[PATCH 00/23] userfaultfd v4

@@ -302,6 +302,7 @@ Code  Seq#(hex)	Include File		Comments
 0xA3	80-8F	Port ACL		in development:
 					<mailto:tlewis-mn4gwa5WIIQysxA8WJXlww@public.gmane.org>
 0xA3	90-9F	linux/dtlk.h
+0xAA	00-3F	linux/uapi/linux/userfaultfd.h
 0xAB	00-1F	linux/nbd.h
 0xAC	00-1F	linux/raw.h
 0xAD	00	Netfilter device	in development:

@@ -452,3 +452,4 @@ header-y += xfrm.h
 header-y += xilinx-v4l2-controls.h
 header-y += zorro.h
 header-y += zorro_ids.h
+header-y += userfaultfd.h

@@ -0,0 +1,81 @@
+/*
+ *  include/linux/userfaultfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel-AhlLAIvw+VEjIGhXcJzhZg@public.gmane.org>
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ */
+
+#ifndef _LINUX_USERFAULTFD_H
+#define _LINUX_USERFAULTFD_H
+
+#define UFFD_API ((__u64)0xAA)
+/* FIXME: add "|UFFD_BIT_WP" to UFFD_API_BITS after implementing it */
+#define UFFD_API_BITS (UFFD_BIT_WRITE)
+#define UFFD_API_IOCTLS				\
+	((__u64)1 << _UFFDIO_REGISTER |		\
+	 (__u64)1 << _UFFDIO_UNREGISTER |	\
+	 (__u64)1 << _UFFDIO_API)
+#define UFFD_API_RANGE_IOCTLS			\
+	((__u64)1 << _UFFDIO_WAKE)
+
+/*
+ * Valid ioctl command number range with this API is from 0x00 to
+ * 0x3F.  UFFDIO_API is the fixed number, everything else can be
+ * changed by implementing a different UFFD_API. If sticking to the
+ * same UFFD_API more ioctl can be added and userland will be aware of
+ * which ioctl the running kernel implements through the ioctl command
+ * bitmask written by the UFFDIO_API.
+ */
+#define _UFFDIO_REGISTER		(0x00)
+#define _UFFDIO_UNREGISTER		(0x01)
+#define _UFFDIO_WAKE			(0x02)
+#define _UFFDIO_API			(0x3F)
+
+/* userfaultfd ioctl ids */
+#define UFFDIO 0xAA
+#define UFFDIO_API		_IOWR(UFFDIO, _UFFDIO_API,	\
+				      struct uffdio_api)
+#define UFFDIO_REGISTER		_IOWR(UFFDIO, _UFFDIO_REGISTER, \
+				      struct uffdio_register)
+#define UFFDIO_UNREGISTER	_IOR(UFFDIO, _UFFDIO_UNREGISTER,	\
+				     struct uffdio_range)
+#define UFFDIO_WAKE		_IOR(UFFDIO, _UFFDIO_WAKE,	\
+				     struct uffdio_range)
+
+/*
+ * Valid bits below PAGE_SHIFT in the userfault address read through
+ * the read() syscall.
+ */
+#define UFFD_BIT_WRITE	(1<<0)	/* this was a write fault, MISSING or WP */
+#define UFFD_BIT_WP	(1<<1)	/* handle_userfault() reason VM_UFFD_WP */
+#define UFFD_BITS	2	/* two above bits used for UFFD_BIT_* mask */
+
+struct uffdio_api {
+	/* userland asks for an API number */
+	__u64 api;
+
+	/* kernel answers below with the available features for the API */
+	__u64 bits;
+	__u64 ioctls;
+};
+
+struct uffdio_range {
+	__u64 start;
+	__u64 len;
+};
+
+struct uffdio_register {
+	struct uffdio_range range;
+#define UFFDIO_REGISTER_MODE_MISSING	((__u64)1<<0)
+#define UFFDIO_REGISTER_MODE_WP		((__u64)1<<1)
+	__u64 mode;
+
+	/*
+	 * kernel answers which ioctl commands are available for the
+	 * range, keep at the end as the last 8 bytes aren't read.
+	 */
+	__u64 ioctls;
+};
+
+#endif /* _LINUX_USERFAULTFD_H */

