mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage

The previous patch introduced a flag that specified pages in a VMA should
be placed on the unevictable LRU, but they should not be made present when
the area is created.  This patch adds the ability to set this state via
the new mlock system calls.

We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
MCL_ONFAULT should be used as a modifier to the two other mlockall flags.
When used with MCL_CURRENT, all current mappings will be marked with
VM_LOCKED | VM_LOCKONFAULT.  When used with MCL_FUTURE, the mm->def_flags
will be marked with VM_LOCKED | VM_LOCKONFAULT.  When used with both
MCL_CURRENT and MCL_FUTURE, all current mappings and mm->def_flags will be
marked with VM_LOCKED | VM_LOCKONFAULT.

Prior to this patch, mlockall() will unconditionally clear the
mm->def_flags any time it is called without MCL_FUTURE.  This behavior is
maintained after adding MCL_ONFAULT.  If a call to mlockall(MCL_FUTURE) is
followed by mlockall(MCL_CURRENT), the mm->def_flags will be cleared and
new VMAs will be unlocked.  This remains true with or without MCL_ONFAULT
in either mlockall() invocation.

munlock() will unconditionally clear both vma flags.  munlockall()
unconditionally clears for VMA flags on all VMAs and in the mm->def_flags
field.

Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 0086b472bc2b4c8e2a588a2a8ab763c3243362f7..f2f9496717981766aa0ac53ef5054a9250dd1218 100644 (file)
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -37,6 +37,9 @@
 
 #define MCL_CURRENT     8192           /* lock all currently mapped pages */
 #define MCL_FUTURE     16384           /* lock all additions to address space */
+#define MCL_ONFAULT    32768           /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT  0x01            /* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL    0               /* no further special treatment */
 #define MADV_RANDOM    1               /* expect random page references */

diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index cfcb876cae6bc017e7fbf53e3df33fdc637680f3..97c03f4689243be4e7b6157df73683fb47480d39 100644 (file)
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -61,6 +61,12 @@
  */
 #define MCL_CURRENT    1               /* lock all current mappings */
 #define MCL_FUTURE     2               /* lock all future mappings */
+#define MCL_ONFAULT    4               /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT  0x01            /* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL    0               /* no further special treatment */
 #define MADV_RANDOM    1               /* expect random page references */

diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 294d251ca7b2ee6472d6da01cf4e73f84a177cc2..ecc3ae1ca28e2d573f578709fa6c2c023159fa72 100644 (file)
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -31,6 +31,9 @@
 
 #define MCL_CURRENT    1               /* lock all current mappings */
 #define MCL_FUTURE     2               /* lock all future mappings */
+#define MCL_ONFAULT    4               /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT  0x01            /* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL     0               /* no further special treatment */
 #define MADV_RANDOM     1               /* expect random page references */

diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 6ea26df0a73c19ba7461292d2538f8f07908ad36..03c06ba7464f4fc47d7f5b6f0fb0057fa69d8f1c 100644 (file)
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -22,6 +22,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT    0x8000          /* lock all pages that are faulted in */
 
 #define MAP_POPULATE   0x8000          /* populate (prefault) pagetables */
 #define MAP_NONBLOCK   0x10000         /* do not block on IO */

diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h
index 0b14df33cffa48ab9d0a98c553020af60c00d67d..9765896ecb2c89204465de20bc41afb53561a77e 100644 (file)
--- a/arch/sparc/include/uapi/asm/mman.h
+++ b/arch/sparc/include/uapi/asm/mman.h
@@ -17,6 +17,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT    0x8000          /* lock all pages that are faulted in */
 
 #define MAP_POPULATE   0x8000          /* populate (prefault) pagetables */
 #define MAP_NONBLOCK   0x10000         /* do not block on IO */

diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h
index 81b8fc348d63d9caea21b2edd5e94cfe999313dd..63ee13faf17d2461ad79255bde0669a862e8d344 100644 (file)
--- a/arch/tile/include/uapi/asm/mman.h
+++ b/arch/tile/include/uapi/asm/mman.h
@@ -36,6 +36,7 @@
  */
 #define MCL_CURRENT    1               /* lock all current mappings */
 #define MCL_FUTURE     2               /* lock all future mappings */
+#define MCL_ONFAULT    4               /* lock all pages that are faulted in */
 
