File 5f76ca65-evtchn-Flask-prealloc-for-send.patch of Package xen

# Commit 52e1fc47abc3a0123d2b5bb7e9172e84fd571851
# Date 2020-10-02 08:36:21 +0200
# Author Jan Beulich <jbeulich@suse.com>
# Committer Jan Beulich <jbeulich@suse.com>
evtchn/Flask: pre-allocate node on send path

xmalloc() & Co may not be called with IRQs off, or else check_lock()
will have its assertion trigger about locks getting acquired
inconsistently. Re-arranging the locking in evtchn_send() doesn't seem
very reasonable, especially since the per-channel lock was introduced to
avoid acquiring the per-domain event lock on the send paths. Issue a
second call to xsm_evtchn_send() instead, before acquiring the lock, to
give XSM / Flask a chance to pre-allocate whatever it may need.

As these nodes are used merely for caching earlier decisions' results,
allocate just one node in AVC code despite two potentially being needed.
Things will merely be not as performant if a second allocation was
wanted, just like when the pre-allocation fails.

Fixes: c0ddc8634845 ("evtchn: convert per-channel lock to be IRQ-safe")
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Jason Andryuk <jandryuk@gmail.com>
Acked-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Jason Andryuk <jandryuk@gmail.com>

--- a/xen/common/event_channel.c
+++ b/xen/common/event_channel.c
@@ -723,6 +723,12 @@ int evtchn_send(struct domain *ld, unsig
     if ( !port_is_valid(ld, lport) )
         return -EINVAL;
 
+    /*
+     * As the call further down needs to avoid allocations (due to running
+     * with IRQs off), give XSM a chance to pre-allocate if needed.
+     */
+    xsm_evtchn_send(XSM_HOOK, ld, NULL);
+
     lchn = evtchn_from_port(ld, lport);
 
     spin_lock_irqsave(&lchn->lock, flags);
--- a/xen/include/xsm/xsm.h
+++ b/xen/include/xsm/xsm.h
@@ -59,6 +59,7 @@ struct xsm_operations {
     int (*evtchn_interdomain) (struct domain *d1, struct evtchn *chn1,
                                         struct domain *d2, struct evtchn *chn2);
     void (*evtchn_close_post) (struct evtchn *chn);
+    /* Note: Next hook may be called with 'chn' set to NULL. See call site. */
     int (*evtchn_send) (struct domain *d, struct evtchn *chn);
     int (*evtchn_status) (struct domain *d, struct evtchn *chn);
     int (*evtchn_reset) (struct domain *d1, struct domain *d2);
--- a/xen/xsm/flask/avc.c
+++ b/xen/xsm/flask/avc.c
@@ -24,7 +24,9 @@
 #include <xen/prefetch.h>
 #include <xen/kernel.h>
 #include <xen/sched.h>
+#include <xen/cpu.h>
 #include <xen/init.h>
+#include <xen/percpu.h>
 #include <xen/rcupdate.h>
 #include <asm/atomic.h>
 #include <asm/current.h>
@@ -341,17 +343,79 @@ static inline int avc_reclaim_node(void)
     return ecx;
 }
 
+static struct avc_node *new_node(void)
+{
+    struct avc_node *node = xzalloc(struct avc_node);
+
+    if ( node )
+    {
+        INIT_RCU_HEAD(&node->rhead);
+        INIT_HLIST_NODE(&node->list);
+        avc_cache_stats_incr(allocations);
+    }
+
+    return node;
+}
+
+/*
+ * avc_has_perm_noaudit() may consume up to two nodes, which we may not be
+ * able to obtain from the allocator at that point. Since the is merely
+ * about caching earlier decisions, allow for (just) one pre-allocated node.
+ */
+static DEFINE_PER_CPU(struct avc_node *, prealloc_node);
+
+void avc_prealloc(void)
+{
+    struct avc_node **prealloc = &this_cpu(prealloc_node);
+
+    if ( !*prealloc )
+        *prealloc = new_node();
+}
+
+static int cpu_callback(struct notifier_block *nfb, unsigned long action,
+                        void *hcpu)
+{
+    unsigned int cpu = (unsigned long)hcpu;
+    struct avc_node **prealloc = &per_cpu(prealloc_node, cpu);
+
+    if ( action == CPU_DEAD && *prealloc )
+    {
+        xfree(*prealloc);
+        *prealloc = NULL;
+        avc_cache_stats_incr(frees);
+    }
+
+    return NOTIFY_DONE;
+}
+
+static struct notifier_block cpu_nfb = {
+    .notifier_call = cpu_callback,
+    .priority = 99
+};
+
+static int __init cpu_nfb_init(void)
+{
+    register_cpu_notifier(&cpu_nfb);
+    return 0;
+}
+__initcall(cpu_nfb_init);
+
 static struct avc_node *avc_alloc_node(void)
 {
-    struct avc_node *node;
+    struct avc_node *node, **prealloc = &this_cpu(prealloc_node);
 
-    node = xzalloc(struct avc_node);
-    if (!node)
-        goto out;
-
-    INIT_RCU_HEAD(&node->rhead);
-    INIT_HLIST_NODE(&node->list);
-    avc_cache_stats_incr(allocations);
+    node = *prealloc;
+    *prealloc = NULL;
+
+    if ( !node )
+    {
+        /* Must not call xmalloc() & Co with IRQs off. */
+        if ( !local_irq_is_enabled() )
+            goto out;
+        node = new_node();
+        if ( !node )
+            goto out;
+    }
 
     atomic_inc(&avc_cache.active_nodes);
     if ( atomic_read(&avc_cache.active_nodes) > avc_cache_threshold )
--- a/xen/xsm/flask/hooks.c
+++ b/xen/xsm/flask/hooks.c
@@ -281,6 +281,16 @@ static int flask_evtchn_send(struct doma
 {
     int rc;
 
+    /*
+     * When called with non-NULL chn, memory allocation may not be permitted.
+     * Allow AVC to preallocate nodes as necessary upon early notification.
+     */
+    if ( !chn )
+    {
+        avc_prealloc();
+        return 0;
+    }
+
     switch ( chn->state )
     {
     case ECS_INTERDOMAIN:
--- a/xen/xsm/flask/include/avc.h
+++ b/xen/xsm/flask/include/avc.h
@@ -91,6 +91,8 @@ int avc_has_perm_noaudit(u32 ssid, u32 t
 int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested,
                                              struct avc_audit_data *auditdata);
 
+void avc_prealloc(void);
+
 /* Exported to selinuxfs */
 struct xen_flask_hash_stats;
 int avc_get_hash_stats(struct xen_flask_hash_stats *arg);