The patch titled
Subject: mm: add zone device coherent type memory support
has been added to the -mm tree. Its filename is
mm-add-zone-device-coherent-type-memory-support.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-add-zone-device-coherent-type-memory-support.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-add-zone-device-coherent-type-memory-support.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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Christoph Hellwig <hch@xxxxxx>
Subject: mm: add zone device coherent type memory support
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@xxxxxx: rebased ontop of the refcount changes, removed is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220210072828.2930359-16-hch@xxxxxx
Signed-off-by: Alex Sierra <alex.sierra@xxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Acked-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Reviewed-by: Alistair Popple <apopple@xxxxxxxxxx>
Tested-by: "Sierra Guiza, Alejandro (Alex)" <alex.sierra@xxxxxxx>
Cc: Alex Deucher <alexander.deucher@xxxxxxx>
Cc: Ben Skeggs <bskeggs@xxxxxxxxxx>
Cc: Chaitanya Kulkarni <kch@xxxxxxxxxx>
Cc: Christian Knig <christian.koenig@xxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Karol Herbst <kherbst@xxxxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Lyude Paul <lyude@xxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: "Pan, Xinhui" <Xinhui.Pan@xxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- 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,
@@ -138,6 +146,12 @@ static inline bool is_device_private_pag
page->pgmap->type == MEMORY_DEVICE_PRIVATE;
}
+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 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
@@ -5689,8 +5689,8 @@ 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.
@@ -5724,7 +5724,8 @@ 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
@@ -1619,12 +1619,16 @@ 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
@@ -334,6 +334,16 @@ 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
@@ -494,7 +494,7 @@ 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,
@@ -570,11 +570,8 @@ 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;
}
@@ -677,10 +674,11 @@ 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
@@ -1852,7 +1852,7 @@ static bool try_to_migrate_one(struct pa
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (is_zone_device_page(page)) {
+ if (is_device_private_page(page)) {
unsigned long pfn = page_to_pfn(page);
swp_entry_t entry;
pte_t swp_pte;
@@ -1999,7 +1999,8 @@ void try_to_migrate(struct page *page, e
TTU_SYNC)))
return;
- if (is_zone_device_page(page) && !is_device_private_page(page))
+ if (is_zone_device_page(page) &&
+ (!is_device_private_page(page) && !is_device_coherent_page(page)))
return;
/*
_
Patches currently in -mm which might be from hch@xxxxxx are
mm-unexport-page_init_poison.patch
mm-remove-a-pointless-config_zone_device-check-in-memremap_pages.patch
mm-remove-the-__kernel__-guard-from-linux-mmh.patch
mm-remove-pointless-includes-from-linux-hmmh.patch
mm-move-free_devmap_managed_page-to-memremapc.patch
mm-simplify-freeing-of-devmap-managed-pages.patch
mm-dont-include-linux-memremaph-in-linux-mmh.patch
mm-remove-the-extra-zone_device-struct-page-refcount.patch
fsdax-depend-on-zone_device-fs_dax_limited.patch
mm-generalize-the-pgmap-based-page_free-infrastructure.patch
mm-refactor-check_and_migrate_movable_pages.patch
mm-refactor-the-zone_device-handling-in-migrate_vma_insert_page.patch
mm-refactor-the-zone_device-handling-in-migrate_vma_pages.patch
mm-move-the-migrate_vma_-device-migration-code-into-its-own-file.patch
mm-build-migrate_vma_-for-all-configs-with-zone_device-support.patch
mm-add-zone-device-coherent-type-memory-support.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
