[PATCH 21/23] userfaultfd: mcopy_atomic|mfill_zeropage: UFFDIO_COPY|UFFDIO_ZEROPAGE preparation
This implements mcopy_atomic and mfill_zeropage that are the lowlevel
VM methods that are invoked respectively by the UFFDIO_COPY and
UFFDIO_ZEROPAGE userfaultfd commands.
Signed-off-by: Andrea Arcangeli
---
include/linux/userfaultfd_k.h | 6 +
mm/Makefile | 1 +
mm/userfaultfd.c | 269 ++
3 files changed, 276 insertions(+)
create mode 100644 mm/userfaultfd.c
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index e1e4360..587480a 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -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)
diff --git a/mm/Makefile b/mm/Makefile
index 98c4eae..b424d5e 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -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
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
new file mode 100644
index 000..c54c761
--- /dev/null
+++ b/mm/userfaultfd.c
@@ -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
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#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, ))
+ 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, );
+ 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, );
+ if (!pte_none(*dst_pte))
+ goto out_unlock;
+ set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+ /* No need to invalidate
[PATCH 21/23] userfaultfd: mcopy_atomic|mfill_zeropage: UFFDIO_COPY|UFFDIO_ZEROPAGE preparation
This implements mcopy_atomic and mfill_zeropage that are the lowlevel
VM methods that are invoked respectively by the UFFDIO_COPY and
UFFDIO_ZEROPAGE userfaultfd commands.
Signed-off-by: Andrea Arcangeli aarca...@redhat.com
---
include/linux/userfaultfd_k.h | 6 +
mm/Makefile | 1 +
mm/userfaultfd.c | 269 ++
3 files changed, 276 insertions(+)
create mode 100644 mm/userfaultfd.c
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index e1e4360..587480a 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -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)
diff --git a/mm/Makefile b/mm/Makefile
index 98c4eae..b424d5e 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -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
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
new file mode 100644
index 000..c54c761
--- /dev/null
+++ b/mm/userfaultfd.c
@@ -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
