->scribble;
else
srcs = (void **) src_list;
/* reuse the 'src_list' array to convert to buffer pointers */
/* convert to buffer pointers */
for (i = 0; i < src_cnt; i++)
srcs[i] = page_address(src_list[i]) + offset;
/* set destination address */
dest_buf = page_address(dest) + offset;
if (flags & ASYNC_TX_XOR_ZERO_DST)
if (submit->flags & ASYNC_TX_XOR_ZERO_DST)
memset(dest_buf, 0, len);
while (src_cnt > 0) {
......@@ -153,61 +153,70 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
src_off += xor_src_cnt;
}
async_tx_sync_epilog(cb_fn, cb_param);
async_tx_sync_epilog(submit);
}
/**
* async_xor - attempt to xor a set of blocks with a dma engine.
* xor_blocks always uses the dest as a source so the ASYNC_TX_XOR_ZERO_DST
* flag must be set to not include dest data in the calculation. The
* assumption with dma eninges is that they only use the destination
* buffer as a source when it is explicity specified in the source list.
* @dest: destination page
* @src_list: array of source pages (if the dest is also a source it must be
* at index zero). The contents of this array may be overwritten.
* @offset: offset in pages to start transaction
* @src_list: array of source pages
* @offset: common src/dst offset to start transaction
* @src_cnt: number of source pages
* @len: length in bytes
* @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST,
* ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: xor depends on the result of this transaction.
* @cb_fn: function to call when the xor completes
* @cb_param: parameter to pass to the callback routine
* @submit: submission / completion modifiers
*
* honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST
*
* xor_blocks always uses the dest as a source so the
* ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in
* the calculation. The assumption with dma eninges is that they only
* use the destination buffer as a source when it is explicity specified
* in the source list.
*
* src_list note: if the dest is also a source it must be at index zero.
* The contents of this array will be overwritten if a scribble region
* is not specified.
*/
struct dma_async_tx_descriptor *
async_xor(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
int src_cnt, size_t len, struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR,
struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
&dest, 1, src_list,
src_cnt, len);
dma_addr_t *dma_src = NULL;
BUG_ON(src_cnt <= 1);
if (chan) {
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) src_list;
if (dma_src && chan && is_dma_xor_aligned(chan->device, offset, 0, len)) {
/* run the xor asynchronously */
pr_debug("%s (async): len: %zu\n", __func__, len);
return do_async_xor(chan, dest, src_list, offset, src_cnt, len,
flags, depend_tx, cb_fn, cb_param);
dma_src, submit);
} else {
/* run the xor synchronously */
pr_debug("%s (sync): len: %zu\n", __func__, len);
WARN_ONCE(chan, "%s: no space for dma address conversion\n",
__func__);
/* in the sync case the dest is an implied source
* (assumes the dest is the first source)
*/
if (flags & ASYNC_TX_XOR_DROP_DST) {
if (submit->flags & ASYNC_TX_XOR_DROP_DST) {
src_cnt--;
src_list++;
}
/* wait for any prerequisite operations */
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
do_sync_xor(dest, src_list, offset, src_cnt, len,
flags, cb_fn, cb_param);
do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
return NULL;
}
......@@ -222,104 +231,94 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len)
}
/**
* async_xor_zero_sum - attempt a xor parity check with a dma engine.
* async_xor_val - attempt a xor parity check with a dma engine.
* @dest: destination page used if the xor is performed synchronously
* @src_list: array of source pages. The dest page must be listed as a source
* at index zero. The contents of this array may be overwritten.
* @src_list: array of source pages
* @offset: offset in pages to start transaction
* @src_cnt: number of source pages
* @len: length in bytes
* @result: 0 if sum == 0 else non-zero
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: xor depends on the result of this transaction.
* @cb_fn: function to call when the xor completes
* @cb_param: parameter to pass to the callback routine
* @submit: submission / completion modifiers
*
* honored flags: ASYNC_TX_ACK
*
* src_list note: if the dest is also a source it must be at index zero.
* The contents of this array will be overwritten if a scribble region
* is not specified.
*/
struct dma_async_tx_descriptor *
async_xor_zero_sum(struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len,
u32 *result, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, enum sum_check_flags *result,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_ZERO_SUM,
struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL,
&dest, 1, src_list,
src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
dma_addr_t *dma_src = NULL;
BUG_ON(src_cnt <= 1);
if (device && src_cnt <= device->max_xor) {
dma_addr_t *dma_src = (dma_addr_t *) src_list;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) src_list;
if (dma_src && device && src_cnt <= device->max_xor &&
is_dma_xor_aligned(device, offset, 0, len)) {
unsigned long dma_prep_flags = 0;
int i;
pr_debug("%s: (async) len: %zu\n", __func__, len);
if (submit->cb_fn)
dma_prep_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_prep_flags |= DMA_PREP_FENCE;
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i],
offset, len, DMA_TO_DEVICE);
tx = device->device_prep_dma_zero_sum(chan, dma_src, src_cnt,
len, result,
dma_prep_flags);
tx = device->device_prep_dma_xor_val(chan, dma_src, src_cnt,
len, result,
dma_prep_flags);
if (unlikely(!tx)) {
async_tx_quiesce(&depend_tx);
async_tx_quiesce(&submit->depend_tx);
while (!tx) {
dma_async_issue_pending(chan);
tx = device->device_prep_dma_zero_sum(chan,
tx = device->device_prep_dma_xor_val(chan,
dma_src, src_cnt, len, result,
dma_prep_flags);
}
}
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
async_tx_submit(chan, tx, submit);
} else {
unsigned long xor_flags = flags;
enum async_tx_flags flags_orig = submit->flags;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
WARN_ONCE(device && src_cnt <= device->max_xor,
"%s: no space for dma address conversion\n",
__func__);
xor_flags |= ASYNC_TX_XOR_DROP_DST;
xor_flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_XOR_DROP_DST;
submit->flags &= ~ASYNC_TX_ACK;
tx = async_xor(dest, src_list, offset, src_cnt, len, xor_flags,
depend_tx, NULL, NULL);
tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
async_tx_quiesce(&tx);
*result = page_is_zero(dest, offset, len) ? 0 : 1;
*result = !page_is_zero(dest, offset, len) << SUM_CHECK_P;
async_tx_sync_epilog(cb_fn, cb_param);
async_tx_sync_epilog(submit);
submit->flags = flags_orig;
}
return tx;
}
EXPORT_SYMBOL_GPL(async_xor_zero_sum);
static int __init async_xor_init(void)
{
#ifdef CONFIG_ASYNC_TX_DMA
/* To conserve stack space the input src_list (array of page pointers)
* is reused to hold the array of dma addresses passed to the driver.
* This conversion is only possible when dma_addr_t is less than the
* the size of a pointer. HIGHMEM64G is known to violate this
* assumption.
*/
BUILD_BUG_ON(sizeof(dma_addr_t) > sizeof(struct page *));
#endif
return 0;
}
static void __exit async_xor_exit(void)
{
do { } while (0);
}
module_init(async_xor_init);
module_exit(async_xor_exit);
EXPORT_SYMBOL_GPL(async_xor_val);
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("asynchronous xor/xor-zero-sum api");
......
/*
* asynchronous raid6 recovery self test
* Copyright (c) 2009, Intel Corporation.
