linux_dsm_epyc7002/include/linux/sched/mm.h
Aneesh Kumar K.V d7fefcc8de mm/cma: add PF flag to force non cma alloc
Patch series "mm/kvm/vfio/ppc64: Migrate compound pages out of CMA
region", v8.

ppc64 uses the CMA area for the allocation of guest page table (hash
page table).  We won't be able to start guest if we fail to allocate
hash page table.  We have observed hash table allocation failure because
we failed to migrate pages out of CMA region because they were pinned.
This happen when we are using VFIO.  VFIO on ppc64 pins the entire guest
RAM.  If the guest RAM pages get allocated out of CMA region, we won't
be able to migrate those pages.  The pages are also pinned for the
lifetime of the guest.

Currently we support migration of non-compound pages.  With THP and with
the addition of hugetlb migration we can end up allocating compound
pages from CMA region.  This patch series add support for migrating
compound pages.

This patch (of 4):

Add PF_MEMALLOC_NOCMA which make sure any allocation in that context is
marked non-movable and hence cannot be satisfied by CMA region.

This is useful with get_user_pages_longterm where we want to take a page
pin by migrating pages from CMA region.  Marking the section
PF_MEMALLOC_NOCMA ensures that we avoid unnecessary page migration
later.

Link: http://lkml.kernel.org/r/20190114095438.32470-2-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 21:07:19 -08:00

