[PATCH] x86: make IOPL explicit

The pushf/popf in switch_to are ONLY used to switch IOPL.  Making this
explicit in C code is more clear.  This pushf/popf pair was added as a
bugfix for leaking IOPL to unprivileged processes when using
sysenter/sysexit based system calls (sysexit does not restore flags).

When requesting an IOPL change in sys_iopl(), it is just as easy to change
the current flags and the flags in the stack image (in case an IRET is
required), but there is no reason to force an IRET if we came in from the
SYSENTER path.

This change is the minimal solution for supporting a paravirtualized Linux
kernel that allows user processes to run with I/O privilege.  Other
solutions require radical rewrites of part of the low level fault / system
call handling code, or do not fully support sysenter based system calls.

Unfortunately, this added one field to the thread_struct.  But as a bonus,
on P4, the fastest time measured for switch_to() went from 312 to 260
cycles, a win of about 17% in the fast case through this performance
critical path.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/ioport.c

@@ -132,6 +132,7 @@ asmlinkage long sys_iopl(unsigned long unused)
 	volatile struct pt_regs * regs = (struct pt_regs *) &unused;
 	unsigned int level = regs->ebx;
 	unsigned int old = (regs->eflags >> 12) & 3;
+	struct thread_struct *t = &current->thread;
 
 	if (level > 3)
 		return -EINVAL;
@@ -140,8 +141,8 @@ asmlinkage long sys_iopl(unsigned long unused)
 		if (!capable(CAP_SYS_RAWIO))
 			return -EPERM;
 	}
-	regs->eflags = (regs->eflags &~ 0x3000UL) | (level << 12);
-	/* Make sure we return the long way (not sysenter) */
-	set_thread_flag(TIF_IRET);
+	t->iopl = level << 12;
+	regs->eflags = (regs->eflags & ~X86_EFLAGS_IOPL) | t->iopl;
+	set_iopl_mask(t->iopl);
 	return 0;
 }

arch/i386/kernel/process.c

@@ -711,6 +711,12 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
+	/*
+	 * Restore IOPL if needed.
+	 */
+	if (unlikely(prev->iopl != next->iopl))
+		set_iopl_mask(next->iopl);
+
 	/*
 	 * Now maybe reload the debug registers
 	 */

include/asm-i386/processor.h

@@ -455,6 +455,7 @@ struct thread_struct {
 	unsigned int		saved_fs, saved_gs;
 /* IO permissions */
 	unsigned long	*io_bitmap_ptr;
+ 	unsigned long	iopl;
 /* max allowed port in the bitmap, in bytes: */
 	unsigned long	io_bitmap_max;
 };
@@ -511,6 +512,21 @@ static inline void load_esp0(struct tss_struct *tss, struct thread_struct *threa
 			: /* no output */			\
 			:"r" (value))
 
+/*
+ * Set IOPL bits in EFLAGS from given mask
+ */
+static inline void set_iopl_mask(unsigned mask)
+{
+	unsigned int reg;
+	__asm__ __volatile__ ("pushfl;"
+			      "popl %0;"
+			      "andl %1, %0;"
+			      "orl %2, %0;"
+			      "pushl %0;"
+			      "popfl"
+				: "=&r" (reg)
+				: "i" (~X86_EFLAGS_IOPL), "r" (mask));
+}
 
 /* Forward declaration, a strange C thing */
 struct task_struct;

include/asm-i386/system.h

@@ -14,8 +14,7 @@ extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struc
 
 #define switch_to(prev,next,last) do {					\
 	unsigned long esi,edi;						\
-	asm volatile("pushfl\n\t"					\
-		     "pushl %%ebp\n\t"					\
+	asm volatile("pushl %%ebp\n\t"					\
 		     "movl %%esp,%0\n\t"	/* save ESP */		\
 		     "movl %5,%%esp\n\t"	/* restore ESP */	\
 		     "movl $1f,%1\n\t"		/* save EIP */		\
@@ -23,7 +22,6 @@ extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struc
 		     "jmp __switch_to\n"				\
 		     "1:\t"						\
 		     "popl %%ebp\n\t"					\
-		     "popfl"						\
 		     :"=m" (prev->thread.esp),"=m" (prev->thread.eip),	\
 		      "=a" (last),"=S" (esi),"=D" (edi)			\
 		     :"m" (next->thread.esp),"m" (next->thread.eip),	\