From nobody Mon Oct 6 06:40:56 2025 Received: from mout-p-202.mailbox.org (mout-p-202.mailbox.org [80.241.56.172]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 90D1426A1A3; Thu, 24 Jul 2025 08:32:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=80.241.56.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345957; cv=none; b=CiKDdyy4CV1T0xr3nNnh7tD/a0sDjJpAk0GJOniQ70NgPuBDdSslf8p4afAFoH5M7VpqGi+xT6HM4dk60xPVEDz5jD2/3EHjF4h4ukj7z9MEdEjZH80I6qInVn1tPjnlKufJ+0xzyFm17S4LO10ny9bj5QabTxxe5fzLpcGrdrk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345957; c=relaxed/simple; bh=KixoyUtbGrLnA3MTF47jcmrfse0K1oiiVQANOqAk1hI=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=pB28jcvtlvAsv58SbODxdiFsoF9iF2kuAVbrx5e/Nd3KvV4/N7QN6VMedaC/tILBQsYZ6CFSeg+GukIP+bv6Jvb6+P3/2eVD7/d6dEGNA2BDk7AKNuM34vwq1P8oWtoTbj9GDtR1VVNkN8B88uUuBLOMGXYB+6Zft260Dur6kPs= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com; spf=pass smtp.mailfrom=cyphar.com; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b=atZF9+1z; arc=none smtp.client-ip=80.241.56.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=cyphar.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b="atZF9+1z" Received: from smtp1.mailbox.org (smtp1.mailbox.org [IPv6:2001:67c:2050:b231:465::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mout-p-202.mailbox.org (Postfix) with ESMTPS id 4bnklG2l7Lz9t95; Thu, 24 Jul 2025 10:32:26 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cyphar.com; s=MBO0001; t=1753345946; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Cz5+/xzkeEXoj428r2lantinAr2RMkc/0PWdNpXULag=; b=atZF9+1zhyrl4eHa/Crrcp/HNJb/OYpnX9YXw9ICtMgS3OUNOyFq5M/fwIKe7XNcrP/xrz qzuHWfyfSJvbPp0yGbn+8g4io3puYL+7A/0Nul3+9tZtu3VZHuYmOgUSi56FClpime/fZj 1F4cyZWvpOsSpJoUcrSJgUqoUpmKZ1Akwgr/w552h75aNMMpNcTxsg/E9FxEji54SUavtD sAhv6KCO9UHSpsqrE0zTNKeoXfF6aEvSGi1GzgTw/ZD4VlyN7jW8B1YLbtkTjq2WaPhiU3 0RIaj1Is0Ob083L5CTYBy91Um7d+9W0yRhviWt7vXgX5SEUuU9PLyzg/eElxmQ== Authentication-Results: outgoing_mbo_mout; dkim=none; spf=pass (outgoing_mbo_mout: domain of cyphar@cyphar.com designates 2001:67c:2050:b231:465::1 as permitted sender) smtp.mailfrom=cyphar@cyphar.com From: Aleksa Sarai Date: Thu, 24 Jul 2025 18:32:03 +1000 Subject: [PATCH v3 1/4] pidns: move is-ancestor logic to helper Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250724-procfs-pidns-api-v3-1-4c685c910923@cyphar.com> References: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> In-Reply-To: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> To: Alexander Viro , Christian Brauner , Jan Kara , Jonathan Corbet , Shuah Khan Cc: Andy Lutomirski , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-api@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Aleksa Sarai X-Developer-Signature: v=1; a=openpgp-sha256; l=2749; i=cyphar@cyphar.com; h=from:subject:message-id; bh=KixoyUtbGrLnA3MTF47jcmrfse0K1oiiVQANOqAk1hI=; b=owGbwMvMwCWmMf3Xpe0vXfIZT6slMWQ0vu/U3h2k9kNHVelrxGQXxyufc2LkzS8vPbitN8Bwj s3WtJA1HaUsDGJcDLJiiizb/DxDN81ffCX500o2mDmsTCBDGLg4BWAiTqsY/ul5ce16cKhyx5zC rx+fT+hZs79195Sj4hyLhDsXzbU2S4xlZHh++KztVlmWo8uZ9ngyPVmosaPBPsaIa9VT+Vu++ry 2JxkB X-Developer-Key: i=cyphar@cyphar.com; a=openpgp; fpr=C9C370B246B09F6DBCFC744C34401015D1D2D386 X-Rspamd-Queue-Id: 4bnklG2l7Lz9t95 This check will be needed in later patches, and there's no point open-coding it each time. Signed-off-by: Aleksa Sarai --- include/linux/pid_namespace.h | 9 +++++++++ kernel/pid_namespace.c | 23 +++++++++++++++-------- 2 files changed, 24 insertions(+), 8 deletions(-) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c67a5811199..17fdc059f8da 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -84,6 +84,9 @@ extern void zap_pid_ns_processes(struct pid_namespace *pi= d_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); =20 +extern bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor); + #else /* !CONFIG_PID_NS */ #include =20 @@ -118,6 +121,12 @@ static inline int reboot_pid_ns(struct pid_namespace *= pid_ns, int cmd) { return 0; } + +static inline bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor) +{ + return false; +} #endif /* CONFIG_PID_NS */ =20 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 7098ed44e717..c2783c5fa90b 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -390,11 +390,24 @@ static void pidns_put(struct ns_common *ns) put_pid_ns(to_pid_ns(ns)); } =20 +bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor) +{ + struct pid_namespace *ns; + + if (child->level < ancestor->level) + return false; + for (ns =3D child; ns->level > ancestor->level; ns =3D ns->parent) + ; + return ns =3D=3D ancestor; +} +EXPORT_SYMBOL_GPL(pidns_is_ancestor); + static int pidns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy =3D nsset->nsproxy; struct pid_namespace *active =3D task_active_pid_ns(current); - struct pid_namespace *ancestor, *new =3D to_pid_ns(ns); + struct pid_namespace *new =3D to_pid_ns(ns); =20 if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) @@ -408,13 +421,7 @@ static int pidns_install(struct nsset *nsset, struct n= s_common *ns) * this maintains the property that processes and their * children can not escape their current pid namespace. */ - if (new->level < active->level) - return -EINVAL; - - ancestor =3D new; - while (ancestor->level > active->level) - ancestor =3D ancestor->parent; - if (ancestor !=3D active) + if (!pidns_is_ancestor(new, active)) return -EINVAL; =20 put_pid_ns(nsproxy->pid_ns_for_children); --=20 2.50.0 From nobody Mon Oct 6 06:40:56 2025 Received: from mout-p-101.mailbox.org (mout-p-101.mailbox.org [80.241.56.151]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9E3922727F8; Thu, 24 Jul 2025 08:32:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=80.241.56.151 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345958; cv=none; b=Em6r8x1mc8VwWLNSwexkLzeYRM2At/JPrCR4mNzpStUKDY5mC9N6BwKA8CUa1Kw71REQtBFtCuxheaeeI1986xM3393gXka6yiO9a3ESKsQcBuOauJRP68E8Q6qbj0aG7POIEDXrfvq3XYn5VwEKe5jApxB0JWlvlYArB64cels= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345958; c=relaxed/simple; bh=WR2Yjuz8Mc/vXG9KvxrS5QXxToTR5cQK70jR9IK+U0Q=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=I7oG+HHvvG4bA+sQEdGWm85l45JcYJtz90N6mtcG2YE0cF3DqKwXdXgbhPcTFVqlWii+MyE8e4bINTAP83RUuDGSae5tFZf2LsVa2Zdxx2+uwydDlPMnrmRd0BPNVCTPEXA5NaAdbqhdDNboFxq3HOiFZNJXXxjyaXFWQAreUKo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com; spf=pass smtp.mailfrom=cyphar.com; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b=RgVhC88L; arc=none smtp.client-ip=80.241.56.151 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=cyphar.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b="RgVhC88L" Received: from smtp1.mailbox.org (smtp1.mailbox.org [IPv6:2001:67c:2050:b231:465::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mout-p-101.mailbox.org (Postfix) with ESMTPS id 4bnklM68lbz9slG; Thu, 24 Jul 2025 10:32:31 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cyphar.com; s=MBO0001; t=1753345951; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Rl5yvqTtnRR//NXgj32CA5MMFGAzw4ESehbikqsVXv0=; b=RgVhC88Ld673w7DV9RCIcveV70tUsUHdyAVFp1vBEoGeOPgJmwiIb3rqkhUUxJxRX+goLe ZbiQHcglXOZ16byKSg5b9s7NqIkiIjOtlcjWQeO0a1IDz6G7AgIv/ppi3niRDFwTiR8bD4 7FbPxdBM3JPFOJotFGx59TwPRyE1yQZNCHRGFWLJmBonTbDpZpUnVClot0TOUrZ9AXjOTy WfVbsoMRx9ciPD60yJB7MVZB92b1N3HJ6PqIr5DwgUvlcI2xJpikgsf54BKt1sU6dIRw2K rRxSAcZydpegmd2j9eVC9E3IaptdsI6ICVTaa6IcxTmg6hTnJeGIVkZhzAZxUw== Authentication-Results: outgoing_mbo_mout; dkim=none; spf=pass (outgoing_mbo_mout: domain of cyphar@cyphar.com designates 2001:67c:2050:b231:465::1 as permitted sender) smtp.mailfrom=cyphar@cyphar.com From: Aleksa Sarai Date: Thu, 24 Jul 2025 18:32:04 +1000 Subject: [PATCH v3 2/4] procfs: add "pidns" mount option Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250724-procfs-pidns-api-v3-2-4c685c910923@cyphar.com> References: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> In-Reply-To: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> To: Alexander Viro , Christian Brauner , Jan Kara , Jonathan Corbet , Shuah Khan Cc: Andy Lutomirski , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-api@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Aleksa Sarai X-Developer-Signature: v=1; a=openpgp-sha256; l=7582; i=cyphar@cyphar.com; h=from:subject:message-id; bh=WR2Yjuz8Mc/vXG9KvxrS5QXxToTR5cQK70jR9IK+U0Q=; b=owGbwMvMwCWmMf3Xpe0vXfIZT6slMWQ0vu+sltpY2FoUwDDjcuhTzplCxfw9x5QeFif3Nkad3 1g7c+qqjlIWBjEuBlkxRZZtfp6hm+YvvpL8aSUbzBxWJpAhDFycAjCRmp+MDK8knY2qFxVO+LtQ mam8X+CitUBfxUZrjvd+Ya0f+QLbGhj+GRgba87e6RA/5U1Nl/u0Jz4yzyRW5x0yWqT+cW9Zn28 gEwA= X-Developer-Key: i=cyphar@cyphar.com; a=openpgp; fpr=C9C370B246B09F6DBCFC744C34401015D1D2D386 X-Rspamd-Queue-Id: 4bnklM68lbz9slG Since the introduction of pid namespaces, their interaction with procfs has been entirely implicit in ways that require