From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795376161; b=I/m/WknjkepquTHZzeigYfg3TxX3yHJGFeZfWf1fPwQLWNhCKsKr+E32Oo7UGqq4QW/T a1F8fBZzwQnt/2Dfk+1mqjZXN8xadmAlIkhqLicWOm4/pNTAnXDwNoOFuHewaGTVYgWjR tEMhkALAOzYh+RqGu9qR1msJyyoubRXP8sVr7CuKPPuNslN08qayV1z5BTRlUn/OOuMVh Ipbx9lxEDBPF+0NOzjRv+dalwwHXdka3MBi2r+tC9cm35y3J/R0rajarHqWtGhpHscULz x3yPOzXECz779wsn+Shs5CWicnWaDfcWHKGEjBU46yN/UwpiVrCgN5kKs4qfprSoAng== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795376161; h=Received:DKIM-Signature:From:To:Cc:Subject:Date:Message-ID:X-Mailer: In-Reply-To:References:MIME-Version:Content-Transfer-Encoding; bh=PxWsspzEioIIwUqnuiIeYKp1fTe5D8PzGx83Wd5XdHY=; b=uN4bDiJt4K/gBOp0Yn3/NndacLmnAE+IyoCelvck80qqMIZGAvvmyjvI8X88GN6rcruG GRu2l5J0+29shwyprW+y2jRfMq83R80fA1GAQABpqRyC5EYBSCKenzGNOM8E+1MjsgALo mdgmnk49UzvCAGa3JtAzCqzPkxOkuhReDQEpjgjiqfVddGOtZ82osQX3kVEVk1ylsz19M MSkv/FXYiN30KJsLXbOfQaAqTu2EtgFnCPDWgUBHAe5Gnd2q8ImBS3zCjHQF3Hjto00dm buovwfa83f7qkSZAhsBlb1ouPDfeGEAj/kkPU7Ia8zgByPmobEcXMcYcclxgmj3CcMA== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=DFiqTxJB; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with UTF8SMTPS id 46200606A32C; Sun, 22 Nov 2026 19:36:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=DFiqTxJB Received: by smtp.kernel.org (Postfix) with UTF8SMTPSA id C697E1F000C0; Sun, 22 Nov 2026 19:35:59 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1795376160; bh=PxWsspzEioIIwUqnuiIeYKp1fTe5D8PzGx83Wd5XdHY=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=DFiqTxJBeq3OOH2VDJJY2sRb16klNa8m8RHt5Abh/YsPImOZ5nu0uM/UuMH+1ycLe S+SXiQ9ZdkEJGKkPN8frshQVWuicTWsoG5qYiFtE16U0SbJ6N0d/pprgRSmcbMWB0L 0fc+vdB1MX5xOtwmvvCKQVbCxtNDWEr972W+bhnrLZB08bFuYj96P+xs8sX24UVzV5 vR6e0SgrDbPp5c3KER4nWHsM3H80dhGu3haKOn8CZtqET9eS+adDfRk0TJeYI2DcSh DNDD/KxSNtFTnTtbxIpVpUpwPU2Jqbe3L0B6Jmlu7Ie34V9iCvX0vbkLcG4h/jk/TN FUckdOsdfl/JQ== From: Jarkko Sakkinen To: linux-fsdevel@vger.kernel.org Cc: Jarkko Sakkinen , bpf@vger.kernel.org, containers@lists.linux.dev, linux-api@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, linux-mm@kvack.org, linux-security-module@vger.kernel.org, Aleksa Sarai , Alexander Mikhalitsyn , Alexander Viro , Andy Lutomirski , Arnd Bergmann , Christian Brauner , David Howells , Eric Biggers , Giuseppe Scrivano , Hugh Dickins , Jan Kara , Jeff Layton , Jonathan Corbet , Josef Bacik , Kees Cook , KP Singh , Lennart Poettering , Neal Gompa , Oleg Nesterov , Paul Moore , Pavel Tikhomirov , Serge Hallyn , Shuah Khan , Zygmunt Krynicki Subject: [RFC PATCH v7 01/26] userns: Factor out idmap validation and commit helpers Date: Sun, 22 Nov 2026 21:35:14 +0200 Message-ID: <20261122193539.3334213-2-jarkko@kernel.org> X-Mailer: git-send-email 2.47.3 In-Reply-To: <20261122193539.3334213-1-jarkko@kernel.org> References: <20261122193539.3334213-1-jarkko@kernel.org> X-Mailing-List: linux-api@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Transfer-Encoding: 8bit map_write() and its permission helpers validate extent ranges, check root and unprivileged self-mappings, translate parent ID ranges, sort extents, and install the resulting map inline for procfs text writes, preventing non-procfs callers from reusing the same validation and commit path. Extract idmap_maps_root(), unpriv_idmap_permitted(), validate_and_insert_extent(), free_new_idmap(), resolve_new_idmap(), and commit_new_idmap() with no functional change. Signed-off-by: Jarkko Sakkinen --- kernel/user_namespace.c | 229 +++++++++++++++++++++------------------- 1 file changed, 122 insertions(+), 107 deletions(-) diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index cd748e1cbace..caba2ac33077 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -884,6 +884,22 @@ VISIBLE_IF_KUNIT int uid_gid_map_sort(struct uid_gid_map *map) } EXPORT_SYMBOL_IF_KUNIT(uid_gid_map_sort); +static bool idmap_maps_root(const struct uid_gid_map *new_map) +{ + unsigned int idx; + + for (idx = 0; idx < new_map->nr_extents; idx++) { + const struct uid_gid_extent *e; + + if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) + e = &new_map->extent[idx]; + else + e = &new_map->forward[idx]; + if (e->lower_first == 0) + return true; + } + return false; +} /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file @@ -900,22 +916,9 @@ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { - int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; - struct uid_gid_extent *extent0 = NULL; - - for (idx = 0; idx < new_map->nr_extents; idx++) { - if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) - extent0 = &new_map->extent[idx]; - else - extent0 = &new_map->forward[idx]; - if (extent0->lower_first == 0) - break; - - extent0 = NULL; - } - if (!extent0) + if (!idmap_maps_root(new_map)) return true; if (map_ns == file_ns) { @@ -938,6 +941,103 @@ static bool verify_root_map(const struct file *file, return true; } +static int validate_and_insert_extent(struct uid_gid_map *new_map, + struct uid_gid_extent *extent) +{ + if ((extent->first == (u32)-1) || (extent->lower_first == (u32)-1)) + return -EINVAL; + + if ((extent->first + extent->count) <= extent->first) + return -EINVAL; + if ((extent->lower_first + extent->count) <= extent->lower_first) + return -EINVAL; + + if (mappings_overlap(new_map, extent)) + return -EINVAL; + + if (new_map->nr_extents >= UID_GID_MAP_MAX_EXTENTS) + return -EINVAL; + + return uid_gid_map_insert_extent(new_map, extent); +} + +static void free_new_idmap(struct uid_gid_map *new_map) +{ + if (new_map->nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { + kfree(new_map->forward); + kfree(new_map->reverse); + } + memset(new_map, 0, sizeof(*new_map)); +} + +static int resolve_new_idmap(struct uid_gid_map *new_map, + struct uid_gid_map *parent_map) +{ + unsigned int idx; + + if (new_map->nr_extents == 0) + return -EINVAL; + + for (idx = 0; idx < new_map->nr_extents; idx++) { + struct uid_gid_extent *e; + u32 lower_first; + + if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) + e = &new_map->extent[idx]; + else + e = &new_map->forward[idx]; + + lower_first = map_id_range_down(parent_map, + e->lower_first, + e->count); + if (lower_first == (u32)-1) + return -EPERM; + + e->lower_first = lower_first; + } + + return uid_gid_map_sort(new_map); +} + +static void commit_new_idmap(struct uid_gid_map *map, + struct uid_gid_map *new_map) +{ + if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { + memcpy(map->extent, new_map->extent, + new_map->nr_extents * sizeof(new_map->extent[0])); + } else { + map->forward = new_map->forward; + map->reverse = new_map->reverse; + } + /* + * Pairs with smp_rmb() in map_id_range_down(), map_id_range_up(), + * and m_start(). + */ + smp_wmb(); + map->nr_extents = new_map->nr_extents; + memset(new_map, 0, sizeof(*new_map)); +} + +static bool unpriv_idmap_permitted(const struct user_namespace *ns, + const struct cred *cred, int cap_setid, + unsigned long ns_flags, + const struct uid_gid_map *new_map) +{ + u32 id; + + if (new_map->nr_extents != 1 || new_map->extent[0].count != 1 || + !uid_eq(ns->owner, cred->euid)) + return false; + + id = new_map->extent[0].lower_first; + if (cap_setid == CAP_SETUID) + return uid_eq(make_kuid(ns->parent, id), cred->euid); + if (cap_setid == CAP_SETGID) + return !