summaryrefslogtreecommitdiffstats
path: root/mm/hmm.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hmm.c')
-rw-r--r--mm/hmm.c969
1 files changed, 192 insertions, 777 deletions
diff --git a/mm/hmm.c b/mm/hmm.c
index 16b6731a34db..72e5a6d9a417 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -8,7 +8,7 @@
* Refer to include/linux/hmm.h for information about heterogeneous memory
* management or HMM for short.
*/
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
@@ -26,267 +26,11 @@
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
-static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
-
-/**
- * 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;
-
- lockdep_assert_held_write(&mm->mmap_sem);
-
- /* Abuse the page_table_lock to also protect mm->hmm. */
- spin_lock(&mm->page_table_lock);
- hmm = mm->hmm;
- if (mm->hmm && kref_get_unless_zero(&mm->hmm->kref))
- goto out_unlock;
- spin_unlock(&mm->page_table_lock);
-
- 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);
- spin_lock_init(&hmm->ranges_lock);
- kref_init(&hmm->kref);
- hmm->notifiers = 0;
- hmm->mm = mm;
-
- hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
- if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
- kfree(hmm);
- return NULL;
- }
-
- mmgrab(hmm->mm);
-
- /*
- * We hold the exclusive mmap_sem here so we know that mm->hmm is
- * still NULL or 0 kref, and is safe to update.
- */
- spin_lock(&mm->page_table_lock);
- mm->hmm = hmm;
-
-out_unlock:
- spin_unlock(&mm->page_table_lock);
- return hmm;
-}
-
-static void hmm_free_rcu(struct rcu_head *rcu)
-{
- struct hmm *hmm = container_of(rcu, struct hmm, rcu);
-
- mmdrop(hmm->mm);
- kfree(hmm);
-}
-
-static void hmm_free(struct kref *kref)
-{
- struct hmm *hmm = container_of(kref, struct hmm, kref);
-
- spin_lock(&hmm->mm->page_table_lock);
- if (hmm->mm->hmm == hmm)
- hmm->mm->hmm = NULL;
- spin_unlock(&hmm->mm->page_table_lock);
-
- mmu_notifier_unregister_no_release(&hmm->mmu_notifier, hmm->mm);
- mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu);
-}
-
-static inline void hmm_put(struct hmm *hmm)
-{
- kref_put(&hmm->kref, hmm_free);
-}
-
-static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
-{
- struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
- struct hmm_mirror *mirror;
-
- /* Bail out if hmm is in the process of being freed */
- if (!kref_get_unless_zero(&hmm->kref))
- return;
-
- /*
- * Since hmm_range_register() holds the mmget() lock hmm_release() is
- * prevented as long as a range exists.
- */
- WARN_ON(!list_empty_careful(&hmm->ranges));
-
- down_read(&hmm->mirrors_sem);
- list_for_each_entry(mirror, &hmm->mirrors, list) {
- /*
- * Note: The driver is not allowed to trigger
- * hmm_mirror_unregister() from this thread.
- */
- if (mirror->ops->release)
- mirror->ops->release(mirror);
- }
- up_read(&hmm->mirrors_sem);
-
- hmm_put(hmm);
-}
-
-static void notifiers_decrement(struct hmm *hmm)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&hmm->ranges_lock, flags);
- hmm->notifiers--;
- if (!hmm->notifiers) {
- struct hmm_range *range;
-
- list_for_each_entry(range, &hmm->ranges, list) {
- if (range->valid)
- continue;
- range->valid = true;
- }
- wake_up_all(&hmm->wq);
- }
- spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-}
-
-static int hmm_invalidate_range_start(struct mmu_notifier *mn,
- const struct mmu_notifier_range *nrange)
-{
- struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
- struct hmm_mirror *mirror;
- struct hmm_update update;
- struct hmm_range *range;
- unsigned long flags;
- int ret = 0;
-
- if (!kref_get_unless_zero(&hmm->kref))
- return 0;
-
- update.start = nrange->start;
- update.end = nrange->end;
- update.event = HMM_UPDATE_INVALIDATE;
- update.blockable = mmu_notifier_range_blockable(nrange);
-
- spin_lock_irqsave(&hmm->ranges_lock, flags);
- hmm->notifiers++;
- list_for_each_entry(range, &hmm->ranges, list) {
- if (update.end < range->start || update.start >= range->end)
- continue;
-
- range->valid = false;
