* + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch
@ 2022-06-29 23:33 Andrew Morton
0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-06-29 23:33 UTC (permalink / raw)
To: mm-commits, willy, rcampbell, jglisse, jgg, hch, Felix.Kuehling,
david, apopple, alex.sierra, akpm
The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm mm-unstable branch. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-zone-device-coherent-type-memory-support.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: mm: add zone device coherent type memory support
Date: Tue, 28 Jun 2022 22:54:14 -0500
Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI or
CXL). Any page of a process can be migrated to such memory. However, no
one should be allowed to pin such memory so that it can always be evicted.
[hch@lst.de: rebased ontop of the refcount changes, removed is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220629035426.20013-3-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memremap.h | 22 +++++++++++++++++++++-
mm/memcontrol.c | 7 ++++---
mm/memory-failure.c | 8 ++++++--
mm/memremap.c | 10 ++++++++++
mm/migrate_device.c | 16 +++++++---------
mm/rmap.c | 5 +++--
6 files changed, 51 insertions(+), 17 deletions(-)
--- a/include/linux/memremap.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/memremap.h
@@ -41,6 +41,13 @@ struct vmem_altmap {
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/mm/hmm.rst.
*
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
@@ -61,6 +68,7 @@ struct vmem_altmap {
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
@@ -143,6 +151,17 @@ static inline bool folio_is_device_priva
return is_device_private_page(&folio->page);
}
+static inline bool is_device_coherent_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+ return is_device_coherent_page(&folio->page);
+}
+
static inline bool is_pci_p2pdma_page(const struct page *page)
{
return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
@@ -160,7 +179,8 @@ static inline bool is_longterm_pinnable_
if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
return false;
#endif
- return !(is_zone_movable_page(page) ||
+ return !(is_device_coherent_page(page) ||
+ is_zone_movable_page(page) ||
is_zero_pfn(page_to_pfn(page)));
}
#else
--- a/mm/memcontrol.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memcontrol.c
@@ -5716,8 +5716,8 @@ out:
* 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
* target for charge migration. if @target is not NULL, the entry is stored
* in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE
- * (so ZONE_DEVICE page and thus not on the lru).
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
+ * thus not on the lru.
* For now we such page is charge like a regular page would be as for all
* intent and purposes it is just special memory taking the place of a
* regular page.
@@ -5755,7 +5755,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_coherent_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
--- a/mm/memory-failure.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memory-failure.c
@@ -1685,12 +1685,16 @@ static int memory_failure_dev_pagemap(un
goto unlock;
}
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
/*
- * TODO: Handle HMM pages which may need coordination
+ * TODO: Handle device pages which may need coordination
* with device-side memory.
*/
goto unlock;
+ default:
+ break;
}
/*
--- a/mm/memremap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memremap.c
@@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap
return ERR_PTR(-EINVAL);
}
break;
+ case MEMORY_DEVICE_COHERENT:
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
--- a/mm/migrate_device.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/migrate_device.c
@@ -518,7 +518,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
* handle_pte_fault()
* do_anonymous_page()
* to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
*/
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -594,11 +594,8 @@ static void migrate_vma_insert_page(stru
page_to_pfn(page));
entry = swp_entry_to_pte(swp_entry);
} else {
- /*
- * For now we only support migrating to un-addressable device
- * memory.
- */
- if (is_zone_device_page(page)) {
+ if (is_zone_device_page(page) &&
+ !is_device_coherent_page(page)) {
pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
goto abort;
}
@@ -701,10 +698,11 @@ void migrate_vma_pages(struct migrate_vm
mapping = page_mapping(page);
- if (is_device_private_page(newpage)) {
+ if (is_device_private_page(newpage) ||
+ is_device_coherent_page(newpage)) {
/*
- * For now only support private anonymous when migrating
- * to un-addressable device memory.
+ * For now only support anonymous memory migrating to
+ * device private or coherent memory.
