[PATCH 1/2] unshare system call: System Call handler function sys_unshare
Signed-off-by: Janak Desai
fork.c | 202 +++--
1 files changed, 196 insertions(+), 6 deletions(-)
diff -Naurp 2.6.13-rc5-mm1/kernel/fork.c 2.6.13-rc5-mm1+unshare/kernel/fork.c
--- 2.6.13-rc5-mm1/kernel/fork.c2005-08-07 15:33:45.0 +
+++ 2.6.13-rc5-mm1+unshare/kernel/fork.c2005-08-07 19:03:49.0
+
@@ -57,6 +57,17 @@ int nr_threads; /* The idle threads do
int max_threads; /* tunable limit on nr_threads */
+/*
+ * mm_copy gets called from clone or unshare system calls. When called
+ * from clone, mm_struct may be shared depending on the clone flags
+ * argument, however, when called from the unshare system call, a private
+ * copy of mm_struct is made.
+ */
+enum mm_copy_share {
+ MAY_SHARE,
+ UNSHARE,
+};
+
DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
@@ -447,16 +458,26 @@ void mm_release(struct task_struct *tsk,
}
}
-static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_mm(unsigned long clone_flags, struct task_struct * tsk,
+ enum mm_copy_share copy_share_action)
{
struct mm_struct * mm, *oldmm;
int retval;
- tsk->min_flt = tsk->maj_flt = 0;
- tsk->nvcsw = tsk->nivcsw = 0;
+ /*
+* If the process memory is being duplicated as part of the
+* unshare system call, we are working with the current process
+* and not a newly allocated task strucutre, and should not
+* zero out fault info, context switch counts, mm and active_mm
+* fields.
+*/
+ if (copy_share_action == MAY_SHARE) {
+ tsk->min_flt = tsk->maj_flt = 0;
+ tsk->nvcsw = tsk->nivcsw = 0;
- tsk->mm = NULL;
- tsk->active_mm = NULL;
+ tsk->mm = NULL;
+ tsk->active_mm = NULL;
+ }
/*
* Are we cloning a kernel thread?
@@ -973,7 +994,7 @@ static task_t *copy_process(unsigned lon
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
- if ((retval = copy_mm(clone_flags, p)))
+ if ((retval = copy_mm(clone_flags, p, MAY_SHARE)))
goto bad_fork_cleanup_signal;
if ((retval = copy_keys(clone_flags, p)))
goto bad_fork_cleanup_mm;
@@ -1288,3 +1309,172 @@ void __init proc_caches_init(void)
sizeof(struct mm_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
}
+
+/*
+ * unshare_mm is called from the unshare system call handler function to
+ * make a private copy of the mm_struct structure. It calls copy_mm with
+ * CLONE_VM flag cleard, to ensure that a private copy of mm_struct is made,
+ * and with mm_copy_share enum set to UNSHARE, to ensure that copy_mm
+ * does not clear fault info, context switch counts, mm and active_mm
+ * fields of the mm_struct.
+ */
+static int unshare_mm(unsigned long unshare_flags, struct task_struct *tsk)
+{
+ int retval = 0;
+ struct mm_struct *mm = tsk->mm;
+
+ /*
+* If the virtual memory is being shared, make a private
+* copy and disassociate the process from the shared virtual
+* memory.
+*/
+ if (atomic_read(&mm->mm_users) > 1) {
+ retval = copy_mm((unshare_flags & ~CLONE_VM), tsk, UNSHARE);
+
+ /*
+* If copy_mm was successful, decrement the number of users
+* on the original, shared, mm_struct.
+*/
+ if (!retval)
+ atomic_dec(&mm->mm_users);
+ }
+ return retval;
+}
+
+/*
+ * unshare_sighand is called from the unshare system call handler function to
+ * make a private copy of the sighand_struct structure. It calls copy_sighand
+ * with CLONE_SIGHAND cleared to ensure that a new signal handler structure
+ * is cloned from the current shared one.
+ */
+static int unshare_sighand(unsigned long unshare_flags, struct task_struct
*tsk)
+{
+ int retval = 0;
+ struct sighand_struct *sighand = tsk->sighand;
+
+ /*
+* If the signal handlers are being shared, make a private
+* copy and disassociate the process from the shared signal
+* handlers.
+*/
+ if (atomic_read(&sighand->count) > 1) {
+ retval = copy_sighand((unshare_flags & ~CLONE_SIGHAND), tsk);
+
+ /*
+* If copy_sighand was successful, decrement the use count
+* on the original, shared, sighand_struct.
+*/
+ if (!retval)
+ atomic_dec(&sighand->count);
+ }
+ return retval;
+}
+
+/*
+ * unshare_namespa
