.gitignore

@@ -1 +1 @@
-SOURCES/runc-2abd837.tar.gz
+SOURCES/v1.2.4.tar.gz

.runc.metadata

@@ -1 +1 @@
-cf7119a838db2963e7af6ecdba90a2cc95ec0d56 SOURCES/runc-2abd837.tar.gz
+14c6119053012f4072aed8dbb9fd47b57c47279b SOURCES/v1.2.4.tar.gz

SOURCES/0001-Bump-runtime-spec-to-latest-git-HEAD.patch

@@ -0,0 +1,103 @@
+From c6dad73d617864f3a281ac1fdaacd5ed971fa317 Mon Sep 17 00:00:00 2001
+From: Kir Kolyshkin <kolyshkin@gmail.com>
+Date: Thu, 27 Jun 2024 09:00:51 -0700
+Subject: [PATCH 1/2] Bump runtime-spec to latest git HEAD
+
+This is to include
+ - https://github.com/opencontainers/runtime-spec/pull/1261
+ - https://github.com/opencontainers/runtime-spec/pull/1253
+
+Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
+(cherry picked from commit 2cac22b1e29e6be4c004f35ce582aa2b7e1c2fda)
+Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
+---
+ go.mod                                                    | 2 +-
+ go.sum                                                    | 4 ++--
+ .../opencontainers/runtime-spec/specs-go/config.go        | 8 ++++++++
+ .../opencontainers/runtime-spec/specs-go/version.go       | 2 +-
+ vendor/modules.txt                                        | 2 +-
+ 5 files changed, 13 insertions(+), 5 deletions(-)
+
+diff --git a/go.mod b/go.mod
+index 348bc9c6..db2d7ef1 100644
+--- a/go.mod
++++ b/go.mod
+@@ -19,7 +19,7 @@ require (
+ 	github.com/moby/sys/user v0.3.0
+ 	github.com/moby/sys/userns v0.1.0
+ 	github.com/mrunalp/fileutils v0.5.1
+-	github.com/opencontainers/runtime-spec v1.2.0
++	github.com/opencontainers/runtime-spec v1.2.1-0.20240625190033-701738418b95
+ 	github.com/opencontainers/selinux v1.11.0
+ 	github.com/seccomp/libseccomp-golang v0.10.0
+ 	github.com/sirupsen/logrus v1.9.3
+diff --git a/go.sum b/go.sum
+index 225d5860..4c863cc9 100644
+--- a/go.sum
++++ b/go.sum
+@@ -46,8 +46,8 @@ github.com/moby/sys/userns v0.1.0 h1:tVLXkFOxVu9A64/yh59slHVv9ahO9UIev4JZusOLG/g
+ github.com/moby/sys/userns v0.1.0/go.mod h1:IHUYgu/kao6N8YZlp9Cf444ySSvCmDlmzUcYfDHOl28=
+ github.com/mrunalp/fileutils v0.5.1 h1:F+S7ZlNKnrwHfSwdlgNSkKo67ReVf8o9fel6C3dkm/Q=
+ github.com/mrunalp/fileutils v0.5.1/go.mod h1:M1WthSahJixYnrXQl/DFQuteStB1weuxD2QJNHXfbSQ=
+-github.com/opencontainers/runtime-spec v1.2.0 h1:z97+pHb3uELt/yiAWD691HNHQIF07bE7dzrbT927iTk=
+-github.com/opencontainers/runtime-spec v1.2.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
++github.com/opencontainers/runtime-spec v1.2.1-0.20240625190033-701738418b95 h1:Ghl8Z3l+yPQUDSxAp7Kg7fJLRNNXjOsR6ooDcca7PjU=
++github.com/opencontainers/runtime-spec v1.2.1-0.20240625190033-701738418b95/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
+ github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU=
+ github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
+ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+diff --git a/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go b/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go
+index d1236ba7..671f0d01 100644
+--- a/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go
++++ b/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go
+@@ -94,6 +94,8 @@ type Process struct {
+ 	SelinuxLabel string `json:"selinuxLabel,omitempty" platform:"linux"`
+ 	// IOPriority contains the I/O priority settings for the cgroup.
+ 	IOPriority *LinuxIOPriority `json:"ioPriority,omitempty" platform:"linux"`
++	// ExecCPUAffinity specifies CPU affinity for exec processes.
++	ExecCPUAffinity *CPUAffinity `json:"execCPUAffinity,omitempty" platform:"linux"`
+ }
+ 
+ // LinuxCapabilities specifies the list of allowed capabilities that are kept for a process.
+@@ -127,6 +129,12 @@ const (
+ 	IOPRIO_CLASS_IDLE IOPriorityClass = "IOPRIO_CLASS_IDLE"
+ )
+ 
++// CPUAffinity specifies process' CPU affinity.
++type CPUAffinity struct {
++	Initial string `json:"initial,omitempty"`
++	Final   string `json:"final,omitempty"`
++}
++
+ // Box specifies dimensions of a rectangle. Used for specifying the size of a console.
+ type Box struct {
+ 	// Height is the vertical dimension of a box.
+diff --git a/vendor/github.com/opencontainers/runtime-spec/specs-go/version.go b/vendor/github.com/opencontainers/runtime-spec/specs-go/version.go
+index 503971e0..f6c15f6c 100644
+--- a/vendor/github.com/opencontainers/runtime-spec/specs-go/version.go
++++ b/vendor/github.com/opencontainers/runtime-spec/specs-go/version.go
+@@ -11,7 +11,7 @@ const (
+ 	VersionPatch = 0
+ 
+ 	// VersionDev indicates development branch. Releases will be empty string.
+-	VersionDev = ""
++	VersionDev = "+dev"
+ )
+ 
+ // Version is the specification version that the package types support.
+diff --git a/vendor/modules.txt b/vendor/modules.txt
+index 3b245e0d..df520923 100644
+--- a/vendor/modules.txt
++++ b/vendor/modules.txt
+@@ -46,7 +46,7 @@ github.com/moby/sys/userns
+ # github.com/mrunalp/fileutils v0.5.1
+ ## explicit; go 1.13
+ github.com/mrunalp/fileutils
+-# github.com/opencontainers/runtime-spec v1.2.0
++# github.com/opencontainers/runtime-spec v1.2.1-0.20240625190033-701738418b95
+ ## explicit
+ github.com/opencontainers/runtime-spec/specs-go
+ github.com/opencontainers/runtime-spec/specs-go/features
+-- 
+2.47.1
+

