[WHY]
Have a cleaner way to expose all page zone helpers in one header
file, rather than split them between mm.h and memremap.h files.
Signed-off-by: Alex Sierra <alex.sierra@xxxxxxx>
---
drivers/infiniband/core/rw.c | 1 -
drivers/nvme/target/io-cmd-bdev.c | 1 -
include/linux/memremap.h | 113 +----------------
include/linux/mm.h | 79 +-----------
include/linux/page_zone.h | 194 ++++++++++++++++++++++++++++++
mm/memcontrol.c | 1 -
6 files changed, 196 insertions(+), 193 deletions(-)
create mode 100644 include/linux/page_zone.h
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 4d98f931a13d..5a3bd41b331c 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -2,7 +2,6 @@
/*
* Copyright (c) 2016 HGST, a Western Digital Company.
*/
-#include <linux/memremap.h>
#include <linux/moduleparam.h>
#include <linux/slab.h>
#include <linux/pci-p2pdma.h>
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 27a72504d31c..16a8b7665fe4 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -6,7 +6,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
-#include <linux/memremap.h>
#include <linux/module.h>
#include "nvmet.h"
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 8af304f6b504..0f22f6f42e7d 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -2,70 +2,14 @@
#ifndef _LINUX_MEMREMAP_H_
#define _LINUX_MEMREMAP_H_
-#include <linux/mm.h>
#include <linux/range.h>
#include <linux/ioport.h>
#include <linux/percpu-refcount.h>
+#include <linux/page_zone.h>
struct resource;
struct device;
-/**
- * struct vmem_altmap - pre-allocated storage for vmemmap_populate
- * @base_pfn: base of the entire dev_pagemap mapping
- * @reserve: pages mapped, but reserved for driver use (relative to @base)
- * @free: free pages set aside in the mapping for memmap storage
- * @align: pages reserved to meet allocation alignments
- * @alloc: track pages consumed, private to vmemmap_populate()
- */
-struct vmem_altmap {
- unsigned long base_pfn;
- const unsigned long end_pfn;
- const unsigned long reserve;
- unsigned long free;
- unsigned long align;
- unsigned long alloc;
-};
-
-/*
- * Specialize ZONE_DEVICE memory into multiple types each has a different
- * usage.
- *
- * MEMORY_DEVICE_PRIVATE:
- * Device memory that is not directly addressable by the CPU: CPU can neither
- * read nor write private memory. In this case, we do still have struct pages
- * backing the device memory. Doing so simplifies the implementation, but it is
- * important to remember that there are certain points at which the struct page
- * must be treated as an opaque object, rather than a "normal" struct page.
- *
- * A more complete discussion of unaddressable memory may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.rst.
- *
- * 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
- * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
- * wakeup event whenever a page is unpinned and becomes idle. This
- * wakeup is used to coordinate physical address space management (ex:
- * fs truncate/hole punch) vs pinned pages (ex: device dma).
- *
- * MEMORY_DEVICE_GENERIC:
- * Host memory that has similar access semantics as System RAM i.e. DMA
- * coherent and supports page pinning. This is for example used by DAX devices
- * that expose memory using a character device.
- *
- * MEMORY_DEVICE_PCI_P2PDMA:
- * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
- * transactions.
- */
-enum memory_type {
- /* 0 is reserved to catch uninitialized type fields */
- MEMORY_DEVICE_PRIVATE = 1,
- MEMORY_DEVICE_FS_DAX,
- MEMORY_DEVICE_GENERIC,
- MEMORY_DEVICE_PCI_P2PDMA,
-};
-
struct dev_pagemap_ops {
/*
* Called once the page refcount reaches 0. The reference count will be
@@ -83,42 +27,6 @@ struct dev_pagemap_ops {
#define PGMAP_ALTMAP_VALID (1 << 0)
-/**
- * struct dev_pagemap - metadata for ZONE_DEVICE mappings
- * @altmap: pre-allocated/reserved memory for vmemmap allocations
- * @ref: reference count that pins the devm_memremap_pages() mapping
- * @done: completion for @ref
- * @type: memory type: see MEMORY_* in memory_hotplug.h
- * @flags: PGMAP_* flags to specify defailed behavior
- * @vmemmap_shift: structural definition of how the vmemmap page metadata
- * is populated, specifically the metadata page order.
- * A zero value (default) uses base pages as the vmemmap metadata
- * representation. A bigger value will set up compound struct pages
- * of the requested order value.
- * @ops: method table
- * @owner: an opaque pointer identifying the entity that manages this
- * instance. Used by various helpers to make sure that no
- * foreign ZONE_DEVICE memory is accessed.
