mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 16:15:29 +07:00
5d6527a784
Patch series "mmu notifier contextual informations", v2. This patchset adds contextual information, why an invalidation is happening, to mmu notifier callback. This is necessary for user of mmu notifier that wish to maintains their own data structure without having to add new fields to struct vm_area_struct (vma). For instance device can have they own page table that mirror the process address space. When a vma is unmap (munmap() syscall) the device driver can free the device page table for the range. Today we do not have any information on why a mmu notifier call back is happening and thus device driver have to assume that it is always an munmap(). This is inefficient at it means that it needs to re-allocate device page table on next page fault and rebuild the whole device driver data structure for the range. Other use case beside munmap() also exist, for instance it is pointless for device driver to invalidate the device page table when the invalidation is for the soft dirtyness tracking. Or device driver can optimize away mprotect() that change the page table permission access for the range. This patchset enables all this optimizations for device drivers. I do not include any of those in this series but another patchset I am posting will leverage this. The patchset is pretty simple from a code point of view. The first two patches consolidate all mmu notifier arguments into a struct so that it is easier to add/change arguments. The last patch adds the contextual information (munmap, protection, soft dirty, clear, ...). This patch (of 3): To avoid having to change many callback definition everytime we want to add a parameter use a structure to group all parameters for the mmu_notifier invalidate_range_start/end callback. No functional changes with this patch. [akpm@linux-foundation.org: fix drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c kerneldoc] Link: http://lkml.kernel.org/r/20181205053628.3210-2-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Acked-by: Jason Gunthorpe <jgg@mellanox.com> [infiniband] Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Felix Kuehling <felix.kuehling@amd.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
340 lines
8.2 KiB
C
340 lines
8.2 KiB
C
/*
|
|
* 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>
|
|
*/
|
|
|
|
#include <linux/firmware.h>
|
|
#include <linux/module.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <drm/drmP.h>
|
|
#include <drm/drm.h>
|
|
|
|
#include "radeon.h"
|
|
|
|
struct radeon_mn {
|
|
/* constant after initialisation */
|
|
struct radeon_device *rdev;
|
|
struct mm_struct *mm;
|
|
struct mmu_notifier mn;
|
|
|
|
/* only used on destruction */
|
|
struct work_struct work;
|
|
|
|
/* protected by rdev->mn_lock */
|
|
struct hlist_node node;
|
|
|
|
/* objects protected by lock */
|
|
struct mutex lock;
|
|
struct rb_root_cached objects;
|
|
};
|
|
|
|
struct radeon_mn_node {
|
|
struct interval_tree_node it;
|
|
struct list_head bos;
|
|
};
|
|
|
|
/**
|
|
* radeon_mn_destroy - destroy the rmn
|
|
*
|
|
* @work: previously sheduled work item
|
|
*
|
|
* Lazy destroys the notifier from a work item
|
|
*/
|
|
static void radeon_mn_destroy(struct work_struct *work)
|
|
{
|
|
struct radeon_mn *rmn = container_of(work, struct radeon_mn, work);
|
|
struct radeon_device *rdev = rmn->rdev;
|
|
struct radeon_mn_node *node, *next_node;
|
|
struct radeon_bo *bo, *next_bo;
|
|
|
|
mutex_lock(&rdev->mn_lock);
|
|
mutex_lock(&rmn->lock);
|
|
hash_del(&rmn->node);
|
|
rbtree_postorder_for_each_entry_safe(node, next_node,
|
|
&rmn->objects.rb_root, it.rb) {
|
|
|
|
interval_tree_remove(&node->it, &rmn->objects);
|
|
list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
|
|
bo->mn = NULL;
|
|
list_del_init(&bo->mn_list);
|
|
}
|
|
kfree(node);
|
|
}
|
|
mutex_unlock(&rmn->lock);
|
|
mutex_unlock(&rdev->mn_lock);
|
|
mmu_notifier_unregister(&rmn->mn, rmn->mm);
|
|
kfree(rmn);
|
|
}
|
|
|
|
/**
|
|
* radeon_mn_release - callback to notify about mm destruction
|
|
*
|
|
* @mn: our notifier
|
|
* @mn: the mm this callback is about
|
|
*
|
|
* Shedule a work item to lazy destroy our notifier.