SOURCES/0001-Revert-Apply-cgroups-earlier.patch

@@ -1,62 +0,0 @@
-From dfb3496c174377b860b62872ce6af951364cc3ac Mon Sep 17 00:00:00 2001
-From: Lokesh Mandvekar <lsm5@fedoraproject.org>
-Date: Tue, 12 Dec 2017 13:22:42 +0530
-Subject: [PATCH] Revert "Apply cgroups earlier"
-
-This reverts commit 7062c7556b71188abc18d7516441ff4b03fbc1fc.
----
- libcontainer/process_linux.go | 31 ++++++++++++++-----------------
- 1 file changed, 14 insertions(+), 17 deletions(-)
-
-diff --git a/libcontainer/process_linux.go b/libcontainer/process_linux.go
-index 149b1126..b8a395af 100644
---- a/libcontainer/process_linux.go
-+++ b/libcontainer/process_linux.go
-@@ -272,6 +272,20 @@ func (p *initProcess) start() error {
- 		p.process.ops = nil
- 		return newSystemErrorWithCause(err, "starting init process command")
- 	}
-+	if _, err := io.Copy(p.parentPipe, p.bootstrapData); err != nil {
-+		return newSystemErrorWithCause(err, "copying bootstrap data to pipe")
-+	}
-+	if err := p.execSetns(); err != nil {
-+		return newSystemErrorWithCause(err, "running exec setns process for init")
-+	}
-+	// Save the standard descriptor names before the container process
-+	// can potentially move them (e.g., via dup2()).  If we don't do this now,
-+	// we won't know at checkpoint time which file descriptor to look up.
-+	fds, err := getPipeFds(p.pid())
-+	if err != nil {
-+		return newSystemErrorWithCausef(err, "getting pipe fds for pid %d", p.pid())
-+	}
-+	p.setExternalDescriptors(fds)
- 	// Do this before syncing with child so that no children can escape the
- 	// cgroup. We don't need to worry about not doing this and not being root
- 	// because we'd be using the rootless cgroup manager in that case.
-@@ -292,23 +306,6 @@ func (p *initProcess) start() error {
- 			}
- 		}
- 	}()
--
--	if _, err := io.Copy(p.parentPipe, p.bootstrapData); err != nil {
--		return newSystemErrorWithCause(err, "copying bootstrap data to pipe")
--	}
--
--	if err := p.execSetns(); err != nil {
--		return newSystemErrorWithCause(err, "running exec setns process for init")
--	}
--
--	// Save the standard descriptor names before the container process
--	// can potentially move them (e.g., via dup2()).  If we don't do this now,
--	// we won't know at checkpoint time which file descriptor to look up.
--	fds, err := getPipeFds(p.pid())
--	if err != nil {
--		return newSystemErrorWithCausef(err, "getting pipe fds for pid %d", p.pid())
--	}
--	p.setExternalDescriptors(fds)
- 	if err := p.createNetworkInterfaces(); err != nil {
- 		return newSystemErrorWithCause(err, "creating network interfaces")
- 	}
--- 
-2.14.3
-

