The memory size alignment workaround for a TLB bug on gfx802 was
breaking userptrs because it would attempt to get_user_pages beyond
the end of a VMA. Refine this workaround based on our understanding
of the HW bug. It only affects L2 cacheline allocation, which is
decided by the last page in the cache line (8 entries = 32KB of
address space). Thus aligning memory allocation so that the last
page falls on the end of a 8 entry TLB cache line allows caching
to work correctly.
Imported images require specific alignments. If their size is not
naturally aligned with 8 cache lines, it may have bad TLB cache
performance.
This patch will only have the desired effect if redundant size
padding in KFD is also removed.
Change-Id: I984cbe7fa61fec04d70fa387aaf9aab370eabeb9
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
By using user-allocated pages instead of kernel-allocated pages
from TTM, we're not subject to TTM's self imposed limits on kernel
memory usage. This also paves the way for for more wide-spread use
of HMM on upstream kernels.
Change-Id: Iac82964c98a441e29b7f1986d1be1bb5ccb1e569
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
child process clone vm objects from svm->apertures if parent process
doesn't free memory before fork. fmm_clear_all_mem suppose to clear the
apertures in forked child process but this only works if gpu_vm is not
NULL. parent process call hsaKmtCloseKFD reset gpu_vm to NULL and then
fork, then child process will not clear svm->apertures.
As a result, the child process will allocate vm object with same address
and add to aperture, there are duplicate vm objects with same address
in aperture. Then mapping to GPU will find the wrong vm object and
create incorrect GPU mapping cause rocrtst IPC test VM fault. The issue
happened with HSA_USERPTR_FOR_PAGED_MEM=1.
The fix is to clear vm objects in all apertures in clear_after_fork.
Change-Id: I92e42a967075a634a3f475b915c8242d82077ecb
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
This reverts commit 632ad3a749.
This change causes KFDTest failed on gfx803. The first hsaKmtCreateEvent
call allocate system memory for events_page because global variable
events_page is NULL. And this events page vm address should not be freed
until the process exit.
The change to destrory objects in hsaKmtCloseKFD removes events page. As
a result, KFDTest call hsaKmtOpenKFD again and then allocate memory will
get same events_page vm address on gfx803, and map this vm failed because
the vm conflict with events_page mapping.
KFDTest passed on VG10, gfx906 because allocate memory get different vm
address. hsaKmtCreateEvent still works fine as the driver keeps the
events page mapping of the process.
We should only destroy objects in fork cloned child process regardless
if gpu_vm is NULL or not.
Change-Id: I174ef65321cbd6074c855c2021318fe961c8c72c
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Otherwise the parent call hsaKmtCloseKFD and then fork child process,
child process will duplicate the vm_objects from the parent.
Change-Id: Ia6ffc51cbae983b6a7cdc58ccf3b11ebe4087d97
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Ignore requests to bind to invalid NUMA nodes. This affects only
legacy applications (such as KFDTest) that allocate system memory
as paged memory with a GPU node ID.
Change-Id: I81e514af6d0c1ab2ed5229adeeca1fa0ab2a0685
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
mbind walks through pages to setup vma memory policy. So we need do mmap
to create vma mappings first, then call mbind. mbind will do nothing if
vma does not exist.
And add numa available check before executing mbind, and return NULL to
hsaKmtAllocMemory if mbind failed.
Change-Id: I28ab661885d807ca51ef90e87230669dc80f10ec
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Remove the HSA_DEBUG environment variable that controlled the
creation of these mappings.
This should allow the debugger to attach to a running process and
access VRAM buffers through ptrace without having to do anything
special.
On processes that create many small VRAM mappings, this may cause
regressions due to the per-process mmap limit. However, the
sub-allocator in ROCr should consolidate most small allocations
into 2MB blocks nowadays, for good TLB efficiency. So this is
unlikely to cause problems.
