* [PATCH v3 01/12] mm/hmm: select mmu notifier when selecting HMM v2
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 02/12] mm/hmm: use reference counting for HMM struct v3 jglisse
` (10 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Ralph Campbell,
John Hubbard, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
To avoid random config build issue, select mmu notifier when HMM is
selected. In any cases when HMM get selected it will be by users that
will also wants the mmu notifier.
Changes since v1:
- remove select MMU_NOTIFIER from HMM_MIRROR as it select HMM
which select MMU_NOTIFIER now
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
---
mm/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/Kconfig b/mm/Kconfig
index 25c71eb8a7db..2e6d24d783f7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -694,12 +694,12 @@ config DEV_PAGEMAP_OPS
config HMM
bool
+ select MMU_NOTIFIER
select MIGRATE_VMA_HELPER
config HMM_MIRROR
bool "HMM mirror CPU page table into a device page table"
depends on ARCH_HAS_HMM
- select MMU_NOTIFIER
select HMM
help
Select HMM_MIRROR if you want to mirror range of the CPU page table of a
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 02/12] mm/hmm: use reference counting for HMM struct v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
2019-04-03 19:33 ` [PATCH v3 01/12] mm/hmm: select mmu notifier when selecting HMM v2 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 03/12] mm/hmm: do not erase snapshot when a range is invalidated jglisse
` (9 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, John Hubbard, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
Every time i read the code to check that the HMM structure does not
vanish before it should thanks to the many lock protecting its removal
i get a headache. Switch to reference counting instead it is much
easier to follow and harder to break. This also remove some code that
is no longer needed with refcounting.
Changes since v2:
- Renamed hmm_register() to hmm_get_or_create() updated comments
accordingly
Changes since v1:
- removed bunch of useless check (if API is use with bogus argument
better to fail loudly so user fix their code)
- s/hmm_get/mm_get_hmm/
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
---
include/linux/hmm.h | 2 +
mm/hmm.c | 190 ++++++++++++++++++++++++++++----------------
2 files changed, 124 insertions(+), 68 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index ad50b7b4f141..716fc61fa6d4 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -131,6 +131,7 @@ enum hmm_pfn_value_e {
/*
* struct hmm_range - track invalidation lock on virtual address range
*
+ * @hmm: the core HMM structure this range is active against
* @vma: the vm area struct for the range
* @list: all range lock are on a list
* @start: range virtual start address (inclusive)
@@ -142,6 +143,7 @@ enum hmm_pfn_value_e {
* @valid: pfns array did not change since it has been fill by an HMM function
*/
struct hmm_range {
+ struct hmm *hmm;
struct vm_area_struct *vma;
struct list_head list;
unsigned long start;
diff --git a/mm/hmm.c b/mm/hmm.c
index fe1cd87e49ac..919d78fd21c5 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -50,6 +50,7 @@ static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
*/
struct hmm {
struct mm_struct *mm;
+ struct kref kref;
spinlock_t lock;
struct list_head ranges;
struct list_head mirrors;
@@ -57,24 +58,33 @@ struct hmm {
struct rw_semaphore mirrors_sem;
};
-/*
- * hmm_register - register HMM against an mm (HMM internal)
+static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
+{
+ struct hmm *hmm = READ_ONCE(mm->hmm);
+
+ if (hmm && kref_get_unless_zero(&hmm->kref))
+ return hmm;
+
+ return NULL;
+}
+
+/**
+ * hmm_get_or_create - register HMM against an mm (HMM internal)
*
* @mm: mm struct to attach to
+ * Returns: returns an HMM object, either by referencing the existing
+ * (per-process) object, or by creating a new one.
*
- * This is not intended to be used directly by device drivers. It allocates an
- * HMM struct if mm does not have one, and initializes it.
+ * 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_register(struct mm_struct *mm)
+static struct hmm *hmm_get_or_create(struct mm_struct *mm)
{
- struct hmm *hmm = READ_ONCE(mm->hmm);
+ struct hmm *hmm = mm_get_hmm(mm);
bool cleanup = false;
- /*
- * 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;
@@ -86,6 +96,7 @@ static struct hmm *hmm_register(struct mm_struct *mm)
hmm->mmu_notifier.ops = NULL;
INIT_LIST_HEAD(&hmm->ranges);
spin_lock_init(&hmm->lock);
+ kref_init(&hmm->kref);
hmm->mm = mm;
spin_lock(&mm->page_table_lock);
@@ -106,7 +117,7 @@ static struct hmm *hmm_register(struct mm_struct *mm)
if (__mmu_notifier_register(&hmm->mmu_notifier, mm))
goto error_mm;
- return mm->hmm;
+ return hmm;
error_mm:
spin_lock(&mm->page_table_lock);
@@ -118,9 +129,41 @@ static struct hmm *hmm_register(struct mm_struct *mm)
return NULL;
}
+static void hmm_free(struct kref *kref)
+{
+ struct hmm *hmm = container_of(kref, struct hmm, kref);
+ struct mm_struct *mm = hmm->mm;
+
+ mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
+
+ spin_lock(&mm->page_table_lock);
+ if (mm->hmm == hmm)
+ mm->hmm = NULL;
+ spin_unlock(&mm->page_table_lock);
+
+ kfree(hmm);
+}
+
+static inline void hmm_put(struct hmm *hmm)
+{
+ kref_put(&hmm->kref, hmm_free);
+}
+
void hmm_mm_destroy(struct mm_struct *mm)
{
- kfree(mm->hmm);
+ struct hmm *hmm;
+
+ spin_lock(&mm->page_table_lock);
+ hmm = mm_get_hmm(mm);
+ mm->hmm = NULL;
+ if (hmm) {
+ hmm->mm = NULL;
+ spin_unlock(&mm->page_table_lock);
+ hmm_put(hmm);
+ return;
+ }
+
+ spin_unlock(&mm->page_table_lock);
}
static int hmm_invalidate_range(struct hmm *hmm, bool device,
@@ -165,7 +208,7 @@ static int hmm_invalidate_range(struct hmm *hmm, bool device,
static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
struct hmm_mirror *mirror;
- struct hmm *hmm = mm->hmm;
+ struct hmm *hmm = mm_get_hmm(mm);
down_write(&hmm->mirrors_sem);
mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror,
@@ -186,13 +229,16 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
struct hmm_mirror, list);
}
up_write(&hmm->mirrors_sem);
+
+ hmm_put(hmm);
}
static int hmm_invalidate_range_start(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
+ struct hmm *hmm = mm_get_hmm(range->mm);
struct hmm_update update;
- struct hmm *hmm = range->mm->hmm;
+ int ret;
VM_BUG_ON(!hmm);
@@ -200,14 +246,16 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
update.end = range->end;
update.event = HMM_UPDATE_INVALIDATE;
update.blockable = range->blockable;
- return hmm_invalidate_range(hmm, true, &update);
+ ret = hmm_invalidate_range(hmm, true, &update);
+ hmm_put(hmm);
+ return ret;
}
static void hmm_invalidate_range_end(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
+ struct hmm *hmm = mm_get_hmm(range->mm);
struct hmm_update update;
- struct hmm *hmm = range->mm->hmm;
VM_BUG_ON(!hmm);
@@ -216,6 +264,7 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn,
update.event = HMM_UPDATE_INVALIDATE;
update.blockable = true;
hmm_invalidate_range(hmm, false, &update);
+ hmm_put(hmm);
}
static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
@@ -241,24 +290,13 @@ int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
if (!mm || !mirror || !mirror->ops)
return -EINVAL;
-again:
- mirror->hmm = hmm_register(mm);
+ mirror->hmm = hmm_get_or_create(mm);
if (!mirror->hmm)
return -ENOMEM;
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;
}
@@ -273,33 +311,18 @@ EXPORT_SYMBOL(hmm_mirror_register);
*/
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
- bool should_unregister = false;
- struct mm_struct *mm;
- struct hmm *hmm;
+ struct hmm *hmm = READ_ONCE(mirror->hmm);
- if (mirror->hmm == NULL)
+ if (hmm == NULL)
return;
- hmm = mirror->hmm;
down_write(&hmm->mirrors_sem);
list_del_init(&mirror->list);
- should_unregister = list_empty(&hmm->mirrors);
+ /* To protect us against double unregister ... */
mirror->hmm = NULL;
- mm = hmm->mm;
- hmm->mm = NULL;
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);
+ hmm_put(hmm);
}
EXPORT_SYMBOL(hmm_mirror_unregister);
@@ -708,23 +731,29 @@ int hmm_vma_get_pfns(struct hmm_range *range)
struct mm_walk mm_walk;
struct hmm *hmm;
+ range->hmm = NULL;
+
/* 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);
+ hmm = hmm_get_or_create(vma->vm_mm);
if (!hmm)
return -ENOMEM;
- /* Caller must have registered a mirror, via hmm_mirror_register() ! */
- if (!hmm->mmu_notifier.ops)
+
+ /* Check if hmm_mm_destroy() was call. */
+ if (hmm->mm == NULL) {
+ hmm_put(hmm);
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);
+ hmm_put(hmm);
return -EINVAL;
}
@@ -736,6 +765,7 @@ int hmm_vma_get_pfns(struct hmm_range *range)
* operations such has atomic access would not work.
