[PATCH] i386: Allow a kernel not to be in ring 0

We allow for the fact that the guest kernel may not run in ring 0.  This
requires some abstraction in a few places when setting %cs or checking
privilege level (user vs kernel).

This is Chris' [RFC PATCH 15/33] move segment checks to subarch, except rather
than using #define USER_MODE_MASK which depends on a config option, we use
Zach's more flexible approach of assuming ring 3 == userspace.  I also used
"get_kernel_rpl()" over "get_kernel_cs()" because I think it reads better in
the code...

1) Remove the hardcoded 3 and introduce #define SEGMENT_RPL_MASK 3 2) Add a
get_kernel_rpl() macro, and don't assume it's zero.

And:

Clean up of patch for letting kernel run other than ring 0:

a. Add some comments about the SEGMENT_IS_*_CODE() macros.
b. Add a USER_RPL macro.  (Code was comparing a value to a mask
   in some places and to the magic number 3 in other places.)
c. Add macros for table indicator field and use them.
d. Change the entry.S tests for LDT stack segment to use the macros

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Andi Kleen <ak@suse.de>

6 files changed, 31 insertions, 15 deletions

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 3872fca5c74a..284f2e908ad0 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -240,8 +240,9 @@ ret_from_intr:
 check_userspace:
 	movl EFLAGS(%esp), %eax		# mix EFLAGS and CS
 	movb CS(%esp), %al
-	testl $(VM_MASK | 3), %eax
-	jz resume_kernel
+	andl $(VM_MASK | SEGMENT_RPL_MASK), %eax
+	cmpl $USER_RPL, %eax
+	jb resume_kernel		# not returning to v8086 or userspace
 ENTRY(resume_userspace)
  	DISABLE_INTERRUPTS		# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
@@ -377,8 +378,8 @@ restore_all:
 	# See comments in process.c:copy_thread() for details.
 	movb OLDSS(%esp), %ah
 	movb CS(%esp), %al
-	andl $(VM_MASK | (4 << 8) | 3), %eax
-	cmpl $((4 << 8) | 3), %eax
+	andl $(VM_MASK | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
 restore_nocheck:
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 220aeca59c3a..8c190ca7ae44 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -338,7 +338,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 	regs.xes = __USER_DS;
 	regs.orig_eax = -1;
 	regs.eip = (unsigned long) kernel_thread_helper;
-	regs.xcs = __KERNEL_CS;
+	regs.xcs = __KERNEL_CS | get_kernel_rpl();
 	regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
 
 	/* Ok, create the new process.. */
diff --git a/arch/i386/mm/extable.c b/arch/i386/mm/extable.c
index de03c5430abc..0ce4f22a2635 100644
--- a/arch/i386/mm/extable.c
+++ b/arch/i386/mm/extable.c
@@ -11,7 +11,7 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 #ifdef CONFIG_PNPBIOS
-	if (unlikely((regs->xcs & ~15) == (GDT_ENTRY_PNPBIOS_BASE << 3)))
+	if (unlikely(SEGMENT_IS_PNP_CODE(regs->xcs)))
 	{
 		extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
 		extern u32 pnp_bios_is_utter_crap;
diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
index 0ce86168a0b1..5e17a3f43b41 100644
--- a/arch/i386/mm/fault.c
+++ b/arch/i386/mm/fault.c
@@ -27,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/kdebug.h>
+#include <asm/segment.h>
 
 extern void die(const char *,struct pt_regs *,long);
 
@@ -113,10 +114,10 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs,
 	}
 
 	/* The standard kernel/user address space limit. */
-	*eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg;
+	*eip_limit = user_mode(regs) ? USER_DS.seg : KERNEL_DS.seg;
 	
 	/* By far the most common cases. */
-	if (likely(seg == __USER_CS || seg == __KERNEL_CS))
+	if (likely(SEGMENT_IS_FLAT_CODE(seg)))
 		return eip;
 
 	/* Check the segment exists, is within the current LDT/GDT size,
@@ -430,11 +431,7 @@ good_area:
 	write = 0;
 	switch (error_code & 3) {
 		default:	/* 3: write, present */
-#ifdef TEST_VERIFY_AREA
-			if (regs->cs == KERNEL_CS)
-				printk("WP fault at %08lx\n", regs->eip);
-#endif
-			/* fall through */
+				/* fall through */
 		case 2:		/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto bad_area;
diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h
index 30a442ec2059..21bb91679c82 100644
--- a/include/asm-i386/ptrace.h
+++ b/include/asm-i386/ptrace.h
@@ -60,6 +60,7 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #include <asm/vm86.h>
+#include <asm/segment.h>
 
 struct task_struct;
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code);
@@ -73,11 +74,11 @@ extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int erro
  */
 static inline int user_mode(struct pt_regs *regs)
 {
-	return (regs->xcs & 3) != 0;
+	return (regs->xcs & SEGMENT_RPL_MASK) == USER_RPL;
 }
 static inline int user_mode_vm(struct pt_regs *regs)
 {
-	return ((regs->xcs & 3) | (regs->eflags & VM_MASK)) != 0;
+	return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL;
 }
 #define instruction_pointer(regs) ((regs)->eip)
 extern unsigned long profile_pc(struct pt_regs *regs);
diff --git a/include/asm-i386/segment.h b/include/asm-i386/segment.h
index faf995307b9e..b7ab59685ba7 100644
--- a/include/asm-i386/segment.h
+++ b/include/asm-i386/segment.h
@@ -83,6 +83,11 @@
 
 #define GDT_SIZE (GDT_ENTRIES * 8)
 
+/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */
+#define SEGMENT_IS_FLAT_CODE(x)  (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8)
+/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */
+#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
+
 /* Simple and small GDT entries for booting only */
 
 #define GDT_ENTRY_BOOT_CS		2
@@ -112,4 +117,16 @@
  */
 #define IDT_ENTRIES 256
 
+/* Bottom two bits of selector give the ring privilege level */
+#define SEGMENT_RPL_MASK	0x3
+/* Bit 2 is table indicator (LDT/GDT) */
+#define SEGMENT_TI_MASK		0x4
+
+/* User mode is privilege level 3 */
+#define USER_RPL		0x3
+/* LDT segment has TI set, GDT has it cleared */
+#define SEGMENT_LDT		0x4
+#define SEGMENT_GDT		0x0
+
+#define get_kernel_rpl()  0
 #endif