[PATCH v2 1/6] workqueue: Inherit NOIO and NOFS alloc flags

[Håkon Bugge]

For drivers/modules running inside a
memalloc_{noio,nofs}_{save,restore} region, if a work-queue is
created, we make sure work executed on the work-queue inherits the
same flag(s).

This in order to conditionally enable drivers to work aligned with
block I/O devices. This commit makes sure that any work queued later
on work-queues created during module initialization, when current's
flags has PF_MEMALLOC_{NOIO,NOFS} set, will inherit the same flags.

We do this in order to enable drivers to be used as a network block
I/O device. This in order to support XFS or other file-systems on top
of a raw block device which uses said drivers as the network transport
layer.

Under intense memory pressure, we get memory reclaims. Assume the
file-system reclaims memory, goes to the raw block device, which calls
into said drivers. Now, if regular GFP_KERNEL allocations in the
drivers require reclaims to be fulfilled, we end up in a circular
dependency.

We break this circular dependency by:

1. Force all allocations in the drivers to use GFP_NOIO, by means of a
   parenthetic use of memalloc_noio_{save,restore} on all relevant
   entry points.

2. Make sure work-queues inherits current->flags
   wrt. PF_MEMALLOC_{NOIO,NOFS}, such that work executed on the
   work-queue inherits the same flag(s). That is what this commit
   contributes with.

Signed-off-by: Håkon Bugge <haakon.bugge@xxxxxxxxxx>

---

v1 -> v2:
   * Added missing hunk in alloc_workqueue()
---
 include/linux/workqueue.h |  2 ++
 kernel/workqueue.c        | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 158784dd189ab..09ecc692ffcae 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -398,6 +398,8 @@ enum wq_flags {
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
+	__WQ_NOIO               = 1 << 19, /* internal: execute work with NOIO */
+	__WQ_NOFS               = 1 << 20, /* internal: execute work with NOFS */
 
 	/* BH wq only allows the following flags */
 	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d2dbe099286b9..8eb7562372ce2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -51,6 +51,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/mm.h>
 #include <linux/nmi.h>
 #include <linux/kvm_para.h>
 #include <linux/delay.h>
@@ -3172,6 +3173,10 @@ __acquires(&pool->lock)
 	unsigned long work_data;
 	int lockdep_start_depth, rcu_start_depth;
 	bool bh_draining = pool->flags & POOL_BH_DRAINING;
+	bool use_noio_allocs = pwq->wq->flags & __WQ_NOIO;
+	bool use_nofs_allocs = pwq->wq->flags & __WQ_NOFS;
+	unsigned long noio_flags;
+	unsigned long nofs_flags;
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * It is permissible to free the struct work_struct from
@@ -3184,6 +3189,12 @@ __acquires(&pool->lock)
 
 	lockdep_copy_map(&lockdep_map, &work->lockdep_map);
 #endif
+	/* Set inherited alloc flags */
+	if (use_noio_allocs)
+		noio_flags = memalloc_noio_save();
+	if (use_nofs_allocs)
+		nofs_flags = memalloc_nofs_save();
+
 	/* ensure we're on the correct CPU */
 	WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
 		     raw_smp_processor_id() != pool->cpu);
@@ -3320,6 +3331,12 @@ __acquires(&pool->lock)
 
 	/* must be the last step, see the function comment */
 	pwq_dec_nr_in_flight(pwq, work_data);
+
+	/* Restore alloc flags */
+	if (use_nofs_allocs)
+		memalloc_nofs_restore(nofs_flags);
+	if (use_noio_allocs)
+		memalloc_noio_restore(noio_flags);
 }
 
 /**
@@ -5583,6 +5600,10 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 
 	/* init wq */
 	wq->flags = flags;
+	if (current->flags & PF_MEMALLOC_NOIO)
+		wq->flags |= __WQ_NOIO;
+	if (current->flags & PF_MEMALLOC_NOFS)
+		wq->flags |= __WQ_NOFS;
 	wq->max_active = max_active;
 	wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE);
 	wq->saved_max_active = wq->max_active;
-- 
2.45.0