Change-Id: I929da1be0f6cb51ec00a02f3f241d16083e4d95f
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Add a MMIO_REMAP heap type and expose mmio virtual address
through HsaKmtGetNodeMemoryProperties
Change-Id: I1e585e6dfbec8fa7c85f1dda7b89b763a8e2c439
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
HDP conherence registers are remapped at driver level
to an empty page in mmio space (the remapped mmio page).
This change allocate and map the remapped mmio page to
process space.
Change-Id: I89c405c41870a79c5b58eea0d8e564aa35f55182
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
The previous name doorbell_offset is used too extensively throughout
the code and did not reflect the true usage.
Change-Id: I50d33f5c00e82c46cdf4264a78b8f925705bed6a
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Some test case alloc >4gb memory.
Use HSAuint64 in bytes and HSAuint32 in pages.
Change-Id: I0d5e6c299903b5898cfea024178a7a26b9ba3c90
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Map scratch memory to the GPU that specified when allocate the memory
Change-Id: I788f9ef0dccb63b894a75e75cac5f94a60d7ec48
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
EPERM means "operation not permitted" and is returned when CGroup
access checks fail. EACCES means "permission denied" and is returned
when the device file permission bits or access control list don't
allow access.
EPERM can fail silently, since we assume the administrator disabled
a device on purpose in the CGroup. EACCESS should produce an error
message and an info message to check the device file permissions.
Change-Id: Iee4c5584c5fdc4e113c3d760dede6661097b4341
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Device whiltelist controller cgroup allows to track and enforce open and
mknod restrictions on device files. Tasks should works with
/dev/dri/renderN devices that are whitelisted for its cgroup. If a
certain node is not whitelisted it is not an error condition.
Change-Id: I0b997423ccdc00aee98df5b6f04ed6794549604e
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
GPU Resource management can disable some of the GPU nodes.
The Kernel driver could be not aware of this.
Get from Kernel driver information of all the nodes and then filter it.
Change-Id: I4eeb126a5efce2192c35f5d2b72be1811e9ded32
Signed-off-by: Mike Li <Tianxinmike.Li@amd.com>
Handle the case that svm.dgpu_aperture does not exist in vm_find_object.
Change-Id: Ic0983d4f321f1b6248514f2fa25162976e90bd75
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
This reverts commit ab181c46c0.
This fixes ambiguity when looking up GPU addresses with
hsaKmtQueryPointerInfo.
hsa_amd_agents_allow_access uses hsaKmtQueryPointerInfo, and
depends on finding the correct object from a GPU address. Finding
the wrong userptr object based on its CPU address leads to
incorrect GPU mappings and results in VM faults.
Change-Id: I7c5f571ee6e1f9d32687aa3eab6d96944ad032be
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Added a helper vm_find_object that can be used everywhere we need to
lookup objects by their address and optionally size. This unifies
all subtly different, partially incomplete, or broken ways of doing
this in various functions:
* map
* unmap
* register
* deregister
* free
* get_mem_info
* set_mem_user_data
At the same time fix some subtle problems for userptr lookup that
got a bit more complex when the userptr address can match the GPU
address.
Change-Id: I98572d1734fc7688a1d68f6a784e02c8dee90af5
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Currently, all HSA nodes are exposed to user. So the existing
implementation assumes a one to one mapping between user
NodeId and sysfs nodeId.
GPU Resource Management will provide control over the exposed
HSA nodes. This means not all HSA nodes will be exposed to the user.
Decouple it.
The mapping from user NodeId to sysfs NodeId will be local
to topology.c and topology helper functions. For others NodeId
should be sequential from 0 to Number of Nodes exposed to user.
v1: initial implementation
v2: map node id within the topology_* functions
v3: remove two static globals
v4: add bounds check got node id
Change-Id: Id12147ece41d682430f398944bbb339ca906eb1b
Signed-off-by: Mike Li <Tianxinmike.Li@amd.com>
If the CPU addr of a userptr is accessible by the GPU, try to use it
instead of allocating a different GPU address. If something else is
already registered with an overlapping address range, we still need to
allocate a GPU address, because KFD does not support overlapping GPUVM
mappings.