SOURCES/0001-nsenter-clone-proc-self-exe-to-avoid-exposing-host-b-runc.patch

@@ -1,290 +0,0 @@
-From bf6405284aa3870a39b402309003633a1c230ed9 Mon Sep 17 00:00:00 2001
-From: Aleksa Sarai <asarai@suse.de>
-Date: Wed, 9 Jan 2019 13:40:01 +1100
-Subject: [PATCH 1/1] nsenter: clone /proc/self/exe to avoid exposing host
- binary to container
-
-There are quite a few circumstances where /proc/self/exe pointing to a
-pretty important container binary is a _bad_ thing, so to avoid this we
-have to make a copy (preferably doing self-clean-up and not being
-writeable).
-
-As a hotfix we require memfd_create(2), but we can always extend this to
-use a scratch MNT_DETACH overlayfs or tmpfs. The main downside to this
-approach is no page-cache sharing for the runc binary (which overlayfs
-would give us) but this is far less complicated.
-
-This is only done during nsenter so that it happens transparently to the
-Go code, and any libcontainer users benefit from it. This also makes
-ExtraFiles and --preserve-fds handling trivial (because we don't need to
-worry about it).
-
-Fixes: CVE-2019-5736
-Co-developed-by: Christian Brauner <christian.brauner@ubuntu.com>
-Signed-off-by: Aleksa Sarai <asarai@suse.de>
-Signed-off-by: Mrunal Patel <mrunalp@gmail.com>
----
- libcontainer/nsenter/cloned_binary.c | 221 +++++++++++++++++++++++++++
- libcontainer/nsenter/nsexec.c        |  11 ++
- 2 files changed, 232 insertions(+)
- create mode 100644 libcontainer/nsenter/cloned_binary.c
-
-diff --git a/libcontainer/nsenter/cloned_binary.c b/libcontainer/nsenter/cloned_binary.c
-new file mode 100644
-index 00000000..d9f6093a
---- /dev/null
-+++ b/libcontainer/nsenter/cloned_binary.c
-@@ -0,0 +1,221 @@
-+#define _GNU_SOURCE
-+#include <unistd.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <stdbool.h>
-+#include <string.h>
-+#include <limits.h>
-+#include <fcntl.h>
-+#include <errno.h>
-+
-+#include <sys/types.h>
-+#include <sys/stat.h>
-+#include <sys/vfs.h>
-+#include <sys/mman.h>
-+#include <sys/sendfile.h>
-+#include <sys/syscall.h>
-+
-+#include <linux/magic.h>
-+#include <linux/memfd.h>
-+
-+/* Use our own wrapper for memfd_create. */
-+#if !defined(SYS_memfd_create) && defined(__NR_memfd_create)
-+#  define SYS_memfd_create __NR_memfd_create
-+#endif
-+#ifndef SYS_memfd_create
-+#  error "memfd_create(2) syscall not supported by this glibc version"
-+#endif
-+int memfd_create(const char *name, unsigned int flags)
-+{
-+	return syscall(SYS_memfd_create, name, flags);
-+}
-+
-+/* This comes directly from <linux/fcntl.h>. */
-+#ifndef F_LINUX_SPECIFIC_BASE
-+#  define F_LINUX_SPECIFIC_BASE 1024
-+#endif
-+#ifndef F_ADD_SEALS
-+#  define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
-+#  define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
-+#endif
-+#ifndef F_SEAL_SEAL
-+#  define F_SEAL_SEAL   0x0001	/* prevent further seals from being set */
-+#  define F_SEAL_SHRINK 0x0002	/* prevent file from shrinking */
-+#  define F_SEAL_GROW   0x0004	/* prevent file from growing */
-+#  define F_SEAL_WRITE  0x0008	/* prevent writes */
-+#endif
-+
-+
-+#define OUR_MEMFD_COMMENT "runc_cloned:/proc/self/exe"
-+#define OUR_MEMFD_SEALS \
-+	(F_SEAL_SEAL | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_WRITE)
-+
-+static void *must_realloc(void *ptr, size_t size)
-+{
-+	void *old = ptr;
-+	do {
-+		ptr = realloc(old, size);
-+	} while(!ptr);
-+	return ptr;
-+}
-+
-+/*
-+ * Verify whether we are currently in a self-cloned program (namely, is
-+ * /proc/self/exe a memfd). F_GET_SEALS will only succeed for memfds (or rather
-+ * for shmem files), and we want to be sure it's actually sealed.
-+ */
-+static int is_self_cloned(void)
-+{
-+	int fd, seals;
-+
-+	fd = open("/proc/self/exe", O_RDONLY|O_CLOEXEC);
-+	if (fd < 0)
-+		return -ENOTRECOVERABLE;
-+
-+	seals = fcntl(fd, F_GET_SEALS);
-+	close(fd);
-+	return seals == OUR_MEMFD_SEALS;
-+}
-+
-+/*
-+ * Basic wrapper around mmap(2) that gives you the file length so you can
-+ * safely treat it as an ordinary buffer. Only gives you read access.
-+ */
-+static char *read_file(char *path, size_t *length)
-+{
-+	int fd;
-+	char buf[4096], *copy = NULL;
-+
-+	if (!length)
-+		return NULL;
-+
-+	fd = open(path, O_RDONLY | O_CLOEXEC);
-+	if (fd < 0)
-+		return NULL;
-+
-+	*length = 0;
-+	for (;;) {
-+		int n;
-+
-+		n = read(fd, buf, sizeof(buf));
-+		if (n < 0)
-+			goto error;
-+		if (!n)
-+			break;
-+
-+		copy = must_realloc(copy, (*length + n) * sizeof(*copy));
-+		memcpy(copy + *length, buf, n);
-+		*length += n;
-+	}
-+	close(fd);
-+	return copy;
-+
-+error:
-+	close(fd);
-+	free(copy);
-+	return NULL;
-+}
-+
-+/*
-+ * A poor-man's version of "xargs -0". Basically parses a given block of
-+ * NUL-delimited data, within the given length and adds a pointer to each entry
-+ * to the array of pointers.
-+ */
-+static int parse_xargs(char *data, int data_length, char ***output)
-+{
-+	int num = 0;
-+	char *cur = data;
-+
-+	if (!data || *output != NULL)
-+		return -1;
-+
-+	while (cur < data + data_length) {
-+		num++;
-+		*output = must_realloc(*output, (num + 1) * sizeof(**output));
-+		(*output)[num - 1] = cur;
-+		cur += strlen(cur) + 1;
-+	}
-+	(*output)[num] = NULL;
-+	return num;
-+}
-+
-+/*
-+ * "Parse" out argv and envp from /proc/self/cmdline and /proc/self/environ.
-+ * This is necessary because we are running in a context where we don't have a
-+ * main() that we can just get the arguments from.
-+ */
-+static int fetchve(char ***argv, char ***envp)
-+{
-+	char *cmdline = NULL, *environ = NULL;
-+	size_t cmdline_size, environ_size;
-+
-+	cmdline = read_file("/proc/self/cmdline", &cmdline_size);
-+	if (!cmdline)
-+		goto error;
-+	environ = read_file("/proc/self/environ", &environ_size);
-+	if (!environ)
-+		goto error;
-+
-+	if (parse_xargs(cmdline, cmdline_size, argv) <= 0)
-+		goto error;
-+	if (parse_xargs(environ, environ_size, envp) <= 0)
-+		goto error;
-+
-+	return 0;
-+
-+error:
-+	free(environ);
-+	free(cmdline);
-+	return -EINVAL;
-+}
-+
-+#define SENDFILE_MAX 0x7FFFF000 /* sendfile(2) is limited to 2GB. */
-+static int clone_binary(void)
-+{
-+	int binfd, memfd, err;
-+	ssize_t sent = 0;
-+
-+	memfd = memfd_create(OUR_MEMFD_COMMENT, MFD_CLOEXEC | MFD_ALLOW_SEALING);
-+	if (memfd < 0)
-+		return -ENOTRECOVERABLE;
-+
-+	binfd = open("/proc/self/exe", O_RDONLY | O_CLOEXEC);
-+	if (binfd < 0)
-+		goto error;
-+
-+	sent = sendfile(memfd, binfd, NULL, SENDFILE_MAX);
-+	close(binfd);
-+	if (sent < 0)
-+		goto error;
-+
-+	err = fcntl(memfd, F_ADD_SEALS, OUR_MEMFD_SEALS);
-+	if (err < 0)
-+		goto error;
-+
-+	return memfd;
-+
-+error:
-+	close(memfd);
-+	return -EIO;
-+}
-+
-+int ensure_cloned_binary(void)
-+{
-+	int execfd;
-+	char **argv = NULL, **envp = NULL;
-+
-+	/* Check that we're not self-cloned, and if we are then bail. */
-+	int cloned = is_self_cloned();
-+	if (cloned > 0 || cloned == -ENOTRECOVERABLE)
-+		return cloned;
-+
-+	if (fetchve(&argv, &envp) < 0)
-+		return -EINVAL;
-+
-+	execfd = clone_binary();
-+	if (execfd < 0)
-+		return -EIO;
-+
-+	fexecve(execfd, argv, envp);
-+	return -ENOEXEC;
-+}
-diff --git a/libcontainer/nsenter/nsexec.c b/libcontainer/nsenter/nsexec.c
-index cb224314..784fd9b0 100644
---- a/libcontainer/nsenter/nsexec.c
-+++ b/libcontainer/nsenter/nsexec.c
-@@ -528,6 +528,9 @@ void join_namespaces(char *nslist)
- 	free(namespaces);
- }
- 
-+/* Defined in cloned_binary.c. */
-+int ensure_cloned_binary(void);
-+
- void nsexec(void)
- {
- 	int pipenum;
-@@ -543,6 +546,14 @@ void nsexec(void)
- 	if (pipenum == -1)
- 		return;
- 
-+	/*
-+	 * We need to re-exec if we are not in a cloned binary. This is necessary
-+	 * to ensure that containers won't be able to access the host binary
-+	 * through /proc/self/exe. See CVE-2019-5736.
-+	 */
-+	if (ensure_cloned_binary() < 0)
-+		bail("could not ensure we are a cloned binary");
-+
- 	/* Parse all of the netlink configuration. */
- 	nl_parse(pipenum, &config);
- 
--- 
-2.20.1
-

