The patch titled
Subject: mm/device-public-memory: device memory cache coherent with CPU
has been removed from the -mm tree. Its filename was
mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm/device-public-memory: device memory cache coherent with CPU
Platform with advance system bus (like CAPI or CCIX) allow device memory
to be accessible from CPU in a cache coherent fashion. Add a new type of
ZONE_DEVICE to represent such memory. The use case are the same as for
the un-addressable device memory but without all the corners cases.
Link: http://lkml.kernel.org/r/20170817000548.32038-19-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Aneesh Kumar <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Balbir Singh <bsingharora@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: Sherry Cheung <SCheung@xxxxxxxxxx>
Cc: Subhash Gutti <sgutti@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: Bob Liu <liubo95@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/task_mmu.c | 2 -
include/linux/hmm.h | 4 +-
include/linux/ioport.h | 1
include/linux/memremap.h | 21 ++++++++++++++
include/linux/mm.h | 20 ++++++++-----
kernel/memremap.c | 8 ++---
mm/Kconfig | 11 +++++++
mm/gup.c | 7 ++++
mm/hmm.c | 4 +-
mm/madvise.c | 2 -
mm/memcontrol.c | 12 ++++----
mm/memory.c | 46 +++++++++++++++++++++++++++---
mm/migrate.c | 55 ++++++++++++++++++++++++-------------
mm/swap.c | 11 +++++++
14 files changed, 158 insertions(+), 46 deletions(-)
diff -puN fs/proc/task_mmu.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/fs/proc/task_mmu.c
@@ -1267,7 +1267,7 @@ static pagemap_entry_t pte_to_pagemap_en
if (pm->show_pfn)
frame = pte_pfn(pte);
flags |= PM_PRESENT;
- page = vm_normal_page(vma, addr, pte);
+ page = _vm_normal_page(vma, addr, pte, true);
if (pte_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
} else if (is_swap_pte(pte)) {
diff -puN include/linux/hmm.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 include/linux/hmm.h
--- a/include/linux/hmm.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/include/linux/hmm.h
@@ -327,7 +327,7 @@ int hmm_vma_fault(struct vm_area_struct
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
struct hmm_devmem;
struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
@@ -494,7 +494,7 @@ struct hmm_device {
*/
struct hmm_device *hmm_device_new(void *drvdata);
void hmm_device_put(struct hmm_device *hmm_device);
-#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
/* Below are for HMM internal use only! Not to be used by device driver! */
diff -puN include/linux/ioport.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 include/linux/ioport.h
--- a/include/linux/ioport.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/include/linux/ioport.h
@@ -131,6 +131,7 @@ enum {
IORES_DESC_PERSISTENT_MEMORY = 4,
IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5,
IORES_DESC_DEVICE_PRIVATE_MEMORY = 6,
+ IORES_DESC_DEVICE_PUBLIC_MEMORY = 7,
};
/* helpers to define resources */
diff -puN include/linux/memremap.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 include/linux/memremap.h
--- a/include/linux/memremap.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/include/linux/memremap.h
@@ -57,10 +57,18 @@ static inline struct vmem_altmap *to_vme
*
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/vm/hmm.txt.
+ *
+ * MEMORY_DEVICE_PUBLIC:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is use on platform that have an advance system bus (like CAPI or CCIX). 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 allow to pin such memory so that it can always be evicted.
*/
enum memory_type {
MEMORY_DEVICE_HOST = 0,
MEMORY_DEVICE_PRIVATE,
+ MEMORY_DEVICE_PUBLIC,
};
/*
@@ -92,6 +100,8 @@ enum memory_type {
* The page_free() callback is called once the page refcount reaches 1
* (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug.
* This allows the device driver to implement its own memory management.)
+ *
+ * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter.