*/
if (mapping) {
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
--- a/mm/rmap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/rmap.c
@@ -1972,7 +1972,7 @@ static bool try_to_migrate_one(struct fo
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (folio_is_zone_device(folio)) {
+ if (folio_is_device_private(folio)) {
unsigned long pfn = folio_pfn(folio);
swp_entry_t entry;
pte_t swp_pte;
@@ -2138,7 +2138,8 @@ void try_to_migrate(struct folio *folio,
TTU_SYNC)))
return;
- if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+ if (folio_is_zone_device(folio) &&
+ (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
_
Patches currently in -mm which might be from alex.sierra@amd.com are
mm-rename-is_pinnable_pages-to-is_pinnable_longterm_pages.patch
mm-add-zone-device-coherent-type-memory-support.patch
mm-handling-non-lru-pages-returned-by-vm_normal_pages.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
drm-amdkfd-add-spm-support-for-svm.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch
tools-add-hmm-gup-tests-for-device-coherent-type.patch
tools-add-selftests-to-hmm-for-cow-in-device-memory.patch
^ permalink raw reply [flat|nested] 5+ messages in thread
* + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch
@ 2022-07-15 23:25 Andrew Morton
0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-07-15 23:25 UTC (permalink / raw)
To: mm-commits, willy, rcampbell, jglisse, jgg, hch, Felix.Kuehling,
david, apopple, alex.sierra, akpm
The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm mm-unstable branch. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-zone-device-coherent-type-memory-support.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: mm: add zone device coherent type memory support
Date: Fri, 15 Jul 2022 10:05:10 -0500
Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI or
CXL). Any page of a process can be migrated to such memory. However, no
one should be allowed to pin such memory so that it can always be evicted.
[hch@lst.de: rebased ontop of the refcount changes, remove is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220715150521.18165-4-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memremap.h | 19 +++++++++++++++++++
include/linux/mm.h | 5 ++++-
mm/memcontrol.c | 7 ++++---
mm/memory-failure.c | 8 ++++++--
mm/memremap.c | 10 ++++++++++
mm/migrate_device.c | 16 +++++++---------
mm/rmap.c | 5 +++--
7 files changed, 53 insertions(+), 17 deletions(-)
--- a/include/linux/memremap.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/memremap.h
@@ -41,6 +41,13 @@ struct vmem_altmap {
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/mm/hmm.rst.
*
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
@@ -61,6 +68,7 @@ struct vmem_altmap {
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
@@ -150,6 +158,17 @@ static inline bool is_pci_p2pdma_page(co
page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
}
+static inline bool is_device_coherent_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+ return is_device_coherent_page(&folio->page);
+}
+
#ifdef CONFIG_ZONE_DEVICE
void *memremap_pages(struct dev_pagemap *pgmap, int nid);
void memunmap_pages(struct dev_pagemap *pgmap);
--- a/include/linux/mm.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/mm.h
@@ -28,6 +28,7 @@
#include <linux/sched.h>
#include <linux/pgtable.h>
#include <linux/kasan.h>
+#include <linux/memremap.h>
struct mempolicy;
struct anon_vma;
@@ -1572,7 +1573,9 @@ static inline bool is_longterm_pinnable_
if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
return false;
#endif
- return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page));
+ return !(is_device_coherent_page(page) ||
+ is_zone_movable_page(page) ||
+ is_zero_pfn(page_to_pfn(page)));
}
#else
static inline bool is_longterm_pinnable_page(struct page *page)
--- a/mm/memcontrol.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memcontrol.c
@@ -5716,8 +5716,8 @@ out:
* 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
* target for charge migration. if @target is not NULL, the entry is stored
* in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE
- * (so ZONE_DEVICE page and thus not on the lru).
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
+ * thus not on the lru.
* For now we such page is charge like a regular page would be as for all
* intent and purposes it is just special memory taking the place of a
* regular page.
@@ -5755,7 +5755,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_coherent_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
--- a/mm/memory-failure.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memory-failure.c
@@ -1686,12 +1686,16 @@ static int memory_failure_dev_pagemap(un
goto unlock;
}
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
/*
- * TODO: Handle HMM pages which may need coordination
+ * TODO: Handle device pages which may need coordination
* with device-side memory.
*/
goto unlock;
+ default:
+ break;
}
/*
--- a/mm/memremap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memremap.c
@@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap
return ERR_PTR(-EINVAL);
}
break;
+ case MEMORY_DEVICE_COHERENT:
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
--- a/mm/migrate_device.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/migrate_device.c
@@ -518,7 +518,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
* handle_pte_fault()
* do_anonymous_page()
* to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
*/
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -594,11 +594,8 @@ static void migrate_vma_insert_page(stru
page_to_pfn(page));
entry = swp_entry_to_pte(swp_entry);
} else {
- /*
- * For now we only support migrating to un-addressable device
- * memory.
