* [PATCH RFC v2 4/4] selftests/proc: add tests for new pidns APIs
From: Aleksa Sarai @ 2025-07-22 23:18 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Jonathan Corbet,
Shuah Khan
Cc: linux-kernel, linux-fsdevel, linux-api, linux-doc,
linux-kselftest, Aleksa Sarai
In-Reply-To: <20250723-procfs-pidns-api-v2-0-621e7edd8e40@cyphar.com>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
tools/testing/selftests/proc/.gitignore | 1 +
tools/testing/selftests/proc/Makefile | 1 +
tools/testing/selftests/proc/proc-pidns.c | 286 ++++++++++++++++++++++++++++++
3 files changed, 288 insertions(+)
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/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/selftests/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 += setns-sysvipc
TEST_GEN_PROGS += thread-self
TEST_GEN_PROGS += proc-multiple-procfs
TEST_GEN_PROGS += proc-fsconfig-hidepid
+TEST_GEN_PROGS += proc-pidns
include ../lib.mk
diff --git a/tools/testing/selftests/proc/proc-pidns.c b/tools/testing/selftests/proc/proc-pidns.c
new file mode 100644
index 000000000000..e7e34c78d383
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-pidns.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2025 SUSE LLC.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/prctl.h>
+
+#include "../kselftest_harness.h"
+
+#define bail(fmt, ...) \
+ do { \
+ fprintf(stderr, fmt ": %m", __VA_ARGS__); \
+ exit(1); \
+ } while (0)
+
+#define ASSERT_SUCCESS ASSERT_FALSE
+#define ASSERT_FAIL ASSERT_TRUE
+
+int touch(char *path)
+{
+ int fd = open(path, O_WRONLY|O_CREAT|O_CLOEXEC, 0644);
+ if (fd < 0 || close(fd) < 0)
+ return -errno;
+ return 0;
+}
+
+FIXTURE(ns)
+{
+ int host_mntns, host_pidns;
+ int dummy_pidns;
+};
+
+FIXTURE_SETUP(ns)
+{
+ /* Stash the old mntns. */
+ self->host_mntns = open("/proc/self/ns/mnt", O_RDONLY|O_CLOEXEC);
+ ASSERT_GE(self->host_mntns, 0);
+
+ /* 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 = open("/proc/self/ns/pid", O_RDONLY|O_CLOEXEC);
+ ASSERT_GE(self->host_pidns, 0);
+ ASSERT_SUCCESS(unshare(CLONE_NEWPID));
+
+ pid_t pid = fork();
+ ASSERT_GE(pid, 0);
+ if (!pid) {
+ prctl(PR_SET_PDEATHSIG, SIGKILL);
+ ASSERT_SUCCESS(mount("/proc/self/ns/pid", "/tmp/dummy-pidns", NULL, MS_BIND, 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 = open("/tmp/dummy-pidns", O_RDONLY|O_CLOEXEC);
+ ASSERT_GE(self->dummy_pidns, 0);
+}
+
+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=/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=/tmp/dummy-pidns"));
+ ASSERT_FAIL(access("/tmp/proc-dummy/1/", X_OK));
+ ASSERT_FAIL(access("/tmp/proc-dummy/self/", X_OK));
+}
+
+TEST_F(ns, pidns_fsconfig_string_path)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy-pidns", 0));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ ASSERT_FAIL(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_FAIL(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_F(ns, pidns_fsconfig_fd)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy_pidns));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ ASSERT_FAIL(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_FAIL(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/self/", X_OK));
+
+ ASSERT_SUCCESS(mount(NULL, "/tmp/proc", NULL, MS_REMOUNT, "pidns=/tmp/dummy-pidns"));
+ ASSERT_FAIL(access("/tmp/proc/self/", X_OK));
+}
+
+TEST_F(ns, pidns_reconfigure_fsconfig_string_path)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy-pidns", 0));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0));
+
+ ASSERT_FAIL(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_FAIL(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_F(ns, pidns_reconfigure_fsconfig_fd)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy_pidns));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0));
+
+ ASSERT_FAIL(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_FAIL(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) == 0);
+ assert(fstat(fd2, &stat2) == 0);
+
+ return stat1.st_ino == stat2.st_ino && stat1.st_dev == stat2.st_dev;
+}
+
+#define PROCFS_IOCTL_MAGIC 'f'
+#define PROCFS_GET_PID_NAMESPACE _IO(PROCFS_IOCTL_MAGIC, 1)
+
+TEST_F(ns, get_pidns_ioctl)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy_pidns));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ /* fsmount returns an O_PATH, which ioctl(2) doesn't accept. */
+ int new_mountfd = openat(mountfd, ".", O_RDONLY|O_DIRECTORY|O_CLOEXEC);
+ ASSERT_GE(new_mountfd, 0);
+
+ ASSERT_SUCCESS(close(mountfd));
+ mountfd = -EBADF;
+
+ int procfs_pidns = ioctl(new_mountfd, PROCFS_GET_PID_NAMESPACE);
+ ASSERT_GE(procfs_pidns, 0);
+
+ 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_F(ns, reconfigure_get_pidns_ioctl)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_GE(fsfd, 0);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_GE(mountfd, 0);
+
+ /* fsmount returns an O_PATH, which ioctl(2) doesn't accept. */
+ int new_mountfd = openat(mountfd, ".", O_RDONLY|O_DIRECTORY|O_CLOEXEC);
+ ASSERT_GE(new_mountfd, 0);
+
+ ASSERT_SUCCESS(close(mountfd));
+ mountfd = -EBADF;
+
+ int procfs_pidns1 = ioctl(new_mountfd, PROCFS_GET_PID_NAMESPACE);
+ ASSERT_GE(procfs_pidns1, 0);
+
+ ASSERT_NE(self->dummy_pidns, procfs_pidns1);
+ ASSERT_TRUE(is_same_inode(self->host_pidns, procfs_pidns1));
+ ASSERT_FALSE(is_same_inode(self->dummy_pidns, procfs_pidns1));
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy-pidns", 0));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0));
+
+ int procfs_pidns2 = ioctl(new_mountfd, PROCFS_GET_PID_NAMESPACE);
+ ASSERT_GE(procfs_pidns2, 0);
+
+ ASSERT_NE(self->dummy_pidns, procfs_pidns2);
+ ASSERT_FALSE(is_same_inode(self->host_pidns, procfs_pidns2));
+ ASSERT_TRUE(is_same_inode(self->dummy_pidns, procfs_pidns2));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(new_mountfd));
+ ASSERT_SUCCESS(close(procfs_pidns1));
+ ASSERT_SUCCESS(close(procfs_pidns2));
+}
+
+TEST_HARNESS_MAIN
--
2.50.0
^ permalink raw reply related
* Re: [PATCH v1 17/32] liveupdate: luo_sysfs: add sysfs state monitoring
From: Pasha Tatashin @ 2025-07-23 13:53 UTC (permalink / raw)
To: Randy Dunlap
Cc: pratyush, jasonmiu, graf, changyuanl, rppt, dmatlack, rientjes,
corbet, ilpo.jarvinen, kanie, ojeda, aliceryhl, masahiroy, akpm,
tj, yoann.congal, mmaurer, roman.gushchin, chenridong, axboe,
mark.rutland, jannh, vincent.guittot, hannes, dan.j.williams,
david, joel.granados, rostedt, anna.schumaker, song, zhangguopeng,
linux, linux-kernel, linux-doc, linux-mm, gregkh, tglx, mingo, bp,
dave.hansen, x86, hpa, rafael, dakr, bartosz.golaszewski,
cw00.choi, myungjoo.ham, yesanishhere, Jonathan.Cameron,
quic_zijuhu, aleksander.lobakin, ira.weiny, andriy.shevchenko,
leon, lukas, bhelgaas, wagi, djeffery, stuart.w.hayes, ptyadav,
lennart, brauner, linux-api, linux-fsdevel
In-Reply-To: <d6e44430-ec9c-4d77-a00b-15e97ab9beab@infradead.org>
On Thu, Jun 26, 2025 at 12:29 AM Randy Dunlap <rdunlap@infradead.org> wrote:
>
> Hi,
>
>
> On 6/25/25 4:18 PM, Pasha Tatashin wrote:
> > diff --git a/Documentation/ABI/testing/sysfs-kernel-liveupdate b/Documentation/ABI/testing/sysfs-kernel-liveupdate
> > new file mode 100644
> > index 000000000000..4cd4a4fe2f93
> > --- /dev/null
> > +++ b/Documentation/ABI/testing/sysfs-kernel-liveupdate
> > @@ -0,0 +1,51 @@
> > +What: /sys/kernel/liveupdate/
> > +Date: May 2025
> > +KernelVersion: 6.16.0
> > +Contact: pasha.tatashin@soleen.com
> > +Description: Directory containing interfaces to query the live
> > + update orchestrator. Live update is the ability to reboot the
> > + host kernel (e.g., via kexec, without a full power cycle) while
> > + keeping specifically designated devices operational ("alive")
> > + across the transition. After the new kernel boots, these devices
> > + can be re-attached to their original workloads (e.g., virtual
> > + machines) with their state preserved. This is particularly
> > + useful, for example, for quick hypervisor updates without
> > + terminating running virtual machines.
