linux-stable/include/linux/mempolicy.h

261 lines
6.4 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 */
#define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */
/* Flags for mbind */
#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */
#define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to mapping */
#define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to mapping */
#define MPOL_MF_INTERNAL (1<<3) /* Internal flags start here */
#ifdef __KERNEL__
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>
struct vm_area_struct;
struct mm_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;
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:56 +00:00
nodemask_t cpuset_mems_allowed; /* mempolicy relative to these nodes */
};
/*
* 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)
/*
* 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;
};
void mpol_shared_policy_init(struct shared_policy *info, int policy,
nodemask_t *nodes);
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);
extern void numa_default_policy(void);
extern void numa_policy_init(void);
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:56 +00:00
extern void mpol_rebind_task(struct task_struct *tsk,
const nodemask_t *new);
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:59 +00:00
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
extern void mpol_fix_fork_child_flag(struct task_struct *p);
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:59 +00:00
extern struct mempolicy default_policy;
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
Fix NUMA Memory Policy Reference Counting This patch proposes fixes to the reference counting of memory policy in the page allocation paths and in show_numa_map(). Extracted from my "Memory Policy Cleanups and Enhancements" series as stand-alone. Shared policy lookup [shmem] has always added a reference to the policy, but this was never unrefed after page allocation or after formatting the numa map data. Default system policy should not require additional ref counting, nor should the current task's task policy. However, show_numa_map() calls get_vma_policy() to examine what may be [likely is] another task's policy. The latter case needs protection against freeing of the policy. This patch adds a reference count to a mempolicy returned by get_vma_policy() when the policy is a vma policy or another task's mempolicy. Again, shared policy is already reference counted on lookup. A matching "unref" [__mpol_free()] is performed in alloc_page_vma() for shared and vma policies, and in show_numa_map() for shared and another task's mempolicy. We can call __mpol_free() directly, saving an admittedly inexpensive inline NULL test, because we know we have a non-NULL policy. Handling policy ref counts for hugepages is a bit trickier. huge_zonelist() returns a zone list that might come from a shared or vma 'BIND policy. In this case, we should hold the reference until after the huge page allocation in dequeue_hugepage(). The patch modifies huge_zonelist() to return a pointer to the mempolicy if it needs to be unref'd after allocation. Kernel Build [16cpu, 32GB, ia64] - average of 10 runs: w/o patch w/ refcount patch Avg Std Devn Avg Std Devn Real: 100.59 0.38 100.63 0.43 User: 1209.60 0.37 1209.91 0.31 System: 81.52 0.42 81.64 0.34 Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Andi Kleen <ak@suse.de> Cc: Christoph Lameter <clameter@sgi.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 05:46:47 +00:00
unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol);
[PATCH] NUMA policies in the slab allocator V2 This patch fixes a regression in 2.6.14 against 2.6.13 that causes an imbalance in memory allocation during bootup. The slab allocator in 2.6.13 is not numa aware and simply calls alloc_pages(). This means that memory policies may control the behavior of alloc_pages(). During bootup the memory policy is set to MPOL_INTERLEAVE resulting in the spreading out of allocations during bootup over all available nodes. The slab allocator in 2.6.13 has only a single list of slab pages. As a result the per cpu slab cache and the spinlock controlled page lists may contain slab entries from off node memory. The slab allocator in 2.6.13 makes no effort to discern the locality of an entry on its lists. The NUMA aware slab allocator in 2.6.14 controls locality of the slab pages explicitly by calling alloc_pages_node(). The NUMA slab allocator manages slab entries by having lists of available slab pages for each node. The per cpu slab cache can only contain slab entries associated with the node local to the processor. This guarantees that the default allocation mode of the slab allocator always assigns local memory if available. Setting MPOL_INTERLEAVE as a default policy during bootup has no effect anymore. In 2.6.14 all node unspecific slab allocations are performed on the boot processor. This means that most of key data structures are allocated on one node. Most processors will have to refer to these structures making the boot node a potential bottleneck. This may reduce performance and cause unnecessary memory pressure on the boot node. This patch implements NUMA policies in the slab layer. There is the need of explicit application of NUMA memory policies by the slab allcator itself since the NUMA slab allocator does no longer let the page_allocator control locality. The check for policies is made directly at the beginning of __cache_alloc using current->mempolicy. The memory policy is already frequently checked by the page allocator (alloc_page_vma() and alloc_page_current()). So it is highly likely that the cacheline is present. For MPOL_INTERLEAVE kmalloc() will spread out each request to one node after another so that an equal distribution of allocations can be obtained during bootup. It is not possible to push the policy check to lower layers of the NUMA slab allocator since the per cpu caches are now only containing slab entries from the current node. If the policy says that the local node is not to be preferred or forbidden then there is no point in checking the slab cache or local list of slab pages. The allocation better be directed immediately to the lists containing slab entries for the allowed set of nodes. This way of applying policy also fixes another strange behavior in 2.6.13. alloc_pages() is controlled by the memory allocation policy of the current process. It could therefore be that one