*/
hmm_pfns_clear(range, range->pfns, range->start, range->end);
+ hmm_put(hmm);
return -EPERM;
}
@@ -758,6 +788,12 @@ int hmm_vma_get_pfns(struct hmm_range *range)
mm_walk.pte_hole = hmm_vma_walk_hole;
walk_page_range(range->start, range->end, &mm_walk);
+ /*
+ * Transfer hmm reference to the range struct it will be drop inside
+ * the hmm_vma_range_done() function (which _must_ be call if this
+ * function return 0).
+ */
+ range->hmm = hmm;
return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);
@@ -802,25 +838,27 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
*/
bool hmm_vma_range_done(struct hmm_range *range)
{
- unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
- struct hmm *hmm;
+ bool ret = false;
- if (range->end <= range->start) {
+ /* Sanity check this really should not happen. */
+ if (range->hmm == NULL || range->end <= range->start) {
BUG();
return false;
}
- hmm = hmm_register(range->vma->vm_mm);
- if (!hmm) {
- memset(range->pfns, 0, sizeof(*range->pfns) * npages);
- return false;
- }
-
- spin_lock(&hmm->lock);
+ spin_lock(&range->hmm->lock);
list_del_rcu(&range->list);
- spin_unlock(&hmm->lock);
+ ret = range->valid;
+ spin_unlock(&range->hmm->lock);
- return range->valid;
+ /* Is the mm still alive ? */
+ if (range->hmm->mm == NULL)
+ ret = false;
+
+ /* Drop reference taken by hmm_vma_fault() or hmm_vma_get_pfns() */
+ hmm_put(range->hmm);
+ range->hmm = NULL;
+ return ret;
}
EXPORT_SYMBOL(hmm_vma_range_done);
@@ -880,25 +918,31 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
struct hmm *hmm;
int ret;
+ range->hmm = NULL;
+
/* 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);
+ hmm = hmm_get_or_create(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)
+
+ /* Check if hmm_mm_destroy() was call. */
+ if (hmm->mm == NULL) {
+ hmm_put(hmm);
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);
+ hmm_put(hmm);
return -EINVAL;
}
@@ -910,6 +954,7 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
* operations such has atomic access would not work.
*/
hmm_pfns_clear(range, range->pfns, range->start, range->end);
+ hmm_put(hmm);
return -EPERM;
}
@@ -945,7 +990,16 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
hmm_pfns_clear(range, &range->pfns[i], hmm_vma_walk.last,
range->end);
hmm_vma_range_done(range);
+ hmm_put(hmm);
+ } else {
+ /*
+ * Transfer hmm reference to the range struct it will be drop
+ * inside the hmm_vma_range_done() function (which _must_ be
+ * call if this function return 0).
+ */
+ range->hmm = hmm;
}
+
return ret;
}
EXPORT_SYMBOL(hmm_vma_fault);
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 03/12] mm/hmm: do not erase snapshot when a range is invalidated
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
2019-04-03 19:33 ` [PATCH v3 01/12] mm/hmm: select mmu notifier when selecting HMM v2 jglisse
2019-04-03 19:33 ` [PATCH v3 02/12] mm/hmm: use reference counting for HMM struct v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 04/12] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() v2 jglisse
` (8 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
Users of HMM might be using the snapshot information to do
preparatory step like dma mapping pages to a device before
checking for invalidation through hmm_vma_range_done() so
do not erase that information and assume users will do the
right thing.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
---
mm/hmm.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/mm/hmm.c b/mm/hmm.c
index 919d78fd21c5..84e0577a912a 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -174,16 +174,10 @@ static int hmm_invalidate_range(struct hmm *hmm, bool device,
spin_lock(&hmm->lock);
list_for_each_entry(range, &hmm->ranges, list) {
- unsigned long addr, idx, npages;
-
if (update->end < range->start || update->start >= range->end)
continue;
range->valid = false;
- addr = max(update->start, range->start);
- idx = (addr - range->start) >> PAGE_SHIFT;
- npages = (min(range->end, update->end) - addr) >> PAGE_SHIFT;
- memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages);
}
spin_unlock(&hmm->lock);
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 04/12] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() v2
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (2 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 03/12] mm/hmm: do not erase snapshot when a range is invalidated jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 05/12] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() v3 jglisse
` (7 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
Rename for consistency between code, comments and documentation. Also
improves the comments on all the possible returns values. Improve the
function by returning the number of populated entries in pfns array.
Changes since v1:
- updated documentation
- reformated some comments
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
---
Documentation/vm/hmm.rst | 26 ++++++++++++++++++--------
include/linux/hmm.h | 4 ++--
mm/hmm.c | 31 +++++++++++++++++--------------
3 files changed, 37 insertions(+), 24 deletions(-)
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 44205f0b671f..d9b27bdadd1b 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -189,11 +189,7 @@ the driver callback returns.
When the device driver wants to populate a range of virtual addresses, it can
use either::
- int hmm_vma_get_pfns(struct vm_area_struct *vma,
- struct hmm_range *range,
- unsigned long start,
- unsigned long end,
- hmm_pfn_t *pfns);
+ long hmm_range_snapshot(struct hmm_range *range);
int hmm_vma_fault(struct vm_area_struct *vma,
struct hmm_range *range,
unsigned long start,
@@ -202,7 +198,7 @@ When the device driver wants to populate a range of virtual addresses, it can
bool write,
bool block);
-The first one (hmm_vma_get_pfns()) will only fetch present CPU page table
+The first one (hmm_range_snapshot()) will only fetch present CPU page table
entries and will not trigger a page fault on missing or non-present entries.
The second one does trigger a page fault on missing or read-only entry if the
write parameter is true. Page faults use the generic mm page fault code path
@@ -220,19 +216,33 @@ Locking with the update() callback is the most important aspect the driver must
{
struct hmm_range range;
...
+
+ range.start = ...;
+ range.end = ...;
+ range.pfns = ...;
+ range.flags = ...;
+ range.values = ...;
+ range.pfn_shift = ...;
+
again:
- ret = hmm_vma_get_pfns(vma, &range, start, end, pfns);
- if (ret)
+ down_read(&mm->mmap_sem);
+ range.vma = ...;
+ ret = hmm_range_snapshot(&range);
+ if (ret) {
+ up_read(&mm->mmap_sem);
return ret;
+ }
take_lock(driver->update);
if (!hmm_vma_range_done(vma, &range)) {
release_lock(driver->update);
+ up_read(&mm->mmap_sem);
goto again;
}
// Use pfns array content to update device page table
release_lock(driver->update);
+ up_read(&mm->mmap_sem);
return 0;
}
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 716fc61fa6d4..32206b0b1bfd 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -365,11 +365,11 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
* table invalidation serializes on it.
*
* YOU MUST CALL hmm_vma_range_done() ONCE AND ONLY ONCE EACH TIME YOU CALL
- * hmm_vma_get_pfns() WITHOUT ERROR !
+ * hmm_range_snapshot() WITHOUT ERROR !
*
* IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID !
*/
-int hmm_vma_get_pfns(struct hmm_range *range);
+long hmm_range_snapshot(struct hmm_range *range);
bool hmm_vma_range_done(struct hmm_range *range);
diff --git a/mm/hmm.c b/mm/hmm.c
index 84e0577a912a..bd957a9f10d1 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -702,23 +702,25 @@ static void hmm_pfns_special(struct hmm_range *range)
}
/*
- * 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_snapshot() - snapshot CPU page table for a range
+ * @range: range
+ * Returns: 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:
+ *
+ * -EINVAL invalid arguments or mm or virtual address are in an
+ * invalid vma (ie either hugetlbfs or device file vma).
