| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Before, every time fdinfo is queried we try to lock all the BOs in the
VM and calculate memory usage from scratch. This works okay if the
fdinfo is rarely read and the VMs don't have a ton of BOs. If either of
these conditions is not true, we get a massive performance hit.
In this new revision, we track the BOs as they change states. This way
when the fdinfo is queried we only need to take the status lock and copy
out the usage stats with minimal impact to the runtime performance. With
this new approach however, we would no longer be able to track active
buffers.
Signed-off-by: Yunxiang Li <[email protected]>
Reviewed-by: Christian König <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Christian König <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When memory stats is generated fresh everytime by going though all the
BOs, their active information is quite easy to get. But if the stats are
tracked with BO's state this becomes harder since the job scheduling
part doesn't really deal with individual buffers.
Make drm-active- optional to enable amdgpu to switch to the second
method.
Signed-off-by: Yunxiang Li <[email protected]>
Reviewed-by: Tvrtko Ursulin <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Christian König <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
In the past these specialized on chip memory pools were reported as system
memory (aka 'cpu') which was not correct and misleading. That has since
been removed so lets make them visible as their own respective memory
regions.
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Tvrtko Ursulin <[email protected]>
Cc: Christian König <[email protected]>
Cc: Yunxiang Li <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Since on modern systems all of vram can be made visible anyways, to
simplify the new implementation, drops tracking how much memory is
visible for now. If this is really needed we can add it back on top of
the new implementation, or just report all the BOs as visible.
Signed-off-by: Yunxiang Li <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Tvrtko Ursulin <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
The old behavior reports the resident memory usage for this key and the
documentation say so as well. However this was accidentally changed to
include buffers that was evicted.
Fixes: 04bdba46542c ("drm/amdgpu: Use drm_print_memory_stats helper from fdinfo")
Signed-off-by: Yunxiang Li <[email protected]>
Reviewed-by: Tvrtko Ursulin <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Tvrtko Ursulin <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Convert fdinfo memory stats to use the common drm_print_memory_stats
helper.
This achieves alignment with the common keys as documented in
drm-usage-stats.rst, adding specifically drm-total- key the driver was
missing until now.
Additionally I made the code stop skipping total size for objects which
currently do not have a backing store, and I added resident, active and
purgeable reporting.
Legacy keys have been preserved, with the outlook of only potentially
removing only the drm-memory- when the time gets right.
The example output now looks like this:
pos: 0
flags: 02100002
mnt_id: 24
ino: 1239
drm-driver: amdgpu
drm-client-id: 4
drm-pdev: 0000:04:00.0
pasid: 32771
drm-total-cpu: 0
drm-shared-cpu: 0
drm-active-cpu: 0
drm-resident-cpu: 0
drm-purgeable-cpu: 0
drm-total-gtt: 2392 KiB
drm-shared-gtt: 0
drm-active-gtt: 0
drm-resident-gtt: 2392 KiB
drm-purgeable-gtt: 0
drm-total-vram: 44564 KiB
drm-shared-vram: 31952 KiB
drm-active-vram: 0
drm-resident-vram: 44564 KiB
drm-purgeable-vram: 0
drm-memory-vram: 44564 KiB
drm-memory-gtt: 2392 KiB
drm-memory-cpu: 0 KiB
amd-memory-visible-vram: 44564 KiB
amd-evicted-vram: 0 KiB
amd-evicted-visible-vram: 0 KiB
amd-requested-vram: 44564 KiB
amd-requested-visible-vram: 11952 KiB
amd-requested-gtt: 2392 KiB
drm-engine-compute: 46464671 ns
v2:
* Track purgeable via AMDGPU_GEM_CREATE_DISCARDABLE.
Acked-by: Daniel Vetter <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Tvrtko Ursulin <[email protected]>
Cc: Alex Deucher <[email protected]>
Cc: Christian König <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Rob Clark <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Add shared stats. Useful for seeing shared memory.
v2: take dma-buf into account as well
v3: use the new gem helper
Link: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Alex Deucher <[email protected]>
Cc: Rob Clark <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Christian König <[email protected]>
|
| |
|
|
|
|
|
|
| |
Remove unused variables from amdgpu_show_fdinfo
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Umio Yasuno <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Some of the fields that are handled by drm_show_fdinfo() crept back in
when rebasing the patch. Remove them again.
Fixes: 376c25f8ca47 ("drm/amdgpu: Switch to fdinfo helper")
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: <[email protected]>
Co-developed-by: Umio Yasuno <[email protected]>
Signed-off-by: Umio Yasuno <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
| |
Enable command submission to VPE from user space.
Signed-off-by: Lang Yu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fixes the following:
WARNING: %Lu is non-standard C, use %llu
+ seq_printf(m, "drm-client-id:\t%Lu\n", vm->immediate.fence_context);
WARNING: %Ld is non-standard C, use %lld
+ seq_printf(m, "drm-engine-%s:\t%Ld ns\n", amdgpu_ip_name[hw_ip],
Cc: Guchun Chen <[email protected]>
Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Reviewed-by: Guchun Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
v2: Rebase on drm-misc-next
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Christian König <[email protected]>
Acked-by: Dave Airlie <[email protected]>
Signed-off-by: Neil Armstrong <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
|
| |
|
|
|
|
|
|
| |
This will be used for performance investigations.
Signed-off-by: Marek Olšák <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
This is enough to get gputop working :)
v2: rebase and some addition cleanup
Signed-off-by: Christian König <[email protected]>
Reviewed-by: Shashank Sharma <[email protected]> (v1)
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Convert fdinfo format to one documented in drm-usage-stats.rst.
It turned out that the existing implementation was actually completely
nonsense. The calculated percentages indeed represented the usage of the
engine, but with varying time slices.
So 10% usage for application A could mean something completely different
than 10% usage for application B.
Completely nuke that and just use the now standardized nanosecond
interface.
v2: drop the documentation change for now, nuke percentage calculation
v3: only account for each hw_ip, move the time_spend to the ctx mgr.
v4: move general ctx changes into separate patch, rework the fdinfo to
ctx_mgr interface so that all usages are calculated at once, drop
some unecessary and dangerous refcount dance.
v5: add one more comment how we calculate the time spend
Signed-off-by: Tvrtko Ursulin <[email protected]>
Signed-off-by: Christian König <[email protected]>
Reviewed-by: Shashank Sharma <[email protected]>
Cc: Daniel Vetter <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Get process vm root BO ref in case process is exiting and root BO is
freed, to avoid NULL pointer dereference backtrace:
BUG: unable to handle kernel NULL pointer dereference at
0000000000000000
Call Trace:
amdgpu_show_fdinfo+0xfe/0x2a0 [amdgpu]
seq_show+0x12c/0x180
seq_read+0x153/0x410
vfs_read+0x91/0x140[ 3427.206183] ksys_read+0x4f/0xb0
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
Signed-off-by: Philip Yang <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
Page table entries are now in embedded in VM BO, so
we do not need struct amdgpu_vm_pt. This patch replaces
struct amdgpu_vm_pt with struct amdgpu_vm_bo_base.
Signed-off-by: Nirmoy Das <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
|
Tracking devices, process info and fence info using
/proc/pid/fdinfo
Signed-off-by: David M Nieto <[email protected]>
Signed-off-by: Roy Sun <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Christian König <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
|