*
* based on drivers/md/raid6test/test.c:
* Copyright 2002-2007 H. Peter Anvin
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*
*/
#include <linux/async_tx.h>
#include <linux/random.h>
#undef pr
#define pr(fmt, args...) pr_info("raid6test: " fmt, ##args)
#define NDISKS 16 /* Including P and Q */
static struct page *dataptrs[NDISKS];
static addr_conv_t addr_conv[NDISKS];
static struct page *data[NDISKS+3];
static struct page *spare;
static struct page *recovi;
static struct page *recovj;
static void callback(void *param)
{
struct completion *cmp = param;
complete(cmp);
}
static void makedata(int disks)
{
int i, j;
for (i = 0; i < disks; i++) {
for (j = 0; j < PAGE_SIZE/sizeof(u32); j += sizeof(u32)) {
u32 *p = page_address(data[i]) + j;
*p = random32();
}
dataptrs[i] = data[i];
}
}
static char disk_type(int d, int disks)
{
if (d == disks - 2)
return 'P';
else if (d == disks - 1)
return 'Q';
else
return 'D';
}
/* Recover two failed blocks. */
static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
{
struct async_submit_ctl submit;
struct completion cmp;
struct dma_async_tx_descriptor *tx = NULL;
enum sum_check_flags result = ~0;
if (faila > failb)
swap(faila, failb);
if (failb == disks-1) {
if (faila == disks-2) {
/* P+Q failure. Just rebuild the syndrome. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
} else {
struct page *blocks[disks];
struct page *dest;
int count = 0;
int i;
/* data+Q failure. Reconstruct data from P,
* then rebuild syndrome
*/
for (i = disks; i-- ; ) {
if (i == faila || i == failb)
continue;
blocks[count++] = ptrs[i];
}
dest = ptrs[faila];
init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL,
NULL, NULL, addr_conv);
tx = async_xor(dest, blocks, 0, count, bytes, &submit);
init_async_submit(&submit, 0, tx, NULL, NULL, addr_conv);
tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
}
} else {
if (failb == disks-2) {
/* data+P failure. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
tx = async_raid6_datap_recov(disks, bytes, faila, ptrs, &submit);
} else {
/* data+data failure. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
tx = async_raid6_2data_recov(disks, bytes, faila, failb, ptrs, &submit);
}
}
init_completion(&cmp);
init_async_submit(&submit, ASYNC_TX_ACK, tx, callback, &cmp, addr_conv);
tx = async_syndrome_val(ptrs, 0, disks, bytes, &result, spare, &submit);
async_tx_issue_pending(tx);
if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
pr("%s: timeout! (faila: %d failb: %d disks: %d)\n",
__func__, faila, failb, disks);
if (result != 0)
pr("%s: validation failure! faila: %d failb: %d sum_check_flags: %x\n",
__func__, faila, failb, result);
}
static int test_disks(int i, int j, int disks)
{
int erra, errb;
memset(page_address(recovi), 0xf0, PAGE_SIZE);
memset(page_address(recovj), 0xba, PAGE_SIZE);
dataptrs[i] = recovi;
dataptrs[j] = recovj;
raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
pr("%s(%d, %d): faila=%3d(%c) failb=%3d(%c) %s\n",
__func__, i, j, i, disk_type(i, disks), j, disk_type(j, disks),
(!erra && !errb) ? "OK" : !erra ? "ERRB" : !errb ? "ERRA" : "ERRAB");
dataptrs[i] = data[i];
dataptrs[j] = data[j];
return erra || errb;
}
static int test(int disks, int *tests)
{
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
struct completion cmp;
int err = 0;
int i, j;
recovi = data[disks];
recovj = data[disks+1];
spare = data[disks+2];
makedata(disks);
/* Nuke syndromes */
memset(page_address(data[disks-2]), 0xee, PAGE_SIZE);
memset(page_address(data[disks-1]), 0xee, PAGE_SIZE);
/* Generate assumed good syndrome */
init_completion(&cmp);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, callback, &cmp, addr_conv);
tx = async_gen_syndrome(dataptrs, 0, disks, PAGE_SIZE, &submit);
async_tx_issue_pending(tx);
if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {
pr("error: initial gen_syndrome(%d) timed out\n", disks);
return 1;
}
pr("testing the %d-disk case...\n", disks);
for (i = 0; i < disks-1; i++)
for (j = i+1; j < disks; j++) {
(*tests)++;
err += test_disks(i, j, disks);
}
return err;
}
static int raid6_test(void)
{
int err = 0;
int tests = 0;
int i;
for (i = 0; i < NDISKS+3; i++) {
data[i] = alloc_page(GFP_KERNEL);
if (!data[i]) {
while (i--)
put_page(data[i]);
return -ENOMEM;
}
}
/* the 4-disk and 5-disk cases are special for the recovery code */
if (NDISKS > 4)
err += test(4, &tests);
if (NDISKS > 5)
err += test(5, &tests);
err += test(NDISKS, &tests);
pr("\n");
pr("complete (%d tests, %d failure%s)\n",
tests, err, err == 1 ? "" : "s");
for (i = 0; i < NDISKS+3; i++)
put_page(data[i]);
return 0;
}
static void raid6_test_exit(void)
{
}
/* when compiled-in wait for drivers to load first (assumes dma drivers
* are also compliled-in)
*/
late_initcall(raid6_test);
module_exit(raid6_test_exit);
MODULE_AUTHOR("Dan Williams <dan.j.williams@intel.com>");
MODULE_DESCRIPTION("asynchronous RAID-6 recovery self tests");
MODULE_LICENSE("GPL");
......@@ -28,7 +28,7 @@
#include <linux/device.h>
#include <linux/dca.h>
#define DCA_VERSION "1.8"
#define DCA_VERSION "1.12.1"
MODULE_VERSION(DCA_VERSION);
MODULE_LICENSE("GPL");
......@@ -36,20 +36,92 @@ MODULE_AUTHOR("Intel Corporation");
static DEFINE_SPINLOCK(dca_lock);
static LIST_HEAD(dca_providers);
static LIST_HEAD(dca_domains);
static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
static struct pci_bus *dca_pci_rc_from_dev(struct device *dev)
{
struct dca_provider *dca, *ret = NULL;
struct pci_dev *pdev = to_pci_dev(dev);
struct pci_bus *bus = pdev->bus;
list_for_each_entry(dca, &dca_providers, node) {
if ((!dev) || (dca->ops->dev_managed(dca, dev))) {
ret = dca;
break;
}
while (bus->parent)
bus = bus->parent;
return bus;
}
static struct dca_domain *dca_allocate_domain(struct pci_bus *rc)
{
struct dca_domain *domain;
domain = kzalloc(sizeof(*domain), GFP_NOWAIT);
if (!domain)
return NULL;
INIT_LIST_HEAD(&domain->dca_providers);
domain->pci_rc = rc;
return domain;
}
static void dca_free_domain(struct dca_domain *domain)
{
list_del(&domain->node);
kfree(domain);
}
static struct dca_domain *dca_find_domain(struct pci_bus *rc)
{
struct dca_domain *domain;
list_for_each_entry(domain, &dca_domains, node)
if (domain->pci_rc == rc)
return domain;
return NULL;
}
static struct dca_domain *dca_get_domain(struct device *dev)
{
struct pci_bus *rc;
struct dca_domain *domain;
rc = dca_pci_rc_from_dev(dev);
domain = dca_find_domain(rc);
if (!domain) {
domain = dca_allocate_domain(rc);