+ * -EPERM For example, asking for write, when the range is
+ * read-only
+ * -EAGAIN Caller needs to retry
+ * -EFAULT Either no valid vma exists for this range, or it is
+ * illegal to access the range
*
* 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.
- *
- * 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 !
*/
-int hmm_vma_get_pfns(struct hmm_range *range)
+long hmm_range_snapshot(struct hmm_range *range)
{
struct vm_area_struct *vma = range->vma;
struct hmm_vma_walk hmm_vma_walk;
@@ -772,6 +774,7 @@ int hmm_vma_get_pfns(struct hmm_range *range)
hmm_vma_walk.fault = false;
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;
@@ -788,9 +791,9 @@ int hmm_vma_get_pfns(struct hmm_range *range)
* function return 0).
*/
range->hmm = hmm;
- return 0;
+ return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
-EXPORT_SYMBOL(hmm_vma_get_pfns);
+EXPORT_SYMBOL(hmm_range_snapshot);
/*
* hmm_vma_range_done() - stop tracking change to CPU page table over a range
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 05/12] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (3 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 04/12] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() v2 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 06/12] mm/hmm: improve driver API to work and wait over a range v3 jglisse
` (6 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, John Hubbard, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
Minor optimization around hmm_pte_need_fault(). Rename for
consistency between code, comments and documentation. Also
improves the comments on all the possible returns values.
Improve the function by returning the number of populated
entries in pfns array.
Changes since v2:
- updated commit message
Changes since v1:
- updated documentation
- reformated some comments
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
---
Documentation/vm/hmm.rst | 8 +---
include/linux/hmm.h | 13 +++++-
mm/hmm.c | 91 +++++++++++++++++-----------------------
3 files changed, 52 insertions(+), 60 deletions(-)
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index d9b27bdadd1b..61f073215a8d 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -190,13 +190,7 @@ When the device driver wants to populate a range of virtual addresses, it can
use either::
long hmm_range_snapshot(struct hmm_range *range);
- int hmm_vma_fault(struct vm_area_struct *vma,
- struct hmm_range *range,
- unsigned long start,
- unsigned long end,
- hmm_pfn_t *pfns,
- bool write,
- bool block);
+ long hmm_range_fault(struct hmm_range *range, bool block);
The first one (hmm_range_snapshot()) will only fetch present CPU page table
entries and will not trigger a page fault on missing or non-present entries.
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 32206b0b1bfd..e9afd23c2eac 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -391,7 +391,18 @@ bool hmm_vma_range_done(struct hmm_range *range);
*
* See the function description in mm/hmm.c for further documentation.
*/
-int hmm_vma_fault(struct hmm_range *range, bool block);
+long hmm_range_fault(struct hmm_range *range, bool block);
+
+/* This is a temporary helper to avoid merge conflict between trees. */
+static inline int hmm_vma_fault(struct hmm_range *range, bool block)
+{
+ long ret = hmm_range_fault(range, block);
+ if (ret == -EBUSY)
+ ret = -EAGAIN;
+ else if (ret == -EAGAIN)
+ ret = -EBUSY;
+ return ret < 0 ? ret : 0;
+}
/* Below are for HMM internal use only! Not to be used by device driver! */
void hmm_mm_destroy(struct mm_struct *mm);
diff --git a/mm/hmm.c b/mm/hmm.c
index bd957a9f10d1..b7e4034d96e1 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -340,13 +340,13 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
flags |= write_fault ? FAULT_FLAG_WRITE : 0;
ret = handle_mm_fault(vma, addr, flags);
if (ret & VM_FAULT_RETRY)
- return -EBUSY;
+ return -EAGAIN;
if (ret & VM_FAULT_ERROR) {
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
}
- return -EAGAIN;
+ return -EBUSY;
}
static int hmm_pfns_bad(unsigned long addr,
@@ -372,7 +372,7 @@ static int hmm_pfns_bad(unsigned long addr,
* @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
+ * Returns: 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.
@@ -395,12 +395,12 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
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,
@@ -531,11 +531,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
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;
@@ -574,7 +574,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
hmm_vma_walk->last = addr;
migration_entry_wait(vma->vm_mm,
pmdp, addr);
- return -EAGAIN;
+ return -EBUSY;
}
return 0;
}
@@ -582,6 +582,10 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
/* 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)
@@ -632,7 +636,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
if (fault || write_fault) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(vma->vm_mm, pmdp);
- return -EAGAIN;
+ return -EBUSY;
}
return 0;
} else if (!pmd_present(pmd))
@@ -860,53 +864,34 @@ bool hmm_vma_range_done(struct hmm_range *range)
EXPORT_SYMBOL(hmm_vma_range_done);
/*
- * hmm_vma_fault() - try to fault some address in a virtual address range
+ * 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)
- * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
+ * Returns: 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:
+ *
+ * -EINVAL invalid arguments or mm or virtual address are in an
+ * invalid vma (ie either hugetlbfs or 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).
*
* 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, bool block)
{
struct vm_area_struct *vma = range->vma;
unsigned long start = range->start;
@@ -978,7 +963,8 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
do {
ret = walk_page_range(start, range->end, &mm_walk);
start = hmm_vma_walk.last;
- } while (ret == -EAGAIN);
+ /* Keep trying while the range is valid. */
+ } while (ret == -EBUSY && range->valid);
if (ret) {
unsigned long i;
@@ -988,6 +974,7 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
range->end);
hmm_vma_range_done(range);
hmm_put(hmm);
+ return ret;
} else {
/*
* Transfer hmm reference to the range struct it will be drop
@@ -997,9 +984,9 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
range->hmm = hmm;
}
- return ret;
+ return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
-EXPORT_SYMBOL(hmm_vma_fault);
+EXPORT_SYMBOL(hmm_range_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 06/12] mm/hmm: improve driver API to work and wait over a range v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (4 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 05/12] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 07/12] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays v2 jglisse
` (5 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, John Hubbard,
Dan Williams, Dan Carpenter, Matthew Wilcox
From: Jérôme Glisse <jglisse@redhat.com>
A common use case for HMM mirror is user trying to mirror a range
and before they could program the hardware it get invalidated by
some core mm event. Instead of having user re-try right away to
mirror the range provide a completion mechanism for them to wait
for any active invalidation affecting the range.
This also changes how hmm_range_snapshot() and hmm_range_fault()
works by not relying on vma so that we can drop the mmap_sem
when waiting and lookup the vma again on retry.
Changes since v2:
- Updated documentation to match new API.
- Added more comments in old API temporary wrapper.
- Consolidated documentation in hmm.rst to avoid out of sync.
Changes since v1:
- squashed: Dan Carpenter: potential deadlock in nonblocking code
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
---
Documentation/vm/hmm.rst | 25 +-
include/linux/hmm.h | 145 ++++++++---
mm/hmm.c | 531 +++++++++++++++++++--------------------
3 files changed, 387 insertions(+), 314 deletions(-)
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 61f073215a8d..945d5fb6d14a 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -217,17 +217,33 @@ Locking with the update() callback is the most important aspect the driver must
range.flags = ...;
range.values = ...;
range.pfn_shift = ...;
+ hmm_range_register(&range);
+
+ /*
+ * Just wait for range to be valid, safe to ignore return value as we
+ * will use the return value of hmm_range_snapshot() below under the
+ * mmap_sem to ascertain the validity of the range.
+ */
+ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
again:
down_read(&mm->mmap_sem);
- range.vma = ...;
ret = hmm_range_snapshot(&range);
if (ret) {
up_read(&mm->mmap_sem);
+ if (ret == -EAGAIN) {
+ /*
+ * No need to check hmm_range_wait_until_valid() return value
+ * on retry we will get proper error with hmm_range_snapshot()
+ */
+ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
+ goto again;
+ }
+ hmm_mirror_unregister(&range);
return ret;
}
take_lock(driver->update);
- if (!hmm_vma_range_done(vma, &range)) {
+ if (!range.valid) {
release_lock(driver->update);
up_read(&mm->mmap_sem);
goto again;
@@ -235,14 +251,15 @@ Locking with the update() callback is the most important aspect the driver must
// Use pfns array content to update device page table
+ hmm_mirror_unregister(&range);
release_lock(driver->update);
up_read(&mm->mmap_sem);
return 0;
}
The driver->update lock is the same lock that the driver takes inside its
-update() callback. That lock must be held before hmm_vma_range_done() to avoid
-any race with a concurrent CPU page table update.
+update() callback. That lock must be held before checking the range.valid
+field to avoid any race with a concurrent CPU page table update.
