From 101c268bd2f37e965a5468353e62d154db38838e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 22 Oct 2024 18:43:49 -0700 Subject: cxl/port: Fix use-after-free, permit out-of-order decoder shutdown In support of investigating an initialization failure report [1], cxl_test was updated to register mock memory-devices after the mock root-port/bus device had been registered. That led to cxl_test crashing with a use-after-free bug with the following signature: cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem0:decoder7.0 @ 0 next: cxl_switch_uport.0 nr_eps: 1 nr_targets: 1 cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem4:decoder14.0 @ 1 next: cxl_switch_uport.0 nr_eps: 2 nr_targets: 1 cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[0] = cxl_switch_dport.0 for mem0:decoder7.0 @ 0 1) cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[1] = cxl_switch_dport.4 for mem4:decoder14.0 @ 1 [..] cxld_unregister: cxl decoder14.0: cxl_region_decode_reset: cxl_region region3: mock_decoder_reset: cxl_port port3: decoder3.0 reset 2) mock_decoder_reset: cxl_port port3: decoder3.0: out of order reset, expected decoder3.1 cxl_endpoint_decoder_release: cxl decoder14.0: [..] cxld_unregister: cxl decoder7.0: 3) cxl_region_decode_reset: cxl_region region3: Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6bc3: 0000 [#1] PREEMPT SMP PTI [..] RIP: 0010:to_cxl_port+0x8/0x60 [cxl_core] [..] Call Trace: cxl_region_decode_reset+0x69/0x190 [cxl_core] cxl_region_detach+0xe8/0x210 [cxl_core] cxl_decoder_kill_region+0x27/0x40 [cxl_core] cxld_unregister+0x5d/0x60 [cxl_core] At 1) a region has been established with 2 endpoint decoders (7.0 and 14.0). Those endpoints share a common switch-decoder in the topology (3.0). At teardown, 2), decoder14.0 is the first to be removed and hits the "out of order reset case" in the switch decoder. The effect though is that region3 cleanup is aborted leaving it in-tact and referencing decoder14.0. At 3) the second attempt to teardown region3 trips over the stale decoder14.0 object which has long since been deleted. The fix here is to recognize that the CXL specification places no mandate on in-order shutdown of switch-decoders, the driver enforces in-order allocation, and hardware enforces in-order commit. So, rather than fail and leave objects dangling, always remove them. In support of making cxl_region_decode_reset() always succeed, cxl_region_invalidate_memregion() failures are turned into warnings. Crashing the kernel is ok there since system integrity is at risk if caches cannot be managed around physical address mutation events like CXL region destruction. A new device_for_each_child_reverse_from() is added to cleanup port->commit_end after all dependent decoders have been disabled. In other words if decoders are allocated 0->1->2 and disabled 1->2->0 then port->commit_end only decrements from 2 after 2 has been disabled, and it decrements all the way to zero since 1 was disabled previously. Link: http://lore.kernel.org/20241004212504.1246-1-gourry@gourry.net [1] Cc: stable@vger.kernel.org Fixes: 176baefb2eb5 ("cxl/hdm: Commit decoder state to hardware") Reviewed-by: Jonathan Cameron Cc: Greg Kroah-Hartman Cc: Davidlohr Bueso Cc: Dave Jiang Cc: Alison Schofield Cc: Ira Weiny Cc: Zijun Hu Signed-off-by: Dan Williams Reviewed-by: Ira Weiny Link: https://patch.msgid.link/172964782781.81806.17902885593105284330.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Ira Weiny --- drivers/base/core.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index a4c853411a6b..e42f1ad73078 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4037,6 +4037,41 @@ int device_for_each_child_reverse(struct device *parent, void *data, } EXPORT_SYMBOL_GPL(device_for_each_child_reverse); +/** + * device_for_each_child_reverse_from - device child iterator in reversed order. + * @parent: parent struct device. + * @from: optional starting point in child list + * @fn: function to be called for each device. + * @data: data for the callback. + * + * Iterate over @parent's child devices, starting at @from, and call @fn + * for each, passing it @data. This helper is identical to + * device_for_each_child_reverse() when @from is NULL. + * + * @fn is checked each iteration. If it returns anything other than 0, + * iteration stop and that value is returned to the caller of + * device_for_each_child_reverse_from(); + */ +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)) +{ + struct klist_iter i; + struct device *child; + int error = 0; + + if (!parent->p) + return 0; + + klist_iter_init_node(&parent->p->klist_children, &i, + (from ? &from->p->knode_parent : NULL)); + while ((child = prev_device(&i)) && !error) + error = fn(child, data); + klist_iter_exit(&i); + return error; +} +EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from); + /** * device_find_child - device iterator for locating a particular device. * @parent: parent struct device -- cgit v1.2.3 From 9a71892cbcdb9d1459c84f5a4c722b14354158a5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 29 Oct 2024 01:23:04 +0100 Subject: Revert "driver core: Fix uevent_show() vs driver detach race" This reverts commit 15fffc6a5624b13b428bb1c6e9088e32a55eb82c. This commit causes a regression, so revert it for now until it can come back in a way that works for everyone. Link: https://lore.kernel.org/all/172790598832.1168608.4519484276671503678.stgit@dwillia2-xfh.jf.intel.com/ Fixes: 15fffc6a5624 ("driver core: Fix uevent_show() vs driver detach race") Cc: stable Cc: Ashish Sangwan Cc: Namjae Jeon Cc: Dirk Behme Cc: Greg Kroah-Hartman Cc: Rafael J. Wysocki Cc: Dan Williams Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 13 +++++-------- drivers/base/module.c | 4 ---- 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index a4c853411a6b..adc0d74fa96c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -2634,7 +2633,6 @@ static const char *dev_uevent_name(const struct kobject *kobj) static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct device *dev = kobj_to_dev(kobj); - struct device_driver *driver; int retval = 0; /* add device node properties if present */ @@ -2663,12 +2661,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); - /* Synchronize with module_remove_driver() */ - rcu_read_lock(); - driver = READ_ONCE(dev->driver); - if (driver) - add_uevent_var(env, "DRIVER=%s", driver->name); - rcu_read_unlock(); + if (dev->driver) + add_uevent_var(env, "DRIVER=%s", dev->driver->name); /* Add common DT information about the device */ of_device_uevent(dev, env); @@ -2738,8 +2732,11 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; + /* Synchronize with really_probe() */ + device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); + device_unlock(dev); if (retval) goto out; diff --git a/drivers/base/module.c b/drivers/base/module.c index c4eaa1158d54..5bc71bea883a 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,7 +7,6 @@ #include #include #include -#include #include "base.h" static char *make_driver_name(const struct device_driver *drv) @@ -102,9 +101,6 @@ void module_remove_driver(const struct device_driver *drv) if (!drv) return; - /* Synchronize with dev_uevent() */ - synchronize_rcu(); - sysfs_remove_link(&drv->p->kobj, "module"); if (drv->owner) -- cgit v1.2.3