Change-Id: I452963ee45a454f735755a0b43122b9aee5d55be
Signed-off-by: Felix Kuehling <felix.kuehling@gmail.com>
If the GPU virtual address space is >= 47 bits, don't reserve virtual
address space at startup and use mmap to allocate virtual addresses.
Change-Id: Ic935b03c8e78271829fc8e6cfd0e543184aff818
Signed-off-by: Felix Kuehling <felix.kuehling@gmail.com>
So far we have assumed that userptrs are always memory outside
reserved SVM apertures that are mapped into the SVM aperture for
GPU access.
With an unreserved SVM aperture that covers the entire virtual
address range, this distinction will no longer be true. Userptrs
will generally be inside the unreserved SVM aperture. Take that
into consideration when registering, mapping and unmapping virtual
addresses.
We now need a retry logic when looking up buffers from addresses.
If it is not found by its GPU address, try it as a userptr.
We also need to consider the new possibility that a userptr is
registered at the same address for CPU and GPU access. So a buffer
found by its GPU address may also turn out to be a userptr. In
that case use a stricter lookup using the userptr and size (if
the size is known), to identify the correct one of multiple
overlapping objects.
Change-Id: Ia43633aaa40f9fd2a74918ae969a631d2ff68419
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Make dgpu_aperture and dgpu_alt_aperture pointers that can point to
the same actual aperture. This will be useful on GFXv9 and later,
where the MType is not defined by the aperture and we want to have
a single aperture covering the entire virtual address space.
aperture->is_coherent can no longer be a reliable indicator of
coherency. Replace it with different conditions based on mem flags
and svm.disable_cache (from HSA_DISABLE_CACHE environment).
Change-Id: Iefc415b87b8abd96e3916586485a0a55d9b27c19
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
This prepares the code for an alternative aperture management method
that needs to unmap memory differently.
Change-Id: I5494aa5420f85edb8f7857f00c17e1d2e6479a51
Signed-off-by: Felix Kuehling <felix.kuehling@gmail.com>
Only scratch_physical, for scratch-backing memory is managed by the Thunk.
Change-Id: I4716981aa908d9569584dc35f40ffd270a2f9014
Signed-off-by: Felix Kuehling <felix.kuehling@gmail.com>
This parameter was used for non-canonical GPUVM allocations on GFX7/8 APUs
only, to prevent getting NULL pointers from valid allocation after
subtracting the aperture base. The same can be achieved less intrusively
by reserving address space at the start of the aperture during
initialization.
Change-Id: I0aae773f069c2b228824ba464b0612a4d8b489ce
Signed-off-by: Felix Kuehling <felix.kuehling@gmail.com>
On some asics, like tonga, the memory alignment size is as big as 0x8000.
fmm_allocate* alloc vm area with size passed in which is not aligned mostly.
But __fmm_release free vm area with vm_object_t->size which is aligned.
That might cause aperture_release_area fail to free the vm area as the
size might be bigger than zone itself or it just free another vm area
nearby unexpected.
This patch somehow will alloc more space than it needed on tonga.
gfx900+ is not affected.
Change-Id: I5a88c92b08c4e6f6bc05881798f769b55d6debe9
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Previously we used the first dgpu mem, but after careful examination, we
found it only needs to be a GPU, so we modify the code to reflect that as
well.
Change-Id: I069d9b8e247aed55c1f885b79f743ea8e03ddf93
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Unset ret_addr when unmapping the address space reservation. Otherwise
it may try to unmap it again later.
Remember the actual map_size and use it instead of len outside the
reservation loops.
