From 6b2e428e673b3f55965674a426c40922e91388aa Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 27 Oct 2023 20:13:23 -0700 Subject: [PATCH] cxl/port: Fix delete_endpoint() vs parent unregistration race commit 8d2ad999ca3c64cb08cf6a58d227b9d9e746d708 upstream. The CXL subsystem, at cxl_mem ->probe() time, establishes a lineage of ports (struct cxl_port objects) between an endpoint and the root of a CXL topology. Each port including the endpoint port is attached to the cxl_port driver. Given that setup, it follows that when either any port in that lineage goes through a cxl_port ->remove() event, or the memdev goes through a cxl_mem ->remove() event. The hierarchy below the removed port, or the entire hierarchy if the memdev is removed needs to come down. The delete_endpoint() callback is careful to check whether it is being called to tear down the hierarchy, or if it is only being called to teardown the memdev because an ancestor port is going through ->remove(). That care needs to take the device_lock() of the endpoint's parent. Which requires 2 bugs to be fixed: 1/ A reference on the parent is needed to prevent use-after-free scenarios like this signature: BUG: spinlock bad magic on CPU#0, kworker/u56:0/11 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc38 05/24/2023 Workqueue: cxl_port detach_memdev [cxl_core] RIP: 0010:spin_bug+0x65/0xa0 Call Trace: do_raw_spin_lock+0x69/0xa0 __mutex_lock+0x695/0xb80 delete_endpoint+0xad/0x150 [cxl_core] devres_release_all+0xb8/0x110 device_unbind_cleanup+0xe/0x70 device_release_driver_internal+0x1d2/0x210 detach_memdev+0x15/0x20 [cxl_core] process_one_work+0x1e3/0x4c0 worker_thread+0x1dd/0x3d0 2/ In the case of RCH topologies, the parent device that needs to be locked is not always @port->dev as returned by cxl_mem_find_port(), use endpoint->dev.parent instead. Fixes: 8dd2bc0f8e02 ("cxl/mem: Add the cxl_mem driver") Cc: Reported-by: Robert Richter Closes: http://lore.kernel.org/r/20231018171713.1883517-2-rrichter@amd.com Signed-off-by: Dan Williams Signed-off-by: Greg Kroah-Hartman --- drivers/cxl/core/port.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 2c60015..6a75a3c 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1242,35 +1242,39 @@ static struct device *grandparent(struct device *dev) return NULL; } +static struct device *endpoint_host(struct cxl_port *endpoint) +{ + struct cxl_port *port = to_cxl_port(endpoint->dev.parent); + + if (is_cxl_root(port)) + return port->uport_dev; + return &port->dev; +} + static void delete_endpoint(void *data) { struct cxl_memdev *cxlmd = data; struct cxl_port *endpoint = cxlmd->endpoint; - struct cxl_port *parent_port; - struct device *parent; - - parent_port = cxl_mem_find_port(cxlmd, NULL); - if (!parent_port) - goto out; - parent = &parent_port->dev; + struct device *host = endpoint_host(endpoint); - device_lock(parent); - if (parent->driver && !endpoint->dead) { - devm_release_action(parent, cxl_unlink_parent_dport, endpoint); - devm_release_action(parent, cxl_unlink_uport, endpoint); - devm_release_action(parent, unregister_port, endpoint); + device_lock(host); + if (host->driver && !endpoint->dead) { + devm_release_action(host, cxl_unlink_parent_dport, endpoint); + devm_release_action(host, cxl_unlink_uport, endpoint); + devm_release_action(host, unregister_port, endpoint); } cxlmd->endpoint = NULL; - device_unlock(parent); - put_device(parent); -out: + device_unlock(host); put_device(&endpoint->dev); + put_device(host); } int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) { + struct device *host = endpoint_host(endpoint); struct device *dev = &cxlmd->dev; + get_device(host); get_device(&endpoint->dev); cxlmd->endpoint = endpoint; cxlmd->depth = endpoint->depth; -- 2.7.4