- }
- spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-
- if (mmu_notifier_range_blockable(nrange))
- down_read(&hmm->mirrors_sem);
- else if (!down_read_trylock(&hmm->mirrors_sem)) {
- ret = -EAGAIN;
- goto out;
- }
-
- list_for_each_entry(mirror, &hmm->mirrors, list) {
- int rc;
-
- rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
- if (rc) {
- if (WARN_ON(update.blockable || rc != -EAGAIN))
- continue;
- ret = -EAGAIN;
- break;
- }
- }
- up_read(&hmm->mirrors_sem);
-
-out:
- if (ret)
- notifiers_decrement(hmm);
- hmm_put(hmm);
- return ret;
-}
-
-static void hmm_invalidate_range_end(struct mmu_notifier *mn,
- const struct mmu_notifier_range *nrange)
-{
- struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
-
- if (!kref_get_unless_zero(&hmm->kref))
- return;
-
- notifiers_decrement(hmm);
- hmm_put(hmm);
-}
-
-static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
- .release = hmm_release,
- .invalidate_range_start = hmm_invalidate_range_start,
- .invalidate_range_end = hmm_invalidate_range_end,
-};
-
-/*
- * hmm_mirror_register() - register a mirror against an mm
- *
- * @mirror: new mirror struct to register
- * @mm: mm to register against
- * Return: 0 on success, -ENOMEM if no memory, -EINVAL if invalid arguments
- *
- * To start mirroring a process address space, the device driver must register
- * an HMM mirror struct.
- */
-int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
-{
- lockdep_assert_held_write(&mm->mmap_sem);
-
- /* Sanity check */
- if (!mm || !mirror || !mirror->ops)
- return -EINVAL;
-
- mirror->hmm = hmm_get_or_create(mm);
- if (!mirror->hmm)
- return -ENOMEM;
-
- down_write(&mirror->hmm->mirrors_sem);
- list_add(&mirror->list, &mirror->hmm->mirrors);
- up_write(&mirror->hmm->mirrors_sem);
-
- return 0;
-}
-EXPORT_SYMBOL(hmm_mirror_register);
-
-/*
- * hmm_mirror_unregister() - unregister a mirror
- *
- * @mirror: mirror struct to unregister
- *
- * Stop mirroring a process address space, and cleanup.
- */
-void hmm_mirror_unregister(struct hmm_mirror *mirror)
-{
- struct hmm *hmm = mirror->hmm;
-
- down_write(&hmm->mirrors_sem);
- list_del(&mirror->list);
- up_write(&hmm->mirrors_sem);
- hmm_put(hmm);
-}
-EXPORT_SYMBOL(hmm_mirror_unregister);
-
struct hmm_vma_walk {
struct hmm_range *range;
struct dev_pagemap *pgmap;
unsigned long last;
- bool fault;
- bool block;
+ unsigned int flags;
};
static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
@@ -298,38 +42,45 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
vm_fault_t ret;
- flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
- flags |= write_fault ? FAULT_FLAG_WRITE : 0;
+ if (!vma)
+ goto err;
+
+ if (hmm_vma_walk->flags & HMM_FAULT_ALLOW_RETRY)
+ flags |= FAULT_FLAG_ALLOW_RETRY;
+ if (write_fault)
+ flags |= FAULT_FLAG_WRITE;
+
ret = handle_mm_fault(vma, addr, flags);
- if (ret & VM_FAULT_RETRY)
+ if (ret & VM_FAULT_RETRY) {
+ /* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */
return -EAGAIN;
- if (ret & VM_FAULT_ERROR) {
- *pfn = range->values[HMM_PFN_ERROR];
- return -EFAULT;
}
+ if (ret & VM_FAULT_ERROR)
+ goto err;
return -EBUSY;
+
+err:
+ *pfn = range->values[HMM_PFN_ERROR];
+ return -EFAULT;
}
-static int hmm_pfns_bad(unsigned long addr,
- unsigned long end,
- struct mm_walk *walk)
+static int hmm_pfns_fill(unsigned long addr, unsigned long end,
+ struct hmm_range *range, enum hmm_pfn_value_e value)
{
- struct hmm_vma_walk *hmm_vma_walk = walk->private;
- struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long i;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
- pfns[i] = range->values[HMM_PFN_ERROR];
+ pfns[i] = range->values[value];
return 0;
}
/*
- * hmm_vma_walk_hole() - handle a range lacking valid pmd or pte(s)
- * @start: range virtual start address (inclusive)
+ * hmm_vma_walk_hole_() - handle a range lacking valid pmd or pte(s)
+ * @addr: range virtual start address (inclusive)
* @end: range virtual end address (exclusive)
* @fault: should we fault or not ?