SOURCES/0002-runc-exec-implement-CPU-affinity.patch

@@ -0,0 +1,521 @@
+From 73786942b7176eae1e676cf2f78af548f090e418 Mon Sep 17 00:00:00 2001
+From: Kir Kolyshkin <kolyshkin@gmail.com>
+Date: Mon, 21 Oct 2024 15:50:38 -0700
+Subject: [PATCH 2/2] runc exec: implement CPU affinity
+
+As per
+- https://github.com/opencontainers/runtime-spec/pull/1253
+- https://github.com/opencontainers/runtime-spec/pull/1261
+
+CPU affinity can be set in two ways:
+1. When creating/starting a container, in config.json's
+   Process.ExecCPUAffinity, which is when applied to all execs.
+2. When running an exec, in process.json's CPUAffinity, which
+   applied to a given exec and overrides the value from (1).
+
+Add some basic tests.
+
+Note that older kernels (RHEL8, Ubuntu 20.04) change CPU affinity of a
+process to that of a container's cgroup, as soon as it is moved to that
+cgroup, while newer kernels (Ubuntu 24.04, Fedora 41) don't do that.
+
+Because of the above,
+ - it's impossible to really test initial CPU affinity without adding
+   debug logging to libcontainer/nsenter;
+ - for older kernels, there can be a brief moment when exec's affinity
+   is different than either initial or final affinity being set;
+ - exec's final CPU affinity, if not specified, can be different
+   depending on the kernel, therefore we don't test it.
+
+Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
+(cherry picked from commit 57237b31de367a722c5d49088912d57c28c6fb46)
+Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
+---
+ libcontainer/configs/config.go      |  72 ++++++++++++++++++++
+ libcontainer/container_linux.go     |   4 ++
+ libcontainer/init_linux.go          |   3 +-
+ libcontainer/nsenter/log.c          |   9 ++-
+ libcontainer/nsenter/log.h          |   3 +
+ libcontainer/nsenter/nsexec.c       |  29 ++++++++
+ libcontainer/process.go             |   2 +
+ libcontainer/process_linux.go       |  49 +++++++++++++-
+ libcontainer/specconv/spec_linux.go |   5 ++
+ tests/integration/cpu_affinity.bats | 101 ++++++++++++++++++++++++++++
+ utils_linux.go                      |   6 ++
+ 11 files changed, 277 insertions(+), 6 deletions(-)
+ create mode 100644 tests/integration/cpu_affinity.bats
+
+diff --git a/libcontainer/configs/config.go b/libcontainer/configs/config.go
+index 22fe0f9b..daffd130 100644
+--- a/libcontainer/configs/config.go
++++ b/libcontainer/configs/config.go
+@@ -3,8 +3,11 @@ package configs
+ import (
+ 	"bytes"
+ 	"encoding/json"
++	"errors"
+ 	"fmt"
+ 	"os/exec"
++	"strconv"
++	"strings"
+ 	"time"
+ 
+ 	"github.com/sirupsen/logrus"
+@@ -225,6 +228,9 @@ type Config struct {
+ 
+ 	// IOPriority is the container's I/O priority.
+ 	IOPriority *IOPriority `json:"io_priority,omitempty"`
++
++	// ExecCPUAffinity is CPU affinity for a non-init process to be run in the container.
++	ExecCPUAffinity *CPUAffinity `json:"exec_cpu_affinity,omitempty"`
+ }
+ 
+ // Scheduler is based on the Linux sched_setattr(2) syscall.
+@@ -294,6 +300,72 @@ var IOPrioClassMapping = map[specs.IOPriorityClass]int{
+ 
+ type IOPriority = specs.LinuxIOPriority
+ 
++type CPUAffinity struct {
++	Initial, Final *unix.CPUSet
++}
++
++func toCPUSet(str string) (*unix.CPUSet, error) {
++	if str == "" {
++		return nil, nil
++	}
++	s := new(unix.CPUSet)
++	for _, r := range strings.Split(str, ",") {
++		// Allow extra spaces around.
++		r = strings.TrimSpace(r)
++		// Allow empty elements (extra commas).
++		if r == "" {
++			continue
++		}
++		if r0, r1, found := strings.Cut(r, "-"); found {
++			start, err := strconv.ParseUint(r0, 10, 32)
++			if err != nil {
++				return nil, err
++			}
++			end, err := strconv.ParseUint(r1, 10, 32)
++			if err != nil {
++				return nil, err
++			}
++			if start > end {
++				return nil, errors.New("invalid range: " + r)
++			}
++			for i := int(start); i <= int(end); i++ {
++				s.Set(i)
++			}
++		} else {
++			val, err := strconv.ParseUint(r, 10, 32)
++			if err != nil {
++				return nil, err
++			}
++			s.Set(int(val))
++		}
++	}
++
++	return s, nil
++}
++
++// ConvertCPUAffinity converts [specs.CPUAffinity] to [CPUAffinity].
++func ConvertCPUAffinity(sa *specs.CPUAffinity) (*CPUAffinity, error) {
++	if sa == nil {
++		return nil, nil
++	}
++	initial, err := toCPUSet(sa.Initial)
++	if err != nil {
++		return nil, fmt.Errorf("bad CPUAffinity.Initial: %w", err)
++	}
++	final, err := toCPUSet(sa.Final)
++	if err != nil {
++		return nil, fmt.Errorf("bad CPUAffinity.Final: %w", err)
++	}
++	if initial == nil && final == nil {
++		return nil, nil
++	}
++
++	return &CPUAffinity{
++		Initial: initial,
++		Final:   final,
++	}, nil
++}
++
+ type (
+ 	HookName string
+ 	HookList []Hook
+diff --git a/libcontainer/container_linux.go b/libcontainer/container_linux.go
+index c0211617..1fc590a5 100644
+--- a/libcontainer/container_linux.go
++++ b/libcontainer/container_linux.go
+@@ -692,6 +692,7 @@ func (c *Container) newInitConfig(process *Process) *initConfig {
+ 		AppArmorProfile:  c.config.AppArmorProfile,
+ 		ProcessLabel:     c.config.ProcessLabel,
+ 		Rlimits:          c.config.Rlimits,
++		CPUAffinity:      c.config.ExecCPUAffinity,
+ 		CreateConsole:    process.ConsoleSocket != nil,
+ 		ConsoleWidth:     process.ConsoleWidth,
+ 		ConsoleHeight:    process.ConsoleHeight,
+@@ -708,6 +709,9 @@ func (c *Container) newInitConfig(process *Process) *initConfig {
+ 	if len(process.Rlimits) > 0 {
