mirror of
https://github.com/tbsdtv/linux_media.git
synced 2025-07-23 20:51:03 +02:00
In preparation to set a fallback value for dev_dax->target_node, introduce generic fallback helpers for phys_to_target_node() A generic implementation based on node-data or memblock was proposed, but as noted by Mike: "Here again, I would prefer to add a weak default for phys_to_target_node() because the "generic" implementation is not really generic. The fallback to reserved ranges is x86 specfic because on x86 most of the reserved areas is not in memblock.memory. AFAIK, no other architecture does this." The info message in the generic memory_add_physaddr_to_nid() implementation is fixed up to properly reflect that memory_add_physaddr_to_nid() communicates "online" node info and phys_to_target_node() indicates "target / to-be-onlined" node info. [akpm@linux-foundation.org: fix CONFIG_MEMORY_HOTPLUG=n build] Link: https://lkml.kernel.org/r/202008252130.7YrHIyMI%25lkp@intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Jia He <justin.he@arm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: kernel test robot <lkp@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Link: https://lkml.kernel.org/r/159643097768.4062302.3135192588966888630.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
371 lines
11 KiB
C
371 lines
11 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_MEMORY_HOTPLUG_H
|
|
#define __LINUX_MEMORY_HOTPLUG_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/bug.h>
|
|
|
|
struct page;
|
|
struct zone;
|
|
struct pglist_data;
|
|
struct mem_section;
|
|
struct memory_block;
|
|
struct resource;
|
|
struct vmem_altmap;
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
/*
|
|
* Return page for the valid pfn only if the page is online. All pfn
|
|
* walkers which rely on the fully initialized page->flags and others
|
|
* should use this rather than pfn_valid && pfn_to_page
|
|
*/
|
|
#define pfn_to_online_page(pfn) \
|
|
({ \
|
|
struct page *___page = NULL; \
|
|
unsigned long ___pfn = pfn; \
|
|
unsigned long ___nr = pfn_to_section_nr(___pfn); \
|
|
\
|
|
if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
|
|
pfn_valid_within(___pfn)) \
|
|
___page = pfn_to_page(___pfn); \
|
|
___page; \
|
|
})
|
|
|
|
/*
|
|
* Types for free bootmem stored in page->lru.next. These have to be in
|
|
* some random range in unsigned long space for debugging purposes.
|
|
*/
|
|
enum {
|
|
MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
|
|
SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
|
|
MIX_SECTION_INFO,
|
|
NODE_INFO,
|
|
MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
|
|
};
|
|
|
|
/* Types for control the zone type of onlined and offlined memory */
|
|
enum {
|
|
/* Offline the memory. */
|
|
MMOP_OFFLINE = 0,
|
|
/* Online the memory. Zone depends, see default_zone_for_pfn(). */
|
|
MMOP_ONLINE,
|
|
/* Online the memory to ZONE_NORMAL. */
|
|
MMOP_ONLINE_KERNEL,
|
|
/* Online the memory to ZONE_MOVABLE. */
|
|
MMOP_ONLINE_MOVABLE,
|
|
};
|
|
|
|
/*
|
|
* Extended parameters for memory hotplug:
|
|
* altmap: alternative allocator for memmap array (optional)
|
|
* pgprot: page protection flags to apply to newly created page tables
|
|
* (required)
|
|
*/
|
|
struct mhp_params {
|
|
struct vmem_altmap *altmap;
|
|
pgprot_t pgprot;
|
|
};
|
|
|
|
/*
|
|
* Zone resizing functions
|
|
*
|
|
* Note: any attempt to resize a zone should has pgdat_resize_lock()
|
|
* zone_span_writelock() both held. This ensure the size of a zone
|
|
* can't be changed while pgdat_resize_lock() held.
