Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/hmm.c b/mm/hmm.c
index 90193a7..902f5fa 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1,23 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright 2013 Red Hat Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Authors: Jérôme Glisse <jglisse@redhat.com>
+ * 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/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
@@ -29,190 +20,140 @@
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
+#include <linux/sched/mm.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;
-
-/*
- * struct hmm - HMM per mm struct
- *
- * @mm: mm struct this HMM struct is bound to
- * @lock: lock protecting ranges list
- * @sequence: we track updates to the CPU page table with a sequence number
- * @ranges: list of range being snapshotted
- * @mirrors: list of mirrors for this mm
- * @mmu_notifier: mmu notifier to track updates to CPU page table
- * @mirrors_sem: read/write semaphore protecting the mirrors list
- */
-struct hmm {
- struct mm_struct *mm;
- spinlock_t lock;
- atomic_t sequence;
- struct list_head ranges;
- struct list_head mirrors;
- struct mmu_notifier mmu_notifier;
- struct rw_semaphore mirrors_sem;
-};
-
-/*
- * hmm_register - register HMM against an mm (HMM internal)
- *
- * @mm: mm struct to attach to
- *
- * This is not intended to be used directly by device drivers. It allocates an
- * HMM struct if mm does not have one, and initializes it.
- */
-static struct hmm *hmm_register(struct mm_struct *mm)
+static struct mmu_notifier *hmm_alloc_notifier(struct mm_struct *mm)
{
- struct hmm *hmm = READ_ONCE(mm->hmm);
- bool cleanup = false;
+ struct hmm *hmm;
- /*
- * The hmm struct can only be freed once the mm_struct goes away,
- * hence we should always have pre-allocated an new hmm struct
- * above.
- */
- if (hmm)
- return hmm;
-
- hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
+ hmm = kzalloc(sizeof(*hmm), GFP_KERNEL);
if (!hmm)
- return NULL;
+ return ERR_PTR(-ENOMEM);
+
+ init_waitqueue_head(&hmm->wq);
INIT_LIST_HEAD(&hmm->mirrors);
init_rwsem(&hmm->mirrors_sem);
- atomic_set(&hmm->sequence, 0);
- hmm->mmu_notifier.ops = NULL;
INIT_LIST_HEAD(&hmm->ranges);
- spin_lock_init(&hmm->lock);
- hmm->mm = mm;
+ spin_lock_init(&hmm->ranges_lock);
+ hmm->notifiers = 0;
+ return &hmm->mmu_notifier;
+}
- spin_lock(&mm->page_table_lock);
- if (!mm->hmm)
- mm->hmm = hmm;
- else
- cleanup = true;
- spin_unlock(&mm->page_table_lock);
+static void hmm_free_notifier(struct mmu_notifier *mn)
+{
+ struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
- 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 mm->hmm;
-
-error_mm:
- spin_lock(&mm->page_table_lock);
- if (mm->hmm == hmm)
- mm->hmm = NULL;
- spin_unlock(&mm->page_table_lock);
-error:
+ WARN_ON(!list_empty(&hmm->ranges));
+ WARN_ON(!list_empty(&hmm->mirrors));
kfree(hmm);
- return NULL;
-}
-
-void hmm_mm_destroy(struct mm_struct *mm)
-{
- kfree(mm->hmm);
-}
-
-static void hmm_invalidate_range(struct hmm *hmm,
- enum hmm_update_type action,
- unsigned long start,
- unsigned long end)
-{
- struct hmm_mirror *mirror;
- struct hmm_range *range;
-
- spin_lock(&hmm->lock);
- list_for_each_entry(range, &hmm->ranges, list) {
- unsigned long addr, idx, npages;
-
- if (end < range->start || start >= range->end)
- continue;
-
- range->valid = false;
- addr = max(start, range->start);
- idx = (addr - range->start) >> PAGE_SHIFT;
- npages = (min(range->end, end) - addr) >> PAGE_SHIFT;
- memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages);
- }
- spin_unlock(&hmm->lock);
-
- down_read(&hmm->mirrors_sem);
- list_for_each_entry(mirror, &hmm->mirrors, list)
- mirror->ops->sync_cpu_device_pagetables(mirror, action,
- start, end);
- up_read(&hmm->mirrors_sem);
}
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;
- struct hmm *hmm = mm->hmm;
- 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);
+ /*
+ * 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);
- down_write(&hmm->mirrors_sem);
- }
- mirror = list_first_entry_or_null(&hmm->mirrors,
- struct hmm_mirror, list);
}
- up_write(&hmm->mirrors_sem);
+ up_read(&hmm->mirrors_sem);
+}
+
+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,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end,
- bool blockable)
+ const struct mmu_notifier_range *nrange)
{
- struct hmm *hmm = mm->hmm;
+ struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
+ struct hmm_mirror *mirror;
+ struct hmm_range *range;
+ unsigned long flags;
+ int ret = 0;
- VM_BUG_ON(!hmm);
+ spin_lock_irqsave(&hmm->ranges_lock, flags);
+ hmm->notifiers++;
+ list_for_each_entry(range, &hmm->ranges, list) {
+ if (nrange->end < range->start || nrange->start >= range->end)
+ continue;
- atomic_inc(&hmm->sequence);
+ range->valid = false;
+ }
+ spin_unlock_irqrestore(&hmm->ranges_lock, flags);
- return 0;
+ 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, nrange);
+ if (rc) {
+ if (WARN_ON(mmu_notifier_range_blockable(nrange) ||
+ rc != -EAGAIN))
+ continue;
+ ret = -EAGAIN;
+ break;
+ }
+ }
+ up_read(&hmm->mirrors_sem);
+
+out:
+ if (ret)
+ notifiers_decrement(hmm);
+ return ret;
}
static void hmm_invalidate_range_end(struct mmu_notifier *mn,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
+ const struct mmu_notifier_range *nrange)
{
- struct hmm *hmm = mm->hmm;
+ struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
- VM_BUG_ON(!hmm);
-
- hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end);
+ notifiers_decrement(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,
+ .alloc_notifier = hmm_alloc_notifier,
+ .free_notifier = hmm_free_notifier,
};
/*
@@ -220,36 +161,35 @@
*
* @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.