process is running with MPOL_INTERLEAVE and would f.e. obtain a new page following that policy since no slab entries are in the lists anymore. A page can typically be used for multiple slab entries but lets say that the current process is only using one. The other entries are then added to the slab lists. These are now non local entries in the slab lists despite of the possible availability of local pages that would provide faster access and increase the performance of the application. Another process without MPOL_INTERLEAVE may now run and expect a local slab entry from kmalloc(). However, there are still these free slab entries from the off node page obtained from the other process via MPOL_INTERLEAVE in the cache. The process will then get an off node slab entry although other slab entries may be available that are local to that process. This means that the policy if one process may contaminate the locality of the slab caches for other processes. This patch in effect insures that a per process policy is followed for the allocation of slab entries and that there cannot be a memory policy influence from one process to another. A process with default policy will always get a local slab entry if one is available. And the process using memory policies will get its memory arranged as requested. Off-node slab allocation will require the use of spinlocks and will make the use of per cpu caches not possible. A process using memory policies to redirect allocations offnode will have to cope with additional lock overhead in addition to the latency added by the need to access a remote slab entry. Changes V1->V2 - Remove #ifdef CONFIG_NUMA by moving forward declaration into prior #ifdef CONFIG_NUMA section. - Give the function determining the node number to use a saner name. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 01:42:36 +00:00
extern unsigned slab_node(struct mempolicy *policy);
extern enum zone_type policy_zone;
static inline void check_highest_zone(enum zone_type k)
{
Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE The NUMA layer only supports NUMA policies for the highest zone. When ZONE_MOVABLE is configured with kernelcore=, the the highest zone becomes ZONE_MOVABLE. The result is that policies are only applied to allocations like anonymous pages and page cache allocated from ZONE_MOVABLE when the zone is used. This patch applies policies to the two highest zones when the highest zone is ZONE_MOVABLE. As ZONE_MOVABLE consists of pages from the highest "real" zone, it's always functionally equivalent. The patch has been tested on a variety of machines both NUMA and non-NUMA covering x86, x86_64 and ppc64. No abnormal results were seen in kernbench, tbench, dbench or hackbench. It passes regression tests from the numactl package with and without kernelcore= once numactl tests are patched to wait for vmstat counters to update. akpm: this is the nasty hack to fix NUMA mempolicies in the presence of ZONE_MOVABLE and kernelcore= in 2.6.23. Christoph says "For .24 either merge the mobility or get the other solution that Mel is working on. That solution would only use a single zonelist per node and filter on the fly. That may help performance and also help to make memory policies work better." Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-22 21:02:05 +00:00
if (k > policy_zone && k != ZONE_MOVABLE)
policy_zone = k;
}
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:00:51 +00:00
int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
#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;
}
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,
int policy, nodemask_t *nodes)
{
}
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] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:56 +00:00
static inline void mpol_rebind_task(struct task_struct *tsk,
[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
const nodemask_t *new)
{
}
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:01:59 +00:00
static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
}
static inline void mpol_fix_fork_child_flag(struct task_struct *p)
{
}
static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
Fix NUMA Memory Policy Reference Counting This patch proposes fixes to the reference counting of memory policy in the page allocation paths and in show_numa_map(). Extracted from my "Memory Policy Cleanups and Enhancements" series as stand-alone. Shared policy lookup [shmem] has always added a reference to the policy, but this was never unrefed after page allocation or after formatting the numa map data. Default system policy should not require additional ref counting, nor should the current task's task policy. However, show_numa_map() calls get_vma_policy() to examine what may be [likely is] another task's policy. The latter case needs protection against freeing of the policy. This patch adds a reference count to a mempolicy returned by get_vma_policy() when the policy is a vma policy or another task's mempolicy. Again, shared policy is already reference counted on lookup. A matching "unref" [__mpol_free()] is performed in alloc_page_vma() for shared and vma policies, and in show_numa_map() for shared and another task's mempolicy. We can call __mpol_free() directly, saving an admittedly inexpensive inline NULL test, because we know we have a non-NULL policy. Handling policy ref counts for hugepages is a bit trickier. huge_zonelist() returns a zone list that might come from a shared or vma 'BIND policy. In this case, we should hold the reference until after the huge page allocation in dequeue_hugepage(). The patch modifies huge_zonelist() to return a pointer to the mempolicy if it needs to be unref'd after allocation. Kernel Build [16cpu, 32GB, ia64] - average of 10 runs: w/o patch w/ refcount patch Avg Std Devn Avg Std Devn Real: 100.59 0.38 100.63 0.43 User: 1209.60 0.37 1209.91 0.31 System: 81.52 0.42 81.64 0.34 Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Andi Kleen <ak@suse.de> Cc: Christoph Lameter <clameter@sgi.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 05:46:47 +00:00
unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
{
return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags);
}
static inline int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes,
const nodemask_t *to_nodes, int flags)
{
return 0;
}
static inline void check_highest_zone(int k)
{
}
#endif /* CONFIG_NUMA */
#endif /* __KERNEL__ */
#endif