drm/nv40: implement ctxprog/state generation
The context programs are *very* simple compared to the ones used by
the binary driver. There's notes in nv40_grctx.c explaining most of
the things we don't implement. If we discover if/why any of it is
required further down the track, we'll handle it then.
The PGRAPH state generated for each chipset should match what NVIDIA
do almost exactly (there's a couple of exceptions). If someone has
a lot of time on their hands, they could figure out the mapping of
object/method to PGRAPH register and demagic the initial state a little,
it's not terribly important however.
At time of commit, confirmed to be working at least well enough for
accelerated X (and where tested, for 3D apps) on NV40, NV43, NV44, NV46,
NV49, NV4A, NV4B and NV4E.
A module option has been added to force the use of external firmware
blobs if it becomes required.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-12-15 12:02:47 +00:00
|
|
|
/*
|
|
|
|
* Copyright 2009 Red Hat Inc.
|
|
|
|
*
|
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
|
|
* to deal in the Software without restriction, including without limitation
|
|
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
|
|
*
|
|
|
|
* The above copyright notice and this permission notice shall be included in
|
|
|
|
* all copies or substantial portions of the Software.
|
|
|
|
*
|
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
|
|
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
|
|
|
|
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
|
|
|
|
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
|
|
|
|
* OTHER DEALINGS IN THE SOFTWARE.
|
|
|
|
*
|
|
|
|
* Authors: Ben Skeggs
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/firmware.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>
|
drm/nv40: implement ctxprog/state generation
The context programs are *very* simple compared to the ones used by
the binary driver. There's notes in nv40_grctx.c explaining most of
the things we don't implement. If we discover if/why any of it is
required further down the track, we'll handle it then.
The PGRAPH state generated for each chipset should match what NVIDIA
do almost exactly (there's a couple of exceptions). If someone has
a lot of time on their hands, they could figure out the mapping of
object/method to PGRAPH register and demagic the initial state a little,
it's not terribly important however.
At time of commit, confirmed to be working at least well enough for
accelerated X (and where tested, for 3D apps) on NV40, NV43, NV44, NV46,
NV49, NV4A, NV4B and NV4E.
A module option has been added to force the use of external firmware
blobs if it becomes required.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-12-15 12:02:47 +00:00
|
|
|
|
|
|
|
#include "drmP.h"
|
|
|
|
#include "nouveau_drv.h"
|
|
|
|
|
|
|
|
struct nouveau_ctxprog {
|
|
|
|
uint32_t signature;
|
|
|
|
uint8_t version;
|
|
|
|
uint16_t length;
|
|
|
|
uint32_t data[];
|
|
|
|
} __attribute__ ((packed));
|
|
|
|
|
|
|
|
struct nouveau_ctxvals {
|
|
|
|
uint32_t signature;
|
|
|
|
uint8_t version;
|
|
|
|
uint32_t length;
|
|
|
|
struct {
|
|
|
|
uint32_t offset;
|
|
|
|
uint32_t value;
|
|
|
|
} data[];
|
|
|
|
} __attribute__ ((packed));
|
|
|
|
|
|
|
|
int
|
|
|
|
nouveau_grctx_prog_load(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_nouveau_private *dev_priv = dev->dev_private;
|
|
|
|
struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph;
|
|
|
|
const int chipset = dev_priv->chipset;
|
|
|
|
const struct firmware *fw;
|
|
|
|
const struct nouveau_ctxprog *cp;
|
|
|
|
const struct nouveau_ctxvals *cv;
|
|
|
|
char name[32];
|
|
|
|
int ret, i;
|
|
|
|
|
2009-12-16 05:07:45 +00:00
|
|
|
if (pgraph->accel_blocked)
|
|
|
|
return -ENODEV;
|
|
|
|
|
drm/nv40: implement ctxprog/state generation
The context programs are *very* simple compared to the ones used by
the binary driver. There's notes in nv40_grctx.c explaining most of
the things we don't implement. If we discover if/why any of it is
required further down the track, we'll handle it then.
The PGRAPH state generated for each chipset should match what NVIDIA
do almost exactly (there's a couple of exceptions). If someone has
a lot of time on their hands, they could figure out the mapping of
object/method to PGRAPH register and demagic the initial state a little,
it's not terribly important however.
At time of commit, confirmed to be working at least well enough for
accelerated X (and where tested, for 3D apps) on NV40, NV43, NV44, NV46,
NV49, NV4A, NV4B and NV4E.
A module option has been added to force the use of external firmware
blobs if it becomes required.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-12-15 12:02:47 +00:00
|
|
|
if (!pgraph->ctxprog) {
|
|
|
|
sprintf(name, "nouveau/nv%02x.ctxprog", chipset);
|
|
|
|
ret = request_firmware(&fw, name, &dev->pdev->dev);
|
|
|
|
if (ret) {
|
|
|
|
NV_ERROR(dev, "No ctxprog for NV%02x\n", chipset);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-05-15 21:17:40 +00:00
|
|
|
pgraph->ctxprog = kmemdup(fw->data, fw->size, GFP_KERNEL);
|
drm/nv40: implement ctxprog/state generation
The context programs are *very* simple compared to the ones used by
the binary driver. There's notes in nv40_grctx.c explaining most of
the things we don't implement. If we discover if/why any of it is
required further down the track, we'll handle it then.