- */
- if (is_zone_device_page(page)) {
+ if (is_zone_device_page(page) &&
+ !is_device_coherent_page(page)) {
pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
goto abort;
}
@@ -701,10 +698,11 @@ void migrate_vma_pages(struct migrate_vm
mapping = page_mapping(page);
- if (is_device_private_page(newpage)) {
+ if (is_device_private_page(newpage) ||
+ is_device_coherent_page(newpage)) {
/*
- * For now only support private anonymous when migrating
- * to un-addressable device memory.
+ * For now only support anonymous memory migrating to
+ * device private or coherent memory.
*/
if (mapping) {
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
--- a/mm/rmap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/rmap.c
@@ -1968,7 +1968,7 @@ static bool try_to_migrate_one(struct fo
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (folio_is_zone_device(folio)) {
+ if (folio_is_device_private(folio)) {
unsigned long pfn = folio_pfn(folio);
swp_entry_t entry;
pte_t swp_pte;
@@ -2131,7 +2131,8 @@ void try_to_migrate(struct folio *folio,
TTU_SYNC)))
return;
- if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+ if (folio_is_zone_device(folio) &&
+ (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
_
Patches currently in -mm which might be from alex.sierra@amd.com are
mm-rename-is_pinnable_pages-to-is_longterm_pinnable_pages.patch
mm-move-page-zone-helpers-from-mmh-to-mmzoneh.patch
mm-add-zone-device-coherent-type-memory-support.patch
mm-handling-non-lru-pages-returned-by-vm_normal_pages.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
drm-amdkfd-add-spm-support-for-svm.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch
tools-add-hmm-gup-tests-for-device-coherent-type.patch
tools-add-selftests-to-hmm-for-cow-in-device-memory.patch
^ permalink raw reply [flat|nested] 5+ messages in thread
* + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch
@ 2022-07-07 19:54 Andrew Morton
0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-07-07 19:54 UTC (permalink / raw)
To: mm-commits, willy, rcampbell, jglisse, jgg, hch, Felix.Kuehling,
david, apopple, alex.sierra, akpm
The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm mm-unstable branch. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-zone-device-coherent-type-memory-support.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: mm: add zone device coherent type memory support
Date: Thu, 7 Jul 2022 14:03:37 -0500
Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI or
CXL). Any page of a process can be migrated to such memory. However, no
one should be allowed to pin such memory so that it can always be evicted.
[hch@lst.de: rebased ontop of the refcount changes, removed is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220707190349.9778-4-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm.h | 4 +++-
include/linux/page_zone.h | 19 +++++++++++++++++++
mm/memcontrol.c | 7 ++++---
mm/memory-failure.c | 8 ++++++--
mm/memremap.c | 10 ++++++++++
mm/migrate_device.c | 16 +++++++---------
mm/rmap.c | 5 +++--
7 files changed, 52 insertions(+), 17 deletions(-)
--- a/include/linux/mm.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/mm.h
@@ -1573,7 +1573,9 @@ static inline bool is_longterm_pinnable_
if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
return false;
#endif
- return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page));
+ return !(is_device_coherent_page(page) ||
+ is_zone_movable_page(page) ||
+ is_zero_pfn(page_to_pfn(page)));
}
#else
static inline bool is_longterm_pinnable_page(struct page *page)
--- a/include/linux/page_zone.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/page_zone.h
@@ -59,6 +59,13 @@
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/mm/hmm.rst.
*
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
@@ -79,6 +86,7 @@
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
@@ -191,4 +199,15 @@ static inline bool is_pci_p2pdma_page(co
page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
}
+static inline bool is_device_coherent_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+ return is_device_coherent_page(&folio->page);
+}
+
#endif /* _PAGE_ZONE_H_ */
--- a/mm/memcontrol.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memcontrol.c
@@ -5715,8 +5715,8 @@ out:
* 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
* target for charge migration. if @target is not NULL, the entry is stored
* in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE
- * (so ZONE_DEVICE page and thus not on the lru).