Change-Id: I1a6b3fecfb59e22a713e5ed49c3ed37914cb6fb5
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
simple test of mapping many system memory to gpu.
before
[ RUN ] KFDMemoryTest.MMap
[ ] Using ISA for GFXIP 9.0
[ ] successfully register/map 32GB system memory to gpu
[ OK ] KFDMemoryTest.MMap (36932 ms)
after
[ RUN ] KFDMemoryTest.MMap
[ ] Using ISA for GFXIP 9.0
[ ] successfully register/map 32GB system memory to gpu
[ OK ] KFDMemoryTest.MMap (11441 ms)
So there is 11s VS 36s improvement.
Looks like we can do something similar with vm_area too.
Change-Id: I0349aacdeddec3534016d28176f0fabf632c61fc
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Compare with gpu_mem_count instead of deprecated NUM_OF_SUPPORTED_GPUS
to prevent overflows in case no dGPUs are present.
Change-Id: I71fcb7503ba4c20bffadbdb04cefc4e4027a7df7
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
If opening drm render device fails (usually when the user is not a member
of video group), fmm_init_process_apertures() still returns success,
resulting in weird segfault in a later stage.
Change-Id: Ifbde4481629988944ad7f384d59753c88e287fa9
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Add back missing pthread_mutex_lock.
Handle all error cases in fmm_release.
Change-Id: I8efa561ddadfd769cede5bf86300215ba3fb3dd1
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
__fmm_release actually fails to find the object if address is not
pagesize aligned. And the caller did not notice this as __fmm_release
has no err code return.
So to fix this, move the object lookup in caller, and use vm-object
instead. Also fmm_release will pass up the error code.
Change-Id: Ib8ea1ea5ae844844fd20e8e01f0fdb841d218f2c
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
- Clean up and renumber scratch memory ioctl
- Renumber get_tile_config ioctl
- Renumber set_trap_handler ioctl
- Update KFD_IOC_ALLOC_MEM_FLAGS
- Renumber GPUVM memory management ioctls
- Remove unused SEP_PROCESS_DGPU_APERTURE ioctl
- Update memory management ioctls
Replace device_ids_array_size (in bytes) with n_devices. Fix error
handling and use n_success to update device_id arrays in objects.
This commit breaks the ABI and requires a corresponding KFD change.
Change-Id: Ibf0af5a5188e817c886eab388d1533130fc18293
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Move opening of DRM render nodes from topology to FMM aperture
initialization. Keep the same FDs open for the life time of the
process to match how KFD uses the VMs in the FDs. Call acquire_vm
ioctl during aperture initialization to let KFD use the VMs from
the render nodes.
Change-Id: Ie07d57788cbe685b1841cccc00820c12894a0356
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Query GPUVM aperture limits of all dGPUs to determine SVM aperture
base and limit. This depends on a recent KFD change that reports
the GPUVM apurture limits for dGPUs in the
AMDKFD_IOC_GET_PROCESS_APERTURES_NEW ioctl (drm/amdkfd: Simplify
dGPU SVM aperture handling).
Only initialize SVM aperture once, instead of once per GPU.
Don't call AMDKFD_IOC_SET_PROCESS_DGPU_APERTURE. It's not needed any
more and will not be upstreamed.
Change-Id: Ib3389e8ba18505ba15fc33f45fe8a57e690a565d
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Define dgpu_mem_init before it's used and keep the code close to the
rest of the aperture initialization code.
Change-Id: I14ad11a364524a15affee9186b1298ba7d56d2c9
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Invisible device memory is mmapped as PROT_NONE.
Normal CPU access to the memory is still not allowed but
struct vm_area_struct will be created for the memory address
so ptrace can access the memory via the vma.
Change-Id: I07c69208716c920ccce33e6b494b610b61a0a7c1
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Felix Kuehling
Philip Yang
Oak Zeng
Alex Voicu
Sean Keely
Yong Zhao
xinhui pan
shaoyunl
Gang Ba
Harish Kasiviswanathan
Mike Li
Felix Kuehling