We eventually want to make it all the way into C code before
enabling interrupts.  We need to rework our flags handling slightly
to delay enabling interrupts.

Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
 arch/x86/entry/entry_64_compat.S | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index aa76864a8a6b..1432d60a1f4a 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -58,14 +58,9 @@ ENDPROC(native_usergs_sysret32)
  * with the int 0x80 path.
  */
 ENTRY(entry_SYSENTER_compat)
-       /*
-        * Interrupts are off on entry.
-        * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-        * it is too small to ever cause noticeable irq latency.
-        */
+       /* Interrupts are off on entry. */
        SWAPGS_UNSAFE_STACK
        movq    PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-       ENABLE_INTERRUPTS(CLBR_NONE)
 
        /* Zero-extending 32-bit regs, do not remove */
        movl    %ebp, %ebp
@@ -76,7 +71,16 @@ ENTRY(entry_SYSENTER_compat)
        /* Construct struct pt_regs on stack */
        pushq   $__USER32_DS            /* pt_regs->ss */
        pushq   %rbp                    /* pt_regs->sp */
-       pushfq                          /* pt_regs->flags */
+
+       /*
+        * Push flags.  This is nasty.  First, interrupts are currently
+        * off, but we need pt_regs->flags to have IF set.  Second, even
+        * if TF was set when SYSENTER started, it's clear by now.  We fix
+        * that later using TIF_SINGLESTEP.
+        */
+       pushfq                          /* pt_regs->flags (except IF = 0) */
+       orl     $X86_EFLAGS_IF, (%rsp)  /* Fix saved flags */
+
        pushq   $__USER32_CS            /* pt_regs->cs */
        pushq   %r10                    /* pt_regs->ip = 
thread_info->sysenter_return */
        pushq   %rax                    /* pt_regs->orig_ax */
@@ -92,12 +96,22 @@ ENTRY(entry_SYSENTER_compat)
         * Sysenter doesn't filter flags, so we need to clear NT
         * ourselves.  To save a few cycles, we can check whether
         * NT was set instead of doing an unconditional popfq.
+        * This needs to happen before enabling interrupts so that
+        * we don't get preempted with NT set.
         */
        testl   $X86_EFLAGS_NT, EFLAGS(%rsp)
        jnz     sysenter_fix_flags
 sysenter_flags_fixed:
 
        /*
+        * Re-enable interrupts.  IRQ tracing already thinks that IRQs are
+        * on (since we treat user mode as having IRQs on), and the
+        * prologue above is too short for it to be worth adding a
+        * tracing round trip.
+        */
+       ENABLE_INTERRUPTS(CLBR_NONE)
+
+       /*
         * no need to do an access_ok check here because rbp has been
         * 32-bit zero extended
         */
@@ -244,7 +258,7 @@ sysexit_audit:
 #endif
 
 sysenter_fix_flags:
-       pushq   $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+       pushq   $X86_EFLAGS_FIXED
        popfq
        jmp     sysenter_flags_fixed
 
-- 
2.4.3

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

Reply via email to