|
|
*/
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return read_seqbegin(&zone->span_seqlock);
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return read_seqretry(&zone->span_seqlock, iv);
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone)
|
|
{
|
|
write_seqlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_span_writeunlock(struct zone *zone)
|
|
{
|
|
write_sequnlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_seqlock_init(struct zone *zone)
|
|
{
|
|
seqlock_init(&zone->span_seqlock);
|
|
}
|
|
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
|
|
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
|
|
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
|
|
/* VM interface that may be used by firmware interface */
|
|
extern int online_pages(unsigned long pfn, unsigned long nr_pages,
|
|
int online_type, int nid);
|
|
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
|
|
unsigned long end_pfn);
|
|
extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
|
|
unsigned long end_pfn);
|
|
|
|
typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
|
|
|
|
extern void generic_online_page(struct page *page, unsigned int order);
|
|
extern int set_online_page_callback(online_page_callback_t callback);
|
|
extern int restore_online_page_callback(online_page_callback_t callback);
|
|
|
|
extern int try_online_node(int nid);
|
|
|
|
extern int arch_add_memory(int nid, u64 start, u64 size,
|
|
struct mhp_params *params);
|
|
extern u64 max_mem_size;
|
|
|
|
extern int memhp_online_type_from_str(const char *str);
|
|
|
|
/* Default online_type (MMOP_*) when new memory blocks are added. */
|
|
extern int memhp_default_online_type;
|
|
/* If movable_node boot option specified */
|
|
extern bool movable_node_enabled;
|
|
static inline bool movable_node_is_enabled(void)
|
|
{
|
|
return movable_node_enabled;
|
|
}
|
|
|
|
extern void arch_remove_memory(int nid, u64 start, u64 size,
|
|
struct vmem_altmap *altmap);
|
|
extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
|
|
struct vmem_altmap *altmap);
|
|
|
|
/* reasonably generic interface to expand the physical pages */
|
|
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
|
|
struct mhp_params *params);
|
|
|
|
#ifndef CONFIG_ARCH_HAS_ADD_PAGES
|
|
static inline int add_pages(int nid, unsigned long start_pfn,
|
|
unsigned long nr_pages, struct mhp_params *params)
|
|
{
|
|
return __add_pages(nid, start_pfn, nr_pages, params);
|
|
}
|
|
#else /* ARCH_HAS_ADD_PAGES */
|
|
int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
|
|
struct mhp_params *params);
|
|
#endif /* ARCH_HAS_ADD_PAGES */
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
|
|
/*
|
|
* For supporting node-hotadd, we have to allocate a new pgdat.
|
|
*
|
|
* If an arch has generic style NODE_DATA(),
|
|
* node_data[nid] = kzalloc() works well. But it depends on the architecture.
|
|
*
|
|
* In general, generic_alloc_nodedata() is used.
|
|
* Now, arch_free_nodedata() is just defined for error path of node_hot_add.
|
|
*
|
|
*/
|
|
extern pg_data_t *arch_alloc_nodedata(int nid);
|
|
extern void arch_free_nodedata(pg_data_t *pgdat);
|
|
extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
|
|
|
|
#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid)
|
|
#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
|
|
* XXX: kmalloc_node() can't work well to get new node's memory at this time.
|
|
* Because, pgdat for the new node is not allocated/initialized yet itself.
|
|
* To use new node's memory, more consideration will be necessary.
|
|
*/
|
|
#define generic_alloc_nodedata(nid) \
|
|
({ \
|
|
kzalloc(sizeof(pg_data_t), GFP_KERNEL); \
|
|
})
|
|
/*
|
|
* This definition is just for error path in node hotadd.
|
|
* For node hotremove, we have to replace this.
