Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit c2110923 authored by Dan Williams's avatar Dan Williams
Browse files

dmaengine: driver for the iop32x, iop33x, and iop13xx raid engines



The Intel(R) IOP series of i/o processors integrate an Xscale core with
raid acceleration engines.  The capabilities per platform are:

iop219:
 (2) copy engines
iop321:
 (2) copy engines
 (1) xor and block fill engine
iop33x:
 (2) copy and crc32c engines
 (1) xor, xor zero sum, pq, pq zero sum, and block fill engine
iop34x (iop13xx):
 (2) copy, crc32c, xor, xor zero sum, and block fill engines
 (1) copy, crc32c, xor, xor zero sum, pq, pq zero sum, and block fill engine

The driver supports the features of the async_tx api:
* asynchronous notification of operation completion
* implicit (interupt triggered) handling of inter-channel transaction
  dependencies

The driver adapts to the platform it is running by two methods.
1/ #include <asm/arch/adma.h> which defines the hardware specific
   iop_chan_* and iop_desc_* routines as a series of static inline
   functions
2/ The private platform data attached to the platform_device defines the
   capabilities of the channels

20070626: Callbacks are run in a tasklet.  Given the recent discussion on
LKML about killing tasklets in favor of workqueues I did a quick conversion
of the driver.  Raid5 resync performance dropped from 50MB/s to 30MB/s, so
the tasklet implementation remains until a generic softirq interface is
available.

Changelog:
* fixed a slot allocation bug in do_iop13xx_adma_xor that caused too few
slots to be requested eventually leading to data corruption
* enabled the slot allocation routine to attempt to free slots before
returning -ENOMEM
* switched the cleanup routine to solely use the software chain and the
status register to determine if a descriptor is complete.  This is
necessary to support other IOP engines that do not have status writeback
capability
* make the driver iop generic
* modified the allocation routines to understand allocating a group of
slots for a single operation
* added a null xor initialization operation for the xor only channel on
iop3xx
* support xor operations on buffers larger than the hardware maximum
* split the do_* routines into separate prep, src/dest set, submit stages
* added async_tx support (dependent operations initiation at cleanup time)
* simplified group handling
* added interrupt support (callbacks via tasklets)
* brought the pending depth inline with ioat (i.e. 4 descriptors)
* drop dma mapping methods, suggested by Chris Leech
* don't use inline in C files, Adrian Bunk
* remove static tasklet declarations
* make iop_adma_alloc_slots easier to read and remove chances for a
  corrupted descriptor chain
* fix locking bug in iop_adma_alloc_chan_resources, Benjamin Herrenschmidt
* convert capabilities over to dma_cap_mask_t
* fixup sparse warnings
* add descriptor flush before iop_chan_enable
* checkpatch.pl fixes
* gpl v2 only correction
* move set_src, set_dest, submit to async_tx methods
* move group_list and phys to async_tx

Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
parent f6dff381
Loading
Loading
Loading
Loading
+9 −0
Original line number Diff line number Diff line
@@ -31,4 +31,13 @@ config INTEL_IOATDMA
	default m
	---help---
	  Enable support for the Intel(R) I/OAT DMA engine.

config INTEL_IOP_ADMA
        tristate "Intel IOP ADMA support"
        depends on DMA_ENGINE && (ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX)
	select ASYNC_CORE
        default m
        ---help---
          Enable support for the Intel(R) IOP Series RAID engines.

endmenu
+1 −0
Original line number Diff line number Diff line
obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
obj-$(CONFIG_NET_DMA) += iovlock.o
obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o

drivers/dma/iop-adma.c

0 → 100644
+1467 −0

File added.

Preview size limit exceeded, changes collapsed.

+118 −0
Original line number Diff line number Diff line
/*
 * Copyright © 2006, Intel Corporation.
 *
 * 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.
 *
 */
#ifndef IOP_ADMA_H
#define IOP_ADMA_H
#include <linux/types.h>
#include <linux/dmaengine.h>
#include <linux/interrupt.h>

#define IOP_ADMA_SLOT_SIZE 32
#define IOP_ADMA_THRESHOLD 4

/**
 * struct iop_adma_device - internal representation of an ADMA device
 * @pdev: Platform device
 * @id: HW ADMA Device selector
 * @dma_desc_pool: base of DMA descriptor region (DMA address)
 * @dma_desc_pool_virt: base of DMA descriptor region (CPU address)
 * @common: embedded struct dma_device
 */
struct iop_adma_device {
	struct platform_device *pdev;
	int id;
	dma_addr_t dma_desc_pool;
	void *dma_desc_pool_virt;
	struct dma_device common;
};

/**
 * struct iop_adma_chan - internal representation of an ADMA device
 * @pending: allows batching of hardware operations
 * @completed_cookie: identifier for the most recently completed operation
 * @lock: serializes enqueue/dequeue operations to the slot pool
 * @mmr_base: memory mapped register base
 * @chain: device chain view of the descriptors
 * @device: parent device
 * @common: common dmaengine channel object members
 * @last_used: place holder for allocation to continue from where it left off
 * @all_slots: complete domain of slots usable by the channel
 * @cleanup_watchdog: workaround missed interrupts on iop3xx
 * @slots_allocated: records the actual size of the descriptor slot pool
 * @irq_tasklet: bottom half where iop_adma_slot_cleanup runs
 */
struct iop_adma_chan {
	int pending;
	dma_cookie_t completed_cookie;
	spinlock_t lock; /* protects the descriptor slot pool */
	void __iomem *mmr_base;
	struct list_head chain;
	struct iop_adma_device *device;
	struct dma_chan common;
	struct iop_adma_desc_slot *last_used;
	struct list_head all_slots;
	struct timer_list cleanup_watchdog;
	int slots_allocated;
	struct tasklet_struct irq_tasklet;
};

/**
 * struct iop_adma_desc_slot - IOP-ADMA software descriptor
 * @slot_node: node on the iop_adma_chan.all_slots list
 * @chain_node: node on the op_adma_chan.chain list
 * @hw_desc: virtual address of the hardware descriptor chain
 * @phys: hardware address of the hardware descriptor chain
 * @group_head: first operation in a transaction
 * @slot_cnt: total slots used in an transaction (group of operations)
 * @slots_per_op: number of slots per operation
 * @idx: pool index
 * @unmap_src_cnt: number of xor sources
 * @unmap_len: transaction bytecount
 * @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
 */
struct iop_adma_desc_slot {
	struct list_head slot_node;
	struct list_head chain_node;
	void *hw_desc;
	struct iop_adma_desc_slot *group_head;
	u16 slot_cnt;
	u16 slots_per_op;
	u16 idx;
	u16 unmap_src_cnt;
	size_t unmap_len;
	struct dma_async_tx_descriptor async_tx;
	union {
		u32 *xor_check_result;
		u32 *crc32_result;
	};
};

struct iop_adma_platform_data {
	int hw_id;
	dma_cap_mask_t cap_mask;
	size_t pool_size;
};

#define to_iop_sw_desc(addr_hw_desc) \
	container_of(addr_hw_desc, struct iop_adma_desc_slot, hw_desc)
#define iop_hw_desc_slot_idx(hw_desc, idx) \
	( (void *) (((unsigned long) hw_desc) + ((idx) << 5)) )
#endif