Remove use of linux/kernel.h and linux/compiler.h. We don't use
anything in those headers.
Also replace use of linux/bitops.h with new wrapper nvgpu/bitops.h.
JIRA NVGPU-13
Change-Id: Iefa6b4598d5a5e7fc386c0a7a554e778a87010d6
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1460777
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Add back the automatic '\n' addition for logging functions. Since the
driver was developed like this it is simpler to add this back.
Change-Id: Iff097d667cf0fac7d64dc916a1d1b3b4f8c519ff
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1458140
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add nvgpu_* wrappers for determining if we're running in simulation
or silicon, and if we're running in hypervisor.
The new wrappers require struct gk20a pointer, and gk20a_fence_wait()
did not have access to one. Add struct gk20a pointer as the first
parameter.
JIRA NVGPU-16
Change-Id: I73b2b8f091ca29fb1827054abd2adaf583710331
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1331565
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
gk20a_err() and gk20a_warn() require a struct device pointer,
which is not portable across operating systems. The new nvgpu_err()
and nvgpu_warn() macros take struct gk20a pointer. Convert code
to use the more portable macros.
JIRA NVGPU-16
Change-Id: Ie3cf6f278dd4468832de3c3a6a6b601d55185461
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1459818
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
gk20a_err() and gk20a_warn() require a struct device pointer,
which is not portable across operating systems. The new nvgpu_err()
and nvgpu_warn() macros take struct gk20a pointer. Convert code
to use the more portable macros.
JIRA NVGPU-16
Change-Id: Ia51f36d94c5ce57a5a0ab83b3c83a6bce09e2d5c
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1331694
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
Use nvgpu list APIs instead of linux list APIs
to store pending semaphore waits
Jira NVGPU-13
Change-Id: I42fc6c6233e39f475a939ddd6a81c0cda851b6bf
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1454693
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
gk20a_err() and gk20a_warn() require a struct device pointer,
which is not portable across operating systems. The new nvgpu_err()
and nvgpu_warn() macros take struct gk20a pointer. Convert code
to use the more portable macros.
JIRA NVGPU-16
Change-Id: I1a63fbbe21f14f203f10a6abd4c16bcda97db524
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1457343
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
gk20a_err() and gk20a_warn() require a struct device pointer,
which is not portable across operating systems. The new nvgpu_err()
and nvgpu_warn() macros take struct gk20a pointer. Convert code
to use the more portable macros.
JIRA NVGPU-16
Change-Id: Ic5a48ca066712b14140909a34e639c1d2b99554b
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1457342
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Rename the nvgpu DMA APIs from gk20a_gmmu_alloc* to nvgpu_dma_alloc*.
This better reflects the purpose of the APIs (to allocate DMA suitable
memory) and avoids confusion with GMMU related code.
JIRA NVGPU-12
Change-Id: I673d607db56dd6e44f02008dc7b5293209ef67bf
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1325548
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Make an nvgpu DMA API include file so that the intricacies of the
Linux DMA API can be hidden from the calling code.
Also document the nvgpu DMA API.
JIRA NVGPU-12
Change-Id: I7578e4c726ad46344b7921179d95861858e9a27e
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1323326
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Renaming was done with the following command:
$ find -type f | \
xargs sed -i 's/struct mem_desc/struct nvgpu_mem/g'
Also rename mem_desc.[ch] to nvgpu_mem.[ch].
JIRA NVGPU-12
Change-Id: I69395758c22a56aa01e3dffbcded70a729bf559a
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1325547
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Split the mem_desc code out from the MM code. This is to help
simplify the MM code and make it easier to abstract the DMA
allocation routines.
JIRA NVGPU-12
Change-Id: I2ccb643efe6bbed80d1360a580ff5593acb407bd
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1323324
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In order to remove nvgpu's dependency from Linux,
add nvgpu's own rbtree implementation
Define a rbtree node as
struct nvgpu_rbtree_node *node;
Add below APIs to support rbtree operations
nvgpu_rbtree_insert()
- insert a new node into tree
nvgpu_rbtree_unlink()
- remove a node from tree
nvgpu_rbtree_search()
- search a key in tree
nvgpu_rbtree_range_search()
- search a node with key falling in range
nvgpu_rbtree_less_than_search()
- search a node with key lesser than given key
nvgpu_rbtree_enum_start()
- start enumerating a tree
nvgpu_rbtree_enum_next()
- find next node in enumeration
Jira NVGPU-13
Change-Id: Idceb375dc20d9411799c92608b0264e59886bf68
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1331537
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Replace the last of the Linux kmem API usage with nvgpu kmem
calls instead. Several places are left alone - allocating the
struct gk20a in particular.
