The patch titled
Subject: mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY
has been added to the -mm tree. Its filename is
mm-migrate-new-migrate-mode-migrate_sync_no_copy.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-migrate-new-migrate-mode-migrate_sync_no_copy.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-migrate-new-migrate-mode-migrate_sync_no_copy.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY
Introduce a new migration mode that allow to offload the copy to a device
DMA engine. This changes the workflow of migration and not all
address_space migratepage callback can support this. So it needs to be
tested in those cases.
This is intended to be use by migrate_vma() which itself is use for thing
like HMM (see include/linux/hmm.h).
Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Aneesh Kumar <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: David Nellans <dnellans@xxxxxxxxxx>
Cc: Evgeny Baskakov <ebaskakov@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Mark Hairgrove <mhairgrove@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Sherry Cheung <SCheung@xxxxxxxxxx>
Cc: Subhash Gutti <sgutti@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/aio.c | 8 +++++
fs/f2fs/data.c | 5 ++-
fs/hugetlbfs/inode.c | 5 ++-
fs/ubifs/file.c | 5 ++-
include/linux/migrate.h | 5 +++
include/linux/migrate_mode.h | 5 +++
mm/balloon_compaction.c | 8 +++++
mm/migrate.c | 52 +++++++++++++++++++++++++--------
mm/zsmalloc.c | 8 +++++
9 files changed, 86 insertions(+), 15 deletions(-)
diff -puN fs/aio.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy fs/aio.c
--- a/fs/aio.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/fs/aio.c
@@ -373,6 +373,14 @@ static int aio_migratepage(struct addres
pgoff_t idx;
int rc;
+ /*
+ * We cannot support the _NO_COPY case here, because copy needs to
+ * happen under the ctx->completion_lock. That does not work with the
+ * migration workflow of MIGRATE_SYNC_NO_COPY.
+ */
+ if (mode == MIGRATE_SYNC_NO_COPY)
+ return -EINVAL;
+
rc = 0;
/* mapping->private_lock here protects against the kioctx teardown. */
diff -puN fs/f2fs/data.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy fs/f2fs/data.c
--- a/fs/f2fs/data.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/fs/f2fs/data.c
@@ -2252,7 +2252,10 @@ int f2fs_migrate_page(struct address_spa
SetPagePrivate(newpage);
set_page_private(newpage, page_private(page));
- migrate_page_copy(newpage, page);
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
diff -puN fs/hugetlbfs/inode.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy fs/hugetlbfs/inode.c
--- a/fs/hugetlbfs/inode.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/fs/hugetlbfs/inode.c
@@ -830,7 +830,10 @@ static int hugetlbfs_migrate_page(struct
rc = migrate_huge_page_move_mapping(mapping, newpage, page);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
- migrate_page_copy(newpage, page);
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
diff -puN fs/ubifs/file.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy fs/ubifs/file.c
--- a/fs/ubifs/file.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/fs/ubifs/file.c
@@ -1490,7 +1490,10 @@ static int ubifs_migrate_page(struct add
SetPagePrivate(newpage);
}
- migrate_page_copy(newpage, page);
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
#endif
diff -puN include/linux/migrate.h~mm-migrate-new-migrate-mode-migrate_sync_no_copy include/linux/migrate.h
--- a/include/linux/migrate.h~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/include/linux/migrate.h
@@ -72,6 +72,7 @@ extern void putback_movable_page(struct
extern int migrate_prep(void);
extern int migrate_prep_local(void);
+extern void migrate_page_states(struct page *newpage, struct page *page);
extern void migrate_page_copy(struct page *newpage, struct page *page);
extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
@@ -92,6 +93,10 @@ static inline int isolate_movable_page(s
static inline int migrate_prep(void) { return -ENOSYS; }
static inline int migrate_prep_local(void) { return -ENOSYS; }
+static inline void migrate_page_states(struct page *newpage, struct page *page)
+{
+}
+
static inline void migrate_page_copy(struct page *newpage,
struct page *page) {}
diff -puN include/linux/migrate_mode.h~mm-migrate-new-migrate-mode-migrate_sync_no_copy include/linux/migrate_mode.h
--- a/include/linux/migrate_mode.h~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/include/linux/migrate_mode.h
@@ -6,11 +6,16 @@
* on most operations but not ->writepage as the potential stall time
* is too significant
* MIGRATE_SYNC will block when migrating pages
+ * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages
+ * with the CPU. Instead, page copy happens outside the migratepage()
+ * callback and is likely using a DMA engine. See migrate_vma() and HMM
+ * (mm/hmm.c) for users of this mode.
*/
enum migrate_mode {
MIGRATE_ASYNC,
MIGRATE_SYNC_LIGHT,
MIGRATE_SYNC,
+ MIGRATE_SYNC_NO_COPY,
};
#endif /* MIGRATE_MODE_H_INCLUDED */
diff -puN mm/balloon_compaction.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy mm/balloon_compaction.c
--- a/mm/balloon_compaction.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/mm/balloon_compaction.c
@@ -139,6 +139,14 @@ int balloon_page_migrate(struct address_
{
struct balloon_dev_info *balloon = balloon_page_device(page);
+ /*
+ * We can not easily support the no copy case here so ignore it as it
+ * is unlikely to be use with ballon pages. See include/linux/hmm.h for
+ * user of the MIGRATE_SYNC_NO_COPY mode.
