kernel-ark/include/linux/mempolicy.h

239 lines
5.6 KiB
C
Raw Normal View History

#ifndef _LINUX_MEMPOLICY_H
#define _LINUX_MEMPOLICY_H 1
#include <linux/errno.h>
/*
* NUMA memory policies for Linux.
* Copyright 2003,2004 Andi Kleen SuSE Labs
*/
/* Policies */
#define MPOL_DEFAULT 0
#define MPOL_PREFERRED 1
#define MPOL_BIND 2
#define MPOL_INTERLEAVE 3
#define MPOL_MAX MPOL_INTERLEAVE
/* Flags for get_mem_policy */
#define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */
#define MPOL_F_ADDR (1<<1) /* look up vma using address */
/* Flags for mbind */
#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */
#ifdef __KERNEL__
#include <linux/config.h>
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>
struct vm_area_struct;
#ifdef CONFIG_NUMA
/*
* Describe a memory policy.
*
* A mempolicy can be either associated with a process or with a VMA.
* For VMA related allocations the VMA policy is preferred, otherwise
* the process policy is used. Interrupts ignore the memory policy
* of the current process.
*
* Locking policy for interlave:
* In process context there is no locking because only the process accesses
* its own state. All vma manipulation is somewhat protected by a down_read on
* mmap_sem.
*
* Freeing policy:
* When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
* All other policies don't have any external state. mpol_free() handles this.
*
* Copying policy objects:
* For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this.
*/
struct mempolicy {
atomic_t refcnt;
short policy; /* See MPOL_* above */
union {
struct zonelist *zonelist; /* bind */
short preferred_node; /* preferred */
nodemask_t nodes; /* interleave */
/* undefined for default */
} v;
};
/*
* Support for managing mempolicy data objects (clone, copy, destroy)
* The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
*/
extern void __mpol_free(struct mempolicy *pol);
static inline void mpol_free(struct mempolicy *pol)
{
if (pol)
__mpol_free(pol);
}
extern struct mempolicy *__mpol_copy(struct mempolicy *pol);
static inline struct mempolicy *mpol_copy(struct mempolicy *pol)
{
if (pol)
pol = __mpol_copy(pol);
return pol;
}
#define vma_policy(vma) ((vma)->vm_policy)
#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol))
static inline void mpol_get(struct mempolicy *pol)
{
if (pol)
atomic_inc(&pol->refcnt);
}
extern int __mpol_equal(struct mempolicy *a, struct mempolicy *b);
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (a == b)
return 1;
return __mpol_equal(a, b);
}
#define vma_mpol_equal(a,b) mpol_equal(vma_policy(a), vma_policy(b))
/* Could later add inheritance of the process policy here. */
#define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL)
/*
* Hugetlb policy. i386 hugetlb so far works with node numbers
* instead of zone lists, so give it special interfaces for now.
*/
extern int mpol_first_node(struct vm_area_struct *vma, unsigned long addr);
extern int mpol_node_valid(int nid, struct vm_area_struct *vma,
unsigned long addr);
/*
* Tree of shared policies for a shared memory region.
* Maintain the policies in a pseudo mm that contains vmas. The vmas
* carry the policy. As a special twist the pseudo mm is indexed in pages, not
* bytes, so that we can work with shared memory segments bigger than
* unsigned long.
*/
struct sp_node {
struct rb_node nd;
unsigned long start, end;
struct mempolicy *policy;
};
struct shared_policy {
struct rb_root root;
spinlock_t lock;
};
static inline void mpol_shared_policy_init(struct shared_policy *info)
{
info->root = RB_ROOT;
spin_lock_init(&info->lock);
}
int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma,
struct mempolicy *new);
void mpol_free_shared_policy(struct shared_policy *p);
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
unsigned long idx);
[PATCH] /proc/<pid>/numa_maps to show on which nodes pages reside This patch was recently discussed on linux-mm: http://marc.theaimsgroup.com/?t=112085728500002&r=1&w=2 I inherited a large code base from Ray for page migration. There was a small patch in there that I find to be very useful since it allows the display of the locality of the pages in use by a process. I reworked that patch and came up with a /proc/<pid>/numa_maps that gives more information about the vma's of a process. numa_maps is indexes by the start address found in /proc/<pid>/maps. F.e. with this patch you can see the page use of the "getty" process: margin:/proc/12008 # cat maps 00000000-00004000 r--p 00000000 00:00 0 2000000000000000-200000000002c000 r-xp 00000000 08:04 516 /lib/ld-2.3.3.so 2000000000038000-2000000000040000 rw-p 00028000 08:04 516 /lib/ld-2.3.3.so 2000000000040000-2000000000044000 rw-p 2000000000040000 00:00 0 2000000000058000-2000000000260000 r-xp 00000000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000260000-2000000000268000 ---p 00208000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000268000-2000000000274000 rw-p 00200000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000274000-2000000000280000 rw-p 2000000000274000 00:00 0 2000000000280000-20000000002b4000 r--p 00000000 08:04 9126923 /usr/lib/locale/en_US.utf8/LC_CTYPE 2000000000300000-2000000000308000 r--s 00000000 08:04 60071467 /usr/lib/gconv/gconv-modules.cache 2000000000318000-2000000000328000 rw-p 2000000000318000 00:00 0 4000000000000000-4000000000008000 r-xp 00000000 08:04 29576399 /sbin/mingetty 6000000000004000-6000000000008000 rw-p 00004000 08:04 29576399 /sbin/mingetty 6000000000008000-600000000002c000 rw-p 6000000000008000 00:00 0 [heap] 60000fff7fffc000-60000fff80000000 rw-p 60000fff7fffc000 00:00 0 60000ffffff44000-60000ffffff98000 rw-p 60000ffffff44000 00:00 0 [stack] a000000000000000-a000000000020000 ---p 00000000 00:00 0 [vdso] cat numa_maps 2000000000000000 default MaxRef=43 Pages=11 Mapped=11 N0=4 N1=3 N2=2 N3=2 2000000000038000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000040000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 2000000000058000 default MaxRef=43 Pages=61 Mapped=61 N0=14 N1=15 N2=16 N3=16 2000000000268000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000274000 default MaxRef=1 Pages=3 Mapped=3 Anon=3 N0=3 2000000000280000 default MaxRef=8 Pages=3 Mapped=3 N0=3 2000000000300000 default MaxRef=8 Pages=2 Mapped=2 N0=2 2000000000318000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N2=1 4000000000000000 default MaxRef=6 Pages=2 Mapped=2 N1=2 6000000000004000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 6000000000008000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000fff7fffc000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000ffffff44000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 getty uses ld.so. The first vma is the code segment which is used by 43 other processes and the pages are evenly distributed over the 4 nodes. The second vma is the process specific data portion for ld.so. This is only one page. The display format is: <startaddress> Links to information in /proc/<pid>/map <memory policy> This can be "default" "interleave={}", "prefer=<node>" or "bind={<zones>}" MaxRef= <maximum reference to a page in this vma> Pages= <Nr of pages in use> Mapped= <Nr of pages with mapcount > Anon= <nr of anonymous pages> Nx= <Nr of pages on Node x> The content of the proc-file is self-evident. If this would be tied into the sparsemem system then the contents of this file would not be too useful. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-03 22:54:45 +00:00
struct mempolicy *get_vma_policy(struct task_struct *task,
struct vm_area_struct *vma, unsigned long addr);
extern void numa_default_policy(void);
extern void numa_policy_init(void);
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 23:02:36 +00:00
extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new);
extern struct mempolicy default_policy;
#else
struct mempolicy {};
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
return 1;
}
#define vma_mpol_equal(a,b) 1
#define mpol_set_vma_default(vma) do {} while(0)
static inline void mpol_free(struct mempolicy *p)
{
}
static inline void mpol_get(struct mempolicy *pol)
{
}
static inline struct mempolicy *mpol_copy(struct mempolicy *old)
{
return NULL;
}
static inline int mpol_first_node(struct vm_area_struct *vma, unsigned long a)
{
return numa_node_id();
}
static inline int
mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long a)
{
return 1;
}
struct shared_policy {};
static inline int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma,
struct mempolicy *new)
{
return -EINVAL;
}
static inline void mpol_shared_policy_init(struct shared_policy *info)
{
}
static inline void mpol_free_shared_policy(struct shared_policy *p)
{
}
static inline struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
return NULL;
}
#define vma_policy(vma) NULL
#define vma_set_policy(vma, pol) do {} while(0)
static inline void numa_policy_init(void)
{
}
static inline void numa_default_policy(void)
{
}
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 23:02:36 +00:00
static inline void numa_policy_rebind(const nodemask_t *old,
const nodemask_t *new)
{
}
#endif /* CONFIG_NUMA */
#endif /* __KERNEL__ */
#endif