HMM implements all this on top of the mmu_notifier API because we wanted a
simpler API and also to be able to perform optimizations latter on like doing
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index e9afd23c2eac..ec4bfa91648f 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -77,8 +77,34 @@
#include <linux/migrate.h>
#include <linux/memremap.h>
#include <linux/completion.h>
+#include <linux/mmu_notifier.h>
-struct hmm;
+
+/*
+ * struct hmm - HMM per mm struct
+ *
+ * @mm: mm struct this HMM struct is bound to
+ * @lock: lock protecting ranges list
+ * @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
+ * @wq: wait queue for user waiting on a range invalidation
+ * @notifiers: count of active mmu notifiers
+ * @dead: is the mm dead ?
+ */
+struct hmm {
+ struct mm_struct *mm;
+ struct kref kref;
+ struct mutex lock;
+ struct list_head ranges;
+ struct list_head mirrors;
+ struct mmu_notifier mmu_notifier;
+ struct rw_semaphore mirrors_sem;
+ wait_queue_head_t wq;
+ long notifiers;
+ bool dead;
+};
/*
* hmm_pfn_flag_e - HMM flag enums
@@ -155,6 +181,38 @@ struct hmm_range {
bool valid;
};
+/*
+ * hmm_range_wait_until_valid() - wait for range to be valid
+ * @range: range affected by invalidation to wait on
+ * @timeout: time out for wait in ms (ie abort wait after that period of time)
+ * Returns: true if the range is valid, false otherwise.
+ */
+static inline bool hmm_range_wait_until_valid(struct hmm_range *range,
+ unsigned long timeout)
+{
+ /* Check if mm is dead ? */
+ if (range->hmm == NULL || range->hmm->dead || range->hmm->mm == NULL) {
+ range->valid = false;
+ return false;
+ }
+ if (range->valid)
+ return true;
+ wait_event_timeout(range->hmm->wq, range->valid || range->hmm->dead,
+ msecs_to_jiffies(timeout));
+ /* Return current valid status just in case we get lucky */
+ return range->valid;
+}
+
+/*
+ * hmm_range_valid() - test if a range is valid or not
+ * @range: range
+ * Returns: true if the range is valid, false otherwise.
+ */
+static inline bool hmm_range_valid(struct hmm_range *range)
+{
+ return range->valid;
+}
+
/*
* hmm_pfn_to_page() - return struct page pointed to by a valid HMM pfn
* @range: range use to decode HMM pfn value
@@ -357,51 +415,66 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
/*
- * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device
- * driver lock that serializes device page table updates, then call
- * hmm_vma_range_done(), to check if the snapshot is still valid. The same
- * device driver page table update lock must also be used in the
- * hmm_mirror_ops.sync_cpu_device_pagetables() callback, so that CPU page
- * table invalidation serializes on it.
- *
- * YOU MUST CALL hmm_vma_range_done() ONCE AND ONLY ONCE EACH TIME YOU CALL
- * hmm_range_snapshot() WITHOUT ERROR !
- *
- * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID !
+ * Please see Documentation/vm/hmm.rst for how to use the range API.
*/
+int hmm_range_register(struct hmm_range *range,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end);
+void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
-bool hmm_vma_range_done(struct hmm_range *range);
-
+long hmm_range_fault(struct hmm_range *range, bool block);
/*
- * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will
- * not migrate any device memory back to system memory. The HMM pfn array will
- * be updated with the fault result and current snapshot of the CPU page table
- * for the range.
- *
- * The mmap_sem must be taken in read mode before entering and it might be
- * dropped by the function if the block argument is false. In that case, the
- * function returns -EAGAIN.
- *
- * Return value does not reflect if the fault was successful for every single
- * address or not. Therefore, the caller must to inspect the HMM pfn array to
- * determine fault status for each address.
- *
- * Trying to fault inside an invalid vma will result in -EINVAL.
+ * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
*
- * See the function description in mm/hmm.c for further documentation.
+ * When waiting for mmu notifiers we need some kind of time out otherwise we
+ * could potentialy wait for ever, 1000ms ie 1s sounds like a long time to
+ * wait already.
*/
-long hmm_range_fault(struct hmm_range *range, bool block);
+#define HMM_RANGE_DEFAULT_TIMEOUT 1000
+
+/* This is a temporary helper to avoid merge conflict between trees. */
+static inline bool hmm_vma_range_done(struct hmm_range *range)
+{
+ bool ret = hmm_range_valid(range);
+
+ hmm_range_unregister(range);
+ return ret;
+}
/* This is a temporary helper to avoid merge conflict between trees. */
static inline int hmm_vma_fault(struct hmm_range *range, bool block)
{
- long ret = hmm_range_fault(range, block);
- if (ret == -EBUSY)
- ret = -EAGAIN;
- else if (ret == -EAGAIN)
- ret = -EBUSY;
- return ret < 0 ? ret : 0;
+ long ret;
+
+ ret = hmm_range_register(range, range->vma->vm_mm,
+ range->start, range->end);
+ if (ret)
+ return (int)ret;
+
+ if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
+ /*
+ * The mmap_sem was taken by driver we release it here and
+ * returns -EAGAIN which correspond to mmap_sem have been
+ * drop in the old API.
+ */
+ up_read(&range->vma->vm_mm->mmap_sem);
+ return -EAGAIN;
+ }
+
+ ret = hmm_range_fault(range, block);
+ if (ret <= 0) {
+ if (ret == -EBUSY || !ret) {
+ /* Same as above drop mmap_sem to match old API. */
+ up_read(&range->vma->vm_mm->mmap_sem);
+ ret = -EBUSY;
+ } else if (ret == -EAGAIN)
+ ret = -EBUSY;
+ hmm_range_unregister(range);
+ return ret;
+ }
+ return 0;
}
/* Below are for HMM internal use only! Not to be used by device driver! */
diff --git a/mm/hmm.c b/mm/hmm.c
index b7e4034d96e1..3e07f32b94f8 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -38,26 +38,6 @@
#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
- * @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;
- struct kref kref;
- spinlock_t lock;
- struct list_head ranges;
- struct list_head mirrors;
- struct mmu_notifier mmu_notifier;
- struct rw_semaphore mirrors_sem;
-};
-
static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
{
struct hmm *hmm = READ_ONCE(mm->hmm);
@@ -91,12 +71,15 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
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->lock);
+ mutex_init(&hmm->lock);
kref_init(&hmm->kref);
+ hmm->notifiers = 0;
+ hmm->dead = false;
hmm->mm = mm;
spin_lock(&mm->page_table_lock);
@@ -158,6 +141,7 @@ void hmm_mm_destroy(struct mm_struct *mm)
mm->hmm = NULL;
if (hmm) {
hmm->mm = NULL;
+ hmm->dead = true;
spin_unlock(&mm->page_table_lock);
hmm_put(hmm);
return;
@@ -166,43 +150,22 @@ void hmm_mm_destroy(struct mm_struct *mm)
spin_unlock(&mm->page_table_lock);
}
-static int hmm_invalidate_range(struct hmm *hmm, bool device,
- const struct hmm_update *update)
+static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
+ struct hmm *hmm = mm_get_hmm(mm);
struct hmm_mirror *mirror;
struct hmm_range *range;
- spin_lock(&hmm->lock);
- list_for_each_entry(range, &hmm->ranges, list) {
- if (update->end < range->start || update->start >= range->end)
- continue;
+ /* Report this HMM as dying. */
+ hmm->dead = true;
+ /* Wake-up everyone waiting on any range. */
+ mutex_lock(&hmm->lock);
+ list_for_each_entry(range, &hmm->ranges, list) {
range->valid = false;
}
- spin_unlock(&hmm->lock);
-
- if (!device)
- return 0;
-
- down_read(&hmm->mirrors_sem);
- list_for_each_entry(mirror, &hmm->mirrors, list) {
- int ret;
-
- ret = mirror->ops->sync_cpu_device_pagetables(mirror, update);
- if (!update->blockable && ret == -EAGAIN) {
- up_read(&hmm->mirrors_sem);
- return -EAGAIN;
- }
- }
- up_read(&hmm->mirrors_sem);
-
- return 0;
-}
-
-static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
-{
- struct hmm_mirror *mirror;
- struct hmm *hmm = mm_get_hmm(mm);
+ wake_up_all(&hmm->wq);
+ mutex_unlock(&hmm->lock);
down_write(&hmm->mirrors_sem);
mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror,
@@ -228,36 +191,80 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
}
static int hmm_invalidate_range_start(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
+ const struct mmu_notifier_range *nrange)
{
- struct hmm *hmm = mm_get_hmm(range->mm);
+ struct hmm *hmm = mm_get_hmm(nrange->mm);
+ struct hmm_mirror *mirror;
struct hmm_update update;
- int ret;
+ struct hmm_range *range;
+ int ret = 0;
VM_BUG_ON(!hmm);
- update.start = range->start;
- update.end = range->end;
+ update.start = nrange->start;
+ update.end = nrange->end;
