linux_dsm_epyc7002/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

158 lines
4.9 KiB
C
Raw Normal View History

/*
* Copyright 2014 Advanced Micro Devices, Inc.
* All Rights Reserved.
*
* 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
*/
/*
* Authors:
* Christian König <christian.koenig@amd.com>
*/
/**
* DOC: MMU Notifier
*
* For coherent userptr handling registers an MMU notifier to inform the driver
* about updates on the page tables of a process.
*
* When somebody tries to invalidate the page tables we block the update until
* all operations on the pages in question are completed, then those pages are
* marked as accessed and also dirty if it wasn't a read only access.
*
* New command submissions using the userptrs in question are delayed until all
* page table invalidation are completed and we once more see a coherent process
* address space.
*/
#include <linux/firmware.h>
#include <linux/module.h>
#include <drm/drm.h>
#include "amdgpu.h"
#include "amdgpu_amdkfd.h"
/**
* amdgpu_mn_invalidate_gfx - callback to notify about mm change
*
* @mni: the range (mm) is about to update
* @range: details on the invalidation
* @cur_seq: Value to pass to mmu_interval_set_seq()
*
* Block for operations on BOs to finish and mark pages as accessed and
* potentially dirty.
*/
static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq)
{
struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
long r;
if (!mmu_notifier_range_blockable(range))
return false;
mutex_lock(&adev->notifier_lock);
mmu_interval_set_seq(mni, cur_seq);
r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false,
MAX_SCHEDULE_TIMEOUT);
mutex_unlock(&adev->notifier_lock);
if (r <= 0)
DRM_ERROR("(%ld) failed to wait for user bo\n", r);
return true;
}
static const struct mmu_interval_notifier_ops amdgpu_mn_gfx_ops = {
.invalidate = amdgpu_mn_invalidate_gfx,
};
/**
* amdgpu_mn_invalidate_hsa - callback to notify about mm change
*
* @mni: the range (mm) is about to update
* @range: details on the invalidation
* @cur_seq: Value to pass to mmu_interval_set_seq()
*
* We temporarily evict the BO attached to this range. This necessitates
* evicting all user-mode queues of the process.
*/
static bool amdgpu_mn_invalidate_hsa(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq)
{
struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
if (!mmu_notifier_range_blockable(range))
return false;
mm, oom: distinguish blockable mode for mmu notifiers There are several blockable mmu notifiers which might sleep in mmu_notifier_invalidate_range_start and that is a problem for the oom_reaper because it needs to guarantee a forward progress so it cannot depend on any sleepable locks. Currently we simply back off and mark an oom victim with blockable mmu notifiers as done after a short sleep. That can result in selecting a new oom victim prematurely because the previous one still hasn't torn its memory down yet. We can do much better though. Even if mmu notifiers use sleepable locks there is no reason to automatically assume those locks are held. Moreover majority of notifiers only care about a portion of the address space and there is absolutely zero reason to fail when we are unmapping an unrelated range. Many notifiers do really block and wait for HW which is harder to handle and we have to bail out though. This patch handles the low hanging fruit. __mmu_notifier_invalidate_range_start gets a blockable flag and callbacks are not allowed to sleep if the flag is set to false. This is achieved by using trylock instead of the sleepable lock for most callbacks and continue as long as we do not block down the call chain. I think we can improve that even further because there is a common pattern to do a range lookup first and then do something about that. The first part can be done without a sleeping lock in most cases AFAICS. The oom_reaper end then simply retries if there is at least one notifier which couldn't make any progress in !blockable mode. A retry loop is already implemented to wait for the mmap_sem and this is basically the same thing. The simplest way for driver developers to test this code path is to wrap userspace code which uses these notifiers into a memcg and set the hard limit to hit the oom. This can be done e.g. after the test faults in all the mmu notifier managed memory and set the hard limit to something really small. Then we are looking for a proper process tear down. [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: minor code simplification] Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp Reported-by: David Rientjes <rientjes@google.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Doug Ledford <dledford@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Mike Marciniszyn <mike.marciniszyn@intel.com> Cc: Dennis Dalessandro <dennis.dalessandro@intel.com> Cc: Sudeep Dutt <sudeep.dutt@intel.com> Cc: Ashutosh Dixit <ashutosh.dixit@intel.com> Cc: Dimitri Sivanich <sivanich@sgi.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-22 11:52:33 +07:00
mutex_lock(&adev->notifier_lock);
mmu_interval_set_seq(mni, cur_seq);
amdgpu_amdkfd_evict_userptr(bo->kfd_bo, bo->notifier.mm);
mutex_unlock(&adev->notifier_lock);
return true;
}
static const struct mmu_interval_notifier_ops amdgpu_mn_hsa_ops = {
.invalidate = amdgpu_mn_invalidate_hsa,
};
/**
* amdgpu_mn_register - register a BO for notifier updates
*
* @bo: amdgpu buffer object
* @addr: userptr addr we should monitor
*
* Registers a mmu_notifier for the given BO at the specified address.
* Returns 0 on success, -ERRNO if anything goes wrong.
*/
int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
{
if (bo->kfd_bo)
return mmu_interval_notifier_insert(&bo->notifier, current->mm,
addr, amdgpu_bo_size(bo),
&amdgpu_mn_hsa_ops);
return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
amdgpu_bo_size(bo),
&amdgpu_mn_gfx_ops);
}
/**
* amdgpu_mn_unregister - unregister a BO for notifier updates
*
* @bo: amdgpu buffer object
*
* Remove any registration of mmu notifier updates from the buffer object.
*/
void amdgpu_mn_unregister(struct amdgpu_bo *bo)
{
if (!bo->notifier.mm)
return;
mmu_interval_notifier_remove(&bo->notifier);
bo->notifier.mm = NULL;
}