*
- * THE mm->mmap_sem MUST BE HELD IN WRITE MODE !
+ * The caller cannot unregister the hmm_mirror while any ranges are
+ * registered.
+ *
+ * Callers using this function must put a call to mmu_notifier_synchronize()
+ * in their module exit functions.
*/
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
+ struct mmu_notifier *mn;
+
+ lockdep_assert_held_write(&mm->mmap_sem);
+
/* Sanity check */
if (!mm || !mirror || !mirror->ops)
return -EINVAL;
-again:
- mirror->hmm = hmm_register(mm);
- if (!mirror->hmm)
- return -ENOMEM;
+ mn = mmu_notifier_get_locked(&hmm_mmu_notifier_ops, mm);
+ if (IS_ERR(mn))
+ return PTR_ERR(mn);
+ mirror->hmm = container_of(mn, struct hmm, mmu_notifier);
down_write(&mirror->hmm->mirrors_sem);
- if (mirror->hmm->mm == NULL) {
- /*
- * A racing hmm_mirror_unregister() is about to destroy the hmm
- * struct. Try again to allocate a new one.
- */
- up_write(&mirror->hmm->mirrors_sem);
- mirror->hmm = NULL;
- goto again;
- } else {
- list_add(&mirror->list, &mirror->hmm->mirrors);
- up_write(&mirror->hmm->mirrors_sem);
- }
+ list_add(&mirror->list, &mirror->hmm->mirrors);
+ up_write(&mirror->hmm->mirrors_sem);
return 0;
}
@@ -258,69 +198,58 @@
/*
* hmm_mirror_unregister() - unregister a mirror
*
- * @mirror: new mirror struct to register
+ * @mirror: mirror struct to unregister
*
* Stop mirroring a process address space, and cleanup.
*/
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
- bool should_unregister = false;
- struct mm_struct *mm;
- struct hmm *hmm;
+ struct hmm *hmm = mirror->hmm;
- if (mirror->hmm == NULL)
- return;
-
- hmm = mirror->hmm;
down_write(&hmm->mirrors_sem);
- list_del_init(&mirror->list);
- should_unregister = list_empty(&hmm->mirrors);
- mirror->hmm = NULL;
- mm = hmm->mm;
- hmm->mm = NULL;
+ list_del(&mirror->list);
up_write(&hmm->mirrors_sem);
-
- if (!should_unregister || mm == NULL)
- return;
-
- 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);
+ mmu_notifier_put(&hmm->mmu_notifier);
}
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,
bool write_fault, uint64_t *pfn)
{
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
+ unsigned int flags = FAULT_FLAG_REMOTE;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
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;
- ret = handle_mm_fault(vma, addr, flags);
- if (ret & VM_FAULT_RETRY)
- return -EBUSY;
- if (ret & VM_FAULT_ERROR) {
- *pfn = range->values[HMM_PFN_ERROR];
- return -EFAULT;
- }
+ if (!vma)
+ goto err;
- return -EAGAIN;
+ 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) {
+ /* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */
+ return -EAGAIN;
+ }
+ 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,
@@ -340,13 +269,13 @@
}
/*
- * 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 ?
* @walk: mm_walk structure
- * Returns: 0 on success, -EAGAIN after page fault, or page fault error
+ * Return: 0 on success, -EBUSY after page fault, or page fault error
*
* This function will be called whenever pmd_none() or pte_none() returns true,
* or whenever there is no page directory covering the virtual address range.
@@ -362,6 +291,10 @@
hmm_vma_walk->last = addr;
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++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
@@ -369,12 +302,12 @@
ret = hmm_vma_do_fault(walk, addr, write_fault,
&pfns[i]);
- if (ret != -EAGAIN)
+ if (ret != -EBUSY)
return ret;
}
}
- return (fault || write_fault) ? -EAGAIN : 0;
+ return (fault || write_fault) ? -EBUSY : 0;
}
static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
@@ -383,14 +316,25 @@
{
struct hmm_range *range = hmm_vma_walk->range;
- *fault = *write_fault = false;
- 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 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.
