x86/intel_rdt: Fix possible circular lock dependency

Lockdep is reporting a possible circular locking dependency:

 ======================================================
 WARNING: possible circular locking dependency detected
 4.18.0-rc1-test-test+ #4 Not tainted
 ------------------------------------------------------
 user_example/766 is trying to acquire lock:
 0000000073479a0f (rdtgroup_mutex){+.+.}, at: pseudo_lock_dev_mmap

 but task is already holding lock:
 000000001ef7a35b (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0x9f/0x

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #2 (&mm->mmap_sem){++++}:
        _copy_to_user+0x1e/0x70
        filldir+0x91/0x100
        dcache_readdir+0x54/0x160
        iterate_dir+0x142/0x190
        __x64_sys_getdents+0xb9/0x170
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 -> #1 (&sb->s_type->i_mutex_key#3){++++}:
        start_creating+0x60/0x100
        debugfs_create_dir+0xc/0xc0
        rdtgroup_pseudo_lock_create+0x217/0x4d0
        rdtgroup_schemata_write+0x313/0x3d0
        kernfs_fop_write+0xf0/0x1a0
        __vfs_write+0x36/0x190
        vfs_write+0xb7/0x190
        ksys_write+0x52/0xc0
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 -> #0 (rdtgroup_mutex){+.+.}:
        __mutex_lock+0x80/0x9b0
        pseudo_lock_dev_mmap+0x2f/0x170
        mmap_region+0x3d6/0x610
        do_mmap+0x387/0x580
        vm_mmap_pgoff+0xcf/0x110
        ksys_mmap_pgoff+0x170/0x1f0
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 other info that might help us debug this:

 Chain exists of:
   rdtgroup_mutex --> &sb->s_type->i_mutex_key#3 --> &mm->mmap_sem

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&mm->mmap_sem);
                                lock(&sb->s_type->i_mutex_key#3);
                                lock(&mm->mmap_sem);
   lock(rdtgroup_mutex);

  *** DEADLOCK ***

 1 lock held by user_example/766:
  #0: 000000001ef7a35b (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0x9f/0x110

rdtgroup_mutex is already being released temporarily during pseudo-lock
region creation to prevent the potential deadlock between rdtgroup_mutex
and mm->mmap_sem that is obtained during device_create(). Move the
debugfs creation into this area to avoid the same circular dependency.

Signed-off-by: Reinette Chatre <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lkml.kernel.org/r/fffb57f9c6b8285904c9a60cc91ce21591af17fe.1531332480.git.reinette.chatre@intel.com

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 751c78f9992fa9cafb69452e2318f92a0580e6e9..f80c58f8adc31e985f0fff32824371cd9f8b3d8f 100644 (file)
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -1254,19 +1254,10 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
                goto out_cstates;
        }
 
-       if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-               plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-                                                     debugfs_resctrl);
-               if (!IS_ERR_OR_NULL(plr->debugfs_dir))
-                       debugfs_create_file("pseudo_lock_measure", 0200,
-                                           plr->debugfs_dir, rdtgrp,
-                                           &pseudo_measure_fops);
-       }
-
        ret = pseudo_lock_minor_get(&new_minor);
        if (ret < 0) {
                rdt_last_cmd_puts("unable to obtain a new minor number\n");
-               goto out_debugfs;
+               goto out_cstates;
        }
 
        /*
@@ -1275,11 +1266,20 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
         *
         * The mutex has to be released temporarily to avoid a potential
         * deadlock with the mm->mmap_sem semaphore which is obtained in
-        * the device_create() callpath below as well as before the mmap()
-        * callback is called.
+        * the device_create() and debugfs_create_dir() callpath below
+        * as well as before the mmap() callback is called.
         */
        mutex_unlock(&rdtgroup_mutex);
 
+       if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+               plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+                                                     debugfs_resctrl);
+               if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+                       debugfs_create_file("pseudo_lock_measure", 0200,
+                                           plr->debugfs_dir, rdtgrp,
+                                           &pseudo_measure_fops);
+       }
+
        dev = device_create(pseudo_lock_class, NULL,
                            MKDEV(pseudo_lock_major, new_minor),
                            rdtgrp, "%s", rdtgrp->kn->name);
@@ -1290,7 +1290,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
                ret = PTR_ERR(dev);
                rdt_last_cmd_printf("failed to create character device: %d\n",
                                    ret);
-               goto out_minor;
+               goto out_debugfs;
        }
 
        /* We released the mutex - check if group was removed while we did so */
@@ -1311,10 +1311,9 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 out_device:
        device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
-out_minor:
-       pseudo_lock_minor_release(new_minor);
 out_debugfs:
        debugfs_remove_recursive(plr->debugfs_dir);
+       pseudo_lock_minor_release(new_minor);
 out_cstates:
        pseudo_lock_cstates_relax(plr);
 out_region: