The patch titled
Subject: mm/hmm/migrate: support un-addressable ZONE_DEVICE page in migration
has been added to the -mm tree. Its filename is
mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration.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/hmm/migrate: support un-addressable ZONE_DEVICE page in migration
Allow to unmap and restore special swap entry of un-addressable
ZONE_DEVICE memory.
Link: http://lkml.kernel.org/r/1489680335-6594-14-git-send-email-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/migrate.h | 2
mm/migrate.c | 141 +++++++++++++++++++++++++++++---------
mm/page_vma_mapped.c | 10 ++
mm/rmap.c | 25 ++++++
4 files changed, 147 insertions(+), 31 deletions(-)
diff -puN include/linux/migrate.h~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration include/linux/migrate.h
--- a/include/linux/migrate.h~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration
+++ a/include/linux/migrate.h
@@ -130,6 +130,8 @@ static inline int migrate_misplaced_tran
#define MIGRATE_PFN_HUGE (1UL << (BITS_PER_LONG_LONG - 3))
#define MIGRATE_PFN_LOCKED (1UL << (BITS_PER_LONG_LONG - 4))
#define MIGRATE_PFN_WRITE (1UL << (BITS_PER_LONG_LONG - 5))
+#define MIGRATE_PFN_DEVICE (1UL << (BITS_PER_LONG_LONG - 6))
+#define MIGRATE_PFN_ERROR (1UL << (BITS_PER_LONG_LONG - 7))
#define MIGRATE_PFN_MASK ((1UL << (BITS_PER_LONG_LONG - PAGE_SHIFT)) - 1)
static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
diff -puN mm/migrate.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration mm/migrate.c
--- a/mm/migrate.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration
+++ a/mm/migrate.c
@@ -41,6 +41,7 @@
#include <linux/page_idle.h>
#include <linux/page_owner.h>
#include <linux/sched/mm.h>
+#include <linux/memremap.h>
#include <asm/tlbflush.h>
@@ -230,7 +231,15 @@ static bool remove_migration_pte(struct
pte = arch_make_huge_pte(pte, vma, new, 0);
}
#endif
- flush_dcache_page(new);
+
+ if (unlikely(is_zone_device_page(new)) &&
+ !is_addressable_page(new)) {
+ entry = make_device_entry(new, pte_write(pte));
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(*pvmw.pte))
+ pte = pte_mksoft_dirty(pte);
+ } else
+ flush_dcache_page(new);
set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
if (PageHuge(new)) {
@@ -302,6 +311,8 @@ void __migration_entry_wait(struct mm_st
*/
if (!get_page_unless_zero(page))
goto out;
+ if (is_zone_device_page(page))
+ get_zone_device_page(page);
pte_unmap_unlock(ptep, ptl);
wait_on_page_locked(page);
put_page(page);
@@ -2099,12 +2110,14 @@ static int migrate_vma_collect_hole(unsi
next = pmd_addr_end(addr, end);
npages = (next - addr) >> PAGE_SHIFT;
if (npages == (PMD_SIZE >> PAGE_SHIFT)) {
+ migrate->dst[migrate->npages] = 0;
migrate->src[migrate->npages++] = MIGRATE_PFN_HUGE;
ret = migrate_vma_array_full(migrate);
if (ret)
return ret;
} else {
for (i = 0; i < npages; ++i) {
+ migrate->dst[migrate->npages] = 0;
migrate->src[migrate->npages++] = 0;
ret = migrate_vma_array_full(migrate);
if (ret)
@@ -2146,17 +2159,44 @@ static int migrate_vma_collect_pmd(pmd_t
pte = *ptep;
pfn = pte_pfn(pte);
- if (!pte_present(pte)) {
+ if (pte_none(pte)) {
flags = pfn = 0;
goto next;
}
+ if (!pte_present(pte)) {
+ flags = pfn = 0;
+
+ /*
+ * Only care about unaddressable device page special
+ * page table entry. Other special swap entry are not
+ * migratable and we ignore regular swapped page.
