From 2ecedd7569080fd05c1a457e8af2165afecfa29f Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:04 -0800 Subject: membarrier: Add an actual barrier before rseq_preempt() It seems that most RSEQ membarrier users will expect any stores done before the membarrier() syscall to be visible to the target task(s). While this is extremely likely to be true in practice, nothing actually guarantees it by a strict reading of the x86 manuals. Rather than providing this guarantee by accident and potentially causing a problem down the road, just add an explicit barrier. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/d3e7197e034fa4852afcf370ca49c30496e58e40.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index e23e74d52db5..7d98ef5d3bcd 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -40,6 +40,14 @@ static void ipi_mb(void *info) static void ipi_rseq(void *info) { + /* + * Ensure that all stores done by the calling thread are visible + * to the current task before the current task resumes. We could + * probably optimize this away on most architectures, but by the + * time we've already sent an IPI, the cost of the extra smp_mb() + * is negligible. + */ + smp_mb(); rseq_preempt(current); } -- cgit v1.2.3 From 758c9373d84168dc7d039cf85a0e920046b17b41 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:05 -0800 Subject: membarrier: Explicitly sync remote cores when SYNC_CORE is requested 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 Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/776b448d5f7bd6b12690707f5ed67bcda7f1d427.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 7d98ef5d3bcd..1c278dff4f2d 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -38,6 +38,23 @@ 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_rseq(void *info) { /* @@ -162,6 +179,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) return -EPERM; + ipi_func = ipi_sync_core; } else if (flags == MEMBARRIER_FLAG_RSEQ) { if (!IS_ENABLED(CONFIG_RSEQ)) return -EINVAL; -- cgit v1.2.3 From e45cdc71d1fa5ac3a57b23acc31eb959e4f60135 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:06 -0800 Subject: membarrier: Execute SYNC_CORE on the calling thread membarrier()'s MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE is documented as syncing the core on all sibling threads but not necessarily the calling thread. This behavior is fundamentally buggy and cannot be used safely. Suppose a user program has two threads. Thread A is on CPU 0 and thread B is on CPU 1. Thread A modifies some text and calls membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE). Then thread B executes the modified code. If, at any point after membarrier() decides which CPUs to target, thread A could be preempted and replaced by thread B on CPU 0. This could even happen on exit from the membarrier() syscall. If this happens, thread B will end up running on CPU 0 without having synced. In principle, this could be fixed by arranging for the scheduler to issue sync_core_before_usermode() whenever switching between two threads in the same mm if there is any possibility of a concurrent membarrier() call, but this would have considerable overhead. Instead, make membarrier() sync the calling CPU as well. As an optimization, this avoids an extra smp_mb() in the default barrier-only mode and an extra rseq preempt on the caller. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/250ded637696d490c69bef1877148db86066881c.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 51 ++++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 1c278dff4f2d..9d8df34bea75 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -194,7 +194,8 @@ static int membarrier_private_expedited(int flags, int cpu_id) return -EPERM; } - if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1) + if (flags != MEMBARRIER_FLAG_SYNC_CORE && + (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)) return 0; /* @@ -213,8 +214,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id)) goto out; - if (cpu_id == raw_smp_processor_id()) - goto out; rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu_id)->curr); if (!p || p->mm != mm) { @@ -229,16 +228,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) for_each_online_cpu(cpu) { struct task_struct *p; - /* - * Skipping the current CPU is OK even through we can be - * migrated at any point. The current CPU, at the point - * where we read raw_smp_processor_id(), is ensured to - * be in program order with respect to the caller - * thread. Therefore, we can skip this CPU from the - * iteration. - */ - if (cpu == raw_smp_processor_id()) - continue; p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); @@ -246,12 +235,38 @@ static int membarrier_private_expedited(int flags, int cpu_id) rcu_read_unlock(); } - preempt_disable(); - if (cpu_id >= 0) + if (cpu_id >= 0) { + /* + * smp_call_function_single() will call ipi_func() if cpu_id + * is the calling CPU. + */ smp_call_function_single(cpu_id, ipi_func, NULL, 1); - else - smp_call_function_many(tmpmask, ipi_func, NULL, 1); - preempt_enable(); + } else { + /* + * For regular membarrier, we can save a few cycles by + * skipping the current cpu -- we're about to do smp_mb() + * below, and if we migrate to a different cpu, this cpu + * and the new cpu will execute a full barrier in the + * scheduler. + * + * For SYNC_CORE, we do need a barrier on the current cpu -- + * otherwise, if we are migrated and replaced by a different + * task in the same mm just before, during, or after + * membarrier, we will end up with some thread in the mm + * running without a core sync. + * + * For RSEQ, don't rseq_preempt() the caller. User code + * is not supposed to issue syscalls at all from inside an + * rseq critical section. + */ + if (flags != MEMBARRIER_FLAG_SYNC_CORE) { + preempt_disable(); + smp_call_function_many(tmpmask, ipi_func, NULL, true); + preempt_enable(); + } else { + on_each_cpu_mask(tmpmask, ipi_func, NULL, true); + } + } out: if (cpu_id < 0) -- cgit v1.2.3