> > +
> > +
> > +What: /sys/kernel/liveupdate/state
> > +Date: May 2025
> > +KernelVersion: 6.16.0
> > +Contact: pasha.tatashin@soleen.com
> > +Description: Read-only file that displays the current state of the live
> > + update orchestrator as a string. Possible values are:
> > +
> > + "normal": No live update operation is in progress. This is
> > + the default operational state.
>
> Just an opinion, but the ':'s after each possible value aren't needed
> and just add noise.
Removed columns, thanks.
Pasha
^ permalink raw reply
* Re: [PATCH v1 21/32] liveupdate: add selftests for subsystems un/registration
From: Pasha Tatashin @ 2025-07-23 13:55 UTC (permalink / raw)
To: Randy Dunlap
Cc: pratyush, jasonmiu, graf, changyuanl, rppt, dmatlack, rientjes,
corbet, ilpo.jarvinen, kanie, ojeda, aliceryhl, masahiroy, akpm,
tj, yoann.congal, mmaurer, roman.gushchin, chenridong, axboe,
mark.rutland, jannh, vincent.guittot, hannes, dan.j.williams,
david, joel.granados, rostedt, anna.schumaker, song, zhangguopeng,
linux, linux-kernel, linux-doc, linux-mm, gregkh, tglx, mingo, bp,
dave.hansen, x86, hpa, rafael, dakr, bartosz.golaszewski,
cw00.choi, myungjoo.ham, yesanishhere, Jonathan.Cameron,
quic_zijuhu, aleksander.lobakin, ira.weiny, andriy.shevchenko,
leon, lukas, bhelgaas, wagi, djeffery, stuart.w.hayes, ptyadav,
lennart, brauner, linux-api, linux-fsdevel
In-Reply-To: <829fa3b2-58be-493f-b26c-8d68063b96ed@infradead.org>
On Thu, Jun 26, 2025 at 12:06 AM Randy Dunlap <rdunlap@infradead.org> wrote:
>
>
>
> On 6/25/25 4:18 PM, Pasha Tatashin wrote:
> > diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig
> > index 75a17ca8a592..db7bbff3edec 100644
> > --- a/kernel/liveupdate/Kconfig
> > +++ b/kernel/liveupdate/Kconfig
> > @@ -47,6 +47,21 @@ config LIVEUPDATE_SYSFS_API
> >
> > If unsure, say N.
> >
> > +config LIVEUPDATE_SELFTESTS
> > + bool "Live Update Orchestrator - self tests"
>
> self-tests"
>
> as below...
Done.
^ permalink raw reply
* Re: [PATCH v1 25/32] mm: shmem: use SHMEM_F_* flags instead of VM_* flags
From: Pasha Tatashin @ 2025-07-23 14:08 UTC (permalink / raw)
To: Pratyush Yadav
Cc: jasonmiu, graf, changyuanl, rppt, dmatlack, rientjes, corbet,
rdunlap, ilpo.jarvinen, kanie, ojeda, aliceryhl, masahiroy, akpm,
tj, yoann.congal, mmaurer, roman.gushchin, chenridong, axboe,
mark.rutland, jannh, vincent.guittot, hannes, dan.j.williams,
david, joel.granados, rostedt, anna.schumaker, song, zhangguopeng,
linux, linux-kernel, linux-doc, linux-mm, gregkh, tglx, mingo, bp,
dave.hansen, x86, hpa, rafael, dakr, bartosz.golaszewski,
cw00.choi, myungjoo.ham, yesanishhere, Jonathan.Cameron,
quic_zijuhu, aleksander.lobakin, ira.weiny, andriy.shevchenko,
leon, lukas, bhelgaas, wagi, djeffery, stuart.w.hayes, lennart,
brauner, linux-api, linux-fsdevel
In-Reply-To: <mafs01pr6u06u.fsf@kernel.org>
On Thu, Jun 26, 2025 at 1:01 PM Pratyush Yadav <pratyush@kernel.org> wrote:
>
> Hi all,
>
> On Wed, Jun 25 2025, Pasha Tatashin wrote:
>
> > From: Pratyush Yadav <ptyadav@amazon.de>
> >
> > shmem_inode_info::flags can have the VM flags VM_NORESERVE and
> > VM_LOCKED. These are used to suppress pre-accounting or to lock the
> > pages in the inode respectively. Using the VM flags directly makes it
> > difficult to add shmem-specific flags that are unrelated to VM behavior
> > since one would need to find a VM flag not used by shmem and re-purpose
> > it.
> >
> > Introduce SHMEM_F_NORESERVE and SHMEM_F_LOCKED which represent the same
> > information, but their bits are independent of the VM flags. Callers can
> > still pass VM_NORESERVE to shmem_get_inode(), but it gets transformed to
> > the shmem-specific flag internally.
> >
> > No functional changes intended.
>
> I was reading through this patch again and just realized that I missed a
> spot. __shmem_file_setup() passes VM flags to shmem_{un,}acct_size(),
> even though it now expects SHMEM_F flag. Below fixup patch should fix
> that.
Added for v2.