@@ -265,6 +265,16 @@ struct vm_region {
 						* this region */
 };
 
+#ifdef CONFIG_USERFAULTFD
+#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, })
+struct vm_userfaultfd_ctx {
+	struct userfaultfd_ctx *ctx;
+};
+#else /* CONFIG_USERFAULTFD */
+#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {})
+struct vm_userfaultfd_ctx {};
+#endif /* CONFIG_USERFAULTFD */
+
 /*
  * This struct defines a memory VMM memory area. There is one of these
  * per VM-area/task.  A VM area is any part of the process virtual memory

@@ -331,6 +341,7 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
+	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 };
 
 struct core_thread {

@@ -451,6 +451,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
 		tmp->vm_next = tmp->vm_prev = NULL;
+		tmp->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file_inode(file);

--

@@ -167,6 +167,67 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
 }
 
 /*
+ * Verify the pagetables are still not ok after having reigstered into
+ * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
+ * userfault that has already been resolved, if userfaultfd_read and
+ * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
+ * threads.
+ */
+static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
+					 unsigned long address,
+					 unsigned long flags,
+					 unsigned long reason)
+{
+	struct mm_struct *mm = ctx->mm;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd, _pmd;
+	pte_t *pte;
+	bool ret = true;
+
+	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		goto out;
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		goto out;
+	pmd = pmd_offset(pud, address);
+	/*
+	 * READ_ONCE must function as a barrier with narrower scope
+	 * and it must be equivalent to:
+	 *	_pmd = *pmd; barrier();
+	 *
+	 * This is to deal with the instability (as in
+	 * pmd_trans_unstable) of the pmd.
+	 */
+	_pmd = READ_ONCE(*pmd);
+	if (!pmd_present(_pmd))
+		goto out;
+
+	ret = false;
+	if (pmd_trans_huge(_pmd))
+		goto out;
+
+	/*
+	 * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
+	 * and use the standard pte_offset_map() instead of parsing _pmd.
+	 */
+	pte = pte_offset_map(pmd, address);
+	/*
+	 * Lockless access: we're in a wait_event so it's ok if it
+	 * changes under us.
+	 */
+	if (pte_none(*pte))
+		ret = true;
+	pte_unmap(pte);
+
+out:
+	return ret;
+}
+
+/*
  * The locking rules involved in returning VM_FAULT_RETRY depending on
  * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
  * FAULT_FLAG_KILLABLE are not straightforward. The "Caution"

@@ -188,6 +249,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	int ret;
+	bool must_wait;
 
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 

@@ -247,9 +309,6 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	/* take the reference before dropping the mmap_sem */
 	userfaultfd_ctx_get(ctx);
 
-	/* be gentle and immediately relinquish the mmap_sem */
-	up_read(&mm->mmap_sem);
-
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
 	uwq.msg = userfault_msg(address, flags, reason);

@@ -269,7 +328,10 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	set_current_state(TASK_KILLABLE);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	if (likely(!ACCESS_ONCE(ctx->released) &&
+	must_wait = userfaultfd_must_wait(ctx, address, flags, reason);
+	up_read(&mm->mmap_sem);
+
+	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&
 		   !fatal_signal_pending(current))) {
 		wake_up_poll(&ctx->fd_wqh, POLLIN);
 		schedule();

@@ -845,17 +907,6 @@ out:
 }
 
 /*
- * userfaultfd_wake is needed in case an userfault is in flight by the
- * time a UFFDIO_COPY (or other ioctl variants) completes. The page
- * may be well get mapped and the page fault if repeated wouldn't lead
- * to a userfault anymore, but before scheduling in TASK_KILLABLE mode
- * handle_userfault() doesn't recheck the pagetables and it doesn't
- * serialize against UFFDO_COPY (or other ioctl variants). Ultimately
- * the knowledge of which pages are mapped is left to userland who is
- * responsible for handling the race between read() userfaults and
- * background UFFDIO_COPY (or other ioctl variants), if done by
- * separate concurrent threads.
- *
  * userfaultfd_wake may be used in combination with the
  * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
  */

@@ -30,6 +30,12 @@
 extern int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 			    unsigned int flags, unsigned long reason);
 
+extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
+			    unsigned long src_start, unsigned long len);
+extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
+			      unsigned long dst_start,
+			      unsigned long len);
+
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 					struct vm_userfaultfd_ctx vm_ctx)

@@ -78,3 +78,4 @@ obj-$(CONFIG_CMA)	+= cma.o
 obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
 obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
 obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
+obj-$(CONFIG_USERFAULTFD) += userfaultfd.o

@@ -0,0 +1,269 @@
+/*
+ *  mm/userfaultfd.c
+ *
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/mmu_notifier.h>
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+static int mcopy_atomic_pte(struct mm_struct *dst_mm,
+			    pmd_t *dst_pmd,
+			    struct vm_area_struct *dst_vma,
+			    unsigned long dst_addr,
+			    unsigned long src_addr)
+{
+	struct mem_cgroup *memcg;
+	pte_t _dst_pte, *dst_pte;
+	spinlock_t *ptl;
+	struct page *page;
+	void *page_kaddr;
+	int ret;
+
+	ret = -ENOMEM;
+	page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr);
+	if (!page)
+		goto out;
+
+	page_kaddr = kmap(page);
+	ret = -EFAULT;
+	if (copy_from_user(page_kaddr, (const void __user *) src_addr,
+			   PAGE_SIZE))
+		goto out_kunmap_release;
+	kunmap(page);
+
+	/*
+	 * The memory barrier inside __SetPageUptodate makes sure that
+	 * preceeding stores to the page contents become visible before
+	 * the set_pte_at() write.
+	 */
+	__SetPageUptodate(page);
+
+	ret = -ENOMEM;
+	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg))
+		goto out_release;
+
+	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
+	if (dst_vma->vm_flags & VM_WRITE)
+		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+
+	ret = -EEXIST;
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (!pte_none(*dst_pte))
+		goto out_release_uncharge_unlock;
+
+	inc_mm_counter(dst_mm, MM_ANONPAGES);
+	page_add_new_anon_rmap(page, dst_vma, dst_addr);
+	mem_cgroup_commit_charge(page, memcg, false);
+	lru_cache_add_active_or_unevictable(page, dst_vma);
+
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+
+	pte_unmap_unlock(dst_pte, ptl);
+	ret = 0;
+out:
+	return ret;
+out_release_uncharge_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+	mem_cgroup_cancel_charge(page, memcg);
+out_release:
+	page_cache_release(page);
+	goto out;
+out_kunmap_release:
+	kunmap(page);
+	goto out_release;
+}
+
+static int mfill_zeropage_pte(struct mm_struct *dst_mm,
+			      pmd_t *dst_pmd,
+			      struct vm_area_struct *dst_vma,
+			      unsigned long dst_addr)
+{
+	pte_t _dst_pte, *dst_pte;
+	spinlock_t *ptl;
+	int ret;
+
+	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
+					 dst_vma->vm_page_prot));
+	ret = -EEXIST;
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (!pte_none(*dst_pte))
+		goto out_unlock;
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+	ret = 0;
+out_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+	return ret;
+}
+
+static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, address);
+	pud = pud_alloc(mm, pgd, address);
+	if (pud)
+		/*
+		 * Note that we didn't run this because the pmd was
+		 * missing, the *pmd may be already established and in
+		 * turn it may also be a trans_huge_pmd.
+		 */
+		pmd = pmd_alloc(mm, pud, address);
+	return pmd;
+}
+