 
 #endif /* _ASM_TILE_MMAN_H */

diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 201aec0e0446e84d2ee27d1f8bcd5a050c42344c..360944e1da52a0f31572a423a72a16a33fc86537 100644 (file)
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -74,6 +74,12 @@
  */
 #define MCL_CURRENT    1               /* lock all current mappings */
 #define MCL_FUTURE     2               /* lock all future mappings */
+#define MCL_ONFAULT    4               /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT  0x01            /* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL    0               /* no further special treatment */
 #define MADV_RANDOM    1               /* expect random page references */

diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36f1046bd6605ecdd769e4f70e59404e16b..a74dd84bbb6d04777fe76e043dbd6246b5914d1a 100644 (file)
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -25,6 +25,11 @@
 # define MAP_UNINITIALIZED 0x0         /* Don't support this flag */
 #endif
 
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT  0x01            /* Lock pages in range after they are faulted in, do not prefault */
+
 #define MS_ASYNC       1               /* sync memory asynchronously */
 #define MS_INVALIDATE  2               /* invalidate the caches */
 #define MS_SYNC                4               /* synchronous memory sync */

diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index e9fe6fd2a07450b36b607b321c056089e7bd59dc..7162cd4cca737b5e92e873e31f2c2a3bf50e3029 100644 (file)
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -17,5 +17,6 @@
 
 #define MCL_CURRENT    1               /* lock all current mappings */
 #define MCL_FUTURE     2               /* lock all future mappings */
+#define MCL_ONFAULT    4               /* lock all pages that are faulted in */
 
 #endif /* __ASM_GENERIC_MMAN_H */

diff --git a/mm/mlock.c b/mm/mlock.c
index ca3894113b974963aefa547fa36c7a11ad672d16..a18d4aea7685534142425d224acc38c19a44d5f1 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
        if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
            is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
-               goto out;       /* don't set VM_LOCKED,  don't count */
+               /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+               goto out;
 
        pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
        *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
@@ -577,7 +578,8 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
                prev = vma;
 
        for (nstart = start ; ; ) {
-               vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED;
+               vm_flags_t newflags =
+                       vma->vm_flags & ~(VM_LOCKED | VM_LOCKONFAULT);
 
                newflags |= flags;
 
@@ -646,10 +648,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
 {
-       if (flags)
+       vm_flags_t vm_flags = VM_LOCKED;
+
+       if (flags & ~MLOCK_ONFAULT)
                return -EINVAL;
 
-       return do_mlock(start, len, VM_LOCKED);
+       if (flags & MLOCK_ONFAULT)
+               vm_flags |= VM_LOCKONFAULT;
+
+       return do_mlock(start, len, vm_flags);
 }
 
 SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
@@ -666,24 +673,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
        return ret;
 }
 
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this.  If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack.  If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
 static int apply_mlockall_flags(int flags)
 {
        struct vm_area_struct * vma, * prev = NULL;
+       vm_flags_t to_add = 0;
 
-       if (flags & MCL_FUTURE)
+       current->mm->def_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
+       if (flags & MCL_FUTURE) {
                current->mm->def_flags |= VM_LOCKED;
-       else
-               current->mm->def_flags &= ~VM_LOCKED;
 
-       if (flags == MCL_FUTURE)
-               goto out;
+               if (flags & MCL_ONFAULT)
+                       current->mm->def_flags |= VM_LOCKONFAULT;
+
+               if (!(flags & MCL_CURRENT))
+                       goto out;
+       }
+
+       if (flags & MCL_CURRENT) {
+               to_add |= VM_LOCKED;
+               if (flags & MCL_ONFAULT)
+                       to_add |= VM_LOCKONFAULT;
+       }
 
        for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
                vm_flags_t newflags;
 
-               newflags = vma->vm_flags & ~VM_LOCKED;
-               if (flags & MCL_CURRENT)
-                       newflags |= VM_LOCKED;
+               newflags = vma->vm_flags & ~(VM_LOCKED | VM_LOCKONFAULT);
+               newflags |= to_add;
 
                /* Ignore errors */
                mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -698,7 +724,7 @@ SYSCALL_DEFINE1(mlockall, int, flags)
        unsigned long lock_limit;
        int ret;
 
-       if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
+       if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
                return -EINVAL;
 
        if (!can_do_mlock())