android_kernel_motorola_sm6225/include/linux/dmaengine.h
Dan Williams b2f46fd8ef async_tx: add support for asynchronous GF multiplication
[ Based on an original patch by Yuri Tikhonov ]

This adds support for doing asynchronous GF multiplication by adding
two additional functions to the async_tx API:

 async_gen_syndrome() does simultaneous XOR and Galois field
    multiplication of sources.

 async_syndrome_val() validates the given source buffers against known P
    and Q values.

When a request is made to run async_pq against more than the hardware
maximum number of supported sources we need to reuse the previous
generated P and Q values as sources into the next operation.  Care must
be taken to remove Q from P' and P from Q'.  For example to perform a 5
source pq op with hardware that only supports 4 sources at a time the
following approach is taken:

p, q = PQ(src0, src1, src2, src3, COEF({01}, {02}, {04}, {08}))
p', q' = PQ(p, q, q, src4, COEF({00}, {01}, {00}, {10}))

p' = p + q + q + src4 = p + src4
q' = {00}*p + {01}*q + {00}*q + {10}*src4 = q + {10}*src4

Note: 4 is the minimum acceptable maxpq otherwise we punt to
synchronous-software path.

The DMA_PREP_CONTINUE flag indicates to the driver to reuse p and q as
sources (in the above manner) and fill the remaining slots up to maxpq
with the new sources/coefficients.

Note1: Some devices have native support for P+Q continuation and can skip
this extra work.  Devices with this capability can advertise it with
dma_set_maxpq.  It is up to each driver how to handle the
DMA_PREP_CONTINUE flag.

Note2: The api supports disabling the generation of P when generating Q,
this is ignored by the synchronous path but is implemented by some dma
devices to save unnecessary writes.  In this case the continuation
algorithm is simplified to only reuse Q as a source.

Cc: H. Peter Anvin <hpa@zytor.com>
Cc: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Yuri Tikhonov <yur@emcraft.com>
Signed-off-by: Ilya Yanok <yanok@emcraft.com>
Reviewed-by: Andre Noll <maan@systemlinux.org>
Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-08-29 19:09:27 -07:00