* @write_fault: write fault ?
@@ -346,13 +97,15 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
- unsigned long i, page_size;
+ unsigned long i;
hmm_vma_walk->last = addr;
- page_size = hmm_range_page_size(range);
- i = (addr - range->start) >> range->page_shift;
+ i = (addr - range->start) >> PAGE_SHIFT;
+
+ if (write_fault && walk->vma && !(walk->vma->vm_flags & VM_WRITE))
+ return -EPERM;
- for (; addr < end; addr += page_size, i++) {
+ for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
@@ -373,15 +126,15 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
{
struct hmm_range *range = hmm_vma_walk->range;
- if (!hmm_vma_walk->fault)
+ if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT)
return;
/*
* So we not only consider the individual per page request we also
* consider the default flags requested for the range. The API can
- * be use in 2 fashions. The first one where the HMM user coalesce
- * multiple page fault into one request and set flags per pfns for
- * of those faults. The second one where the HMM user want to pre-
+ * be used 2 ways. The first one where the HMM user coalesces
+ * multiple page faults into one request and sets flags per pfn for
+ * those faults. The second one where the HMM user wants to pre-
* fault a range with specific flags. For the latter one it is a
* waste to have the user pre-fill the pfn arrays with a default
* flags value.
@@ -391,7 +144,7 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
/* We aren't ask to do anything ... */
if (!(pfns & range->flags[HMM_PFN_VALID]))
return;
- /* If this is device memory than only fault if explicitly requested */
+ /* If this is device memory then only fault if explicitly requested */
if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) {
/* Do we fault on device memory ? */
if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) {
@@ -418,7 +171,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
{
unsigned long i;
- if (!hmm_vma_walk->fault) {
+ if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) {
*fault = *write_fault = false;
return;
}
@@ -433,7 +186,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
}
static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
- struct mm_walk *walk)
+ __always_unused int depth, struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
@@ -458,22 +211,10 @@ static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
range->flags[HMM_PFN_VALID];
}
-static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
-{
- if (!pud_present(pud))
- return 0;
- return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
- range->flags[HMM_PFN_WRITE] :
- range->flags[HMM_PFN_VALID];
-}
-
-static int hmm_vma_handle_pmd(struct mm_walk *walk,
- unsigned long addr,
- unsigned long end,
- uint64_t *pfns,
- pmd_t pmd)
-{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
+ unsigned long end, uint64_t *pfns, pmd_t pmd)
+{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
@@ -488,7 +229,7 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
if (pmd_protnone(pmd) || fault || write_fault)
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
- pfn = pmd_pfn(pmd) + pte_index(addr);
+ pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
if (pmd_devmap(pmd)) {
hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
@@ -504,11 +245,12 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
}
hmm_vma_walk->last = end;
return 0;
-#else
- /* If THP is not enabled then we should never reach that code ! */
- return -EINVAL;
-#endif
}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+/* stub to allow the code below to compile */
+int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
+ unsigned long end, uint64_t *pfns, pmd_t pmd);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
{
@@ -525,7 +267,6 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
- struct vm_area_struct *vma = walk->vma;
bool fault, write_fault;
uint64_t cpu_flags;
pte_t pte = *ptep;
@@ -546,6 +287,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
swp_entry_t entry = pte_to_swp_entry(pte);
if (!non_swap_entry(entry)) {
+ cpu_flags = pte_to_hmm_pfn_flags(range, pte);
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+ &fault, &write_fault);
if (fault || write_fault)
goto fault;
return 0;
@@ -574,8 +318,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
if (fault || write_fault) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
- migration_entry_wait(vma->vm_mm,
- pmdp, addr);
+ migration_entry_wait(walk->mm, pmdp, addr);
return -EBUSY;
}
return 0;
@@ -599,8 +342,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
} else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
- *pfn = range->values[HMM_PFN_SPECIAL];
- return -EFAULT;
+ if (!is_zero_pfn(pte_pfn(pte))) {
+ *pfn = range->values[HMM_PFN_SPECIAL];
+ return -EFAULT;
+ }
+ /*
+ * Since each architecture defines a struct page for the zero
+ * page, just fall through and treat it like a normal page.