if (domain)
list_add(&domain->node, &dca_domains);
}
return domain;
}
static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
{
struct dca_provider *dca;
struct pci_bus *rc;
struct dca_domain *domain;
if (dev) {
rc = dca_pci_rc_from_dev(dev);
domain = dca_find_domain(rc);
if (!domain)
return NULL;
} else {
if (!list_empty(&dca_domains))
domain = list_first_entry(&dca_domains,
struct dca_domain,
node);
else
return NULL;
}
return ret;
list_for_each_entry(dca, &domain->dca_providers, node)
if ((!dev) || (dca->ops->dev_managed(dca, dev)))
return dca;
return NULL;
}
/**
......@@ -61,6 +133,8 @@ int dca_add_requester(struct device *dev)
struct dca_provider *dca;
int err, slot = -ENODEV;
unsigned long flags;
struct pci_bus *pci_rc;
struct dca_domain *domain;
if (!dev)
return -EFAULT;
......@@ -74,7 +148,14 @@ int dca_add_requester(struct device *dev)
return -EEXIST;
}
list_for_each_entry(dca, &dca_providers, node) {
pci_rc = dca_pci_rc_from_dev(dev);
domain = dca_find_domain(pci_rc);
if (!domain) {
spin_unlock_irqrestore(&dca_lock, flags);
return -ENODEV;
}
list_for_each_entry(dca, &domain->dca_providers, node) {
slot = dca->ops->add_requester(dca, dev);
if (slot >= 0)
break;
......@@ -222,13 +303,19 @@ int register_dca_provider(struct dca_provider *dca, struct device *dev)
{
int err;
unsigned long flags;
struct dca_domain *domain;
err = dca_sysfs_add_provider(dca, dev);
if (err)
return err;
spin_lock_irqsave(&dca_lock, flags);
list_add(&dca->node, &dca_providers);
domain = dca_get_domain(dev);
if (!domain) {
spin_unlock_irqrestore(&dca_lock, flags);
return -ENODEV;
}
list_add(&dca->node, &domain->dca_providers);
spin_unlock_irqrestore(&dca_lock, flags);
blocking_notifier_call_chain(&dca_provider_chain,
......@@ -241,15 +328,24 @@ EXPORT_SYMBOL_GPL(register_dca_provider);
* unregister_dca_provider - remove a dca provider
* @dca - struct created by alloc_dca_provider()
*/
void unregister_dca_provider(struct dca_provider *dca)
void unregister_dca_provider(struct dca_provider *dca, struct device *dev)
{
unsigned long flags;
struct pci_bus *pci_rc;
struct dca_domain *domain;
blocking_notifier_call_chain(&dca_provider_chain,
DCA_PROVIDER_REMOVE, NULL);
spin_lock_irqsave(&dca_lock, flags);
list_del(&dca->node);
pci_rc = dca_pci_rc_from_dev(dev);
domain = dca_find_domain(pci_rc);
if (list_empty(&domain->dca_providers))
dca_free_domain(domain);
spin_unlock_irqrestore(&dca_lock, flags);
dca_sysfs_remove_provider(dca);
......@@ -276,7 +372,7 @@ EXPORT_SYMBOL_GPL(dca_unregister_notify);
static int __init dca_init(void)
{
printk(KERN_ERR "dca service started, version %s\n", DCA_VERSION);
pr_info("dca service started, version %s\n", DCA_VERSION);
return dca_sysfs_init();
}
......
......@@ -17,11 +17,15 @@ if DMADEVICES
comment "DMA Devices"
config ASYNC_TX_DISABLE_CHANNEL_SWITCH
bool
config INTEL_IOATDMA
tristate "Intel I/OAT DMA support"
depends on PCI && X86
select DMA_ENGINE
select DCA
select ASYNC_TX_DISABLE_CHANNEL_SWITCH
help
Enable support for the Intel(R) I/OAT DMA engine present
in recent Intel Xeon chipsets.
......@@ -97,6 +101,14 @@ config TXX9_DMAC
Support the TXx9 SoC internal DMA controller. This can be
integrated in chips such as the Toshiba TX4927/38/39.
config SH_DMAE
tristate "Renesas SuperH DMAC support"
depends on SUPERH && SH_DMA
depends on !SH_DMA_API
select DMA_ENGINE
help
Enable support for the Renesas SuperH DMA controllers.
config DMA_ENGINE
bool
......@@ -116,7 +128,7 @@ config NET_DMA
config ASYNC_TX_DMA
bool "Async_tx: Offload support for the async_tx api"
depends on DMA_ENGINE && !HIGHMEM64G
depends on DMA_ENGINE
help
This allows the async_tx api to take advantage of offload engines for
memcpy, memset, xor, and raid6 p+q operations. If your platform has
......
obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
obj-$(CONFIG_NET_DMA) += iovlock.o
obj-$(CONFIG_DMATEST) += dmatest.o
obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
ioatdma-objs := ioat.o ioat_dma.o ioat_dca.o
obj-$(CONFIG_INTEL_IOATDMA) += ioat/
obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
obj-$(CONFIG_FSL_DMA) += fsldma.o
obj-$(CONFIG_MV_XOR) += mv_xor.o
......@@ -10,3 +9,4 @@ obj-$(CONFIG_DW_DMAC) += dw_dmac.o
obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
obj-$(CONFIG_MX3_IPU) += ipu/
obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
obj-$(CONFIG_SH_DMAE) += shdma.o
......@@ -87,6 +87,7 @@ static struct at_desc *atc_alloc_descriptor(struct dma_chan *chan,
desc = dma_pool_alloc(atdma->dma_desc_pool, gfp_flags, &phys);
if (desc) {
memset(desc, 0, sizeof(struct at_desc));
INIT_LIST_HEAD(&desc->tx_list);
dma_async_tx_descriptor_init(&desc->txd, chan);
/* txd.flags will be overwritten in prep functions */
desc->txd.flags = DMA_CTRL_ACK;
......@@ -150,11 +151,11 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
struct at_desc *child;
spin_lock_bh(&atchan->lock);
list_for_each_entry(child, &desc->txd.tx_list, desc_node)
list_for_each_entry(child, &desc->tx_list, desc_node)
dev_vdbg(chan2dev(&atchan->chan_common),
"moving child desc %p to freelist\n",
child);
list_splice_init(&desc->txd.tx_list, &atchan->free_list);
list_splice_init(&desc->tx_list, &atchan->free_list);
dev_vdbg(chan2dev(&atchan->chan_common),
"moving desc %p to freelist\n", desc);
list_add(&desc->desc_node, &atchan->free_list);
......@@ -247,30 +248,33 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
param = txd->callback_param;
/* move children to free_list */
list_splice_init(&txd->tx_list, &atchan->free_list);
list_splice_init(&desc->tx_list, &atchan->free_list);
/* move myself to free_list */
list_move(&desc->desc_node, &atchan->free_list);
/* unmap dma addresses */
if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
dma_unmap_single(chan2parent(&atchan->chan_common),
desc->lli.daddr,
desc->len, DMA_FROM_DEVICE);
else
dma_unmap_page(chan2parent(&atchan->chan_common),
desc->lli.daddr,
desc->len, DMA_FROM_DEVICE);
}
if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
dma_unmap_single(chan2parent(&atchan->chan_common),
desc->lli.saddr,
desc->len, DMA_TO_DEVICE);
else
dma_unmap_page(chan2parent(&atchan->chan_common),
desc->lli.saddr,
desc->len, DMA_TO_DEVICE);
if (!atchan->chan_common.private) {
struct device *parent = chan2parent(&atchan->chan_common);
if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
dma_unmap_single(parent,
desc->lli.daddr,
desc->len, DMA_FROM_DEVICE);
