#include <linux/pgtable.h>
#include <linux/kasan.h>
#include <linux/memremap.h>
+#include <linux/slab.h>
struct mempolicy;
struct anon_vma;
struct vm_area_struct *vm_area_alloc(struct mm_struct *);
struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
void vm_area_free(struct vm_area_struct *);
+/* Use only if VMA has no other users */
+void __vm_area_free(struct vm_area_struct *vma);
#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
{ FAULT_FLAG_USER, "USER" }, \
{ FAULT_FLAG_REMOTE, "REMOTE" }, \
{ FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \
- { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }
+ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \
+ { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" }
/*
* vm_fault is filled by the pagefault handler and passed to the vma's
unsigned long addr);
};
-#ifdef CONFIG_PER_VMA_LOCK
-static inline void vma_init_lock(struct vm_area_struct *vma)
+#ifdef CONFIG_NUMA_BALANCING
+static inline void vma_numab_state_init(struct vm_area_struct *vma)
+{
+ vma->numab_state = NULL;
+}
+static inline void vma_numab_state_free(struct vm_area_struct *vma)
{
- init_rwsem(&vma->lock);
- vma->vm_lock_seq = -1;
+ kfree(vma->numab_state);
}
+#else
+static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
+static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
+#endif /* CONFIG_NUMA_BALANCING */
+#ifdef CONFIG_PER_VMA_LOCK
/*
* Try to read-lock a vma. The function is allowed to occasionally yield false
* locked result to avoid performance overhead, in which case we fall back to
if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
return false;
- if (unlikely(down_read_trylock(&vma->lock) == 0))
+ if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
return false;
/*
* Overflow might produce false locked result.
* False unlocked result is impossible because we modify and check
- * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq
+ * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
* modification invalidates all existing locks.
*/
if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
- up_read(&vma->lock);
+ up_read(&vma->vm_lock->lock);
return false;
}
return true;
static inline void vma_end_read(struct vm_area_struct *vma)
{
rcu_read_lock(); /* keeps vma alive till the end of up_read */
- up_read(&vma->lock);
+ up_read(&vma->vm_lock->lock);
rcu_read_unlock();
}
-static inline void vma_start_write(struct vm_area_struct *vma)
+static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
{
- int mm_lock_seq;
-
mmap_assert_write_locked(vma->vm_mm);
/*
* current task is holding mmap_write_lock, both vma->vm_lock_seq and
* mm->mm_lock_seq can't be concurrently modified.
*/
- mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
- if (vma->vm_lock_seq == mm_lock_seq)
+ *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
+ return (vma->vm_lock_seq == *mm_lock_seq);
+}
+
+static inline void vma_start_write(struct vm_area_struct *vma)
+{
+ int mm_lock_seq;
+
+ if (__is_vma_write_locked(vma, &mm_lock_seq))
return;
- down_write(&vma->lock);
+ down_write(&vma->vm_lock->lock);
vma->vm_lock_seq = mm_lock_seq;
- up_write(&vma->lock);
+ up_write(&vma->vm_lock->lock);
+}
+
+static inline bool vma_try_start_write(struct vm_area_struct *vma)
+{
+ int mm_lock_seq;
+
+ if (__is_vma_write_locked(vma, &mm_lock_seq))
+ return true;
+
+ if (!down_write_trylock(&vma->vm_lock->lock))
+ return false;
+
+ vma->vm_lock_seq = mm_lock_seq;
+ up_write(&vma->vm_lock->lock);
+ return true;
}
static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{
- mmap_assert_write_locked(vma->vm_mm);
- /*
- * current task is holding mmap_write_lock, both vma->vm_lock_seq and
- * mm->mm_lock_seq can't be concurrently modified.
- */
- VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma);
+ int mm_lock_seq;
+
+ VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
}
+static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
+{
+ /* When detaching vma should be write-locked */
+ if (detached)
+ vma_assert_write_locked(vma);
+ vma->detached = detached;
+}
+
+struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
+ unsigned long address);
+
#else /* CONFIG_PER_VMA_LOCK */
static inline void vma_init_lock(struct vm_area_struct *vma) {}
{ return false; }
static inline void vma_end_read(struct vm_area_struct *vma) {}
static inline void vma_start_write(struct vm_area_struct *vma) {}
+static inline bool vma_try_start_write(struct vm_area_struct *vma)
+ { return true; }
static inline void vma_assert_write_locked(struct vm_area_struct *vma) {}
+static inline void vma_mark_detached(struct vm_area_struct *vma,
+ bool detached) {}
#endif /* CONFIG_PER_VMA_LOCK */
+/*
+ * WARNING: vma_init does not initialize vma->vm_lock.
+ * Use vm_area_alloc()/vm_area_free() if vma needs locking.
+ */
static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
{
static const struct vm_operations_struct dummy_vm_ops = {};
vma->vm_mm = mm;
vma->vm_ops = &dummy_vm_ops;
INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma_init_lock(vma);
+ vma_mark_detached(vma, false);
+ vma_numab_state_init(vma);
}
/* Use when VMA is not part of the VMA tree and needs no locking */
last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS);
return last_time << PAGE_ACCESS_TIME_BUCKETS;
}
+
+static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
+{
+ unsigned int pid_bit;
+
+ pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG));
+ if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) {
+ __set_bit(pid_bit, &vma->numab_state->access_pids[1]);
+ }
+}
#else /* !CONFIG_NUMA_BALANCING */
static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
{
{
return false;
}
+
+static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
+{
+}
#endif /* CONFIG_NUMA_BALANCING */
#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
extern int min_free_kbytes;
extern int watermark_boost_factor;
extern int watermark_scale_factor;
-extern bool arch_has_descending_max_zone_pfns(void);
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap);
#endif
+
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
+{
+ return is_power_of_2(sizeof(struct page)) &&
+ pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
+}
+#else
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
+{
+ return false;
+}
+#endif
+
void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
unsigned long nr_pages);
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
-extern int sysctl_memory_failure_early_kill;
-extern int sysctl_memory_failure_recovery;
extern void shake_page(struct page *p);
extern atomic_long_t num_poisoned_pages __read_mostly;
extern int soft_offline_page(unsigned long pfn, int flags);
bool *migratable_cleared);
void num_poisoned_pages_inc(unsigned long pfn);
void num_poisoned_pages_sub(unsigned long pfn, long i);
+struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
#else
static inline void memory_failure_queue(unsigned long pfn, int flags)
{
}
#endif
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM)
+void add_to_kill_ksm(struct task_struct *tsk, struct page *p,
+ struct vm_area_struct *vma, struct list_head *to_kill,
+ unsigned long ksm_addr);
+#endif
+
#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
extern void memblk_nr_poison_inc(unsigned long pfn);
extern void memblk_nr_poison_sub(unsigned long pfn, long i);
extern void clear_huge_page(struct page *page,
unsigned long addr_hint,
unsigned int pages_per_huge_page);
-extern void copy_user_huge_page(struct page *dst, struct page *src,
- unsigned long addr_hint,
- struct vm_area_struct *vma,
- unsigned int pages_per_huge_page);
-extern long copy_huge_page_from_user(struct page *dst_page,
- const void __user *usr_src,
- unsigned int pages_per_huge_page,
- bool allow_pagefault);
+int copy_user_large_folio(struct folio *dst, struct folio *src,
+ unsigned long addr_hint,
+ struct vm_area_struct *vma);
+long copy_folio_from_user(struct folio *dst_folio,
+ const void __user *usr_src,
+ bool allow_pagefault);
/**
* vma_is_special_huge - Are transhuge page-table entries considered special?