linux/drivers/firewire/core-iso.c

366 lines
9.5 KiB
C
Raw Normal View History

/*
* Isochronous I/O functionality:
* - Isochronous DMA context management
* - Isochronous bus resource management (channels, bandwidth), client side
*
* Copyright (C) 2006 Kristian Hoegsberg <krh@bitplanet.net>
*
* 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.
*/
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/firewire.h>
#include <linux/firewire-constants.h>
#include <linux/kernel.h>
#include <linux/mm.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <asm/byteorder.h>
#include "core.h"
/*
* Isochronous DMA context management
*/
int fw_iso_buffer_init(struct fw_iso_buffer *buffer, struct fw_card *card,
int page_count, enum dma_data_direction direction)
{
int i, j;
dma_addr_t address;
buffer->page_count = page_count;
buffer->direction = direction;
buffer->pages = kmalloc(page_count * sizeof(buffer->pages[0]),
GFP_KERNEL);
if (buffer->pages == NULL)
goto out;
for (i = 0; i < buffer->page_count; i++) {
buffer->pages[i] = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
if (buffer->pages[i] == NULL)
goto out_pages;
address = dma_map_page(card->device, buffer->pages[i],
0, PAGE_SIZE, direction);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 02:44:49 +00:00
if (dma_mapping_error(card->device, address)) {
__free_page(buffer->pages[i]);
goto out_pages;
}
set_page_private(buffer->pages[i], address);
}
return 0;
out_pages:
for (j = 0; j < i; j++) {
address = page_private(buffer->pages[j]);
dma_unmap_page(card->device, address,
PAGE_SIZE, direction);
__free_page(buffer->pages[j]);
}
kfree(buffer->pages);
out:
buffer->pages = NULL;
return -ENOMEM;
}
EXPORT_SYMBOL(fw_iso_buffer_init);
int fw_iso_buffer_map(struct fw_iso_buffer *buffer, struct vm_area_struct *vma)
{
unsigned long uaddr;
int i, err;
uaddr = vma->vm_start;
for (i = 0; i < buffer->page_count; i++) {
err = vm_insert_page(vma, uaddr, buffer->pages[i]);
if (err)
return err;
uaddr += PAGE_SIZE;
}
return 0;
}
void fw_iso_buffer_destroy(struct fw_iso_buffer *buffer,
struct fw_card *card)
{
int i;
dma_addr_t address;
for (i = 0; i < buffer->page_count; i++) {
address = page_private(buffer->pages[i]);
dma_unmap_page(card->device, address,
PAGE_SIZE, buffer->direction);
__free_page(buffer->pages[i]);
}
kfree(buffer->pages);
buffer->pages = NULL;
}
EXPORT_SYMBOL(fw_iso_buffer_destroy);
/* Convert DMA address to offset into virtually contiguous buffer. */
size_t fw_iso_buffer_lookup(struct fw_iso_buffer *buffer, dma_addr_t completed)
{
int i;
dma_addr_t address;
ssize_t offset;
for (i = 0; i < buffer->page_count; i++) {
address = page_private(buffer->pages[i]);
offset = (ssize_t)completed - (ssize_t)address;
if (offset > 0 && offset <= PAGE_SIZE)
return (i << PAGE_SHIFT) + offset;
}
return 0;
}
struct fw_iso_context *fw_iso_context_create(struct fw_card *card,
int type, int channel, int speed, size_t header_size,
fw_iso_callback_t callback, void *callback_data)
{
struct fw_iso_context *ctx;
ctx = card->driver->allocate_iso_context(card,
type, channel, header_size);
if (IS_ERR(ctx))
return ctx;
ctx->card = card;
ctx->type = type;
ctx->channel = channel;
ctx->speed = speed;
ctx->header_size = header_size;
ctx->callback.sc = callback;
ctx->callback_data = callback_data;
return ctx;
}
EXPORT_SYMBOL(fw_iso_context_create);
void fw_iso_context_destroy(struct fw_iso_context *ctx)
{
ctx->card->driver->free_iso_context(ctx);
}
EXPORT_SYMBOL(fw_iso_context_destroy);
int fw_iso_context_start(struct fw_iso_context *ctx,
int cycle, int sync, int tags)
{
return ctx->card->driver->start_iso(ctx, cycle, sync, tags);
}
EXPORT_SYMBOL(fw_iso_context_start);
int fw_iso_context_set_channels(struct fw_iso_context *ctx, u64 *channels)
{
return ctx->card->driver->set_iso_channels(ctx, channels);
}
int fw_iso_context_queue(struct fw_iso_context *ctx,
struct fw_iso_packet *packet,
struct fw_iso_buffer *buffer,
unsigned long payload)
{
return ctx->card->driver->queue_iso(ctx, packet, buffer, payload);
}
EXPORT_SYMBOL(fw_iso_context_queue);
int fw_iso_context_stop(struct fw_iso_context *ctx)
{
return ctx->card->driver->stop_iso(ctx);
}
EXPORT_SYMBOL(fw_iso_context_stop);
/*
* Isochronous bus resource management (channels, bandwidth), client side
*/
static int manage_bandwidth(struct fw_card *card, int irm_id, int generation,
int bandwidth, bool allocate, __be32 data[2])
{
int try, new, old = allocate ? BANDWIDTH_AVAILABLE_INITIAL : 0;
/*
* On a 1394a IRM with low contention, try < 1 is enough.
