vserver 1.9.5.x5

[linux-2.6.git] / mm / mlock.c

diff --git a/mm/mlock.c b/mm/mlock.c
index 861c7a3..e3bc9cd 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -7,6 +7,7 @@
 
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/syscalls.h>
 #include <linux/vs_memory.h>
 
 
@@ -21,17 +22,15 @@ static int mlock_fixup(struct vm_area_struct * vma,
                goto out;
 
        if (start != vma->vm_start) {
-               if (split_vma(mm, vma, start, 1)) {
-                       ret = -EAGAIN;
+               ret = split_vma(mm, vma, start, 1);
+               if (ret)
                        goto out;
-               }
        }
 
        if (end != vma->vm_end) {
-               if (split_vma(mm, vma, end, 0)) {
-                       ret = -EAGAIN;
+               ret = split_vma(mm, vma, end, 0);
+               if (ret)
                        goto out;
-               }
        }
 
        /*
@@ -47,12 +46,15 @@ static int mlock_fixup(struct vm_area_struct * vma,
        pages = (end - start) >> PAGE_SHIFT;
        if (newflags & VM_LOCKED) {
                pages = -pages;
-               ret = make_pages_present(start, end);
+               if (!(newflags & VM_IO))
+                       ret = make_pages_present(start, end);
        }
 
        // vma->vm_mm->locked_vm -= pages;
        vx_vmlocked_sub(vma->vm_mm, pages);
 out:
+       if (ret == -ENOMEM)
+               ret = -EAGAIN;
        return ret;
 }
 
@@ -62,8 +64,6 @@ static int do_mlock(unsigned long start, size_t len, int on)
        struct vm_area_struct * vma, * next;
        int error;
 
-       if (on && !capable(CAP_IPC_LOCK))
-               return -EPERM;
        len = PAGE_ALIGN(len);
        end = start + len;
        if (end < start)
@@ -109,6 +109,9 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
        unsigned long lock_limit;
        int error = -ENOMEM;
 
+       if (!can_do_mlock())
+               return -EPERM;
+
        down_write(&current->mm->mmap_sem);
        len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
        start &= PAGE_MASK;
@@ -118,11 +121,11 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
                goto out;
        locked = current->mm->locked_vm + grow;
 
-       lock_limit = current->rlim[RLIMIT_MEMLOCK].rlim_cur;
+       lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
        lock_limit >>= PAGE_SHIFT;
 
        /* check against resource limits */
-       if (locked <= lock_limit)
+       if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
                error = do_mlock(start, len, 1);
 out:
        up_write(&current->mm->mmap_sem);
@@ -143,19 +146,15 @@ asmlinkage long sys_munlock(unsigned long start, size_t len)
 
 static int do_mlockall(int flags)
 {
-       int error;
-       unsigned int def_flags;
        struct vm_area_struct * vma;
+       unsigned int def_flags = 0;
 
-       if (!capable(CAP_IPC_LOCK))
-               return -EPERM;
-
-       def_flags = 0;
        if (flags & MCL_FUTURE)
                def_flags = VM_LOCKED;
        current->mm->def_flags = def_flags;
+       if (flags == MCL_FUTURE)
+               goto out;
 
-       error = 0;
        for (vma = current->mm->mmap; vma ; vma = vma->vm_next) {
                unsigned int newflags;
 
@@ -166,7 +165,8 @@ static int do_mlockall(int flags)
                /* Ignore errors */
                mlock_fixup(vma, vma->vm_start, vma->vm_end, newflags);
        }
-       return error;
+out:
+       return 0;
 }
 
 asmlinkage long sys_mlockall(int flags)
@@ -174,20 +174,26 @@ asmlinkage long sys_mlockall(int flags)
        unsigned long lock_limit;
        int ret = -EINVAL;
 
-       down_write(&current->mm->mmap_sem);
        if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
                goto out;
 
-       lock_limit = current->rlim[RLIMIT_MEMLOCK].rlim_cur;
+       ret = -EPERM;
+       if (!can_do_mlock())
+               goto out;
+
+       down_write(&current->mm->mmap_sem);
+
+       lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
        lock_limit >>= PAGE_SHIFT;
 
        ret = -ENOMEM;
        if (!vx_vmlocked_avail(current->mm, current->mm->total_vm))
                goto out;
-       if (current->mm->total_vm <= lock_limit)
+       if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
+           capable(CAP_IPC_LOCK))
                ret = do_mlockall(flags);
-out:
        up_write(&current->mm->mmap_sem);
+out:
        return ret;
 }
 
@@ -200,3 +206,36 @@ asmlinkage long sys_munlockall(void)
        up_write(&current->mm->mmap_sem);
        return ret;
 }
+
+/*
+ * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
+ * shm segments) get accounted against the user_struct instead.
+ */
+static DEFINE_SPINLOCK(shmlock_user_lock);
+
+int user_shm_lock(size_t size, struct user_struct *user)
+{
+       unsigned long lock_limit, locked;
+       int allowed = 0;
+
+       locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+       lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+       lock_limit >>= PAGE_SHIFT;
+       spin_lock(&shmlock_user_lock);
+       if (locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
+               goto out;
+       get_uid(user);
+       user->locked_shm += locked;
+       allowed = 1;
+out:
+       spin_unlock(&shmlock_user_lock);
+       return allowed;
+}
+
+void user_shm_unlock(size_t size, struct user_struct *user)
+{
+       spin_lock(&shmlock_user_lock);
+       user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+       spin_unlock(&shmlock_user_lock);
+       free_uid(user);
+}