*/
typedef int (*dev_page_fault_t)(struct vm_area_struct *vma,
unsigned long addr,
@@ -134,6 +144,12 @@ static inline bool is_device_private_pag
return is_zone_device_page(page) &&
page->pgmap->type == MEMORY_DEVICE_PRIVATE;
}
+
+static inline bool is_device_public_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_PUBLIC;
+}
#else
static inline void *devm_memremap_pages(struct device *dev,
struct resource *res, struct percpu_ref *ref,
@@ -157,6 +173,11 @@ static inline bool is_device_private_pag
{
return false;
}
+
+static inline bool is_device_public_page(const struct page *page)
+{
+ return false;
+}
#endif
/**
diff -puN include/linux/mm.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 include/linux/mm.h
--- a/include/linux/mm.h~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/include/linux/mm.h
@@ -800,15 +800,16 @@ static inline bool is_zone_device_page(c
}
#endif
-#ifdef CONFIG_DEVICE_PRIVATE
-void put_zone_device_private_page(struct page *page);
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+void put_zone_device_private_or_public_page(struct page *page);
#else
-static inline void put_zone_device_private_page(struct page *page)
+static inline void put_zone_device_private_or_public_page(struct page *page)
{
}
-#endif
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
static inline bool is_device_private_page(const struct page *page);
+static inline bool is_device_public_page(const struct page *page);
DECLARE_STATIC_KEY_FALSE(device_private_key);
@@ -834,8 +835,9 @@ static inline void put_page(struct page
* include/linux/memremap.h and HMM for details.
*/
if (static_branch_unlikely(&device_private_key) &&
- unlikely(is_device_private_page(page))) {
- put_zone_device_private_page(page);
+ unlikely(is_device_private_page(page) ||
+ is_device_public_page(page))) {
+ put_zone_device_private_or_public_page(page);
return;
}
@@ -1224,8 +1226,10 @@ struct zap_details {
pgoff_t last_index; /* Highest page->index to unmap */
};
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
- pte_t pte);
+struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte, bool with_public_device);
+#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false)
+
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd);
diff -puN kernel/memremap.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 kernel/memremap.c
--- a/kernel/memremap.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/kernel/memremap.c
@@ -501,8 +501,8 @@ struct vmem_altmap *to_vmem_altmap(unsig
#endif /* CONFIG_ZONE_DEVICE */
-#ifdef CONFIG_DEVICE_PRIVATE
-void put_zone_device_private_page(struct page *page)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+void put_zone_device_private_or_public_page(struct page *page)
{
int count = page_ref_dec_return(page);
@@ -522,5 +522,5 @@ void put_zone_device_private_page(struct
} else if (!count)
__put_page(page);
}
-EXPORT_SYMBOL(put_zone_device_private_page);
-#endif /* CONFIG_DEVICE_PRIVATE */
+EXPORT_SYMBOL(put_zone_device_private_or_public_page);
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
diff -puN mm/Kconfig~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/Kconfig
--- a/mm/Kconfig~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/Kconfig
@@ -720,12 +720,23 @@ config HMM_MIRROR
config DEVICE_PRIVATE
bool "Unaddressable device memory (GPU memory, ...)"
depends on ARCH_HAS_HMM
+ select HMM
help
Allows creation of struct pages to represent unaddressable device
memory; i.e., memory that is only accessible from the device (or
group of devices). You likely also want to select HMM_MIRROR.
+config DEVICE_PUBLIC
+ bool "Addressable device memory (like GPU memory)"
+ depends on ARCH_HAS_HMM
+ select HMM
+
+ help
+ Allows creation of struct pages to represent addressable device
+ memory; i.e., memory that is accessible from both the device and
+ the CPU
+
config FRAME_VECTOR
bool
diff -puN mm/gup.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/gup.c
--- a/mm/gup.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/gup.c
@@ -456,6 +456,13 @@ static int get_gate_page(struct mm_struc
if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
goto unmap;
*page = pte_page(*pte);
+
+ /*
+ * This should never happen (a device public page in the gate
+ * area).
