[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
/*
|
|
|
|
|
* sparse memory mappings.
|
|
|
|
|
*/
|
|
|
|
|
#include <linux/mm.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
#include <linux/mmzone.h>
|
|
|
|
|
#include <linux/bootmem.h>
|
2005-10-30 09:16:55 +08:00
|
|
|
#include <linux/highmem.h>
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
#include <linux/module.h>
|
2005-09-04 06:54:29 +08:00
|
|
|
#include <linux/spinlock.h>
|
2005-10-30 09:16:55 +08:00
|
|
|
#include <linux/vmalloc.h>
|
2008-04-28 17:13:34 +08:00
|
|
|
#include "internal.h"
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
#include <asm/dma.h>
|
2007-10-16 16:24:13 +08:00
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
|
#include <asm/pgtable.h>
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Permanent SPARSEMEM data:
|
|
|
|
|
*
|
|
|
|
|
* 1) mem_section - memory sections, mem_map's for valid memory
|
|
|
|
|
*/
|
2005-09-04 06:54:28 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_EXTREME
|
2005-09-04 06:54:26 +08:00
|
|
|
struct mem_section *mem_section[NR_SECTION_ROOTS]
|
2006-01-08 17:01:27 +08:00
|
|
|
____cacheline_internodealigned_in_smp;
|
2005-09-04 06:54:28 +08:00
|
|
|
#else
|
|
|
|
|
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
|
2006-01-08 17:01:27 +08:00
|
|
|
____cacheline_internodealigned_in_smp;
|
2005-09-04 06:54:28 +08:00
|
|
|
#endif
|
|
|
|
|
EXPORT_SYMBOL(mem_section);
|
|
|
|
|
|
2006-12-07 12:31:45 +08:00
|
|
|
#ifdef NODE_NOT_IN_PAGE_FLAGS
|
|
|
|
|
/*
|
|
|
|
|
* If we did not store the node number in the page then we have to
|
|
|
|
|
* do a lookup in the section_to_node_table in order to find which
|
|
|
|
|
* node the page belongs to.
|
|
|
|
|
*/
|
|
|
|
|
#if MAX_NUMNODES <= 256
|
|
|
|
|
static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
|
|
|
|
|
#else
|
|
|
|
|
static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
|
|
|
|
|
#endif
|
|
|
|
|
|
2006-12-07 12:33:03 +08:00
|
|
|
int page_to_nid(struct page *page)
|
2006-12-07 12:31:45 +08:00
|
|
|
{
|
|
|
|
|
return section_to_node_table[page_to_section(page)];
|
|
|
|
|
}
|
|
|
|
|
EXPORT_SYMBOL(page_to_nid);
|
2007-08-23 05:01:03 +08:00
|
|
|
|
|
|
|
|
static void set_section_nid(unsigned long section_nr, int nid)
|
|
|
|
|
{
|
|
|
|
|
section_to_node_table[section_nr] = nid;
|
|
|
|
|
}
|
|
|
|
|
#else /* !NODE_NOT_IN_PAGE_FLAGS */
|
|
|
|
|
static inline void set_section_nid(unsigned long section_nr, int nid)
|
|
|
|
|
{
|
|
|
|
|
}
|
2006-12-07 12:31:45 +08:00
|
|
|
#endif
|
|
|
|
|
|
2005-09-04 06:54:28 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_EXTREME
|
2007-05-18 05:29:25 +08:00
|
|
|
static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
|
2005-09-04 06:54:29 +08:00
|
|
|
{
|
|
|
|
|
struct mem_section *section = NULL;
|
|
|
|
|
unsigned long array_size = SECTIONS_PER_ROOT *
|
|
|
|
|
sizeof(struct mem_section);
|
|
|
|
|
|
2009-09-22 08:01:19 +08:00
|
|
|
if (slab_is_available()) {
|
|
|
|
|
if (node_state(nid, N_HIGH_MEMORY))
|
|
|
|
|
section = kmalloc_node(array_size, GFP_KERNEL, nid);
|
|
|
|
|
else
|
|
|
|
|
section = kmalloc(array_size, GFP_KERNEL);
|
|
|
|
|
} else
|
2006-05-02 03:16:09 +08:00
|
|
|
section = alloc_bootmem_node(NODE_DATA(nid), array_size);
|
2005-09-04 06:54:29 +08:00
|
|
|
|
|
|
|
|
if (section)
|
|
|
|
|
memset(section, 0, array_size);
|
|
|
|
|
|
|
|
|
|
return section;
|
2005-09-04 06:54:28 +08:00
|
|
|
}
|
2005-09-04 06:54:26 +08:00
|
|
|
|
2007-05-08 15:23:07 +08:00
|
|
|
static int __meminit sparse_index_init(unsigned long section_nr, int nid)
|
2005-09-04 06:54:26 +08:00
|
|
|
{
|
2006-06-27 17:53:55 +08:00
|
|
|
static DEFINE_SPINLOCK(index_init_lock);
|
2005-09-04 06:54:29 +08:00
|
|
|
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
|
|
|
|
|
struct mem_section *section;
|
|
|
|
|
int ret = 0;
|
2005-09-04 06:54:26 +08:00
|
|
|
|
|
|
|
|
if (mem_section[root])
|
2005-09-04 06:54:29 +08:00
|
|
|
return -EEXIST;
|
2005-09-04 06:54:28 +08:00
|
|
|
|
2005-09-04 06:54:29 +08:00
|
|
|
section = sparse_index_alloc(nid);
|
2007-12-18 08:19:58 +08:00
|
|
|
if (!section)
|
|
|
|
|
return -ENOMEM;
|
2005-09-04 06:54:29 +08:00
|
|
|
/*
|
|
|
|
|
* This lock keeps two different sections from
|
|
|
|
|
* reallocating for the same index
|
|
|
|
|
*/
|
|
|
|
|
spin_lock(&index_init_lock);
|
2005-09-04 06:54:28 +08:00
|
|
|
|
2005-09-04 06:54:29 +08:00
|
|
|
if (mem_section[root]) {
|
|
|
|
|
ret = -EEXIST;
|
|
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
mem_section[root] = section;
|
|
|
|
|
out:
|
|
|
|
|
spin_unlock(&index_init_lock);
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
#else /* !SPARSEMEM_EXTREME */
|
|
|
|
|
static inline int sparse_index_init(unsigned long section_nr, int nid)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
2005-09-04 06:54:26 +08:00
|
|
|
}
|
2005-09-04 06:54:29 +08:00
|
|
|
#endif
|
|
|
|
|
|
2005-10-30 09:16:51 +08:00
|
|
|
/*
|
|
|
|
|
* Although written for the SPARSEMEM_EXTREME case, this happens
|
sparsemem: clean up spelling error in comments
SPARSEMEM is a pretty nice framework that unifies quite a bit of code over all
the arches. It would be great if it could be the default so that we can get
rid of various forms of DISCONTIG and other variations on memory maps. So far
what has hindered this are the additional lookups that SPARSEMEM introduces
for virt_to_page and page_address. This goes so far that the code to do this
has to be kept in a separate function and cannot be used inline.