else
dma_unmap_page(parent,
desc->lli.daddr,
desc->len, DMA_FROM_DEVICE);
}
if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
dma_unmap_single(parent,
desc->lli.saddr,
desc->len, DMA_TO_DEVICE);
else
dma_unmap_page(parent,
desc->lli.saddr,
desc->len, DMA_TO_DEVICE);
}
}
/*
......@@ -334,7 +338,7 @@ static void atc_cleanup_descriptors(struct at_dma_chan *atchan)
/* This one is currently in progress */
return;
list_for_each_entry(child, &desc->txd.tx_list, desc_node)
list_for_each_entry(child, &desc->tx_list, desc_node)
if (!(child->lli.ctrla & ATC_DONE))
/* Currently in progress */
return;
......@@ -407,7 +411,7 @@ static void atc_handle_error(struct at_dma_chan *atchan)
dev_crit(chan2dev(&atchan->chan_common),
" cookie: %d\n", bad_desc->txd.cookie);
atc_dump_lli(atchan, &bad_desc->lli);
list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
list_for_each_entry(child, &bad_desc->tx_list, desc_node)
atc_dump_lli(atchan, &child->lli);
/* Pretend the descriptor completed successfully */
......@@ -587,7 +591,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
prev->lli.dscr = desc->txd.phys;
/* insert the link descriptor to the LD ring */
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
}
......@@ -646,8 +650,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
reg_width = atslave->reg_width;
sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
......@@ -687,7 +689,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
prev->lli.dscr = desc->txd.phys;
/* insert the link descriptor to the LD ring */
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
total_len += len;
......@@ -729,7 +731,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
prev->lli.dscr = desc->txd.phys;
/* insert the link descriptor to the LD ring */
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
total_len += len;
......
......@@ -165,6 +165,7 @@ struct at_desc {
struct at_lli lli;
/* THEN values for driver housekeeping */
struct list_head tx_list;
struct dma_async_tx_descriptor txd;
struct list_head desc_node;
size_t len;
......
......@@ -608,6 +608,40 @@ void dmaengine_put(void)
}
EXPORT_SYMBOL(dmaengine_put);
static bool device_has_all_tx_types(struct dma_device *device)
{
/* A device that satisfies this test has channels that will never cause
* an async_tx channel switch event as all possible operation types can
* be handled.
*/
#ifdef CONFIG_ASYNC_TX_DMA
if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask))
return false;
#endif
#if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE)
if (!dma_has_cap(DMA_MEMCPY, device->cap_mask))
return false;
#endif
#if defined(CONFIG_ASYNC_MEMSET) || defined(CONFIG_ASYNC_MEMSET_MODULE)
if (!dma_has_cap(DMA_MEMSET, device->cap_mask))
return false;
#endif
#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
if (!dma_has_cap(DMA_XOR, device->cap_mask))
return false;
#endif
#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
if (!dma_has_cap(DMA_PQ, device->cap_mask))
return false;
#endif
return true;
}
static int get_dma_id(struct dma_device *device)
{
int rc;
......@@ -644,8 +678,12 @@ int dma_async_device_register(struct dma_device *device)
!device->device_prep_dma_memcpy);
BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) &&
!device->device_prep_dma_xor);
BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) &&
!device->device_prep_dma_zero_sum);
BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) &&
!device->device_prep_dma_xor_val);
BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) &&
!device->device_prep_dma_pq);
BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) &&
!device->device_prep_dma_pq_val);
BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) &&
!device->device_prep_dma_memset);
BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) &&
......@@ -661,6 +699,12 @@ int dma_async_device_register(struct dma_device *device)
BUG_ON(!device->device_issue_pending);
BUG_ON(!device->dev);
/* note: this only matters in the
* CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH=y case
*/
if (device_has_all_tx_types(device))
dma_cap_set(DMA_ASYNC_TX, device->cap_mask);
idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
if (!idr_ref)
return -ENOMEM;
......@@ -933,55 +977,29 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
{
tx->chan = chan;
spin_lock_init(&tx->lock);
INIT_LIST_HEAD(&tx->tx_list);
}
EXPORT_SYMBOL(dma_async_tx_descriptor_init);
/* dma_wait_for_async_tx - spin wait for a transaction to complete
* @tx: in-flight transaction to wait on
*
* This routine assumes that tx was obtained from a call to async_memcpy,
* async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped
* and submitted). Walking the parent chain is only meant to cover for DMA
* drivers that do not implement the DMA_INTERRUPT capability and may race with
* the driver's descriptor cleanup routine.
*/
enum dma_status
dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
{
enum dma_status status;
struct dma_async_tx_descriptor *iter;
struct dma_async_tx_descriptor *parent;
unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
if (!tx)
return DMA_SUCCESS;
WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for"
" %s\n", __func__, dma_chan_name(tx->chan));
/* poll through the dependency chain, return when tx is complete */
do {
iter = tx;
/* find the root of the unsubmitted dependency chain */
do {
parent = iter->parent;
if (!parent)
break;
else
iter = parent;
} while (parent);
/* there is a small window for ->parent == NULL and
* ->cookie == -EBUSY
*/
while (iter->cookie == -EBUSY)
cpu_relax();
status = dma_sync_wait(iter->chan, iter->cookie);
} while (status == DMA_IN_PROGRESS || (iter != tx));
return status;
while (tx->cookie == -EBUSY) {
if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
pr_err("%s timeout waiting for descriptor submission\n",
__func__);
return DMA_ERROR;
}
cpu_relax();
}
return dma_sync_wait(tx->chan, tx->cookie);
}
EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
......
......@@ -48,6 +48,11 @@ module_param(xor_sources, uint, S_IRUGO);
MODULE_PARM_DESC(xor_sources,
"Number of xor source buffers (default: 3)");
static unsigned int pq_sources = 3;
module_param(pq_sources, uint, S_IRUGO);
MODULE_PARM_DESC(pq_sources,
"Number of p+q source buffers (default: 3)");
/*
* Initialization patterns. All bytes in the source buffer has bit 7
* set, all bytes in the destination buffer has bit 7 cleared.
