// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright 2013 Red Hat Inc.
*
* Authors: Jérôme Glisse <jglisse@redhat.com>
*/
/*
* Refer to include/linux/hmm.h for information about heterogeneous memory
* management or HMM for short.
*/
#include <linux/mm.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
#define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT)
#if IS_ENABLED(CONFIG_HMM_MIRROR)
static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
{
struct hmm *hmm = READ_ONCE(mm->hmm);
if (hmm && kref_get_unless_zero(&hmm->kref))
return hmm;
return NULL;
}
/**
* hmm_get_or_create - register HMM against an mm (HMM internal)
*
* @mm: mm struct to attach to
* Returns: returns an HMM object, either by referencing the existing
* (per-process) object, or by creating a new one.
*
* This is not intended to be used directly by device drivers. If mm already
* has an HMM struct then it get a reference on it and returns it. Otherwise
* it allocates an HMM struct, initializes it, associate it with the mm and
* returns it.
*/
static struct hmm *hmm_get_or_create(struct mm_struct *mm)
{
struct hmm *hmm = mm_get_hmm(mm);
bool cleanup = false;
if (hmm)
return hmm;
hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
if (!hmm)
return NULL;
init_waitqueue_head(&hmm->wq);
INIT_LIST_HEAD(&hmm->mirrors);
init_rwsem(&hmm->mirrors_sem);
hmm->mmu_notifier.ops = NULL;
INIT_LIST_HEAD(&hmm->ranges);
mutex_init(&hmm->lock);
kref_init(&hmm->kref);
hmm->notifiers = 0;
hmm->dead = false;
hmm->mm = mm;
spin_lock(&mm->page_table_lock);
if (!mm->hmm)
mm->hmm = hmm;
else
cleanup = true;
spin_unlock(&mm->page_table_lock);
if (cleanup)
goto error;
/*
* We should only get here if hold the mmap_sem in write mode ie on
* registration of first mirror through hmm_mirror_register()
*/
hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
if (__mmu_notifier_register(&hmm->mmu_notifier, mm))
goto error_mm;
return hmm;
error_mm:
spin_lock(&mm->page_table_lock);
if (mm->hmm == hmm)
mm->hmm = NULL;
spin_unlock(&mm->page_table_lock);
error:
kfree(hmm);
return NULL;
}
static void hmm_free(struct kref *kref)
{
struct hmm *hmm = container_of(kref, struct hmm, kref);
struct mm_struct *mm = hmm->mm;
mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
spin_lock(&mm->page_table_lock);
if (mm->hmm == hmm)
mm->hmm = NULL;
spin_unlock(&mm->page_table_lock);
kfree(hmm);
}
static inline void hmm_put(struct hmm *hmm)
{
kref_put(&hmm->kref, hmm_free);
}
void hmm_mm_destroy(struct mm_struct *mm)
{
struct hmm *hmm;
spin_lock(&mm->page_table_lock);
hmm = mm_get_hmm(mm);
mm->hmm = NULL;
if (hmm) {
hmm->mm = NULL;
hmm->dead = true;
spin_unlock(&mm->page_table_lock);
hmm_put(hmm);
return;
}
spin_unlock(&mm->page_table_lock);
}
static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
struct hmm *hmm = mm_get_hmm(mm);
struct hmm_mirror *mirror;
struct hmm_range *range;
/* Report this HMM as dying. */
hmm->dead = true;
/* Wake-up everyone waiting on any range. */
mutex_lock(&hmm->lock);
list_for_each_entry(range, &hmm->ranges, list) {
range->valid = false;
}
wake_up_all(&hmm->wq);
mutex_unlock(&hmm->lock);
down_write(&hmm->mirrors_sem);
mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror,
list);
while (mirror) {
list_del_init(&mirror->list);
if (mirror->ops->release) {
/*
* Drop mirrors_sem so callback can wait on any pending
* work that might itself trigger mmu_notifier callback
* and thus would deadlock with us.
*/
up_write(&hmm->mirrors_sem);
mirror->ops->release(mirror);
down_write(&hmm->mirrors_sem);
}
mirror = list_first_entry_or_null(&hmm->mirrors,
struct hmm_mirr
|