summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAndy Lutomirski <luto@kernel.org>2020-12-03 21:07:05 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2020-12-21 13:27:07 +0100
commitc4f90940701589acb67498fbf1626218dd6220b5 (patch)
tree027670f3ea76738fa02e57cc5ea136d652a58d17
parenta840e37ef8003d70c3aa5ce2ee1a3e5ce4647431 (diff)
downloadlinux-stable-c4f90940701589acb67498fbf1626218dd6220b5.tar.gz
linux-stable-c4f90940701589acb67498fbf1626218dd6220b5.tar.bz2
linux-stable-c4f90940701589acb67498fbf1626218dd6220b5.zip
membarrier: Explicitly sync remote cores when SYNC_CORE is requested
commit 758c9373d84168dc7d039cf85a0e920046b17b41 upstream. membarrier() does not explicitly sync_core() remote CPUs; instead, it relies on the assumption that an IPI will result in a core sync. On x86, this may be true in practice, but it's not architecturally reliable. In particular, the SDM and APM do not appear to guarantee that interrupt delivery is serializing. While IRET does serialize, IPI return can schedule, thereby switching to another task in the same mm that was sleeping in a syscall. The new task could then SYSRET back to usermode without ever executing IRET. Make this more robust by explicitly calling sync_core_before_usermode() on remote cores. (This also helps people who search the kernel tree for instances of sync_core() and sync_core_before_usermode() -- one might be surprised that the core membarrier code doesn't currently show up in a such a search.) Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/776b448d5f7bd6b12690707f5ed67bcda7f1d427.1607058304.git.luto@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--kernel/sched/membarrier.c21
1 files changed, 20 insertions, 1 deletions
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 168479a7d61b..be0ca3306be8 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -30,6 +30,23 @@ static void ipi_mb(void *info)
smp_mb(); /* IPIs should be serializing but paranoid. */
}
+static void ipi_sync_core(void *info)
+{
+ /*
+ * The smp_mb() in membarrier after all the IPIs is supposed to
+ * ensure that memory on remote CPUs that occur before the IPI
+ * become visible to membarrier()'s caller -- see scenario B in
+ * the big comment at the top of this file.
+ *
+ * A sync_core() would provide this guarantee, but
+ * sync_core_before_usermode() might end up being deferred until
+ * after membarrier()'s smp_mb().
+ */
+ smp_mb(); /* IPIs should be serializing but paranoid. */
+
+ sync_core_before_usermode();
+}
+
static void ipi_sync_rq_state(void *info)
{
struct mm_struct *mm = (struct mm_struct *) info;
@@ -134,6 +151,7 @@ static int membarrier_private_expedited(int flags)
int cpu;
cpumask_var_t tmpmask;
struct mm_struct *mm = current->mm;
+ smp_call_func_t ipi_func = ipi_mb;
if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
@@ -141,6 +159,7 @@ static int membarrier_private_expedited(int flags)
if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
return -EPERM;
+ ipi_func = ipi_sync_core;
} else {
if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
@@ -181,7 +200,7 @@ static int membarrier_private_expedited(int flags)
rcu_read_unlock();
preempt_disable();
- smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+ smp_call_function_many(tmpmask, ipi_func, NULL, 1);
preempt_enable();
free_cpumask_var(tmpmask);