+ */
+ if (is_device_public_page(*page))
+ goto unmap;
}
get_page(*page);
out:
diff -puN mm/hmm.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/hmm.c
--- a/mm/hmm.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/hmm.c
@@ -737,7 +737,7 @@ EXPORT_SYMBOL(hmm_vma_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
unsigned long addr)
{
@@ -1177,4 +1177,4 @@ static int __init hmm_init(void)
}
device_initcall(hmm_init);
-#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
diff -puN mm/madvise.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/madvise.c
--- a/mm/madvise.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/madvise.c
@@ -355,7 +355,7 @@ static int madvise_free_pte_range(pmd_t
continue;
}
- page = vm_normal_page(vma, addr, ptent);
+ page = _vm_normal_page(vma, addr, ptent, true);
if (!page)
continue;
diff -puN mm/memcontrol.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/memcontrol.c
--- a/mm/memcontrol.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/memcontrol.c
@@ -4623,10 +4623,11 @@ 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). 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.
+ * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PUBLIC
+ * or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page 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.
*
* See Documentations/vm/hmm.txt and include/linux/hmm.h
*
@@ -4657,7 +4658,8 @@ static enum mc_target_type get_mctgt_typ
*/
if (page->mem_cgroup == mc.from) {
ret = MC_TARGET_PAGE;
- if (is_device_private_page(page))
+ if (is_device_private_page(page) ||
+ is_device_public_page(page))
ret = MC_TARGET_DEVICE;
if (target)
target->page = page;
diff -puN mm/memory.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/memory.c
--- a/mm/memory.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/memory.c
@@ -818,8 +818,8 @@ static void print_bad_pte(struct vm_area
#else
# define HAVE_PTE_SPECIAL 0
#endif
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
- pte_t pte)
+struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte, bool with_public_device)
{
unsigned long pfn = pte_pfn(pte);
@@ -830,8 +830,31 @@ struct page *vm_normal_page(struct vm_ar
return vma->vm_ops->find_special_page(vma, addr);
if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
- if (!is_zero_pfn(pfn))
- print_bad_pte(vma, addr, pte, NULL);
+ if (is_zero_pfn(pfn))
+ return NULL;
+
+ /*
+ * Device public pages are special pages (they are ZONE_DEVICE
+ * pages but different from persistent memory). They behave
+ * allmost like normal pages. The difference is that they are
+ * not on the lru and thus should never be involve with any-
+ * thing that involve lru manipulation (mlock, numa balancing,
+ * ...).
+ *
+ * This is why we still want to return NULL for such page from
+ * vm_normal_page() so that we do not have to special case all
+ * call site of vm_normal_page().
+ */
+ if (likely(pfn < highest_memmap_pfn)) {
+ struct page *page = pfn_to_page(pfn);
+
+ if (is_device_public_page(page)) {
+ if (with_public_device)
+ return page;
+ return NULL;
+ }
+ }
+ print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
@@ -1012,6 +1035,19 @@ copy_one_pte(struct mm_struct *dst_mm, s
get_page(page);
page_dup_rmap(page, false);
rss[mm_counter(page)]++;
+ } else if (pte_devmap(pte)) {
+ page = pte_page(pte);
+
+ /*
+ * Cache coherent device memory behave like regular page and
+ * not like persistent memory page. For more informations see
+ * MEMORY_DEVICE_CACHE_COHERENT in memory_hotplug.h
+ */
+ if (is_device_public_page(page)) {
+ get_page(page);
+ page_dup_rmap(page, false);
+ rss[mm_counter(page)]++;
+ }
}
out_set_pte:
@@ -1267,7 +1303,7 @@ again:
if (pte_present(ptent)) {
struct page *page;
- page = vm_normal_page(vma, addr, ptent);
+ page = _vm_normal_page(vma, addr, ptent, true);
if (unlikely(details) && page) {
/*
* unmap_shared_mapping_pages() wants to
diff -puN mm/migrate.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/migrate.c
--- a/mm/migrate.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/migrate.c
@@ -36,6 +36,7 @@
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
+#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/balloon_compaction.h>
@@ -239,10 +240,14 @@ static bool remove_migration_pte(struct
if (is_write_migration_entry(entry))
pte = maybe_mkwrite(pte, vma);
- if (unlikely(is_zone_device_page(new)) &&
- is_device_private_page(new)) {
- entry = make_device_private_entry(new, pte_write(pte));
- pte = swp_entry_to_pte(entry);
+ if (unlikely(is_zone_device_page(new))) {
+ if (is_device_private_page(new)) {
+ entry = make_device_private_entry(new, pte_write(pte));
+ pte = swp_entry_to_pte(entry);
+ } else if (is_device_public_page(new)) {
+ pte = pte_mkdevmap(pte);
+ flush_dcache_page(new);
+ }
} else
flush_dcache_page(new);
@@ -437,12 +442,11 @@ int migrate_page_move_mapping(struct add
void **pslot;
/*
- * ZONE_DEVICE pages have 1 refcount always held by their device
- *
- * Note that DAX memory will never reach that point as it does not have
- * the MEMORY_DEVICE_ALLOW_MIGRATE flag set (see memory_hotplug.h).