Pasha
^ permalink raw reply
* Re: [PATCH v1 03/32] kho: warn if KHO is disabled due to an error
From: Pasha Tatashin @ 2025-07-23 14:39 UTC (permalink / raw)
To: Randy Dunlap
Cc: pratyush, jasonmiu, graf, changyuanl, rppt, dmatlack, rientjes,
corbet, ilpo.jarvinen, kanie, ojeda, aliceryhl, masahiroy, akpm,
tj, yoann.congal, mmaurer, roman.gushchin, chenridong, axboe,
mark.rutland, jannh, vincent.guittot, hannes, dan.j.williams,
david, joel.granados, rostedt, anna.schumaker, song, zhangguopeng,
linux, linux-kernel, linux-doc, linux-mm, gregkh, tglx, mingo, bp,
dave.hansen, x86, hpa, rafael, dakr, bartosz.golaszewski,
cw00.choi, myungjoo.ham, yesanishhere, Jonathan.Cameron,
quic_zijuhu, aleksander.lobakin, ira.weiny, andriy.shevchenko,
leon, lukas, bhelgaas, wagi, djeffery, stuart.w.hayes, ptyadav,
lennart, brauner, linux-api, linux-fsdevel
In-Reply-To: <ac8efa08-3f85-4532-8762-573ebd258ca7@infradead.org>
On Wed, Jun 25, 2025 at 11:57 PM Randy Dunlap <rdunlap@infradead.org> wrote:
>
>
>
> On 6/25/25 4:17 PM, Pasha Tatashin wrote:
> > During boot scratch area is allocated based on command line
> > parameters or auto calculated. However, scratch area may fail
> > to allocate, and in that case KHO is disabled. Currently,
> > no warning is printed that KHO is disabled, which makes it
> > confusing for the end user to figure out why KHO is not
> > available. Add the missing warning message.
>
> Are users even going to know what "KHO" means in the warning message?
Changed warning to: Failed to reserve scratch area, disabling kexec handover
>
> >
> > Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
> > ---
> > kernel/kexec_handover.c | 1 +
> > 1 file changed, 1 insertion(+)
> >
> > diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
> > index 1ff6b242f98c..069d5890841c 100644
> > --- a/kernel/kexec_handover.c
> > +++ b/kernel/kexec_handover.c
> > @@ -565,6 +565,7 @@ static void __init kho_reserve_scratch(void)
> > err_free_scratch_desc:
> > memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
> > err_disable_kho:
> > + pr_warn("Failed to reserve scratch area, disabling KHO\n");
> > kho_enable = false;
> > }
> >
>
> --
> ~Randy
>
^ permalink raw reply
* [PATCH v2 00/32] Live Update Orchestrator
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
This series introduces the LUO, a kernel subsystem designed to
facilitate live kernel updates with minimal downtime,
particularly in cloud delplyoments aiming to update without fully
disrupting running virtual machines.
This series builds upon KHO framework by adding programmatic
control over KHO's lifecycle and leveraging KHO for persisting LUO's
own metadata across the kexec boundary. The git branch for this series
can be found at:
https://github.com/googleprodkernel/linux-liveupdate/tree/luo/v2
Changelog from v1:
- Addressed comments from Randy Dunlap
- Fix from Pratyush Yadav for missing vm_flags update
- v1 submission had mail-server issue, hopefully it is resolved in v2.
Changelog from rfc-v2:
- Addressed review comments from Mike Rapoport, Pratyush Yadav,
David Matlack
- Moved everything under kernel/liveupdate including KHO.
- Added a number fixes to KHO that were discovered.
- luo_files is not a registred as a subsystem.
- Added sessions support to preserved files.
- Added support for memfd (Pratyush Yadav)
- Added libluo (proposed as RFC) (Pratyush Yadav)
- Removed notifiers from KHO (Mike Rapoport)
What is Live Update?
Live Update is a kexec based reboot process where selected kernel
resources (memory, file descriptors, and eventually devices) are kept
operational or their state preserved across a kernel transition. For
certain resources, DMA and interrupt activity might continue with
minimal interruption during the kernel reboot.
LUO provides a framework for coordinating live updates. It features:
State Machine: Manages the live update process through states:
NORMAL, PREPARED, FROZEN, UPDATED.
KHO Integration:
LUO programmatically drives KHO's finalization and abort sequences.
KHO's debugfs interface is now optional configured via
CONFIG_KEXEC_HANDOVER_DEBUG.
LUO preserves its own metadata via KHO's kho_add_subtree and
kho_preserve_phys() mechanisms.
Subsystem Participation: A callback API liveupdate_register_subsystem()
allows kernel subsystems (e.g., KVM, IOMMU, VFIO, PCI) to register
handlers for LUO events (PREPARE, FREEZE, FINISH, CANCEL) and persist a
u64 payload via the LUO FDT.
File Descriptor Preservation: Infrastructure
liveupdate_register_filesystem, luo_register_file, luo_retrieve_file to
allow specific types of file descriptors (e.g., memfd, vfio) to be
preserved and restored.
Handlers for specific file types can be registered to manage their
preservation and restoration, storing a u64 payload in the LUO FDT.
User-space Interface:
ioctl (/dev/liveupdate): The primary control interface for
triggering LUO state transitions (prepare, freeze, finish, cancel)
and managing the preservation/restoration of file descriptors.
Access requires CAP_SYS_ADMIN.
sysfs (/sys/kernel/liveupdate/state): A read-only interface for
monitoring the current LUO state. This allows userspace services to
track progress and coordinate actions.
Selftests: Includes kernel-side hooks and userspace selftests to
verify core LUO functionality, particularly subsystem registration and
basic state transitions.
LUO State Machine and Events:
NORMAL: Default operational state.
PREPARED: Initial preparation complete after LIVEUPDATE_PREPARE
event. Subsystems have saved initial state.
FROZEN: Final "blackout window" state after LIVEUPDATE_FREEZE
event, just before kexec. Workloads must be suspended.
UPDATED: Next kernel has booted via live update. Awaiting restoration
and LIVEUPDATE_FINISH.
Events:
LIVEUPDATE_PREPARE: Prepare for reboot, serialize state.
LIVEUPDATE_FREEZE: Final opportunity to save state before kexec.
LIVEUPDATE_FINISH: Post-reboot cleanup in the next kernel.