update.event = HMM_UPDATE_INVALIDATE;
- update.blockable = range->blockable;
- ret = hmm_invalidate_range(hmm, true, &update);
+ update.blockable = nrange->blockable;
+
+ if (nrange->blockable)
+ mutex_lock(&hmm->lock);
+ else if (!mutex_trylock(&hmm->lock)) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ hmm->notifiers++;
+ list_for_each_entry(range, &hmm->ranges, list) {
+ if (update.end < range->start || update.start >= range->end)
+ continue;
+
+ range->valid = false;
+ }
+ mutex_unlock(&hmm->lock);
+
+ if (nrange->blockable)
+ 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 ret;
+
+ ret = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
+ if (!update.blockable && ret == -EAGAIN) {
+ up_read(&hmm->mirrors_sem);
+ ret = -EAGAIN;
+ goto out;
+ }
+ }
+ up_read(&hmm->mirrors_sem);
+
+out:
hmm_put(hmm);
return ret;
}
static void hmm_invalidate_range_end(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
+ const struct mmu_notifier_range *nrange)
{
- struct hmm *hmm = mm_get_hmm(range->mm);
- struct hmm_update update;
+ struct hmm *hmm = mm_get_hmm(nrange->mm);
VM_BUG_ON(!hmm);
- update.start = range->start;
- update.end = range->end;
- update.event = HMM_UPDATE_INVALIDATE;
- update.blockable = true;
- hmm_invalidate_range(hmm, false, &update);
+ mutex_lock(&hmm->lock);
+ 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);
+ }
+ mutex_unlock(&hmm->lock);
+
hmm_put(hmm);
}
@@ -409,7 +416,6 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
{
struct hmm_range *range = hmm_vma_walk->range;
- *fault = *write_fault = false;
if (!hmm_vma_walk->fault)
return;
@@ -448,10 +454,11 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
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;
}
}
@@ -706,162 +713,155 @@ static void hmm_pfns_special(struct hmm_range *range)
}
/*
- * hmm_range_snapshot() - snapshot CPU page table for a range
+ * hmm_range_register() - start tracking change to CPU page table over a range
* @range: range
- * Returns: 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:
+ * @mm: the mm struct for the range of virtual address
+ * @start: start virtual address (inclusive)
+ * @end: end virtual address (exclusive)
+ * Returns 0 on success, -EFAULT if the address space is no longer valid
*
- * -EINVAL invalid arguments or mm or virtual address are in an
- * invalid vma (ie either hugetlbfs or device file vma).
- * -EPERM For example, asking for write, when the range is
- * read-only
- * -EAGAIN Caller needs to retry
- * -EFAULT Either no valid vma exists for this range, or it is
- * illegal to access the range
- *
- * 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.
+ * Track updates to the CPU page table see include/linux/hmm.h
*/
-long hmm_range_snapshot(struct hmm_range *range)
+int hmm_range_register(struct hmm_range *range,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
{
- struct vm_area_struct *vma = range->vma;
- struct hmm_vma_walk hmm_vma_walk;
- struct mm_walk mm_walk;
- struct hmm *hmm;
-
+ range->start = start & PAGE_MASK;
+ range->end = end & PAGE_MASK;
+ range->valid = false;
range->hmm = NULL;
- /* 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)
+ if (range->start >= range->end)
return -EINVAL;
- hmm = hmm_get_or_create(vma->vm_mm);
- if (!hmm)
- return -ENOMEM;
+ range->start = start;
+ range->end = end;
+
+ range->hmm = hmm_get_or_create(mm);
+ if (!range->hmm)
+ return -EFAULT;
/* Check if hmm_mm_destroy() was call. */
- if (hmm->mm == NULL) {
- hmm_put(hmm);
- return -EINVAL;
+ if (range->hmm->mm == NULL || range->hmm->dead) {
+ hmm_put(range->hmm);
+ 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);
- hmm_put(hmm);
- return -EINVAL;
- }
+ /* Initialize range to track CPU page table update */
+ mutex_lock(&range->hmm->lock);
- 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);
- hmm_put(hmm);
- return -EPERM;
- }
+ list_add_rcu(&range->list, &range->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);
-
- hmm_vma_walk.fault = false;
- 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;
-
- walk_page_range(range->start, range->end, &mm_walk);
/*
- * Transfer hmm reference to the range struct it will be drop inside
- * the hmm_vma_range_done() function (which _must_ be call if this
- * function return 0).
+ * If there are any concurrent notifiers we have to wait for them for
+ * the range to be valid (see hmm_range_wait_until_valid()).
*/
- range->hmm = hmm;
- return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+ if (!range->hmm->notifiers)
+ range->valid = true;
+ mutex_unlock(&range->hmm->lock);
+
+ return 0;
}
-EXPORT_SYMBOL(hmm_range_snapshot);
+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)
{
- bool ret = false;
-
/* Sanity check this really should not happen. */
- if (range->hmm == NULL || range->end <= range->start) {
- BUG();
- return false;
- }
+ if (range->hmm == NULL || range->end <= range->start)
+ return;
- spin_lock(&range->hmm->lock);
+ mutex_lock(&range->hmm->lock);
list_del_rcu(&range->list);
- ret = range->valid;
- spin_unlock(&range->hmm->lock);
+ mutex_unlock(&range->hmm->lock);
- /* Is the mm still alive ? */
- if (range->hmm->mm == NULL)
- ret = false;
-
- /* Drop reference taken by hmm_vma_fault() or hmm_vma_get_pfns() */
+ /* Drop reference taken by hmm_range_register() */
+ range->valid = false;
hmm_put(range->hmm);
range->hmm = NULL;
- return ret;
}
-EXPORT_SYMBOL(hmm_vma_range_done);
+EXPORT_SYMBOL(hmm_range_unregister);
+
+/*
+ * hmm_range_snapshot() - snapshot CPU page table for a range
+ * @range: range
+ * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
+ * permission (for instance asking for write and range is read only),
+ * -EAGAIN 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)
+{
+ 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;
+
+ /* Check if hmm_mm_destroy() was call. */
+ if (hmm->mm == NULL || hmm->dead)
+ return -EFAULT;
+
+ do {
+ /* If range is no longer valid force retry. */
+ if (!range->valid)
+ return -EAGAIN;
+
+ vma = find_vma(hmm->mm, start);
+ if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ return -EFAULT;
+
+ /* FIXME support hugetlb fs/dax */
+ if (is_vm_hugetlb_page(vma) || 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. 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.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.pmd_entry = hmm_vma_walk_pmd;
+ mm_walk.pte_hole = hmm_vma_walk_hole;
+
+ walk_page_range(start, end, &mm_walk);
+ start = end;
+ } while (start < range->end);
+
+ return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+}
+EXPORT_SYMBOL(hmm_range_snapshot);
/*
* hmm_range_fault() - try to fault some address in a virtual address range
@@ -893,96 +893,79 @@ EXPORT_SYMBOL(hmm_vma_range_done);
*/
long hmm_range_fault(struct hmm_range *range, bool block)
{
- struct vm_area_struct *vma = range->vma;
- unsigned long start = range->start;
+ 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 *hmm;
int ret;
- range->hmm = NULL;
-
- /* 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;
+ /* Check if hmm_mm_destroy() was call. */
+ if (hmm->mm == NULL || hmm->dead)
+ return -EFAULT;
- hmm = hmm_get_or_create(vma->vm_mm);
- if (!hmm) {
- hmm_pfns_clear(range, range->pfns, range->start, range->end);
- return -ENOMEM;
- }
+ do {
+ /* If range is no longer valid force retry. */
+ if (!range->valid) {
+ up_read(&hmm->mm->mmap_sem);
+ return -EAGAIN;
+ }
- /* Check if hmm_mm_destroy() was call. */
- if (hmm->mm == NULL) {
- hmm_put(hmm);
- return -EINVAL;
- }
+ vma = find_vma(hmm->mm, start);
+ if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ 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);
- hmm_put(hmm);
- return -EINVAL;
- }
+ /* FIXME support hugetlb fs/dax */
+ if (is_vm_hugetlb_page(vma) || 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);
- hmm_put(hmm);
- return -EPERM;
- }
+ 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;
+ }
- /* 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;
+ range->vma = vma;
+ 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.pmd_entry = hmm_vma_walk_pmd;
+ mm_walk.pte_hole = hmm_vma_walk_hole;
+
+ 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;
- do {
- ret = walk_page_range(start, range->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);
- hmm_vma_range_done(range);
- hmm_put(hmm);
- return ret;
- } else {
- /*
- * Transfer hmm reference to the range struct it will be drop
- * inside the hmm_vma_range_done() function (which _must_ be
- * call if this function return 0).
