Re: [kvm-devel] [PATCH] mmu notifiers #v4

[Andrea Arcangeli]

This last update avoids the need to refresh the young bit in the linux
pte through follow_page and it allows tracking the accessed bits set
by the hardware in the sptes without requiring vmexits in certain
implementations.

KVM side is here:

    http://marc.info/?l=kvm-devel&m=120103225508669&w=2

Signed-off-by: Andrea Arcangeli <andrea@xxxxxxxxxxxx>

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -46,6 +46,7 @@
 	__young = ptep_test_and_clear_young(__vma, __address, __ptep);	\
 	if (__young)							\
 		flush_tlb_page(__vma, __address);			\
+	__young |= mmu_notifier_age_page((__vma)->vm_mm, __address);	\
 	__young;							\
 })
 #endif
@@ -86,6 +87,7 @@ do {									\
 	pte_t __pte;							\
 	__pte = ptep_get_and_clear((__vma)->vm_mm, __address, __ptep);	\
 	flush_tlb_page(__vma, __address);				\
+	mmu_notifier(invalidate_page, (__vma)->vm_mm, __address);	\
 	__pte;								\
 })
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -10,6 +10,7 @@
 #include <linux/rbtree.h>
 #include <linux/rwsem.h>
 #include <linux/completion.h>
+#include <linux/mmu_notifier.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
@@ -219,6 +220,10 @@ struct mm_struct {
 	/* aio bits */
 	rwlock_t		ioctx_list_lock;
 	struct kioctx		*ioctx_list;
+
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_notifier_head mmu_notifier; /* MMU notifier list */
+#endif
 };
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
new file mode 100644
--- /dev/null
+++ b/include/linux/mmu_notifier.h
@@ -0,0 +1,82 @@
+#ifndef _LINUX_MMU_NOTIFIER_H
+#define _LINUX_MMU_NOTIFIER_H
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_MMU_NOTIFIER
+
+struct mmu_notifier;
+
+struct mmu_notifier_ops {
+	void (*release)(struct mmu_notifier *mn,
+			struct mm_struct *mm);
+	int (*age_page)(struct mmu_notifier *mn,
+			struct mm_struct *mm,
+			unsigned long address);
+	void (*invalidate_page)(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long address);
+	void (*invalidate_range)(struct mmu_notifier *mn,
+				 struct mm_struct *mm,
+				 unsigned long start, unsigned long end);
+};
+
+struct mmu_notifier_head {
+	struct hlist_head head;
+	rwlock_t lock;
+};
+
+struct mmu_notifier {
+	struct hlist_node hlist;
+	const struct mmu_notifier_ops *ops;
+};
+
+#include <linux/mm_types.h>
+
+extern void mmu_notifier_register(struct mmu_notifier *mn,
+				  struct mm_struct *mm);
+extern void mmu_notifier_unregister(struct mmu_notifier *mn,
+				    struct mm_struct *mm);
+extern void mmu_notifier_release(struct mm_struct *mm);
+extern int mmu_notifier_age_page(struct mm_struct *mm,
+				 unsigned long address);
+
+static inline void mmu_notifier_head_init(struct mmu_notifier_head *mnh)
+{
+	INIT_HLIST_HEAD(&mnh->head);
+	rwlock_init(&mnh->lock);
+}
+
+#define mmu_notifier(function, mm, args...)				\
+	do {								\
+		struct mmu_notifier *__mn;				\
+		struct hlist_node *__n;					\
+									\
+		if (unlikely(!hlist_empty(&(mm)->mmu_notifier.head))) { \
+			read_lock(&(mm)->mmu_notifier.lock);		\
+			hlist_for_each_entry(__mn, __n,			\
+					     &(mm)->mmu_notifier.head,	\
+					     hlist)			\
+				if (__mn->ops->function)		\
+					__mn->ops->function(__mn,	\
+							    mm,		\
+							    args);	\
+			read_unlock(&(mm)->mmu_notifier.lock);		\
+		}							\
+	} while (0)
+
+#else /* CONFIG_MMU_NOTIFIER */
+
+#define mmu_notifier_register(mn, mm) do {} while(0)
+#define mmu_notifier_unregister(mn, mm) do {} while (0)
+#define mmu_notifier_release(mm) do {} while (0)
+#define mmu_notifier_age_page(mm, address) ({ 0; })
+#define mmu_notifier_head_init(mmh) do {} while (0)
+
+#define mmu_notifier(function, mm, args...)	\
+	do { } while (0)
+
+#endif /* CONFIG_MMU_NOTIFIER */
+
+#endif /* _LINUX_MMU_NOTIFIER_H */
diff --git a/kernel/fork.c b/kernel/fork.c
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -359,6 +359,7 @@ static struct mm_struct * mm_init(struct
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
+		mmu_notifier_head_init(&mm->mmu_notifier);
 		return mm;
 	}
 	free_mm(mm);
diff --git a/mm/Kconfig b/mm/Kconfig
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -193,3 +193,7 @@ config VIRT_TO_BUS
 config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
+
+config MMU_NOTIFIER
+	def_bool y
+	bool "MMU notifier, for paging KVM/RDMA"
diff --git a/mm/Makefile b/mm/Makefile
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -30,4 +30,5 @@ obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
+obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -753,6 +753,7 @@ void __unmap_hugepage_range(struct vm_ar
 	}
 	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
+	mmu_notifier(invalidate_range, mm, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
 		list_del(&page->lru);
 		put_page(page);
diff --git a/mm/memory.c b/mm/memory.c
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -889,6 +889,7 @@ unsigned long zap_page_range(struct vm_a
 	end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
 	if (tlb)
 		tlb_finish_mmu(tlb, address, end);
+	mmu_notifier(invalidate_range, mm, address, end);
 	return end;
 }
 