+ */
}
*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
@@ -623,20 +372,15 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
- struct vm_area_struct *vma = walk->vma;
uint64_t *pfns = range->pfns;
unsigned long addr = start, i;
pte_t *ptep;
pmd_t pmd;
-
again:
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
- return hmm_vma_walk_hole(start, end, walk);
-
- if (pmd_huge(pmd) && (range->vma->vm_flags & VM_HUGETLB))
- return hmm_pfns_bad(start, end, walk);
+ return hmm_vma_walk_hole(start, end, -1, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
bool fault, write_fault;
@@ -651,20 +395,20 @@ again:
0, &fault, &write_fault);
if (fault || write_fault) {
hmm_vma_walk->last = addr;
- pmd_migration_entry_wait(vma->vm_mm, pmdp);
+ pmd_migration_entry_wait(walk->mm, pmdp);
return -EBUSY;
}
return 0;
} else if (!pmd_present(pmd))
- return hmm_pfns_bad(start, end, walk);
+ return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
/*
- * No need to take pmd_lock here, even if some other threads
+ * No need to take pmd_lock here, even if some other thread
* is splitting the huge pmd we will get that event through
* mmu_notifier callback.
*
- * So just read pmd value and check again its a transparent
+ * So just read pmd value and check again it's a transparent
* huge or device mapping one and compute corresponding pfn
* values.
*/
@@ -678,13 +422,13 @@ again:
}
/*
- * We have handled all the valid case above ie either none, migration,
+ * We have handled all the valid cases above ie either none, migration,
* huge or transparent huge. At this point either it is a valid pmd
* entry pointing to pte directory or it is a bad pmd that will not
* recover.
*/
if (pmd_bad(pmd))
- return hmm_pfns_bad(start, end, walk);
+ return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
ptep = pte_offset_map(pmdp, addr);
i = (addr - range->start) >> PAGE_SHIFT;
@@ -714,30 +458,48 @@ again:
return 0;
}
-static int hmm_vma_walk_pud(pud_t *pudp,
- unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
+#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
+ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
+{
+ if (!pud_present(pud))
+ return 0;
+ return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
+ range->flags[HMM_PFN_WRITE] :
+ range->flags[HMM_PFN_VALID];
+}
+
+static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
+ struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
- unsigned long addr = start, next;
- pmd_t *pmdp;
+ unsigned long addr = start;
pud_t pud;
- int ret;
+ int ret = 0;
+ spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
+
+ if (!ptl)
+ return 0;
+
+ /* Normally we don't want to split the huge page */
+ walk->action = ACTION_CONTINUE;
-again:
pud = READ_ONCE(*pudp);
- if (pud_none(pud))
- return hmm_vma_walk_hole(start, end, walk);
+ if (pud_none(pud)) {
+ ret = hmm_vma_walk_hole(start, end, -1, walk);
+ goto out_unlock;
+ }
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
uint64_t *pfns, cpu_flags;
bool fault, write_fault;
- if (!pud_present(pud))
- return hmm_vma_walk_hole(start, end, walk);
+ if (!pud_present(pud)) {
+ ret = hmm_vma_walk_hole(start, end, -1, walk);
+ goto out_unlock;
+ }
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
@@ -746,16 +508,20 @@ again:
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
cpu_flags, &fault, &write_fault);
- if (fault || write_fault)
- return hmm_vma_walk_hole_(addr, end, fault,
- write_fault, walk);
+ if (fault || write_fault) {
+ ret = hmm_vma_walk_hole_(addr, end, fault,
+ write_fault, walk);
+ goto out_unlock;
+ }
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn) {
hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
hmm_vma_walk->pgmap);
- if (unlikely(!hmm_vma_walk->pgmap))
- return -EBUSY;
+ if (unlikely(!hmm_vma_walk->pgmap)) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
}
@@ -764,59 +530,39 @@ again:
hmm_vma_walk->pgmap = NULL;
}
hmm_vma_walk->last = end;
- return 0;
+ goto out_unlock;
}
- split_huge_pud(walk->vma, pudp, addr);
- if (pud_none(*pudp))
- goto again;
-
- pmdp = pmd_offset(pudp, addr);
- do {
- next = pmd_addr_end(addr, end);
- ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
- if (ret)
- return ret;
- } while (pmdp++, addr = next, addr != end);
+ /* Ask for the PUD to be split */
+ walk->action = ACTION_SUBTREE;
- return 0;
+out_unlock:
+ spin_unlock(ptl);
+ return ret;
}
+#else
+#define hmm_vma_walk_pud NULL
