x86, cpumask: fix tlb flush race

Impact: fix bootup crash

The cpumask is now passed in as a reference to mm->cpu_vm_mask, not on
the stack - hence it is not constant anymore during the TLB flush.

That way it could race and some static sanity checks would trigger:

[  238.154287] ------------[ cut here ]------------
[  238.156039] kernel BUG at arch/x86/kernel/tlb_32.c:130!
[  238.156039] invalid opcode: 0000 [#1] SMP
[  238.156039] last sysfs file: /sys/class/net/eth2/address
[  238.156039] Modules linked in:
[  238.156039]
[  238.156039] Pid: 6493, comm: ifup-eth Not tainted (2.6.29-rc2-tip #1) P4DC6
[  238.156039] EIP: 0060:[<c0118f87>] EFLAGS: 00010202 CPU: 2
[  238.156039] EIP is at native_flush_tlb_others+0x35/0x158
[  238.156039] EAX: c0ef972c EBX: f6143301 ECX: 00000000 EDX: 00000000
[  238.156039] ESI: f61433a8 EDI: f6143200 EBP: f34f3e00 ESP: f34f3df0
[  238.156039]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[  238.156039] Process ifup-eth (pid: 6493, ti=f34f2000 task=f399ab00 task.ti=f34f2000)
[  238.156039] Stack:
[  238.156039]  ffffffff f61433a8 ffffffff f6143200 f34f3e18 c0118e9c 00000000 f6143200
[  238.156039]  f61433a8 f5bec738 f34f3e28 c0119435 c2b5b830 f6143200 f34f3e34 c01c2dc3
[  238.156039]  bffd9000 f34f3e60 c01c3051 00000000 ffffffff f34f3e4c 00000000 00000071
[  238.156039] Call Trace:
[  238.156039]  [<c0118e9c>] ? flush_tlb_others+0x52/0x5b
[  238.156039]  [<c0119435>] ? flush_tlb_mm+0x7f/0x8b
[  238.156039]  [<c01c2dc3>] ? tlb_finish_mmu+0x2d/0x55
[  238.156039]  [<c01c3051>] ? exit_mmap+0x124/0x170
[  238.156039]  [<c013e965>] ? mmput+0x40/0xf5
[  238.156039]  [<c01e4788>] ? flush_old_exec+0x640/0x94b
[  238.156039]  [<c01ddb4e>] ? fsnotify_access+0x37/0x39
[  238.156039]  [<c01e3435>] ? kernel_read+0x39/0x4b
[  238.156039]  [<c021bc8a>] ? load_elf_binary+0x4a1/0x11bb
[  238.156039]  [<c01c0af9>] ? might_fault+0x51/0x9c
[  238.156039]  [<c010a2cc>] ? paravirt_read_tsc+0x20/0x4f
[  238.156039]  [<c010a406>] ? native_sched_clock+0x5d/0x60
[  238.156039]  [<c01e2fda>] ? search_binary_handler+0xab/0x2c4
[  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
[  238.156039]  [<c04ae9a5>] ? _raw_read_unlock+0x21/0x46
[  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
[  238.156039]  [<c01e2fe1>] ? search_binary_handler+0xb2/0x2c4
[  238.156039]  [<c01e4076>] ? do_execve+0x21c/0x2ee
[  238.156039]  [<c01029b7>] ? sys_execve+0x51/0x8c
[  238.156039]  [<c0103eaf>] ? sysenter_do_call+0x12/0x43

Fix it by not assuming that the cpumask is constant.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index ec53818f4e380d7e935baa9e9c4269c9635b1db6..d37bbfcb813d35b11981761d3626abe5de6f9e8e 100644 (file)
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -125,9 +125,8 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
                             struct mm_struct *mm, unsigned long va)
 {
        /*
-        * - mask must exist :)
+        * mm must exist :)
         */
-       BUG_ON(cpumask_empty(cpumask));
        BUG_ON(!mm);
 
        /*
@@ -138,14 +137,18 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
        spin_lock(&tlbstate_lock);
 
        cpumask_andnot(flush_cpumask, cpumask, cpumask_of(smp_processor_id()));
-#ifdef CONFIG_HOTPLUG_CPU
-       /* If a CPU which we ran on has gone down, OK. */
        cpumask_and(flush_cpumask, flush_cpumask, cpu_online_mask);
+
+       /*
+        * If a task whose mm mask we are looking at has descheduled and
+        * has cleared its presence from the mask, or if a CPU which we ran
+        * on has gone down then there might be no flush work left:
+        */
        if (unlikely(cpumask_empty(flush_cpumask))) {
                spin_unlock(&tlbstate_lock);
                return;
        }
-#endif
+
        flush_mm = mm;
        flush_va = va;