mirror of
https://github.com/KolibriOS/kolibrios.git
synced 2024-11-28 11:43:09 +03:00
007ea344db
git-svn-id: svn://kolibrios.org@1405 a494cfbc-eb01-0410-851d-a64ba20cac60
484 lines
13 KiB
C++
484 lines
13 KiB
C++
|
|
struct agp_3_5_dev
|
|
{
|
|
link_t link;
|
|
int capndx;
|
|
u32_t maxbw;
|
|
PCITAG tag;
|
|
};
|
|
|
|
static inline list_insert_tail(link_t *new, link_t *old)
|
|
{
|
|
new->prev = old;
|
|
new->next = old->next;
|
|
new->next->prev = new;
|
|
old->next = new;
|
|
}
|
|
|
|
static void agp_3_5_dev_list_insert(link_t *head, link_t *new)
|
|
{
|
|
struct agp_3_5_dev *cur, *n = (struct agp_3_5_dev*)new;
|
|
link_t *pos = head->next;
|
|
|
|
while(pos != head){
|
|
cur = (struct agp_3_5_dev*)pos;
|
|
if(cur->maxbw > n->maxbw)
|
|
break;
|
|
}
|
|
list_insert_tail(new, pos);
|
|
}
|
|
|
|
static void agp_3_5_dev_list_sort(link_t *list, unsigned int ndevs)
|
|
{
|
|
struct agp_3_5_dev *cur;
|
|
link_t *pos, *tmp, *start = list->next;
|
|
u32_t nistat;
|
|
|
|
list_initialize(list);
|
|
|
|
for (pos = start; pos != list; )
|
|
{
|
|
PCITAG tag;
|
|
|
|
cur = (struct agp_3_5_dev*)pos;
|
|
tag = cur->tag;
|
|
|
|
nistat = pciReadLong(tag, cur->capndx+AGPNISTAT);
|
|
cur->maxbw = (nistat >> 16) & 0xff;
|
|
|
|
tmp = pos;
|
|
pos = pos->next;
|
|
agp_3_5_dev_list_insert(list, tmp);
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* Initialize all isochronous transfer parameters for an AGP 3.0
|
|
* node (i.e. a host bridge in combination with the adapters
|
|
* lying behind it...)
|
|
*/
|
|
|
|
static int agp_3_5_isochronous_node_enable(agp_t *bridge,
|
|
link_t *dev_list, unsigned int ndevs)
|
|
{
|
|
/*
|
|
* Convenience structure to make the calculations clearer
|
|
* here. The field names come straight from the AGP 3.0 spec.
|
|
*/
|
|
struct isoch_data {
|
|
u32_t maxbw;
|
|
u32_t n;
|
|
u32_t y;
|
|
u32_t l;
|
|
u32_t rq;
|
|
struct agp_3_5_dev *dev;
|
|
};
|
|
|
|
PCITAG td = bridge->PciTag;
|
|
|
|
// struct list_head *head = &dev_list->list, *pos;
|
|
struct agp_3_5_dev *cur;
|
|
struct isoch_data *master, target;
|
|
unsigned int cdev = 0;
|
|
u32_t mnistat, tnistat, tstatus, mcmd;
|
|
u16_t tnicmd, mnicmd;
|
|
u8_t mcapndx;
|
|
u32_t tot_bw = 0, tot_n = 0, tot_rq = 0, y_max, rq_isoch, rq_async;
|
|
u32_t step, rem, rem_isoch, rem_async;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* We'll work with an array of isoch_data's (one for each
|
|
* device in dev_list) throughout this function.
|
|
*/
|
|
if ((master = malloc(ndevs * sizeof(*master))) == NULL) {
|
|
ret = -1;
|
|
goto get_out;
|
|
}
|
|
|
|
/*
|
|
* Sort the device list by maxbw. We need to do this because the
|
|
* spec suggests that the devices with the smallest requirements
|
|
* have their resources allocated first, with all remaining resources
|
|
* falling to the device with the largest requirement.
|
|
*
|
|
* We don't exactly do this, we divide target resources by ndevs
|
|
* and split them amongst the AGP 3.0 devices. The remainder of such
|
|
* division operations are dropped on the last device, sort of like
|
|
* the spec mentions it should be done.
|
|
*
|
|
* We can't do this sort when we initially construct the dev_list
|
|
* because we don't know until this function whether isochronous
|
|
* transfers are enabled and consequently whether maxbw will mean
|
|
* anything.