+ */
+ pfns = (pfns & range->pfn_flags_mask) | range->default_flags;
+
/* 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]) {
@@ -417,15 +361,16 @@
{
unsigned long i;
- if (!hmm_vma_walk->fault) {
+ if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) {
*fault = *write_fault = false;
return;
}
+ *fault = *write_fault = false;
for (i = 0; i < npages; ++i) {
hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags,
fault, write_fault);
- if ((*fault) || (*write_fault))
+ if ((*write_fault))
return;
}
}
@@ -456,11 +401,9 @@
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;
@@ -476,16 +419,32 @@
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);
- for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
- pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+ 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,
+ hmm_vma_walk->pgmap);
+ if (unlikely(!hmm_vma_walk->pgmap))
+ return -EBUSY;
+ }
+ pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
+ }
+ if (hmm_vma_walk->pgmap) {
+ put_dev_pagemap(hmm_vma_walk->pgmap);
+ hmm_vma_walk->pgmap = NULL;
+ }
hmm_vma_walk->last = end;
return 0;
}
+#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)
{
- if (pte_none(pte) || !pte_present(pte))
+ if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
return 0;
return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
@@ -498,18 +457,17 @@
{
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;
uint64_t orig_pfn = *pfn;
*pfn = range->values[HMM_PFN_NONE];
- cpu_flags = pte_to_hmm_pfn_flags(range, pte);
- hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
- &fault, &write_fault);
+ fault = write_fault = false;
if (pte_none(pte)) {
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0,
+ &fault, &write_fault);
if (fault || write_fault)
goto fault;
return 0;
@@ -519,6 +477,9 @@
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;
@@ -537,7 +498,8 @@
&fault, &write_fault);
if (fault || write_fault)
goto fault;
- *pfn = hmm_pfn_from_pfn(range, swp_offset(entry));
+ *pfn = hmm_device_entry_from_pfn(range,
+ swp_offset(entry));
*pfn |= cpu_flags;
return 0;
}
@@ -546,9 +508,8 @@
if (fault || write_fault) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
- migration_entry_wait(vma->vm_mm,
- pmdp, addr);
- return -EAGAIN;
+ migration_entry_wait(walk->mm, pmdp, addr);
+ return -EBUSY;
}
return 0;
}
@@ -556,15 +517,33 @@
/* Report error for everything else */
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
+ } else {
+ 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;
- *pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
+ if (pte_devmap(pte)) {
+ hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte),
+ hmm_vma_walk->pgmap);
+ 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;
+ }
+
+ *pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
return 0;
fault:
+ if (hmm_vma_walk->pgmap) {
+ put_dev_pagemap(hmm_vma_walk->pgmap);
+ hmm_vma_walk->pgmap = NULL;
+ }
pte_unmap(ptep);
/* Fault any virtual address we were asked to fault */
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
@@ -580,25 +559,40 @@
uint64_t *pfns = range->pfns;
unsigned long addr = start, i;
pte_t *ptep;
-
- i = (addr - range->start) >> PAGE_SHIFT;
+ pmd_t pmd;
again:
- if (pmd_none(*pmdp))
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
return hmm_vma_walk_hole(start, end, walk);
- if (pmd_huge(*pmdp) && (range->vma->vm_flags & VM_HUGETLB))
+ if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
+ bool fault, write_fault;
+ unsigned long npages;
+ uint64_t *pfns;
+
+ i = (addr - range->start) >> PAGE_SHIFT;
+ npages = (end - addr) >> PAGE_SHIFT;
+ pfns = &range->pfns[i];
+
+ hmm_range_need_fault(hmm_vma_walk, pfns, npages,
+ 0, &fault, &write_fault);
+ if (fault || write_fault) {
+ hmm_vma_walk->last = addr;
+ pmd_migration_entry_wait(walk->mm, pmdp);
+ return -EBUSY;
+ }
+ return 0;
+ } else if (!pmd_present(pmd))
return hmm_pfns_bad(start, end, walk);
- if (pmd_devmap(*pmdp) || pmd_trans_huge(*pmdp)) {
- pmd_t pmd;
-
+ 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.
*/
@@ -607,13 +601,21 @@
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
+ i = (addr - range->start) >> PAGE_SHIFT;
return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd);
}
- if (pmd_bad(*pmdp))
+ /*
+ * 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);
ptep = pte_offset_map(pmdp, addr);
+ i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
int r;
@@ -624,12 +626,150 @@
return r;
}
}
+ if (hmm_vma_walk->pgmap) {
+ /*
+ * We do put_dev_pagemap() here and not in hmm_vma_handle_pte()
+ * so that we can leverage get_dev_pagemap() optimization which
+ * will not re-take a reference on a pgmap if we already have
+ * one.
+ */
+ put_dev_pagemap(hmm_vma_walk->pgmap);
+ hmm_vma_walk->pgmap = NULL;
+ }
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
+#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;
+ pud_t pud;
+ int ret;
+
+again:
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ return hmm_vma_walk_hole(start, end, walk);
+
+ 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);
+
+ i = (addr - range->start) >> PAGE_SHIFT;
+ npages = (end - addr) >> PAGE_SHIFT;
+ pfns = &range->pfns[i];
+
+ 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);
+
+ 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;
+ pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
+ cpu_flags;
+ }
+ if (hmm_vma_walk->pgmap) {
+ put_dev_pagemap(hmm_vma_walk->pgmap);
+ hmm_vma_walk->pgmap = NULL;
+ }
+ hmm_vma_walk->last = end;
+ return 0;
+ }
+
+ 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);
+
+ return 0;
+}
+#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)
+{
+ 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;
+ uint64_t orig_pfn, cpu_flags;
+ bool fault, write_fault;
+ spinlock_t *ptl;
+ pte_t entry;
+ int ret = 0;
+
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
+ entry = huge_ptep_get(pte);
+
+ 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);
+ fault = write_fault = false;
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+ &fault, &write_fault);
+ if (fault || write_fault) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+
+ 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;
+
+unlock:
+ spin_unlock(ptl);
+
+ if (ret == -ENOENT)
+ return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
+
+ return ret;
+}
+#else
+#define hmm_vma_walk_hugetlb_entry NULL
+#endif /* CONFIG_HUGETLB_PAGE */
+
static void hmm_pfns_clear(struct hmm_range *range,
uint64_t *pfns,
unsigned long addr,
@@ -639,789 +779,320 @@
*pfns = range->values[HMM_PFN_NONE];
}
-static void hmm_pfns_special(struct hmm_range *range)
-{
- unsigned long addr = range->start, i = 0;
-
- for (; addr < range->end; addr += PAGE_SIZE, i++)
- range->pfns[i] = range->values[HMM_PFN_SPECIAL];
-}
-
/*
- * hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses
- * @range: range being snapshotted
- * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
- * vma permission, 0 success
+ * 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
*
- * This snapshots the CPU page table for a range of virtual addresses. Snapshot
- * validity is tracked by range struct. See hmm_vma_range_done() for further
- * information.
+ * Return: 0 on success, -EFAULT if the address space is no longer valid
*
- * The range struct is initialized here. It tracks the CPU page table, but only
- * if the function returns success (0), in which case the caller must then call
- * hmm_vma_range_done() to stop CPU page table update tracking on this range.