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
+ * thus not on the lru.
* For now we such page is charge like a regular page would be as for all
* intent and purposes it is just special memory taking the place of a
* regular page.
@@ -5754,7 +5754,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_coherent_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
--- a/mm/memory-failure.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memory-failure.c
@@ -1686,12 +1686,16 @@ static int memory_failure_dev_pagemap(un
goto unlock;
}
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
/*
- * TODO: Handle HMM pages which may need coordination
+ * TODO: Handle device pages which may need coordination
* with device-side memory.
*/
goto unlock;
+ default:
+ break;
}
/*
--- a/mm/memremap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memremap.c
@@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap
return ERR_PTR(-EINVAL);
}
break;
+ case MEMORY_DEVICE_COHERENT:
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
--- a/mm/migrate_device.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/migrate_device.c
@@ -518,7 +518,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
* handle_pte_fault()
* do_anonymous_page()
* to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
*/
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -594,11 +594,8 @@ static void migrate_vma_insert_page(stru
page_to_pfn(page));
entry = swp_entry_to_pte(swp_entry);
} else {
- /*
- * For now we only support migrating to un-addressable device
- * memory.
- */
- if (is_zone_device_page(page)) {
+ if (is_zone_device_page(page) &&
+ !is_device_coherent_page(page)) {
pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
goto abort;
}
@@ -701,10 +698,11 @@ void migrate_vma_pages(struct migrate_vm
mapping = page_mapping(page);
- if (is_device_private_page(newpage)) {
+ if (is_device_private_page(newpage) ||
+ is_device_coherent_page(newpage)) {
/*
- * For now only support private anonymous when migrating
- * to un-addressable device memory.
+ * For now only support anonymous memory migrating to
+ * device private or coherent memory.
*/
if (mapping) {
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
--- a/mm/rmap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/rmap.c
@@ -1968,7 +1968,7 @@ static bool try_to_migrate_one(struct fo
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (folio_is_zone_device(folio)) {
+ if (folio_is_device_private(folio)) {
unsigned long pfn = folio_pfn(folio);
swp_entry_t entry;
pte_t swp_pte;
@@ -2131,7 +2131,8 @@ void try_to_migrate(struct folio *folio,
TTU_SYNC)))
return;
- if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+ if (folio_is_zone_device(folio) &&
+ (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
_
Patches currently in -mm which might be from alex.sierra@amd.com are
mm-rename-is_pinnable_pages-to-is_longterm_pinnable_pages.patch
mm-move-page-zone-helpers-into-new-header-specific-file.patch
mm-add-zone-device-coherent-type-memory-support.patch
mm-handling-non-lru-pages-returned-by-vm_normal_pages.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
drm-amdkfd-add-spm-support-for-svm.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch
tools-add-hmm-gup-tests-for-device-coherent-type.patch
tools-add-selftests-to-hmm-for-cow-in-device-memory.patch
^ permalink raw reply [flat|nested] 5+ messages in thread
* + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch
@ 2022-05-31 20:22 Andrew Morton
0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-05-31 20:22 UTC (permalink / raw)
To: mm-commits, willy, rcampbell, jglisse, jgg, hch, Felix.Kuehling,
david, apopple, alex.sierra, akpm
The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm mm-unstable branch. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-zone-device-coherent-type-memory-support.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: mm: add zone device coherent type memory support
Date: Tue, 31 May 2022 15:00:29 -0500
Patch series "Add MEMORY_DEVICE_COHERENT for coherent device memory mapping", v5.
This patch series introduces MEMORY_DEVICE_COHERENT, a type of memory
owned by a device that can be mapped into CPU page tables like
MEMORY_DEVICE_GENERIC and can also be migrated like MEMORY_DEVICE_PRIVATE.
This patch series is mostly self-contained except for a few places where
it needs to update other subsystems to handle the new memory type.
System stability and performance are not affected according to our ongoing
testing, including xfstests.
How it works: The system BIOS advertises the GPU device memory (aka VRAM)
as SPM (special purpose memory) in the UEFI system address map.