@@ -1317,7 +1318,7 @@ int remap_pfn_range(struct vm_area_struc
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long end = addr + PAGE_ALIGN(size);
+	unsigned long start = addr, end = addr + PAGE_ALIGN(size);
 	struct mm_struct *mm = vma->vm_mm;
 	int err;
 
@@ -1358,6 +1359,7 @@ int remap_pfn_range(struct vm_area_struc
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
+	mmu_notifier(invalidate_range, mm, start, end);
 	return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);
@@ -1441,7 +1443,7 @@ int apply_to_page_range(struct mm_struct
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long end = addr + size;
+	unsigned long start = addr, end = addr + size;
 	int err;
 
 	BUG_ON(addr >= end);
@@ -1452,6 +1454,7 @@ int apply_to_page_range(struct mm_struct
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
+	mmu_notifier(invalidate_range, mm, start, end);
 	return err;
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
diff --git a/mm/mmap.c b/mm/mmap.c
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1747,6 +1747,7 @@ static void unmap_region(struct mm_struc
 	free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
 				 next? next->vm_start: 0);
 	tlb_finish_mmu(tlb, start, end);
+	mmu_notifier(invalidate_range, mm, start, end);
 }
 
 /*
@@ -2043,6 +2044,7 @@ void exit_mmap(struct mm_struct *mm)
 	vm_unacct_memory(nr_accounted);
 	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
 	tlb_finish_mmu(tlb, 0, end);
+	mmu_notifier_release(mm);
 
 	/*
 	 * Walk the list again, actually closing and freeing it,
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
new file mode 100644
--- /dev/null
+++ b/mm/mmu_notifier.c
@@ -0,0 +1,68 @@
+/*
+ *  linux/mm/mmu_notifier.c
+ *
+ *  Copyright (C) 2008  Qumranet, 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/mmu_notifier.h>
+#include <linux/module.h>
+
+void mmu_notifier_release(struct mm_struct *mm)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n, *tmp;
+
+	if (unlikely(!hlist_empty(&mm->mmu_notifier.head))) {
+		read_lock(&mm->mmu_notifier.lock);
+		hlist_for_each_entry_safe(mn, n, tmp,
+					  &mm->mmu_notifier.head, hlist) {
+			if (mn->ops->release)
+				mn->ops->release(mn, mm);
+			hlist_del(&mn->hlist);
+		}
+		read_unlock(&mm->mmu_notifier.lock);
+	}
+}
+
+/*
+ * If no young bitflag is supported by the hardware, ->age_page can
+ * unmap the address and return 1 or 0 depending if the mapping previously
+ * existed or not.
+ */
+int mmu_notifier_age_page(struct mm_struct *mm, unsigned long address)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n, *tmp;
+	int young = 0;
+
+	if (unlikely(!hlist_empty(&mm->mmu_notifier.head))) {
+		read_lock(&mm->mmu_notifier.lock);
+		hlist_for_each_entry_safe(mn, n, tmp,
+					  &mm->mmu_notifier.head, hlist) {
+			if (mn->ops->age_page)
+				young |= mn->ops->age_page(mn, mm, address);
+		}
+		read_unlock(&mm->mmu_notifier.lock);
+	}
+
+	return young;
+}
+
+void mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	write_lock(&mm->mmu_notifier.lock);
+	hlist_add_head(&mn->hlist, &mm->mmu_notifier.head);
+	write_unlock(&mm->mmu_notifier.lock);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_register);
+
+void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	write_lock(&mm->mmu_notifier.lock);
+	hlist_del(&mn->hlist);
+	write_unlock(&mm->mmu_notifier.lock);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/