- * @nr_range: number of ranges to be mapped
- * @range: range to be mapped when nr_range == 1
- * @ranges: array of ranges to be mapped when nr_range > 1
- */
-struct dev_pagemap {
- struct vmem_altmap altmap;
- struct percpu_ref ref;
- struct completion done;
- enum memory_type type;
- unsigned int flags;
- unsigned long vmemmap_shift;
- const struct dev_pagemap_ops *ops;
- void *owner;
- int nr_range;
- union {
- struct range range;
- struct range ranges[0];
- };
-};
-
static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
{
if (pgmap->flags & PGMAP_ALTMAP_VALID)
@@ -131,25 +39,6 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap)
return 1 << pgmap->vmemmap_shift;
}
-static inline bool is_device_private_page(const struct page *page)
-{
- return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
- is_zone_device_page(page) &&
- page->pgmap->type == MEMORY_DEVICE_PRIVATE;
-}
-
-static inline bool folio_is_device_private(const struct folio *folio)
-{
- return is_device_private_page(&folio->page);
-}
-
-static inline bool is_pci_p2pdma_page(const struct page *page)
-{
- return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
- is_zone_device_page(page) &&
- page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
-}
-
#ifdef CONFIG_ZONE_DEVICE
void *memremap_pages(struct dev_pagemap *pgmap, int nid);
void memunmap_pages(struct dev_pagemap *pgmap);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3b31b33bd5be..e551616cd208 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -28,6 +28,7 @@
#include <linux/sched.h>
#include <linux/pgtable.h>
#include <linux/kasan.h>
+#include <linux/page_zone.h>
struct mempolicy;
struct anon_vma;
@@ -1049,84 +1050,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
* back into memory.
*/
-/*
- * The zone field is never updated after free_area_init_core()
- * sets it, so none of the operations on it need to be atomic.
- */
-
-/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
-#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
-#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
-#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
-#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH)
-#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
-
-/*
- * Define the bit shifts to access each section. For non-existent
- * sections we define the shift as 0; that plus a 0 mask ensures
- * the compiler will optimise away reference to them.
- */
-#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
-#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0))
-#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0))
-#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))
-#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0))
-
-/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
-#ifdef NODE_NOT_IN_PAGE_FLAGS
-#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT)
-#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \
- SECTIONS_PGOFF : ZONES_PGOFF)
-#else
-#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT)
-#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \
- NODES_PGOFF : ZONES_PGOFF)
-#endif
-
-#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
-
-#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
-#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
-#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
-#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1)
-#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1)
-#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1)
-
-static inline enum zone_type page_zonenum(const struct page *page)
-{
- ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
- return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
-}
-
-static inline enum zone_type folio_zonenum(const struct folio *folio)
-{
- return page_zonenum(&folio->page);
-}
-
-#ifdef CONFIG_ZONE_DEVICE
-static inline bool is_zone_device_page(const struct page *page)
-{
- return page_zonenum(page) == ZONE_DEVICE;
-}
-extern void memmap_init_zone_device(struct zone *, unsigned long,
- unsigned long, struct dev_pagemap *);
-#else
-static inline bool is_zone_device_page(const struct page *page)
-{
- return false;
-}
-#endif
-
-static inline bool folio_is_zone_device(const struct folio *folio)
-{
- return is_zone_device_page(&folio->page);
-}
-
-static inline bool is_zone_movable_page(const struct page *page)
-{
- return page_zonenum(page) == ZONE_MOVABLE;
-}
-
#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
diff --git a/include/linux/page_zone.h b/include/linux/page_zone.h
new file mode 100644
index 000000000000..2a7a347173ee
--- /dev/null
+++ b/include/linux/page_zone.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PAGE_ZONE_H_
+#define _PAGE_ZONE_H_
+
+/*
+ * The zone field is never updated after free_area_init_core()
+ * sets it, so none of the operations on it need to be atomic.
+ */
+
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
+#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
+#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
+#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
+#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH)
+#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
+
+/*
+ * Define the bit shifts to access each section. For non-existent
+ * sections we define the shift as 0; that plus a 0 mask ensures
+ * the compiler will optimise away reference to them.
+ */
+#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
+#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0))
+#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0))
+#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))
+#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0))
+
+/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT)
+#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \
+ SECTIONS_PGOFF : ZONES_PGOFF)
+#else
+#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT)
+#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \
+ NODES_PGOFF : ZONES_PGOFF)
+#endif
+
+#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
+
+#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
+#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
+#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
+#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1)
+#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1)
+#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1)
+
+/*
+ * Specialize ZONE_DEVICE memory into multiple types each has a different
+ * usage.
+ *
+ * MEMORY_DEVICE_PRIVATE:
+ * Device memory that is not directly addressable by the CPU: CPU can neither
+ * read nor write private memory. In this case, we do still have struct pages
+ * backing the device memory. Doing so simplifies the implementation, but it is
+ * important to remember that there are certain points at which the struct page
+ * must be treated as an opaque object, rather than a "normal" struct page.