579 lines
18 KiB
C

/*
* Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License 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.
*/
#ifndef DMAENGINE_H
#define DMAENGINE_H
#include <linux/device.h>
#include <linux/uio.h>
#include <linux/dma-mapping.h>
/**
* typedef dma_cookie_t - an opaque DMA cookie
*
* if dma_cookie_t is >0 it's a DMA request cookie, <0 it's an error code
*/
typedef s32 dma_cookie_t;
#define dma_submit_error(cookie) ((cookie) < 0 ? 1 : 0)
/**
* enum dma_status - DMA transaction status
* @DMA_SUCCESS: transaction completed successfully
* @DMA_IN_PROGRESS: transaction not yet processed
* @DMA_ERROR: transaction failed
*/
enum dma_status {
DMA_SUCCESS,
DMA_IN_PROGRESS,
DMA_ERROR,
};
/**
* enum dma_transaction_type - DMA transaction types/indexes
*/
enum dma_transaction_type {
DMA_MEMCPY,
DMA_XOR,
DMA_PQ,
DMA_DUAL_XOR,
DMA_PQ_UPDATE,
DMA_XOR_VAL,
DMA_PQ_VAL,
DMA_MEMSET,
DMA_MEMCPY_CRC32C,
DMA_INTERRUPT,
DMA_PRIVATE,
DMA_SLAVE,
};
/* last transaction type for creation of the capabilities mask */
#define DMA_TX_TYPE_END (DMA_SLAVE + 1)
/**
* enum dma_ctrl_flags - DMA flags to augment operation preparation,
* control completion, and communicate status.
* @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of
* this transaction
* @DMA_CTRL_ACK - the descriptor cannot be reused until the client
* acknowledges receipt, i.e. has has a chance to establish any dependency
* chains
* @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
* @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
* @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q
* @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P
* @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as
* sources that were the result of a previous operation, in the case of a PQ
* operation it continues the calculation with new sources
*/
enum dma_ctrl_flags {
DMA_PREP_INTERRUPT = (1 << 0),
DMA_CTRL_ACK = (1 << 1),
DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2),
DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
DMA_PREP_PQ_DISABLE_P = (1 << 4),
DMA_PREP_PQ_DISABLE_Q = (1 << 5),
DMA_PREP_CONTINUE = (1 << 6),
};
/**
* enum sum_check_bits - bit position of pq_check_flags
*/
enum sum_check_bits {
SUM_CHECK_P = 0,
SUM_CHECK_Q = 1,
};
/**
* enum pq_check_flags - result of async_{xor,pq}_zero_sum operations
* @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise
* @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise
*/
enum sum_check_flags {
SUM_CHECK_P_RESULT = (1 << SUM_CHECK_P),
SUM_CHECK_Q_RESULT = (1 << SUM_CHECK_Q),
};
/**
* dma_cap_mask_t - capabilities bitmap modeled after cpumask_t.
* See linux/cpumask.h
*/
typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t;
/**
* struct dma_chan_percpu - the per-CPU part of struct dma_chan
* @memcpy_count: transaction counter
* @bytes_transferred: byte counter
*/
struct dma_chan_percpu {
/* stats */
unsigned long memcpy_count;
unsigned long bytes_transferred;
};
/**
* struct dma_chan - devices supply DMA channels, clients use them
* @device: ptr to the dma device who supplies this channel, always !%NULL
* @cookie: last cookie value returned to client
* @chan_id: channel ID for sysfs
* @dev: class device for sysfs
* @device_node: used to add this to the device chan list
* @local: per-cpu pointer to a struct dma_chan_percpu
* @client-count: how many clients are using this channel
* @table_count: number of appearances in the mem-to-mem allocation table
* @private: private data for certain client-channel associations
*/
struct dma_chan {
struct dma_device *device;
dma_cookie_t cookie;
/* sysfs */
int chan_id;
struct dma_chan_dev *dev;
struct list_head device_node;
struct dma_chan_percpu *local;
int client_count;
int table_count;
void *private;
};
/**
* struct dma_chan_dev - relate sysfs device node to backing channel device
* @chan - driver channel device
* @device - sysfs device
* @dev_id - parent dma_device dev_id
* @idr_ref - reference count to gate release of dma_device dev_id
*/
struct dma_chan_dev {
struct dma_chan *chan;
struct device device;
int dev_id;
atomic_t *idr_ref;
};
static inline const char *dma_chan_name(struct dma_chan *chan)
{
return dev_name(&chan->dev->device);
}