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
{
-#ifdef CONFIG_HUGETLB_PAGE
- unsigned long addr = start, i, pfn, mask, size, pfn_inc;
+ unsigned long addr = start, i, pfn;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
- struct hstate *h = hstate_vma(vma);
uint64_t orig_pfn, cpu_flags;
bool fault, write_fault;
spinlock_t *ptl;
pte_t entry;
int ret = 0;
- size = 1UL << huge_page_shift(h);
- mask = size - 1;
- if (range->page_shift != PAGE_SHIFT) {
- /* Make sure we are looking at full page. */
- if (start & mask)
- return -EINVAL;
- if (end < (start + size))
- return -EINVAL;
- pfn_inc = size >> PAGE_SHIFT;
- } else {
- pfn_inc = 1;
- size = PAGE_SIZE;
- }
-
-
- ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
entry = huge_ptep_get(pte);
- i = (start - range->start) >> range->page_shift;
+ i = (start - range->start) >> PAGE_SHIFT;
orig_pfn = range->pfns[i];
range->pfns[i] = range->values[HMM_PFN_NONE];
cpu_flags = pte_to_hmm_pfn_flags(range, entry);
@@ -828,8 +574,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
goto unlock;
}
- pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift);
- for (; addr < end; addr += size, i++, pfn += pfn_inc)
+ pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
+ for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
@@ -841,205 +587,82 @@ unlock:
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
return ret;
-#else /* CONFIG_HUGETLB_PAGE */
- return -EINVAL;
-#endif
-}
-
-static void hmm_pfns_clear(struct hmm_range *range,
- uint64_t *pfns,
- unsigned long addr,
- unsigned long end)
-{
- for (; addr < end; addr += PAGE_SIZE, pfns++)
- *pfns = range->values[HMM_PFN_NONE];
}
+#else
+#define hmm_vma_walk_hugetlb_entry NULL
+#endif /* CONFIG_HUGETLB_PAGE */
-/*
- * hmm_range_register() - start tracking change to CPU page table over a range
- * @range: range
- * @mm: the mm struct for the range of virtual address
- * @start: start virtual address (inclusive)
- * @end: end virtual address (exclusive)
- * @page_shift: expect page shift for the range
- * Returns 0 on success, -EFAULT if the address space is no longer valid
- *
- * Track updates to the CPU page table see include/linux/hmm.h
- */
-int hmm_range_register(struct hmm_range *range,
- struct hmm_mirror *mirror,
- unsigned long start,
- unsigned long end,
- unsigned page_shift)
+static int hmm_vma_walk_test(unsigned long start, unsigned long end,
+ struct mm_walk *walk)
{
- unsigned long mask = ((1UL << page_shift) - 1UL);
- struct hmm *hmm = mirror->hmm;
- unsigned long flags;
-
- range->valid = false;
- range->hmm = NULL;
-
- if ((start & mask) || (end & mask))
- return -EINVAL;
- if (start >= end)
- return -EINVAL;
-
- range->page_shift = page_shift;
- range->start = start;
- range->end = end;
-
- /* Prevent hmm_release() from running while the range is valid */
- if (!mmget_not_zero(hmm->mm))
- return -EFAULT;
-
- /* Initialize range to track CPU page table updates. */
- spin_lock_irqsave(&hmm->ranges_lock, flags);
-
- range->hmm = hmm;
- kref_get(&hmm->kref);
- list_add(&range->list, &hmm->ranges);
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+ struct vm_area_struct *vma = walk->vma;
/*
- * If there are any concurrent notifiers we have to wait for them for
- * the range to be valid (see hmm_range_wait_until_valid()).
+ * Skip vma ranges that don't have struct page backing them or
+ * map I/O devices directly.
*/
- if (!hmm->notifiers)
- range->valid = true;
- spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-
- return 0;
-}
-EXPORT_SYMBOL(hmm_range_register);
-
-/*
- * hmm_range_unregister() - stop tracking change to CPU page table over a range
- * @range: range
- *
- * Range struct is used to track updates to the CPU page table after a call to
- * hmm_range_register(). See include/linux/hmm.h for how to use it.
- */
-void hmm_range_unregister(struct hmm_range *range)
-{
- struct hmm *hmm = range->hmm;
- unsigned long flags;
-
- spin_lock_irqsave(&hmm->ranges_lock, flags);
- list_del_init(&range->list);
- spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-
- /* Drop reference taken by hmm_range_register() */
- mmput(hmm->mm);
- hmm_put(hmm);
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP | VM_MIXEDMAP))
+ return -EFAULT;
/*
- * The range is now invalid and the ref on the hmm is dropped, so
- * poison the pointer. Leave other fields in place, for the caller's
- * use.