367 lines
10 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_MM_H
#define _LINUX_SCHED_MM_H
#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/gfp.h>
#include <linux/sync_core.h>
/*
* Routines for handling mm_structs
*/
extern struct mm_struct *mm_alloc(void);
/**
* mmgrab() - Pin a &struct mm_struct.
* @mm: The &struct mm_struct to pin.
*
* Make sure that @mm will not get freed even after the owning task
* exits. This doesn't guarantee that the associated address space
* will still exist later on and mmget_not_zero() has to be used before
* accessing it.
*
* This is a preferred way to to pin @mm for a longer/unbounded amount
* of time.
*
* Use mmdrop() to release the reference acquired by mmgrab().
*
* See also <Documentation/vm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmgrab(struct mm_struct *mm)
{
atomic_inc(&mm->mm_count);
}
extern void __mmdrop(struct mm_struct *mm);
static inline void mmdrop(struct mm_struct *mm)
{
/*
* The implicit full barrier implied by atomic_dec_and_test() is
* required by the membarrier system call before returning to
* user-space, after storing to rq->curr.
*/
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
__mmdrop(mm);
}
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
*
* Make sure that the address space of the given &struct mm_struct doesn't
* go away. This does not protect against parts of the address space being
* modified or freed, however.
*
* Never use this function to pin this address space for an
* unbounded/indefinite amount of time.
*
* Use mmput() to release the reference acquired by mmget().
*
* See also <Documentation/vm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmget(struct mm_struct *mm)
{
atomic_inc(&mm->mm_users);
}
static inline bool mmget_not_zero(struct mm_struct *mm)
{
return atomic_inc_not_zero(&mm->mm_users);
}
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
#ifdef CONFIG_MMU
/* same as above but performs the slow path from the async context. Can
* be called from the atomic context as well
*/
void mmput_async(struct mm_struct *);
#endif
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/*
* Grab a reference to a task's mm, if it is not already going away
* and ptrace_may_access with the mode parameter passed to it
* succeeds.
*/
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
#ifdef CONFIG_MEMCG
extern void mm_update_next_owner(struct mm_struct *mm);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}
#endif /* CONFIG_MEMCG */
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm,
struct rlimit *rlim_stack);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm,
struct rlimit *rlim_stack) {}
#endif
static inline bool in_vfork(struct task_struct *tsk)
{
bool ret;
/*
* need RCU to access ->real_parent if CLONE_VM was used along with
* CLONE_PARENT.
*
* We check real_parent->mm == tsk->mm because CLONE_VFORK does not
* imply CLONE_VM
*
* CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
* ->real_parent is not necessarily the task doing vfork(), so in
* theory we can't rely on task_lock() if we want to dereference it.
*
* And in this case we can't trust the real_parent->mm == tsk->mm
* check, it can be false negative. But we do not care, if init or
* another oom-unkillable task does this it should blame itself.
*/
rcu_read_lock();
ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
rcu_read_unlock();
return ret;
}
/*
* Applies per-task gfp context to the given allocation flags.
* PF_MEMALLOC_NOIO implies GFP_NOIO
* PF_MEMALLOC_NOFS implies GFP_NOFS
* PF_MEMALLOC_NOCMA implies no allocation from CMA region.
*/
static inline gfp_t current_gfp_context(gfp_t flags)
{
if (unlikely(current->flags &
(PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
/*
* NOIO implies both NOIO and NOFS and it is a weaker context
* so always make sure it makes precedence
*/
if (current->flags & PF_MEMALLOC_NOIO)
flags &= ~(__GFP_IO | __GFP_FS);
else if (current->flags & PF_MEMALLOC_NOFS)
flags &= ~__GFP_FS;
#ifdef CONFIG_CMA
if (current->flags & PF_MEMALLOC_NOCMA)
flags &= ~__GFP_MOVABLE;
#endif
}
return flags;
}
#ifdef CONFIG_LOCKDEP
extern void __fs_reclaim_acquire(void);
extern void __fs_reclaim_release(void);
extern void fs_reclaim_acquire(gfp_t gfp_mask);
extern void fs_reclaim_release(gfp_t gfp_mask);
#else
static inline void __fs_reclaim_acquire(void) { }
static inline void __fs_reclaim_release(void) { }
static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
static inline void fs_reclaim_release(gfp_t gfp_mask) { }
#endif
/**
* memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
*
* This functions marks the beginning of the GFP_NOIO allocation scope.
* All further allocations will implicitly drop __GFP_IO flag and so
* they are safe for the IO critical section from the allocation recursion
* point of view. Use memalloc_noio_restore to end the scope with flags
* returned by this function.
*
* This function is safe to be used from any context.
*/
static inline unsigned int memalloc_noio_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
current->flags |= PF_MEMALLOC_NOIO;
return flags;
}
/**
* memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
* @flags: Flags to restore.
*
* Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
* Always make sure that that the given flags is the return value from the
* pairing memalloc_noio_save call.
*/
static inline void memalloc_noio_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}
/**
* memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
*
* This functions marks the beginning of the GFP_NOFS allocation scope.
* All further allocations will implicitly drop __GFP_FS flag and so
* they are safe for the FS critical section from the allocation recursion
* point of view. Use memalloc_nofs_restore to end the scope with flags
* returned by this function.
*
* This function is safe to be used from any context.
*/
static inline unsigned int memalloc_nofs_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
current->flags |= PF_MEMALLOC_NOFS;
return flags;
}
/**
* memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
* @flags: Flags to restore.
*
* Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
* Always make sure that that the given flags is the return value from the
* pairing memalloc_nofs_save call.
*/
static inline void memalloc_nofs_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
}
static inline unsigned int memalloc_noreclaim_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC;
current->flags |= PF_MEMALLOC;
return flags;
}
static inline void memalloc_noreclaim_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}
#ifdef CONFIG_CMA
static inline unsigned int memalloc_nocma_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
current->flags |= PF_MEMALLOC_NOCMA;
return flags;
}
static inline void memalloc_nocma_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
}
#else
static inline unsigned int memalloc_nocma_save(void)
{
return 0;
}
static inline void memalloc_nocma_restore(unsigned int flags)
{
}
#endif
#ifdef CONFIG_MEMCG
/**
* memalloc_use_memcg - Starts the remote memcg charging scope.
* @memcg: memcg to charge.
*
* This function marks the beginning of the remote memcg charging scope. All the
* __GFP_ACCOUNT allocations till the end of the scope will be charged to the
* given memcg.
*
* NOTE: This function is not nesting safe.
*/
static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
{
WARN_ON_ONCE(current->active_memcg);
current->active_memcg = memcg;
}
/**
* memalloc_unuse_memcg - Ends the remote memcg charging scope.
*
* This function marks the end of the remote memcg charging scope started by
* memalloc_use_memcg().
*/
static inline void memalloc_unuse_memcg(void)
{
current->active_memcg = NULL;
}
#else
static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
{
}
static inline void memalloc_unuse_memcg(void)
{
}
#endif
#ifdef CONFIG_MEMBARRIER
enum {
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0),
MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1),
MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2),
MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5),
};
enum {
MEMBARRIER_FLAG_SYNC_CORE = (1U << 0),
};
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
#include <asm/membarrier.h>
#endif
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
if (likely(!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
return;
sync_core_before_usermode();
}
static inline void membarrier_execve(struct task_struct *t)
{
atomic_set(&t->mm->membarrier_state, 0);
}
#else
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
struct mm_struct *next,
struct task_struct *tsk)
{
}
#endif
static inline void membarrier_execve(struct task_struct *t)
{
}
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
}
#endif
#endif /* _LINUX_SCHED_MM_H */