![Miao Xie](/assets/img/avatar_default.png)
Nick Piggin reported that the allocator may see an empty nodemask when changing cpuset's mems[1]. It happens only on the kernel that do not do atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG) But I found that there is also a problem on the kernel that can do atomic nodemask_t stores. The problem is that the allocator can't find a node to alloc page when changing cpuset's mems though there is a lot of free memory. The reason is like this: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom I can use the attached program reproduce it by the following step: # mkdir /dev/cpuset # mount -t cpuset cpuset /dev/cpuset # mkdir /dev/cpuset/1 # echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus # echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems # echo $$ > /dev/cpuset/1/tasks # numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog <nr_tasks> & <nr_tasks> = max(nr_cpus - 1, 1) # killall -s SIGUSR1 cpuset_mem_hog # ./change_mems.sh several hours later, oom will happen though there is a lot of free memory. This patchset fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. This patch: In order to fix no node to alloc memory, when we want to update mempolicy and mems_allowed, we expand the set of nodes first (set all the newly nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the mempolicy's rebind functions may breaks the expanding. So we restructure the mempolicy's rebind functions and split the rebind work to two steps, just like the update of cpuset's mems: The 1st step: expand the set of the mempolicy's nodes. The 2nd step: shrink the set of the mempolicy's nodes. It is used when there is no real lock to protect the mempolicy in the read-side. Otherwise we can do rebind work at once. In order to implement it, we define enum mpol_rebind_step { MPOL_REBIND_ONCE, MPOL_REBIND_STEP1, MPOL_REBIND_STEP2, MPOL_REBIND_NSTEP, }; If the mempolicy needn't be updated by two steps, we can pass MPOL_REBIND_ONCE to the rebind functions. Or we can pass MPOL_REBIND_STEP1 to do the first step of the rebind work and pass MPOL_REBIND_STEP2 to do the second step work. Besides that, it maybe long time between these two step and we have to release the lock that protects mempolicy and mems_allowed. If we hold the lock once again, we must check whether the current mempolicy is under the rebinding (the first step has been done) or not, because the task may alloc a new mempolicy when we don't hold the lock. So we defined the following flag to identify it: #define MPOL_F_REBINDING (1 << 2) The new functions will be used in the next patch. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Menage <menage@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
372 lines
9.4 KiB
C
372 lines
9.4 KiB
C
#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
|
|
*/
|
|
|
|
/*
|
|
* Both the MPOL_* mempolicy mode and the MPOL_F_* optional mode flags are
|
|
* passed by the user to either set_mempolicy() or mbind() in an 'int' actual.
|
|
* The MPOL_MODE_FLAGS macro determines the legal set of optional mode flags.
|
|
*/
|
|
|
|
/* Policies */
|
|
enum {
|
|
MPOL_DEFAULT,
|
|
MPOL_PREFERRED,
|
|
MPOL_BIND,
|
|
MPOL_INTERLEAVE,
|
|
MPOL_MAX, /* always last member of enum */
|
|
};
|
|
|
|
enum mpol_rebind_step {
|
|
MPOL_REBIND_ONCE, /* do rebind work at once(not by two step) */
|
|
MPOL_REBIND_STEP1, /* first step(set all the newly nodes) */
|
|
MPOL_REBIND_STEP2, /* second step(clean all the disallowed nodes)*/
|
|
MPOL_REBIND_NSTEP,
|
|
};
|
|
|
|
/* Flags for set_mempolicy */
|
|
#define MPOL_F_STATIC_NODES (1 << 15)
|
|
#define MPOL_F_RELATIVE_NODES (1 << 14)
|
|
|
|
/*
|
|
* MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to
|
|
* either set_mempolicy() or mbind().
|
|
*/
|
|
#define MPOL_MODE_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES)
|
|
|
|
/* Flags for get_mempolicy */
|
|
#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 */
|
|
|
|
/*
|
|
* Internal flags that share the struct mempolicy flags word with
|
|
* "mode flags". These flags are allocated from bit 0 up, as they
|
|
* are never OR'ed into the mode in mempolicy API arguments.
|
|
*/
|
|
#define MPOL_F_SHARED (1 << 0) /* identify shared policies */
|
|
#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
|
|
#define MPOL_F_REBINDING (1 << 2) /* identify policies in rebinding */
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/nodemask.h>
|
|
#include <linux/pagemap.h>
|
|
|
|
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:
|
|
* Mempolicy objects are reference counted. A mempolicy will be freed when
|
|
* mpol_put() decrements the reference count to zero.
|
|
*
|
|
* Duplicating policy objects:
|
|
* mpol_dup() allocates a new mempolicy and copies the specified mempolicy
|
|
* to the new storage. The reference count of the new object is initialized
|
|
* to 1, representing the caller of mpol_dup().