+static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
+					      unsigned long dst_start,
+					      unsigned long src_start,
+					      unsigned long len,
+					      bool zeropage)
+{
+	struct vm_area_struct *dst_vma;
+	ssize_t err;
+	pmd_t *dst_pmd;
+	unsigned long src_addr, dst_addr;
+	long copied = 0;
+
+	/*
+	 * Sanitize the command parameters:
+	 */
+	BUG_ON(dst_start & ~PAGE_MASK);
+	BUG_ON(len & ~PAGE_MASK);
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	BUG_ON(src_start + len <= src_start);
+	BUG_ON(dst_start + len <= dst_start);
+
+	down_read(&dst_mm->mmap_sem);
+
+	/*
+	 * Make sure the vma is not shared, that the dst range is
+	 * both valid and fully within a single existing vma.
+	 */
+	err = -EINVAL;
+	dst_vma = find_vma(dst_mm, dst_start);
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (dst_start < dst_vma->vm_start ||
+	    dst_start + len > dst_vma->vm_end)
+		goto out;
+
+	/*
+	 * Be strict and only allow __mcopy_atomic on userfaultfd
+	 * registered ranges to prevent userland errors going
+	 * unnoticed. As far as the VM consistency is concerned, it
+	 * would be perfectly safe to remove this check, but there's
+	 * no useful usage for __mcopy_atomic ouside of userfaultfd
+	 * registered ranges. This is after all why these are ioctls
+	 * belonging to the userfaultfd and not syscalls.
+	 */
+	if (!dst_vma->vm_userfaultfd_ctx.ctx)
+		goto out;
+
+	/*
+	 * FIXME: only allow copying on anonymous vmas, tmpfs should
+	 * be added.
+	 */
+	if (dst_vma->vm_ops)
+		goto out;
+
+	/*
+	 * Ensure the dst_vma has a anon_vma or this page
+	 * would get a NULL anon_vma when moved in the
+	 * dst_vma.
+	 */
+	err = -ENOMEM;
+	if (unlikely(anon_vma_prepare(dst_vma)))
+		goto out;
+
+	for (src_addr = src_start, dst_addr = dst_start;
+	     src_addr < src_start + len; ) {
+		pmd_t dst_pmdval;
+		BUG_ON(dst_addr >= dst_start + len);
+		dst_pmd = mm_alloc_pmd(dst_mm, dst_addr);
+		if (unlikely(!dst_pmd)) {
+			err = -ENOMEM;
+			break;
+		}
+
+		dst_pmdval = pmd_read_atomic(dst_pmd);
+		/*
+		 * If the dst_pmd is mapped as THP don't
+		 * override it and just be strict.
+		 */
+		if (unlikely(pmd_trans_huge(dst_pmdval))) {
+			err = -EEXIST;
+			break;
+		}
+		if (unlikely(pmd_none(dst_pmdval)) &&
+		    unlikely(__pte_alloc(dst_mm, dst_vma, dst_pmd,
+					 dst_addr))) {
+			err = -ENOMEM;
+			break;
+		}
+		/* If an huge pmd materialized from under us fail */
+		if (unlikely(pmd_trans_huge(*dst_pmd))) {
+			err = -EFAULT;
+			break;
+		}
+
+		BUG_ON(pmd_none(*dst_pmd));
+		BUG_ON(pmd_trans_huge(*dst_pmd));
+
+		if (!zeropage)
+			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
+					       dst_addr, src_addr);
+		else
+			err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma,
+						 dst_addr);
+
+		cond_resched();
+
+		if (!err) {
+			dst_addr += PAGE_SIZE;
+			src_addr += PAGE_SIZE;
+			copied += PAGE_SIZE;
+
+			if (fatal_signal_pending(current))
+				err = -EINTR;
+		}
+		if (err)
+			break;
+	}
+
+out:
+	up_read(&dst_mm->mmap_sem);
+	BUG_ON(copied < 0);
+	BUG_ON(err > 0);
+	BUG_ON(!copied && !err);
+	return copied ? copied : err;
+}
+
+ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
+		     unsigned long src_start, unsigned long len)
+{
+	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false);
+}
+
+ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
+		       unsigned long len)
+{
+	return __mcopy_atomic(dst_mm, start, 0, len, true);
+}

