2 files changed, 14 insertions, 1 deletions

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 1e45ff292bc9..3c73dc865ead 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -245,6 +245,9 @@ syscall_exit:
 
 restore_all:
         movl EFLAGS(%esp), %eax         # mix EFLAGS, SS and CS
+        # Warning: OLDSS(%esp) contains the wrong/random values if we
+        # are returning to the kernel.
+        # See comments in process.c:copy_thread() for details.
         movb OLDSS(%esp), %ah
         movb CS(%esp), %al
         andl $(VM_MASK | (4 << 8) | 3), %eax
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index c36fedf40e95..36145efc61b5 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -405,7 +405,17 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
         childregs->esp = esp;
 
         p->thread.esp = (unsigned long) childregs;
-        p->thread.esp0 = (unsigned long) (childregs+1);
+        /*
+         * The below -8 is to reserve 8 bytes on top of the ring0 stack.
+         * This is necessary to guarantee that the entire "struct pt_regs"
+         * is accessable even if the CPU haven't stored the SS/ESP registers
+         * on the stack (interrupt gate does not save these registers
+         * when switching to the same priv ring).
+         * Therefore beware: accessing the xss/esp fields of the
+         * "struct pt_regs" is possible, but they may contain the
+         * completely wrong values.
+         */
+        p->thread.esp0 = (unsigned long) (childregs+1) - 8;
 
         p->thread.eip = (unsigned long) ret_from_fork;