- *
- * NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS
- * MEMORY CORRUPTION ! YOU HAVE BEEN WARNED !
+ * Track updates to the CPU page table see include/linux/hmm.h
*/
-int hmm_vma_get_pfns(struct hmm_range *range)
+int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror)
{
- struct vm_area_struct *vma = range->vma;
- struct hmm_vma_walk hmm_vma_walk;
- struct mm_walk mm_walk;
- struct hmm *hmm;
+ struct hmm *hmm = mirror->hmm;
+ unsigned long flags;
- /* Sanity check, this really should not happen ! */
- if (range->start < vma->vm_start || range->start >= vma->vm_end)
+ range->valid = false;
+ range->hmm = NULL;
+
+ if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1)))
return -EINVAL;
- if (range->end < vma->vm_start || range->end > vma->vm_end)
+ if (range->start >= range->end)
return -EINVAL;
- hmm = hmm_register(vma->vm_mm);
- if (!hmm)
- return -ENOMEM;
- /* Caller must have registered a mirror, via hmm_mirror_register() ! */
- if (!hmm->mmu_notifier.ops)
- return -EINVAL;
+ /* Prevent hmm_release() from running while the range is valid */
+ if (!mmget_not_zero(hmm->mmu_notifier.mm))
+ return -EFAULT;
- /* FIXME support hugetlb fs */
- if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
- vma_is_dax(vma)) {
- hmm_pfns_special(range);
- return -EINVAL;
- }
+ /* Initialize range to track CPU page table updates. */
+ spin_lock_irqsave(&hmm->ranges_lock, flags);
- if (!(vma->vm_flags & VM_READ)) {
- /*
- * If vma do not allow read access, then assume that it does
- * not allow write access, either. Architecture that allow
- * write without read access are not supported by HMM, because
- * operations such has atomic access would not work.
- */
- hmm_pfns_clear(range, range->pfns, range->start, range->end);
- return -EPERM;
- }
+ range->hmm = hmm;
+ list_add(&range->list, &hmm->ranges);
- /* Initialize range to track CPU page table update */
- spin_lock(&hmm->lock);
- range->valid = true;
- list_add_rcu(&range->list, &hmm->ranges);
- spin_unlock(&hmm->lock);
+ /*
+ * If there are any concurrent notifiers we have to wait for them for
+ * the range to be valid (see hmm_range_wait_until_valid()).
+ */
+ if (!hmm->notifiers)
+ range->valid = true;
+ spin_unlock_irqrestore(&hmm->ranges_lock, flags);
- hmm_vma_walk.fault = false;
- hmm_vma_walk.range = range;
- mm_walk.private = &hmm_vma_walk;
-
- 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.pmd_entry = hmm_vma_walk_pmd;
- mm_walk.pte_hole = hmm_vma_walk_hole;
-
- walk_page_range(range->start, range->end, &mm_walk);
return 0;
}
-EXPORT_SYMBOL(hmm_vma_get_pfns);
+EXPORT_SYMBOL(hmm_range_register);
/*
- * hmm_vma_range_done() - stop tracking change to CPU page table over a range
- * @range: range being tracked
- * Returns: false if range data has been invalidated, true otherwise
+ * 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
- * either hmm_vma_get_pfns() or hmm_vma_fault(). Once the device driver is done
- * using the data, or wants to lock updates to the data it got from those
- * functions, it must call the hmm_vma_range_done() function, which will then
- * stop tracking CPU page table updates.
- *
- * Note that device driver must still implement general CPU page table update
- * tracking either by using hmm_mirror (see hmm_mirror_register()) or by using
- * the mmu_notifier API directly.
- *
- * CPU page table update tracking done through hmm_range is only temporary and
- * to be used while trying to duplicate CPU page table contents for a range of
- * virtual addresses.
- *
- * There are two ways to use this :
- * again:
- * hmm_vma_get_pfns(range); or hmm_vma_fault(...);
- * trans = device_build_page_table_update_transaction(pfns);
- * device_page_table_lock();
- * if (!hmm_vma_range_done(range)) {
- * device_page_table_unlock();
- * goto again;
- * }
- * device_commit_transaction(trans);
- * device_page_table_unlock();
- *
- * Or:
- * hmm_vma_get_pfns(range); or hmm_vma_fault(...);
- * device_page_table_lock();
- * hmm_vma_range_done(range);
- * device_update_page_table(range->pfns);
- * device_page_table_unlock();
+ * hmm_range_register(). See include/linux/hmm.h for how to use it.
*/
-bool hmm_vma_range_done(struct hmm_range *range)
+void hmm_range_unregister(struct hmm_range *range)
{
- unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
- struct hmm *hmm;
+ struct hmm *hmm = range->hmm;
+ unsigned long flags;
- if (range->end <= range->start) {
- BUG();
- return false;
- }
+ spin_lock_irqsave(&hmm->ranges_lock, flags);
+ list_del_init(&range->list);
+ spin_unlock_irqrestore(&hmm->ranges_lock, flags);
- hmm = hmm_register(range->vma->vm_mm);
- if (!hmm) {
- memset(range->pfns, 0, sizeof(*range->pfns) * npages);
- return false;
- }
+ /* Drop reference taken by hmm_range_register() */
+ mmput(hmm->mmu_notifier.mm);
- spin_lock(&hmm->lock);
- list_del_rcu(&range->list);
- spin_unlock(&hmm->lock);
-
- return range->valid;
+ /*
+ * 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.
+ */
+ range->valid = false;
+ memset(&range->hmm, POISON_INUSE, sizeof(range->hmm));
}
-EXPORT_SYMBOL(hmm_vma_range_done);
+EXPORT_SYMBOL(hmm_range_unregister);
-/*
- * hmm_vma_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)
- * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
+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,
+};
+
+/**
+ * hmm_range_fault - try to fault some address in a virtual address range
+ * @range: range being faulted
+ * @flags: HMM_FAULT_* flags
+ *
+ * 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.