a lot of dancing around by programs that need to construct sandboxes with different PID namespaces. Being able to explicitly specify the pid namespace to use when constructing a procfs super block will allow programs to no longer need to fork off a process which does then does unshare(2) / setns(2) and forks again in order to construct a procfs in a pidns. So, provide a "pidns" mount option which allows such users to just explicitly state which pid namespace they want that procfs instance to use. This interface can be used with fsconfig(2) either with a file descriptor or a path: fsconfig(procfd, FSCONFIG_SET_FD, "pidns", NULL, nsfd); fsconfig(procfd, FSCONFIG_SET_STRING, "pidns", "/proc/self/ns/pid", 0); or with classic mount(2) / mount(8): // mount -t proc -o pidns=3D/proc/self/ns/pid proc /tmp/proc mount("proc", "/tmp/proc", "proc", MS_..., "pidns=3D/proc/self/ns/pid"); As this new API is effectively shorthand for setns(2) followed by mount(2), the permission model for this mirrors pidns_install() to avoid opening up new attack surfaces by loosening the existing permission model. In order to avoid having to RCU-protect all users of proc_pid_ns() (to avoid UAFs), attempting to reconfigure an existing procfs instance's pid namespace will error out with -EBUSY. Creating new procfs instances is quite cheap, so this should not be an impediment to most users, and lets us avoid a lot of churn in fs/proc/* for a feature that it seems unlikely userspace would use. Signed-off-by: Aleksa Sarai --- Documentation/filesystems/proc.rst | 8 +++ fs/proc/root.c | 102 +++++++++++++++++++++++++++++++++= +--- 2 files changed, 104 insertions(+), 6 deletions(-) diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems= /proc.rst index 5236cb52e357..5a157dadea0b 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -2360,6 +2360,7 @@ The following mount options are supported: hidepid=3D Set /proc// access mode. gid=3D Set the group authorized to learn processes information. subset=3D Show only the specified subset of procfs. + pidns=3D Specify a the namespace used by this procfs. =3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =20 hidepid=3Doff or hidepid=3D0 means classic mode - everybody may access all @@ -2392,6 +2393,13 @@ information about processes information, just add id= entd to this group. subset=3Dpid hides all top level files and directories in the procfs that are not related to tasks. =20 +pidns=3D specifies a pid namespace (either as a string path to something l= ike +`/proc/$pid/ns/pid`, or a file descriptor when using `FSCONFIG_SET_FD`) th= at +will be used by the procfs instance when translating pids. By default, pro= cfs +will use the calling process's active pid namespace. Note that the pid +namespace of an existing procfs instance cannot be modified (attempting to= do +so will give an `-EBUSY` error). + Chapter 5: Filesystem behavior =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D =20 diff --git a/fs/proc/root.c b/fs/proc/root.c index ed86ac710384..22f8b10f6265 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -38,12 +38,18 @@ enum proc_param { Opt_gid, Opt_hidepid, Opt_subset, +#ifdef CONFIG_PID_NS + Opt_pidns, +#endif }; =20 static const struct fs_parameter_spec proc_fs_parameters[] =3D { - fsparam_u32("gid", Opt_gid), + fsparam_u32("gid", Opt_gid), fsparam_string("hidepid", Opt_hidepid), fsparam_string("subset", Opt_subset), +#ifdef CONFIG_PID_NS + fsparam_file_or_string("pidns", Opt_pidns), +#endif {} }; =20 @@ -109,11 +115,67 @@ static int proc_parse_subset_param(struct fs_context = *fc, char *value) return 0; } =20 +#ifdef CONFIG_PID_NS +static int proc_parse_pidns_param(struct fs_context *fc, + struct fs_parameter *param, + struct fs_parse_result *result) +{ + struct proc_fs_context *ctx =3D fc->fs_private; + struct pid_namespace *target, *active =3D task_active_pid_ns(current); + struct ns_common *ns; + struct file *ns_filp __free(fput) =3D NULL; + + switch (param->type) { + case fs_value_is_file: + /* came throug fsconfig, steal the file reference */ + ns_filp =3D param->file; + param->file =3D NULL; + break; + case fs_value_is_string: + ns_filp =3D filp_open(param->string, O_RDONLY, 0); + break; + default: + WARN_ON_ONCE(true); + break; + } + if (!ns_filp) + ns_filp =3D ERR_PTR(-EBADF); + if (IS_ERR(ns_filp)) { + errorfc(fc, "could not get file from pidns argument"); + return PTR_ERR(ns_filp); + } + + if (!proc_ns_file(ns_filp)) + return invalfc(fc, "pidns argument is not an nsfs file"); + ns =3D get_proc_ns(file_inode(ns_filp)); + if (ns->ops->type !