[PATCH] i386: Profile pc badness

Profile_pc was broken when using paravirtualization because the
assumption the kernel was running at CPL 0 was violated, causing
bad logic to read a random value off the stack.

The only way to be in kernel lock functions is to be in kernel
code, so validate that assumption explicitly by checking the CS
value.  We don't want to be fooled by BIOS / APM segments and
try to read those stacks, so only match KERNEL_CS.

I moved some stuff in segment.h to make it prettier.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andi Kleen <ak@suse.de>

3 files changed, 21 insertions, 12 deletions

diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 9603ccaba997..a4f67a6e6821 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -131,15 +131,13 @@ unsigned long profile_pc(struct pt_regs *regs)
         unsigned long pc = instruction_pointer(regs);
 
 #ifdef CONFIG_SMP
-        if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+        if (!v8086_mode(regs) && SEGMENT_IS_KERNEL_CODE(regs->xcs) &&
+            in_lock_functions(pc)) {
 #ifdef CONFIG_FRAME_POINTER
                 return *(unsigned long *)(regs->ebp + 4);
 #else
-                unsigned long *sp;
-                if ((regs->xcs & 3) == 0)
-                        sp = (unsigned long *)&regs->esp;
-                else
-                        sp = (unsigned long *)regs->esp;
+                unsigned long *sp = (unsigned long *)&regs->esp;
+
                 /* Return address is either directly at stack pointer
                    or above a saved eflags. Eflags has bits 22-31 zero,
                    kernel addresses don't. */
diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h
index 1646996c73da..6002597b9e12 100644
--- a/include/asm-i386/ptrace.h
+++ b/include/asm-i386/ptrace.h
@@ -49,6 +49,10 @@ static inline int user_mode_vm(struct pt_regs *regs)
 {
         return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL;
 }
+static inline int v8086_mode(struct pt_regs *regs)
+{
+        return (regs->eflags & VM_MASK);
+}
 
 #define instruction_pointer(regs) ((regs)->eip)
 #define regs_return_value(regs) ((regs)->eax)
diff --git a/include/asm-i386/segment.h b/include/asm-i386/segment.h
index 3c796af33776..065f10bfa487 100644
--- a/include/asm-i386/segment.h
+++ b/include/asm-i386/segment.h
@@ -83,14 +83,8 @@
  * The GDT has 32 entries
  */
 #define GDT_ENTRIES 32
-
 #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
@@ -134,4 +128,17 @@
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif
+/*
+ * Matching rules for certain types of segments.
+ */
+
+/* Matches only __KERNEL_CS, ignoring PnP / USER / APM segments */
+#define SEGMENT_IS_KERNEL_CODE(x) (((x) & 0xfc) == GDT_ENTRY_KERNEL_CS * 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)
+
 #endif