void dma_chan_cleanup(struct kref *kref);
/**
* typedef dma_filter_fn - callback filter for dma_request_channel
* @chan: channel to be reviewed
* @filter_param: opaque parameter passed through dma_request_channel
*
* When this optional parameter is specified in a call to dma_request_channel a
* suitable channel is passed to this routine for further dispositioning before
* being returned. Where 'suitable' indicates a non-busy channel that
* satisfies the given capability mask. It returns 'true' to indicate that the
* channel is suitable.
*/
typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
typedef void (*dma_async_tx_callback)(void *dma_async_param);
/**
* struct dma_async_tx_descriptor - async transaction descriptor
* ---dma generic offload fields---
* @cookie: tracking cookie for this transaction, set to -EBUSY if
* this tx is sitting on a dependency list
* @flags: flags to augment operation preparation, control completion, and
* communicate status
* @phys: physical address of the descriptor
* @tx_list: driver common field for operations that require multiple
* descriptors
* @chan: target channel for this operation
* @tx_submit: set the prepared descriptor(s) to be executed by the engine
* @callback: routine to call after this operation is complete
* @callback_param: general parameter to pass to the callback routine
* ---async_tx api specific fields---
* @next: at completion submit this descriptor
* @parent: pointer to the next level up in the dependency chain
* @lock: protect the parent and next pointers
*/
struct dma_async_tx_descriptor {
dma_cookie_t cookie;
enum dma_ctrl_flags flags; /* not a 'long' to pack with cookie */
dma_addr_t phys;
struct list_head tx_list;
struct dma_chan *chan;
dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx);
dma_async_tx_callback callback;
void *callback_param;
struct dma_async_tx_descriptor *next;
struct dma_async_tx_descriptor *parent;
spinlock_t lock;
};
/**
* struct dma_device - info on the entity supplying DMA services
* @chancnt: how many DMA channels are supported
* @privatecnt: how many DMA channels are requested by dma_request_channel
* @channels: the list of struct dma_chan
* @global_node: list_head for global dma_device_list
* @cap_mask: one or more dma_capability flags
* @max_xor: maximum number of xor sources, 0 if no capability
* @max_pq: maximum number of PQ sources and PQ-continue capability
* @dev_id: unique device ID
* @dev: struct device reference for dma mapping api
* @device_alloc_chan_resources: allocate resources and return the
* number of allocated descriptors
* @device_free_chan_resources: release DMA channel's resources
* @device_prep_dma_memcpy: prepares a memcpy operation
* @device_prep_dma_xor: prepares a xor operation
* @device_prep_dma_xor_val: prepares a xor validation operation
* @device_prep_dma_pq: prepares a pq operation
* @device_prep_dma_pq_val: prepares a pqzero_sum operation
* @device_prep_dma_memset: prepares a memset operation
* @device_prep_dma_interrupt: prepares an end of chain interrupt operation
* @device_prep_slave_sg: prepares a slave dma operation
* @device_terminate_all: terminate all pending operations
* @device_is_tx_complete: poll for transaction completion
* @device_issue_pending: push pending transactions to hardware
*/
struct dma_device {
unsigned int chancnt;
unsigned int privatecnt;
struct list_head channels;
struct list_head global_node;
dma_cap_mask_t cap_mask;
unsigned short max_xor;
unsigned short max_pq;
#define DMA_HAS_PQ_CONTINUE (1 << 15)
int dev_id;
struct device *dev;
int (*device_alloc_chan_resources)(struct dma_chan *chan);
void (*device_free_chan_resources)(struct dma_chan *chan);
struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
size_t len, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
unsigned int src_cnt, size_t len, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)(
struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt,
size_t len, enum sum_check_flags *result, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_pq)(
struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
unsigned int src_cnt, const unsigned char *scf,
size_t len, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_pq_val)(
struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
unsigned int src_cnt, const unsigned char *scf, size_t len,
enum sum_check_flags *pqres, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_memset)(
struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
struct dma_chan *chan, unsigned long flags);
struct dma_async_tx_descriptor *(*device_prep_slave_sg)(
struct dma_chan *chan, struct scatterlist *sgl,
unsigned int sg_len, enum dma_data_direction direction,
unsigned long flags);
void (*device_terminate_all)(struct dma_chan *chan);
enum dma_status (*device_is_tx_complete)(struct dma_chan *chan,
dma_cookie_t cookie, dma_cookie_t *last,
dma_cookie_t *used);
void (*device_issue_pending)(struct dma_chan *chan);
};
static inline void
dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue)
{
dma->max_pq = maxpq;
if (has_pq_continue)
dma->max_pq |= DMA_HAS_PQ_CONTINUE;
}
static inline bool dmaf_continue(enum dma_ctrl_flags flags)
{
return (flags & DMA_PREP_CONTINUE) == DMA_PREP_CONTINUE;
}
static inline bool dmaf_p_disabled_continue(enum dma_ctrl_flags flags)
{
enum dma_ctrl_flags mask = DMA_PREP_CONTINUE | DMA_PREP_PQ_DISABLE_P;
return (flags & mask) == mask;
}
static inline bool dma_dev_has_pq_continue(struct dma_device *dma)
{
return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE;
}
static unsigned short dma_dev_to_maxpq(struct dma_device *dma)
{
return dma->max_pq & ~DMA_HAS_PQ_CONTINUE;
}
/* dma_maxpq - reduce maxpq in the face of continued operations
* @dma - dma device with PQ capability
* @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set
*
* When an engine does not support native continuation we need 3 extra
* source slots to reuse P and Q with the following coefficients:
* 1/ {00} * P : remove P from Q', but use it as a source for P'
* 2/ {01} * Q : use Q to continue Q' calculation
* 3/ {00} * Q : subtract Q from P' to cancel (2)
*
* In the case where P is disabled we only need 1 extra source:
* 1/ {01} * Q : use Q to continue Q' calculation
*/
static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags)
{
if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags))
return dma_dev_to_maxpq(dma);
else if (dmaf_p_disabled_continue(flags))
return dma_dev_to_maxpq(dma) - 1;
else if (dmaf_continue(flags))
return dma_dev_to_maxpq(dma) - 3;
BUG();
}
/* --- public DMA engine API --- */
#ifdef CONFIG_DMA_ENGINE
void dmaengine_get(void);
void dmaengine_put(void);
#else
static inline void dmaengine_get(void)
{
}
static inline void dmaengine_put(void)
{
}
#endif
#ifdef CONFIG_NET_DMA
#define net_dmaengine_get() dmaengine_get()
#define net_dmaengine_put() dmaengine_put()
#else
static inline void net_dmaengine_get(void)
{
}
static inline void net_dmaengine_put(void)
{
}
#endif
#ifdef CONFIG_ASYNC_TX_DMA
#define async_dmaengine_get() dmaengine_get()
#define async_dmaengine_put() dmaengine_put()
#define async_dma_find_channel(type) dma_find_channel(type)
#else
static inline void async_dmaengine_get(void)
{
}
static inline void async_dmaengine_put(void)
{
}
static inline struct dma_chan *
async_dma_find_channel(enum dma_transaction_type type)
{
return NULL;
}
#endif
dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
void *dest, void *src, size_t len);
dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
struct page *page, unsigned int offset, void *kdata, size_t len);
dma_cookie_t dma_async_memcpy_pg_to_pg(struct dma_chan *chan,
struct page *dest_pg, unsigned int dest_off, struct page *src_pg,
unsigned int src_off, size_t len);
void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
struct dma_chan *chan);
static inline void async_tx_ack(struct dma_async_tx_descriptor *tx)
{
tx->flags |= DMA_CTRL_ACK;
}
static inline void async_tx_clear_ack(struct dma_async_tx_descriptor *tx)
{
tx->flags &= ~DMA_CTRL_ACK;
}
static inline bool async_tx_test_ack(struct dma_async_tx_descriptor *tx)
{
return (tx->flags & DMA_CTRL_ACK) == DMA_CTRL_ACK;
}
#define first_dma_cap(mask) __first_dma_cap(&(mask))
static inline int __first_dma_cap(const dma_cap_mask_t *srcp)
{
return min_t(int, DMA_TX_TYPE_END,
find_first_bit(srcp->bits, DMA_TX_TYPE_END));
}
#define next_dma_cap(n, mask) __next_dma_cap((n), &(mask))