=3D CLONE_NEWPID) + return invalfc(fc, "pidns argument is not a pidns file"); + target =3D container_of(ns, struct pid_namespace, ns); + + /* + * pidns=3D is shorthand for joining the pidns to get a fsopen fd, so the + * permission model should be the same as pidns_install(). + */ + if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) { + errorfc(fc, "insufficient permissions to set pidns"); + return -EPERM; + } + if (!pidns_is_ancestor(target, active)) + return invalfc(fc, "cannot set pidns to non-descendant pidns"); + + put_pid_ns(ctx->pid_ns); + ctx->pid_ns =3D get_pid_ns(target); + put_user_ns(fc->user_ns); + fc->user_ns =3D get_user_ns(ctx->pid_ns->user_ns); + return 0; +} +#endif /* CONFIG_PID_NS */ + static int proc_parse_param(struct fs_context *fc, struct fs_parameter *pa= ram) { struct proc_fs_context *ctx =3D fc->fs_private; struct fs_parse_result result; - int opt; + int opt, err; =20 opt =3D fs_parse(fc, proc_fs_parameters, param, &result); if (opt < 0) @@ -125,15 +187,36 @@ static int proc_parse_param(struct fs_context *fc, st= ruct fs_parameter *param) break; =20 case Opt_hidepid: - if (proc_parse_hidepid_param(fc, param)) - return -EINVAL; + err =3D proc_parse_hidepid_param(fc, param); + if (err) + return err; break; =20 case Opt_subset: - if (proc_parse_subset_param(fc, param->string) < 0) - return -EINVAL; + err =3D proc_parse_subset_param(fc, param->string); + if (err) + return err; break; =20 +#ifdef CONFIG_PID_NS + case Opt_pidns: + /* + * We would have to RCU-protect every proc_pid_ns() or + * proc_sb_info() access if we allowed this to be reconfigured + * for an existing procfs instance. Luckily, procfs instances + * are cheap to create, and mount-beneath would let you + * atomically replace an instance even with overmounts. + */ + if (fc->purpose =3D=3D FS_CONTEXT_FOR_RECONFIGURE) { + errorfc(fc, "cannot reconfigure pidns for existing procfs"); + return -EBUSY; + } + err =3D proc_parse_pidns_param(fc, param, &result); + if (err) + return err; + break; +#endif + default: return -EINVAL; } @@ -154,6 +237,13 @@ static void proc_apply_options(struct proc_fs_info *fs= _info, fs_info->hide_pid =3D ctx->hidepid; if (ctx->mask & (1 << Opt_subset)) fs_info->pidonly =3D ctx->pidonly; +#ifdef CONFIG_PID_NS + if (ctx->mask & (1 << Opt_pidns) && + !WARN_ON_ONCE(fc->purpose =3D=3D FS_CONTEXT_FOR_RECONFIGURE)) { + put_pid_ns(fs_info->pid_ns); + fs_info->pid_ns =3D get_pid_ns(ctx->pid_ns); + } +#endif } =20 static int proc_fill_super(struct super_block *s, struct fs_context *fc) --=20 2.50.0 From nobody Mon Oct 6 06:40:56 2025 Received: from mout-p-103.mailbox.org (mout-p-103.mailbox.org [80.241.56.161]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1DCD1274B59; Thu, 24 Jul 2025 08:32:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=80.241.56.161 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345963; cv=none; b=hC/nK5zqo3CUthd170eynO22L6EWYoiFncl5nfxfu56APm/pxTpHkD+mK+3engE0dXjUlUa4SYW0nZwpzt0p2tvFZ3IJYIO+PaOkYpYIsMtHxg0JmG9bf3becjzDjPa2e6J21V5uYvAWIdoBlKN6fhRfzuFo6iBx6MOhL2LiPnI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345963; c=relaxed/simple; bh=wwOMOIEXpOTsKokLHFgbCzkAoRkI6EpGwh603o/RxDg=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=S0B8xPklXbhV0DBYvbO0lun/+evJZGu0ZhInlwOZgV6Ow8wrkMQ6JShf7XFF0B4Ha9HnrbnyluNCFxZcRB1c9uX81AD4ATnTWR+0eILSqD0XRUUrYOXrJxwBdcdAqgbvV0NRmncPgV2Fc1gY6HIJl55yUR6F0o54NQBxjkmuwec= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com; spf=pass smtp.mailfrom=cyphar.com; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b=Raa1quzZ; arc=none smtp.client-ip=80.241.56.161 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=cyphar.