+ * any memory migration if the memory being faulted is not accessible by CPUs
+ * and caller does not ask for migration.
*
* On error, for one virtual address in the range, the function will mark the
* corresponding HMM pfn entry with an error flag.
- *
- * Expected use pattern:
- * retry:
- * down_read(&mm->mmap_sem);
- * // Find vma and address device wants to fault, initialize hmm_pfn_t
- * // array accordingly
- * ret = hmm_vma_fault(range, write, block);
- * switch (ret) {
- * case -EAGAIN:
- * hmm_vma_range_done(range);
- * // You might want to rate limit or yield to play nicely, you may
- * // also commit any valid pfn in the array assuming that you are
- * // getting true from hmm_vma_range_monitor_end()
- * goto retry;
- * case 0:
- * break;
- * case -ENOMEM:
- * case -EINVAL:
- * case -EPERM:
- * default:
- * // Handle error !
- * up_read(&mm->mmap_sem)
- * return;
- * }
- * // Take device driver lock that serialize device page table update
- * driver_lock_device_page_table_update();
- * hmm_vma_range_done(range);
- * // Commit pfns we got from hmm_vma_fault()
- * driver_unlock_device_page_table_update();
- * up_read(&mm->mmap_sem)
- *
- * YOU MUST CALL hmm_vma_range_done() AFTER THIS FUNCTION RETURN SUCCESS (0)
- * BEFORE FREEING THE range struct OR YOU WILL HAVE SERIOUS MEMORY CORRUPTION !
- *
- * YOU HAVE BEEN WARNED !
*/
-int hmm_vma_fault(struct hmm_range *range, bool block)
+long hmm_range_fault(struct hmm_range *range, unsigned int flags)
{
- struct vm_area_struct *vma = range->vma;
- unsigned long start = range->start;
+ 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 mm_walk mm_walk;
- struct hmm *hmm;
+ struct hmm *hmm = range->hmm;
+ struct vm_area_struct *vma;
int ret;
- /* Sanity check, this really should not happen ! */
- if (range->start < vma->vm_start || range->start >= vma->vm_end)
- return -EINVAL;
- if (range->end < vma->vm_start || range->end > vma->vm_end)
- return -EINVAL;
-
- hmm = hmm_register(vma->vm_mm);
- if (!hmm) {
- hmm_pfns_clear(range, range->pfns, range->start, range->end);
- return -ENOMEM;
- }
- /* Caller must have registered a mirror using hmm_mirror_register() */
- if (!hmm->mmu_notifier.ops)
- return -EINVAL;
-
- /* FIXME support hugetlb fs */
- if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
- vma_is_dax(vma)) {
- hmm_pfns_special(range);
- 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. Architecture that allow
- * write without read access are not supported by HMM, because
- * operations such has atomic access would not work.
- */
- hmm_pfns_clear(range, range->pfns, range->start, range->end);
- return -EPERM;
- }
-
- /* Initialize range to track CPU page table update */
- spin_lock(&hmm->lock);
- range->valid = true;
- list_add_rcu(&range->list, &hmm->ranges);
- spin_unlock(&hmm->lock);
-
- hmm_vma_walk.fault = true;
- hmm_vma_walk.block = block;
- hmm_vma_walk.range = range;
- mm_walk.private = &hmm_vma_walk;
- hmm_vma_walk.last = range->start;
-
- 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.pmd_entry = hmm_vma_walk_pmd;
- mm_walk.pte_hole = hmm_vma_walk_hole;
+ lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem);
do {
- ret = walk_page_range(start, range->end, &mm_walk);
- start = hmm_vma_walk.last;
- } while (ret == -EAGAIN);
+ /* If range is no longer valid force retry. */
+ if (!range->valid)
+ return -EBUSY;
- if (ret) {
- unsigned long i;
+ vma = find_vma(hmm->mmu_notifier.mm, start);
+ if (vma == NULL || (vma->vm_flags & device_vma))
+ return -EFAULT;
- i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
- hmm_pfns_clear(range, &range->pfns[i], hmm_vma_walk.last,
- range->end);
- hmm_vma_range_done(range);
- }
- return ret;
-}
-EXPORT_SYMBOL(hmm_vma_fault);
-#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-
-
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
-struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
- unsigned long addr)
-{
- struct page *page;
-
- page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
- if (!page)
- return NULL;
- lock_page(page);
- return page;
-}
-EXPORT_SYMBOL(hmm_vma_alloc_locked_page);
-
-
-static void hmm_devmem_ref_release(struct percpu_ref *ref)
-{
- struct hmm_devmem *devmem;
-
- devmem = container_of(ref, struct hmm_devmem, ref);
- complete(&devmem->completion);
-}
-
-static void hmm_devmem_ref_exit(void *data)
-{
- struct percpu_ref *ref = data;
- struct hmm_devmem *devmem;
-
- devmem = container_of(ref, struct hmm_devmem, ref);
- percpu_ref_exit(ref);
- devm_remove_action(devmem->device, &hmm_devmem_ref_exit, data);
-}
-
-static void hmm_devmem_ref_kill(void *data)
-{
- struct percpu_ref *ref = data;
- struct hmm_devmem *devmem;
-
- devmem = container_of(ref, struct hmm_devmem, ref);
- percpu_ref_kill(ref);