+ */
+ if (mode == MIGRATE_SYNC_NO_COPY)
+ return -EINVAL;
+
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
diff -puN mm/migrate.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy mm/migrate.c
--- a/mm/migrate.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/mm/migrate.c
@@ -633,15 +633,10 @@ static void copy_huge_page(struct page *
/*
* Copy the page to its new location
*/
-void migrate_page_copy(struct page *newpage, struct page *page)
+void migrate_page_states(struct page *newpage, struct page *page)
{
int cpupid;
- if (PageHuge(page) || PageTransHuge(page))
- copy_huge_page(newpage, page);
- else
- copy_highpage(newpage, page);
-
if (PageError(page))
SetPageError(newpage);
if (PageReferenced(page))
@@ -695,6 +690,17 @@ void migrate_page_copy(struct page *newp
mem_cgroup_migrate(page, newpage);
}
+EXPORT_SYMBOL(migrate_page_states);
+
+void migrate_page_copy(struct page *newpage, struct page *page)
+{
+ if (PageHuge(page) || PageTransHuge(page))
+ copy_huge_page(newpage, page);
+ else
+ copy_highpage(newpage, page);
+
+ migrate_page_states(newpage, page);
+}
EXPORT_SYMBOL(migrate_page_copy);
/************************************************************
@@ -720,7 +726,10 @@ int migrate_page(struct address_space *m
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
- migrate_page_copy(newpage, page);
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);
@@ -770,12 +779,15 @@ int buffer_migrate_page(struct address_s
SetPagePrivate(newpage);
- migrate_page_copy(newpage, page);
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
bh = head;
do {
unlock_buffer(bh);
- put_bh(bh);
+ put_bh(bh);
bh = bh->b_this_page;
} while (bh != head);
@@ -834,8 +846,13 @@ static int fallback_migrate_page(struct
{
if (PageDirty(page)) {
/* Only writeback pages in full synchronous migration */
- if (mode != MIGRATE_SYNC)
+ switch (mode) {
+ case MIGRATE_SYNC:
+ case MIGRATE_SYNC_NO_COPY:
+ break;
+ default:
return -EBUSY;
+ }
return writeout(mapping, page);
}
@@ -972,7 +989,11 @@ static int __unmap_and_move(struct page
* the retry loop is too short and in the sync-light case,
* the overhead of stalling is too much
*/
- if (mode != MIGRATE_SYNC) {
+ switch (mode) {
+ case MIGRATE_SYNC:
+ case MIGRATE_SYNC_NO_COPY:
+ break;
+ default:
rc = -EBUSY;
goto out_unlock;
}
@@ -1242,8 +1263,15 @@ static int unmap_and_move_huge_page(new_
return -ENOMEM;
if (!trylock_page(hpage)) {
- if (!force || mode != MIGRATE_SYNC)
+ if (!force)
goto out;
+ switch (mode) {
+ case MIGRATE_SYNC:
+ case MIGRATE_SYNC_NO_COPY:
+ break;
+ default:
+ goto out;
+ }
lock_page(hpage);
}
diff -puN mm/zsmalloc.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy mm/zsmalloc.c
--- a/mm/zsmalloc.c~mm-migrate-new-migrate-mode-migrate_sync_no_copy
+++ a/mm/zsmalloc.c
@@ -1969,6 +1969,14 @@ int zs_page_migrate(struct address_space
unsigned int obj_idx;
int ret = -EAGAIN;
+ /*
+ * We cannot support the _NO_COPY case here, because copy needs to
+ * happen under the zs lock, which does not work with
+ * MIGRATE_SYNC_NO_COPY workflow.
+ */
+ if (mode == MIGRATE_SYNC_NO_COPY)
+ return -EINVAL;
+
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
hmm-heterogeneous-memory-management-documentation-v3.patch
mm-hmm-heterogeneous-memory-management-hmm-for-short-v5.patch
mm-hmm-mirror-mirror-process-address-space-on-device-with-hmm-helpers-v3.patch
mm-hmm-mirror-helper-to-snapshot-cpu-page-table-v4.patch
mm-hmm-mirror-device-page-fault-handler.patch
mm-zone_device-new-type-of-zone_device-for-unaddressable-memory-v5.patch
mm-zone_device-special-case-put_page-for-device-private-pages-v4.patch
mm-memcontrol-allow-to-uncharge-page-without-using-page-lru-field.patch
mm-memcontrol-support-memory_device_private-v4.patch
mm-hmm-devmem-device-memory-hotplug-using-zone_device-v7.patch
mm-hmm-devmem-dummy-hmm-device-for-zone_device-memory-v3.patch
mm-migrate-new-migrate-mode-migrate_sync_no_copy.patch
mm-migrate-new-memory-migration-helper-for-use-with-device-memory-v5.patch
mm-migrate-migrate_vma-unmap-page-from-vma-while-collecting-pages.patch
mm-migrate-support-un-addressable-zone_device-page-in-migration-v3.patch
mm-migrate-allow-migrate_vma-to-alloc-new-page-on-empty-entry-v4.patch
mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5.patch
mm-hmm-add-new-helper-to-hotplug-cdm-memory-region-v3.patch
lib-interval_tree-fast-overlap-detection-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
