summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/entry_64.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/entry_64.S')
-rw-r--r--arch/x86/kernel/entry_64.S47
1 files changed, 37 insertions, 10 deletions
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 10074ad..f0095a7 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -269,11 +269,14 @@ ENTRY(ret_from_fork)
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
jz 1f
- testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET
- jnz int_ret_from_sys_call
-
- RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
- jmp ret_from_sys_call # go to the SYSRET fastpath
+ /*
+ * By the time we get here, we have no idea whether our pt_regs,
+ * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+ * the slow path, or one of the ia32entry paths.
+ * Use int_ret_from_sys_call to return, since it can safely handle
+ * all of the above.
+ */
+ jmp int_ret_from_sys_call
1:
subq $REST_SKIP, %rsp # leave space for volatiles
@@ -361,12 +364,21 @@ system_call_fastpath:
* Has incomplete stack frame and undefined top of stack.
*/
ret_from_sys_call:
- testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- jnz int_ret_from_sys_call_fixup /* Go the the slow path */
-
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
+
+ /*
+ * We must check ti flags with interrupts (or at least preemption)
+ * off because we must *never* return to userspace without
+ * processing exit work that is enqueued if we're preempted here.
+ * In particular, returning to userspace with any of the one-shot
+ * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+ * very bad.
+ */
+ testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ jnz int_ret_from_sys_call_fixup /* Go the the slow path */
+
CFI_REMEMBER_STATE
/*
* sysretq will re-enable interrupts:
@@ -383,7 +395,7 @@ ret_from_sys_call:
int_ret_from_sys_call_fixup:
FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
- jmp int_ret_from_sys_call
+ jmp int_ret_from_sys_call_irqs_off
/* Do syscall tracing */
tracesys:
@@ -429,6 +441,7 @@ tracesys_phase2:
GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
movl $_TIF_ALLWORK_MASK,%edi
/* edi: mask to check */
GLOBAL(int_with_check)
@@ -786,7 +799,21 @@ retint_swapgs: /* return to user-space */
cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp) /* R11 == RFLAGS */
jne opportunistic_sysret_failed
- testq $X86_EFLAGS_RF,%r11 /* sysret can't restore RF */
+ /*
+ * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
+ * restoring TF results in a trap from userspace immediately after
+ * SYSRET. This would cause an infinite loop whenever #DB happens
+ * with register state that satisfies the opportunistic SYSRET
+ * conditions. For example, single-stepping this user code:
+ *
+ * movq $stuck_here,%rcx
+ * pushfq
+ * popq %r11
+ * stuck_here:
+ *
+ * would never get past 'stuck_here'.
+ */
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
jnz opportunistic_sysret_failed
/* nothing to check for RSP */