--

@@ -597,6 +597,8 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_HUGEPAGE)]	= "hg",
 		[ilog2(VM_NOHUGEPAGE)]	= "nh",
 		[ilog2(VM_MERGEABLE)]	= "mg",
+		[ilog2(VM_UFFD_MISSING)]= "um",
+		[ilog2(VM_UFFD_WP)]	= "uw",
 	};
 	size_t i;
 

@@ -123,8 +123,10 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_MAYSHARE	0x00000080
 
 #define VM_GROWSDOWN	0x00000100	/* general info on the segment */
+#define VM_UFFD_MISSING	0x00000200	/* missing pages tracking */
 #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
 #define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
+#define VM_UFFD_WP	0x00001000	/* wrprotect pages tracking */
 
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000	/* Memory mapped I/O or similar */

@@ -449,7 +449,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
-		tmp->vm_flags &= ~VM_LOCKED;
+		tmp->vm_flags &= ~(VM_LOCKED|VM_UFFD_MISSING|VM_UFFD_WP);
 		tmp->vm_next = tmp->vm_prev = NULL;
 		tmp->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 		file = tmp->vm_file;

--

@@ -147,7 +147,8 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 
 typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
+			  void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);

@@ -179,7 +180,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_poll(x, m)						\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
 #define wake_up_locked_poll(x, m)					\
-	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
+	__wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m))
 #define wake_up_interruptible_poll(x, m)				\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)				\

@@ -106,9 +106,10 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
+			  void *key)
 {
-	__wake_up_common(q, mode, 1, 0, key);
+	__wake_up_common(q, mode, nr, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 

@@ -283,7 +284,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_locked_key(q, mode, key);
+		__wake_up_locked_key(q, mode, 1, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);

@@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task)
 	clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
 	ret = atomic_dec_and_test(&task->tk_count);
 	if (waitqueue_active(wq))
-		__wake_up_locked_key(wq, TASK_NORMAL, &k);
+		__wake_up_locked_key(wq, TASK_NORMAL, 1, &k);
 	spin_unlock_irqrestore(&wq->lock, flags);
 	return ret;
 }

--

@@ -1763,7 +1763,7 @@ extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 extern struct vm_area_struct *vma_merge(struct mm_struct *,
 	struct vm_area_struct *prev, unsigned long addr, unsigned long end,
 	unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
-	struct mempolicy *);
+	struct mempolicy *, struct vm_userfaultfd_ctx);
 extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
 extern int split_vma(struct mm_struct *,
 	struct vm_area_struct *, unsigned long addr, int new_below);

@@ -111,7 +111,8 @@ static long madvise_behavior(struct vm_area_struct *vma,
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
-				vma->vm_file, pgoff, vma_policy(vma));
+			  vma->vm_file, pgoff, vma_policy(vma),
+			  vma->vm_userfaultfd_ctx);
 	if (*prev) {
 		vma = *prev;
 		goto success;

@@ -722,8 +722,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 		pgoff = vma->vm_pgoff +
 			((vmstart - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
-				  vma->anon_vma, vma->vm_file, pgoff,
-				  new_pol);
+				 vma->anon_vma, vma->vm_file, pgoff,
+				 new_pol, vma->vm_userfaultfd_ctx);
 		if (prev) {
 			vma = prev;
 			next = vma->vm_next;

@@ -510,7 +510,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
-			  vma->vm_file, pgoff, vma_policy(vma));
+			  vma->vm_file, pgoff, vma_policy(vma),
+			  vma->vm_userfaultfd_ctx);
 	if (*prev) {
 		vma = *prev;
 		goto success;

@@ -41,6 +41,7 @@
 #include <linux/notifier.h>
 #include <linux/memory.h>
 #include <linux/printk.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>

@@ -919,7 +920,8 @@ again:			remove_next = 1 + (end > next->vm_end);
  * per-vma resources, so we don't attempt to merge those.
  */
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
-			struct file *file, unsigned long vm_flags)
+				struct file *file, unsigned long vm_flags,
+				struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
 	/*
 	 * VM_SOFTDIRTY should not prevent from VMA merging, if we

@@ -935,6 +937,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
 		return 0;
 	if (vma->vm_ops && vma->vm_ops->close)
 		return 0;
+	if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
+		return 0;
 	return 1;
 }
 

@@ -965,9 +969,11 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
  */
 static int
 can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+		     struct anon_vma *anon_vma, struct file *file,
+		     pgoff_t vm_pgoff,
+		     struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		if (vma->vm_pgoff == vm_pgoff)
 			return 1;

@@ -984,9 +990,11 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
  */
 static int
 can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+		    struct anon_vma *anon_vma, struct file *file,
+		    pgoff_t vm_pgoff,
+		    struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		pgoff_t vm_pglen;
 		vm_pglen = vma_pages(vma);