+ *
+ * A more complete discussion of unaddressable memory may be found in
+ * include/linux/hmm.h and Documentation/vm/hmm.rst.
+ *
+ * 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
+ * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
+ * wakeup event whenever a page is unpinned and becomes idle. This
+ * wakeup is used to coordinate physical address space management (ex:
+ * fs truncate/hole punch) vs pinned pages (ex: device dma).
+ *
+ * MEMORY_DEVICE_GENERIC:
+ * Host memory that has similar access semantics as System RAM i.e. DMA
+ * coherent and supports page pinning. This is for example used by DAX devices
+ * that expose memory using a character device.
+ *
+ * MEMORY_DEVICE_PCI_P2PDMA:
+ * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
+ * transactions.
+ */
+enum memory_type {
+ /* 0 is reserved to catch uninitialized type fields */
+ MEMORY_DEVICE_PRIVATE = 1,
+ MEMORY_DEVICE_FS_DAX,
+ MEMORY_DEVICE_GENERIC,
+ MEMORY_DEVICE_PCI_P2PDMA,
+};
+
+/**
+ * struct vmem_altmap - pre-allocated storage for vmemmap_populate
+ * @base_pfn: base of the entire dev_pagemap mapping
+ * @reserve: pages mapped, but reserved for driver use (relative to @base)
+ * @free: free pages set aside in the mapping for memmap storage
+ * @align: pages reserved to meet allocation alignments
+ * @alloc: track pages consumed, private to vmemmap_populate()
+ */
+struct vmem_altmap {
+ unsigned long base_pfn;
+ const unsigned long end_pfn;
+ const unsigned long reserve;
+ unsigned long free;
+ unsigned long align;
+ unsigned long alloc;
+};
+
+/**
+ * struct dev_pagemap - metadata for ZONE_DEVICE mappings
+ * @altmap: pre-allocated/reserved memory for vmemmap allocations
+ * @ref: reference count that pins the devm_memremap_pages() mapping
+ * @done: completion for @ref
+ * @type: memory type: see MEMORY_* in memory_hotplug.h
+ * @flags: PGMAP_* flags to specify defailed behavior
+ * @vmemmap_shift: structural definition of how the vmemmap page metadata
+ * is populated, specifically the metadata page order.
+ * A zero value (default) uses base pages as the vmemmap metadata
+ * representation. A bigger value will set up compound struct pages
+ * of the requested order value.
+ * @ops: method table
+ * @owner: an opaque pointer identifying the entity that manages this
+ * instance. Used by various helpers to make sure that no
+ * foreign ZONE_DEVICE memory is accessed.
+ * @nr_range: number of ranges to be mapped
+ * @range: range to be mapped when nr_range == 1
+ * @ranges: array of ranges to be mapped when nr_range > 1
+ */
+struct dev_pagemap {
+ struct vmem_altmap altmap;
+ struct percpu_ref ref;
+ struct completion done;
+ enum memory_type type;
+ unsigned int flags;
+ unsigned long vmemmap_shift;
+ const struct dev_pagemap_ops *ops;
+ void *owner;
+ int nr_range;
+ union {
+ struct range range;
+ struct range ranges[0];
+ };
+};
+
+static inline enum zone_type page_zonenum(const struct page *page)
+{
+ ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
+ return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
+}
+
+static inline enum zone_type folio_zonenum(const struct folio *folio)
+{
+ return page_zonenum(&folio->page);
+}
+
+static inline bool is_zone_movable_page(const struct page *page)
+{
+ return page_zonenum(page) == ZONE_MOVABLE;
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+static inline bool is_zone_device_page(const struct page *page)
+{
+ return page_zonenum(page) == ZONE_DEVICE;
+}
+extern void memmap_init_zone_device(struct zone *, unsigned long,
+ unsigned long, struct dev_pagemap *);
+#else
+static inline bool is_zone_device_page(const struct page *page)
+{
+ return false;
+}
+#endif
+
+static inline bool folio_is_zone_device(const struct folio *folio)
+{
+ return is_zone_device_page(&folio->page);
+}
+
+static inline bool is_device_private_page(const struct page *page)
+{
+ return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
+ is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_PRIVATE;
+}
+
+static inline bool folio_is_device_private(const struct folio *folio)
+{
+ return is_device_private_page(&folio->page);
+}
+
+static inline bool is_pci_p2pdma_page(const struct page *page)
+{
+ return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
+ is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
+}
+
+#endif /* _PAGE_ZONE_H_ */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 618c366a2f07..a2df2f193f06 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -53,7 +53,6 @@
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmpressure.h>
-#include <linux/memremap.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
--
2.32.0