|
|
*/
|
|
agp_3_5_dev_list_sort(dev_list, ndevs);
|
|
|
|
tnistat = pciReadLong(td, bridge->capndx+AGPNISTAT);
|
|
tstatus = pciReadLong(td, bridge->capndx+AGPSTAT);
|
|
|
|
/* Extract power-on defaults from the target */
|
|
target.maxbw = (tnistat >> 16) & 0xff;
|
|
target.n = (tnistat >> 8) & 0xff;
|
|
target.y = (tnistat >> 6) & 0x3;
|
|
target.l = (tnistat >> 3) & 0x7;
|
|
target.rq = (tstatus >> 24) & 0xff;
|
|
|
|
y_max = target.y;
|
|
|
|
/*
|
|
* Extract power-on defaults for each device in dev_list. Along
|
|
* the way, calculate the total isochronous bandwidth required
|
|
* by these devices and the largest requested payload size.
|
|
*/
|
|
|
|
link_t *pos;
|
|
|
|
for (pos = dev_list->next; pos != dev_list; pos = pos->next )
|
|
{
|
|
PCITAG dev;
|
|
|
|
cur = (struct agp_3_5_dev*)pos;
|
|
dev = cur->tag;
|
|
|
|
mcapndx = cur->capndx;
|
|
|
|
mnistat = pciReadLong(dev, cur->capndx+AGPNISTAT);
|
|
|
|
master[cdev].maxbw = (mnistat >> 16) & 0xff;
|
|
master[cdev].n = (mnistat >> 8) & 0xff;
|
|
master[cdev].y = (mnistat >> 6) & 0x3;
|
|
master[cdev].dev = cur;
|
|
|
|
tot_bw += master[cdev].maxbw;
|
|
y_max = max(y_max, master[cdev].y);
|
|
|
|
cdev++;
|
|
}
|
|
|
|
/* Check if this configuration has any chance of working */
|
|
if (tot_bw > target.maxbw) {
|
|
dbgprintf("isochronous bandwidth required "
|
|
"by AGP 3.0 devices exceeds that which is supported by "
|
|
"the AGP 3.0 bridge!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
|
|
target.y = y_max;
|
|
|
|
/*
|
|
* Write the calculated payload size into the target's NICMD
|
|
* register. Doing this directly effects the ISOCH_N value
|
|
* in the target's NISTAT register, so we need to do this now
|
|
* to get an accurate value for ISOCH_N later.
|
|
*/
|
|
tnicmd = pciReadWord(td, bridge->capndx+AGPNICMD);
|
|
tnicmd &= ~(0x3 << 6);
|
|
tnicmd |= target.y << 6;
|
|
pciWriteWord(td, bridge->capndx+AGPNICMD, tnicmd);
|
|
|
|
/* Reread the target's ISOCH_N */
|
|
tnistat = pciReadLong(td, bridge->capndx+AGPNISTAT);
|
|
target.n = (tnistat >> 8) & 0xff;
|
|
|
|
/* Calculate the minimum ISOCH_N needed by each master */
|
|
for (cdev=0; cdev<ndevs; cdev++) {
|
|
master[cdev].y = target.y;
|
|
master[cdev].n = master[cdev].maxbw / (master[cdev].y + 1);
|
|
|
|
tot_n += master[cdev].n;
|
|
}
|
|
|
|
/* Exit if the minimal ISOCH_N allocation among the masters is more
|
|
* than the target can handle. */
|
|
if (tot_n > target.n) {
|
|
dbgprintf("number of isochronous "
|
|
"transactions per period required by AGP 3.0 devices "
|
|
"exceeds that which is supported by the AGP 3.0 "
|
|
"bridge!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
|
|
/* Calculate left over ISOCH_N capability in the target. We'll give
|
|
* this to the hungriest device (as per the spec) */
|
|
rem = target.n - tot_n;
|
|
|
|
/*
|
|
* Calculate the minimum isochronous RQ depth needed by each master.
|
|
* Along the way, distribute the extra ISOCH_N capability calculated
|
|
* above.
|
|
*/
|
|
for (cdev=0; cdev<ndevs; cdev++) {
|
|
/*
|
|
* This is a little subtle. If ISOCH_Y > 64B, then ISOCH_Y
|
|
* byte isochronous writes will be broken into 64B pieces.
|
|
* This means we need to budget more RQ depth to account for
|
|
* these kind of writes (each isochronous write is actually
|
|
* many writes on the AGP bus).