......@@ -232,6 +237,7 @@ static int dmatest_func(void *data)
dma_cookie_t cookie;
enum dma_status status;
enum dma_ctrl_flags flags;
u8 pq_coefs[pq_sources];
int ret;
int src_cnt;
int dst_cnt;
......@@ -248,6 +254,11 @@ static int dmatest_func(void *data)
else if (thread->type == DMA_XOR) {
src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
dst_cnt = 1;
} else if (thread->type == DMA_PQ) {
src_cnt = pq_sources | 1; /* force odd to ensure dst = src */
dst_cnt = 2;
for (i = 0; i < pq_sources; i++)
pq_coefs[i] = 1;
} else
goto err_srcs;
......@@ -283,6 +294,7 @@ static int dmatest_func(void *data)
dma_addr_t dma_dsts[dst_cnt];
struct completion cmp;
unsigned long tmo = msecs_to_jiffies(3000);
u8 align = 0;
total_tests++;
......@@ -290,6 +302,18 @@ static int dmatest_func(void *data)
src_off = dmatest_random() % (test_buf_size - len + 1);
dst_off = dmatest_random() % (test_buf_size - len + 1);
/* honor alignment restrictions */
if (thread->type == DMA_MEMCPY)
align = dev->copy_align;
else if (thread->type == DMA_XOR)
align = dev->xor_align;
else if (thread->type == DMA_PQ)
align = dev->pq_align;
len = (len >> align) << align;
src_off = (src_off >> align) << align;
dst_off = (dst_off >> align) << align;
dmatest_init_srcs(thread->srcs, src_off, len);
dmatest_init_dsts(thread->dsts, dst_off, len);
......@@ -306,6 +330,7 @@ static int dmatest_func(void *data)
DMA_BIDIRECTIONAL);
}
if (thread->type == DMA_MEMCPY)
tx = dev->device_prep_dma_memcpy(chan,
dma_dsts[0] + dst_off,
......@@ -316,6 +341,15 @@ static int dmatest_func(void *data)
dma_dsts[0] + dst_off,
dma_srcs, xor_sources,
len, flags);
else if (thread->type == DMA_PQ) {
dma_addr_t dma_pq[dst_cnt];
for (i = 0; i < dst_cnt; i++)
dma_pq[i] = dma_dsts[i] + dst_off;
tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
pq_sources, pq_coefs,
len, flags);
}
if (!tx) {
for (i = 0; i < src_cnt; i++)
......@@ -459,6 +493,8 @@ static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_ty
op = "copy";
else if (type == DMA_XOR)
op = "xor";
else if (type == DMA_PQ)
op = "pq";
else
return -EINVAL;
......@@ -514,6 +550,10 @@ static int dmatest_add_channel(struct dma_chan *chan)
cnt = dmatest_add_threads(dtc, DMA_XOR);
thread_count += cnt > 0 ? cnt : 0;
}
if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
cnt = dmatest_add_threads(dtc, DMA_PQ);
thread_count += cnt > 0 ?: 0;
}
pr_info("dmatest: Started %u threads using %s\n",
thread_count, dma_chan_name(chan));
......
......@@ -116,7 +116,7 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
{
struct dw_desc *child;
list_for_each_entry(child, &desc->txd.tx_list, desc_node)
list_for_each_entry(child, &desc->tx_list, desc_node)
dma_sync_single_for_cpu(chan2parent(&dwc->chan),
child->txd.phys, sizeof(child->lli),
DMA_TO_DEVICE);
......@@ -137,11 +137,11 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
dwc_sync_desc_for_cpu(dwc, desc);
spin_lock_bh(&dwc->lock);
list_for_each_entry(child, &desc->txd.tx_list, desc_node)
list_for_each_entry(child, &desc->tx_list, desc_node)
dev_vdbg(chan2dev(&dwc->chan),
"moving child desc %p to freelist\n",
child);
list_splice_init(&desc->txd.tx_list, &dwc->free_list);
list_splice_init(&desc->tx_list, &dwc->free_list);
dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
list_add(&desc->desc_node, &dwc->free_list);
spin_unlock_bh(&dwc->lock);
......@@ -209,19 +209,28 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
param = txd->callback_param;
dwc_sync_desc_for_cpu(dwc, desc);
list_splice_init(&txd->tx_list, &dwc->free_list);
list_splice_init(&desc->tx_list, &dwc->free_list);
list_move(&desc->desc_node, &dwc->free_list);
/*
* We use dma_unmap_page() regardless of how the buffers were
* mapped before they were submitted...
*/
if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
dma_unmap_page(chan2parent(&dwc->chan), desc->lli.dar,
desc->len, DMA_FROM_DEVICE);
if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
dma_unmap_page(chan2parent(&dwc->chan), desc->lli.sar,
desc->len, DMA_TO_DEVICE);
if (!dwc->chan.private) {
struct device *parent = chan2parent(&dwc->chan);
if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
dma_unmap_single(parent, desc->lli.dar,
desc->len, DMA_FROM_DEVICE);
else
dma_unmap_page(parent, desc->lli.dar,
desc->len, DMA_FROM_DEVICE);
}
if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
dma_unmap_single(parent, desc->lli.sar,
desc->len, DMA_TO_DEVICE);
else
dma_unmap_page(parent, desc->lli.sar,
desc->len, DMA_TO_DEVICE);
}
}
/*
* The API requires that no submissions are done from a
......@@ -289,7 +298,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
/* This one is currently in progress */
return;
list_for_each_entry(child, &desc->txd.tx_list, desc_node)
list_for_each_entry(child, &desc->tx_list, desc_node)
if (child->lli.llp == llp)
/* Currently in progress */
return;
......@@ -356,7 +365,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
" cookie: %d\n", bad_desc->txd.cookie);
dwc_dump_lli(dwc, &bad_desc->lli);
list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
list_for_each_entry(child, &bad_desc->tx_list, desc_node)
dwc_dump_lli(dwc, &child->lli);
/* Pretend the descriptor completed successfully */
......@@ -608,7 +617,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
prev->txd.phys, sizeof(prev->lli),
DMA_TO_DEVICE);
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
}
......@@ -658,8 +667,6 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
reg_width = dws->reg_width;
prev = first = NULL;
sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
switch (direction) {
case DMA_TO_DEVICE:
ctllo = (DWC_DEFAULT_CTLLO
......@@ -700,7 +707,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
sizeof(prev->lli),
DMA_TO_DEVICE);
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
total_len += len;
......@@ -746,7 +753,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
sizeof(prev->lli),
DMA_TO_DEVICE);
list_add_tail(&desc->desc_node,
&first->txd.tx_list);
&first->tx_list);
}
prev = desc;
total_len += len;
......@@ -902,6 +909,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
break;
}
INIT_LIST_HEAD(&desc->tx_list);
dma_async_tx_descriptor_init(&desc->txd, chan);
desc->txd.tx_submit = dwc_tx_submit;
desc->txd.flags = DMA_CTRL_ACK;
......
......@@ -217,6 +217,7 @@ struct dw_desc {
/* THEN values for driver housekeeping */
struct list_head desc_node;
struct list_head tx_list;
struct dma_async_tx_descriptor txd;
size_t len;
};
......
......@@ -34,6 +34,7 @@
#include <linux/dmapool.h>
#include <linux/of_platform.h>
#include <asm/fsldma.h>
#include "fsldma.h"
static void dma_init(struct fsl_dma_chan *fsl_chan)
......@@ -280,28 +281,40 @@ static void fsl_chan_set_dest_loop_size(struct fsl_dma_chan *fsl_chan, int size)
}
/**
* fsl_chan_toggle_ext_pause - Toggle channel external pause status
* fsl_chan_set_request_count - Set DMA Request Count for external control
* @fsl_chan : Freescale DMA channel
* @size : Pause control size, 0 for disable external pause control.
* The maximum is 1024.