The amdgpu driver registers the memory with devmap as
MEMORY_DEVICE_COHERENT using devm_memremap_pages. The initial user for
this hardware page migration capability is the Frontier supercomputer
project. This functionality is not AMD-specific. We expect other GPU
vendors to find this functionality useful, and possibly other hardware
types in the future.
Our test nodes in the lab are similar to the Frontier configuration, with
.5 TB of system memory plus 256 GB of device memory split across 4 GPUs,
all in a single coherent address space. Page migration is expected to
improve application efficiency significantly. We will report empirical
results as they become available.
Coherent device type pages at gup are now migrated back to system memory
if they are being pinned long-term (FOLL_LONGTERM). The reason is, that
long-term pinning would interfere with the device memory manager owning
the device-coherent pages (e.g. evictions in TTM). These series
incorporate Alistair Popple patches to do this migration from
pin_user_pages() calls. hmm_gup_test has been added to hmm-test to test
different get user pages calls.
This series includes handling of device-managed anonymous pages returned
by vm_normal_pages. Although they behave like normal pages for purposes
of mapping in CPU page tables and for COW, they do not support LRU lists,
NUMA migration or THP.
We also introduce a FOLL_LRU flag that adds the same behaviour to
follow_page and related APIs, to allow callers to specify that they expect
to put pages on an LRU list.
This patch (od 13):
Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI or
CXL). Any page of a process can be migrated to such memory. However, no
one should be allowed to pin such memory so that it can always be evicted.
[hch@lst.de: rebased ontop of the refcount changes, removed is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220531200041.24904-1-alex.sierra@amd.com
Link: https://lkml.kernel.org/r/20220531200041.24904-2-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memremap.h | 19 +++++++++++++++++++
mm/memcontrol.c | 7 ++++---
mm/memory-failure.c | 8 ++++++--
mm/memremap.c | 10 ++++++++++
mm/migrate_device.c | 16 +++++++---------
mm/rmap.c | 5 +++--
6 files changed, 49 insertions(+), 16 deletions(-)
--- a/include/linux/memremap.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/memremap.h
@@ -41,6 +41,13 @@ struct vmem_altmap {
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/vm/hmm.rst.
*
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
@@ -61,6 +68,7 @@ struct vmem_altmap {
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
@@ -143,6 +151,17 @@ static inline bool folio_is_device_priva
return is_device_private_page(&folio->page);
}
+static inline bool is_device_coherent_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+ return is_device_coherent_page(&folio->page);
+}
+
static inline bool is_pci_p2pdma_page(const struct page *page)
{
return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
--- a/mm/memcontrol.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memcontrol.c
@@ -5665,8 +5665,8 @@ out:
* 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
* target for charge migration. if @target is not NULL, the entry is stored
* in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE
- * (so ZONE_DEVICE page and thus not on the lru).
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
+ * thus not on the lru.
* For now we such page is charge like a regular page would be as for all
* intent and purposes it is just special memory taking the place of a
* regular page.
@@ -5704,7 +5704,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_coherent_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
--- a/mm/memory-failure.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memory-failure.c
@@ -1683,12 +1683,16 @@ static int memory_failure_dev_pagemap(un
goto unlock;
}
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
/*
- * TODO: Handle HMM pages which may need coordination
+ * TODO: Handle device pages which may need coordination
* with device-side memory.
*/
goto unlock;
+ default:
+ break;
}
/*
--- a/mm/memremap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memremap.c
@@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap
return ERR_PTR(-EINVAL);
}
break;
+ case MEMORY_DEVICE_COHERENT:
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
--- a/mm/migrate_device.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/migrate_device.c
@@ -518,7 +518,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
* handle_pte_fault()
* do_anonymous_page()
* to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
*/
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -594,11 +594,8 @@ static void migrate_vma_insert_page(stru
page_to_pfn(page));
entry = swp_entry_to_pte(swp_entry);
} else {
- /*
- * For now we only support migrating to un-addressable device
- * memory.
- */
- if (is_zone_device_page(page)) {
+ if (is_zone_device_page(page) &&
+ !is_device_coherent_page(page)) {
pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
goto abort;
}
@@ -701,10 +698,11 @@ void migrate_vma_pages(struct migrate_vm
mapping = page_mapping(page);
- if (is_device_private_page(newpage)) {
+ if (is_device_private_page(newpage) ||
+ is_device_coherent_page(newpage)) {
/*
- * For now only support private anonymous when migrating
- * to un-addressable device memory.