This patch introduces a virtual memmap mode for SPARSEMEM, in which the memmap
is mapped into a virtually contigious area, only the active sections are
physically backed. This allows virt_to_page page_address and cohorts become
simple shift/add operations. No page flag fields, no table lookups, nothing
involving memory is required.
The two key operations pfn_to_page and page_to_page become:
#define __pfn_to_page(pfn) (vmemmap + (pfn))
#define __page_to_pfn(page) ((page) - vmemmap)
By having a virtual mapping for the memmap we allow simple access without
wasting physical memory. As kernel memory is typically already mapped 1:1
this introduces no additional overhead. The virtual mapping must be big
enough to allow a struct page to be allocated and mapped for all valid
physical pages. This vill make a virtual memmap difficult to use on 32 bit
platforms that support 36 address bits.
However, if there is enough virtual space available and the arch already maps
its 1-1 kernel space using TLBs (f.e. true of IA64 and x86_64) then this
technique makes SPARSEMEM lookups even more efficient than CONFIG_FLATMEM.
FLATMEM needs to read the contents of the mem_map variable to get the start of
the memmap and then add the offset to the required entry. vmemmap is a
constant to which we can simply add the offset.
This patch has the potential to allow us to make SPARSMEM the default (and
even the only) option for most systems. It should be optimal on UP, SMP and
NUMA on most platforms. Then we may even be able to remove the other memory
models: FLATMEM, DISCONTIG etc.
The current aim is to bring a common virtually mapped mem_map to all
architectures. This should facilitate the removal of the bespoke
implementations from the architectures. This also brings performance
improvements for most architecture making sparsmem vmemmap the more desirable
memory model. The ultimate aim of this work is to expand sparsemem support to
encompass all the features of the other memory models. This could allow us to
drop support for and remove the other models in the longer term.
Below are some comparitive kernbench numbers for various architectures,
comparing default memory model against SPARSEMEM VMEMMAP. All but ia64 show
marginal improvement; we expect the ia64 figures to be sorted out when the
larger mapping support returns.
x86-64 non-NUMA
Base VMEMAP % change (-ve good)
User 85.07 84.84 -0.26
System 34.32 33.84 -1.39
Total 119.38 118.68 -0.59
ia64
Base VMEMAP % change (-ve good)
User 1016.41 1016.93 0.05
System 50.83 51.02 0.36
Total 1067.25 1067.95 0.07
x86-64 NUMA
Base VMEMAP % change (-ve good)
User 30.77 431.73 0.22
System 45.39 43.98 -3.11
Total 476.17 475.71 -0.10
ppc64
Base VMEMAP % change (-ve good)
User 488.77 488.35 -0.09
System 56.92 56.37 -0.97
Total 545.69 544.72 -0.18
Below are some AIM bencharks on IA64 and x86-64 (thank Bob). The seems
pretty much flat as you would expect.
ia64 results 2 cpu non-numa 4Gb SCSI disk
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" extreme Jun 1 07:17:24 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 98.9 100 58.9 1.3 1.6482
101 5547.1 95 106.0 79.4 0.9154
201 6377.7 95 183.4 158.3 0.5288
301 6932.2 95 252.7 237.3 0.3838
401 7075.8 93 329.8 316.7 0.2941
501 7235.6 94 403.0 396.2 0.2407
600 7387.5 94 472.7 475.0 0.2052
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" vmemmap Jun 1 09:59:04 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 99.1 100 58.8 1.2 1.6509
101 5480.9 95 107.2 79.2 0.9044
201 6490.3 95 180.2 157.8 0.5382
301 6886.6 94 254.4 236.8 0.3813
401 7078.2 94 329.7 316.0 0.2942
501 7250.3 95 402.2 395.4 0.2412
600 7399.1 94 471.9 473.9 0.2055
open power 710 2 cpu, 4 Gb, SCSI and configured physically
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" extreme May 29 15:42:53 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 25.7 100 226.3 4.3 0.4286
101 1096.0 97 536.4 199.8 0.1809
201 1236.4 96 946.1 389.1 0.1025
301 1280.5 96 1368.0 582.3 0.0709
401 1270.2 95 1837.4 771.0 0.0528
501 1251.4 96 2330.1 955.9 0.0416
601 1252.6 96 2792.4 1139.2 0.0347
701 1245.2 96 3276.5 1334.6 0.0296
918 1229.5 96 4345.4 1728.7 0.0223
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" vmemmap May 30 07:28:26 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 25.6 100 226.9 4.3 0.4275
101 1049.3 97 560.2 198.1 0.1731
201 1199.1 97 975.6 390.7 0.0994
301 1261.7 96 1388.5 591.5 0.0699
401 1256.1 96 1858.1 771.9 0.0522
501 1220.1 96 2389.7 955.3 0.0406
601 1224.6 96 2856.3 1133.4 0.0340
701 1252.0 96 3258.7 1314.1 0.0298
915 1232.8 96 4319.7 1704.0 0.0225
amd64 2 2-core, 4Gb and SATA
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" extreme Jun 2 03:59:48 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 13.0 100 446.4 2.1 0.2173
101 533.4 97 1102.0 110.2 0.0880
201 578.3 97 2022.8 220.8 0.0480
301 583.8 97 3000.6 332.3 0.0323
401 580.5 97 4020.1 442.2 0.0241
501 574.8 98 5072.8 558.8 0.0191
600 566.5 98 6163.8 671.0 0.0157
Benchmark Version Machine Run Date
AIM Multiuser Benchmark - Suite VII "1.1" vmemmap Jun 3 04:19:31 2007
Tasks Jobs/Min JTI Real CPU Jobs/sec/task
1 13.0 100 447.8 2.0 0.2166
101 536.5 97 1095.6 109.7 0.0885
201 567.7 97 2060.5 219.3 0.0471
301 582.1 96 3009.4 330.2 0.0322
401 578.2 96 4036.4 442.4 0.0240
501 585.1 98 4983.2 555.1 0.0195
600 565.5 98 6175.2 660.6 0.0157
This patch:
Fix some spelling errors.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:10 +08:00
|
|
|
* to also work for the flat array case because
|
2005-10-30 09:16:51 +08:00
|
|
|
* NR_SECTION_ROOTS==NR_MEM_SECTIONS.