+ * If the vma does not allow read access, then assume that it does not
+ * allow write access either. HMM does not support architectures
+ * that allow write without read.
*/
- range->valid = false;
- memset(&range->hmm, POISON_INUSE, sizeof(range->hmm));
-}
-EXPORT_SYMBOL(hmm_range_unregister);
-
-/*
- * hmm_range_snapshot() - snapshot CPU page table for a range
- * @range: range
- * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
- * permission (for instance asking for write and range is read only),
- * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid
- * vma or it is illegal to access that range), number of valid pages
- * in range->pfns[] (from range start address).
- *
- * This snapshots the CPU page table for a range of virtual addresses. Snapshot
- * validity is tracked by range struct. See in include/linux/hmm.h for example
- * on how to use.
- */
-long hmm_range_snapshot(struct hmm_range *range)
-{
- const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
- unsigned long start = range->start, end;
- struct hmm_vma_walk hmm_vma_walk;
- struct hmm *hmm = range->hmm;
- struct vm_area_struct *vma;
- struct mm_walk mm_walk;
-
- lockdep_assert_held(&hmm->mm->mmap_sem);
- do {
- /* If range is no longer valid force retry. */
- if (!range->valid)
- return -EBUSY;
+ if (!(vma->vm_flags & VM_READ)) {
+ bool fault, write_fault;
- vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & device_vma))
+ /*
+ * Check to see if a fault is requested for any page in the
+ * range.
+ */
+ hmm_range_need_fault(hmm_vma_walk, range->pfns +
+ ((start - range->start) >> PAGE_SHIFT),
+ (end - start) >> PAGE_SHIFT,
+ 0, &fault, &write_fault);
+ if (fault || write_fault)
return -EFAULT;
- if (is_vm_hugetlb_page(vma)) {
- if (huge_page_shift(hstate_vma(vma)) !=
- range->page_shift &&
- range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- } else {
- if (range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- }
-
- if (!(vma->vm_flags & VM_READ)) {
- /*
- * If vma do not allow read access, then assume that it
- * does not allow write access, either. HMM does not
- * support architecture that allow write without read.
- */
- hmm_pfns_clear(range, range->pfns,
- range->start, range->end);
- return -EPERM;
- }
+ hmm_pfns_fill(start, end, range, HMM_PFN_NONE);
+ hmm_vma_walk->last = end;
- range->vma = vma;
- hmm_vma_walk.pgmap = NULL;
- hmm_vma_walk.last = start;
- hmm_vma_walk.fault = false;
- hmm_vma_walk.range = range;
- mm_walk.private = &hmm_vma_walk;
- end = min(range->end, vma->vm_end);
-
- mm_walk.vma = vma;
- mm_walk.mm = vma->vm_mm;
- mm_walk.pte_entry = NULL;
- mm_walk.test_walk = NULL;
- mm_walk.hugetlb_entry = NULL;
- mm_walk.pud_entry = hmm_vma_walk_pud;
- mm_walk.pmd_entry = hmm_vma_walk_pmd;
- mm_walk.pte_hole = hmm_vma_walk_hole;
- mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
-
- walk_page_range(start, end, &mm_walk);
- start = end;
- } while (start < range->end);
+ /* Skip this vma and continue processing the next vma. */
+ return 1;
+ }
- return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+ return 0;
}
-EXPORT_SYMBOL(hmm_range_snapshot);
-/*
- * hmm_range_fault() - try to fault some address in a virtual address range
- * @range: range being faulted
- * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
- * Return: number of valid pages in range->pfns[] (from range start
- * address). This may be zero. If the return value is negative,
- * then one of the following values may be returned:
+static const struct mm_walk_ops hmm_walk_ops = {
+ .pud_entry = hmm_vma_walk_pud,
+ .pmd_entry = hmm_vma_walk_pmd,
+ .pte_hole = hmm_vma_walk_hole,
+ .hugetlb_entry = hmm_vma_walk_hugetlb_entry,
+ .test_walk = hmm_vma_walk_test,
+};
+
+/**
+ * hmm_range_fault - try to fault some address in a virtual address range
+ * @range: range being faulted
+ * @flags: HMM_FAULT_* flags
*
- * -EINVAL invalid arguments or mm or virtual address are in an
- * invalid vma (for instance device file vma).