+ 		cfg.Rlimits = process.Rlimits
+ 	}
++	if process.CPUAffinity != nil {
++		cfg.CPUAffinity = process.CPUAffinity
++	}
+ 	if cgroups.IsCgroup2UnifiedMode() {
+ 		cfg.Cgroup2Path = c.cgroupManager.Path("")
+ 	}
+diff --git a/libcontainer/init_linux.go b/libcontainer/init_linux.go
+index 1eb0279d..eddbfba6 100644
+--- a/libcontainer/init_linux.go
++++ b/libcontainer/init_linux.go
+@@ -72,6 +72,7 @@ type initConfig struct {
+ 	RootlessCgroups  bool                  `json:"rootless_cgroups,omitempty"`
+ 	SpecState        *specs.State          `json:"spec_state,omitempty"`
+ 	Cgroup2Path      string                `json:"cgroup2_path,omitempty"`
++	CPUAffinity      *configs.CPUAffinity  `json:"cpu_affinity,omitempty"`
+ }
+ 
+ // Init is part of "runc init" implementation.
+@@ -151,7 +152,7 @@ func startInitialization() (retErr error) {
+ 
+ 	logrus.SetOutput(logPipe)
+ 	logrus.SetFormatter(new(logrus.JSONFormatter))
+-	logrus.Debug("child process in init()")
++	logrus.Debugf("child process in init()")
+ 
+ 	// Only init processes have FIFOFD.
+ 	var fifoFile *os.File
+diff --git a/libcontainer/nsenter/log.c b/libcontainer/nsenter/log.c
+index 086b5398..72774cb0 100644
+--- a/libcontainer/nsenter/log.c
++++ b/libcontainer/nsenter/log.c
+@@ -31,6 +31,11 @@ void setup_logpipe(void)
+ 	loglevel = i;
+ }
+ 
++bool log_enabled_for(int level)
++{
++	return (logfd >= 0 && level <= loglevel);
++}
++
+ /* Defined in nsexec.c */
+ extern int current_stage;
+ 
+@@ -40,8 +45,8 @@ void write_log(int level, const char *format, ...)
+ 	va_list args;
+ 	int ret;
+ 
+-	if (logfd < 0 || level > loglevel)
+-		goto out;
++	if (!log_enabled_for(level))
++		return;
+ 
+ 	va_start(args, format);
+ 	ret = vasprintf(&message, format, args);
+diff --git a/libcontainer/nsenter/log.h b/libcontainer/nsenter/log.h
+index 1fe95a11..3e18de68 100644
+--- a/libcontainer/nsenter/log.h
++++ b/libcontainer/nsenter/log.h
+@@ -1,6 +1,7 @@
+ #ifndef NSENTER_LOG_H
+ #define NSENTER_LOG_H
+ 
++#include <stdbool.h>
+ #include <stdio.h>
+ 
+ /*
+@@ -20,6 +21,8 @@
+  */
+ void setup_logpipe(void);
+ 
++bool log_enabled_for(int level);
++
+ void write_log(int level, const char *format, ...) __attribute__((format(printf, 2, 3)));
+ 
+ extern int logfd;
+diff --git a/libcontainer/nsenter/nsexec.c b/libcontainer/nsenter/nsexec.c
+index 565b2ca2..aa4976d6 100644
+--- a/libcontainer/nsenter/nsexec.c
++++ b/libcontainer/nsenter/nsexec.c
+@@ -558,6 +558,25 @@ static void update_timens_offsets(pid_t pid, char *map, size_t map_len)
+ 		bail("failed to update /proc/%d/timens_offsets", pid);
+ }
+ 
++void print_cpu_affinity()
++{
++	cpu_set_t cpus = { };
++	size_t i, mask = 0;
++
++	if (sched_getaffinity(0, sizeof(cpus), &cpus) < 0) {
++		write_log(WARNING, "sched_getaffinity: %m");
++		return;
++	}
++
++	/* Do not print the complete mask, we only need a few first CPUs. */
++	for (i = 0; i < sizeof(mask) * 8; i++) {
++		if (CPU_ISSET(i, &cpus))
++			mask |= 1 << i;
++	}
++
++	write_log(DEBUG, "affinity: 0x%zx", mask);
++}
++
+ void nsexec(void)
+ {
+ 	int pipenum;
+@@ -584,6 +603,16 @@ void nsexec(void)
+ 
+ 	write_log(DEBUG, "=> nsexec container setup");
+ 
++	/* This is for ../../tests/integration/cpu_affinity.bats test only.
++	 *
++	 * Printing this from Go code might be too late as some kernels
++	 * change the process' CPU affinity to that of container's cpuset
++	 * as soon as the process is moved into container's cgroup.
++	 */
++	if (log_enabled_for(DEBUG)) {
++		print_cpu_affinity();
++	}
++
+ 	/* Parse all of the netlink configuration. */
+ 	nl_parse(pipenum, &config);
+ 
+diff --git a/libcontainer/process.go b/libcontainer/process.go
+index 114b3f2b..5339583f 100644
+--- a/libcontainer/process.go
++++ b/libcontainer/process.go
+@@ -102,6 +102,8 @@ type Process struct {
+ 	Scheduler *configs.Scheduler
+ 
+ 	IOPriority *configs.IOPriority
++
++	CPUAffinity *configs.CPUAffinity
+ }
+ 
+ // Wait waits for the process to exit.
+diff --git a/libcontainer/process_linux.go b/libcontainer/process_linux.go
+index fcbb54a3..477c8a77 100644
+--- a/libcontainer/process_linux.go
++++ b/libcontainer/process_linux.go
+@@ -122,6 +122,46 @@ func (p *setnsProcess) signal(sig os.Signal) error {
+ 	return unix.Kill(p.pid(), s)
+ }
+ 
++// Starts setns process with specified initial CPU affinity.
++func (p *setnsProcess) startWithCPUAffinity() error {
++	aff := p.config.CPUAffinity
++	if aff == nil || aff.Initial == nil {
++		return p.cmd.Start()
++	}
++	errCh := make(chan error)
++	defer close(errCh)
++
++	// Use a goroutine to dedicate an OS thread.
++	go func() {
++		runtime.LockOSThread()
++		// Command inherits the CPU affinity.
++		if err := unix.SchedSetaffinity(unix.Gettid(), aff.Initial); err != nil {
++			runtime.UnlockOSThread()
++			errCh <- fmt.Errorf("error setting initial CPU affinity: %w", err)
++			return
++		}
++
++		errCh <- p.cmd.Start()
++		// Deliberately omit runtime.UnlockOSThread here.
++		// https://pkg.go.dev/runtime#LockOSThread says:
++		// "If the calling goroutine exits without unlocking the
++		// thread, the thread will be terminated".
++	}()
++
++	return <-errCh
++}
++
++func (p *setnsProcess) setFinalCPUAffinity() error {
++	aff := p.config.CPUAffinity
++	if aff == nil || aff.Final == nil {
++		return nil
++	}
++	if err := unix.SchedSetaffinity(p.pid(), aff.Final); err != nil {