- wait_for_completion(&devmem->completion);
- devm_remove_action(devmem->device, &hmm_devmem_ref_kill, data);
-}
-
-static int hmm_devmem_fault(struct vm_area_struct *vma,
- unsigned long addr,
- const struct page *page,
- unsigned int flags,
- pmd_t *pmdp)
-{
- struct hmm_devmem *devmem = page->pgmap->data;
-
- return devmem->ops->fault(devmem, vma, addr, page, flags, pmdp);
-}
-
-static void hmm_devmem_free(struct page *page, void *data)
-{
- struct hmm_devmem *devmem = data;
-
- page->mapping = NULL;
-
- devmem->ops->free(devmem, page);
-}
-
-static DEFINE_MUTEX(hmm_devmem_lock);
-static RADIX_TREE(hmm_devmem_radix, GFP_KERNEL);
-
-static void hmm_devmem_radix_release(struct resource *resource)
-{
- resource_size_t key;
-
- mutex_lock(&hmm_devmem_lock);
- for (key = resource->start;
- key <= resource->end;
- key += PA_SECTION_SIZE)
- radix_tree_delete(&hmm_devmem_radix, key >> PA_SECTION_SHIFT);
- mutex_unlock(&hmm_devmem_lock);
-}
-
-static void hmm_devmem_release(struct device *dev, void *data)
-{
- struct hmm_devmem *devmem = data;
- struct resource *resource = devmem->resource;
- unsigned long start_pfn, npages;
- struct zone *zone;
- struct page *page;
-
- if (percpu_ref_tryget_live(&devmem->ref)) {
- dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
- percpu_ref_put(&devmem->ref);
- }
-
- /* pages are dead and unused, undo the arch mapping */
- start_pfn = (resource->start & ~(PA_SECTION_SIZE - 1)) >> PAGE_SHIFT;
- npages = ALIGN(resource_size(resource), PA_SECTION_SIZE) >> PAGE_SHIFT;
-
- page = pfn_to_page(start_pfn);
- zone = page_zone(page);
-
- mem_hotplug_begin();
- if (resource->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY)
- __remove_pages(zone, start_pfn, npages, NULL);
- else
- arch_remove_memory(start_pfn << PAGE_SHIFT,
- npages << PAGE_SHIFT, NULL);
- mem_hotplug_done();
-
- hmm_devmem_radix_release(resource);
-}
-
-static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
-{
- resource_size_t key, align_start, align_size, align_end;
- struct device *device = devmem->device;
- int ret, nid, is_ram;
- unsigned long pfn;
-
- align_start = devmem->resource->start & ~(PA_SECTION_SIZE - 1);
- align_size = ALIGN(devmem->resource->start +
- resource_size(devmem->resource),
- PA_SECTION_SIZE) - align_start;
-
- is_ram = region_intersects(align_start, align_size,
- IORESOURCE_SYSTEM_RAM,
- IORES_DESC_NONE);
- if (is_ram == REGION_MIXED) {
- WARN_ONCE(1, "%s attempted on mixed region %pr\n",
- __func__, devmem->resource);
- return -ENXIO;
- }
- if (is_ram == REGION_INTERSECTS)
- return -ENXIO;
-
- if (devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY)
- devmem->pagemap.type = MEMORY_DEVICE_PUBLIC;
- else
- devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-
- devmem->pagemap.res = *devmem->resource;
- devmem->pagemap.page_fault = hmm_devmem_fault;
- devmem->pagemap.page_free = hmm_devmem_free;
- devmem->pagemap.dev = devmem->device;
- devmem->pagemap.ref = &devmem->ref;
- devmem->pagemap.data = devmem;
-
- mutex_lock(&hmm_devmem_lock);
- align_end = align_start + align_size - 1;
- for (key = align_start; key <= align_end; key += PA_SECTION_SIZE) {
- struct hmm_devmem *dup;
-
- dup = radix_tree_lookup(&hmm_devmem_radix,
- key >> PA_SECTION_SHIFT);
- if (dup) {
- dev_err(device, "%s: collides with mapping for %s\n",
- __func__, dev_name(dup->device));
- mutex_unlock(&hmm_devmem_lock);
- ret = -EBUSY;
- goto error;
+ 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;
}
- ret = radix_tree_insert(&hmm_devmem_radix,
- key >> PA_SECTION_SHIFT,
- devmem);
+
+ hmm_vma_walk.pgmap = NULL;
+ hmm_vma_walk.last = start;
+ hmm_vma_walk.flags = flags;
+ hmm_vma_walk.range = range;
+ end = min(range->end, vma->vm_end);
+
+ walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops,
+ &hmm_vma_walk);
+
+ do {
+ ret = walk_page_range(vma->vm_mm, start, end,
+ &hmm_walk_ops, &hmm_vma_walk);
+ start = hmm_vma_walk.last;
+
+ /* Keep trying while the range is valid. */
+ } while (ret == -EBUSY && range->valid);
+
if (ret) {
- dev_err(device, "%s: failed: %d\n", __func__, ret);
- mutex_unlock(&hmm_devmem_lock);
- goto error_radix;
+ 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;
}
- }
- mutex_unlock(&hmm_devmem_lock);
+ start = end;
- nid = dev_to_node(device);
- if (nid < 0)
- nid = numa_mem_id();
+ } while (start < range->end);
- mem_hotplug_begin();
- /*
- * For device private memory we call add_pages() as we only need to
- * allocate and initialize struct page for the device memory. More-
- * over the device memory is un-accessible thus we do not want to
- * create a linear mapping for the memory like arch_add_memory()
- * would do.
- *
- * For device public memory, which is accesible by the CPU, we do
- * want the linear mapping and thus use arch_add_memory().
