goto out;
WRITE_ONCE(uwq->waken, true);
/*
- * The implicit smp_mb__before_spinlock in try_to_wake_up()
- * renders uwq->waken visible to other CPUs before the task is
- * waken.
+ * The Program-Order guarantees provided by the scheduler
+ * ensure uwq->waken is visible before the task is woken.
*/
ret = wake_up_state(wq->private, mode);
- if (ret)
+ if (ret) {
/*
* Wake only once, autoremove behavior.
*
- * After the effect of list_del_init is visible to the
- * other CPUs, the waitqueue may disappear from under
- * us, see the !list_empty_careful() in
- * handle_userfault(). try_to_wake_up() has an
- * implicit smp_mb__before_spinlock, and the
- * wq->private is read before calling the extern
- * function "wake_up_state" (which in turns calls
- * try_to_wake_up). While the spin_lock;spin_unlock;
- * wouldn't be enough, the smp_mb__before_spinlock is
- * enough to avoid an explicit smp_mb() here.
+ * After the effect of list_del_init is visible to the other
+ * CPUs, the waitqueue may disappear from under us, see the
+ * !list_empty_careful() in handle_userfault().
+ *
+ * try_to_wake_up() has an implicit smp_mb(), and the
+ * wq->private is read before calling the extern function
+ * "wake_up_state" (which in turns calls try_to_wake_up).
*/
list_del_init(&wq->entry);
+ }
out:
return ret;
}
uffdio_copy.len);
mmput(ctx->mm);
} else {
- return -ENOSPC;
+ return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
uffdio_zeropage.range.len);
mmput(ctx->mm);
} else {
- return -ENOSPC;
+ return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
return -EFAULT;
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
#endif
- #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
/*
* An operation with batched TLB flushing is going on. Anything that
* can move process memory needs to flush the TLB when moving a
* PROT_NONE or PROT_NUMA mapped page.
*/
- bool tlb_flush_pending;
- #endif
+ atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/* See flush_tlb_batched_pending() */
bool tlb_flush_batched;
return mm->cpu_vm_mask_var;
}
- #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+ struct mmu_gather;
+ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+ unsigned long start, unsigned long end);
+ extern void tlb_finish_mmu(struct mmu_gather *tlb,
+ unsigned long start, unsigned long end);
+
/*
* Memory barriers to keep this state in sync are graciously provided by
* the page table locks, outside of which no page table modifications happen.
- * The barriers below prevent the compiler from re-ordering the instructions
- * around the memory barriers that are already present in the code.
+ * The barriers are used to ensure the order between tlb_flush_pending updates,
+ * which happen while the lock is not taken, and the PTE updates, which happen
+ * while the lock is taken, are serialized.
*/
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
- return mm->tlb_flush_pending;
+ /*
+ * Must be called with PTL held; such that our PTL acquire will have
+ * observed the store from set_tlb_flush_pending().
+ */
+ return atomic_read(&mm->tlb_flush_pending) > 0;
+ }
+
+ /*
+ * Returns true if there are two above TLB batching threads in parallel.
+ */
+ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+ {
+ return atomic_read(&mm->tlb_flush_pending) > 1;
+ }
+
+ static inline void init_tlb_flush_pending(struct mm_struct *mm)
+ {
+ atomic_set(&mm->tlb_flush_pending, 0);
}
- static inline void set_tlb_flush_pending(struct mm_struct *mm)
+
+ static inline void inc_tlb_flush_pending(struct mm_struct *mm)
{
- mm->tlb_flush_pending = true;
+ atomic_inc(&mm->tlb_flush_pending);
+
/*
- * Guarantee that the tlb_flush_pending increase does not leak into the
- * critical section updating the page tables
+ * The only time this value is relevant is when there are indeed pages
+ * to flush. And we'll only flush pages after changing them, which
+ * requires the PTL.
+ *
+ * So the ordering here is:
+ *
- * mm->tlb_flush_pending = true;
++ * atomic_inc(&mm->tlb_flush_pending);
+ * spin_lock(&ptl);
+ * ...
+ * set_pte_at();
+ * spin_unlock(&ptl);
+ *
+ * spin_lock(&ptl)
+ * mm_tlb_flush_pending();
+ * ....
+ * spin_unlock(&ptl);
+ *
+ * flush_tlb_range();
- * mm->tlb_flush_pending = false;
++ * atomic_dec(&mm->tlb_flush_pending);
+ *
+ * So the =true store is constrained by the PTL unlock, and the =false
+ * store is constrained by the TLB invalidate.
*/
- smp_mb__before_spinlock();
}
+
/* Clearing is done after a TLB flush, which also provides a barrier. */
- static inline void clear_tlb_flush_pending(struct mm_struct *mm)
- {
- /* see set_tlb_flush_pending */
- mm->tlb_flush_pending = false;
- }
- #else
- static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
- {
- return false;
- }
- static inline void set_tlb_flush_pending(struct mm_struct *mm)
- {
- }
- static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+ static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
+ /*
+ * Guarantee that the tlb_flush_pending does not not leak into the
+ * critical section, since we must order the PTE change and changes to
+ * the pending TLB flush indication. We could have relied on TLB flush
+ * as a memory barrier, but this behavior is not clearly documented.