+ * Device public or private pages have an extra refcount as they are
+ * ZONE_DEVICE pages.
*/
- expected_count += is_zone_device_page(page);
+ expected_count += is_device_private_page(page);
+ expected_count += is_device_public_page(page);
if (!mapping) {
/* Anonymous page without mapping */
@@ -2123,7 +2127,6 @@ out_unlock:
#endif /* CONFIG_NUMA */
-
struct migrate_vma {
struct vm_area_struct *vma;
unsigned long *dst;
@@ -2263,7 +2266,7 @@ again:
pfn = 0;
goto next;
}
- page = vm_normal_page(migrate->vma, addr, pte);
+ page = _vm_normal_page(migrate->vma, addr, pte, true);
mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
}
@@ -2406,10 +2409,19 @@ static bool migrate_vma_check_page(struc
if (is_device_private_page(page))
return true;
- /* Other ZONE_DEVICE memory type are not supported */
- return false;
+ /*
+ * Only allow device public page to be migrated and account for
+ * the extra reference count imply by ZONE_DEVICE pages.
+ */
+ if (!is_device_public_page(page))
+ return false;
+ extra++;
}
+ /* For file back page */
+ if (page_mapping(page))
+ extra += 1 + page_has_private(page);
+
if ((page_count(page) - extra) > page_mapcount(page))
return false;
@@ -2647,11 +2659,18 @@ static void migrate_vma_insert_page(stru
*/
__SetPageUptodate(page);
- if (is_zone_device_page(page) && is_device_private_page(page)) {
- swp_entry_t swp_entry;
+ if (is_zone_device_page(page)) {
+ if (is_device_private_page(page)) {
+ swp_entry_t swp_entry;
- swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
- entry = swp_entry_to_pte(swp_entry);
+ swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
+ entry = swp_entry_to_pte(swp_entry);
+ } else if (is_device_public_page(page)) {
+ entry = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
+ if (vma->vm_flags & VM_WRITE)
+ entry = pte_mkwrite(pte_mkdirty(entry));
+ entry = pte_mkdevmap(entry);
+ }
} else {
entry = mk_pte(page, vma->vm_page_prot);
if (vma->vm_flags & VM_WRITE)
@@ -2768,7 +2787,7 @@ static void migrate_vma_pages(struct mig
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
continue;
}
- } else {
+ } else if (!is_device_public_page(newpage)) {
/*
* Other types of ZONE_DEVICE page are not
* supported.
diff -puN mm/swap.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5 mm/swap.c
--- a/mm/swap.c~mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5
+++ a/mm/swap.c
@@ -765,6 +765,17 @@ void release_pages(struct page **pages,
if (is_huge_zero_page(page))
continue;
+ /* Device public page can not be huge page */
+ if (is_device_public_page(page)) {
+ if (locked_pgdat) {
+ spin_unlock_irqrestore(&locked_pgdat->lru_lock,
+ flags);
+ locked_pgdat = NULL;
+ }
+ put_zone_device_private_or_public_page(page);
+ continue;
+ }
+
page = compound_head(page);
if (!put_page_testzero(page))
continue;
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
--
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