Also one function was updated in the clk code to take a struct
gk20a as an argument so that it could use nvgpu_kmalloc().
Bug 1799159
Bug 1823380
Change-Id: I84fc3f8e19c63d6265bac6098dc727d93e3ff613
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1331702
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Update the debugging APIs in nvgpu to be more coherent and less dependent
on Linux kernel APIs and data structures. The old API is maintained for
backwards compatibility but the prints themselves are changed.
The old API now prints stuff like this:
[ 46.376077] nvgpu: gk20a_channel_suspend:3430 [DBG] suspend channel 508
[ 46.376242] nvgpu: gk20a_channel_suspend:3430 [DBG] suspend channel 509
[ 46.376359] nvgpu: gk20a_channel_suspend:3430 [DBG] suspend channel 510
[ 46.376466] nvgpu: gk20a_channel_suspend:3430 [DBG] suspend channel 511
[ 46.376604] nvgpu: gk20a_fifo_update_runlist_locked:3090 [DBG] runlist_id : 0, switch to new buffer 0x 4003a0000
[ 46.378348] nvgpu: gk20a_mm_l2_flush:5259 [DBG] l2_flush_dirty 0x2
[ 46.378562] nvgpu: clk_config_pll:170 [DBG] low_PL 1(div1), high_PL 2(div2)
[ 46.378684] nvgpu: clk_config_pll:170 [DBG] low_PL 8(div8), high_PL 17(div17)
Each line starts with 'nvgpu:' since this is the nvgpu driver. Then there's
the function name which is is right justified and post-fixed with a line
number. This keeps all statements lined up so long as the function name does
not exceed the length of characters alloted for function names (33 currently).
Lines are also left justified with 4 available spaces since there are currently
no source files with over 9999 lines. The type of message (DBG, WRN, ERR) is
then printed in brackets. Finally there's whatever message is to be printed.
The new API will be largely the same except there will be an additional
print of the GPU that the message has originated from in order to help debug
cases where both an iGPU and dGPU are active. Also the implicit newline
added in the legacy API has been removed. This is inline with essentially
every other print function in the C world. There are numerous places where
'\n' is added despite it not being needed which results in log files being
littered with blank lines. This makes the logs much harder to read.
Bug ...
Change-Id: I7bc87f2dbbaebf6eb6c9de1a629a0e2963e1804c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1329487
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move TSG IOCTL specific code to Linux module. This clears most
Linux dependencies from tsg_gk20a.c.
Move also remaining file_operations declarations from channel_gk20a.h
to ioctl_channel.h.
JIRA NVGPU-32
Change-Id: Idcc2a525ebe12b30db46c3893a2735509c41ff39
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1330805
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add abstractions for the following:
msleep()
udelay()
usleep_range()
These functions are only a subset of the available Linux delay and sleep
functions but this seems to be what we use and what is actually useful
for driver development.
Bug 1799159
Jira NVGPU-16
Change-Id: I1a25b66314f365432f2f0a5ff1b3a0a5689fc047
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1309087
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Use nvgpu list APIs instead of linux list APIs
to store chunks of page allocator
Jira NVGPU-13
Change-Id: I63375fc2df683e018c48a90b76eca368438cc32f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1326814
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Split as_gk20a.c into two parts:
common/linux/ioctl_as.c deals with as related devnodes and ioctls.
This file contains all the Linux specific parts of as_gk20a.c.
common/as.c deals with general as_gk20a maintenance and is Linux
independent.
JIRA NVGPU-16
Change-Id: I2d8541e0bd6ce159dc6e4de8e819dfcff0fa8f80
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1330803
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Move all code related to ctrl devnode to under Linux module.
JIRA NVGPU-16
Change-Id: I834b46ec4172076d7bde459168f1e6bc8c5d6c0c
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1330802
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Move Linux specific code to create devnodes to Linux module.
JIRA NVGPU-16
Change-Id: I7f8f74d72f16857973da029b9f949ee8b553eb59
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1330801
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Move the name field from struct gpu_ops up to struct gk20a. The field
is not a function op, so it doesn't belong in gpu_ops.
Replace all uses of dev_name() with use of g->name when possible.
JIRA NVGPU-16
Change-Id: Ic6e99e39258cbf3bb7c806962cbbd7de5126688f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1328534
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Use the new kmem API functions in common/* and common/mm/*.
Add a struct gk20a pointer to struct nvgpu_allocator in order
to store the gk20a pointer used for allocating memory.