|
|
*/
|
|
master[cdev].rq = master[cdev].n;
|
|
if(master[cdev].y > 0x1)
|
|
master[cdev].rq *= (1 << (master[cdev].y - 1));
|
|
|
|
tot_rq += master[cdev].rq;
|
|
}
|
|
master[ndevs-1].n += rem;
|
|
|
|
/* Figure the number of isochronous and asynchronous RQ slots the
|
|
* target is providing. */
|
|
rq_isoch = (target.y > 0x1) ? target.n * (1 << (target.y - 1)) : target.n;
|
|
rq_async = target.rq - rq_isoch;
|
|
|
|
/* Exit if the minimal RQ needs of the masters exceeds what the target
|
|
* can provide. */
|
|
if (tot_rq > rq_isoch) {
|
|
dbgprintf("number of request queue slots "
|
|
"required by the isochronous bandwidth requested by "
|
|
"AGP 3.0 devices exceeds the number provided by the "
|
|
"AGP 3.0 bridge!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
|
|
/* Calculate asynchronous RQ capability in the target (per master) as
|
|
* well as the total number of leftover isochronous RQ slots. */
|
|
step = rq_async / ndevs;
|
|
rem_async = step + (rq_async % ndevs);
|
|
rem_isoch = rq_isoch - tot_rq;
|
|
|
|
/* Distribute the extra RQ slots calculated above and write our
|
|
* isochronous settings out to the actual devices. */
|
|
for (cdev=0; cdev<ndevs; cdev++)
|
|
{
|
|
PCITAG dev;
|
|
|
|
cur = master[cdev].dev;
|
|
dev = cur->tag;
|
|
|
|
mcapndx = cur->capndx;
|
|
|
|
master[cdev].rq += (cdev == ndevs - 1)
|
|
? (rem_async + rem_isoch) : step;
|
|
|
|
mnicmd = pciReadWord(dev, cur->capndx+AGPNICMD);
|
|
mcmd = pciReadLong(dev, cur->capndx+AGPCMD);
|
|
|
|
mnicmd &= ~(0xff << 8);
|
|
mnicmd &= ~(0x3 << 6);
|
|
mcmd &= ~(0xff << 24);
|
|
|
|
mnicmd |= master[cdev].n << 8;
|
|
mnicmd |= master[cdev].y << 6;
|
|
mcmd |= master[cdev].rq << 24;
|
|
|
|
pciWriteLong(dev, cur->capndx+AGPCMD, mcmd);
|
|
pciWriteWord(dev, cur->capndx+AGPNICMD, mnicmd);
|
|
}
|
|
|
|
free_and_exit:
|
|
free(master);
|
|
|
|
get_out:
|
|
return ret;
|
|
}
|
|
|
|
|
|
/*
|
|
* This function basically allocates request queue slots among the
|
|
* AGP 3.0 systems in nonisochronous nodes. The algorithm is
|
|
* pretty stupid, divide the total number of RQ slots provided by the
|
|
* target by ndevs. Distribute this many slots to each AGP 3.0 device,
|
|
* giving any left over slots to the last device in dev_list.
|
|
*/
|
|
static void agp_3_5_nonisochronous_node_enable(agp_t *bridge,
|
|
link_t *dev_list, unsigned int ndevs)
|
|
{
|
|
struct agp_3_5_dev *cur;
|
|
u32_t tstatus, mcmd;
|
|
u32_t trq, mrq, rem;
|
|
unsigned int cdev = 0;
|
|
|
|
tstatus = pciReadLong(bridge->PciTag, bridge->capndx+AGPSTAT);
|
|
|
|
trq = (tstatus >> 24) & 0xff;
|
|
mrq = trq / ndevs;
|
|
|
|
rem = mrq + (trq % ndevs);
|
|
|
|
link_t *pos;
|
|
|
|
for (pos = dev_list->next; cdev<ndevs; cdev++, pos=pos->next) {
|
|
cur = (struct agp_3_5_dev*)pos;
|
|
|
|
mcmd = pciReadLong(cur->tag, cur->capndx+AGPCMD);
|
|
mcmd &= ~(0xff << 24);
|
|
mcmd |= ((cdev == ndevs - 1) ? rem : mrq) << 24;
|
|
pciWriteLong(cur->tag, cur->capndx+AGPCMD, mcmd);
|
|
}
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
* Fully configure and enable an AGP 3.0 host bridge and all the devices
|
|
* lying behind it.