++		return fmt.Errorf("error setting final CPU affinity: %w", err)
++	}
++	return nil
++}
++
+ func (p *setnsProcess) start() (retErr error) {
+ 	defer p.comm.closeParent()
+ 
+@@ -133,8 +173,8 @@ func (p *setnsProcess) start() (retErr error) {
+ 
+ 	// get the "before" value of oom kill count
+ 	oom, _ := p.manager.OOMKillCount()
+-	err := p.cmd.Start()
+-	// close the child-side of the pipes (controlled by child)
++	err := p.startWithCPUAffinity()
++	// Close the child-side of the pipes (controlled by child).
+ 	p.comm.closeChild()
+ 	if err != nil {
+ 		return fmt.Errorf("error starting setns process: %w", err)
+@@ -184,6 +224,10 @@ func (p *setnsProcess) start() (retErr error) {
+ 			}
+ 		}
+ 	}
++	// Set final CPU affinity right after the process is moved into container's cgroup.
++	if err := p.setFinalCPUAffinity(); err != nil {
++		return err
++	}
+ 	if p.intelRdtPath != "" {
+ 		// if Intel RDT "resource control" filesystem path exists
+ 		_, err := os.Stat(p.intelRdtPath)
+@@ -193,7 +237,6 @@ func (p *setnsProcess) start() (retErr error) {
+ 			}
+ 		}
+ 	}
+-
+ 	if err := utils.WriteJSON(p.comm.initSockParent, p.config); err != nil {
+ 		return fmt.Errorf("error writing config to pipe: %w", err)
+ 	}
+diff --git a/libcontainer/specconv/spec_linux.go b/libcontainer/specconv/spec_linux.go
+index 95ada499..2d0db342 100644
+--- a/libcontainer/specconv/spec_linux.go
++++ b/libcontainer/specconv/spec_linux.go
+@@ -556,6 +556,11 @@ func CreateLibcontainerConfig(opts *CreateOpts) (*configs.Config, error) {
+ 			ioPriority := *spec.Process.IOPriority
+ 			config.IOPriority = &ioPriority
+ 		}
++		config.ExecCPUAffinity, err = configs.ConvertCPUAffinity(spec.Process.ExecCPUAffinity)
++		if err != nil {
++			return nil, err
++		}
++
+ 	}
+ 	createHooks(spec, config)
+ 	config.Version = specs.Version
+diff --git a/tests/integration/cpu_affinity.bats b/tests/integration/cpu_affinity.bats
+new file mode 100644
+index 00000000..f6adfa2a
+--- /dev/null
++++ b/tests/integration/cpu_affinity.bats
+@@ -0,0 +1,101 @@
++#!/usr/bin/env bats
++# Exec CPU affinity tests. For more details, see:
++#  - https://github.com/opencontainers/runtime-spec/pull/1253
++
++load helpers
++
++function setup() {
++	requires smp cgroups_cpuset
++	setup_busybox
++}
++
++function teardown() {
++	teardown_bundle
++}
++
++function first_cpu() {
++	sed 's/[-,].*//g' </sys/devices/system/cpu/online
++}
++
++# Convert list of cpus ("0,1" or "0-1") to mask as printed by nsexec.
++# NOTE the range conversion is not proper, merely sufficient for tests here.
++function cpus_to_mask() {
++	local cpus=$* mask=0
++
++	cpus=${cpus//,/-} # 1. "," --> "-".
++	cpus=${cpus//-/ } # 2. "-" --> " ".
++
++	for c in $cpus; do
++		mask=$((mask | 1 << c))
++	done
++
++	printf "0x%x" $mask
++}
++
++@test "runc exec [CPU affinity, only initial set from process.json]" {
++	first="$(first_cpu)"
++	second=$((first + 1)) # Hacky; might not work in all environments.
++
++	runc run -d --console-socket "$CONSOLE_SOCKET" ct1
++	[ "$status" -eq 0 ]
++
++	for cpus in "$second" "$first-$second" "$first,$second" "$first"; do
++		proc='
++{
++    "terminal": false,
++    "execCPUAffinity": {
++	    "initial": "'$cpus'"
++    },
++    "args": [ "/bin/true" ],
++    "cwd": "/"
++}'
++		mask=$(cpus_to_mask "$cpus")
++		echo "CPUS: $cpus, mask: $mask"
++		runc --debug exec --process <(echo "$proc") ct1
++		[[ "$output" == *"nsexec"*": affinity: $mask"* ]]
++	done
++}
++
++@test "runc exec [CPU affinity, initial and final set from process.json]" {
++	first="$(first_cpu)"
++	second=$((first + 1)) # Hacky; might not work in all environments.
++
++	runc run -d --console-socket "$CONSOLE_SOCKET" ct1
++	[ "$status" -eq 0 ]
++
++	for cpus in "$second" "$first-$second" "$first,$second" "$first"; do
++		proc='
++{
++    "terminal": false,
++    "execCPUAffinity": {
++	    "initial": "'$cpus'",
++	    "final": "'$cpus'"
++    },
++    "args": [ "/bin/grep", "-F", "Cpus_allowed_list:", "/proc/self/status" ],
++    "cwd": "/"
++}'
++		mask=$(cpus_to_mask "$cpus")
++		exp=${cpus//,/-} # "," --> "-".
++		echo "CPUS: $cpus, mask: $mask, final: $exp"
++		runc --debug exec --process <(echo "$proc") ct1
++		[[ "$output" == *"nsexec"*": affinity: $mask"* ]]
++		[[ "$output" == *"Cpus_allowed_list:	$exp"* ]] # Mind the literal tab.
++	done
++}
++
++@test "runc exec [CPU affinity, initial and final set from config.json]" {
++	initial="$(first_cpu)"
++	final=$((initial + 1)) # Hacky; might not work in all environments.
++
++	update_config "	  .process.execCPUAffinity.initial = \"$initial\"
++			| .process.execCPUAffinity.final = \"$final\""
++
++	runc run -d --console-socket "$CONSOLE_SOCKET" ct1
++	[ "$status" -eq 0 ]
++
++	runc --debug exec ct1 grep "Cpus_allowed_list:" /proc/self/status
++	[ "$status" -eq 0 ]
++	mask=$(cpus_to_mask "$initial")
++	[[ "$output" == *"nsexec"*": affinity: $mask"* ]]
++	[[ "$output" == *"Cpus_allowed_list:	$final"* ]] # Mind the literal tab.
++}
+diff --git a/utils_linux.go b/utils_linux.go
+index feb6ef80..013dbcf4 100644
+--- a/utils_linux.go
++++ b/utils_linux.go
+@@ -90,6 +90,12 @@ func newProcess(p specs.Process) (*libcontainer.Process, error) {
+ 		}
+ 		lp.Rlimits = append(lp.Rlimits, rl)
+ 	}
++	aff, err := configs.ConvertCPUAffinity(p.ExecCPUAffinity)
++	if err != nil {
++		return nil, err
++	}
++	lp.CPUAffinity = aff
++
+ 	return lp, nil
+ }
+ 
+-- 
+2.47.1
+