LIVEUPDATE_CANCEL: Abort prepare or freeze, revert changes.
v1: https://lore.kernel.org/all/20250625231838.1897085-1-pasha.tatashin@soleen.com
RFC v2: https://lore.kernel.org/all/20250515182322.117840-1-pasha.tatashin@soleen.com
RFC v1: https://lore.kernel.org/all/20250320024011.2995837-1-pasha.tatashin@soleen.com
Changyuan Lyu (1):
kho: add interfaces to unpreserve folios and physical memory ranges
Mike Rapoport (Microsoft) (1):
kho: drop notifiers
Pasha Tatashin (22):
kho: init new_physxa->phys_bits to fix lockdep
kho: mm: Don't allow deferred struct page with KHO
kho: warn if KHO is disabled due to an error
kho: allow to drive kho from within kernel
kho: make debugfs interface optional
kho: don't unpreserve memory during abort
liveupdate: kho: move to kernel/liveupdate
liveupdate: luo_core: Live Update Orchestrator
liveupdate: luo_core: integrate with KHO
liveupdate: luo_subsystems: add subsystem registration
liveupdate: luo_subsystems: implement subsystem callbacks
liveupdate: luo_files: add infrastructure for FDs
liveupdate: luo_files: implement file systems callbacks
liveupdate: luo_ioctl: add ioctl interface
liveupdate: luo_sysfs: add sysfs state monitoring
reboot: call liveupdate_reboot() before kexec
liveupdate: luo_files: luo_ioctl: session-based file descriptor
tracking
kho: move kho debugfs directory to liveupdate
liveupdate: add selftests for subsystems un/registration
selftests/liveupdate: add subsystem/state tests
docs: add luo documentation
MAINTAINERS: add liveupdate entry
Pratyush Yadav (8):
mm: shmem: use SHMEM_F_* flags instead of VM_* flags
mm: shmem: allow freezing inode mapping
mm: shmem: export some functions to internal.h
luo: allow preserving memfd
docs: add documentation for memfd preservation via LUO
tools: introduce libluo
libluo: introduce luoctl
libluo: add tests
.../ABI/testing/sysfs-kernel-liveupdate | 51 +
Documentation/admin-guide/index.rst | 1 +
Documentation/admin-guide/liveupdate.rst | 16 +
Documentation/core-api/index.rst | 1 +
Documentation/core-api/kho/concepts.rst | 2 +-
Documentation/core-api/liveupdate.rst | 57 ++
Documentation/mm/index.rst | 1 +
Documentation/mm/memfd_preservation.rst | 138 +++
Documentation/userspace-api/index.rst | 1 +
.../userspace-api/ioctl/ioctl-number.rst | 2 +
Documentation/userspace-api/liveupdate.rst | 25 +
MAINTAINERS | 20 +-
include/linux/kexec_handover.h | 53 +-
include/linux/liveupdate.h | 235 +++++
include/linux/shmem_fs.h | 23 +
include/uapi/linux/liveupdate.h | 265 +++++
init/Kconfig | 2 +
kernel/Kconfig.kexec | 14 -
kernel/Makefile | 2 +-
kernel/liveupdate/Kconfig | 90 ++
kernel/liveupdate/Makefile | 13 +
kernel/{ => liveupdate}/kexec_handover.c | 556 +++++-----
kernel/liveupdate/kexec_handover_debug.c | 222 ++++
kernel/liveupdate/kexec_handover_internal.h | 45 +
kernel/liveupdate/luo_core.c | 525 ++++++++++
kernel/liveupdate/luo_files.c | 946 ++++++++++++++++++
kernel/liveupdate/luo_internal.h | 47 +
kernel/liveupdate/luo_ioctl.c | 192 ++++
kernel/liveupdate/luo_selftests.c | 344 +++++++
kernel/liveupdate/luo_selftests.h | 84 ++
kernel/liveupdate/luo_subsystems.c | 420 ++++++++
kernel/liveupdate/luo_sysfs.c | 92 ++
kernel/reboot.c | 4 +
mm/Makefile | 1 +
mm/internal.h | 6 +
mm/memblock.c | 56 +-
mm/memfd_luo.c | 501 ++++++++++
mm/shmem.c | 52 +-
tools/lib/luo/LICENSE | 165 +++
tools/lib/luo/Makefile | 45 +
tools/lib/luo/README.md | 166 +++
tools/lib/luo/cli/.gitignore | 1 +
tools/lib/luo/cli/Makefile | 18 +
tools/lib/luo/cli/luoctl.c | 178 ++++
tools/lib/luo/include/libluo.h | 128 +++
tools/lib/luo/include/liveupdate.h | 265 +++++
tools/lib/luo/libluo.c | 203 ++++
tools/lib/luo/tests/.gitignore | 1 +
tools/lib/luo/tests/Makefile | 18 +
tools/lib/luo/tests/test.c | 848 ++++++++++++++++
tools/testing/selftests/Makefile | 1 +
tools/testing/selftests/liveupdate/.gitignore | 1 +
tools/testing/selftests/liveupdate/Makefile | 7 +
tools/testing/selftests/liveupdate/config | 6 +
.../testing/selftests/liveupdate/liveupdate.c | 356 +++++++
55 files changed, 7095 insertions(+), 417 deletions(-)
create mode 100644 Documentation/ABI/testing/sysfs-kernel-liveupdate
create mode 100644 Documentation/admin-guide/liveupdate.rst
create mode 100644 Documentation/core-api/liveupdate.rst
create mode 100644 Documentation/mm/memfd_preservation.rst
create mode 100644 Documentation/userspace-api/liveupdate.rst
create mode 100644 include/linux/liveupdate.h
create mode 100644 include/uapi/linux/liveupdate.h
create mode 100644 kernel/liveupdate/Kconfig
create mode 100644 kernel/liveupdate/Makefile
rename kernel/{ => liveupdate}/kexec_handover.c (74%)
create mode 100644 kernel/liveupdate/kexec_handover_debug.c
create mode 100644 kernel/liveupdate/kexec_handover_internal.h
create mode 100644 kernel/liveupdate/luo_core.c
create mode 100644 kernel/liveupdate/luo_files.c
create mode 100644 kernel/liveupdate/luo_internal.h
create mode 100644 kernel/liveupdate/luo_ioctl.c
create mode 100644 kernel/liveupdate/luo_selftests.c
create mode 100644 kernel/liveupdate/luo_selftests.h
create mode 100644 kernel/liveupdate/luo_subsystems.c
create mode 100644 kernel/liveupdate/luo_sysfs.c
create mode 100644 mm/memfd_luo.c
create mode 100644 tools/lib/luo/LICENSE
create mode 100644 tools/lib/luo/Makefile
create mode 100644 tools/lib/luo/README.md
create mode 100644 tools/lib/luo/cli/.gitignore
create mode 100644 tools/lib/luo/cli/Makefile
create mode 100644 tools/lib/luo/cli/luoctl.c
create mode 100644 tools/lib/luo/include/libluo.h
create mode 100644 tools/lib/luo/include/liveupdate.h
create mode 100644 tools/lib/luo/libluo.c
create mode 100644 tools/lib/luo/tests/.gitignore
create mode 100644 tools/lib/luo/tests/Makefile
create mode 100644 tools/lib/luo/tests/test.c
create mode 100644 tools/testing/selftests/liveupdate/.gitignore
create mode 100644 tools/testing/selftests/liveupdate/Makefile
create mode 100644 tools/testing/selftests/liveupdate/config
create mode 100644 tools/testing/selftests/liveupdate/liveupdate.c
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply
* [PATCH v2 01/32] kho: init new_physxa->phys_bits to fix lockdep
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Lockdep shows the following warning:
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe
you didn't initialize this object before use?
turning off the locking correctness validator.
