[PATCH FIXED] x86: only enable interrupts when kernel state has beenset up

[Jeremy Fitzhardinge]

The sysenter path tries to enable interrupts immediately.  Unfortunately
this doesn't work in a paravirt environment, because not enough kernel
state has been set up at that point (namely, pointing %fs to the kernel
percpu data segment).  To fix this, defer ENABLE_INTERRUPTS until after
the kernel state has been set up.

Unfortunately this means that we're running with interrupts disabled
for a while without calling the IRQ tracing code, but that can't be
called without setting up %fs either.

[ Fix since last posting: make sure saved eflags has interrupts enabled. ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
---
arch/x86/kernel/entry_32.S |   19 ++++++++++---------
1 file changed, 10 insertions(+), 9 deletions(-)

===================================================================
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -290,10 +290,10 @@ ENTRY(ia32_sysenter_target)
	movl TSS_sysenter_sp0(%esp),%esp
ENTRY(sysenter_past_esp)
	/*
-	 * No need to follow this irqs on/off section: the syscall
-	 * disabled irqs and here we enable it straight after entry:
+	 * Interrupts are disabled here, but we can't trace it until
+	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
+	 * we immediately enable interrupts at that point anyway.
	 */
-	ENABLE_INTERRUPTS(CLBR_NONE)
	pushl $(__USER_DS)
	CFI_ADJUST_CFA_OFFSET 4
	/*CFI_REL_OFFSET ss, 0*/
@@ -301,6 +301,7 @@ ENTRY(sysenter_past_esp)
	CFI_ADJUST_CFA_OFFSET 4
	CFI_REL_OFFSET esp, 0
	pushfl
+	orl $X86_EFLAGS_IF, (%esp)
	CFI_ADJUST_CFA_OFFSET 4
	pushl $(__USER_CS)
	CFI_ADJUST_CFA_OFFSET 4
@@ -314,6 +315,11 @@ ENTRY(sysenter_past_esp)
	CFI_ADJUST_CFA_OFFSET 4
	CFI_REL_OFFSET eip, 0

+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
/*
 * Load the potential sixth argument from user stack.
 * Careful about security.
@@ -321,14 +327,12 @@ ENTRY(sysenter_past_esp)
	cmpl $__PAGE_OFFSET-3,%ebp
	jae syscall_fault
1:	movl (%ebp),%ebp
+	movl %ebp,PT_EBP(%esp)
.section __ex_table,"a"
	.align 4
	.long 1b,syscall_fault
.previous

-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
	GET_THREAD_INFO(%ebp)

	/* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
@@ -542,9 +546,6 @@ END(syscall_exit_work)

	RING0_INT_FRAME			# can't unwind into user space anyway
syscall_fault:
-	pushl %eax			# save orig_eax
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
	GET_THREAD_INFO(%ebp)
	movl $-EFAULT,PT_EAX(%esp)
	jmp resume_userspace

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/