- * -ENOMEM: Out of memory.
- * -EPERM: Invalid permission (for instance asking for write and
- * range is read only).
- * -EAGAIN: If you need to retry and mmap_sem was drop. This can only
- * happens if block argument is false.
- * -EBUSY: If the the range is being invalidated and you should wait
- * for invalidation to finish.
- * -EFAULT: Invalid (ie either no valid vma or it is illegal to access
- * that range), number of valid pages in range->pfns[] (from
- * range start address).
+ * Return: the number of valid pages in range->pfns[] (from range start
+ * address), which may be zero. On error one of the following status codes
+ * can be returned:
+ *
+ * -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma
+ * (e.g., device file vma).
+ * -ENOMEM: Out of memory.
+ * -EPERM: Invalid permission (e.g., asking for write and range is read
+ * only).
+ * -EAGAIN: A page fault needs to be retried and mmap_sem was dropped.
+ * -EBUSY: The range has been invalidated and the caller needs to wait for
+ * the invalidation to finish.
+ * -EFAULT: Invalid (i.e., either no valid vma or it is illegal to access
+ * that range) number of valid pages in range->pfns[] (from
+ * range start address).
*
* This is similar to a regular CPU page fault except that it will not trigger
* any memory migration if the memory being faulted is not accessible by CPUs
@@ -1048,237 +671,29 @@ EXPORT_SYMBOL(hmm_range_snapshot);
* On error, for one virtual address in the range, the function will mark the
* corresponding HMM pfn entry with an error flag.
*/
-long hmm_range_fault(struct hmm_range *range, bool block)
+long hmm_range_fault(struct hmm_range *range, unsigned int flags)
{
- const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
- unsigned long start = range->start, end;
- struct hmm_vma_walk hmm_vma_walk;
- struct hmm *hmm = range->hmm;
- struct vm_area_struct *vma;
- struct mm_walk mm_walk;
+ struct hmm_vma_walk hmm_vma_walk = {
+ .range = range,
+ .last = range->start,
+ .flags = flags,
+ };
+ struct mm_struct *mm = range->notifier->mm;
int ret;
- lockdep_assert_held(&hmm->mm->mmap_sem);
+ lockdep_assert_held(&mm->mmap_sem);
do {
/* If range is no longer valid force retry. */
- if (!range->valid)
+ if (mmu_interval_check_retry(range->notifier,
+ range->notifier_seq))
return -EBUSY;
+ ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
+ &hmm_walk_ops, &hmm_vma_walk);
+ } while (ret == -EBUSY);
- vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & device_vma))
- return -EFAULT;
-
- if (is_vm_hugetlb_page(vma)) {
- if (huge_page_shift(hstate_vma(vma)) !=
- range->page_shift &&
- range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- } else {
- if (range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- }
-
- if (!(vma->vm_flags & VM_READ)) {
- /*
- * If vma do not allow read access, then assume that it
- * does not allow write access, either. HMM does not
- * support architecture that allow write without read.
- */
- hmm_pfns_clear(range, range->pfns,
- range->start, range->end);
- return -EPERM;
- }
-
- range->vma = vma;
- hmm_vma_walk.pgmap = NULL;
- hmm_vma_walk.last = start;
- hmm_vma_walk.fault = true;
- hmm_vma_walk.block = block;
- hmm_vma_walk.range = range;
- mm_walk.private = &hmm_vma_walk;
- end = min(range->end, vma->vm_end);
-
- mm_walk.vma = vma;
- mm_walk.mm = vma->vm_mm;
- mm_walk.pte_entry = NULL;
- mm_walk.test_walk = NULL;
- mm_walk.hugetlb_entry = NULL;
- mm_walk.pud_entry = hmm_vma_walk_pud;
- mm_walk.pmd_entry = hmm_vma_walk_pmd;
- mm_walk.pte_hole = hmm_vma_walk_hole;
- mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
-
- do {
- ret = walk_page_range(start, end, &mm_walk);
- start = hmm_vma_walk.last;
-
- /* Keep trying while the range is valid. */
- } while (ret == -EBUSY && range->valid);
-
- if (ret) {
- unsigned long i;
-
- i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
- hmm_pfns_clear(range, &range->pfns[i],
- hmm_vma_walk.last, range->end);
- return ret;
- }
- start = end;
-
- } while (start < range->end);
-
+ if (ret)
+ return ret;
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
EXPORT_SYMBOL(hmm_range_fault);
-
-/**
- * hmm_range_dma_map() - hmm_range_fault() and dma map page all in one.