- */
- range->hmm = hmm;
- }
+ } while (start < range->end);
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 07/12] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays v2
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (5 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 06/12] mm/hmm: improve driver API to work and wait over a range v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 08/12] mm/hmm: mirror hugetlbfs (snapshoting, faulting and DMA mapping) v3 jglisse
` (4 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, John Hubbard, Dan Williams
From: Jérôme Glisse <jglisse@redhat.com>
The HMM mirror API can be use in two fashions. The first one where the HMM
user coalesce multiple page faults into one request and set flags per pfns
for of those faults. The second one where the HMM user want 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.
This patch adds a default flags value allowing user to set them for a range
without having to pre-fill the pfn array.
Changes since v1:
- Added documentation.
- Added comments in the old API wrapper to explain what is going on.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
---
Documentation/vm/hmm.rst | 35 +++++++++++++++++++++++++++++++++++
include/linux/hmm.h | 13 +++++++++++++
mm/hmm.c | 12 ++++++++++++
3 files changed, 60 insertions(+)
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 945d5fb6d14a..ec1efa32af3c 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -276,6 +276,41 @@ report commands as executed is serialized (there is no point in doing this
concurrently).
+Leverage default_flags and pfn_flags_mask
+=========================================
+
+The hmm_range struct has 2 fields default_flags and pfn_flags_mask that allows
+to set fault or snapshot policy for a whole range instead of having to set them
+for each entries in the range.
+
+For instance if the device flags for device entries are:
+ VALID (1 << 63)
+ WRITE (1 << 62)
+
+Now let say that device driver wants to fault with at least read a range then
+it does set:
+ range->default_flags = (1 << 63)
+ range->pfn_flags_mask = 0;
+
+and calls hmm_range_fault() as described above. This will fill fault all page
+in the range with at least read permission.
+
+Now let say driver wants to do the same except for one page in the range for
+which its want to have write. Now driver set:
+ range->default_flags = (1 << 63);
+ range->pfn_flags_mask = (1 << 62);
+ range->pfns[index_of_write] = (1 << 62);
+
+With this HMM will fault in all page with at least read (ie valid) and for the
+address == range->start + (index_of_write << PAGE_SHIFT) it will fault with
+write permission ie if the CPU pte does not have write permission set then HMM
+will call handle_mm_fault().
+
+Note that HMM will populate the pfns array with write permission for any entry
+that have write permission within the CPU pte no matter what are the values set
+in default_flags or pfn_flags_mask.
+
+
Represent and manage device memory from core kernel point of view
=================================================================
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index ec4bfa91648f..dee2f8953b2e 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -165,6 +165,8 @@ enum hmm_pfn_value_e {
* @pfns: array of pfns (big enough for the range)
* @flags: pfn flags to match device driver page table
* @values: pfn value for some special case (none, special, error, ...)
+ * @default_flags: default flags for the range (write, read, ... see hmm doc)
+ * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
* @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
* @valid: pfns array did not change since it has been fill by an HMM function
*/
@@ -177,6 +179,8 @@ struct hmm_range {
uint64_t *pfns;
const uint64_t *flags;
const uint64_t *values;
+ uint64_t default_flags;
+ uint64_t pfn_flags_mask;
uint8_t pfn_shift;
bool valid;
};
@@ -448,6 +452,15 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block)
{
long ret;
+ /*
+ * With the old API the driver must set each individual entries with
+ * the requested flags (valid, write, ...). So here we set the mask to
+ * keep intact the entries provided by the driver and zero out the
+ * default_flags.
+ */
+ range->default_flags = 0;
+ range->pfn_flags_mask = -1UL;
+
ret = hmm_range_register(range, range->vma->vm_mm,
range->start, range->end);
if (ret)
diff --git a/mm/hmm.c b/mm/hmm.c
index 3e07f32b94f8..0e21d3594ab6 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -419,6 +419,18 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
if (!hmm_vma_walk->fault)
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-
+ * 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;
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 08/12] mm/hmm: mirror hugetlbfs (snapshoting, faulting and DMA mapping) v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (6 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 07/12] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays v2 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 09/12] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem v3 jglisse
` (3 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, John Hubbard,
Dan Williams, Arnd Bergmann
From: Jérôme Glisse <jglisse@redhat.com>
HMM mirror is a device driver helpers to mirror range of virtual address.
It means that the process jobs running on the device can access the same
virtual address as the CPU threads of that process. This patch adds support
for hugetlbfs mapping (ie range of virtual address that are mmap of a
hugetlbfs).
Changes since v2:
- Use hmm_range_page_size() where we can.
Changes since v1:
- improved commit message
- squashed: Arnd Bergmann: fix unused variable warnings
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
---
include/linux/hmm.h | 27 +++++++++-
mm/hmm.c | 123 +++++++++++++++++++++++++++++++++++++++-----
2 files changed, 134 insertions(+), 16 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index dee2f8953b2e..e5834082de60 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -181,10 +181,31 @@ struct hmm_range {
const uint64_t *values;
uint64_t default_flags;
uint64_t pfn_flags_mask;
+ uint8_t page_shift;
uint8_t pfn_shift;
bool valid;
};
+/*
+ * hmm_range_page_shift() - return the page shift for the range
+ * @range: range being queried
+ * Returns: page shift (page size = 1 << page shift) for the range
+ */
+static inline unsigned hmm_range_page_shift(const struct hmm_range *range)
+{
+ return range->page_shift;
+}
+
+/*
+ * hmm_range_page_size() - return the page size for the range
+ * @range: range being queried
+ * Returns: page size for the range in bytes
+ */
+static inline unsigned long hmm_range_page_size(const struct hmm_range *range)
+{
+ return 1UL << hmm_range_page_shift(range);
+}
+
/*
* hmm_range_wait_until_valid() - wait for range to be valid
* @range: range affected by invalidation to wait on
@@ -424,7 +445,8 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
int hmm_range_register(struct hmm_range *range,
struct mm_struct *mm,
unsigned long start,
- unsigned long end);
+ unsigned long end,
+ unsigned page_shift);
void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
long hmm_range_fault(struct hmm_range *range, bool block);
@@ -462,7 +484,8 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block)
range->pfn_flags_mask = -1UL;
ret = hmm_range_register(range, range->vma->vm_mm,
- range->start, range->end);
+ range->start, range->end,
+ PAGE_SHIFT);
if (ret)
return (int)ret;
diff --git a/mm/hmm.c b/mm/hmm.c
index 0e21d3594ab6..9140cee24d36 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -391,11 +391,13 @@ 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;
+ unsigned long i, page_size;
hmm_vma_walk->last = addr;
- i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += PAGE_SIZE, i++) {
+ page_size = hmm_range_page_size(range);
+ i = (addr - range->start) >> range->page_shift;
+
+ for (; addr < end; addr += page_size, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
@@ -707,6 +709,69 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
return 0;
}
+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;
+ 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);
+ entry = huge_ptep_get(pte);
+
+ i = (start - range->start) >> range->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 & mask);
+ for (; addr < end; addr += size, i++, pfn += pfn_inc)
+ range->pfns[i] = hmm_pfn_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 /* CONFIG_HUGETLB_PAGE */
+ return -EINVAL;
+#endif
+}
+
static void hmm_pfns_clear(struct hmm_range *range,
uint64_t *pfns,
unsigned long addr,
@@ -730,6 +795,7 @@ static void hmm_pfns_special(struct hmm_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
@@ -737,16 +803,20 @@ static void hmm_pfns_special(struct hmm_range *range)
int hmm_range_register(struct hmm_range *range,
struct mm_struct *mm,
unsigned long start,
- unsigned long end)
+ unsigned long end,
+ unsigned page_shift)
{
- range->start = start & PAGE_MASK;
- range->end = end & PAGE_MASK;
+ unsigned long mask = ((1UL << page_shift) - 1UL);
+
range->valid = false;
range->hmm = NULL;
- if (range->start >= range->end)
+ if ((start & mask) || (end & mask))
+ return -EINVAL;
+ if (start >= end)
return -EINVAL;
+ range->page_shift = page_shift;
range->start = start;
range->end = end;
@@ -816,6 +886,7 @@ EXPORT_SYMBOL(hmm_range_unregister);
*/
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;
@@ -832,15 +903,26 @@ long hmm_range_snapshot(struct hmm_range *range)
return -EAGAIN;
vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support hugetlb fs/dax */
- if (is_vm_hugetlb_page(vma) || vma_is_dax(vma)) {
+ /* FIXME support dax */
+ if (vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
+ if (is_vm_hugetlb_page(vma)) {
+ struct hstate *h = hstate_vma(vma);
+
+ if (huge_page_shift(h) != 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
@@ -866,6 +948,7 @@ long hmm_range_snapshot(struct hmm_range *range)
mm_walk.hugetlb_entry = NULL;
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;
@@ -884,7 +967,7 @@ EXPORT_SYMBOL(hmm_range_snapshot);
* then one of the following values may be returned:
*
* -EINVAL invalid arguments or mm or virtual address are in an
- * invalid vma (ie either hugetlbfs or device file vma).