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b="Raa1quzZ" Received: from smtp1.mailbox.org (smtp1.mailbox.org [IPv6:2001:67c:2050:b231:465::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mout-p-103.mailbox.org (Postfix) with ESMTPS id 4bnklT3GH6z9sqF; Thu, 24 Jul 2025 10:32:37 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cyphar.com; s=MBO0001; t=1753345957; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=5SMShT2oz+CRxYM5X/mjoZAEZ5lq2EhgkYkycDK2QpQ=; b=Raa1quzZByM7ZqSn0cr4T65ZDqBkAcWPEedgpxHeqeei6VhIG5iF9yz1VxqHMWFCbbXYTN Wv0oYJM27pQfbnUj1TRt+7HBLreKNXaAkaoiiCjet6w2lz8deT2F4HAMI8kDVV6H1OpXvl CE8M42WGLxu8lLBWRzHLz+Kie5lvKtTdaSKrjn4BvPwFa+/q5w2EWg+shHPf/zR9jeJ23W DPJZsQHdy9ASnpiGNI1blcJoLt8yyXJlXWsaUyI/JfkfLc2LKe2p+RB3sMsjtbrj1pEDoX 1yK8dIPSWbqYhGUpHRmcSjVt9yMlJEqAFhwuZdTBoF0IN08n7vQhgHGaGv/pfg== Authentication-Results: outgoing_mbo_mout; dkim=none; spf=pass (outgoing_mbo_mout: domain of cyphar@cyphar.com designates 2001:67c:2050:b231:465::1 as permitted sender) smtp.mailfrom=cyphar@cyphar.com From: Aleksa Sarai Date: Thu, 24 Jul 2025 18:32:05 +1000 Subject: [PATCH v3 3/4] procfs: add PROCFS_GET_PID_NAMESPACE ioctl Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250724-procfs-pidns-api-v3-3-4c685c910923@cyphar.com> References: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> In-Reply-To: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> To: Alexander Viro , Christian Brauner , Jan Kara , Jonathan Corbet , Shuah Khan Cc: Andy Lutomirski , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-api@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Aleksa Sarai X-Developer-Signature: v=1; a=openpgp-sha256; l=5652; i=cyphar@cyphar.com; h=from:subject:message-id; bh=wwOMOIEXpOTsKokLHFgbCzkAoRkI6EpGwh603o/RxDg=; b=owGbwMvMwCWmMf3Xpe0vXfIZT6slMWQ0vu+a98FJ9m/V43ybybv7FebGLyv3m7e8rHjPmuerT A5c2GTt31HKwiDGxSArpsiyzc8zdNP8xVeSP61kg5nDygQyhIGLUwAm8t+f4Z/5Dm01gUVTOOw/ Gpun65+sbwh0/SV/NEPBgeHPheOVa6Yz/FMVKPXrXzvxROLdxfpMqzcYHL9o93xPs9Gab1bXa+9 m32UAAA== X-Developer-Key: i=cyphar@cyphar.com; a=openpgp; fpr=C9C370B246B09F6DBCFC744C34401015D1D2D386 X-Rspamd-Queue-Id: 4bnklT3GH6z9sqF /proc has historically had very opaque semantics about PID namespaces, which is a little unfortunate for container runtimes and other programs that deal with switching namespaces very often. One common issue is that of converting between PIDs in the process's namespace and PIDs in the namespace of /proc. In principle, it is possible to do this today by opening a pidfd with pidfd_open(2) and then looking at /proc/self/fdinfo/$n (which will contain a PID value translated to the pid namespace associated with that procfs superblock). However, allocating a new file for each PID to be converted is less than ideal for programs that may need to scan procfs, and it is generally useful for userspace to be able to finally get this information from procfs. So, add a new API for this in the form of an ioctl(2) you can call on the root directory of procfs. The returned file descriptor will have O_CLOEXEC set. This acts as a sister feature to the new "pidns" mount option, finally allowing userspace full control of the pid namespaces associated with procfs instances. The permission model for this is a bit looser than that of the "pidns" mount option, but this is mainly because /proc/1/ns/pid provides the same information, so as long as you have access to that magic-link (or something equivalently reasonable such as privileges with CAP_SYS_ADMIN or being in an ancestor pid namespace) it makes sense to allow userspace to grab a handle. setns(2) will still have their own permission checks, so being able to open a pidns handle doesn't really provide too many other capabilities. Signed-off-by: Aleksa Sarai --- Documentation/filesystems/proc.rst | 4 +++ fs/proc/root.c | 54 ++++++++++++++++++++++++++++++++++= ++-- include/uapi/linux/fs.h | 3 +++ 3 files changed, 59 insertions(+), 2 deletions(-) diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems= /proc.rst index 5a157dadea0b..840f820fb467 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -2400,6 +2400,10 @@ will use the calling process's active pid namespace.= Note that the pid namespace of an existing procfs instance cannot be modified (attempting to= do so will give an `-EBUSY` error). =20 +Processes can check which pid namespace is used by a procfs instance by us= ing +the `PROCFS_GET_PID_NAMESPACE` ioctl() on the root directory of the procfs +instance. + Chapter 5: Filesystem behavior =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D =20 diff --git a/fs/proc/root.c b/fs/proc/root.c index 22f8b10f6265..c6110436e528 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -23,8 +23,10 @@ #include #include #include +#include =20 #include "internal.h" +#include "../internal.h" =20 struct proc_fs_context { struct pid_namespace *pid_ns; @@ -430,15 +432,63 @@ static int proc_root_readdir(struct file *file, struc= t dir_context *ctx) return proc_pid_readdir(file, ctx); } =20 +static