+ */
+ entry = pte_to_swp_entry(pte);
+ if (!is_device_entry(entry))
+ goto next;
+
+ page = device_entry_to_page(entry);
+ if (!dev_page_allow_migrate(page))
+ goto next;
+
+ flags = MIGRATE_PFN_VALID |
+ MIGRATE_PFN_DEVICE |
+ MIGRATE_PFN_MIGRATE;
+ if (is_write_device_entry(entry))
+ flags |= MIGRATE_PFN_WRITE;
+ } else {
+ page = vm_normal_page(migrate->vma, addr, pte);
+ flags = MIGRATE_PFN_VALID | MIGRATE_PFN_MIGRATE;
+ flags |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
+ }
+
/* FIXME support THP */
- page = vm_normal_page(migrate->vma, addr, pte);
if (!page || !page->mapping || PageTransCompound(page)) {
flags = pfn = 0;
goto next;
}
+ pfn = page_to_pfn(page);
/*
* By getting a reference on the page we pin it and that blocks
@@ -2169,8 +2209,6 @@ static int migrate_vma_collect_pmd(pmd_t
*/
get_page(page);
migrate->cpages++;
- flags = MIGRATE_PFN_VALID | MIGRATE_PFN_MIGRATE;
- flags |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
/*
* Optimize for the common case where page is only mapped once
@@ -2201,6 +2239,7 @@ static int migrate_vma_collect_pmd(pmd_t
}
next:
+ migrate->dst[migrate->npages] = 0;
migrate->src[migrate->npages++] = pfn | flags;
ret = migrate_vma_array_full(migrate);
if (ret) {
@@ -2275,6 +2314,13 @@ static bool migrate_vma_check_page(struc
if (PageCompound(page))
return false;
+ /* Page from ZONE_DEVICE have one extra reference */
+ if (is_zone_device_page(page)) {
+ if (!dev_page_allow_migrate(page))
+ return false;
+ extra++;
+ }
+
if ((page_count(page) - extra) > page_mapcount(page))
return false;
@@ -2314,28 +2360,31 @@ static void migrate_vma_prepare(struct m
migrate->src[i] |= MIGRATE_PFN_LOCKED;
}
- if (!PageLRU(page) && allow_drain) {
- /* Drain CPU's pagevec */
- lru_add_drain_all();
- allow_drain = false;
- }
+ /* ZONE_DEVICE page are not on LRU */
+ if (!is_zone_device_page(page)) {
+ if (!PageLRU(page) && allow_drain) {
+ /* Drain CPU's pagevec */
+ lru_add_drain_all();
+ allow_drain = false;
+ }
- if (isolate_lru_page(page)) {
- if (remap) {
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- migrate->cpages--;
- restore++;
- } else {
- migrate->src[i] = 0;
- unlock_page(page);
- migrate->cpages--;
- put_page(page);
+ if (isolate_lru_page(page)) {
+ if (remap) {
+ migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+ migrate->cpages--;
+ restore++;
+ } else {
+ migrate->src[i] = 0;
+ unlock_page(page);
+ migrate->cpages--;
+ put_page(page);
+ }
+ continue;
}
- continue;
- }
- /* Drop the reference we took in collect */
- put_page(page);
+ /* Drop the reference we took in collect */
+ put_page(page);
+ }
if (!migrate_vma_check_page(page)) {
if (remap) {
@@ -2343,14 +2392,19 @@ static void migrate_vma_prepare(struct m
migrate->cpages--;
restore++;
- get_page(page);
- putback_lru_page(page);
+ if (!is_zone_device_page(page)) {
+ get_page(page);
+ putback_lru_page(page);
+ }
} else {
migrate->src[i] = 0;
unlock_page(page);
migrate->cpages--;
- putback_lru_page(page);
+ if (!is_zone_device_page(page))
+ putback_lru_page(page);
+ else
+ put_page(page);
}
}
}
@@ -2389,7 +2443,7 @@ static void migrate_vma_unmap(struct mig
const unsigned long npages = migrate->npages;
const unsigned long start = migrate->start;
- for (i = 0; i < npages && migrate->cpages; addr += size, i++) {
+ for (addr = start, i = 0; i < npages; addr += size, i++) {
struct page *page = migrate_pfn_to_page(migrate->src[i]);
size = migrate_pfn_size(migrate->src[i]);
@@ -2417,7 +2471,10 @@ static void migrate_vma_unmap(struct mig
unlock_page(page);
restore--;
- putback_lru_page(page);
+ if (is_zone_device_page(page))
+ put_page(page);
+ else
+ putback_lru_page(page);
}
}
@@ -2449,6 +2506,22 @@ static void migrate_vma_pages(struct mig
mapping = page_mapping(page);
+ if (is_zone_device_page(newpage)) {
+ if (!dev_page_allow_migrate(newpage)) {
+ migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+ continue;
+ }
+
+ /*
+ * For now only support private anonymous when migrating
+ * to un-addressable device memory.
