x86, fpu: split FPU state from task struct - v5

Split the FPU save area from the task struct. This allows easy migration
of FPU context, and it's generally cleaner. It also allows the following
two optimizations:

1) only allocate when the application actually uses FPU, so in the first
lazy FPU trap. This could save memory for non-fpu using apps. Next patch
does this lazy allocation.

2) allocate the right size for the actual cpu rather than 512 bytes always.
Patches enabling xsave/xrstor support (coming shortly) will take advantage
of this.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 25 insertions, 6 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 9c042f901570..44a18192c420 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -132,6 +132,10 @@ void __put_task_struct(struct task_struct *tsk)
                 free_task(tsk);
 }
 
+void __attribute__((weak)) arch_task_cache_init(void)
+{
+}
+
 void __init fork_init(unsigned long mempages)
 {
 #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
@@ -144,6 +148,9 @@ void __init fork_init(unsigned long mempages)
                         ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL);
 #endif
 
+        /* do the arch specific task caches init */
+        arch_task_cache_init();
+
         /*
          * The default maximum number of threads is set to a safe
          * value: the thread structures can take up at most half
@@ -163,6 +170,13 @@ void __init fork_init(unsigned long mempages)
                 init_task.signal->rlim[RLIMIT_NPROC];
 }
 
+int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
+                                               struct task_struct *src)
+{
+        *dst = *src;
+        return 0;
+}
+
 static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
         struct task_struct *tsk;
@@ -181,15 +195,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
                 return NULL;
         }
 
-        *tsk = *orig;
+        err = arch_dup_task_struct(tsk, orig);
+        if (err)
+                goto out;
+
         tsk->stack = ti;
 
         err = prop_local_init_single(&tsk->dirties);
-        if (err) {
-                free_thread_info(ti);
-                free_task_struct(tsk);
-                return NULL;
-        }
+        if (err)
+                goto out;
 
         setup_thread_stack(tsk, orig);
 
@@ -205,6 +219,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 #endif
         tsk->splice_pipe = NULL;
         return tsk;
+
+out:
+        free_thread_info(ti);
+        free_task_struct(tsk);
+        return NULL;
 }
 
 #ifdef CONFIG_MMU