+ * invalid vma (for instance device file vma).
* -ENOMEM: Out of memory.
* -EPERM: Invalid permission (for instance asking for write and
* range is read only).
@@ -905,6 +988,7 @@ EXPORT_SYMBOL(hmm_range_snapshot);
*/
long hmm_range_fault(struct hmm_range *range, bool block)
{
+ 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;
@@ -924,15 +1008,25 @@ long hmm_range_fault(struct hmm_range *range, bool block)
}
vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support hugetlb fs/dax */
- if (is_vm_hugetlb_page(vma) || vma_is_dax(vma)) {
+ /* FIXME support dax */
+ if (vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
+ 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
@@ -959,6 +1053,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
mm_walk.hugetlb_entry = NULL;
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);
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 09/12] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (7 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 08/12] mm/hmm: mirror hugetlbfs (snapshoting, faulting and DMA mapping) v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 10/12] mm/hmm: add helpers to test if mm is still alive or not jglisse
` (2 subsequent siblings)
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Dan Williams,
John Hubbard, Arnd Bergmann
From: Jérôme Glisse <jglisse@redhat.com>
HMM mirror is a device driver helpers to mirror range of virtual address.
It means that the process jobs running on the device can access the same
virtual address as the CPU threads of that process. This patch adds support
for mirroring mapping of file that are on a DAX block device (ie range of
virtual address that is an mmap of a file in a filesystem on a DAX block
device). There is no reason to not support such case when mirroring virtual
address on a device.
Note that unlike GUP code we do not take page reference hence when we
back-off we have nothing to undo.
Changes since v2:
- Added comments about get_dev_pagemap() optimization.
Changes since v1:
- improved commit message
- squashed: Arnd Bergmann: fix unused variable warning in hmm_vma_walk_pud
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Arnd Bergmann <arnd@arndb.de>
---
mm/hmm.c | 138 ++++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 117 insertions(+), 21 deletions(-)
diff --git a/mm/hmm.c b/mm/hmm.c
index 9140cee24d36..39bc77d7e6e3 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -329,6 +329,7 @@ EXPORT_SYMBOL(hmm_mirror_unregister);
struct hmm_vma_walk {
struct hmm_range *range;
+ struct dev_pagemap *pgmap;
unsigned long last;
bool fault;
bool block;
@@ -503,6 +504,15 @@ 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,
@@ -524,8 +534,19 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
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++)
+ 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_pfn_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;
}
@@ -612,10 +633,24 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
if (fault || write_fault)
goto fault;
+ 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_pfn_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);
@@ -703,12 +738,89 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
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;
}
+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_pfn_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;
+}
+
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
@@ -781,14 +893,6 @@ static void hmm_pfns_clear(struct hmm_range *range,
*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_range_register() - start tracking change to CPU page table over a range
* @range: range
@@ -906,12 +1010,6 @@ long hmm_range_snapshot(struct hmm_range *range)
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support dax */
- if (vma_is_dax(vma)) {
- hmm_pfns_special(range);
- return -EINVAL;
- }
-
if (is_vm_hugetlb_page(vma)) {
struct hstate *h = hstate_vma(vma);
@@ -935,6 +1033,7 @@ long hmm_range_snapshot(struct hmm_range *range)
}
range->vma = vma;
+ hmm_vma_walk.pgmap = NULL;
hmm_vma_walk.last = start;
hmm_vma_walk.fault = false;
hmm_vma_walk.range = range;
@@ -946,6 +1045,7 @@ long hmm_range_snapshot(struct hmm_range *range)
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;
@@ -1011,12 +1111,6 @@ long hmm_range_fault(struct hmm_range *range, bool block)
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support dax */
- if (vma_is_dax(vma)) {
- hmm_pfns_special(range);
- return -EINVAL;
- }
-
if (is_vm_hugetlb_page(vma)) {
if (huge_page_shift(hstate_vma(vma)) !=
range->page_shift &&
@@ -1039,6 +1133,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
}
range->vma = vma;
+ hmm_vma_walk.pgmap = NULL;
hmm_vma_walk.last = start;
hmm_vma_walk.fault = true;
hmm_vma_walk.block = block;
@@ -1051,6 +1146,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
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;
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 10/12] mm/hmm: add helpers to test if mm is still alive or not
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (8 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 09/12] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem v3 jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 11/12] mm/hmm: add an helper function that fault pages and map them to a device v3 jglisse
2019-04-03 19:33 ` [PATCH v3 12/12] mm/hmm: convert various hmm_pfn_* to device_entry which is a better name jglisse
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Ralph Campbell,
John Hubbard, Dan Williams, Ira Weiny
From: Jérôme Glisse <jglisse@redhat.com>
The device driver can have kernel thread or worker doing work against
a process mm and it is useful for those to test wether the mm is dead
or alive to avoid doing useless work. Add an helper to test that so
that driver can bail out early if a process is dying.
Note that the helper does not perform any lock synchronization and thus
is just a hint ie a process might be dying but the helper might still
return the process as alive. All HMM functions are safe to use in that
case as HMM internal properly protect itself with lock. If driver use
this helper with non HMM functions it should ascertain that it is safe
to do so.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
---
include/linux/hmm.h | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index e5834082de60..a79fcc6681f5 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -438,6 +438,30 @@ struct hmm_mirror {
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
void hmm_mirror_unregister(struct hmm_mirror *mirror);
+/*
+ * hmm_mirror_mm_is_alive() - test if mm is still alive
+ * @mirror: the HMM mm mirror for which we want to lock the mmap_sem
+ * Returns: false if the mm is dead, true otherwise
+ *
+ * This is an optimization it will not accurately always return -EINVAL if the
+ * mm is dead ie there can be false negative (process is being kill but HMM is
+ * not yet inform of that). It is only intented to be use to optimize out case
+ * where driver is about to do something time consuming and it would be better
+ * to skip it if the mm is dead.
+ */
+static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror)
+{
+ struct mm_struct *mm;
+
+ if (!mirror || !mirror->hmm)
+ return false;
+ mm = READ_ONCE(mirror->hmm->mm);
+ if (mirror->hmm->dead || !mm)
+ return false;
+
+ return true;
+}
+
/*
* Please see Documentation/vm/hmm.rst for how to use the range API.
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 11/12] mm/hmm: add an helper function that fault pages and map them to a device v3
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (9 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 10/12] mm/hmm: add helpers to test if mm is still alive or not jglisse
@ 2019-04-03 19:33 ` jglisse
2019-04-03 19:33 ` [PATCH v3 12/12] mm/hmm: convert various hmm_pfn_* to device_entry which is a better name jglisse
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Ralph Campbell,
John Hubbard, Dan Williams, Souptick Joarder
From: Jérôme Glisse <jglisse@redhat.com>
This is a all in one helper that fault pages in a range and map them to
a device so that every single device driver do not have to re-implement
this common pattern.
This is taken from ODP RDMA in preparation of ODP RDMA convertion. It
will be use by nouveau and other drivers.
Changes since v2:
- Improved function comment for kernel documentation.
