summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid Gibson <david@gibson.dropbear.id.au>2017-04-19 16:38:26 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2017-04-25 00:24:59 +1000
commit9765ad134a00a01cbcc69c78ff6defbfad209bc5 (patch)
tree70a45c0a8cb45ae570653c50879f2d62d0dd6e34
parente76ca27790a514590af782f83f6eae49e0ccf8c9 (diff)
powerpc/mm: Ensure IRQs are off in switch_mm()
powerpc expects IRQs to already be (soft) disabled when switch_mm() is called, as made clear in the commit message of 9c1e105238c4 ("powerpc: Allow perf_counters to access user memory at interrupt time"). Aside from any race conditions that might exist between switch_mm() and an IRQ, there is also an unconditional hard_irq_disable() in switch_slb(). If that isn't followed at some point by an IRQ enable then interrupts will remain disabled until we return to userspace. It is true that when switch_mm() is called from the scheduler IRQs are off, but not when it's called by use_mm(). Looking closer we see that last year in commit f98db6013c55 ("sched/core: Add switch_mm_irqs_off() and use it in the scheduler") this was made more explicit by the addition of switch_mm_irqs_off() which is now called by the scheduler, vs switch_mm() which is used by use_mm(). Arguably it is a bug in use_mm() to call switch_mm() in a different context than it expects, but fixing that will take time. This was discovered recently when vhost started throwing warnings such as: BUG: sleeping function called from invalid context at kernel/mutex.c:578 in_atomic(): 0, irqs_disabled(): 1, pid: 10768, name: vhost-10760 no locks held by vhost-10760/10768. irq event stamp: 10 hardirqs last enabled at (9): _raw_spin_unlock_irq+0x40/0x80 hardirqs last disabled at (10): switch_slb+0x2e4/0x490 softirqs last enabled at (0): copy_process+0x5e8/0x1260 softirqs last disabled at (0): (null) Call Trace: show_stack+0x88/0x390 (unreliable) dump_stack+0x30/0x44 __might_sleep+0x1c4/0x2d0 mutex_lock_nested+0x74/0x5c0 cgroup_attach_task_all+0x5c/0x180 vhost_attach_cgroups_work+0x58/0x80 [vhost] vhost_worker+0x24c/0x3d0 [vhost] kthread+0xec/0x100 ret_from_kernel_thread+0x5c/0xd4 Prior to commit 04b96e5528ca ("vhost: lockless enqueuing") (Aug 2016) the vhost_worker() would do a spin_unlock_irq() not long after calling use_mm(), which had the effect of reenabling IRQs. Since that commit removed the locking in vhost_worker() the body of the vhost_worker() loop now runs with interrupts off causing the warnings. This patch addresses the problem by making the powerpc code mirror the x86 code, ie. we disable interrupts in switch_mm(), and optimise the scheduler case by defining switch_mm_irqs_off(). Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: David Gibson <david@gibson.dropbear.id.au> [mpe: Flesh out/rewrite change log, add stable] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
-rw-r--r--arch/powerpc/include/asm/mmu_context.h17
1 files changed, 15 insertions, 2 deletions
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 78803a7ebdd9..a114248de2ee 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -71,8 +71,9 @@ extern void drop_cop(unsigned long acop, struct mm_struct *mm);
* switch_mm is the entry point called from the architecture independent
* code in kernel/sched/core.c
*/
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
- struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+ struct mm_struct *next,
+ struct task_struct *tsk)
{
/* Mark this context has been used on the new CPU */
if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
@@ -111,6 +112,18 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
switch_mmu_context(prev, next, tsk);
}
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ switch_mm_irqs_off(prev, next, tsk);
+ local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
+
#define deactivate_mm(tsk,mm) do { } while (0)
/*