- * @range: range being faulted
- * @device: device against to dma map page to
- * @daddrs: dma address of mapped pages
- * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
- * Return: number of pages mapped on success, -EAGAIN if mmap_sem have been
- * drop and you need to try again, some other error value otherwise
- *
- * Note same usage pattern as hmm_range_fault().
- */
-long hmm_range_dma_map(struct hmm_range *range,
- struct device *device,
- dma_addr_t *daddrs,
- bool block)
-{
- unsigned long i, npages, mapped;
- long ret;
-
- ret = hmm_range_fault(range, block);
- if (ret <= 0)
- return ret ? ret : -EBUSY;
-
- npages = (range->end - range->start) >> PAGE_SHIFT;
- for (i = 0, mapped = 0; i < npages; ++i) {
- enum dma_data_direction dir = DMA_TO_DEVICE;
- struct page *page;
-
- /*
- * FIXME need to update DMA API to provide invalid DMA address
- * value instead of a function to test dma address value. This
- * would remove lot of dumb code duplicated accross many arch.
- *
- * For now setting it to 0 here is good enough as the pfns[]
- * value is what is use to check what is valid and what isn't.
- */
- daddrs[i] = 0;
-
- page = hmm_device_entry_to_page(range, range->pfns[i]);
- if (page == NULL)
- continue;
-
- /* Check if range is being invalidated */
- if (!range->valid) {
- ret = -EBUSY;
- goto unmap;
- }
-
- /* If it is read and write than map bi-directional. */
- if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
- dir = DMA_BIDIRECTIONAL;
-
- daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
- if (dma_mapping_error(device, daddrs[i])) {
- ret = -EFAULT;
- goto unmap;
- }
-
- mapped++;
- }
-
- return mapped;
-
-unmap:
- for (npages = i, i = 0; (i < npages) && mapped; ++i) {
- enum dma_data_direction dir = DMA_TO_DEVICE;
- struct page *page;
-
- page = hmm_device_entry_to_page(range, range->pfns[i]);
- if (page == NULL)
- continue;
-
- if (dma_mapping_error(device, daddrs[i]))
- continue;
-
- /* If it is read and write than map bi-directional. */
- if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
- dir = DMA_BIDIRECTIONAL;
-
- dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
- mapped--;
- }
-
- return ret;
-}
-EXPORT_SYMBOL(hmm_range_dma_map);
-
-/**
- * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
- * @range: range being unmapped
- * @vma: the vma against which the range (optional)
- * @device: device against which dma map was done
- * @daddrs: dma address of mapped pages
- * @dirty: dirty page if it had the write flag set
- * Return: number of page unmapped on success, -EINVAL otherwise
- *
- * Note that caller MUST abide by mmu notifier or use HMM mirror and abide
- * to the sync_cpu_device_pagetables() callback so that it is safe here to
- * call set_page_dirty(). Caller must also take appropriate locks to avoid
- * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
- */
-long hmm_range_dma_unmap(struct hmm_range *range,
- struct vm_area_struct *vma,
- struct device *device,
- dma_addr_t *daddrs,
- bool dirty)
-{
- unsigned long i, npages;
- long cpages = 0;
-
- /* Sanity check. */
- if (range->end <= range->start)
- return -EINVAL;
- if (!daddrs)
- return -EINVAL;
- if (!range->pfns)
- return -EINVAL;
-
- npages = (range->end - range->start) >> PAGE_SHIFT;
- for (i = 0; i < npages; ++i) {
- enum dma_data_direction dir = DMA_TO_DEVICE;
- struct page *page;
-
- page = hmm_device_entry_to_page(range, range->pfns[i]);
- if (page == NULL)
- continue;
-
- /* If it is read and write than map bi-directional. */
- if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) {
- dir = DMA_BIDIRECTIONAL;
-
- /*
- * See comments in function description on why it is
- * safe here to call set_page_dirty()
- */
- if (dirty)
- set_page_dirty(page);
- }
-
- /* Unmap and clear pfns/dma address */
- dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
- range->pfns[i] = range->values[HMM_PFN_NONE];
- /* FIXME see comments in hmm_vma_dma_map() */
- daddrs[i] = 0;
- cpages++;
- }
-
- return cpages;
-}
-EXPORT_SYMBOL(hmm_range_dma_unmap);
OpenPOWER on IntegriCloud