arch/x86/syscalls/syscall_64.tbl |    1
 include/linux/syscalls.h         |    2
 mm/Makefile                      |    2
 mm/fincore.c                     |   65 +++++++++++++++++++++++++++++
 4 files changed, 69 insertions(+), 1 deletion(-)

diff -puN arch/x86/syscalls/syscall_64.tbl~fincore arch/x86/syscalls/syscall_64.tbl

--- a/arch/x86/syscalls/syscall_64.tbl~fincore
+++ a/arch/x86/syscalls/syscall_64.tbl

@@ -331,6 +331,7 @@
 322    64      execveat                stub_execveat
 323    64      preadv2                 sys_preadv2
 324    64      pwritev2                sys_pwritev2
+325    common  fincore                 sys_fincore

 #
 # x32-specific system call numbers start at 512 to avoid cache impact

diff -puN include/linux/syscalls.h~fincore include/linux/syscalls.h

--- a/include/linux/syscalls.h~fincore
+++ a/include/linux/syscalls.h

@@ -880,6 +880,8 @@ asmlinkage long sys_process_vm_writev(pi
 asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
                         unsigned long idx1, unsigned long idx2);
 asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
+asmlinkage long sys_fincore(int fd, unsigned char __user *page_map,
+                           loff_t offset, size_t len);
 asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
                            const char __user *uargs);
 asmlinkage long sys_getrandom(char __user *buf, size_t count,

diff -puN mm/Makefile~fincore mm/Makefile

--- a/mm/Makefile~fincore
+++ a/mm/Makefile

@@ -19,7 +19,7 @@ obj-y                 := filemap.o mempool.o oom_kill.
                           readahead.o swap.o truncate.o vmscan.o shmem.o \
                           util.o mmzone.o vmstat.o backing-dev.o \
                           mm_init.o mmu_context.o percpu.o slab_common.o \
-                          compaction.o vmacache.o \
+                          compaction.o vmacache.o fincore.o \
                           interval_tree.o list_lru.o workingset.o \
                           debug.o $(mmu-y)

diff -puN /dev/null mm/fincore.c

--- /dev/null
+++ a/mm/fincore.c

@@ -0,0 +1,65 @@
+#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+
+SYSCALL_DEFINE4(fincore, int, fd, unsigned char __user *, page_map,
+               loff_t, offset, size_t, len)
+{
+       struct fd f;
+       struct address_space *mapping;
+       loff_t cur_off;
+       loff_t end;
+       pgoff_t pgoff;
+       long ret = 0;
+
+       if (offset < 0 || (ssize_t)len <= 0)
+               return -EINVAL;
+
+       f = fdget(fd);
+
+       if (!f.file)
+               return -EBADF;
+
+       if (is_file_hugepages(f.file)) {
+               ret = -EINVAL;
+               goto out;
+       }
+
+       if (!S_ISREG(file_inode(f.file)->i_mode)) {
+               ret = -EBADF;
+               goto out;
+       }
+
+       end = min_t(loff_t, offset + len, i_size_read(file_inode(f.file)));
+       pgoff = offset >> PAGE_CACHE_SHIFT;
+       mapping = f.file->f_mapping;
+
+       /*
+        * We probably need to do somethnig here to reduce the chance of the
+        * pages being reclaimed between fincore() and read().  eg,
+        * SetPageReferenced(page) or mark_page_accessed(page) or
+        * activate_page(page).
+        */
+       for (cur_off = offset; cur_off < end ; ) {
+               struct page *page;
+               loff_t end_of_coverage;
+
+               page = find_get_page(mapping, pgoff);
+               if (!page || !PageUptodate(page))
+                       break;
+               page_cache_release(page);
+
+               pgoff++;
+               end_of_coverage = min_t(loff_t, pgoff << PAGE_CACHE_SHIFT, end);
+               ret += end_of_coverage - cur_off;
+               cur_off = (cur_off + PAGE_CACHE_SIZE) & PAGE_CACHE_MASK;
+       }
+
+out:
+       fdput(f);
+       return ret;
+}

_