Bug 1799159
Bug 1823380
Change-Id: I881ea9545e8a8f0b75d77a1e35dd1812e0bb654e
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1318315
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
bios tables are packed data structures. keeping
packed structrues inside union and assigning values
from it does not work.
bug 200287822
Change-Id: I1df9541495b96786412533570c51d779bfd0f43f
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1326798
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Don't use enum dma_attr in the gk20a_gmmu_alloc_attr* functions, but
define nvgpu-internal flags for no kernel mapping, force contiguous, and
read only modes. Store the flags in the allocated struct mem_desc and
only use gk20a_gmmu_free, remove gk20a_gmmu_free_attr. This helps in OS
abstraction. Rename the notion of attr to flags.
Add implicit NVGPU_DMA_NO_KERNEL_MAPPING to all vidmem buffers
allocated via gk20a_gmmu_alloc_vid for consistency.
Fix a bug in gk20a_gmmu_alloc_map_attr that dropped the attr
parameter accidentally.
Bug 1853519
Change-Id: I1ff67dff9fc425457ae445ce4976a780eb4dcc9f
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1321101
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The main driver structure is not refcounted properly,
so when the driver unload, file desciptors associated to the
driver are kept open with dangling references to the main object.
This change adds referencing to the gk20a structure.
bug 200277762
JIRA: EVLR-1023
Change-Id: Id892e9e1677a344789e99bf649088c076f0bf8de
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1317420
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The Linux timer code prints an error message containing the caller when
a timeout happens. The caller is formatted as a function name instead of
a pointer, so don't print 0x in front of it.
Bug 1799159
Change-Id: I4f86d885aba78ca20ba025a91c8c940d3c927d58
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1315749
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Implement kmem abstraction and tracking in nvgpu. The abstraction
helps move nvgpu's core code away from being Linux dependent and
allows kmem allocation tracking to be done for Linux and any other
OS supported by nvgpu.
Bug 1799159
Bug 1823380
Change-Id: Ieaae4ca1bbd1d4db4a1546616ab8b9fc53a4079d
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1283828
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Implement a worker thread to replace the delayed works in channel
watchdog and job cleanups. Watchdog runs by polling the channel states
periodically, and job cleanup is performed on channels that are appended
on a work queue consumed by the worker thread. Handling both of these
two in the same thread makes it impossible for them to cause a deadlock,
as has previously happened.
The watchdog takes references to channels during checking and possibly
recovering channels. Jobs in the cleanup queue have an additional
reference taken which is released after the channel is processed. The
worker is woken up from periodic sleep when channels are added to the
queue.
Currently, the queue is only used for job cleanups, but it is extendable
for other per-channel works too. The worker can also process other
periodic actions dependent on channels.
Neither the semantics of timeout handling or of job cleanups are yet
significantly changed - this patch only serializes them into one
background thread.
Each job that needs cleanup is tracked and holds a reference to its
channel and a power reference, and timeouts can only be processed on
channels that are tracked, so the thread will always be idle if the
system is going to be suspended, so there is currently no need to
explicitly suspend or stop it.
Bug 1848834
Bug 1851689
Bug 1814773
Bug 200270332
Jira NVGPU-21
Change-Id: I355101802f50841ea9bd8042a017f91c931d2dc7
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1297183
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
API DEFINE_MUTEX() is defined in Linux and might
not be available in other OSs.
Hence remove its usage from nvgpu
Declare and explicitly initialize below mutexes
for both nvgpu and vgpu
g->mm.priv_lock
g->mm.tlb_lock
Jira NVGPU-13
Change-Id: If72885a6da0227a1552303206172f1f2b751471d
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1298042
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Instead of using Linux APIs for mutex and spinlocks
directly, use new APIs defined in <nvgpu/lock.h>
Replace Linux specific mutex/spinlock declaration,
init, lock, unlock APIs with new APIs
e.g
struct mutex is replaced by struct nvgpu_mutex and
mutex_lock() is replaced by nvgpu_mutex_acquire()
And also include <nvgpu/lock.h> instead of including
<linux/mutex.h> and <linux/spinlock.h>
Add explicit nvgpu/lock.h includes to below
files to fix complilation failures.
gk20a/platform_gk20a.h
include/nvgpu/allocator.h
Jira NVGPU-13
Change-Id: I81a05d21ecdbd90c2076a9f0aefd0e40b215bd33
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1293187
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Most of BIOS parsing code is not specific to any particular GPU. Move
most of the code to generic files, and leave only chip specific parts
dealing with microcontroller boot into chip specific files.