+ * For now only support anonymous memory migrating to
+ * device private or coherent memory.
*/
if (mapping) {
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
--- a/mm/rmap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/rmap.c
@@ -1957,7 +1957,7 @@ static bool try_to_migrate_one(struct fo
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (folio_is_zone_device(folio)) {
+ if (folio_is_device_private(folio)) {
unsigned long pfn = folio_pfn(folio);
swp_entry_t entry;
pte_t swp_pte;
@@ -2131,7 +2131,8 @@ void try_to_migrate(struct folio *folio,
TTU_SYNC)))
return;
- if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+ if (folio_is_zone_device(folio) &&
+ (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
_
Patches currently in -mm which might be from alex.sierra@amd.com are
mm-add-zone-device-coherent-type-memory-support.patch
mm-handling-non-lru-pages-returned-by-vm_normal_pages.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
drm-amdkfd-add-spm-support-for-svm.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch
tools-add-hmm-gup-tests-for-device-coherent-type.patch
tools-add-selftests-to-hmm-for-cow-in-device-memory.patch
^ permalink raw reply [flat|nested] 5+ messages in thread
* + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch
@ 2022-05-31 17:32 Andrew Morton
0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-05-31 17:32 UTC (permalink / raw)
To: mm-commits, willy, rcampbell, jglisse, jgg, hch, Felix.Kuehling,
felix.kuehling, david, apopple, alex.sierra, akpm
The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm mm-unstable branch. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-zone-device-coherent-type-memory-support.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: mm: add zone device coherent type memory support
Date: Tue, 31 May 2022 10:56:17 -0500
Patch series "Add MEMORY_DEVICE_COHERENT for coherent device memory mapping", v4.
This patch series introduces MEMORY_DEVICE_COHERENT, a type of memory
owned by a device that can be mapped into CPU page tables like
MEMORY_DEVICE_GENERIC and can also be migrated like MEMORY_DEVICE_PRIVATE.
This patch series is mostly self-contained except for a few places where
it needs to update other subsystems to handle the new memory type.
System stability and performance are not affected according to our ongoing
testing, including xfstests.
How it works: The system BIOS advertises the GPU device memory (aka VRAM)
as SPM (special purpose memory) in the UEFI system address map.
The amdgpu driver registers the memory with devmap as
MEMORY_DEVICE_COHERENT using devm_memremap_pages. The initial user for
this hardware page migration capability is the Frontier supercomputer
project. This functionality is not AMD-specific. We expect other GPU
vendors to find this functionality useful, and possibly other hardware
types in the future.
Our test nodes in the lab are similar to the Frontier configuration, with
.5 TB of system memory plus 256 GB of device memory split across 4 GPUs,
all in a single coherent address space. Page migration is expected to
improve application efficiency significantly. We will report empirical
results as they become available.
Coherent device type pages at gup are now migrated back to system memory
if they are being pinned long-term (FOLL_LONGTERM). The reason is, that
long-term pinning would interfere with the device memory manager owning
the device-coherent pages (e.g. evictions in TTM). These series
incorporate Alistair Popple patches to do this migration from
pin_user_pages() calls. hmm_gup_test has been added to hmm-test to test
different get user pages calls.
This series includes handling of device-managed anonymous pages returned
by vm_normal_pages. Although they behave like normal pages for purposes
of mapping in CPU page tables and for COW, they do not support LRU lists,
NUMA migration or THP.
We also introduced a FOLL_LRU flag that adds the same behaviour to
follow_page and related APIs, to allow callers to specify that they expect
to put pages on an LRU list.
This patch (of 13):
Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI or
CXL). Any page of a process can be migrated to such memory. However, no
one should be allowed to pin such memory so that it can always be evicted.
[hch@lst.de: rebase on top of the refcount changes, remove is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220531155629.20057-1-alex.sierra@amd.com
Link: https://lkml.kernel.org/r/20220531155629.20057-2-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memremap.h | 19 +++++++++++++++++++
mm/memcontrol.c | 7 ++++---
mm/memory-failure.c | 8 ++++++--
mm/memremap.c | 10 ++++++++++
mm/migrate_device.c | 16 +++++++---------
mm/rmap.c | 5 +++--
6 files changed, 49 insertions(+), 16 deletions(-)
--- a/include/linux/memremap.h~mm-add-zone-device-coherent-type-memory-support
+++ a/include/linux/memremap.h
@@ -41,6 +41,13 @@ struct vmem_altmap {
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/vm/hmm.rst.