[<ffffffff810133a6>] dump_stack_lvl+0x66/0xa0
[<ffffffff8136012c>] assign_lock_key+0x10c/0x120
[<ffffffff81358bb4>] register_lock_class+0xf4/0x2f0
[<ffffffff813597ff>] __lock_acquire+0x7f/0x2c40
[<ffffffff81360cb0>] ? __pfx_hlock_conflict+0x10/0x10
[<ffffffff811707be>] ? native_flush_tlb_global+0x8e/0xa0
[<ffffffff8117096e>] ? __flush_tlb_all+0x4e/0xa0
[<ffffffff81172fc2>] ? __kernel_map_pages+0x112/0x140
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff81359556>] lock_acquire+0xe6/0x280
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff8100b9e0>] _raw_spin_lock+0x30/0x40
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff813ec327>] xa_load_or_alloc+0x67/0xe0
[<ffffffff813eb4c0>] kho_preserve_folio+0x90/0x100
[<ffffffff813ebb7f>] __kho_finalize+0xcf/0x400
[<ffffffff813ebef4>] kho_finalize+0x34/0x70
This is becase xa has its own lock, that is not initialized in
xa_load_or_alloc.
Modifiy __kho_preserve_order(), to properly call
xa_init(&new_physxa->phys_bits);
Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/kexec_handover.c | 29 +++++++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 5a21dbe17950..1ff6b242f98c 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -144,14 +144,35 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
unsigned int order)
{
struct kho_mem_phys_bits *bits;
- struct kho_mem_phys *physxa;
+ struct kho_mem_phys *physxa, *new_physxa;
const unsigned long pfn_high = pfn >> order;
might_sleep();
- physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa));
- if (IS_ERR(physxa))
- return PTR_ERR(physxa);
+ physxa = xa_load(&track->orders, order);
+ if (!physxa) {
+ new_physxa = kzalloc(sizeof(*physxa), GFP_KERNEL);
+ if (!new_physxa)
+ return -ENOMEM;
+
+ xa_init(&new_physxa->phys_bits);
+ physxa = xa_cmpxchg(&track->orders, order, NULL, new_physxa,
+ GFP_KERNEL);
+ if (xa_is_err(physxa)) {
+ int err_ret = xa_err(physxa);
+
+ xa_destroy(&new_physxa->phys_bits);
+ kfree(new_physxa);
+
+ return err_ret;
+ }
+ if (physxa) {
+ xa_destroy(&new_physxa->phys_bits);
+ kfree(new_physxa);
+ } else {
+ physxa = new_physxa;
+ }
+ }
bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
sizeof(*bits));
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 02/32] kho: mm: Don't allow deferred struct page with KHO
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
KHO uses struct pages for the preserved memory early in boot, however,
with deferred struct page initialization, only a small portion of
memory has properly initialized struct pages.
This problem was detected where vmemmap is poisoned, and illegal flag
combinations are detected.
Don't allow them to be enabled together, and later we will have to
teach KHO to work properly with deferred struct page init kernel
feature.
Fixes: 990a950fe8fd ("kexec: add config option for KHO")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/Kconfig.kexec | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 2ee603a98813..1224dd937df0 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -97,6 +97,7 @@ config KEXEC_JUMP
config KEXEC_HANDOVER
bool "kexec handover"
depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+ depends on !DEFERRED_STRUCT_PAGE_INIT
select MEMBLOCK_KHO_SCRATCH
select KEXEC_FILE
select DEBUG_FS
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 03/32] kho: warn if KHO is disabled due to an error
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
During boot scratch area is allocated based on command line
parameters or auto calculated. However, scratch area may fail
to allocate, and in that case KHO is disabled. Currently,
no warning is printed that KHO is disabled, which makes it
confusing for the end user to figure out why KHO is not
available. Add the missing warning message.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/kexec_handover.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 1ff6b242f98c..368e23db0a17 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -565,6 +565,7 @@ static void __init kho_reserve_scratch(void)
err_free_scratch_desc:
memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
err_disable_kho:
+ pr_warn("Failed to reserve scratch area, disabling kexec handover\n");
kho_enable = false;
}
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 04/32] kho: allow to drive kho from within kernel
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Allow to do finalize and abort from kernel modules, so LUO could
drive the KHO sequence via its own state machine.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/kexec_handover.h | 15 +++++++++
kernel/kexec_handover.c | 58 ++++++++++++++++++++++++++++++++--
2 files changed, 71 insertions(+), 2 deletions(-)
diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index 348844cffb13..f98565def593 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -54,6 +54,10 @@ void kho_memory_init(void);
void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
u64 scratch_len);
+
+int kho_finalize(void);
+int kho_abort(void);
+
#else
static inline bool kho_is_enabled(void)
{
@@ -104,6 +108,17 @@ static inline void kho_populate(phys_addr_t fdt_phys, u64 fdt_len,
phys_addr_t scratch_phys, u64 scratch_len)
{
}
+
+static inline int kho_finalize(void)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int kho_abort(void)
+{
+ return -EOPNOTSUPP;
+}
+
#endif /* CONFIG_KEXEC_HANDOVER */
#endif /* LINUX_KEXEC_HANDOVER_H */
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 368e23db0a17..c6ccc8e0705d 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -757,7 +757,7 @@ static int kho_out_update_debugfs_fdt(void)
return err;
}
-static int kho_abort(void)
+static int __kho_abort(void)
{
int err;
unsigned long order;
@@ -790,7 +790,34 @@ static int kho_abort(void)
return err;
}
-static int kho_finalize(void)
+int kho_abort(void)
+{
+ int ret = 0;
+
+ if (!kho_enable)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&kho_out.lock);
+
+ if (!kho_out.finalized) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+
+ ret = __kho_abort();
+ if (ret)
+ goto unlock;
+
+ kho_out.finalized = false;
+ ret = kho_out_update_debugfs_fdt();
+
+unlock:
+ mutex_unlock(&kho_out.lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kho_abort);
+
+static int __kho_finalize(void)
{
int err = 0;
u64 *preserved_mem_map;
@@ -839,6 +866,33 @@ static int kho_finalize(void)
return err;
}
+int kho_finalize(void)
+{
+ int ret = 0;
+
+ if (!kho_enable)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&kho_out.lock);
+
+ if (kho_out.finalized) {
+ ret = -EEXIST;
+ goto unlock;
+ }
+
+ ret = __kho_finalize();
+ if (ret)
+ goto unlock;
+
+ kho_out.finalized = true;
+ ret = kho_out_update_debugfs_fdt();
+
+unlock:
+ mutex_unlock(&kho_out.lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kho_finalize);
+
static int kho_out_finalize_get(void *data, u64 *val)
{
mutex_lock(&kho_out.lock);
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 05/32] kho: make debugfs interface optional
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Currently, KHO is controlled via debugfs interface, but once LUO is
introduced, it can control KHO, and the debug interface becomes
optional.
Add a separate config CONFIG_KEXEC_HANDOVER_DEBUG that enables
the debugfs interface, and allows to inspect the tree.