+ */
+ smp_mb__before_atomic();
+ atomic_dec(&mm->tlb_flush_pending);
}
- #endif
struct vm_fault;
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
NULL, free_vm_stack_cache);
#endif
+
+ lockdep_init_task(&init_task);
}
int __weak arch_dup_task_struct(struct task_struct *dst,
mm_init_aio(mm);
mm_init_owner(mm, p);
mmu_notifier_mm_init(mm);
- clear_tlb_flush_pending(mm);
+ init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
+ lockdep_init_task(p);
#endif
#ifdef CONFIG_DEBUG_MUTEXES
bad_fork_cleanup_perf:
perf_event_free_task(p);
bad_fork_cleanup_policy:
+ lockdep_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
int page_nid = -1, this_nid = numa_node_id();
int target_nid, last_cpupid = -1;
+ bool need_flush = false;
bool page_locked;
bool migrated = false;
bool was_writable;
goto clear_pmdnuma;
}
+ /*
+ * The page_table_lock above provides a memory barrier
+ * with change_protection_range.
+ */
+ if (mm_tlb_flush_pending(vma->vm_mm))
+ flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
+ /*
+ * Since we took the NUMA fault, we must have observed the !accessible
+ * bit. Make sure all other CPUs agree with that, to avoid them
+ * modifying the page we're about to migrate.
+ *
+ * Must be done under PTL such that we'll observe the relevant
+ * set_tlb_flush_pending().
+ */
+ if (mm_tlb_flush_pending(vma->vm_mm))
+ need_flush = true;
+
/*
* Migrate the THP to the requested node, returns with page unlocked
* and access rights restored.
*/
spin_unlock(vmf->ptl);
+
+ /*
+ * We are not sure a pending tlb flush here is for a huge page
+ * mapping or not. Hence use the tlb range variant
+ */
+ if (need_flush)
+ flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
vmf->pmd, pmd, vmf->address, page, target_nid);
if (migrated) {
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
+#include <linux/lockdep.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
}
#endif /* CONFIG_COMPACTION */
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map __fs_reclaim_map =
+ STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
+
+static bool __need_fs_reclaim(gfp_t gfp_mask)
+{
+ gfp_mask = current_gfp_context(gfp_mask);
+
+ /* no reclaim without waiting on it */
+ if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+ return false;
+
+ /* this guy won't enter reclaim */
+ if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+ return false;
+
+ /* We're only interested __GFP_FS allocations for now */
+ if (!(gfp_mask & __GFP_FS))
+ return false;
+
+ if (gfp_mask & __GFP_NOLOCKDEP)
+ return false;
+
+ return true;
+}
+
+void fs_reclaim_acquire(gfp_t gfp_mask)
+{
+ if (__need_fs_reclaim(gfp_mask))
+ lock_map_acquire(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
+
+void fs_reclaim_release(gfp_t gfp_mask)
+{
+ if (__need_fs_reclaim(gfp_mask))
+ lock_map_release(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_release);
+#endif
+
/* Perform direct synchronous page reclaim */
static int
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
noreclaim_flag = memalloc_noreclaim_save();
- lockdep_set_current_reclaim_state(gfp_mask);
+ fs_reclaim_acquire(gfp_mask);
reclaim_state.reclaimed_slab = 0;
current->reclaim_state = &reclaim_state;
ac->nodemask);
current->reclaim_state = NULL;
- lockdep_clear_current_reclaim_state();
+ fs_reclaim_release(gfp_mask);
memalloc_noreclaim_restore(noreclaim_flag);
cond_resched();
*alloc_flags |= ALLOC_CPUSET;
}
- lockdep_trace_alloc(gfp_mask);
+ fs_reclaim_acquire(gfp_mask);
+ fs_reclaim_release(gfp_mask);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
* Part of the reclaimable slab consists of items that are in use,
* and cannot be freed. Cap this estimate at the low watermark.
*/
- available += global_page_state(NR_SLAB_RECLAIMABLE) -
- min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+ available += global_node_page_state(NR_SLAB_RECLAIMABLE) -
+ min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
+ wmark_low);
if (available < 0)
available = 0;
global_node_page_state(NR_FILE_DIRTY),
global_node_page_state(NR_WRITEBACK),
global_node_page_state(NR_UNSTABLE_NFS),
- global_page_state(NR_SLAB_RECLAIMABLE),
- global_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_node_page_state(NR_SLAB_RECLAIMABLE),
+ global_node_page_state(NR_SLAB_UNRECLAIMABLE),
global_node_page_state(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_page_state(NR_PAGETABLE),
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
- pr_info("%s: [%lx, %lx) PFNs busy\n",
+ pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
goto done;
if (is_udplite) /* UDP-Lite */
csum = udplite_csum(skb);
- else if (sk->sk_no_check_tx) { /* UDP csum disabled */
+ else if (sk->sk_no_check_tx && !skb_is_gso(skb)) { /* UDP csum off */
skb->ip_summed = CHECKSUM_NONE;
goto send;
static struct static_key udp_encap_needed __read_mostly;
void udp_encap_enable(void)
{
- if (!static_key_enabled(&udp_encap_needed))
- static_key_slow_inc(&udp_encap_needed);
+ static_key_enable(&udp_encap_needed);
}
EXPORT_SYMBOL(udp_encap_enable);