From: Xiaochen Shen xiaochen.shen@intel.com
commit fd8d9db3559a29fd737bcdb7c4fcbe1940caae34 upstream.
Willem reported growing of kernfs_node_cache entries in slabtop when repeatedly creating and removing resctrl subdirectories as well as when repeatedly mounting and unmounting the resctrl filesystem.
On resource group (control as well as monitoring) creation via a mkdir an extra kernfs_node reference is obtained to ensure that the rdtgroup structure remains accessible for the rdtgroup_kn_unlock() calls where it is removed on deletion. The kernfs_node reference count is dropped by kernfs_put() in rdtgroup_kn_unlock().
With the above explaining the need for one kernfs_get()/kernfs_put() pair in resctrl there are more places where a kernfs_node reference is obtained without a corresponding release. The excessive amount of reference count on kernfs nodes will never be dropped to 0 and the kernfs nodes will never be freed in the call paths of rmdir and umount. It leads to reference count leak and kernfs_node_cache memory leak.
Remove the superfluous kernfs_get() calls and expand the existing comments surrounding the remaining kernfs_get()/kernfs_put() pair that remains in use.
Superfluous kernfs_get() calls are removed from two areas:
(1) In call paths of mount and mkdir, when kernfs nodes for "info", "mon_groups" and "mon_data" directories and sub-directories are created, the reference count of newly created kernfs node is set to 1. But after kernfs_create_dir() returns, superfluous kernfs_get() are called to take an additional reference.
(2) kernfs_get() calls in rmdir call paths.
Fixes: 17eafd076291 ("x86/intel_rdt: Split resource group removal in two") Fixes: 4af4a88e0c92 ("x86/intel_rdt/cqm: Add mount,umount support") Fixes: f3cbeacaa06e ("x86/intel_rdt/cqm: Add rmdir support") Fixes: d89b7379015f ("x86/intel_rdt/cqm: Add mon_data") Fixes: c7d9aac61311 ("x86/intel_rdt/cqm: Add mkdir support for RDT monitoring") Fixes: 5dc1d5c6bac2 ("x86/intel_rdt: Simplify info and base file lists") Fixes: 60cf5e101fd4 ("x86/intel_rdt: Add mkdir to resctrl file system") Fixes: 4e978d06dedb ("x86/intel_rdt: Add "info" files to resctrl file system") Reported-by: Willem de Bruijn willemb@google.com Signed-off-by: Xiaochen Shen xiaochen.shen@intel.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Reinette Chatre reinette.chatre@intel.com Tested-by: Willem de Bruijn willemb@google.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1604085053-31639-1-git-send-email-xiaochen.shen@in... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 35 +-------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-)
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1618,7 +1618,6 @@ static int rdtgroup_mkdir_info_resdir(st if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir);
- kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1641,7 +1640,6 @@ static int rdtgroup_create_info_dir(stru kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info);
ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1662,12 +1660,6 @@ static int rdtgroup_create_info_dir(stru goto out_destroy; }
- /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1696,12 +1688,6 @@ mongroup_create_dir(struct kernfs_node * if (dest_kn) *dest_kn = kn;
- /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -1988,13 +1974,11 @@ static int rdt_get_tree(struct fs_contex &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp);
ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; }
@@ -2365,11 +2349,6 @@ static int mkdir_mondata_subdir(struct k if (IS_ERR(kn)) return PTR_ERR(kn);
- /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2705,8 +2684,8 @@ static int mkdir_rdt_prepare(struct kern /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped inside rdtgroup_kn_unlock(). */ kernfs_get(kn);
@@ -2921,11 +2900,6 @@ static int rdtgroup_rmdir_mon(struct ker WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list);
- /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn);
return 0; @@ -2937,11 +2911,6 @@ static int rdtgroup_ctrl_remove(struct k rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list);
- /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; }