- */
- if (devmem->pagemap.type == MEMORY_DEVICE_PUBLIC)
- ret = arch_add_memory(nid, align_start, align_size, NULL,
- false);
- else
- ret = add_pages(nid, align_start >> PAGE_SHIFT,
- align_size >> PAGE_SHIFT, NULL, false);
- if (ret) {
- mem_hotplug_done();
- goto error_add_memory;
- }
- move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
- align_start >> PAGE_SHIFT,
- align_size >> PAGE_SHIFT, NULL);
- mem_hotplug_done();
-
- for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) {
- struct page *page = pfn_to_page(pfn);
-
- page->pgmap = &devmem->pagemap;
- }
- return 0;
-
-error_add_memory:
- untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
-error_radix:
- hmm_devmem_radix_release(devmem->resource);
-error:
- return ret;
+ return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
+EXPORT_SYMBOL(hmm_range_fault);
-static int hmm_devmem_match(struct device *dev, void *data, void *match_data)
-{
- struct hmm_devmem *devmem = data;
-
- return devmem->resource == match_data;
-}
-
-static void hmm_devmem_pages_remove(struct hmm_devmem *devmem)
-{
- devres_release(devmem->device, &hmm_devmem_release,
- &hmm_devmem_match, devmem->resource);
-}
-
-/*
- * hmm_devmem_add() - hotplug ZONE_DEVICE memory for device memory
+/**
+ * hmm_range_dma_map - hmm_range_fault() and dma map page all in one.
+ * @range: range being faulted
+ * @device: device to map page to
+ * @daddrs: array of dma addresses for the mapped pages
+ * @flags: HMM_FAULT_*
*
- * @ops: memory event device driver callback (see struct hmm_devmem_ops)
- * @device: device struct to bind the resource too
- * @size: size in bytes of the device memory to add
- * Returns: pointer to new hmm_devmem struct ERR_PTR otherwise
- *
- * This function first finds an empty range of physical address big enough to
- * contain the new resource, and then hotplugs it as ZONE_DEVICE memory, which
- * in turn allocates struct pages. It does not do anything beyond that; all
- * events affecting the memory will go through the various callbacks provided
- * by hmm_devmem_ops struct.
- *
- * Device driver should call this function during device initialization and
- * is then responsible of memory management. HMM only provides helpers.
+ * Return: the number of pages mapped on success (including zero), or any
+ * status return from hmm_range_fault() otherwise.
*/
-struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
- struct device *device,
- unsigned long size)
+long hmm_range_dma_map(struct hmm_range *range, struct device *device,
+ dma_addr_t *daddrs, unsigned int flags)
{
- struct hmm_devmem *devmem;
- resource_size_t addr;
- int ret;
+ unsigned long i, npages, mapped;
+ long ret;
- dev_pagemap_get_ops();
+ ret = hmm_range_fault(range, flags);
+ if (ret <= 0)
+ return ret ? ret : -EBUSY;
- devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
- GFP_KERNEL, dev_to_node(device));
- if (!devmem)
- return ERR_PTR(-ENOMEM);
+ 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;
- init_completion(&devmem->completion);
- devmem->pfn_first = -1UL;
- devmem->pfn_last = -1UL;
- devmem->resource = NULL;
- devmem->device = device;
- devmem->ops = ops;
+ /*
+ * 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;
- ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
- 0, GFP_KERNEL);
- if (ret)
- goto error_percpu_ref;
-
- ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
- if (ret)
- goto error_devm_add_action;
-
- size = ALIGN(size, PA_SECTION_SIZE);
- addr = min((unsigned long)iomem_resource.end,
- (1UL << MAX_PHYSMEM_BITS) - 1);
- addr = addr - size + 1UL;
-
- /*
- * FIXME add a new helper to quickly walk resource tree and find free
- * range
- *
- * FIXME what about ioport_resource resource ?
- */
- for (; addr > size && addr >= iomem_resource.start; addr -= size) {
- ret = region_intersects(addr, size, 0, IORES_DESC_NONE);
- if (ret != REGION_DISJOINT)
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
+ if (page == NULL)
continue;
- devmem->resource = devm_request_mem_region(device, addr, size,
- dev_name(device));
- if (!devmem->resource) {
- ret = -ENOMEM;
- goto error_no_resource;
+ /* Check if range is being invalidated */
+ if (!range->valid) {
+ ret = -EBUSY;
+ goto unmap;
}
- break;
- }
- if (!devmem->resource) {
- ret = -ERANGE;
- goto error_no_resource;
+
+ /* 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++;
}
- devmem->resource->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
- devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
- devmem->pfn_last = devmem->pfn_first +
- (resource_size(devmem->resource) >> PAGE_SHIFT);
+ return mapped;
- ret = hmm_devmem_pages_create(devmem);
- if (ret)
- goto error_pages;
+unmap:
+ for (npages = i, i = 0; (i < npages) && mapped; ++i) {
+ enum dma_data_direction dir = DMA_TO_DEVICE;
+ struct page *page;
- devres_add(device, devmem);
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
+ if (page == NULL)
+ continue;
- ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
- if (ret) {
- hmm_devmem_remove(devmem);
- return ERR_PTR(ret);
+ 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 devmem;
-
-error_pages:
- devm_release_mem_region(device, devmem->resource->start,
- resource_size(devmem->resource));
-error_no_resource:
-error_devm_add_action:
- hmm_devmem_ref_kill(&devmem->ref);
- hmm_devmem_ref_exit(&devmem->ref);
-error_percpu_ref:
- devres_free(devmem);
- return ERR_PTR(ret);
+ return ret;
}
-EXPORT_SYMBOL(hmm_devmem_add);
+EXPORT_SYMBOL(hmm_range_dma_map);
-struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
- struct device *device,
- struct resource *res)
-{
- struct hmm_devmem *devmem;
- int ret;
-
- if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY)
- return ERR_PTR(-EINVAL);
-
- dev_pagemap_get_ops();
-
- devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
- GFP_KERNEL, dev_to_node(device));
- if (!devmem)
- return ERR_PTR(-ENOMEM);
-
- init_completion(&devmem->completion);
- devmem->pfn_first = -1UL;
- devmem->pfn_last = -1UL;
- devmem->resource = res;
- devmem->device = device;
- devmem->ops = ops;
-
- ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
- 0, GFP_KERNEL);
- if (ret)
- goto error_percpu_ref;
-
- ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
- if (ret)
- goto error_devm_add_action;
-
-
- devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
- devmem->pfn_last = devmem->pfn_first +
- (resource_size(devmem->resource) >> PAGE_SHIFT);
-
- ret = hmm_devmem_pages_create(devmem);
- if (ret)
- goto error_devm_add_action;
-
- devres_add(device, devmem);
-
- ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
- if (ret) {
- hmm_devmem_remove(devmem);
- return ERR_PTR(ret);
- }
-
- return devmem;
-
-error_devm_add_action:
- hmm_devmem_ref_kill(&devmem->ref);
- hmm_devmem_ref_exit(&devmem->ref);
-error_percpu_ref:
- devres_free(devmem);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL(hmm_devmem_add_resource);
-
-/*
- * hmm_devmem_remove() - remove device memory (kill and free ZONE_DEVICE)
+/**
+ * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
+ * @range: range being unmapped
+ * @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
*
- * @devmem: hmm_devmem struct use to track and manage the ZONE_DEVICE memory
- *
- * This will hot-unplug memory that was hotplugged by hmm_devmem_add on behalf
- * of the device driver. It will free struct page and remove the resource that
- * reserved the physical address range for this device memory.
