mm: kill vma flag VM_RESERVED and mm->reserved_vm counter

A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA,
currently it lost original meaning but still has some effects:

 | effect                 | alternative flags
-+------------------------+---------------------------------------------
1| account as reserved_vm | VM_IO
2| skip in core dump      | VM_IO, VM_DONTDUMP
3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP
4| do not mlock           | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP

This patch removes reserved_vm counter from mm_struct.  Seems like nobody
cares about it, it does not exported into userspace directly, it only
reduces total_vm showed in proc.

Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP.

remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP.
remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP.

[akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Carsten Otte <cotte@de.ibm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morris <james.l.morris@oracle.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Venkatesh Pallipadi <venki@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 9 insertions, 14 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index f9ccb16559ee..9638620a7530 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1469,8 +1469,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
                  */
                 if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
                                  VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
-                                 VM_RESERVED  | VM_HUGETLB |
-                                 VM_NONLINEAR | VM_MIXEDMAP))
+                                 VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP))
                         return 0;               /* just ignore the advice */
 
 #ifdef VM_SAO
diff --git a/mm/memory.c b/mm/memory.c
index 7b1e4feaec06..e09c04813186 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2297,14 +2297,13 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
          * rest of the world about it:
          *   VM_IO tells people not to look at these pages
          *      (accesses can have side effects).
-         *   VM_RESERVED is specified all over the place, because
-         *      in 2.4 it kept swapout's vma scan off this vma; but
-         *      in 2.6 the LRU scan won't even find its pages, so this
-         *      flag means no more than count its pages in reserved_vm,
-         *      and omit it from core dump, even when VM_IO turned off.
          *   VM_PFNMAP tells the core MM that the base pages are just
          *      raw PFN mappings, and do not have a "struct page" associated
          *      with them.
+         *   VM_DONTEXPAND
+         *      Disable vma merging and expanding with mremap().
+         *   VM_DONTDUMP
+         *      Omit vma from core dump, even when VM_IO turned off.
          *
          * There's a horrible special case to handle copy-on-write
          * behaviour that some programs depend on. We mark the "original"
@@ -2321,7 +2320,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
         if (err)
                 return -EINVAL;
 
-        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+        vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
 
         BUG_ON(addr >= end);
         pfn -= addr >> PAGE_SHIFT;
diff --git a/mm/mlock.c b/mm/mlock.c
index ef726e8aa8e9..a948be4b7ba7 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -227,7 +227,7 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
         if (vma->vm_flags & (VM_IO | VM_PFNMAP))
                 goto no_mlock;
 
-        if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
+        if (!((vma->vm_flags & VM_DONTEXPAND) ||
                         is_vm_hugetlb_page(vma) ||
                         vma == get_gate_vma(current->mm))) {
 
diff --git a/mm/mmap.c b/mm/mmap.c
index c1ad2e78ea58..a76042dc806d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -945,8 +945,6 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags,
                         mm->exec_vm += pages;
         } else if (flags & stack_flags)
                 mm->stack_vm += pages;
-        if (flags & (VM_RESERVED|VM_IO))
-                mm->reserved_vm += pages;
 }
 #endif /* CONFIG_PROC_FS */
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 9c4a7b63a4df..12e84e69dd06 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1811,7 +1811,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
         if (addr != (pfn << PAGE_SHIFT))
                 return -EINVAL;
 
-        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+        vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
         return 0;
 }
 EXPORT_SYMBOL(remap_pfn_range);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 2bb90b1d241c..8de704679bfc 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2163,8 +2163,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
                 usize -= PAGE_SIZE;
         } while (usize > 0);
 
-        /* Prevent "things" like memory migration? VM_flags need a cleanup... */
-        vma->vm_flags |= VM_RESERVED;
+        vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 
         return 0;
 }