(ns_flags & USERNS_SETGROUPS_ALLOWED) && + gid_eq(make_kgid(ns->parent, id), cred->egid); + return false; +} + /* * Parse the decimal u32 at *pos, up to the next whitespace or NUL, and * leave *pos pointing at that character. @@ -966,8 +1066,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; - struct uid_gid_map new_map; - unsigned idx; + struct uid_gid_map new_map = {}; struct uid_gid_extent extent; char *kbuf, *pos, *next_line; ssize_t ret; @@ -1002,8 +1101,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, */ mutex_lock(&userns_state_mutex); - memset(&new_map, 0, sizeof(struct uid_gid_map)); - ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) @@ -1052,98 +1149,28 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (*pos != '\0') goto out; - /* Verify we have been given valid starting values */ - if ((extent.first == (u32) -1) || - (extent.lower_first == (u32) -1)) - goto out; - - /* Verify count is not zero and does not cause the - * extent to wrap - */ - if ((extent.first + extent.count) <= extent.first) - goto out; - if ((extent.lower_first + extent.count) <= - extent.lower_first) - goto out; - - /* Do the ranges in extent overlap any previous extents? */ - if (mappings_overlap(&new_map, &extent)) - goto out; - - if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && - (next_line != NULL)) - goto out; - - ret = uid_gid_map_insert_extent(&new_map, &extent); + ret = validate_and_insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } - /* Be very certain the new map actually exists */ + if (new_map.nr_extents == 0) goto out; ret = -EPERM; - /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; - ret = -EPERM; - /* Map the lower ids from the parent user namespace to the - * kernel global id space. - */ - for (idx = 0; idx < new_map.nr_extents; idx++) { - struct uid_gid_extent *e; - u32 lower_first; - - if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) - e = &new_map.extent[idx]; - else - e = &new_map.forward[idx]; - - lower_first = map_id_range_down(parent_map, - e->lower_first, - e->count); - - /* Fail if we can not map the specified extent to - * the kernel global id space. - */ - if (lower_first == (u32) -1) - goto out; - - e->lower_first = lower_first; - } - - /* - * If we want to use binary search for lookup, this clones the extent - * array and sorts both copies. - */ - ret = uid_gid_map_sort(&new_map); + ret = resolve_new_idmap(&new_map, parent_map); if (ret < 0) goto out; - /* Install the map */ - if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { - memcpy(map->extent, new_map.extent, - new_map.nr_extents * sizeof(new_map.extent[0])); - } else { - map->forward = new_map.forward; - map->reverse = new_map.reverse; - } - smp_wmb(); - map->nr_extents = new_map.nr_extents; - + commit_new_idmap(map, &new_map); *ppos = count; ret = count; out: - if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { - kfree(new_map.forward); - kfree(new_map.reverse); - map->forward = NULL; - map->reverse = NULL; - map->nr_extents = 0; - } - + free_new_idmap(&new_map); mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; @@ -1213,20 +1240,8 @@ static bool new_idmap_permitted(const struct file *file, /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ - if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && - uid_eq(ns->owner, cred->euid)) { - u32 id = new_map->extent[0].lower_first; - if (cap_setid == CAP_SETUID) { - kuid_t uid = make_kuid(ns->parent, id); - if (uid_eq(uid, cred->euid)) - return true; - } else if (cap_setid == CAP_SETGID) { - kgid_t gid = make_kgid(ns->parent, id); - if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && - gid_eq(gid, cred->egid)) - return true; - } - } + if (unpriv_idmap_permitted(ns, cred, cap_setid, ns->flags, new_map)) + return true; /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) -- 2.47.3