|
|
|
|
|
*/
|
|
|
|
|
int __section_nr(struct mem_section* ms)
|
|
|
|
|
{
|
|
|
|
|
unsigned long root_nr;
|
|
|
|
|
struct mem_section* root;
|
|
|
|
|
|
2006-05-21 06:00:05 +08:00
|
|
|
for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
|
|
|
|
|
root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
|
2005-10-30 09:16:51 +08:00
|
|
|
if (!root)
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
|
|
|
|
|
}
|
|
|
|
|
|
2006-06-23 17:03:41 +08:00
|
|
|
/*
|
|
|
|
|
* During early boot, before section_mem_map is used for an actual
|
|
|
|
|
* mem_map, we use section_mem_map to store the section's NUMA
|
|
|
|
|
* node. This keeps us from having to use another data structure. The
|
|
|
|
|
* node information is cleared just before we store the real mem_map.
|
|
|
|
|
*/
|
|
|
|
|
static inline unsigned long sparse_encode_early_nid(int nid)
|
|
|
|
|
{
|
|
|
|
|
return (nid << SECTION_NID_SHIFT);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int sparse_early_nid(struct mem_section *section)
|
|
|
|
|
{
|
|
|
|
|
return (section->section_mem_map >> SECTION_NID_SHIFT);
|
|
|
|
|
}
|
|
|
|
|
|
2008-07-24 12:26:52 +08:00
|
|
|
/* Validate the physical addressing limitations of the model */
|
|
|
|
|
void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
|
|
|
unsigned long *end_pfn)
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
{
|
2008-07-24 12:26:52 +08:00
|
|
|
unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
|
2008-04-16 07:40:00 +08:00
|
|
|
/*
|
|
|
|
|
* Sanity checks - do not allow an architecture to pass
|
|
|
|
|
* in larger pfns than the maximum scope of sparsemem:
|
|
|
|
|
*/
|
2008-07-24 12:26:52 +08:00
|
|
|
if (*start_pfn > max_sparsemem_pfn) {
|
|
|
|
|
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
|
|
|
|
|
"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
|
|
|
|
|
*start_pfn, *end_pfn, max_sparsemem_pfn);
|
|
|
|
|
WARN_ON_ONCE(1);
|
|
|
|
|
*start_pfn = max_sparsemem_pfn;
|
|
|
|
|
*end_pfn = max_sparsemem_pfn;
|
2009-04-01 06:19:25 +08:00
|
|
|
} else if (*end_pfn > max_sparsemem_pfn) {
|
2008-07-24 12:26:52 +08:00
|
|
|
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
|
|
|
|
|
"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
|
|
|
|
|
*start_pfn, *end_pfn, max_sparsemem_pfn);
|
|
|
|
|
WARN_ON_ONCE(1);
|
|
|
|
|
*end_pfn = max_sparsemem_pfn;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Record a memory area against a node. */
|
|
|
|
|
void __init memory_present(int nid, unsigned long start, unsigned long end)
|
|
|
|
|
{
|
|
|
|
|
unsigned long pfn;
|
2008-04-16 07:40:00 +08:00
|
|
|
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
start &= PAGE_SECTION_MASK;
|
2008-07-24 12:26:52 +08:00
|
|
|
mminit_validate_memmodel_limits(&start, &end);
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
|
|
|
|
|
unsigned long section = pfn_to_section_nr(pfn);
|
2005-09-04 06:54:26 +08:00
|
|
|
struct mem_section *ms;
|
|
|
|
|
|
|
|
|
|
sparse_index_init(section, nid);
|
2007-08-23 05:01:03 +08:00
|
|
|
set_section_nid(section, nid);
|
2005-09-04 06:54:26 +08:00
|
|
|
|
|
|
|
|
ms = __nr_to_section(section);
|
|
|
|
|
if (!ms->section_mem_map)
|
2006-06-23 17:03:41 +08:00
|
|
|
ms->section_mem_map = sparse_encode_early_nid(nid) |
|
|
|
|
|
SECTION_MARKED_PRESENT;
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Only used by the i386 NUMA architecures, but relatively
|
|
|
|
|
* generic code.
|
|
|
|
|
*/
|
|
|
|
|
unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
|
|
|
|
|
unsigned long end_pfn)
|
|
|
|
|
{
|
|
|
|
|
unsigned long pfn;
|
|
|
|
|
unsigned long nr_pages = 0;
|
|
|
|
|
|
2008-07-24 12:26:52 +08:00
|
|
|
mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
|
|
|
if (nid != early_pfn_to_nid(pfn))
|
|
|
|
|
continue;
|
|
|
|
|
|
2007-10-16 16:24:11 +08:00
|
|
|
if (pfn_present(pfn))
|
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:54 +08:00
|
|
|
nr_pages += PAGES_PER_SECTION;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return nr_pages * sizeof(struct page);
|
|
|
|
|
}
|
|
|
|
|
|
2005-06-23 15:08:00 +08:00
|
|
|
/*
|
|
|
|
|
* Subtle, we encode the real pfn into the mem_map such that
|
|
|
|
|
* the identity pfn - section_mem_map will return the actual
|
|
|
|
|
* physical page frame number.