+ */
+ if (mapping && !is_addressable_page(newpage)) {
+ migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+ continue;
+ }
+ }
+
r = migrate_page(mapping, newpage, page, MIGRATE_SYNC, false);
if (r != MIGRATEPAGE_SUCCESS)
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
@@ -2490,11 +2563,17 @@ static void migrate_vma_finalize(struct
unlock_page(page);
migrate->cpages--;
- putback_lru_page(page);
+ if (is_zone_device_page(page))
+ put_page(page);
+ else
+ putback_lru_page(page);
if (newpage != page) {
unlock_page(newpage);
- putback_lru_page(newpage);
+ if (is_zone_device_page(newpage))
+ put_page(newpage);
+ else
+ putback_lru_page(newpage);
}
}
}
diff -puN mm/page_vma_mapped.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration mm/page_vma_mapped.c
--- a/mm/page_vma_mapped.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration
+++ a/mm/page_vma_mapped.c
@@ -48,6 +48,7 @@ static bool check_pte(struct page_vma_ma
if (!is_swap_pte(*pvmw->pte))
return false;
entry = pte_to_swp_entry(*pvmw->pte);
+
if (!is_migration_entry(entry))
return false;
if (migration_entry_to_page(entry) - pvmw->page >=
@@ -60,6 +61,15 @@ static bool check_pte(struct page_vma_ma
WARN_ON_ONCE(1);
#endif
} else {
+ if (is_swap_pte(*pvmw->pte)) {
+ swp_entry_t entry;
+
+ entry = pte_to_swp_entry(*pvmw->pte);
+ if (is_device_entry(entry) &&
+ device_entry_to_page(entry) == pvmw->page)
+ return true;
+ }
+
if (!pte_present(*pvmw->pte))
return false;
diff -puN mm/rmap.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration mm/rmap.c
--- a/mm/rmap.c~mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration
+++ a/mm/rmap.c
@@ -63,6 +63,7 @@
#include <linux/hugetlb.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>
+#include <linux/memremap.h>
#include <asm/tlbflush.h>
@@ -1308,6 +1309,10 @@ static bool try_to_unmap_one(struct page
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
return true;
+ if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
+ is_zone_device_page(page) && !dev_page_allow_migrate(page))
+ return SWAP_AGAIN;
+
if (flags & TTU_SPLIT_HUGE_PMD) {
split_huge_pmd_address(vma, address,
flags & TTU_MIGRATION, page);
@@ -1343,6 +1348,26 @@ static bool try_to_unmap_one(struct page
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
+ if (IS_ENABLED(CONFIG_MIGRATION) &&
+ (flags & TTU_MIGRATION) &&
+ is_zone_device_page(page)) {
+ swp_entry_t entry;
+ pte_t swp_pte;
+
+ pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+
+ /*
+ * Store the pfn of the page in a special migration
+ * pte. do_swap_page() will wait until the migration
+ * pte is removed and then restart fault handling.
+ */
+ entry = make_migration_entry(page, 0);
+ swp_pte = swp_entry_to_pte(entry);
+ if (pte_soft_dirty(pteval))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ set_pte_at(mm, address, pvmw.pte, swp_pte);
+ goto discard;
+ }
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address,
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
mm-memory-hotplug-convert-device-bool-to-int-to-allow-for-more-flags-v3.patch
mm-put_page-move-ref-decrement-to-put_zone_device_page.patch
mm-zone_device-free-page-callback-when-page-is-freed-v3.patch
mm-zone_device-unaddressable-add-support-for-un-addressable-device-memory-v3.patch
mm-zone_device-x86-add-support-for-un-addressable-device-memory.patch
mm-migrate-add-new-boolean-copy-flag-to-migratepage-callback.patch
mm-migrate-new-memory-migration-helper-for-use-with-device-memory-v4.patch
mm-migrate-migrate_vma-unmap-page-from-vma-while-collecting-pages.patch
mm-hmm-heterogeneous-memory-management-hmm-for-short.patch
mm-hmm-mirror-mirror-process-address-space-on-device-with-hmm-helpers.patch
mm-hmm-mirror-helper-to-snapshot-cpu-page-table-v2.patch
mm-hmm-mirror-device-page-fault-handler.patch
mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration.patch
mm-migrate-allow-migrate_vma-to-alloc-new-page-on-empty-entry.patch
mm-hmm-devmem-device-memory-hotplug-using-zone_device.patch
mm-hmm-devmem-dummy-hmm-device-for-zone_device-memory-v2.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