@@ -1029,7 +1037,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 			struct vm_area_struct *prev, unsigned long addr,
 			unsigned long end, unsigned long vm_flags,
 			struct anon_vma *anon_vma, struct file *file,
-			pgoff_t pgoff, struct mempolicy *policy)
+			pgoff_t pgoff, struct mempolicy *policy,
+			struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
 	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
 	struct vm_area_struct *area, *next;

@@ -1056,14 +1065,17 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	if (prev && prev->vm_end == addr &&
 			mpol_equal(vma_policy(prev), policy) &&
 			can_vma_merge_after(prev, vm_flags,
-						anon_vma, file, pgoff)) {
+					    anon_vma, file, pgoff,
+					    vm_userfaultfd_ctx)) {
 		/*
 		 * OK, it can.  Can we now merge in the successor as well?
 		 */
 		if (next && end == next->vm_start &&
 				mpol_equal(policy, vma_policy(next)) &&
 				can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen) &&
+						     anon_vma, file,
+						     pgoff+pglen,
+						     vm_userfaultfd_ctx) &&
 				is_mergeable_anon_vma(prev->anon_vma,
 						      next->anon_vma, NULL)) {
 							/* cases 1, 6 */

@@ -1084,7 +1096,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	if (next && end == next->vm_start &&
 			mpol_equal(policy, vma_policy(next)) &&
 			can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen)) {
+					     anon_vma, file, pgoff+pglen,
+					     vm_userfaultfd_ctx)) {
 		if (prev && addr < prev->vm_end)	/* case 4 */
 			err = vma_adjust(prev, prev->vm_start,
 				addr, prev->vm_pgoff, NULL);

@@ -1570,8 +1583,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	/*
 	 * Can we just expand an old mapping?
 	 */
-	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
-			NULL);
+	vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
+			NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
 	if (vma)
 		goto out;
 

@@ -2757,7 +2770,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 
 	/* Can we just expand an old private anonymous mapping? */
 	vma = vma_merge(mm, prev, addr, addr + len, flags,
-					NULL, NULL, pgoff, NULL);
+			NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
 	if (vma)
 		goto out;
 

@@ -2913,7 +2926,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
 		return NULL;	/* should never get here */
 	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+			    vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			    vma->vm_userfaultfd_ctx);
 	if (new_vma) {
 		/*
 		 * Source vma may have been merged into new_vma

@@ -292,7 +292,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 */
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*pprev = vma_merge(mm, *pprev, start, end, newflags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+			   vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			   vma->vm_userfaultfd_ctx);
 	if (*pprev) {
 		vma = *pprev;
 		goto success;

@@ -27,20 +27,26 @@
 #include <linux/ioctl.h>
 #include <linux/security.h>
 
+static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
+
 enum userfaultfd_state {
 	UFFD_STATE_WAIT_API,
 	UFFD_STATE_RUNNING,
 };
 
+/*
+ * Start with fault_pending_wqh and fault_wqh so they're more likely
+ * to be in the same cacheline.
+ */
 struct userfaultfd_ctx {
-	/* pseudo fd refcounting */
-	atomic_t refcount;
 	/* waitqueue head for the pending (i.e. not read) userfaults */
 	wait_queue_head_t fault_pending_wqh;
 	/* waitqueue head for the userfaults */
 	wait_queue_head_t fault_wqh;
 	/* waitqueue head for the pseudo fd to wakeup poll/read */
 	wait_queue_head_t fd_wqh;
+	/* pseudo fd refcounting */
+	atomic_t refcount;
 	/* userfaultfd syscall flags */
 	unsigned int flags;
 	/* state machine */

@@ -117,7 +123,7 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
 		VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
 		VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
 		mmput(ctx->mm);
-		kfree(ctx);
+		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
 	}
 }
 

@@ -987,6 +993,15 @@ static const struct file_operations userfaultfd_fops = {
 	.llseek		= noop_llseek,
 };
 
+static void init_once_userfaultfd_ctx(void *mem)
+{
+	struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;
+
+	init_waitqueue_head(&ctx->fault_pending_wqh);
+	init_waitqueue_head(&ctx->fault_wqh);
+	init_waitqueue_head(&ctx->fd_wqh);
+}
+
 /**
  * userfaultfd_file_create - Creates an userfaultfd file pointer.
  * @flags: Flags for the userfaultfd file.