*
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
@@ -61,6 +68,7 @@ struct vmem_altmap {
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
@@ -143,6 +151,17 @@ static inline bool folio_is_device_priva
return is_device_private_page(&folio->page);
}
+static inline bool is_device_coherent_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+ return is_device_coherent_page(&folio->page);
+}
+
static inline bool is_pci_p2pdma_page(const struct page *page)
{
return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
--- a/mm/memcontrol.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memcontrol.c
@@ -5665,8 +5665,8 @@ out:
* 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
* target for charge migration. if @target is not NULL, the entry is stored
* in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE
- * (so ZONE_DEVICE page and thus not on the lru).
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
+ * thus not on the lru.
* For now we such page is charge like a regular page would be as for all
* intent and purposes it is just special memory taking the place of a
* regular page.
@@ -5704,7 +5704,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_coherent_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
--- a/mm/memory-failure.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memory-failure.c
@@ -1683,12 +1683,16 @@ static int memory_failure_dev_pagemap(un
goto unlock;
}
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
/*
- * TODO: Handle HMM pages which may need coordination
+ * TODO: Handle device pages which may need coordination
* with device-side memory.
*/
goto unlock;
+ default:
+ break;
}
/*
--- a/mm/memremap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/memremap.c
@@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap
return ERR_PTR(-EINVAL);
}
break;
+ case MEMORY_DEVICE_COHERENT:
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
--- a/mm/migrate_device.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/migrate_device.c
@@ -518,7 +518,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
* handle_pte_fault()
* do_anonymous_page()
* to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
*/
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -594,11 +594,8 @@ static void migrate_vma_insert_page(stru
page_to_pfn(page));
entry = swp_entry_to_pte(swp_entry);
} else {
- /*
- * For now we only support migrating to un-addressable device
- * memory.
- */
- if (is_zone_device_page(page)) {
+ if (is_zone_device_page(page) &&
+ !is_device_coherent_page(page)) {
pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
goto abort;
}
@@ -701,10 +698,11 @@ void migrate_vma_pages(struct migrate_vm
mapping = page_mapping(page);
- if (is_device_private_page(newpage)) {
+ if (is_device_private_page(newpage) ||
+ is_device_coherent_page(newpage)) {
/*
- * For now only support private anonymous when migrating
- * to un-addressable device memory.
+ * For now only support anonymous memory migrating to
+ * device private or coherent memory.
*/
if (mapping) {
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
--- a/mm/rmap.c~mm-add-zone-device-coherent-type-memory-support
+++ a/mm/rmap.c
@@ -1957,7 +1957,7 @@ static bool try_to_migrate_one(struct fo
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (folio_is_zone_device(folio)) {
+ if (folio_is_device_private(folio)) {
unsigned long pfn = folio_pfn(folio);
swp_entry_t entry;
pte_t swp_pte;
@@ -2131,7 +2131,8 @@ void try_to_migrate(struct folio *folio,
TTU_SYNC)))
return;
- if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+ if (folio_is_zone_device(folio) &&
+ (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
_
Patches currently in -mm which might be from alex.sierra@amd.com are
mm-add-zone-device-coherent-type-memory-support.patch
mm-handling-non-lru-pages-returned-by-vm_normal_pages.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
drm-amdkfd-add-spm-support-for-svm.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch
tools-add-hmm-gup-tests-for-device-coherent-type.patch
tools-add-selftests-to-hmm-for-cow-in-device-memory.patch
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2022-07-15 23:25 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-06-29 23:33 + mm-add-zone-device-coherent-type-memory-support.patch added to mm-unstable branch Andrew Morton
-- strict thread matches above, loose matches on Subject: below --
2022-07-15 23:25 Andrew Morton
2022-07-07 19:54 Andrew Morton
2022-05-31 20:22 Andrew Morton
2022-05-31 17:32 Andrew Morton
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.