|
|
|
|
|
*/
|
|
|
|
|
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
|
|
|
|
|
{
|
|
|
|
|
return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2008-04-28 17:12:01 +08:00
|
|
|
* Decode mem_map from the coded memmap
|
2005-06-23 15:08:00 +08:00
|
|
|
*/
|
|
|
|
|
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
|
|
|
|
|
{
|
2008-04-28 17:12:01 +08:00
|
|
|
/* mask off the extra low bits of information */
|
|
|
|
|
coded_mem_map &= SECTION_MAP_MASK;
|
2005-06-23 15:08:00 +08:00
|
|
|
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
|
|
|
|
|
}
|
|
|
|
|
|
2007-05-08 15:23:07 +08:00
|
|
|
static int __meminit sparse_init_one_section(struct mem_section *ms,
|
2007-10-16 16:25:56 +08:00
|
|
|
unsigned long pnum, struct page *mem_map,
|
|
|
|
|
unsigned long *pageblock_bitmap)
|
2005-06-23 15:08:00 +08:00
|
|
|
{
|
2007-10-16 16:24:11 +08:00
|
|
|
if (!present_section(ms))
|
2005-06-23 15:08:00 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
2006-06-23 17:03:41 +08:00
|
|
|
ms->section_mem_map &= ~SECTION_MAP_MASK;
|
2007-10-16 16:24:11 +08:00
|
|
|
ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
|
|
|
|
|
SECTION_HAS_MEM_MAP;
|
2007-10-16 16:25:56 +08:00
|
|
|
ms->pageblock_flags = pageblock_bitmap;
|
2005-06-23 15:08:00 +08:00
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
memory hotplug: register section/node id to free
This patch set is to free pages which is allocated by bootmem for
memory-hotremove. Some structures of memory management are allocated by
bootmem. ex) memmap, etc.
To remove memory physically, some of them must be freed according to
circumstance. This patch set makes basis to free those pages, and free
memmaps.
Basic my idea is using remain members of struct page to remember information
of users of bootmem (section number or node id). When the section is
removing, kernel can confirm it. By this information, some issues can be
solved.
1) When the memmap of removing section is allocated on other
section by bootmem, it should/can be free.
2) When the memmap of removing section is allocated on the
same section, it shouldn't be freed. Because the section has to be
logical memory offlined already and all pages must be isolated against
page allocater. If it is freed, page allocator may use it which will
be removed physically soon.
3) When removing section has other section's memmap,
kernel will be able to show easily which section should be removed
before it for user. (Not implemented yet)
4) When the above case 2), the page isolation will be able to check and skip
memmap's page when logical memory offline (offline_pages()).
Current page isolation code fails in this case because this page is
just reserved page and it can't distinguish this pages can be
removed or not. But, it will be able to do by this patch.
(Not implemented yet.)
5) The node information like pgdat has similar issues. But, this
will be able to be solved too by this.
(Not implemented yet, but, remembering node id in the pages.)
Fortunately, current bootmem allocator just keeps PageReserved flags,
and doesn't use any other members of page struct. The users of
bootmem doesn't use them too.
This patch:
This is to register information which is node or section's id. Kernel can
distinguish which node/section uses the pages allcated by bootmem. This is
basis for hot-remove sections or nodes.
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:31 +08:00
|
|
|
unsigned long usemap_size(void)
|
2007-10-16 16:25:56 +08:00
|
|
|
{
|
|
|
|
|
unsigned long size_bytes;
|
|
|
|
|
size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
|
|
|
|
|
size_bytes = roundup(size_bytes, sizeof(unsigned long));
|
|
|
|
|
return size_bytes;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
|
|
|
static unsigned long *__kmalloc_section_usemap(void)
|
|
|
|
|
{
|
|
|
|
|
return kmalloc(usemap_size(), GFP_KERNEL);
|
|
|
|
|
}
|
|
|
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|
|
|
|
|
|
2008-07-24 12:28:15 +08:00
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
|
static unsigned long * __init
|
2010-02-10 17:20:21 +08:00
|
|
|
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
|
|
|
|
|
unsigned long count)
|
2008-07-24 12:28:15 +08:00
|
|
|
{
|
|
|
|
|
unsigned long section_nr;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* A page may contain usemaps for other sections preventing the
|
|
|
|
|
* page being freed and making a section unremovable while
|
|
|
|
|
* other sections referencing the usemap retmain active. Similarly,
|
|
|
|
|
* a pgdat can prevent a section being removed. If section A
|
|
|
|
|
* contains a pgdat and section B contains the usemap, both
|
|
|
|
|
* sections become inter-dependent. This allocates usemaps
|
|
|
|
|
* from the same section as the pgdat where possible to avoid
|
|
|
|
|
* this problem.
|
|
|
|
|
*/
|
|
|
|
|
section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
|
2010-02-10 17:20:21 +08:00
|
|
|
return alloc_bootmem_section(usemap_size() * count, section_nr);
|
2008-07-24 12:28:15 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
|
|
|
|
|
{
|
|
|
|
|
unsigned long usemap_snr, pgdat_snr;
|
|
|
|
|
static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
|
|
|
|
|
static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
|
|
|
|
|
struct pglist_data *pgdat = NODE_DATA(nid);
|
|
|
|
|
int usemap_nid;
|
|
|
|
|
|
|
|
|
|
usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
|
|
|
|
|
pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
|
|
|
|
|
if (usemap_snr == pgdat_snr)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
|
|
|
|
|
/* skip redundant message */
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
old_usemap_snr = usemap_snr;
|
|
|
|
|
old_pgdat_snr = pgdat_snr;
|
|
|
|
|
|
|
|
|
|
usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
|
|
|
|
|
if (usemap_nid != nid) {
|
|
|
|
|
printk(KERN_INFO
|
|
|
|
|
"node %d must be removed before remove section %ld\n",
|
|
|
|
|
nid, usemap_snr);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
/*
|
|
|
|
|
* There is a circular dependency.