|
|
*/
|
|
#define generic_free_nodedata(pgdat) kfree(pgdat)
|
|
|
|
extern pg_data_t *node_data[];
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
node_data[nid] = pgdat;
|
|
}
|
|
|
|
#else /* !CONFIG_NUMA */
|
|
|
|
/* never called */
|
|
static inline pg_data_t *generic_alloc_nodedata(int nid)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
static inline void generic_free_nodedata(pg_data_t *pgdat)
|
|
{
|
|
}
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
|
|
extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
|
|
#else
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
#endif
|
|
extern void put_page_bootmem(struct page *page);
|
|
extern void get_page_bootmem(unsigned long ingo, struct page *page,
|
|
unsigned long type);
|
|
|
|
void get_online_mems(void);
|
|
void put_online_mems(void);
|
|
|
|
void mem_hotplug_begin(void);
|
|
void mem_hotplug_done(void);
|
|
|
|
#else /* ! CONFIG_MEMORY_HOTPLUG */
|
|
#define pfn_to_online_page(pfn) \
|
|
({ \
|
|
struct page *___page = NULL; \
|
|
if (pfn_valid(pfn)) \
|
|
___page = pfn_to_page(pfn); \
|
|
___page; \
|
|
})
|
|
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone) {}
|
|
static inline void zone_span_writeunlock(struct zone *zone) {}
|
|
static inline void zone_seqlock_init(struct zone *zone) {}
|
|
|
|
static inline int mhp_notimplemented(const char *func)
|
|
{
|
|
printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
|
|
dump_stack();
|
|
return -ENOSYS;
|
|
}
|
|
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline int try_online_node(int nid)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void get_online_mems(void) {}
|
|
static inline void put_online_mems(void) {}
|
|
|
|
static inline void mem_hotplug_begin(void) {}
|
|
static inline void mem_hotplug_done(void) {}
|
|
|
|
static inline bool movable_node_is_enabled(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* ! CONFIG_MEMORY_HOTPLUG */
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern int memory_add_physaddr_to_nid(u64 start);
|
|
extern int phys_to_target_node(u64 start);
|
|
#else
|
|
static inline int memory_add_physaddr_to_nid(u64 start)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int phys_to_target_node(u64 start)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
|
|
/*
|
|
* pgdat resizing functions
|
|
*/
|
|
static inline
|
|
void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_lock_irqsave(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_init(struct pglist_data *pgdat)
|
|
{
|
|
spin_lock_init(&pgdat->node_size_lock);
|
|
}
|
|
#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
|
|
/*
|
|
* Stub functions for when hotplug is off
|
|
*/
|
|
static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
|
|
#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
extern void try_offline_node(int nid);
|
|
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
|
|
extern int remove_memory(int nid, u64 start, u64 size);
|
|
extern void __remove_memory(int nid, u64 start, u64 size);
|
|
extern int offline_and_remove_memory(int nid, u64 start, u64 size);
|
|
|
|
#else
|
|
static inline void try_offline_node(int nid) {}
|
|
|
|
static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
static inline int remove_memory(int nid, u64 start, u64 size)
|
|
{
|
|
return -EBUSY;
|
|
}
|
|
|
|
static inline void __remove_memory(int nid, u64 start, u64 size) {}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
extern void set_zone_contiguous(struct zone *zone);
|
|
extern void clear_zone_contiguous(struct zone *zone);
|
|
|
|
extern void __ref free_area_init_core_hotplug(int nid);
|
|
extern int __add_memory(int nid, u64 start, u64 size);
|
|
extern int add_memory(int nid, u64 start, u64 size);
|
|
extern int add_memory_resource(int nid, struct resource *resource);
|
|
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
|
|
const char *resource_name);
|
|
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages, struct vmem_altmap *altmap);
|
|
extern void remove_pfn_range_from_zone(struct zone *zone,
|
|
unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
extern bool is_memblock_offlined(struct memory_block *mem);
|
|
extern int sparse_add_section(int nid, unsigned long pfn,
|
|
unsigned long nr_pages, struct vmem_altmap *altmap);
|
|
extern void sparse_remove_section(struct mem_section *ms,
|
|
unsigned long pfn, unsigned long nr_pages,
|
|
unsigned long map_offset, struct vmem_altmap *altmap);
|
|
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
|
|
unsigned long pnum);
|
|
extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
|
|
int online_type);
|
|
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
|
|
unsigned long nr_pages);
|
|
#endif /* __LINUX_MEMORY_HOTPLUG_H */
|