|
|
*/
|
|
struct mempolicy {
|
|
atomic_t refcnt;
|
|
unsigned short mode; /* See MPOL_* above */
|
|
unsigned short flags; /* See set_mempolicy() MPOL_F_* above */
|
|
union {
|
|
short preferred_node; /* preferred */
|
|
nodemask_t nodes; /* interleave/bind */
|
|
/* undefined for default */
|
|
} v;
|
|
union {
|
|
nodemask_t cpuset_mems_allowed; /* relative to these nodes */
|
|
nodemask_t user_nodemask; /* nodemask passed by user */
|
|
} w;
|
|
};
|
|
|
|
/*
|
|
* 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_put(struct mempolicy *pol);
|
|
static inline void mpol_put(struct mempolicy *pol)
|
|
{
|
|
if (pol)
|
|
__mpol_put(pol);
|
|
}
|
|
|
|
/*
|
|
* Does mempolicy pol need explicit unref after use?
|
|
* Currently only needed for shared policies.
|
|
*/
|
|
static inline int mpol_needs_cond_ref(struct mempolicy *pol)
|
|
{
|
|
return (pol && (pol->flags & MPOL_F_SHARED));
|
|
}
|
|
|
|
static inline void mpol_cond_put(struct mempolicy *pol)
|
|
{
|
|
if (mpol_needs_cond_ref(pol))
|
|
__mpol_put(pol);
|
|
}
|
|
|
|
extern struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
|
|
struct mempolicy *frompol);
|
|
static inline struct mempolicy *mpol_cond_copy(struct mempolicy *tompol,
|
|
struct mempolicy *frompol)
|
|
{
|
|
if (!frompol)
|
|
return frompol;
|
|
return __mpol_cond_copy(tompol, frompol);
|
|
}
|
|
|
|
extern struct mempolicy *__mpol_dup(struct mempolicy *pol);
|
|
static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
|
|
{
|
|
if (pol)
|
|
pol = __mpol_dup(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);
|
|
}
|
|
|
|
/*
|
|
* 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 *sp, struct mempolicy *mpol);
|
|
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);
|
|
extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
|
|
enum mpol_rebind_step step);
|
|
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
|
|
extern void mpol_fix_fork_child_flag(struct task_struct *p);
|
|
|
|
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
|
|
unsigned long addr, gfp_t gfp_flags,
|
|
struct mempolicy **mpol, nodemask_t **nodemask);
|
|
extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
|
|
extern unsigned slab_node(struct mempolicy *policy);
|
|
|
|
extern enum zone_type policy_zone;
|
|
|
|
static inline void check_highest_zone(enum zone_type k)
|
|
{
|
|
if (k > policy_zone && k != ZONE_MOVABLE)
|
|
policy_zone = k;
|
|
}
|
|
|
|
int do_migrate_pages(struct mm_struct *mm,
|
|
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
|
|
|
|
|
|
#ifdef CONFIG_TMPFS
|
|
extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context);
|
|
|
|
extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
|
|
int no_context);
|
|
#endif
|
|
|
|
/* Check if a vma is migratable */
|
|
static inline int vma_migratable(struct vm_area_struct *vma)
|
|
{
|
|
if (vma->vm_flags & (VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED))
|
|
return 0;
|
|
/*
|
|
* Migration allocates pages in the highest zone. If we cannot
|
|
* do so then migration (at least from node to node) is not
|
|
* possible.
|
|
*/
|
|
if (vma->vm_file &&
|
|
gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping))
|
|
< policy_zone)
|
|
return 0;
|
|
return 1;
|
|
}
|
|
|
|
#else
|
|
|
|
struct mempolicy {};
|
|
|
|
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline void mpol_put(struct mempolicy *p)
|
|
{
|
|
}
|
|
|
|
static inline void mpol_cond_put(struct mempolicy *pol)
|
|
{
|
|
}
|
|
|
|
static inline struct mempolicy *mpol_cond_copy(struct mempolicy *to,
|
|
struct mempolicy *from)
|
|
{
|
|
return from;
|
|
}
|
|
|
|
static inline void mpol_get(struct mempolicy *pol)
|
|
{
|
|
}
|
|
|
|
static inline struct mempolicy *mpol_dup(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 *sp,
|
|
struct mempolicy *mpol)
|
|
{
|
|
}
|
|
|
|
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)
|
|
{
|
|
}
|
|
|
|
static inline void mpol_rebind_task(struct task_struct *tsk,
|
|
const nodemask_t *new,
|
|
enum mpol_rebind_step step)
|
|
{
|
|
}
|
|
|
|
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,
|
|
unsigned long addr, gfp_t gfp_flags,
|
|
struct mempolicy **mpol, nodemask_t **nodemask)
|
|
{
|
|
*mpol = NULL;
|
|
*nodemask = NULL;
|
|
return node_zonelist(0, gfp_flags);
|
|
}
|
|
|
|
static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; }
|
|
|
|
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)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_TMPFS
|
|
static inline int mpol_parse_str(char *str, struct mempolicy **mpol,
|
|
int no_context)
|
|
{
|
|
return 1; /* error */
|
|
}
|
|
|
|
static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
|
|
int no_context)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif
|