sieni
/
linux
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cxl/memdev: Fix endpoint port removal 

Testing of ram region support [1], stimulates a long standing bug in
cxl_detach_ep() where some cxl_ep_remove() cleanup is skipped due to
inability to walk ports after dports have been unregistered. That
results in a failure to re-register a memdev after the port is
re-enabled leading to a crash like the following:

    cxl_port_setup_targets: cxl region4: cxl_host_bridge.0:port4 iw: 1 ig: 256
    general protection fault, ...
    [..]
    RIP: 0010:cxl_region_setup_targets+0x897/0x9e0 [cxl_core]
    dev_name at include/linux/device.h:700
    (inlined by) cxl_port_setup_targets at drivers/cxl/core/region.c:1155
    (inlined by) cxl_region_setup_targets at drivers/cxl/core/region.c:1249
    [..]
    Call Trace:
     <TASK>
     attach_target+0x39a/0x760 [cxl_core]
     ? __mutex_unlock_slowpath+0x3a/0x290
     cxl_add_to_region+0xb8/0x340 [cxl_core]
     ? lockdep_hardirqs_on+0x7d/0x100
     discover_region+0x4b/0x80 [cxl_port]
     ? __pfx_discover_region+0x10/0x10 [cxl_port]
     device_for_each_child+0x58/0x90
     cxl_port_probe+0x10e/0x130 [cxl_port]
     cxl_bus_probe+0x17/0x50 [cxl_core]

Change the port ancestry walk to be by depth rather than by dport. This
ensures that even if a port has unregistered its dports a deferred
memdev cleanup will still be able to cleanup the memdev's interest in
that port.

The parent_port->dev.driver check is only needed for determining if the
bottom up removal beat the top-down removal, but cxl_ep_remove() can
always proceed given the port is pinned. That is, the two sources of
cxl_ep_remove() are in cxl_detach_ep() and cxl_port_release(), and
cxl_port_release() can not run if cxl_detach_ep() holds a reference.

Fixes: 2703c16c75 ("cxl/core/port: Add switch port enumeration")
Link: http://lore.kernel.org/r/167564534874.847146.5222419648551436750.stgit@dwillia2-xfh.jf.intel.com [1]
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/167601992789.1924368.8083994227892600608.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Dan Williams 2023-02-10 17:29:09 -08:00
parent 172738bbcc
commit 2345df5424
3 changed files with 35 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/cxl/core/memdev.c
View File

@ -246,6 +246,7 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_dev_state *cxlds,
if (rc < 0)
goto err;
cxlmd->id = rc;
cxlmd->depth = -1;
dev = &cxlmd->dev;
device_initialize(dev);

58
drivers/cxl/core/port.c
View File

@ -1207,6 +1207,7 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
get_device(&endpoint->dev);
dev_set_drvdata(dev, endpoint);
cxlmd->depth = endpoint->depth;
return devm_add_action_or_reset(dev, delete_endpoint, cxlmd);
}
EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL);
@ -1241,50 +1242,55 @@ static void reap_dports(struct cxl_port *port)
}
}
struct detach_ctx {
struct cxl_memdev *cxlmd;
int depth;
};
static int port_has_memdev(struct device *dev, const void *data)
{
const struct detach_ctx *ctx = data;
struct cxl_port *port;
if (!is_cxl_port(dev))
return 0;
port = to_cxl_port(dev);
if (port->depth != ctx->depth)
return 0;
return !!cxl_ep_load(port, ctx->cxlmd);
}
static void cxl_detach_ep(void *data)
{
struct cxl_memdev *cxlmd = data;
struct device *iter;
for (iter = &cxlmd->dev; iter; iter = grandparent(iter)) {
struct device *dport_dev = grandparent(iter);
for (int i = cxlmd->depth - 1; i >= 1; i--) {
struct cxl_port *port, *parent_port;
struct detach_ctx ctx = {
.cxlmd = cxlmd,
.depth = i,
};
struct device *dev;
struct cxl_ep *ep;
bool died = false;
if (!dport_dev)
break;
port = find_cxl_port(dport_dev, NULL);
if (!port)
dev = bus_find_device(&cxl_bus_type, NULL, &ctx,
port_has_memdev);
if (!dev)
continue;
if (is_cxl_root(port)) {
put_device(&port->dev);
continue;
}
port = to_cxl_port(dev);
parent_port = to_cxl_port(port->dev.parent);
device_lock(&parent_port->dev);
if (!parent_port->dev.driver) {
/*
* The bottom-up race to delete the port lost to a
* top-down port disable, give up here, because the
* parent_port ->remove() will have cleaned up all
* descendants.
*/
device_unlock(&parent_port->dev);
put_device(&port->dev);
continue;
}
device_lock(&port->dev);
ep = cxl_ep_load(port, cxlmd);
dev_dbg(&cxlmd->dev, "disconnect %s from %s\n",
ep ? dev_name(ep->ep) : "", dev_name(&port->dev));
cxl_ep_remove(port, ep);
if (ep && !port->dead && xa_empty(&port->endpoints) &&
!is_cxl_root(parent_port)) {
!is_cxl_root(parent_port) && parent_port->dev.driver) {
/*
* This was the last ep attached to a dynamically
* enumerated port. Block new cxl_add_ep() and garbage

2
drivers/cxl/cxlmem.h
View File

@ -38,6 +38,7 @@
* @cxl_nvb: coordinate removal of @cxl_nvd if present
* @cxl_nvd: optional bridge to an nvdimm if the device supports pmem
* @id: id number of this memdev instance.
* @depth: endpoint port depth
*/
struct cxl_memdev {
struct device dev;
@ -47,6 +48,7 @@ struct cxl_memdev {
struct cxl_nvdimm_bridge *cxl_nvb;
struct cxl_nvdimm *cxl_nvd;
int id;
int depth;
};
static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)