The PGRAPH state generated for each chipset should match what NVIDIA
do almost exactly (there's a couple of exceptions). If someone has
a lot of time on their hands, they could figure out the mapping of
object/method to PGRAPH register and demagic the initial state a little,
it's not terribly important however.
At time of commit, confirmed to be working at least well enough for
accelerated X (and where tested, for 3D apps) on NV40, NV43, NV44, NV46,
NV49, NV4A, NV4B and NV4E.
A module option has been added to force the use of external firmware
blobs if it becomes required.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-12-15 12:02:47 +00:00
|
|
|
if (!pgraph->ctxprog) {
|
|
|
|
NV_ERROR(dev, "OOM copying ctxprog\n");
|
|
|
|
release_firmware(fw);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
cp = pgraph->ctxprog;
|
|
|
|
if (le32_to_cpu(cp->signature) != 0x5043564e ||
|
|
|
|
cp->version != 0 ||
|
|
|
|
le16_to_cpu(cp->length) != ((fw->size - 7) / 4)) {
|
|
|
|
NV_ERROR(dev, "ctxprog invalid\n");
|
|
|
|
release_firmware(fw);
|
|
|
|
nouveau_grctx_fini(dev);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
release_firmware(fw);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!pgraph->ctxvals) {
|
|
|
|
sprintf(name, "nouveau/nv%02x.ctxvals", chipset);
|
|
|
|
ret = request_firmware(&fw, name, &dev->pdev->dev);
|
|
|
|
if (ret) {
|
|
|
|
NV_ERROR(dev, "No ctxvals for NV%02x\n", chipset);
|
|
|
|
nouveau_grctx_fini(dev);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-05-15 21:17:40 +00:00
|
|
|
pgraph->ctxvals = kmemdup(fw->data, fw->size, GFP_KERNEL);
|
2010-02-02 22:40:30 +00:00
|
|
|
if (!pgraph->ctxvals) {
|
|
|
|
NV_ERROR(dev, "OOM copying ctxvals\n");
|
drm/nv40: implement ctxprog/state generation
The context programs are *very* simple compared to the ones used by
the binary driver. There's notes in nv40_grctx.c explaining most of
the things we don't implement. If we discover if/why any of it is
required further down the track, we'll handle it then.
The PGRAPH state generated for each chipset should match what NVIDIA
do almost exactly (there's a couple of exceptions). If someone has
a lot of time on their hands, they could figure out the mapping of
object/method to PGRAPH register and demagic the initial state a little,
it's not terribly important however.
At time of commit, confirmed to be working at least well enough for
accelerated X (and where tested, for 3D apps) on NV40, NV43, NV44, NV46,
NV49, NV4A, NV4B and NV4E.
A module option has been added to force the use of external firmware
blobs if it becomes required.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-12-15 12:02:47 +00:00
|
|
|
release_firmware(fw);
|
|
|
|
nouveau_grctx_fini(dev);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
cv = (void *)pgraph->ctxvals;
|
|
|
|
if (le32_to_cpu(cv->signature) != 0x5643564e ||
|
|
|
|
cv->version != 0 ||
|
|
|
|
le32_to_cpu(cv->length) != ((fw->size - 9) / 8)) {
|
|
|
|
NV_ERROR(dev, "ctxvals invalid\n");
|
|
|
|
release_firmware(fw);
|
|
|
|
nouveau_grctx_fini(dev);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
release_firmware(fw);
|
|
|
|
}
|
|
|
|
|
|
|
|
cp = pgraph->ctxprog;
|
|
|
|
|
|
|
|
nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0);
|
|
|
|
for (i = 0; i < le16_to_cpu(cp->length); i++)
|
|
|
|
nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA,
|
|
|
|
le32_to_cpu(cp->data[i]));
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
nouveau_grctx_fini(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_nouveau_private *dev_priv = dev->dev_private;
|
|
|
|
struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph;
|
|
|
|
|
|
|
|
if (pgraph->ctxprog) {
|
|
|
|
kfree(pgraph->ctxprog);
|
|
|
|
pgraph->ctxprog = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (pgraph->ctxvals) {
|
|
|
|
kfree(pgraph->ctxprog);
|
|
|
|
pgraph->ctxvals = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
nouveau_grctx_vals_load(struct drm_device *dev, struct nouveau_gpuobj *ctx)
|
|
|
|
{
|
|
|
|
struct drm_nouveau_private *dev_priv = dev->dev_private;
|
|
|
|
struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph;
|
|
|
|
struct nouveau_ctxvals *cv = pgraph->ctxvals;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!cv)
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = 0; i < le32_to_cpu(cv->length); i++)
|
|
|
|
nv_wo32(dev, ctx, le32_to_cpu(cv->data[i].offset),
|
|
|
|
le32_to_cpu(cv->data[i].value));
|
|
|
|
}
|