Move all debugfs related code to a new file to keep the .c files
clear of ifdefs.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
MAINTAINERS | 3 +-
kernel/Kconfig.kexec | 10 ++
kernel/Makefile | 1 +
kernel/kexec_handover.c | 278 ++++---------------------------
kernel/kexec_handover_debug.c | 218 ++++++++++++++++++++++++
kernel/kexec_handover_internal.h | 44 +++++
6 files changed, 311 insertions(+), 243 deletions(-)
create mode 100644 kernel/kexec_handover_debug.c
create mode 100644 kernel/kexec_handover_internal.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 10850512c118..00de7c78de86 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13349,13 +13349,14 @@ KEXEC HANDOVER (KHO)
M: Alexander Graf <graf@amazon.com>
M: Mike Rapoport <rppt@kernel.org>
M: Changyuan Lyu <changyuanl@google.com>
+M: Pasha Tatashin <pasha.tatashin@soleen.com>
L: kexec@lists.infradead.org
L: linux-mm@kvack.org
S: Maintained
F: Documentation/admin-guide/mm/kho.rst
F: Documentation/core-api/kho/*
F: include/linux/kexec_handover.h
-F: kernel/kexec_handover.c
+F: kernel/kexec_handover*
KEYS-ENCRYPTED
M: Mimi Zohar <zohar@linux.ibm.com>
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 1224dd937df0..9968d3d4dd17 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -109,6 +109,16 @@ config KEXEC_HANDOVER
to keep data or state alive across the kexec. For this to work,
both source and target kernels need to have this option enabled.
+config KEXEC_HANDOVER_DEBUG
+ bool "kexec handover debug interface"
+ depends on KEXEC_HANDOVER
+ depends on DEBUG_FS
+ help
+ Allow to control kexec handover device tree via debugfs
+ interface, i.e. finalize the state or aborting the finalization.
+ Also, enables inspecting the KHO fdt trees with the debugfs binary
+ blobs.
+
config CRASH_DUMP
bool "kernel crash dumps"
default ARCH_DEFAULT_CRASH_DUMP
diff --git a/kernel/Makefile b/kernel/Makefile
index 32e80dd626af..e4b4afa86a70 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o
obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
+obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_CGROUPS) += cgroup/
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index c6ccc8e0705d..32fdc388752b 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -10,7 +10,6 @@
#include <linux/cma.h>
#include <linux/count_zeros.h>
-#include <linux/debugfs.h>
#include <linux/kexec.h>
#include <linux/kexec_handover.h>
#include <linux/libfdt.h>
@@ -27,6 +26,7 @@
*/
#include "../mm/internal.h"
#include "kexec_internal.h"
+#include "kexec_handover_internal.h"
#define KHO_FDT_COMPATIBLE "kho-v1"
#define PROP_PRESERVED_MEMORY_MAP "preserved-memory-map"
@@ -84,8 +84,6 @@ struct khoser_mem_chunk;
struct kho_serialization {
struct page *fdt;
- struct list_head fdt_list;
- struct dentry *sub_fdt_dir;
struct kho_mem_track track;
/* First chunk of serialized preserved memory map */
struct khoser_mem_chunk *preserved_mem_map;
@@ -381,8 +379,8 @@ static void __init kho_mem_deserialize(const void *fdt)
* area for early allocations that happen before page allocator is
* initialized.
*/
-static struct kho_scratch *kho_scratch;
-static unsigned int kho_scratch_cnt;
+struct kho_scratch *kho_scratch;
+unsigned int kho_scratch_cnt;
/*
* The scratch areas are scaled by default as percent of memory allocated from
@@ -569,36 +567,24 @@ static void __init kho_reserve_scratch(void)
kho_enable = false;
}
-struct fdt_debugfs {
- struct list_head list;
- struct debugfs_blob_wrapper wrapper;
- struct dentry *file;
+struct kho_out {
+ struct blocking_notifier_head chain_head;
+ struct mutex lock; /* protects KHO FDT finalization */
+ struct kho_serialization ser;
+ bool finalized;
+ struct kho_debugfs dbg;
};
-static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir,
- const char *name, const void *fdt)
-{
- struct fdt_debugfs *f;
- struct dentry *file;
-
- f = kmalloc(sizeof(*f), GFP_KERNEL);
- if (!f)
- return -ENOMEM;
-
- f->wrapper.data = (void *)fdt;
- f->wrapper.size = fdt_totalsize(fdt);
-
- file = debugfs_create_blob(name, 0400, dir, &f->wrapper);
- if (IS_ERR(file)) {
- kfree(f);
- return PTR_ERR(file);
- }
-
- f->file = file;
- list_add(&f->list, list);
-
- return 0;
-}
+static struct kho_out kho_out = {
+ .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
+ .lock = __MUTEX_INITIALIZER(kho_out.lock),
+ .ser = {
+ .track = {
+ .orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
+ },
+ },
+ .finalized = false,
+};
/**
* kho_add_subtree - record the physical address of a sub FDT in KHO root tree.
@@ -611,7 +597,8 @@ static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir,
* by KHO for the new kernel to retrieve it after kexec.
*
* A debugfs blob entry is also created at
- * ``/sys/kernel/debug/kho/out/sub_fdts/@name``.
+ * ``/sys/kernel/debug/kho/out/sub_fdts/@name`` when kernel is configured with
+ * CONFIG_KEXEC_HANDOVER_DEBUG
*
* Return: 0 on success, error code on failure
*/
@@ -628,33 +615,10 @@ int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
if (err)
return err;
- return kho_debugfs_fdt_add(&ser->fdt_list, ser->sub_fdt_dir, name, fdt);
+ return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
}
EXPORT_SYMBOL_GPL(kho_add_subtree);
-struct kho_out {
- struct blocking_notifier_head chain_head;
-
- struct dentry *dir;
-
- struct mutex lock; /* protects KHO FDT finalization */
-
- struct kho_serialization ser;
- bool finalized;
-};
-
-static struct kho_out kho_out = {
- .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
- .lock = __MUTEX_INITIALIZER(kho_out.lock),
- .ser = {
- .fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
- .track = {