long int proc_root_ioctl(struct file *filp, unsigned int cmd, unsig= ned long arg) +{ + switch (cmd) { +#ifdef CONFIG_PID_NS + case PROCFS_GET_PID_NAMESPACE: { + struct pid_namespace *active =3D task_active_pid_ns(current); + struct pid_namespace *ns =3D proc_pid_ns(file_inode(filp)->i_sb); + bool can_access_pidns =3D false; + + /* + * If we are in an ancestors of the pidns, or have join + * privileges (CAP_SYS_ADMIN), then it makes sense that we + * would be able to grab a handle to the pidns. + * + * Otherwise, if there is a root process, then being able to + * access /proc/$pid/ns/pid is equivalent to this ioctl and so + * we should probably match the permission model. For empty + * namespaces it seems unlikely for there to be a downside to + * allowing unprivileged users to open a handle to it (setns + * will fail for unprivileged users anyway). + */ + can_access_pidns =3D pidns_is_ancestor(ns, active) || + ns_capable(ns->user_ns, CAP_SYS_ADMIN); + if (!can_access_pidns) { + bool cannot_ptrace_pid1 =3D false; + + read_lock(&tasklist_lock); + if (ns->child_reaper) + cannot_ptrace_pid1 =3D ptrace_may_access(ns->child_reaper, + PTRACE_MODE_READ_FSCREDS); + read_unlock(&tasklist_lock); + can_access_pidns =3D !cannot_ptrace_pid1; + } + if (!can_access_pidns) + return -EPERM; + + /* open_namespace() unconditionally consumes the reference. */ + get_pid_ns(ns); + return open_namespace(to_ns_common(ns)); + } +#endif /* CONFIG_PID_NS */ + default: + return -ENOIOCTLCMD; + } +} + /* * The root /proc directory is special, as it has the * directories. Thus we don't use the generic * directory handling functions for that.. */ static const struct file_operations proc_root_operations =3D { - .read =3D generic_read_dir, - .iterate_shared =3D proc_root_readdir, + .read =3D generic_read_dir, + .iterate_shared =3D proc_root_readdir, .llseek =3D generic_file_llseek, + .unlocked_ioctl =3D proc_root_ioctl, + .compat_ioctl =3D compat_ptr_ioctl, }; =20 /* diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 0bd678a4a10e..aa642cb48feb 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -437,6 +437,9 @@ typedef int __bitwise __kernel_rwf_t; =20 #define PROCFS_IOCTL_MAGIC 'f' =20 +/* procfs root ioctls */ +#define PROCFS_GET_PID_NAMESPACE _IO(PROCFS_IOCTL_MAGIC, 1) + /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) =20 --=20 2.50.0 From nobody Mon Oct 6 06:40:56 2025 Received: from mout-p-103.mailbox.org (mout-p-103.mailbox.org [80.241.56.161]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 836C2276038; Thu, 24 Jul 2025 08:32:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=80.241.56.161 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345968; cv=none; b=QI9+ho+VCHcCSCq/2uAcIW5WVT5/LFNh44Xmn8KiMMiWI5Z/6kIFYBXsdU74vddrX6O/Lic2U1qREsv+DCKoA/cSOrvd2SJhb2jN3c38ryNd58PRaJbGy5dQ4pDHykp9vGgByAbZYOrXyQ6YYPLKB60z0N2zJFJr26/eGHafKSw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1753345968; c=relaxed/simple; bh=qnzDffrtOhieCifIQALbR9Yq8NuI1rDh8ygAqZ4PCnw=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=aKZqMFzZnoZiKRrubfj4BdF8dZ29oPWiQmPnbuO3rtFWOGYxhUC9YWLLMN4XfXfw5vNnUurGBEWZudywAUfawiB2fn2IRIUlAU8uuh2FmBgaoj/HmDAs6IuOBjRHclqMP6Tft/YucpVOQPlq824op2AMIFhYe/gC+vl/gpqqMgM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com; spf=pass smtp.mailfrom=cyphar.com; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b=pZBaZxko; arc=none smtp.client-ip=80.241.56.161 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=cyphar.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=cyphar.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=cyphar.com header.i=@cyphar.com header.b="pZBaZxko" Received: from smtp1.mailbox.org (smtp1.mailbox.org [10.196.197.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mout-p-103.mailbox.org (Postfix) with ESMTPS id 4bnklZ6y3Jz9svR; Thu, 24 Jul 2025 10:32:42 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cyphar.com; s=MBO0001; t=1753345963; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=GTi/FGmUyVjfXcqveVu9fsI9YOLQ9+kwvijsaczxosQ=; b=pZBaZxkorZi22C+ucatZAoKGZxcF2LWH23PGp4pyYVFRlEenmH897gnq0eTz9IFvk/cCYE 2H7ZbqGdabt/s1PJurOqX9y0Lm9RuYRGV2RysHmGczm3CyGfYbIMkr3hQsfTB/Y9rhpJNK /hzPznfO2yGPX1JKKWmoTAaJVIGjPHOWHUgZzsjW5MyrOPq7FL/V0+M+myzyFdG1uVTDgC Cs2fYafIgQfBq6uQDaw/MdM39mZiicO2NWLqOfTAU3By+iWPj9ZngkXGeFTP0d/0i1abf3 Y6UrHuz9IVB3om5RKZmSO6cPuFjm2+tEa9mbX2P6NWqVMqlo9M6f0rEhX6FTIA== From: Aleksa