* On a 1394-1995 IRM, we need at least try < 2.
* Let's just do try < 5.
*/
for (try = 0; try < 5; try++) {
new = allocate ? old - bandwidth : old + bandwidth;
if (new < 0 || new > BANDWIDTH_AVAILABLE_INITIAL)
return -EBUSY;
data[0] = cpu_to_be32(old);
data[1] = cpu_to_be32(new);
switch (fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP,
irm_id, generation, SCODE_100,
CSR_REGISTER_BASE + CSR_BANDWIDTH_AVAILABLE,
data, 8)) {
case RCODE_GENERATION:
/* A generation change frees all bandwidth. */
return allocate ? -EAGAIN : bandwidth;
case RCODE_COMPLETE:
if (be32_to_cpup(data) == old)
return bandwidth;
old = be32_to_cpup(data);
/* Fall through. */
}
}
return -EIO;
}
static int manage_channel(struct fw_card *card, int irm_id, int generation,
u32 channels_mask, u64 offset, bool allocate, __be32 data[2])
{
__be32 bit, all, old;
int channel, ret = -EIO, retry = 5;
old = all = allocate ? cpu_to_be32(~0) : 0;
for (channel = 0; channel < 32; channel++) {
if (!(channels_mask & 1 << channel))
continue;
ret = -EBUSY;
bit = cpu_to_be32(1 << (31 - channel));
if ((old & bit) != (all & bit))
continue;
data[0] = old;
data[1] = old ^ bit;
switch (fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP,
irm_id, generation, SCODE_100,
offset, data, 8)) {
case RCODE_GENERATION:
/* A generation change frees all channels. */
return allocate ? -EAGAIN : channel;
case RCODE_COMPLETE:
if (data[0] == old)
return channel;
old = data[0];
/* Is the IRM 1394a-2000 compliant? */
if ((data[0] & bit) == (data[1] & bit))
continue;
/* 1394-1995 IRM, fall through to retry. */
default:
if (retry) {
retry--;
channel--;
} else {
ret = -EIO;
}
}
}
return ret;
}
static void deallocate_channel(struct fw_card *card, int irm_id,
int generation, int channel, __be32 buffer[2])
{
u32 mask;
u64 offset;
mask = channel < 32 ? 1 << channel : 1 << (channel - 32);
offset = channel < 32 ? CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI :
CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO;
manage_channel(card, irm_id, generation, mask, offset, false, buffer);
}
/**
* fw_iso_resource_manage() - Allocate or deallocate a channel and/or bandwidth
*
* In parameters: card, generation, channels_mask, bandwidth, allocate
* Out parameters: channel, bandwidth
* This function blocks (sleeps) during communication with the IRM.
*
* Allocates or deallocates at most one channel out of channels_mask.
* channels_mask is a bitfield with MSB for channel 63 and LSB for channel 0.
* (Note, the IRM's CHANNELS_AVAILABLE is a big-endian bitfield with MSB for
* channel 0 and LSB for channel 63.)
* Allocates or deallocates as many bandwidth allocation units as specified.
*
* Returns channel < 0 if no channel was allocated or deallocated.
* Returns bandwidth = 0 if no bandwidth was allocated or deallocated.
*
* If generation is stale, deallocations succeed but allocations fail with
* channel = -EAGAIN.
*
* If channel allocation fails, no bandwidth will be allocated either.
* If bandwidth allocation fails, no channel will be allocated either.
* But deallocations of channel and bandwidth are tried independently
* of each other's success.
*/
void fw_iso_resource_manage(struct fw_card *card, int generation,
u64 channels_mask, int *channel, int *bandwidth,
bool allocate, __be32 buffer[2])
{
u32 channels_hi = channels_mask; /* channels 31...0 */
u32 channels_lo = channels_mask >> 32; /* channels 63...32 */
int irm_id, ret, c = -EINVAL;
spin_lock_irq(&card->lock);
irm_id = card->irm_node->node_id;
spin_unlock_irq(&card->lock);
if (channels_hi)
c = manage_channel(card, irm_id, generation, channels_hi,
CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI,
allocate, buffer);
if (channels_lo && c < 0) {
c = manage_channel(card, irm_id, generation, channels_lo,
CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO,
allocate, buffer);
if (c >= 0)
c += 32;
}
*channel = c;
if (allocate && channels_mask != 0 && c < 0)
*bandwidth = 0;
if (*bandwidth == 0)
return;
ret = manage_bandwidth(card, irm_id, generation, *bandwidth,
allocate, buffer);
if (ret < 0)
*bandwidth = 0;
if (allocate && ret < 0) {
if (c >= 0)
deallocate_channel(card, irm_id, generation, c, buffer);
*channel = ret;
}
}
EXPORT_SYMBOL(fw_iso_resource_manage);