Changes since v1:
- improved commit message
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
---
include/linux/hmm.h | 9 +++
mm/hmm.c | 152 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 161 insertions(+)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index a79fcc6681f5..f81fe2c0f343 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -474,6 +474,15 @@ int hmm_range_register(struct hmm_range *range,
void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
long hmm_range_fault(struct hmm_range *range, bool block);
+long hmm_range_dma_map(struct hmm_range *range,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool block);
+long hmm_range_dma_unmap(struct hmm_range *range,
+ struct vm_area_struct *vma,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool dirty);
/*
* HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
diff --git a/mm/hmm.c b/mm/hmm.c
index 39bc77d7e6e3..82fded7273d8 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -30,6 +30,7 @@
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/jump_label.h>
+#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
@@ -1173,6 +1174,157 @@ long hmm_range_fault(struct hmm_range *range, bool block)
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)
+ * Returns: 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_FROM_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_pfn_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->values[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_FROM_DEVICE;
+ struct page *page;
+
+ page = hmm_pfn_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->values[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
+ * Returns: 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_FROM_DEVICE;
+ struct page *page;
+
+ page = hmm_pfn_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->values[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);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 12/12] mm/hmm: convert various hmm_pfn_* to device_entry which is a better name
2019-04-03 19:33 [PATCH v3 00/12] Improve HMM driver API v3 jglisse
` (10 preceding siblings ...)
2019-04-03 19:33 ` [PATCH v3 11/12] mm/hmm: add an helper function that fault pages and map them to a device v3 jglisse
@ 2019-04-03 19:33 ` jglisse
11 siblings, 0 replies; 13+ messages in thread
From: jglisse @ 2019-04-03 19:33 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-kernel, Jérôme Glisse, Ralph Campbell,
John Hubbard, Dan Williams, Ira Weiny
From: Jérôme Glisse <jglisse@redhat.com>
Convert hmm_pfn_* to device_entry_* as here we are dealing with device
driver specific entry format and hmm provide helpers to allow differents
components (including HMM) to create/parse device entry.
We keep wrapper with the old name so that we can convert driver to use the
new API in stages in each device driver tree. This will get remove once all
driver are converted.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
---
include/linux/hmm.h | 93 +++++++++++++++++++++++++++++++--------------
mm/hmm.c | 19 +++++----
2 files changed, 75 insertions(+), 37 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index f81fe2c0f343..51ec27a84668 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -239,36 +239,36 @@ static inline bool hmm_range_valid(struct hmm_range *range)
}
/*
- * hmm_pfn_to_page() - return struct page pointed to by a valid HMM pfn
- * @range: range use to decode HMM pfn value
- * @pfn: HMM pfn value to get corresponding struct page from
- * Returns: struct page pointer if pfn is a valid HMM pfn, NULL otherwise
+ * hmm_device_entry_to_page() - return struct page pointed to by a device entry
+ * @range: range use to decode device entry value
+ * @entry: device entry value to get corresponding struct page from
+ * Returns: struct page pointer if entry is a valid, NULL otherwise
*
- * If the HMM pfn is valid (ie valid flag set) then return the struct page
- * matching the pfn value stored in the HMM pfn. Otherwise return NULL.
+ * If the device entry is valid (ie valid flag set) then return the struct page
+ * matching the entry value. Otherwise return NULL.
*/
-static inline struct page *hmm_pfn_to_page(const struct hmm_range *range,
- uint64_t pfn)
+static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range,
+ uint64_t entry)
{
- if (pfn == range->values[HMM_PFN_NONE])
+ if (entry == range->values[HMM_PFN_NONE])
return NULL;
- if (pfn == range->values[HMM_PFN_ERROR])
+ if (entry == range->values[HMM_PFN_ERROR])
return NULL;
- if (pfn == range->values[HMM_PFN_SPECIAL])
+ if (entry == range->values[HMM_PFN_SPECIAL])
return NULL;
- if (!(pfn & range->flags[HMM_PFN_VALID]))
+ if (!(entry & range->flags[HMM_PFN_VALID]))
return NULL;
- return pfn_to_page(pfn >> range->pfn_shift);
+ return pfn_to_page(entry >> range->pfn_shift);
}
/*
- * hmm_pfn_to_pfn() - return pfn value store in a HMM pfn
- * @range: range use to decode HMM pfn value
- * @pfn: HMM pfn value to extract pfn from
- * Returns: pfn value if HMM pfn is valid, -1UL otherwise
+ * hmm_device_entry_to_pfn() - return pfn value store in a device entry
+ * @range: range use to decode device entry value
+ * @entry: device entry to extract pfn from
+ * Returns: pfn value if device entry is valid, -1UL otherwise
*/
-static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
- uint64_t pfn)
+static inline unsigned long
+hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn)
{
if (pfn == range->values[HMM_PFN_NONE])
return -1UL;
@@ -282,31 +282,66 @@ static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
}
/*
- * hmm_pfn_from_page() - create a valid HMM pfn value from struct page
+ * hmm_device_entry_from_page() - create a valid device entry for a page
* @range: range use to encode HMM pfn value
- * @page: struct page pointer for which to create the HMM pfn
- * Returns: valid HMM pfn for the page
+ * @page: page for which to create the device entry
+ * Returns: valid device entry for the page
*/
-static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range,
- struct page *page)
+static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range,
+ struct page *page)
{
return (page_to_pfn(page) << range->pfn_shift) |
range->flags[HMM_PFN_VALID];
}
/*
- * hmm_pfn_from_pfn() - create a valid HMM pfn value from pfn
+ * hmm_device_entry_from_pfn() - create a valid device entry value from pfn
* @range: range use to encode HMM pfn value
- * @pfn: pfn value for which to create the HMM pfn
- * Returns: valid HMM pfn for the pfn
+ * @pfn: pfn value for which to create the device entry
+ * Returns: valid device entry for the pfn
*/
-static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range,
- unsigned long pfn)
+static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
+ unsigned long pfn)
{
return (pfn << range->pfn_shift) |
range->flags[HMM_PFN_VALID];
}
+/*
+ * Old API:
+ * hmm_pfn_to_page()
+ * hmm_pfn_to_pfn()
+ * hmm_pfn_from_page()
+ * hmm_pfn_from_pfn()
+ *
+ * This are the OLD API please use new API, it is here to avoid cross-tree
+ * merge painfullness ie we convert things to new API in stages.
+ */
+static inline struct page *hmm_pfn_to_page(const struct hmm_range *range,
+ uint64_t pfn)
+{
+ return hmm_device_entry_to_page(range, pfn);
+}
+
+static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
+ uint64_t pfn)
+{
+ return hmm_device_entry_to_pfn(range, pfn);
+}
+
+static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range,
+ struct page *page)
+{
+ return hmm_device_entry_from_page(range, page);
+}
+
+static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range,
+ unsigned long pfn)
+{
+ return hmm_device_entry_from_pfn(range, pfn);
+}
+
+
#if IS_ENABLED(CONFIG_HMM_MIRROR)
/*
diff --git a/mm/hmm.c b/mm/hmm.c
index 82fded7273d8..75d2ea906efb 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -542,7 +542,7 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
}
- pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+ pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
}
if (hmm_vma_walk->pgmap) {
put_dev_pagemap(hmm_vma_walk->pgmap);
@@ -606,7 +606,8 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
&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;
}
@@ -644,7 +645,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
return -EFAULT;
}
- *pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
+ *pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
return 0;
fault:
@@ -797,7 +798,8 @@ static int hmm_vma_walk_pud(pud_t *pudp,
hmm_vma_walk->pgmap);
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
- pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+ pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
+ cpu_flags;
}
if (hmm_vma_walk->pgmap) {
put_dev_pagemap(hmm_vma_walk->pgmap);
@@ -870,7 +872,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
pfn = pte_pfn(entry) + (start & mask);
for (; addr < end; addr += size, i++, pfn += pfn_inc)
- range->pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+ range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
+ cpu_flags;
hmm_vma_walk->last = end;
unlock:
@@ -1213,7 +1216,7 @@ long hmm_range_dma_map(struct hmm_range *range,
*/
daddrs[i] = 0;
- page = hmm_pfn_to_page(range, range->pfns[i]);
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
@@ -1243,7 +1246,7 @@ long hmm_range_dma_map(struct hmm_range *range,
enum dma_data_direction dir = DMA_FROM_DEVICE;
struct page *page;
- page = hmm_pfn_to_page(range, range->pfns[i]);
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
@@ -1298,7 +1301,7 @@ long hmm_range_dma_unmap(struct hmm_range *range,
enum dma_data_direction dir = DMA_FROM_DEVICE;
struct page *page;
- page = hmm_pfn_to_page(range, range->pfns[i]);
+ page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
--
2.17.2
^ permalink raw reply related [flat|nested] 13+ messages in thread