m68k: Add NPTL support

This patch adds several syscalls, that provide necessary
functionality to support NPTL on m68k/ColdFire.
The syscalls are get_thread_area, set_thread_area, atomic_cmpxchg_32 and
atomic_barrier.
The cmpxchg syscall is required for ColdFire as it doesn't support 'cas'
instruction.

Also a ptrace call PTRACE_GET_THREAD_AREA is added to allow debugger to
inspect the TLS storage.

Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

4 files changed, 94 insertions, 0 deletions

diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S
index 77fc7c16bf48..e136b8cbe9b9 100644
--- a/arch/m68k/kernel/entry.S
+++ b/arch/m68k/kernel/entry.S
@@ -761,4 +761,8 @@ sys_call_table:
         .long sys_pwritev               /* 330 */
         .long sys_rt_tgsigqueueinfo
         .long sys_perf_event_open
+        .long sys_get_thread_area
+        .long sys_set_thread_area
+        .long sys_atomic_cmpxchg_32     /* 335 */
+        .long sys_atomic_barrier
 
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 05296593e718..17c3f325255d 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -251,6 +251,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 
         p->thread.usp = usp;
         p->thread.ksp = (unsigned long)childstack;
+
+        if (clone_flags & CLONE_SETTLS)
+                task_thread_info(p)->tp_value = regs->d5;
+
         /*
          * Must save the current SFC/DFC value, NOT the value when
          * the parent was last descheduled - RGH  10-08-96
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index 1fc217e5f06b..616e59752c29 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -245,6 +245,11 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                         ret = -EFAULT;
                 break;
 
+        case PTRACE_GET_THREAD_AREA:
+                ret = put_user(task_thread_info(child)->tp_value,
+                               (unsigned long __user *)data);
+                break;
+
         default:
                 ret = ptrace_request(child, request, addr, data);
                 break;
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 218f441de667..e3ad2d671973 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -28,6 +28,11 @@
 #include <asm/traps.h>
 #include <asm/page.h>
 #include <asm/unistd.h>
+#include <linux/elf.h>
+#include <asm/tlb.h>
+
+asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
+                             unsigned long error_code);
 
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
         unsigned long prot, unsigned long flags,
@@ -595,3 +600,79 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
                         : "d" (__a), "d" (__b), "d" (__c));
         return __res;
 }
+
+asmlinkage unsigned long sys_get_thread_area(void)
+{
+        return current_thread_info()->tp_value;
+}
+
+asmlinkage int sys_set_thread_area(unsigned long tp)
+{
+        current_thread_info()->tp_value = tp;
+        return 0;
+}
+
+/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
+   D1 (newval).  */
+asmlinkage int
+sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
+                      unsigned long __user * mem)
+{
+        /* This was borrowed from ARM's implementation.  */
+        for (;;) {
+                struct mm_struct *mm = current->mm;
+                pgd_t *pgd;
+                pmd_t *pmd;
+                pte_t *pte;
+                spinlock_t *ptl;
+                unsigned long mem_value;
+
+                down_read(&mm->mmap_sem);
+                pgd = pgd_offset(mm, (unsigned long)mem);
+                if (!pgd_present(*pgd))
+                        goto bad_access;
+                pmd = pmd_offset(pgd, (unsigned long)mem);
+                if (!pmd_present(*pmd))
+                        goto bad_access;
+                pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);
+                if (!pte_present(*pte) || !pte_dirty(*pte)
+                    || !pte_write(*pte)) {
+                        pte_unmap_unlock(pte, ptl);
+                        goto bad_access;
+                }
+
+                mem_value = *mem;
+                if (mem_value == oldval)
+                        *mem = newval;
+
+                pte_unmap_unlock(pte, ptl);
+                up_read(&mm->mmap_sem);
+                return mem_value;
+
+              bad_access:
+                up_read(&mm->mmap_sem);
+                /* This is not necessarily a bad access, we can get here if
+                   a memory we're trying to write to should be copied-on-write.
+                   Make the kernel do the necessary page stuff, then re-iterate.
+                   Simulate a write access fault to do that.  */
+                {
+                        /* The first argument of the function corresponds to
+                           D1, which is the first field of struct pt_regs.  */
+                        struct pt_regs *fp = (struct pt_regs *)&newval;
+
+                        /* '3' is an RMW flag.  */
+                        if (do_page_fault(fp, (unsigned long)mem, 3))
+                                /* If the do_page_fault() failed, we don't
+                                   have anything meaningful to return.
+                                   There should be a SIGSEGV pending for
+                                   the process.  */
+                                return 0xdeadbeef;
+                }
+        }
+}
+
+asmlinkage int sys_atomic_barrier(void)
+{
+        /* no code needed for uniprocs */
+        return 0;
+}