SOURCES/1807.patch

@@ -1,200 +0,0 @@
-From ecf53c23545092019602578583031c28fde4d2a1 Mon Sep 17 00:00:00 2001
-From: Giuseppe Scrivano <gscrivan@redhat.com>
-Date: Fri, 25 May 2018 18:04:06 +0200
-Subject: [PATCH] sd-notify: do not hang when NOTIFY_SOCKET is used with create
-
-if NOTIFY_SOCKET is used, do not block the main runc process waiting
-for events on the notify socket.  Change the logic to create a new
-process that monitors exclusively the notify socket until an event is
-received.
-
-Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
----
- init.go          |  12 +++++++
- notify_socket.go | 101 ++++++++++++++++++++++++++++++++++++++++++++++---------
- signals.go       |   5 +--
- 3 files changed, 99 insertions(+), 19 deletions(-)
-
-diff --git a/init.go b/init.go
-index c8f453192..6a3d9e91c 100644
---- a/init.go
-+++ b/init.go
-@@ -20,6 +20,18 @@ var initCommand = cli.Command{
- 	Name:  "init",
- 	Usage: `initialize the namespaces and launch the process (do not call it outside of runc)`,
- 	Action: func(context *cli.Context) error {
-+		// If NOTIFY_SOCKET is used create a new process that stays around
-+		// so to not block "runc start".  It will automatically exits when the
-+		// container notifies that it is ready, or when the container is deleted
-+		if os.Getenv("_NOTIFY_SOCKET_FD") != "" {
-+			fd := os.Getenv("_NOTIFY_SOCKET_FD")
-+			pid := os.Getenv("_NOTIFY_SOCKET_PID")
-+			hostNotifySocket := os.Getenv("_NOTIFY_SOCKET_HOST")
-+			notifySocketPath := os.Getenv("_NOTIFY_SOCKET_PATH")
-+			notifySocketInit(fd, pid, hostNotifySocket, notifySocketPath)
-+			os.Exit(0)
-+		}
-+
- 		factory, _ := libcontainer.New("")
- 		if err := factory.StartInitialization(); err != nil {
- 			// as the error is sent back to the parent there is no need to log
-diff --git a/notify_socket.go b/notify_socket.go
-index cd6c0a989..e04e9d660 100644
---- a/notify_socket.go
-+++ b/notify_socket.go
-@@ -6,10 +6,13 @@ import (
- 	"bytes"
- 	"fmt"
- 	"net"
-+	"os"
-+	"os/exec"
- 	"path/filepath"
-+	"strconv"
-+	"time"
- 
- 	"github.com/opencontainers/runtime-spec/specs-go"
--
- 	"github.com/sirupsen/logrus"
- 	"github.com/urfave/cli"
- )
-@@ -64,24 +67,94 @@ func (s *notifySocket) setupSocket() error {
- 	return nil
- }
- 
-+func (notifySocket *notifySocket) notifyNewPid(pid int) {
-+	notifySocketHostAddr := net.UnixAddr{Name: notifySocket.host, Net: "unixgram"}
-+	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
-+	if err != nil {
-+		return
-+	}
-+	newPid := fmt.Sprintf("MAINPID=%d\n", pid)
-+	client.Write([]byte(newPid))
-+}
-+
- // pid1 must be set only with -d, as it is used to set the new process as the main process
- // for the service in systemd
- func (notifySocket *notifySocket) run(pid1 int) {
--	buf := make([]byte, 512)
--	notifySocketHostAddr := net.UnixAddr{Name: notifySocket.host, Net: "unixgram"}
--	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
-+	file, err := notifySocket.socket.File()
- 	if err != nil {
- 		logrus.Error(err)
- 		return
- 	}
--	for {
--		r, err := notifySocket.socket.Read(buf)
--		if err != nil {
--			break
-+	defer file.Close()
-+	defer notifySocket.socket.Close()
-+
-+	cmd := exec.Command("/proc/self/exe", "init")
-+	cmd.ExtraFiles = []*os.File{file}
-+	cmd.Env = append(cmd.Env, "_NOTIFY_SOCKET_FD=3",
-+		fmt.Sprintf("_NOTIFY_SOCKET_PID=%d", pid1),
-+		fmt.Sprintf("_NOTIFY_SOCKET_HOST=%s", notifySocket.host),
-+		fmt.Sprintf("_NOTIFY_SOCKET_PATH=%s", notifySocket.socketPath))
-+
-+	if err := cmd.Start(); err != nil {
-+		logrus.Fatal(err)
-+	}
-+	notifySocket.notifyNewPid(cmd.Process.Pid)
-+	cmd.Process.Release()
-+}
-+
-+func notifySocketInit(envFd string, envPid string, notifySocketHost string, notifySocketPath string) {
-+	intFd, err := strconv.Atoi(envFd)
-+	if err != nil {
-+		return
-+	}
-+	pid1, err := strconv.Atoi(envPid)
-+	if err != nil {
-+		return
-+	}
-+
-+	file := os.NewFile(uintptr(intFd), "unixgram")
-+	defer file.Close()
-+
-+	fileChan := make(chan []byte)
-+	exitChan := make(chan bool)
-+
-+	go func() {
-+		for {
-+			buf := make([]byte, 512)
-+			r, err := file.Read(buf)
-+			if err != nil {
-+				return
-+			}
-+			fileChan <- buf[0:r]
- 		}
--		var out bytes.Buffer
--		for _, line := range bytes.Split(buf[0:r], []byte{'\n'}) {
--			if bytes.HasPrefix(line, []byte("READY=")) {
-+	}()
-+	go func() {
-+		for {
-+			if _, err := os.Stat(notifySocketPath); os.IsNotExist(err) {
-+				exitChan <- true
-+				return
-+			}
-+			time.Sleep(time.Second)
-+		}
-+	}()
-+
-+	notifySocketHostAddr := net.UnixAddr{Name: notifySocketHost, Net: "unixgram"}
-+	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
-+	if err != nil {
-+		return
-+	}
-+
-+	for {
-+		select {
-+		case <-exitChan:
-+			return
-+		case b := <-fileChan:
-+			for _, line := range bytes.Split(b, []byte{'\n'}) {
-+				if !bytes.HasPrefix(line, []byte("READY=")) {
-+					continue
-+				}
-+
-+				var out bytes.Buffer
- 				_, err = out.Write(line)
- 				if err != nil {
- 					return
-@@ -98,10 +171,8 @@ func (notifySocket *notifySocket) run(pid1 int) {
- 				}
- 
- 				// now we can inform systemd to use pid1 as the pid to monitor
--				if pid1 > 0 {
--					newPid := fmt.Sprintf("MAINPID=%d\n", pid1)
--					client.Write([]byte(newPid))
--				}
-+				newPid := fmt.Sprintf("MAINPID=%d\n", pid1)
-+				client.Write([]byte(newPid))
- 				return
- 			}
- 		}
-diff --git a/signals.go b/signals.go
-index 1811de837..d0988cb39 100644
---- a/signals.go
-+++ b/signals.go
-@@ -70,7 +70,7 @@ func (h *signalHandler) forward(process *libcontainer.Process, tty *tty, detach
- 			h.notifySocket.run(pid1)
- 			return 0, nil
- 		} else {
--			go h.notifySocket.run(0)
-+			h.notifySocket.run(os.Getpid())
- 		}
- 	}
- 
-@@ -98,9 +98,6 @@ func (h *signalHandler) forward(process *libcontainer.Process, tty *tty, detach
- 					// status because we must ensure that any of the go specific process
- 					// fun such as flushing pipes are complete before we return.
- 					process.Wait()
--					if h.notifySocket != nil {
--						h.notifySocket.Close()
--					}
- 					return e.status, nil
- 				}
- 			}