static inline int __next_dma_cap(int n, const dma_cap_mask_t *srcp)
{
return min_t(int, DMA_TX_TYPE_END,
find_next_bit(srcp->bits, DMA_TX_TYPE_END, n+1));
}
#define dma_cap_set(tx, mask) __dma_cap_set((tx), &(mask))
static inline void
__dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
{
set_bit(tx_type, dstp->bits);
}
#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask))
static inline void
__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
{
clear_bit(tx_type, dstp->bits);
}
#define dma_cap_zero(mask) __dma_cap_zero(&(mask))
static inline void __dma_cap_zero(dma_cap_mask_t *dstp)
{
bitmap_zero(dstp->bits, DMA_TX_TYPE_END);
}
#define dma_has_cap(tx, mask) __dma_has_cap((tx), &(mask))
static inline int
__dma_has_cap(enum dma_transaction_type tx_type, dma_cap_mask_t *srcp)
{
return test_bit(tx_type, srcp->bits);
}
#define for_each_dma_cap_mask(cap, mask) \
for ((cap) = first_dma_cap(mask); \
(cap) < DMA_TX_TYPE_END; \
(cap) = next_dma_cap((cap), (mask)))
/**
* dma_async_issue_pending - flush pending transactions to HW
* @chan: target DMA channel
*
* This allows drivers to push copies to HW in batches,
* reducing MMIO writes where possible.
*/
static inline void dma_async_issue_pending(struct dma_chan *chan)
{
chan->device->device_issue_pending(chan);
}
#define dma_async_memcpy_issue_pending(chan) dma_async_issue_pending(chan)
/**
* dma_async_is_tx_complete - poll for transaction completion
* @chan: DMA channel
* @cookie: transaction identifier to check status of
* @last: returns last completed cookie, can be NULL
* @used: returns last issued cookie, can be NULL
*
* If @last and @used are passed in, upon return they reflect the driver
* internal state and can be used with dma_async_is_complete() to check
* the status of multiple cookies without re-checking hardware state.
*/
static inline enum dma_status dma_async_is_tx_complete(struct dma_chan *chan,
dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used)
{
return chan->device->device_is_tx_complete(chan, cookie, last, used);
}
#define dma_async_memcpy_complete(chan, cookie, last, used)\
dma_async_is_tx_complete(chan, cookie, last, used)
/**
* dma_async_is_complete - test a cookie against chan state
* @cookie: transaction identifier to test status of
* @last_complete: last know completed transaction
* @last_used: last cookie value handed out
*
* dma_async_is_complete() is used in dma_async_memcpy_complete()
* the test logic is separated for lightweight testing of multiple cookies
*/
static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie,
dma_cookie_t last_complete, dma_cookie_t last_used)
{
if (last_complete <= last_used) {
if ((cookie <= last_complete) || (cookie > last_used))
return DMA_SUCCESS;
} else {
if ((cookie <= last_complete) && (cookie > last_used))
return DMA_SUCCESS;
}
return DMA_IN_PROGRESS;
}
enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie);
#ifdef CONFIG_DMA_ENGINE
enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
void dma_issue_pending_all(void);
#else
static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
{
return DMA_SUCCESS;
}
static inline void dma_issue_pending_all(void)
{
do { } while (0);
}
#endif
/* --- DMA device --- */
int dma_async_device_register(struct dma_device *device);
void dma_async_device_unregister(struct dma_device *device);
void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type);
#define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y)
struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param);
void dma_release_channel(struct dma_chan *chan);
/* --- Helper iov-locking functions --- */
struct dma_page_list {
char __user *base_address;
int nr_pages;
struct page **pages;
};
struct dma_pinned_list {
int nr_iovecs;
struct dma_page_list page_list[0];
};
struct dma_pinned_list *dma_pin_iovec_pages(struct iovec *iov, size_t len);
void dma_unpin_iovec_pages(struct dma_pinned_list* pinned_list);
dma_cookie_t dma_memcpy_to_iovec(struct dma_chan *chan, struct iovec *iov,
struct dma_pinned_list *pinned_list, unsigned char *kdata, size_t len);
dma_cookie_t dma_memcpy_pg_to_iovec(struct dma_chan *chan, struct iovec *iov,
struct dma_pinned_list *pinned_list, struct page *page,
unsigned int offset, size_t len);
#endif /* DMAENGINE_H */