|
|
|
|
|
* Some platforms allow un-removable section because they will just
|
|
|
|
|
* gather other removable sections for dynamic partitioning.
|
|
|
|
|
* Just notify un-removable section's number here.
|
|
|
|
|
*/
|
|
|
|
|
printk(KERN_INFO "Section %ld and %ld (node %d)", usemap_snr,
|
|
|
|
|
pgdat_snr, nid);
|
|
|
|
|
printk(KERN_CONT
|
|
|
|
|
" have a circular dependency on usemap and pgdat allocations\n");
|
|
|
|
|
}
|
|
|
|
|
#else
|
|
|
|
|
static unsigned long * __init
|
2010-02-10 17:20:21 +08:00
|
|
|
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
|
|
|
|
|
unsigned long count)
|
2008-07-24 12:28:15 +08:00
|
|
|
{
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
|
|
2010-02-10 17:20:21 +08:00
|
|
|
static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
|
|
|
|
|
unsigned long pnum_begin,
|
|
|
|
|
unsigned long pnum_end,
|
|
|
|
|
unsigned long usemap_count, int nodeid)
|
2007-10-16 16:25:56 +08:00
|
|
|
{
|
2010-02-10 17:20:21 +08:00
|
|
|
void *usemap;
|
|
|
|
|
unsigned long pnum;
|
|
|
|
|
int size = usemap_size();
|
2007-10-16 16:25:56 +08:00
|
|
|
|
2010-02-10 17:20:21 +08:00
|
|
|
usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
|
|
|
|
|
usemap_count);
|
2008-07-24 12:28:15 +08:00
|
|
|
if (usemap) {
|
2010-02-10 17:20:21 +08:00
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
usemap_map[pnum] = usemap;
|
|
|
|
|
usemap += size;
|
|
|
|
|
}
|
|
|
|
|
return;
|
2008-07-24 12:28:15 +08:00
|
|
|
}
|
|
|
|
|
|
2010-02-10 17:20:21 +08:00
|
|
|
usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
|
|
|
|
|
if (usemap) {
|
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
usemap_map[pnum] = usemap;
|
|
|
|
|
usemap += size;
|
|
|
|
|
check_usemap_section_nr(nodeid, usemap_map[pnum]);
|
|
|
|
|
}
|
|
|
|
|
return;
|
|
|
|
|
}
|
2007-10-16 16:25:56 +08:00
|
|
|
|
2008-04-30 15:55:07 +08:00
|
|
|
printk(KERN_WARNING "%s: allocation failed\n", __func__);
|
2007-10-16 16:25:56 +08:00
|
|
|
}
|
|
|
|
|
|
2007-10-16 16:24:13 +08:00
|
|
|
#ifndef CONFIG_SPARSEMEM_VMEMMAP
|
2007-10-16 16:26:14 +08:00
|
|
|
struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
|
2005-06-23 15:08:00 +08:00
|
|
|
{
|
|
|
|
|
struct page *map;
|
2010-05-25 05:31:57 +08:00
|
|
|
unsigned long size;
|
2005-06-23 15:08:00 +08:00
|
|
|
|
|
|
|
|
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
|
|
|
|
|
if (map)
|
|
|
|
|
return map;
|
|
|
|
|
|
2010-05-25 05:31:57 +08:00
|
|
|
size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
|
|
|
|
|
map = __alloc_bootmem_node_high(NODE_DATA(nid), size,
|
|
|
|
|
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
|
2007-10-16 16:24:13 +08:00
|
|
|
return map;
|
|
|
|
|
}
|
2010-02-10 17:20:22 +08:00
|
|
|
void __init sparse_mem_maps_populate_node(struct page **map_map,
|
|
|
|
|
unsigned long pnum_begin,
|
|
|
|
|
unsigned long pnum_end,
|
|
|
|
|
unsigned long map_count, int nodeid)
|
|
|
|
|
{
|
|
|
|
|
void *map;
|
|
|
|
|
unsigned long pnum;
|
|
|
|
|
unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
|
|
|
|
|
|
|
|
|
|
map = alloc_remap(nodeid, size * map_count);
|
|
|
|
|
if (map) {
|
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
map_map[pnum] = map;
|
|
|
|
|
map += size;
|
|
|
|
|
}
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
size = PAGE_ALIGN(size);
|
2010-05-25 05:31:57 +08:00
|
|
|
map = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count,
|
|
|
|
|
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
|
2010-02-10 17:20:22 +08:00
|
|
|
if (map) {
|
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
map_map[pnum] = map;
|
|
|
|
|
map += size;
|
|
|
|
|
}
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* fallback */
|
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
|
|
|
struct mem_section *ms;
|
|
|
|
|
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
|
|
|
|
|
if (map_map[pnum])
|
|
|
|
|
continue;
|
|
|
|
|
ms = __nr_to_section(pnum);
|
|
|
|
|
printk(KERN_ERR "%s: sparsemem memory map backing failed "
|
|
|
|
|
"some memory will not be available.\n", __func__);
|
|
|
|
|
ms->section_mem_map = 0;
|
|
|
|
|
}
|
|
|
|
|
}
|
2007-10-16 16:24:13 +08:00
|
|
|
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
|
|
|
|
|
|
2010-02-28 01:29:38 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
2010-02-10 17:20:22 +08:00
|
|
|
static void __init sparse_early_mem_maps_alloc_node(struct page **map_map,
|
|
|
|
|
unsigned long pnum_begin,
|
|
|
|
|
unsigned long pnum_end,
|
|
|
|
|
unsigned long map_count, int nodeid)
|
|
|
|
|
{
|
|
|
|
|
sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
|
|
|
|
|
map_count, nodeid);
|
|
|
|
|
}
|
2010-02-28 01:29:38 +08:00
|
|
|
#else
|
2008-07-26 10:46:22 +08:00
|
|
|
static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
|
2007-10-16 16:24:13 +08:00
|
|
|
{
|
|
|
|
|
struct page *map;
|
|
|
|
|
struct mem_section *ms = __nr_to_section(pnum);
|
|
|
|
|
int nid = sparse_early_nid(ms);
|
|
|
|
|
|
2007-10-16 16:26:14 +08:00
|
|
|
map = sparse_mem_map_populate(pnum, nid);
|
2005-06-23 15:08:00 +08:00
|
|
|
if (map)
|
|
|
|
|
return map;
|
|
|
|
|
|
2007-10-16 16:24:13 +08:00
|
|
|
printk(KERN_ERR "%s: sparsemem memory map backing failed "
|
2008-04-30 15:55:07 +08:00
|
|
|
"some memory will not be available.\n", __func__);
|
2005-09-04 06:54:26 +08:00
|
|
|
ms->section_mem_map = 0;
|
2005-06-23 15:08:00 +08:00
|
|
|
return NULL;
|
|
|
|
|
}
|
2010-02-10 17:20:22 +08:00
|
|
|
#endif
|
2005-06-23 15:08:00 +08:00
|
|
|
|
2008-04-12 16:19:24 +08:00
|
|
|
void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
|
|
|
|
|
{
|
|
|
|
|
}
|
2010-02-10 17:20:21 +08:00
|
|
|
|
2007-06-09 04:46:51 +08:00
|
|
|
/*
|
|
|
|
|
* Allocate the accumulated non-linear sections, allocate a mem_map
|
|
|
|
|
* for each and record the physical to section mapping.