SOURCES/99-containers.conf

@@ -1 +0,0 @@
-fs.may_detach_mounts=1

SOURCES/change-default-root.patch

@@ -1,61 +0,0 @@
-diff --git a/list.go b/list.go
-index 0313d8c..328798b 100644
---- a/list.go
-+++ b/list.go
-@@ -50,7 +50,7 @@ var listCommand = cli.Command{
- 	ArgsUsage: `
- 
- Where the given root is specified via the global option "--root"
--(default: "/run/runc").
-+(default: "/run/runc-ctrs").
- 
- EXAMPLE 1:
- To list containers created via the default "--root":
-diff --git a/main.go b/main.go
-index 278399a..0f49fce 100644
---- a/main.go
-+++ b/main.go
-@@ -62,7 +62,7 @@ func main() {
- 	v = append(v, fmt.Sprintf("spec: %s", specs.Version))
- 	app.Version = strings.Join(v, "\n")
- 
--	root := "/run/runc"
-+	root := "/run/runc-ctrs"
- 	rootless, err := isRootless(nil)
- 	if err != nil {
- 		fatal(err)
-@@ -70,7 +70,7 @@ func main() {
- 	if rootless {
- 		runtimeDir := os.Getenv("XDG_RUNTIME_DIR")
- 		if runtimeDir != "" {
--			root = runtimeDir + "/runc"
-+			root = runtimeDir + "/runc-ctrs"
- 			// According to the XDG specification, we need to set anything in
- 			// XDG_RUNTIME_DIR to have a sticky bit if we don't want it to get
- 			// auto-pruned.
-diff --git a/man/runc-list.8.md b/man/runc-list.8.md
-index f737424..107220e 100644
---- a/man/runc-list.8.md
-+++ b/man/runc-list.8.md
-@@ -6,7 +6,7 @@
- 
- # EXAMPLE
- Where the given root is specified via the global option "--root"
--(default: "/run/runc").
-+(default: "/run/runc-ctrs").
- 
- To list containers created via the default "--root":
-        # runc list
-diff --git a/man/runc.8.md b/man/runc.8.md
-index 6d0ddff..337bc73 100644
---- a/man/runc.8.md
-+++ b/man/runc.8.md
-@@ -51,7 +51,7 @@ value for "bundle" is the current directory.
-    --debug              enable debug output for logging
-    --log value          set the log file path where internal debug information is written (default: "/dev/null")
-    --log-format value   set the format used by logs ('text' (default), or 'json') (default: "text")
--   --root value         root directory for storage of container state (this should be located in tmpfs) (default: "/run/runc" or $XDG_RUNTIME_DIR/runc for rootless containers)
-+   --root value         root directory for storage of container state (this should be located in tmpfs) (default: "/run/runc-ctrs" or $XDG_RUNTIME_DIR/runc-ctrs for rootless containers)
-    --criu value         path to the criu binary used for checkpoint and restore (default: "criu")
-    --systemd-cgroup     enable systemd cgroup support, expects cgroupsPath to be of form "slice:prefix:name" for e.g. "system.slice:runc:434234"
-    --rootless value    enable rootless mode ('true', 'false', or 'auto') (default: "auto")

SOURCES/pivot-root.patch

@@ -1,72 +0,0 @@
-From 28a697cce3e4f905dca700eda81d681a30eef9cd Mon Sep 17 00:00:00 2001
-From: Giuseppe Scrivano <gscrivan@redhat.com>
-Date: Fri, 11 Jan 2019 21:53:45 +0100
-Subject: [PATCH] rootfs: umount all procfs and sysfs with --no-pivot
-
-When creating a new user namespace, the kernel doesn't allow to mount
-a new procfs or sysfs file system if there is not already one instance
-fully visible in the current mount namespace.
-
-When using --no-pivot we were effectively inhibiting this protection
-from the kernel, as /proc and /sys from the host are still present in
-the container mount namespace.
-
-A container without full access to /proc could then create a new user
-namespace, and from there able to mount a fully visible /proc, bypassing
-the limitations in the container.
-
-A simple reproducer for this issue is:
-
-unshare -mrfp sh -c "mount -t proc none /proc && echo c > /proc/sysrq-trigger"
-
-Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
----
- libcontainer/rootfs_linux.go | 35 +++++++++++++++++++++++++++++++++++
- 1 file changed, 35 insertions(+)
-
-diff --git a/libcontainer/rootfs_linux.go b/libcontainer/rootfs_linux.go
-index e7c2f8ada..6bd6da74a 100644
---- a/libcontainer/rootfs_linux.go
-+++ b/libcontainer/rootfs_linux.go
-@@ -748,6 +748,41 @@ func pivotRoot(rootfs string) error {
- }
- 
- func msMoveRoot(rootfs string) error {
-+	mountinfos, err := mount.GetMounts()
-+	if err != nil {
-+		return err
-+	}
-+
-+	absRootfs, err := filepath.Abs(rootfs)
-+	if err != nil {
-+		return err
-+	}
-+
-+	for _, info := range mountinfos {
-+		p, err := filepath.Abs(info.Mountpoint)
-+		if err != nil {
-+			return err
-+		}
-+		// Umount every syfs and proc file systems, except those under the container rootfs
-+		if (info.Fstype != "proc" && info.Fstype != "sysfs") || filepath.HasPrefix(p, absRootfs) {
-+			continue
-+		}
-+		// Be sure umount events are not propagated to the host.
-+		if err := unix.Mount("", p, "", unix.MS_SLAVE|unix.MS_REC, ""); err != nil {
-+			return err
-+		}
-+		if err := unix.Unmount(p, unix.MNT_DETACH); err != nil {
-+			if err != unix.EINVAL && err != unix.EPERM {
-+				return err
-+			} else {
-+				// If we have not privileges for umounting (e.g. rootless), then
-+				// cover the path.
-+				if err := unix.Mount("tmpfs", p, "tmpfs", 0, ""); err != nil {
-+					return err
-+				}
-+			}
-+		}
-+	}
- 	if err := unix.Mount(rootfs, "/", "", unix.MS_MOVE, ""); err != nil {
- 		return err
- 	}