|
|
*/
|
|
static void radeon_mn_release(struct mmu_notifier *mn,
|
|
struct mm_struct *mm)
|
|
{
|
|
struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
|
|
INIT_WORK(&rmn->work, radeon_mn_destroy);
|
|
schedule_work(&rmn->work);
|
|
}
|
|
|
|
/**
|
|
* radeon_mn_invalidate_range_start - callback to notify about mm change
|
|
*
|
|
* @mn: our notifier
|
|
* @mn: the mm this callback is about
|
|
* @start: start of updated range
|
|
* @end: end of updated range
|
|
*
|
|
* We block for all BOs between start and end to be idle and
|
|
* unmap them by move them into system domain again.
|
|
*/
|
|
static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
|
|
const struct mmu_notifier_range *range)
|
|
{
|
|
struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
|
|
struct ttm_operation_ctx ctx = { false, false };
|
|
struct interval_tree_node *it;
|
|
unsigned long end;
|
|
int ret = 0;
|
|
|
|
/* notification is exclusive, but interval is inclusive */
|
|
end = range->end - 1;
|
|
|
|
/* TODO we should be able to split locking for interval tree and
|
|
* the tear down.
|
|
*/
|
|
if (range->blockable)
|
|
mutex_lock(&rmn->lock);
|
|
else if (!mutex_trylock(&rmn->lock))
|
|
return -EAGAIN;
|
|
|
|
it = interval_tree_iter_first(&rmn->objects, range->start, end);
|
|
while (it) {
|
|
struct radeon_mn_node *node;
|
|
struct radeon_bo *bo;
|
|
long r;
|
|
|
|
if (!range->blockable) {
|
|
ret = -EAGAIN;
|
|
goto out_unlock;
|
|
}
|
|
|
|
node = container_of(it, struct radeon_mn_node, it);
|
|
it = interval_tree_iter_next(it, range->start, end);
|
|
|
|
list_for_each_entry(bo, &node->bos, mn_list) {
|
|
|
|
if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
|
|
continue;
|
|
|
|
r = radeon_bo_reserve(bo, true);
|
|
if (r) {
|
|
DRM_ERROR("(%ld) failed to reserve user bo\n", r);
|
|
continue;
|
|
}
|
|
|
|
r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
|
|
true, false, MAX_SCHEDULE_TIMEOUT);
|
|
if (r <= 0)
|
|
DRM_ERROR("(%ld) failed to wait for user bo\n", r);
|
|
|
|
radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
|
|
r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
|
|
if (r)
|
|
DRM_ERROR("(%ld) failed to validate user bo\n", r);
|
|
|
|
radeon_bo_unreserve(bo);
|
|
}
|
|
}
|
|
|
|
out_unlock:
|
|
mutex_unlock(&rmn->lock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static const struct mmu_notifier_ops radeon_mn_ops = {
|
|
.release = radeon_mn_release,
|
|
.invalidate_range_start = radeon_mn_invalidate_range_start,
|
|
};
|
|
|
|
/**
|
|
* radeon_mn_get - create notifier context
|
|
*
|
|
* @rdev: radeon device pointer
|
|
*
|
|
* Creates a notifier context for current->mm.
|
|
*/
|
|
static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct radeon_mn *rmn;
|
|
int r;
|
|
|
|
if (down_write_killable(&mm->mmap_sem))
|
|
return ERR_PTR(-EINTR);
|
|
|
|
mutex_lock(&rdev->mn_lock);
|
|
|
|
hash_for_each_possible(rdev->mn_hash, rmn, node, (unsigned long)mm)
|
|
if (rmn->mm == mm)
|
|
goto release_locks;
|
|
|
|
rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
|
|
if (!rmn) {
|
|
rmn = ERR_PTR(-ENOMEM);
|
|
goto release_locks;
|
|
}
|
|
|
|
rmn->rdev = rdev;
|
|
rmn->mm = mm;
|
|
rmn->mn.ops = &radeon_mn_ops;
|
|
mutex_init(&rmn->lock);
|
|
rmn->objects = RB_ROOT_CACHED;
|
|
|
|
r = __mmu_notifier_register(&rmn->mn, mm);
|
|
if (r)
|
|
goto free_rmn;
|
|
|
|
hash_add(rdev->mn_hash, &rmn->node, (unsigned long)mm);
|
|
|
|
release_locks:
|
|
mutex_unlock(&rdev->mn_lock);
|
|
up_write(&mm->mmap_sem);
|
|
|
|
return rmn;
|
|
|
|
free_rmn:
|
|
mutex_unlock(&rdev->mn_lock);
|
|
up_write(&mm->mmap_sem);
|
|
kfree(rmn);
|
|
|
|
return ERR_PTR(r);
|
|
}
|
|
|
|
/**
|
|
* radeon_mn_register - register a BO for notifier updates
|
|
*
|
|
* @bo: radeon buffer object
|
|
* @addr: userptr addr we should monitor
|
|
*
|
|
* Registers an MMU notifier for the given BO at the specified address.