|
|
*/
|
|
int agp_3_5_enable(agp_t *bridge)
|
|
{
|
|
u8_t mcapndx;
|
|
u32_t isoch, arqsz;
|
|
u32_t tstatus, mstatus, ncapid;
|
|
u32_t mmajor;
|
|
u16_t mpstat;
|
|
|
|
link_t dev_list;
|
|
|
|
struct agp_3_5_dev *cur, *pos;
|
|
|
|
unsigned int ndevs = 0;
|
|
PCITAG dev = 0;
|
|
int ret = 0;
|
|
|
|
/* Extract some power-on defaults from the target */
|
|
tstatus = pciReadLong(bridge->PciTag, bridge->capndx+AGPSTAT);
|
|
isoch = (tstatus >> 17) & 0x1;
|
|
if (isoch == 0) /* isoch xfers not available, bail out. */
|
|
return -1;
|
|
|
|
arqsz = (tstatus >> 13) & 0x7;
|
|
|
|
list_initialize(&dev_list);
|
|
|
|
/* Find all AGP devices, and add them to dev_list. */
|
|
for_each_pci_dev(dev)
|
|
{
|
|
u16_t devclass;
|
|
|
|
mcapndx = pci_find_capability(dev, PCI_CAP_ID_AGP);
|
|
if (mcapndx == 0)
|
|
continue;
|
|
|
|
devclass = pciReadWord(dev, 0x0A);
|
|
|
|
switch (devclass & 0xff00)
|
|
{
|
|
case 0x0600: /* Bridge */
|
|
/* Skip bridges. We should call this function for each one. */
|
|
continue;
|
|
|
|
case 0x0001: /* Unclassified device */
|
|
/* Don't know what this is, but log it for investigation. */
|
|
if (mcapndx != 0) {
|
|
dbgprintf("Wacky, found unclassified AGP device.\n");
|
|
}
|
|
continue;
|
|
|
|
case 0x0300: /* Display controller */
|
|
case 0x0400: /* Multimedia controller */
|
|
if((cur = malloc(sizeof(*cur))) == NULL)
|
|
{
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
cur->tag = dev;
|
|
list_prepend(&cur->link, &dev_list);
|
|
ndevs++;
|
|
continue;
|
|
|
|
default:
|
|
continue;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Take an initial pass through the devices lying behind our host
|
|
* bridge. Make sure each one is actually an AGP 3.0 device, otherwise
|
|
* exit with an error message. Along the way store the AGP 3.0
|
|
* cap_ptr for each device
|
|
*/
|
|
|
|
cur = (struct agp_3_5_dev*)dev_list.next;
|
|
|
|
while(&cur->link != &dev_list)
|
|
{
|
|
dev = cur->tag;
|
|
|
|
mpstat = pciReadWord(dev, PCI_STATUS);
|
|
if ((mpstat & PCI_STATUS_CAP_LIST) == 0)
|
|
continue;
|
|
|
|
mcapndx = pciReadByte(dev, PCI_CAPABILITY_LIST);
|
|
if (mcapndx != 0) {
|
|
do {
|
|
ncapid = pciReadLong(dev, mcapndx);
|
|
if ((ncapid & 0xff) != 2)
|
|
mcapndx = (ncapid >> 8) & 0xff;
|
|
}
|
|
while (((ncapid & 0xff) != 2) && (mcapndx != 0));
|
|
}
|
|
|
|
if (mcapndx == 0) {
|
|
dbgprintf("woah! Non-AGP device "
|
|
"found on the secondary bus of an AGP 3.5 bridge!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
|
|
mmajor = (ncapid >> AGP_MAJOR_VERSION_SHIFT) & 0xf;
|
|
if (mmajor < 3) {
|
|
dbgprintf("woah! AGP 2.0 device "
|
|
"found on the secondary bus of an AGP 3.5 "
|
|
"bridge operating with AGP 3.0 electricals!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
|
|
cur->capndx = mcapndx;
|
|
|
|
mstatus = pciReadLong(dev, cur->capndx+AGPSTAT);
|
|
|
|
if (((mstatus >> 3) & 0x1) == 0) {
|
|
dbgprintf("woah! AGP 3.x device "
|
|
"not operating in AGP 3.x mode found on the "
|
|
"secondary bus of an AGP 3.5 bridge operating "
|
|
"with AGP 3.0 electricals!\n");
|
|
ret = -1;
|
|
goto free_and_exit;
|
|
}
|
|
cur = (struct agp_3_5_dev*)cur->link.next;
|
|
}
|
|
|
|
/*
|
|
* Call functions to divide target resources amongst the AGP 3.0
|
|
* masters. This process is dramatically different depending on
|
|
* whether isochronous transfers are supported.
|
|
*/
|
|
if (isoch) {
|
|
ret = agp_3_5_isochronous_node_enable(bridge, &dev_list, ndevs);
|
|
if (ret) {
|
|
dbgprintf("Something bad happened setting "
|
|
"up isochronous xfers. Falling back to "
|
|
"non-isochronous xfer mode.\n");
|
|
} else {
|
|
goto free_and_exit;
|
|
}
|
|
}
|
|
agp_3_5_nonisochronous_node_enable(bridge, &dev_list, ndevs);
|
|
|
|
free_and_exit:
|
|
/* Be sure to free the dev_list */
|
|
for (pos = (struct agp_3_5_dev*)dev_list.next; &pos->link != &dev_list; )
|
|
{
|
|
cur = pos;
|
|
|
|
pos = (struct agp_3_5_dev*)pos->link.next;
|
|
free(cur);
|
|
}
|
|
|
|
get_out:
|
|
return ret;
|
|
}
|