From: "Jérôme Glisse" <jglisse@redhat.com>
To: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Cc: "John Hubbard" <jhubbard@nvidia.com>,
"Dan Williams" <dan.j.williams@intel.com>,
"Naoya Horiguchi" <n-horiguchi@ah.jp.nec.com>,
"David Nellans" <dnellans@nvidia.com>,
"Jérôme Glisse" <jglisse@redhat.com>
Subject: [HMM 05/16] mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY
Date: Wed, 5 Apr 2017 16:40:15 -0400 [thread overview]
Message-ID: <20170405204026.3940-6-jglisse@redhat.com> (raw)
In-Reply-To: <20170405204026.3940-1-jglisse@redhat.com>
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).
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
---
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 --git a/fs/aio.c b/fs/aio.c
index 7e2ab9c..be21c49 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -373,6 +373,14 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
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 --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9ac2625..7fc08a5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1997,7 +1997,10 @@ int f2fs_migrate_page(struct address_space *mapping,
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 --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cf3669d..b2e0fdb 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -837,7 +837,10 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
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 --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index d9ae86f..c08cbcc 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1482,7 +1482,10 @@ static int ubifs_migrate_page(struct address_space *mapping,
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 --git a/include/linux/migrate.h b/include/linux/migrate.h
index 48e2484..78a0fdc 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -43,6 +43,7 @@ extern void putback_movable_page(struct page *page);
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);
@@ -63,6 +64,10 @@ static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
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 --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h
index ebf3d89..bdf66af 100644
--- a/include/linux/migrate_mode.h
+++ b/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 --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index da91df5..145b903 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -139,6 +139,14 @@ int balloon_page_migrate(struct address_space *mapping,
{
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 --git a/mm/migrate.c b/mm/migrate.c
index 5cfe3c2..5176772 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -601,15 +601,10 @@ static void copy_huge_page(struct page *dst, struct page *src)
/*
* 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))
@@ -663,6 +658,17 @@ void migrate_page_copy(struct page *newpage, struct page *page)
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);
/************************************************************
@@ -688,7 +694,10 @@ int migrate_page(struct address_space *mapping,
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);
@@ -738,12 +747,15 @@ int buffer_migrate_page(struct address_space *mapping,
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);
@@ -802,8 +814,13 @@ static int fallback_migrate_page(struct address_space *mapping,
{
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);
}
@@ -940,7 +957,11 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
* 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;
}
@@ -1210,8 +1231,15 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
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 --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b7b1fb6..37afd65 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1982,6 +1982,14 @@ int zs_page_migrate(struct address_space *mapping, struct page *newpage,
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);
--
2.9.3
next prev parent reply other threads:[~2017-04-05 20:41 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-05 20:40 [HMM 00/16] HMM (Heterogeneous Memory Management) v19 Jérôme Glisse
2017-04-05 20:40 ` [HMM 01/16] mm/memory/hotplug: add memory type parameter to arch_add/remove_memory Jérôme Glisse
2017-04-06 9:45 ` Anshuman Khandual
2017-04-06 13:58 ` Jerome Glisse
2017-04-07 12:13 ` Michal Hocko
2017-04-07 14:32 ` Jerome Glisse
2017-04-07 14:45 ` Michal Hocko
2017-04-07 14:57 ` Jerome Glisse
2017-04-07 15:11 ` Michal Hocko
2017-04-07 16:10 ` Jerome Glisse
2017-04-07 16:37 ` Michal Hocko
2017-04-07 17:10 ` Jerome Glisse
2017-04-07 17:59 ` Michal Hocko
2017-04-07 18:27 ` Jerome Glisse
2017-04-05 20:40 ` [HMM 02/16] mm/put_page: move ZONE_DEVICE page reference decrement v2 Jérôme Glisse
2017-04-05 20:40 ` [HMM 03/16] mm/unaddressable-memory: new type of ZONE_DEVICE for unaddressable memory Jérôme Glisse
2017-04-05 20:40 ` [HMM 04/16] mm/ZONE_DEVICE/x86: add support for un-addressable device memory Jérôme Glisse
2017-04-05 20:40 ` Jérôme Glisse [this message]
2017-04-05 20:40 ` [HMM 06/16] mm/migrate: new memory migration helper for use with device memory v4 Jérôme Glisse
2017-04-05 20:40 ` [HMM 07/16] mm/migrate: migrate_vma() unmap page from vma while collecting pages Jérôme Glisse
2017-04-05 20:40 ` [HMM 08/16] mm/hmm: heterogeneous memory management (HMM for short) Jérôme Glisse
2017-04-05 20:40 ` [HMM 09/16] mm/hmm/mirror: mirror process address space on device with HMM helpers Jérôme Glisse
2017-04-05 20:40 ` [HMM 10/16] mm/hmm/mirror: helper to snapshot CPU page table v2 Jérôme Glisse
2017-04-10 8:35 ` Michal Hocko
2017-04-10 8:43 ` Michal Hocko
2017-04-10 22:10 ` Andrew Morton
2017-04-11 1:33 ` Jerome Glisse
2017-04-11 20:33 ` Andrew Morton
2017-04-05 20:40 ` [HMM 11/16] mm/hmm/mirror: device page fault handler Jérôme Glisse
2017-04-05 20:40 ` [HMM 12/16] mm/migrate: support un-addressable ZONE_DEVICE page in migration Jérôme Glisse
2017-04-05 20:40 ` [HMM 13/16] mm/migrate: allow migrate_vma() to alloc new page on empty entry Jérôme Glisse
2017-04-05 20:40 ` [HMM 14/16] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE Jérôme Glisse
2017-04-06 21:22 ` Jerome Glisse
2017-04-07 1:37 ` Balbir Singh
2017-04-07 2:02 ` Jerome Glisse
2017-04-07 16:26 ` Jerome Glisse
2017-04-10 4:31 ` Balbir Singh
2017-04-05 20:40 ` [HMM 15/16] mm/hmm/devmem: dummy HMM device for ZONE_DEVICE memory v2 Jérôme Glisse
2017-04-05 20:40 ` [HMM 16/16] hmm: heterogeneous memory management documentation Jérôme Glisse
[not found] ` <CAF7GXvptCfV89rAi=j1cy1df12039GDpq_DHOyx+_xk0FjBDPg@mail.gmail.com>
2017-04-06 4:59 ` [HMM 00/16] HMM (Heterogeneous Memory Management) v19 Jerome Glisse
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170405204026.3940-6-jglisse@redhat.com \
--to=jglisse@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=dnellans@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=n-horiguchi@ah.jp.nec.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).