As most of the parsing is generic, they do not need to be called via
HALs so remove the HALs and change the calls into direct function
calls.
All definitions meant to be used outside BIOS code itself are now in
<nvgpu/bios.h>
Change-Id: Id48e94c74511d6e95645e90e5bba5c12ef8da45d
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1302222
GVS: Gerrit_Virtual_Submit
Change the prefix in the semaphore code to 'nvgpu_' since this code
is global to all chips.
Bug 1799159
Change-Id: Ic1f3e13428882019e5d1f547acfe95271cc10da5
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284628
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Move semaphore_gk20a.c drivers/gpu/nvgpu/common/ since the semaphore
code is common to all chips.
Move the semaphore_gk20a.h header file to drivers/gpu/nvgpu/include/nvgpu
and rename it to semaphore.h. Also update all places where the header
is inluced to use the new path.
This revealed an odd location for the enum gk20a_mem_rw_flag. This should
be in the mm headers. As a result many places that did not need anything
semaphore related had to include the semaphore header file. Fixing this
oddity allowed the semaphore include to be removed from many C files that
did not need it.
Bug 1799159
Change-Id: Ie017219acf34c4c481747323b9f3ac33e76e064c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284627
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Move nvgpu_common.c to drivers/gpu/nvgpu/common since it is a common
C file to all drivers.
Similarly move nvgpu_common.h to drivers/gpu/nvgpu/include/nvgpu since
this follows the new include guidelines.
Bug 1799159
Change-Id: I00ebed289973b27704c2cff073526e36505bf699
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284612
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Instead of using a single static kmem_cache for each type of
data structure the allocators may want to allocate each
allocator now has its own instance of the kmem_cache. This is
done so that each GPU driver instance can accurately track how
much memory it is using.
In order to support this on older kernels a new NVGPU API has
been made,
nvgpu_kmem_cache_create(struct gk20a *g, size_t size)
To handle the possibility that caches cannot be created with
the same name.
This patch also fixes numerous places where kfree() was wrongly
used to free kmem_cache allocs.
Bug 1799159
Bug 1823380
Change-Id: Id674f9a5445fde3f95db65ad6bf3ea990444603d
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1283826
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
The basic structure of this patch is to make the small page allocator
and the large page allocator into pointers (where they used to be just
structs). Then assign each of those pointers to the same actual
allocator since the buddy allocator has supported mixed page sizes
since its inception.
For the rest of the driver some changes had to be made in order to
actually support mixed pages in a single address space.
1. Unifying the allocation page size determination
Since the allocation and map operations happen at distinct
times both mapping and allocation of GVA space must agree
on page size. This is because the allocation has to separate
allocations into separate PDEs to avoid the necessity of
supporting mixed PDEs.
To this end a function __get_pte_size() was introduced which
is used both by the balloc code and the core GPU MM code. It
determines page size based only on the length of the mapping/
allocation.
2. Fixed address allocation + page size
Similar to regular mappings/GVA allocations fixed address
mapping page size determination had to be modified. In the
past the address of the mapping determined page size since
the address space split was by address (low addresses were
small pages, high addresses large pages). Since that is no
longer the case the page size field in the reserve memory
ioctl is now honored by the mapping code. When, for instance,
CUDA makes a memory reservation it specifies small or large
pages. When CUDA requests mappings to be made within that
address range the page size is then looked up in the reserved
memory struct.
Fixed address reservations were also modified to now always
allocate at a PDE granularity (64M or 128M depending on
large page size. This prevents non-fixed allocations from
ending up in the same PDE and causing kernel panics or GMMU
faults.
3. The rest...
The rest of the changes are just by products of the above.
Lots of places required minor updates to use a pointer to
the GVA allocator struct instead of the struct itself.
Lastly, this change is not truly complete. More work remains to be
done in order to fully remove the notion that there was such a thing
as separate address spaces for different page sizes. Basically after
this patch what remains is cleanup and proper documentation.
Bug 1396644
Bug 1729947
Change-Id: If51ab396a37ba16c69e434adb47edeef083dce57
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1265300
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Move the GPU allocators to common/mm/ since the allocators are common
code across all GPUs. Also rename the allocator code to move away from
gk20a_ prefixed structs and functions.
This caused one issue with the nvgpu_alloc() and nvgpu_free() functions.
There was a function for allocating either with kmalloc() or vmalloc()
depending on the size of the allocation. Those have now been renamed to
nvgpu_kalloc() and nvgpu_kfree().
Bug 1799159
Change-Id: Iddda92c013612bcb209847084ec85b8953002fa5
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1274400
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