Sarai Date: Thu, 24 Jul 2025 18:32:06 +1000 Subject: [PATCH v3 4/4] selftests/proc: add tests for new pidns APIs Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250724-procfs-pidns-api-v3-4-4c685c910923@cyphar.com> References: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> In-Reply-To: <20250724-procfs-pidns-api-v3-0-4c685c910923@cyphar.com> To: Alexander Viro , Christian Brauner , Jan Kara , Jonathan Corbet , Shuah Khan Cc: Andy Lutomirski , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-api@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Aleksa Sarai X-Developer-Signature: v=1; a=openpgp-sha256; l=8964; i=cyphar@cyphar.com; h=from:subject:message-id; bh=qnzDffrtOhieCifIQALbR9Yq8NuI1rDh8ygAqZ4PCnw=; b=owGbwMvMwCWmMf3Xpe0vXfIZT6slMWQ0vu8y1VD3UBJN+GUQGOl3xDHuwXXbN40TPlUcubBrG 2vFqd8RHaUsDGJcDLJiiizb/DxDN81ffCX500o2mDmsTCBDGLg4BWAiCyYy/DP9GzXd53xb3tHg EP44aVeHZVtz9k3MNboqtrkuc/mlb7UMf/he3X/H75K618my5kv6y2WT4zNCfyasrbe7db/pZ+u +WDYA X-Developer-Key: i=cyphar@cyphar.com; a=openpgp; fpr=C9C370B246B09F6DBCFC744C34401015D1D2D386 Signed-off-by: Aleksa Sarai --- tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/proc-pidns.c | 252 ++++++++++++++++++++++++++= ++++ 3 files changed, 254 insertions(+) diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selfte= sts/proc/.gitignore index 973968f45bba..2dced03e9e0e 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -17,6 +17,7 @@ /proc-tid0 /proc-uptime-001 /proc-uptime-002 +/proc-pidns /read /self /setns-dcache diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftest= s/proc/Makefile index b12921b9794b..c6f7046b9860 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -27,5 +27,6 @@ TEST_GEN_PROGS +=3D setns-sysvipc TEST_GEN_PROGS +=3D thread-self TEST_GEN_PROGS +=3D proc-multiple-procfs TEST_GEN_PROGS +=3D proc-fsconfig-hidepid +TEST_GEN_PROGS +=3D proc-pidns =20 include ../lib.mk diff --git a/tools/testing/selftests/proc/proc-pidns.c b/tools/testing/self= tests/proc/proc-pidns.c new file mode 100644 index 000000000000..5994375e2377 --- /dev/null +++ b/tools/testing/selftests/proc/proc-pidns.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai + * Copyright (C) 2025 SUSE LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest_harness.h" + +#define ASSERT_ERRNO(expected, _t, seen) \ + __EXPECT(expected, #expected, \ + ({__typeof__(seen) _tmp_seen =3D (seen); \ + _tmp_seen >=3D 0 ? _tmp_seen : -errno; }), #seen, _t, 1) + +#define ASSERT_ERRNO_EQ(expected, seen) \ + ASSERT_ERRNO(expected, =3D=3D, seen) + +#define ASSERT_SUCCESS(seen) \ + ASSERT_ERRNO(0, <=3D, seen) + +static int touch(char *path) +{ + int fd =3D open(path, O_WRONLY|O_CREAT|O_CLOEXEC, 0644); + if (fd < 0) + return -1; + return close(fd); +} + +FIXTURE(ns) +{ + int host_mntns, host_pidns; + int dummy_pidns; +}; + +FIXTURE_SETUP(ns) +{ + /* Stash the old mntns. */ + self->host_mntns =3D open("/proc/self/ns/mnt", O_RDONLY|O_CLOEXEC); + ASSERT_SUCCESS(self->host_mntns); + + /* Create a new mount namespace and make it private. */ + ASSERT_SUCCESS(unshare(CLONE_NEWNS)); + ASSERT_SUCCESS(mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL)); + + /* + * Create a proper tmpfs that we can use and will disappear once we + * leave this mntns. + */ + ASSERT_SUCCESS(mount("tmpfs", "/tmp", "tmpfs", 0, NULL)); + + /* + * Create a pidns we can use for later tests. We need to fork off a + * child so that we get a usable nsfd that we can bind-mount and open. + */ + ASSERT_SUCCESS(touch("/tmp/dummy-pidns")); + + self->host_pidns =3D open("/proc/self/ns/pid", O_RDONLY|O_CLOEXEC); + ASSERT_SUCCESS(self->host_pidns); + ASSERT_SUCCESS(unshare(CLONE_NEWPID)); + + pid_t pid =3D fork(); + ASSERT_SUCCESS(pid); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGKILL); + ASSERT_SUCCESS(mount("/proc/self/ns/pid", "/tmp/dummy-pidns", NULL, MS_B= IND, 0)); + exit(0); + } + + int wstatus; + ASSERT_EQ(waitpid(pid, &wstatus, 0), pid); + ASSERT_TRUE(WIFEXITED(wstatus)); + ASSERT_EQ(WEXITSTATUS(wstatus), 0); + + ASSERT_SUCCESS(setns(self->host_pidns, CLONE_NEWPID)); + + self->dummy_pidns =3D open("/tmp/dummy-pidns", O_RDONLY|O_CLOEXEC); + ASSERT_SUCCESS(self->dummy_pidns); +} + +FIXTURE_TEARDOWN(ns) +{ + ASSERT_SUCCESS(setns(self->host_mntns, CLONE_NEWNS)); + ASSERT_SUCCESS(close(self->host_mntns)); + + ASSERT_SUCCESS(close(self->host_pidns)); + ASSERT_SUCCESS(close(self->dummy_pidns)); +} + +TEST_F(ns, pidns_mount_string_path) +{ + ASSERT_SUCCESS(mkdir("/tmp/proc-host", 0755)); + ASSERT_SUCCESS(mount("proc", "/tmp/proc-host", "proc", 0, "pidns=3D/proc/= self/ns/pid")); + ASSERT_SUCCESS(access("/tmp/proc-host/self/", X_OK)); + + ASSERT_SUCCESS(mkdir("/tmp/proc-dummy", 0755)); + ASSERT_SUCCESS(mount("proc", "/tmp/proc-dummy", "proc", 0, "pidns=3D/tmp/= dummy-pidns")); + ASSERT_ERRNO_EQ(-ENOENT, access("/tmp/proc-dummy/1/", X_OK)); + ASSERT_ERRNO_EQ(-ENOENT, access("/tmp/proc-dummy/self/", X_OK)); +} + +TEST_F(ns, pidns_fsconfig_string_path) +{ + int fsfd =3D fsopen("proc", FSOPEN_CLOEXEC); + ASSERT_SUCCESS(fsfd); + + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy-p= idns", 0)); + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)); + + int mountfd =3D fsmount(fsfd, FSMOUNT_CLOEXEC, 0); + ASSERT_SUCCESS(mountfd); + + ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_SUCCESS(close(fsfd)); + ASSERT_SUCCESS(close(mountfd)); +} + +TEST_F(ns, pidns_fsconfig_fd) +{ + int fsfd =3D fsopen("proc", FSOPEN_CLOEXEC); + ASSERT_SUCCESS(fsfd); + + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy= _pidns)); + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)); + + int mountfd =3D fsmount(fsfd, FSMOUNT_CLOEXEC, 0); + ASSERT_SUCCESS(mountfd); + + ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_SUCCESS(close(fsfd)); + ASSERT_SUCCESS(close(mountfd)); +} + +TEST_F(ns, pidns_reconfigure_remount) +{ + ASSERT_SUCCESS(mkdir("/tmp/proc", 0755)); + ASSERT_SUCCESS(mount("proc", "/tmp/proc", "proc", 0, "")); + + ASSERT_SUCCESS(access("/tmp/proc/1/", X_OK)); + ASSERT_SUCCESS(access("/tmp/proc/self/", X_OK)); + + ASSERT_ERRNO_EQ(-EBUSY, mount(NULL, "/tmp/proc", NULL, MS_REMOUNT, "pidns= =3D/tmp/dummy-pidns")); + + ASSERT_SUCCESS(access("/tmp/proc/1/", X_OK)); + ASSERT_SUCCESS(access("/tmp/proc/self/", X_OK)); +} + +TEST_F(ns, pidns_reconfigure_fsconfig_string_path) +{ + int fsfd =3D fsopen("proc", FSOPEN_CLOEXEC); + ASSERT_SUCCESS(fsfd); + + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)); + + int mountfd =3D fsmount(fsfd, FSMOUNT_CLOEXEC, 0); + ASSERT_SUCCESS(mountfd); + + ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_ERRNO_EQ(-EBUSY, fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tm= p/dummy-pidns", 0)); + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0)); = /* noop */ + + ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_SUCCESS(close(fsfd)); + ASSERT_SUCCESS(close(mountfd)); +} + +TEST_F(ns, pidns_reconfigure_fsconfig_fd) +{ + int fsfd =3D fsopen("proc", FSOPEN_CLOEXEC); + ASSERT_SUCCESS(fsfd); + + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)); + + int mountfd =3D fsmount(fsfd, FSMOUNT_CLOEXEC, 0); + ASSERT_SUCCESS(mountfd); + + ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_ERRNO_EQ(-EBUSY, fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, se= lf->dummy_pidns)); + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0)); = /* noop */ + + ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0)); + ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0)); + + ASSERT_SUCCESS(close(fsfd)); + ASSERT_SUCCESS(close(mountfd)); +} + +int is_same_inode(int fd1, int fd2) +{ + struct stat stat1, stat2; + + assert(fstat(fd1, &stat1) =3D=3D 0); + assert(fstat(fd2, &stat2) =3D=3D 0); + + return stat1.st_ino =3D=3D stat2.st_ino && stat1.st_dev =3D=3D stat2.st_d= ev; +} + +#define PROCFS_IOCTL_MAGIC 'f' +#define PROCFS_GET_PID_NAMESPACE _IO(PROCFS_IOCTL_MAGIC, 1) + +TEST_F(ns, get_pidns_ioctl) +{ + int fsfd =3D fsopen("proc", FSOPEN_CLOEXEC); + ASSERT_SUCCESS(fsfd); + + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy= _pidns)); + ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)); + + int mountfd =3D fsmount(fsfd, FSMOUNT_CLOEXEC, 0); + ASSERT_SUCCESS(mountfd); + + /* fsmount returns an O_PATH, which ioctl(2) doesn't accept. */ + int new_mountfd =3D openat(mountfd, ".", O_RDONLY|O_DIRECTORY|O_CLOEXEC); + ASSERT_SUCCESS(new_mountfd); + + ASSERT_SUCCESS(close(mountfd)); + mountfd =3D -EBADF; + + int procfs_pidns =3D ioctl(new_mountfd, PROCFS_GET_PID_NAMESPACE); + ASSERT_SUCCESS(procfs_pidns); + + ASSERT_NE(self->dummy_pidns, procfs_pidns); + ASSERT_FALSE(is_same_inode(self->host_pidns, procfs_pidns)); + ASSERT_TRUE(is_same_inode(self->dummy_pidns, procfs_pidns)); + + ASSERT_SUCCESS(close(fsfd)); + ASSERT_SUCCESS(close(new_mountfd)); + ASSERT_SUCCESS(close(procfs_pidns)); +} + +TEST_HARNESS_MAIN --=20 2.50.0