[PATCH] xen/events: avoid removing an event channel while handling it

From: Juergen Gross jgross@suse.com

mainline inclusion from mainline-v5.10 commit 073d0552ead5bfc7a3a9c01de590e924f11b5dd2 category: bugfix bugzilla: NA CVE: CVE-2020-27675

--------------------------------

Today it can happen that an event channel is being removed from the system while the event handling loop is active. This can lead to a race resulting in crashes or WARN() splats when trying to access the irq_info structure related to the event channel.

Fix this problem by using a rwlock taken as reader in the event handling loop and as writer when deallocating the irq_info structure.

As the observed problem was a NULL dereference in evtchn_from_irq() make this function more robust against races by testing the irq_info pointer to be not NULL before dereferencing it.

And finally make all accesses to evtchn_to_irq[row][col] atomic ones in order to avoid seeing partial updates of an array element in irq handling. Note that irq handling can be entered only for event channels which have been valid before, so any not populated row isn't a problem in this regard, as rows are only ever added and never removed.

This is XSA-331.

Cc: stable@vger.kernel.org Reported-by: Marek Marczykowski-Górecki marmarek@invisiblethingslab.com Reported-by: Jinoh Kang luke1337@theori.io Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Stefano Stabellini sstabellini@kernel.org Reviewed-by: Wei Liu wl@xen.org Conflicts: drivers/xen/events/events_base.c [yyl: adjust context] Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/xen/events/events_base.c | 40 ++++++++++++++++++++++++++++---- 1 file changed, 35 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 95e5a9300ff0..75eade7d2017 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -32,6 +32,7 @@ #include <linux/slab.h> #include <linux/irqnr.h> #include <linux/pci.h> +#include <linux/spinlock.h>

#ifdef CONFIG_X86 #include <asm/desc.h> @@ -69,6 +70,23 @@ const struct evtchn_ops *evtchn_ops; */ static DEFINE_MUTEX(irq_mapping_update_lock);

+/* + * Lock protecting event handling loop against removing event channels. + * Adding of event channels is no issue as the associated IRQ becomes active + * only after everything is setup (before request_[threaded_]irq() the handler + * can't be entered for an event, as the event channel will be unmasked only + * then). + */ +static DEFINE_RWLOCK(evtchn_rwlock); + +/* + * Lock hierarchy: + * + * irq_mapping_update_lock + * evtchn_rwlock + * IRQ-desc lock + */ + static LIST_HEAD(xen_irq_list_head);

/* IRQ <-> VIRQ mapping. */ @@ -101,7 +119,7 @@ static void clear_evtchn_to_irq_row(unsigned row) unsigned col;

for (col = 0; col < EVTCHN_PER_ROW; col++) - evtchn_to_irq[row][col] = -1; + WRITE_ONCE(evtchn_to_irq[row][col], -1); }

static void clear_evtchn_to_irq_all(void) @@ -138,7 +156,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) clear_evtchn_to_irq_row(row); }

- evtchn_to_irq[row][col] = irq; + WRITE_ONCE(evtchn_to_irq[row][col], irq); return 0; }

@@ -148,7 +166,7 @@ int get_evtchn_to_irq(unsigned evtchn) return -1; if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL) return -1; - return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]; + return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]); }

/* Get info for IRQ */ @@ -246,10 +264,14 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ unsigned int evtchn_from_irq(unsigned irq) { - if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq))) + const struct irq_info *info = NULL; + + if (likely(irq < nr_irqs)) + info = info_for_irq(irq); + if (!info) return 0;

- return info_for_irq(irq)->evtchn; + return info->evtchn; }

unsigned irq_from_evtchn(unsigned int evtchn) @@ -425,16 +447,21 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { struct irq_info *info = irq_get_chip_data(irq); + unsigned long flags;

if (WARN_ON(!info)) return;

+ write_lock_irqsave(&evtchn_rwlock, flags); + list_del(&info->list);

irq_set_chip_data(irq, NULL);

WARN_ON(info->refcnt > 0);

+ write_unlock_irqrestore(&evtchn_rwlock, flags); + kfree(info);

/* Legacy IRQ descriptors are managed by the arch. */ @@ -1220,6 +1247,8 @@ static void __xen_evtchn_do_upcall(void) int cpu = get_cpu(); unsigned count;

+ read_lock(&evtchn_rwlock); + do { vcpu_info->evtchn_upcall_pending = 0;

@@ -1236,6 +1265,7 @@ static void __xen_evtchn_do_upcall(void)

out:

+ read_unlock(&evtchn_rwlock); put_cpu(); }