|
|
* Returns 0 on success, -ERRNO if anything goes wrong.
|
|
*/
|
|
int radeon_mn_register(struct radeon_bo *bo, unsigned long addr)
|
|
{
|
|
unsigned long end = addr + radeon_bo_size(bo) - 1;
|
|
struct radeon_device *rdev = bo->rdev;
|
|
struct radeon_mn *rmn;
|
|
struct radeon_mn_node *node = NULL;
|
|
struct list_head bos;
|
|
struct interval_tree_node *it;
|
|
|
|
rmn = radeon_mn_get(rdev);
|
|
if (IS_ERR(rmn))
|
|
return PTR_ERR(rmn);
|
|
|
|
INIT_LIST_HEAD(&bos);
|
|
|
|
mutex_lock(&rmn->lock);
|
|
|
|
while ((it = interval_tree_iter_first(&rmn->objects, addr, end))) {
|
|
kfree(node);
|
|
node = container_of(it, struct radeon_mn_node, it);
|
|
interval_tree_remove(&node->it, &rmn->objects);
|
|
addr = min(it->start, addr);
|
|
end = max(it->last, end);
|
|
list_splice(&node->bos, &bos);
|
|
}
|
|
|
|
if (!node) {
|
|
node = kmalloc(sizeof(struct radeon_mn_node), GFP_KERNEL);
|
|
if (!node) {
|
|
mutex_unlock(&rmn->lock);
|
|
return -ENOMEM;
|
|
}
|
|
}
|
|
|
|
bo->mn = rmn;
|
|
|
|
node->it.start = addr;
|
|
node->it.last = end;
|
|
INIT_LIST_HEAD(&node->bos);
|
|
list_splice(&bos, &node->bos);
|
|
list_add(&bo->mn_list, &node->bos);
|
|
|
|
interval_tree_insert(&node->it, &rmn->objects);
|
|
|
|
mutex_unlock(&rmn->lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* radeon_mn_unregister - unregister a BO for notifier updates
|
|
*
|
|
* @bo: radeon buffer object
|
|
*
|
|
* Remove any registration of MMU notifier updates from the buffer object.
|
|
*/
|
|
void radeon_mn_unregister(struct radeon_bo *bo)
|
|
{
|
|
struct radeon_device *rdev = bo->rdev;
|
|
struct radeon_mn *rmn;
|
|
struct list_head *head;
|
|
|
|
mutex_lock(&rdev->mn_lock);
|
|
rmn = bo->mn;
|
|
if (rmn == NULL) {
|
|
mutex_unlock(&rdev->mn_lock);
|
|
return;
|
|
}
|
|
|
|
mutex_lock(&rmn->lock);
|
|
/* save the next list entry for later */
|
|
head = bo->mn_list.next;
|
|
|
|
bo->mn = NULL;
|
|
list_del(&bo->mn_list);
|
|
|
|
if (list_empty(head)) {
|
|
struct radeon_mn_node *node;
|
|
node = container_of(head, struct radeon_mn_node, bos);
|
|
interval_tree_remove(&node->it, &rmn->objects);
|
|
kfree(node);
|
|
}
|
|
|
|
mutex_unlock(&rmn->lock);
|
|
mutex_unlock(&rdev->mn_lock);
|
|
}
|