* @size : Number of bytes to transfer in a single request
*
* The Freescale DMA channel can be controlled by the external signal DREQ#.
* The DMA request count is how many bytes are allowed to transfer before
* pausing the channel, after which a new assertion of DREQ# resumes channel
* operation.
*
* The Freescale DMA channel can be controlled by the external
* signal DREQ#. The pause control size is how many bytes are allowed
* to transfer before pausing the channel, after which a new assertion
* of DREQ# resumes channel operation.
* A size of 0 disables external pause control. The maximum size is 1024.
*/
static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int size)
static void fsl_chan_set_request_count(struct fsl_dma_chan *fsl_chan, int size)
{
if (size > 1024)
return;
BUG_ON(size > 1024);
DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
| ((__ilog2(size) << 24) & 0x0f000000),
32);
}
if (size) {
DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
| ((__ilog2(size) << 24) & 0x0f000000),
32);
/**
* fsl_chan_toggle_ext_pause - Toggle channel external pause status
* @fsl_chan : Freescale DMA channel
* @enable : 0 is disabled, 1 is enabled.
*
* The Freescale DMA channel can be controlled by the external signal DREQ#.
* The DMA Request Count feature should be used in addition to this feature
* to set the number of bytes to transfer before pausing the channel.
*/
static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int enable)
{
if (enable)
fsl_chan->feature |= FSL_DMA_CHAN_PAUSE_EXT;
} else
else
fsl_chan->feature &= ~FSL_DMA_CHAN_PAUSE_EXT;
}
......@@ -326,7 +339,8 @@ static void fsl_chan_toggle_ext_start(struct fsl_dma_chan *fsl_chan, int enable)
static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
{
struct fsl_dma_chan *fsl_chan = to_fsl_chan(tx->chan);
struct fsl_desc_sw *desc;
struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
struct fsl_desc_sw *child;
unsigned long flags;
dma_cookie_t cookie;
......@@ -334,7 +348,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
spin_lock_irqsave(&fsl_chan->desc_lock, flags);
cookie = fsl_chan->common.cookie;
list_for_each_entry(desc, &tx->tx_list, node) {
list_for_each_entry(child, &desc->tx_list, node) {
cookie++;
if (cookie < 0)
cookie = 1;
......@@ -343,8 +357,8 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
}
fsl_chan->common.cookie = cookie;
append_ld_queue(fsl_chan, tx_to_fsl_desc(tx));
list_splice_init(&tx->tx_list, fsl_chan->ld_queue.prev);
append_ld_queue(fsl_chan, desc);
list_splice_init(&desc->tx_list, fsl_chan->ld_queue.prev);
spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
......@@ -366,6 +380,7 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
desc_sw = dma_pool_alloc(fsl_chan->desc_pool, GFP_ATOMIC, &pdesc);
if (desc_sw) {
memset(desc_sw, 0, sizeof(struct fsl_desc_sw));
INIT_LIST_HEAD(&desc_sw->tx_list);
dma_async_tx_descriptor_init(&desc_sw->async_tx,
&fsl_chan->common);
desc_sw->async_tx.tx_submit = fsl_dma_tx_submit;
......@@ -455,7 +470,7 @@ fsl_dma_prep_interrupt(struct dma_chan *chan, unsigned long flags)
new->async_tx.flags = flags;
/* Insert the link descriptor to the LD ring */
list_add_tail(&new->node, &new->async_tx.tx_list);
list_add_tail(&new->node, &new->tx_list);
/* Set End-of-link to the last link descriptor of new list*/
set_ld_eol(fsl_chan, new);
......@@ -513,7 +528,7 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
dma_dest += copy;
/* Insert the link descriptor to the LD ring */
list_add_tail(&new->node, &first->async_tx.tx_list);
list_add_tail(&new->node, &first->tx_list);
} while (len);
new->async_tx.flags = flags; /* client is in control of this ack */
......@@ -528,7 +543,7 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
if (!first)
return NULL;
list = &first->async_tx.tx_list;
list = &first->tx_list;
list_for_each_entry_safe_reverse(new, prev, list, node) {
list_del(&new->node);
dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
......@@ -537,6 +552,229 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
return NULL;
}
/**
* fsl_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
* @chan: DMA channel
* @sgl: scatterlist to transfer to/from
* @sg_len: number of entries in @scatterlist
* @direction: DMA direction
* @flags: DMAEngine flags
*
* Prepare a set of descriptors for a DMA_SLAVE transaction. Following the
* DMA_SLAVE API, this gets the device-specific information from the
* chan->private variable.
*/
static struct dma_async_tx_descriptor *fsl_dma_prep_slave_sg(
struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
enum dma_data_direction direction, unsigned long flags)
{
struct fsl_dma_chan *fsl_chan;
struct fsl_desc_sw *first = NULL, *prev = NULL, *new = NULL;
struct fsl_dma_slave *slave;
struct list_head *tx_list;
size_t copy;
int i;
struct scatterlist *sg;
size_t sg_used;
size_t hw_used;
struct fsl_dma_hw_addr *hw;
dma_addr_t dma_dst, dma_src;
if (!chan)
return NULL;
if (!chan->private)
return NULL;
fsl_chan = to_fsl_chan(chan);
slave = chan->private;
if (list_empty(&slave->addresses))
return NULL;
hw = list_first_entry(&slave->addresses, struct fsl_dma_hw_addr, entry);
hw_used = 0;
/*
* Build the hardware transaction to copy from the scatterlist to
* the hardware, or from the hardware to the scatterlist
*
* If you are copying from the hardware to the scatterlist and it
* takes two hardware entries to fill an entire page, then both
* hardware entries will be coalesced into the same page
*
* If you are copying from the scatterlist to the hardware and a
* single page can fill two hardware entries, then the data will
* be read out of the page into the first hardware entry, and so on
*/
for_each_sg(sgl, sg, sg_len, i) {
sg_used = 0;
/* Loop until the entire scatterlist entry is used */
while (sg_used < sg_dma_len(sg)) {
/*
* If we've used up the current hardware address/length
* pair, we need to load a new one
*
* This is done in a while loop so that descriptors with
* length == 0 will be skipped
*/
while (hw_used >= hw->length) {
/*
* If the current hardware entry is the last
* entry in the list, we're finished
*/
if (list_is_last(&hw->entry, &slave->addresses))
goto finished;
/* Get the next hardware address/length pair */
hw = list_entry(hw->entry.next,
struct fsl_dma_hw_addr, entry);
hw_used = 0;
}
/* Allocate the link descriptor from DMA pool */
new = fsl_dma_alloc_descriptor(fsl_chan);
if (!new) {
dev_err(fsl_chan->dev, "No free memory for "
"link descriptor\n");
goto fail;
}
#ifdef FSL_DMA_LD_DEBUG