- .orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
- },
- },
- .finalized = false,
-};
-
int register_kho_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&kho_out.chain_head, nb);
@@ -734,29 +698,6 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
}
EXPORT_SYMBOL_GPL(kho_preserve_phys);
-/* Handling for debug/kho/out */
-
-static struct dentry *debugfs_root;
-
-static int kho_out_update_debugfs_fdt(void)
-{
- int err = 0;
- struct fdt_debugfs *ff, *tmp;
-
- if (kho_out.finalized) {
- err = kho_debugfs_fdt_add(&kho_out.ser.fdt_list, kho_out.dir,
- "fdt", page_to_virt(kho_out.ser.fdt));
- } else {
- list_for_each_entry_safe(ff, tmp, &kho_out.ser.fdt_list, list) {
- debugfs_remove(ff->file);
- list_del(&ff->list);
- kfree(ff);
- }
- }
-
- return err;
-}
-
static int __kho_abort(void)
{
int err;
@@ -809,7 +750,8 @@ int kho_abort(void)
goto unlock;
kho_out.finalized = false;
- ret = kho_out_update_debugfs_fdt();
+
+ kho_debugfs_cleanup(&kho_out.dbg);
unlock:
mutex_unlock(&kho_out.lock);
@@ -860,7 +802,7 @@ static int __kho_finalize(void)
abort:
if (err) {
pr_err("Failed to convert KHO state tree: %d\n", err);
- kho_abort();
+ __kho_abort();
}
return err;
@@ -885,7 +827,8 @@ int kho_finalize(void)
goto unlock;
kho_out.finalized = true;
- ret = kho_out_update_debugfs_fdt();
+ ret = kho_debugfs_fdt_add(&kho_out.dbg, "fdt",
+ page_to_virt(kho_out.ser.fdt), true);
unlock:
mutex_unlock(&kho_out.lock);
@@ -893,112 +836,24 @@ int kho_finalize(void)
}
EXPORT_SYMBOL_GPL(kho_finalize);
-static int kho_out_finalize_get(void *data, u64 *val)
+bool kho_finalized(void)
{
- mutex_lock(&kho_out.lock);
- *val = kho_out.finalized;
- mutex_unlock(&kho_out.lock);
-
- return 0;
-}
-
-static int kho_out_finalize_set(void *data, u64 _val)
-{
- int ret = 0;
- bool val = !!_val;
+ bool ret;
mutex_lock(&kho_out.lock);
-
- if (val == kho_out.finalized) {
- if (kho_out.finalized)
- ret = -EEXIST;
- else
- ret = -ENOENT;
- goto unlock;
- }
-
- if (val)
- ret = kho_finalize();
- else
- ret = kho_abort();
-
- if (ret)
- goto unlock;
-
- kho_out.finalized = val;
- ret = kho_out_update_debugfs_fdt();
-
-unlock:
+ ret = kho_out.finalized;
mutex_unlock(&kho_out.lock);
- return ret;
-}
-
-DEFINE_DEBUGFS_ATTRIBUTE(fops_kho_out_finalize, kho_out_finalize_get,
- kho_out_finalize_set, "%llu\n");
-
-static int scratch_phys_show(struct seq_file *m, void *v)
-{
- for (int i = 0; i < kho_scratch_cnt; i++)
- seq_printf(m, "0x%llx\n", kho_scratch[i].addr);
-
- return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(scratch_phys);
-
-static int scratch_len_show(struct seq_file *m, void *v)
-{
- for (int i = 0; i < kho_scratch_cnt; i++)
- seq_printf(m, "0x%llx\n", kho_scratch[i].size);
-
- return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(scratch_len);
-
-static __init int kho_out_debugfs_init(void)
-{
- struct dentry *dir, *f, *sub_fdt_dir;
-
- dir = debugfs_create_dir("out", debugfs_root);
- if (IS_ERR(dir))
- return -ENOMEM;
-
- sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
- if (IS_ERR(sub_fdt_dir))
- goto err_rmdir;
- f = debugfs_create_file("scratch_phys", 0400, dir, NULL,
- &scratch_phys_fops);
- if (IS_ERR(f))
- goto err_rmdir;
-
- f = debugfs_create_file("scratch_len", 0400, dir, NULL,
- &scratch_len_fops);
- if (IS_ERR(f))
- goto err_rmdir;
-
- f = debugfs_create_file("finalize", 0600, dir, NULL,
- &fops_kho_out_finalize);
- if (IS_ERR(f))
- goto err_rmdir;
-
- kho_out.dir = dir;
- kho_out.ser.sub_fdt_dir = sub_fdt_dir;
- return 0;
-
-err_rmdir:
- debugfs_remove_recursive(dir);
- return -ENOENT;
+ return ret;
}
struct kho_in {
- struct dentry *dir;
phys_addr_t fdt_phys;
phys_addr_t scratch_phys;
- struct list_head fdt_list;
+ struct kho_debugfs dbg;
};
static struct kho_in kho_in = {
- .fdt_list = LIST_HEAD_INIT(kho_in.fdt_list),
};
static const void *kho_get_fdt(void)
@@ -1042,56 +897,6 @@ int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
}
EXPORT_SYMBOL_GPL(kho_retrieve_subtree);
-/* Handling for debugfs/kho/in */
-
-static __init int kho_in_debugfs_init(const void *fdt)
-{
- struct dentry *sub_fdt_dir;
- int err, child;
-
- kho_in.dir = debugfs_create_dir("in", debugfs_root);
- if (IS_ERR(kho_in.dir))
- return PTR_ERR(kho_in.dir);
-
- sub_fdt_dir = debugfs_create_dir("sub_fdts", kho_in.dir);
- if (IS_ERR(sub_fdt_dir)) {
- err = PTR_ERR(sub_fdt_dir);
- goto err_rmdir;
- }
-
- err = kho_debugfs_fdt_add(&kho_in.fdt_list, kho_in.dir, "fdt", fdt);
- if (err)
- goto err_rmdir;
-
- fdt_for_each_subnode(child, fdt, 0) {
- int len = 0;
- const char *name = fdt_get_name(fdt, child, NULL);
- const u64 *fdt_phys;
-
- fdt_phys = fdt_getprop(fdt, child, "fdt", &len);
- if (!fdt_phys)
- continue;
- if (len != sizeof(*fdt_phys)) {
- pr_warn("node `%s`'s prop `fdt` has invalid length: %d\n",
- name, len);
- continue;
- }
- err = kho_debugfs_fdt_add(&kho_in.fdt_list, sub_fdt_dir, name,
- phys_to_virt(*fdt_phys));
- if (err) {
- pr_warn("failed to add fdt `%s` to debugfs: %d\n", name,
- err);
- continue;
- }
- }
-
- return 0;
-
-err_rmdir:
- debugfs_remove_recursive(kho_in.dir);
- return err;
-}
-
static __init int kho_init(void)
{
int err = 0;
@@ -1106,27 +911,16 @@ static __init int kho_init(void)
goto err_free_scratch;
}
- debugfs_root = debugfs_create_dir("kho", NULL);
- if (IS_ERR(debugfs_root)) {
- err = -ENOENT;
+ err = kho_debugfs_init();
+ if (err)
goto err_free_fdt;
- }
- err = kho_out_debugfs_init();
+ err = kho_out_debugfs_init(&kho_out.dbg);
if (err)
goto err_free_fdt;
if (fdt) {
- err = kho_in_debugfs_init(fdt);
- /*
- * Failure to create /sys/kernel/debug/kho/in does not prevent
- * reviving state from KHO and setting up KHO for the next
- * kexec.