+ * 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.
*/
-void hmm_devmem_remove(struct hmm_devmem *devmem)
+long hmm_range_dma_unmap(struct hmm_range *range,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool dirty)
{
- resource_size_t start, size;
- struct device *device;
- bool cdm = false;
+ unsigned long i, npages;
+ long cpages = 0;
- if (!devmem)
- return;
+ /* Sanity check. */
+ if (range->end <= range->start)
+ return -EINVAL;
+ if (!daddrs)
+ return -EINVAL;
+ if (!range->pfns)
+ return -EINVAL;
- device = devmem->device;
- start = devmem->resource->start;
- size = resource_size(devmem->resource);
+ npages = (range->end - range->start) >> PAGE_SHIFT;
+ for (i = 0; i < npages; ++i) {
+ enum dma_data_direction dir = DMA_TO_DEVICE;
+ struct page *page;
- cdm = devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY;
- hmm_devmem_ref_kill(&devmem->ref);
- hmm_devmem_ref_exit(&devmem->ref);
- hmm_devmem_pages_remove(devmem);
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
+ if (page == NULL)
+ continue;
- if (!cdm)
- devm_release_mem_region(device, start, size);
-}
-EXPORT_SYMBOL(hmm_devmem_remove);
+ /* If it is read and write than map bi-directional. */
+ if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) {
+ dir = DMA_BIDIRECTIONAL;
-/*
- * A device driver that wants to handle multiple devices memory through a
- * single fake device can use hmm_device to do so. This is purely a helper
- * and it is not needed to make use of any HMM functionality.
- */
-#define HMM_DEVICE_MAX 256
+ /*
+ * See comments in function description on why it is
+ * safe here to call set_page_dirty()
+ */
+ if (dirty)
+ set_page_dirty(page);
+ }
-static DECLARE_BITMAP(hmm_device_mask, HMM_DEVICE_MAX);
-static DEFINE_SPINLOCK(hmm_device_lock);
-static struct class *hmm_device_class;
-static dev_t hmm_device_devt;
-
-static void hmm_device_release(struct device *device)
-{
- struct hmm_device *hmm_device;
-
- hmm_device = container_of(device, struct hmm_device, device);
- spin_lock(&hmm_device_lock);
- clear_bit(hmm_device->minor, hmm_device_mask);
- spin_unlock(&hmm_device_lock);
-
- kfree(hmm_device);
-}
-
-struct hmm_device *hmm_device_new(void *drvdata)
-{
- struct hmm_device *hmm_device;
-
- hmm_device = kzalloc(sizeof(*hmm_device), GFP_KERNEL);
- if (!hmm_device)
- return ERR_PTR(-ENOMEM);
-
- spin_lock(&hmm_device_lock);
- hmm_device->minor = find_first_zero_bit(hmm_device_mask, HMM_DEVICE_MAX);
- if (hmm_device->minor >= HMM_DEVICE_MAX) {
- spin_unlock(&hmm_device_lock);
- kfree(hmm_device);
- return ERR_PTR(-EBUSY);
+ /* 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++;
}
- set_bit(hmm_device->minor, hmm_device_mask);
- spin_unlock(&hmm_device_lock);
- dev_set_name(&hmm_device->device, "hmm_device%d", hmm_device->minor);
- hmm_device->device.devt = MKDEV(MAJOR(hmm_device_devt),
- hmm_device->minor);
- hmm_device->device.release = hmm_device_release;
- dev_set_drvdata(&hmm_device->device, drvdata);
- hmm_device->device.class = hmm_device_class;
- device_initialize(&hmm_device->device);
-
- return hmm_device;
+ return cpages;
}
-EXPORT_SYMBOL(hmm_device_new);
-
-void hmm_device_put(struct hmm_device *hmm_device)
-{
- put_device(&hmm_device->device);
-}
-EXPORT_SYMBOL(hmm_device_put);
-
-static int __init hmm_init(void)
-{
- int ret;
-
- ret = alloc_chrdev_region(&hmm_device_devt, 0,
- HMM_DEVICE_MAX,
- "hmm_device");
- if (ret)
- return ret;
-
- hmm_device_class = class_create(THIS_MODULE, "hmm_device");
- if (IS_ERR(hmm_device_class)) {
- unregister_chrdev_region(hmm_device_devt, HMM_DEVICE_MAX);
- return PTR_ERR(hmm_device_class);
- }
- return 0;
-}
-
-device_initcall(hmm_init);
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
+EXPORT_SYMBOL(hmm_range_dma_unmap);