dev_dbg(fsl_chan->dev, "new link desc alloc %p\n", new);
#endif
/*
* Calculate the maximum number of bytes to transfer,
* making sure it is less than the DMA controller limit
*/
copy = min_t(size_t, sg_dma_len(sg) - sg_used,
hw->length - hw_used);
copy = min_t(size_t, copy, FSL_DMA_BCR_MAX_CNT);
/*
* DMA_FROM_DEVICE
* from the hardware to the scatterlist
*
* DMA_TO_DEVICE
* from the scatterlist to the hardware
*/
if (direction == DMA_FROM_DEVICE) {
dma_src = hw->address + hw_used;
dma_dst = sg_dma_address(sg) + sg_used;
} else {
dma_src = sg_dma_address(sg) + sg_used;
dma_dst = hw->address + hw_used;
}
/* Fill in the descriptor */
set_desc_cnt(fsl_chan, &new->hw, copy);
set_desc_src(fsl_chan, &new->hw, dma_src);
set_desc_dest(fsl_chan, &new->hw, dma_dst);
/*
* If this is not the first descriptor, chain the
* current descriptor after the previous descriptor
*/
if (!first) {
first = new;
} else {
set_desc_next(fsl_chan, &prev->hw,
new->async_tx.phys);
}
new->async_tx.cookie = 0;
async_tx_ack(&new->async_tx);
prev = new;
sg_used += copy;
hw_used += copy;
/* Insert the link descriptor into the LD ring */
list_add_tail(&new->node, &first->tx_list);
}
}
finished:
/* All of the hardware address/length pairs had length == 0 */
if (!first || !new)
return NULL;
new->async_tx.flags = flags;
new->async_tx.cookie = -EBUSY;
/* Set End-of-link to the last link descriptor of new list */
set_ld_eol(fsl_chan, new);
/* Enable extra controller features */
if (fsl_chan->set_src_loop_size)
fsl_chan->set_src_loop_size(fsl_chan, slave->src_loop_size);
if (fsl_chan->set_dest_loop_size)
fsl_chan->set_dest_loop_size(fsl_chan, slave->dst_loop_size);
if (fsl_chan->toggle_ext_start)
fsl_chan->toggle_ext_start(fsl_chan, slave->external_start);
if (fsl_chan->toggle_ext_pause)
fsl_chan->toggle_ext_pause(fsl_chan, slave->external_pause);
if (fsl_chan->set_request_count)
fsl_chan->set_request_count(fsl_chan, slave->request_count);
return &first->async_tx;
fail:
/* If first was not set, then we failed to allocate the very first
* descriptor, and we're done */
if (!first)
return NULL;
/*
* First is set, so all of the descriptors we allocated have been added
* to first->tx_list, INCLUDING "first" itself. Therefore we
* must traverse the list backwards freeing each descriptor in turn
*
* We're re-using variables for the loop, oh well
*/
tx_list = &first->tx_list;
list_for_each_entry_safe_reverse(new, prev, tx_list, node) {
list_del_init(&new->node);
dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
}
return NULL;
}
static void fsl_dma_device_terminate_all(struct dma_chan *chan)
{
struct fsl_dma_chan *fsl_chan;
struct fsl_desc_sw *desc, *tmp;
unsigned long flags;
if (!chan)
return;
fsl_chan = to_fsl_chan(chan);
/* Halt the DMA engine */
dma_halt(fsl_chan);
spin_lock_irqsave(&fsl_chan->desc_lock, flags);
/* Remove and free all of the descriptors in the LD queue */
list_for_each_entry_safe(desc, tmp, &fsl_chan->ld_queue, node) {
list_del(&desc->node);
dma_pool_free(fsl_chan->desc_pool, desc, desc->async_tx.phys);
}
spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
}
/**
* fsl_dma_update_completed_cookie - Update the completed cookie.
* @fsl_chan : Freescale DMA channel
......@@ -883,6 +1121,7 @@ static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev,
new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start;
new_fsl_chan->set_src_loop_size = fsl_chan_set_src_loop_size;
new_fsl_chan->set_dest_loop_size = fsl_chan_set_dest_loop_size;
new_fsl_chan->set_request_count = fsl_chan_set_request_count;
}
spin_lock_init(&new_fsl_chan->desc_lock);
......@@ -962,12 +1201,15 @@ static int __devinit of_fsl_dma_probe(struct of_device *dev,
dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask);
dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask);
dma_cap_set(DMA_SLAVE, fdev->common.cap_mask);
fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources;
fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources;
fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt;
fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy;
fdev->common.device_is_tx_complete = fsl_dma_is_complete;
fdev->common.device_issue_pending = fsl_dma_memcpy_issue_pending;
fdev->common.device_prep_slave_sg = fsl_dma_prep_slave_sg;
fdev->common.device_terminate_all = fsl_dma_device_terminate_all;
fdev->common.dev = &dev->dev;
fdev->irq = irq_of_parse_and_map(dev->node, 0);
......
......@@ -90,6 +90,7 @@ struct fsl_dma_ld_hw {
struct fsl_desc_sw {
struct fsl_dma_ld_hw hw;
struct list_head node;
struct list_head tx_list;
struct dma_async_tx_descriptor async_tx;
struct list_head *ld;
void *priv;
......@@ -143,10 +144,11 @@ struct fsl_dma_chan {
struct tasklet_struct tasklet;
u32 feature;
void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int size);
void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int enable);
void (*toggle_ext_start)(struct fsl_dma_chan *fsl_chan, int enable);
void (*set_src_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
void (*set_dest_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
void (*set_request_count)(struct fsl_dma_chan *fsl_chan, int size);
};
#define to_fsl_chan(chan) container_of(chan, struct fsl_dma_chan, common)
......
obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
ioatdma-objs := pci.o dma.o dma_v2.o dma_v3.o dca.o
......@@ -33,8 +33,8 @@
#define cpu_physical_id(cpu) (cpuid_ebx(1) >> 24)
#endif
#include "ioatdma.h"
#include "ioatdma_registers.h"
#include "dma.h"
#include "registers.h"
/*
* Bit 7 of a tag map entry is the "valid" bit, if it is set then bits 0:6
......@@ -242,7 +242,8 @@ static struct dca_ops ioat_dca_ops = {
};
struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
struct dca_provider * __devinit
ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
{
struct dca_provider *dca;
struct ioat_dca_priv *ioatdca;
......@@ -407,7 +408,8 @@ static int ioat2_dca_count_dca_slots(void __iomem *iobase, u16 dca_offset)
return slots;
}
struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase)
struct dca_provider * __devinit
ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase)
{
struct dca_provider *dca;
struct ioat_dca_priv *ioatdca;
......@@ -602,7 +604,8 @@ static int ioat3_dca_count_dca_slots(void *iobase, u16 dca_offset)
return slots;
}
struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
struct dca_provider * __devinit
ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
{
struct dca_provider *dca;
struct ioat_dca_priv *ioatdca;
......