|
|
|
|
|
*/
|
|
|
|
|
void __init sparse_init(void)
|
|
|
|
|
{
|
|
|
|
|
unsigned long pnum;
|
|
|
|
|
struct page *map;
|
2007-10-16 16:25:56 +08:00
|
|
|
unsigned long *usemap;
|
2008-04-14 02:51:06 +08:00
|
|
|
unsigned long **usemap_map;
|
2010-02-28 01:29:38 +08:00
|
|
|
int size;
|
2010-02-10 17:20:21 +08:00
|
|
|
int nodeid_begin = 0;
|
|
|
|
|
unsigned long pnum_begin = 0;
|
|
|
|
|
unsigned long usemap_count;
|
2010-02-28 01:29:38 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
2010-02-10 17:20:22 +08:00
|
|
|
unsigned long map_count;
|
2010-02-28 01:29:38 +08:00
|
|
|
int size2;
|
|
|
|
|
struct page **map_map;
|
|
|
|
|
#endif
|
2008-04-14 02:51:06 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* map is using big page (aka 2M in x86 64 bit)
|
|
|
|
|
* usemap is less one page (aka 24 bytes)
|
|
|
|
|
* so alloc 2M (with 2M align) and 24 bytes in turn will
|
|
|
|
|
* make next 2M slip to one more 2M later.
|
|
|
|
|
* then in big system, the memory will have a lot of holes...
|
|
|
|
|
* here try to allocate 2M pages continously.
|
|
|
|
|
*
|
|
|
|
|
* powerpc need to call sparse_init_one_section right after each
|
|
|
|
|
* sparse_early_mem_map_alloc, so allocate usemap_map at first.
|
|
|
|
|
*/
|
|
|
|
|
size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
|
|
|
|
|
usemap_map = alloc_bootmem(size);
|
|
|
|
|
if (!usemap_map)
|
|
|
|
|
panic("can not allocate usemap_map\n");
|
2007-06-09 04:46:51 +08:00
|
|
|
|
|
|
|
|
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
|
2010-02-10 17:20:21 +08:00
|
|
|
struct mem_section *ms;
|
|
|
|
|
|
2007-10-16 16:24:11 +08:00
|
|
|
if (!present_section_nr(pnum))
|
2007-06-09 04:46:51 +08:00
|
|
|
continue;
|
2010-02-10 17:20:21 +08:00
|
|
|
ms = __nr_to_section(pnum);
|
|
|
|
|
nodeid_begin = sparse_early_nid(ms);
|
|
|
|
|
pnum_begin = pnum;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
usemap_count = 1;
|
|
|
|
|
for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
|
|
|
|
|
struct mem_section *ms;
|
|
|
|
|
int nodeid;
|
|
|
|
|
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
ms = __nr_to_section(pnum);
|
|
|
|
|
nodeid = sparse_early_nid(ms);
|
|
|
|
|
if (nodeid == nodeid_begin) {
|
|
|
|
|
usemap_count++;
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
/* ok, we need to take cake of from pnum_begin to pnum - 1*/
|
|
|
|
|
sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum,
|
|
|
|
|
usemap_count, nodeid_begin);
|
|
|
|
|
/* new start, update count etc*/
|
|
|
|
|
nodeid_begin = nodeid;
|
|
|
|
|
pnum_begin = pnum;
|
|
|
|
|
usemap_count = 1;
|
2008-04-14 02:51:06 +08:00
|
|
|
}
|
2010-02-10 17:20:21 +08:00
|
|
|
/* ok, last chunk */
|
|
|
|
|
sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
|
|
|
|
|
usemap_count, nodeid_begin);
|
2007-06-09 04:46:51 +08:00
|
|
|
|
2010-02-10 17:20:22 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
|
|
|
size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
|
|
|
|
|
map_map = alloc_bootmem(size2);
|
|
|
|
|
if (!map_map)
|
|
|
|
|
panic("can not allocate map_map\n");
|
|
|
|
|
|
|
|
|
|
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
|
|
|
|
|
struct mem_section *ms;
|
|
|
|
|
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
ms = __nr_to_section(pnum);
|
|
|
|
|
nodeid_begin = sparse_early_nid(ms);
|
|
|
|
|
pnum_begin = pnum;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
map_count = 1;
|
|
|
|
|
for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
|
|
|
|
|
struct mem_section *ms;
|
|
|
|
|
int nodeid;
|
|
|
|
|
|
|
|
|
|
if (!present_section_nr(pnum))
|
|
|
|
|
continue;
|
|
|
|
|
ms = __nr_to_section(pnum);
|
|
|
|
|
nodeid = sparse_early_nid(ms);
|
|
|
|
|
if (nodeid == nodeid_begin) {
|
|
|
|
|
map_count++;
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
/* ok, we need to take cake of from pnum_begin to pnum - 1*/
|
|
|
|
|
sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
|
|
|
|
|
map_count, nodeid_begin);
|
|
|
|
|
/* new start, update count etc*/
|
|
|
|
|
nodeid_begin = nodeid;
|
|
|
|
|
pnum_begin = pnum;
|
|
|
|
|
map_count = 1;
|
|
|
|
|
}
|
|
|
|
|
/* ok, last chunk */
|
|
|
|
|
sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
|
|
|
|
|
map_count, nodeid_begin);
|
|
|
|
|
#endif
|
|
|
|
|
|
2008-04-14 02:51:06 +08:00
|
|
|
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
|
|
|
|
|
if (!present_section_nr(pnum))
|
2007-06-09 04:46:51 +08:00
|
|
|
continue;
|
2007-10-16 16:25:56 +08:00
|
|
|
|
2008-04-14 02:51:06 +08:00
|
|
|
usemap = usemap_map[pnum];
|
2007-10-16 16:25:56 +08:00
|
|
|
if (!usemap)
|
|
|
|
|
continue;
|
|
|
|
|
|
2010-02-10 17:20:22 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
|
|
|
map = map_map[pnum];
|
|
|
|
|
#else
|
2008-04-14 02:51:06 +08:00
|
|
|
map = sparse_early_mem_map_alloc(pnum);
|
2010-02-10 17:20:22 +08:00
|
|
|
#endif
|
2008-04-14 02:51:06 +08:00
|
|
|
if (!map)
|
|
|
|
|
continue;
|
|
|
|
|
|
2007-10-16 16:25:56 +08:00
|
|
|
sparse_init_one_section(__nr_to_section(pnum), pnum, map,
|
|
|
|
|
usemap);
|
2007-06-09 04:46:51 +08:00
|
|
|
}
|
2008-04-14 02:51:06 +08:00
|
|
|
|
2008-04-12 16:19:24 +08:00
|
|
|
vmemmap_populate_print_last();
|
|
|
|
|
|
2010-02-10 17:20:22 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
|
|
|
free_bootmem(__pa(map_map), size2);
|
|
|
|
|
#endif
|
2008-04-14 02:51:06 +08:00
|
|
|
free_bootmem(__pa(usemap_map), size);
|
2007-06-09 04:46:51 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
2007-10-16 16:26:14 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM_VMEMMAP
|
|
|
|
|
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
|
|
|
|
|
unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
/* This will make the necessary allocations eventually. */
|
|
|
|
|
return sparse_mem_map_populate(pnum, nid);
|
|
|
|
|
}
|
|
|
|
|
static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
return; /* XXX: Not implemented yet */
|
|
|
|
|
}
|
2008-04-28 17:13:34 +08:00
|
|
|
static void free_map_bootmem(struct page *page, unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
}
|
2007-10-16 16:26:14 +08:00
|
|
|
#else
|
2005-10-30 09:16:55 +08:00
|
|
|
static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
struct page *page, *ret;
|
|
|
|
|
unsigned long memmap_size = sizeof(struct page) * nr_pages;
|
|
|
|
|
|
2006-10-29 01:38:32 +08:00
|
|
|
page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
|
2005-10-30 09:16:55 +08:00
|
|
|
if (page)
|
|
|
|
|
goto got_map_page;
|
|
|
|
|
|
|
|
|
|
ret = vmalloc(memmap_size);
|
|
|
|
|
if (ret)
|
|
|
|
|
goto got_map_ptr;
|
|
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
|
got_map_page:
|
|
|
|
|
ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
|
|
|
|
|
got_map_ptr:
|
|
|
|
|
memset(ret, 0, memmap_size);
|
|
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
2007-10-16 16:26:14 +08:00
|
|
|
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
|
|
|
|
|
unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
return __kmalloc_section_memmap(nr_pages);
|
|
|
|
|
}
|
|
|
|
|
|
2005-10-30 09:16:55 +08:00
|
|
|
static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
|
|
|
|
|
{
|
2008-02-05 14:28:34 +08:00
|
|
|
if (is_vmalloc_addr(memmap))
|
2005-10-30 09:16:55 +08:00
|
|
|
vfree(memmap);
|
|
|
|
|
else
|
|
|
|
|
free_pages((unsigned long)memmap,
|
|
|
|
|
get_order(sizeof(struct page) * nr_pages));
|
|
|
|
|
}
|
2008-04-28 17:13:34 +08:00
|
|
|
|
|
|
|
|
static void free_map_bootmem(struct page *page, unsigned long nr_pages)
|
|
|
|
|
{
|
|
|
|
|
unsigned long maps_section_nr, removing_section_nr, i;
|
|
|
|
|
int magic;
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i++, page++) {
|
|
|
|
|
magic = atomic_read(&page->_mapcount);
|
|
|
|
|
|
|
|
|
|
BUG_ON(magic == NODE_INFO);
|
|
|
|
|
|
|
|
|
|
maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
|
|
|
|
|
removing_section_nr = page->private;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* When this function is called, the removing section is
|
|
|
|
|
* logical offlined state. This means all pages are isolated
|
|
|
|
|
* from page allocator. If removing section's memmap is placed
|
|
|
|
|
* on the same section, it must not be freed.
|
|
|
|
|
* If it is freed, page allocator may allocate it which will
|
|
|
|
|
* be removed physically soon.