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
......@@ -64,18 +64,37 @@
#define IOAT_DEVICE_STATUS_OFFSET 0x0E /* 16-bit */
#define IOAT_DEVICE_STATUS_DEGRADED_MODE 0x0001
#define IOAT_DEVICE_MMIO_RESTRICTED 0x0002
#define IOAT_DEVICE_MEMORY_BYPASS 0x0004
#define IOAT_DEVICE_ADDRESS_REMAPPING 0x0008
#define IOAT_DMA_CAP_OFFSET 0x10 /* 32-bit */
#define IOAT_CAP_PAGE_BREAK 0x00000001
#define IOAT_CAP_CRC 0x00000002
#define IOAT_CAP_SKIP_MARKER 0x00000004
#define IOAT_CAP_DCA 0x00000010
#define IOAT_CAP_CRC_MOVE 0x00000020
#define IOAT_CAP_FILL_BLOCK 0x00000040
#define IOAT_CAP_APIC 0x00000080
#define IOAT_CAP_XOR 0x00000100
#define IOAT_CAP_PQ 0x00000200
#define IOAT_CHANNEL_MMIO_SIZE 0x80 /* Each Channel MMIO space is this size */
/* DMA Channel Registers */
#define IOAT_CHANCTRL_OFFSET 0x00 /* 16-bit Channel Control Register */
#define IOAT_CHANCTRL_CHANNEL_PRIORITY_MASK 0xF000
#define IOAT3_CHANCTRL_COMPL_DCA_EN 0x0200
#define IOAT_CHANCTRL_CHANNEL_IN_USE 0x0100
#define IOAT_CHANCTRL_DESCRIPTOR_ADDR_SNOOP_CONTROL 0x0020
#define IOAT_CHANCTRL_ERR_INT_EN 0x0010
#define IOAT_CHANCTRL_ANY_ERR_ABORT_EN 0x0008
#define IOAT_CHANCTRL_ERR_COMPLETION_EN 0x0004
#define IOAT_CHANCTRL_INT_DISABLE 0x0001
#define IOAT_CHANCTRL_INT_REARM 0x0001
#define IOAT_CHANCTRL_RUN (IOAT_CHANCTRL_INT_REARM |\
IOAT_CHANCTRL_ERR_COMPLETION_EN |\
IOAT_CHANCTRL_ANY_ERR_ABORT_EN |\
IOAT_CHANCTRL_ERR_INT_EN)
#define IOAT_DMA_COMP_OFFSET 0x02 /* 16-bit DMA channel compatibility */
#define IOAT_DMA_COMP_V1 0x0001 /* Compatibility with DMA version 1 */
......@@ -94,14 +113,14 @@
#define IOAT2_CHANSTS_OFFSET_HIGH 0x0C
#define IOAT_CHANSTS_OFFSET_HIGH(ver) ((ver) < IOAT_VER_2_0 \
? IOAT1_CHANSTS_OFFSET_HIGH : IOAT2_CHANSTS_OFFSET_HIGH)
#define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR ~0x3F
#define IOAT_CHANSTS_SOFT_ERR 0x0000000000000010
#define IOAT_CHANSTS_UNAFFILIATED_ERR 0x0000000000000008
#define IOAT_CHANSTS_DMA_TRANSFER_STATUS 0x0000000000000007
#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE 0x0
#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_DONE 0x1
#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_SUSPENDED 0x2
#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_HALTED 0x3
#define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR (~0x3fULL)
#define IOAT_CHANSTS_SOFT_ERR 0x10ULL
#define IOAT_CHANSTS_UNAFFILIATED_ERR 0x8ULL
#define IOAT_CHANSTS_STATUS 0x7ULL
#define IOAT_CHANSTS_ACTIVE 0x0
#define IOAT_CHANSTS_DONE 0x1
#define IOAT_CHANSTS_SUSPENDED 0x2
#define IOAT_CHANSTS_HALTED 0x3
......@@ -204,22 +223,27 @@
#define IOAT_CDAR_OFFSET_HIGH 0x24
#define IOAT_CHANERR_OFFSET 0x28 /* 32-bit Channel Error Register */
#define IOAT_CHANERR_DMA_TRANSFER_SRC_ADDR_ERR 0x0001
#define IOAT_CHANERR_DMA_TRANSFER_DEST_ADDR_ERR 0x0002
#define IOAT_CHANERR_NEXT_DESCRIPTOR_ADDR_ERR 0x0004
#define IOAT_CHANERR_NEXT_DESCRIPTOR_ALIGNMENT_ERR 0x0008
#define IOAT_CHANERR_SRC_ADDR_ERR 0x0001
#define IOAT_CHANERR_DEST_ADDR_ERR 0x0002
#define IOAT_CHANERR_NEXT_ADDR_ERR 0x0004
#define IOAT_CHANERR_NEXT_DESC_ALIGN_ERR 0x0008
#define IOAT_CHANERR_CHAIN_ADDR_VALUE_ERR 0x0010
#define IOAT_CHANERR_CHANCMD_ERR 0x0020
#define IOAT_CHANERR_CHIPSET_UNCORRECTABLE_DATA_INTEGRITY_ERR 0x0040
#define IOAT_CHANERR_DMA_UNCORRECTABLE_DATA_INTEGRITY_ERR 0x0080
#define IOAT_CHANERR_READ_DATA_ERR 0x0100
#define IOAT_CHANERR_WRITE_DATA_ERR 0x0200
#define IOAT_CHANERR_DESCRIPTOR_CONTROL_ERR 0x0400
#define IOAT_CHANERR_DESCRIPTOR_LENGTH_ERR 0x0800
#define IOAT_CHANERR_CONTROL_ERR 0x0400
#define IOAT_CHANERR_LENGTH_ERR 0x0800
#define IOAT_CHANERR_COMPLETION_ADDR_ERR 0x1000
#define IOAT_CHANERR_INT_CONFIGURATION_ERR 0x2000
#define IOAT_CHANERR_SOFT_ERR 0x4000
#define IOAT_CHANERR_UNAFFILIATED_ERR 0x8000
#define IOAT_CHANERR_XOR_P_OR_CRC_ERR 0x10000
#define IOAT_CHANERR_XOR_Q_ERR 0x20000
#define IOAT_CHANERR_DESCRIPTOR_COUNT_ERR 0x40000
#define IOAT_CHANERR_HANDLE_MASK (IOAT_CHANERR_XOR_P_OR_CRC_ERR | IOAT_CHANERR_XOR_Q_ERR)
#define IOAT_CHANERR_MASK_OFFSET 0x2C /* 32-bit Channel Error Register */
......
此差异已折叠。
此差异已折叠。
此差异已折叠。
......@@ -183,6 +183,11 @@ dma_cookie_t dma_memcpy_to_iovec(struct dma_chan *chan, struct iovec *iov,
iov_byte_offset,
kdata,
copy);
/* poll for a descriptor slot */
if (unlikely(dma_cookie < 0)) {
dma_async_issue_pending(chan);
continue;
}
len -= copy;
iov[iovec_idx].iov_len -= copy;
......@@ -248,6 +253,11 @@ dma_cookie_t dma_memcpy_pg_to_iovec(struct dma_chan *chan, struct iovec *iov,
page,
offset,
copy);
/* poll for a descriptor slot */
if (unlikely(dma_cookie < 0)) {
dma_async_issue_pending(chan);
continue;
}
len -= copy;
iov[iovec_idx].iov_len -= copy;
......
此差异已折叠。
......@@ -126,9 +126,8 @@ struct mv_xor_chan {
* @idx: pool index
* @unmap_src_cnt: number of xor sources
* @unmap_len: transaction bytecount
* @tx_list: list of slots that make up a multi-descriptor transaction
* @async_tx: support for the async_tx api
* @group_list: list of slots that make up a multi-descriptor transaction
* for example transfer lengths larger than the supported hw max
* @xor_check_result: result of zero sum
* @crc32_result: result crc calculation
*/
......@@ -145,6 +144,7 @@ struct mv_xor_desc_slot {
u16 unmap_src_cnt;
u32 value;
size_t unmap_len;
struct list_head tx_list;
struct dma_async_tx_descriptor async_tx;
union {
u32 *xor_check_result;
......
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册