|
|
|
|
|
*/
|
|
|
|
|
if (maps_section_nr != removing_section_nr)
|
|
|
|
|
put_page_bootmem(page);
|
|
|
|
|
}
|
|
|
|
|
}
|
2007-10-16 16:26:14 +08:00
|
|
|
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
|
2005-10-30 09:16:55 +08:00
|
|
|
|
2008-04-28 17:12:01 +08:00
|
|
|
static void free_section_usemap(struct page *memmap, unsigned long *usemap)
|
|
|
|
|
{
|
2008-04-28 17:13:34 +08:00
|
|
|
struct page *usemap_page;
|
|
|
|
|
unsigned long nr_pages;
|
|
|
|
|
|
2008-04-28 17:12:01 +08:00
|
|
|
if (!usemap)
|
|
|
|
|
return;
|
|
|
|
|
|
2008-04-28 17:13:34 +08:00
|
|
|
usemap_page = virt_to_page(usemap);
|
2008-04-28 17:12:01 +08:00
|
|
|
/*
|
|
|
|
|
* Check to see if allocation came from hot-plug-add
|
|
|
|
|
*/
|
2008-04-28 17:13:34 +08:00
|
|
|
if (PageSlab(usemap_page)) {
|
2008-04-28 17:12:01 +08:00
|
|
|
kfree(usemap);
|
|
|
|
|
if (memmap)
|
|
|
|
|
__kfree_section_memmap(memmap, PAGES_PER_SECTION);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2008-04-28 17:13:34 +08:00
|
|
|
* The usemap came from bootmem. This is packed with other usemaps
|
|
|
|
|
* on the section which has pgdat at boot time. Just keep it as is now.
|
2008-04-28 17:12:01 +08:00
|
|
|
*/
|
2008-04-28 17:13:34 +08:00
|
|
|
|
|
|
|
|
if (memmap) {
|
|
|
|
|
struct page *memmap_page;
|
|
|
|
|
memmap_page = virt_to_page(memmap);
|
|
|
|
|
|
|
|
|
|
nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
|
|
|
|
|
>> PAGE_SHIFT;
|
|
|
|
|
|
|
|
|
|
free_map_bootmem(memmap_page, nr_pages);
|
|
|
|
|
}
|
2008-04-28 17:12:01 +08:00
|
|
|
}
|
|
|
|
|
|
2005-06-23 15:08:00 +08:00
|
|
|
/*
|
|
|
|
|
* returns the number of sections whose mem_maps were properly
|
|
|
|
|
* set. If this is <=0, then that means that the passed-in
|
|
|
|
|
* map was not consumed and must be freed.
|
|
|
|
|
*/
|
2008-11-23 01:33:24 +08:00
|
|
|
int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
|
2005-10-30 09:16:55 +08:00
|
|
|
int nr_pages)
|
2005-06-23 15:08:00 +08:00
|
|
|
{
|
2005-10-30 09:16:55 +08:00
|
|
|
unsigned long section_nr = pfn_to_section_nr(start_pfn);
|
|
|
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
|
|
|
struct mem_section *ms;
|
|
|
|
|
struct page *memmap;
|
2007-10-16 16:25:56 +08:00
|
|
|
unsigned long *usemap;
|
2005-10-30 09:16:55 +08:00
|
|
|
unsigned long flags;
|
|
|
|
|
int ret;
|
2005-06-23 15:08:00 +08:00
|
|
|
|
2005-10-30 09:16:55 +08:00
|
|
|
/*
|
|
|
|
|
* no locking for this, because it does its own
|
|
|
|
|
* plus, it does a kmalloc
|
|
|
|
|
*/
|
2007-12-18 08:19:59 +08:00
|
|
|
ret = sparse_index_init(section_nr, pgdat->node_id);
|
|
|
|
|
if (ret < 0 && ret != -EEXIST)
|
|
|
|
|
return ret;
|
2007-10-16 16:26:14 +08:00
|
|
|
memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
|
2007-12-18 08:19:59 +08:00
|
|
|
if (!memmap)
|
|
|
|
|
return -ENOMEM;
|
2007-10-16 16:25:56 +08:00
|
|
|
usemap = __kmalloc_section_usemap();
|
2007-12-18 08:19:59 +08:00
|
|
|
if (!usemap) {
|
|
|
|
|
__kfree_section_memmap(memmap, nr_pages);
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
}
|
2005-10-30 09:16:55 +08:00
|
|
|
|
|
|
|
|
pgdat_resize_lock(pgdat, &flags);
|
2005-06-23 15:08:00 +08:00
|
|
|
|
2005-10-30 09:16:55 +08:00
|
|
|
ms = __pfn_to_section(start_pfn);
|
|
|
|
|
if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
|
|
|
|
|
ret = -EEXIST;
|
|
|
|
|
goto out;
|
|
|
|
|
}
|
2007-10-16 16:25:56 +08:00
|
|
|
|
2005-06-23 15:08:00 +08:00
|
|
|
ms->section_mem_map |= SECTION_MARKED_PRESENT;
|
|
|
|
|
|
2007-10-16 16:25:56 +08:00
|
|
|
ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
|
2005-10-30 09:16:55 +08:00
|
|
|
|
|
|
|
|
out:
|
|
|
|
|
pgdat_resize_unlock(pgdat, &flags);
|
2007-12-18 08:19:59 +08:00
|
|
|
if (ret <= 0) {
|
|
|
|
|
kfree(usemap);
|
2006-05-02 03:16:09 +08:00
|
|
|
__kfree_section_memmap(memmap, nr_pages);
|
2007-12-18 08:19:59 +08:00
|
|
|
}
|
2005-10-30 09:16:55 +08:00
|
|
|
return ret;
|
2005-06-23 15:08:00 +08:00
|
|
|
}
|
2008-04-28 17:12:01 +08:00
|
|
|
|
|
|
|
|
void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
|
|
|
|
|
{
|
|
|
|
|
struct page *memmap = NULL;
|
|
|
|
|
unsigned long *usemap = NULL;
|
|
|
|
|
|
|
|
|
|
if (ms->section_mem_map) {
|
|
|
|
|
usemap = ms->pageblock_flags;
|
|
|
|
|
memmap = sparse_decode_mem_map(ms->section_mem_map,
|
|
|
|
|
__section_nr(ms));
|
|
|
|
|
ms->section_mem_map = 0;
|
|
|
|
|
ms->pageblock_flags = NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
free_section_usemap(memmap, usemap);
|
|
|
|
|
}
|
2007-05-08 15:23:07 +08:00
|
|
|
#endif
|