- */
- if (err)
- pr_err("failed exposing handover FDT in debugfs: %d\n",
- err);
-
+ kho_in_debugfs_init(&kho_in.dbg, fdt);
return 0;
}
diff --git a/kernel/kexec_handover_debug.c b/kernel/kexec_handover_debug.c
new file mode 100644
index 000000000000..b88d138a97be
--- /dev/null
+++ b/kernel/kexec_handover_debug.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_handover.c - kexec handover metadata processing
+ * Copyright (C) 2023 Alexander Graf <graf@amazon.com>
+ * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport <rppt@kernel.org>
+ * Copyright (C) 2025 Google LLC, Changyuan Lyu <changyuanl@google.com>
+ * Copyright (C) 2025 Google LLC, Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#define pr_fmt(fmt) "KHO: " fmt
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include "kexec_handover_internal.h"
+
+static struct dentry *debugfs_root;
+
+struct fdt_debugfs {
+ struct list_head list;
+ struct debugfs_blob_wrapper wrapper;
+ struct dentry *file;
+};
+
+static int __kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir,
+ const char *name, const void *fdt)
+{
+ struct fdt_debugfs *f;
+ struct dentry *file;
+
+ f = kmalloc(sizeof(*f), GFP_KERNEL);
+ if (!f)
+ return -ENOMEM;
+
+ f->wrapper.data = (void *)fdt;
+ f->wrapper.size = fdt_totalsize(fdt);
+
+ file = debugfs_create_blob(name, 0400, dir, &f->wrapper);
+ if (IS_ERR(file)) {
+ kfree(f);
+ return PTR_ERR(file);
+ }
+
+ f->file = file;
+ list_add(&f->list, list);
+
+ return 0;
+}
+
+int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
+ const void *fdt, bool root)
+{
+ struct dentry *dir;
+
+ if (root)
+ dir = dbg->dir;
+ else
+ dir = dbg->sub_fdt_dir;
+
+ return __kho_debugfs_fdt_add(&dbg->fdt_list, dir, name, fdt);
+}
+
+void kho_debugfs_cleanup(struct kho_debugfs *dbg)
+{
+ struct fdt_debugfs *ff, *tmp;
+
+ list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
+ debugfs_remove(ff->file);
+ list_del(&ff->list);
+ kfree(ff);
+ }
+}
+
+static int kho_out_finalize_get(void *data, u64 *val)
+{
+ *val = kho_finalized();
+
+ return 0;
+}
+
+static int kho_out_finalize_set(void *data, u64 _val)
+{
+ bool val = !!_val;
+
+ if (val)
+ return kho_finalize();
+
+ return kho_abort();
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(kho_out_finalize_fops, kho_out_finalize_get,
+ kho_out_finalize_set, "%llu\n");
+
+static int scratch_phys_show(struct seq_file *m, void *v)
+{
+ for (int i = 0; i < kho_scratch_cnt; i++)
+ seq_printf(m, "0x%llx\n", kho_scratch[i].addr);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_phys);
+
+static int scratch_len_show(struct seq_file *m, void *v)
+{
+ for (int i = 0; i < kho_scratch_cnt; i++)
+ seq_printf(m, "0x%llx\n", kho_scratch[i].size);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_len);
+
+__init void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt)
+{
+ struct dentry *dir, *sub_fdt_dir;
+ int err, child;
+
+ INIT_LIST_HEAD(&dbg->fdt_list);
+
+ dir = debugfs_create_dir("in", debugfs_root);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto err_out;
+ }
+
+ sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
+ if (IS_ERR(sub_fdt_dir)) {
+ err = PTR_ERR(sub_fdt_dir);
+ goto err_rmdir;
+ }
+
+ err = __kho_debugfs_fdt_add(&dbg->fdt_list, dir, "fdt", fdt);
+ if (err)
+ goto err_rmdir;
+
+ fdt_for_each_subnode(child, fdt, 0) {
+ int len = 0;
+ const char *name = fdt_get_name(fdt, child, NULL);
+ const u64 *fdt_phys;
+
+ fdt_phys = fdt_getprop(fdt, child, "fdt", &len);
+ if (!fdt_phys)
+ continue;
+ if (len != sizeof(*fdt_phys)) {
+ pr_warn("node %s prop fdt has invalid length: %d\n",
+ name, len);
+ continue;
+ }
+ err = __kho_debugfs_fdt_add(&dbg->fdt_list, sub_fdt_dir, name,
+ phys_to_virt(*fdt_phys));
+ if (err) {
+ pr_warn("failed to add fdt %s to debugfs: %d\n", name,
+ err);
+ continue;
+ }
+ }
+
+ dbg->dir = dir;
+ dbg->sub_fdt_dir = sub_fdt_dir;
+
+ return;
+err_rmdir:
+ debugfs_remove_recursive(dir);
+err_out:
+ /*
+ * Failure to create /sys/kernel/debug/kho/in does not prevent
+ * reviving state from KHO and setting up KHO for the next
+ * kexec.
+ */
+ if (err)
+ pr_err("failed exposing handover FDT in debugfs: %d\n", err);
+}
+
+__init int kho_out_debugfs_init(struct kho_debugfs *dbg)
+{
+ struct dentry *dir, *f, *sub_fdt_dir;
+
+ INIT_LIST_HEAD(&dbg->fdt_list);
+
+ dir = debugfs_create_dir("out", debugfs_root);
+ if (IS_ERR(dir))
+ return -ENOMEM;
+
+ sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
+ if (IS_ERR(sub_fdt_dir))
+ goto err_rmdir;
+
+ f = debugfs_create_file("scratch_phys", 0400, dir, NULL,
+ &scratch_phys_fops);
+ if (IS_ERR(f))
+ goto err_rmdir;
+
+ f = debugfs_create_file("scratch_len", 0400, dir, NULL,
+ &scratch_len_fops);
+ if (IS_ERR(f))
+ goto err_rmdir;
+
+ f = debugfs_create_file("finalize", 0600, dir, NULL,
+ &kho_out_finalize_fops);
+ if (IS_ERR(f))
+ goto err_rmdir;
+
+ dbg->dir = dir;
+ dbg->sub_fdt_dir = sub_fdt_dir;
+ return 0;
+
+err_rmdir:
+ debugfs_remove_recursive(dir);
+ return -ENOENT;
+}
+
+__init int kho_debugfs_init(void)
+{
+ debugfs_root = debugfs_create_dir("kho", NULL);
+ if (IS_ERR(debugfs_root))
+ return -ENOENT;
+ return 0;
+}
diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h
new file mode 100644
index 000000000000..41e9616fcdd0
--- /dev/null
+++ b/kernel/kexec_handover_internal.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H
+#define LINUX_KEXEC_HANDOVER_INTERNAL_H
+
+#include <linux/kexec_handover.h>
+#include <linux/list.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUG
+#include <linux/debugfs.h>
+
+struct kho_debugfs {
+ struct dentry *dir;
+ struct dentry *sub_fdt_dir;
+ struct list_head fdt_list;
+};
+
+#else
+struct kho_debugfs {}
+#endif
+
+extern struct kho_scratch *kho_scratch;
+extern unsigned int kho_scratch_cnt;
+
+bool kho_finalized(void);
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUG
+int kho_debugfs_init(void);
+void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt);
+int kho_out_debugfs_init(struct kho_debugfs *dbg);
+int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
+ const void *fdt, bool root);
+void kho_debugfs_cleanup(struct kho_debugfs *dbg);
+#else
+static inline int kho_debugfs_init(void) { return 0; }
+static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
+ const void *fdt) { }
+static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; }
+static inline int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
+ const void *fdt, bool root) { return 0; }
+static inline void kho_debugfs_cleanup(struct kho_debugfs *dbg) {}
+#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */
+
+#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 06/32] kho: drop notifiers
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
The KHO framework uses a notifier chain as the mechanism for clients to
participate in the finalization process. While this works for a single,
central state machine, it is too restrictive for kernel-internal
components like pstore/reserve_mem or IMA. These components need a
simpler, direct way to register their state for preservation (e.g.,
during their initcall) without being part of a complex,
shutdown-time notifier sequence. The notifier model forces all
participants into a single finalization flow and makes direct
preservation from an arbitrary context difficult.
This patch refactors the client participation model by removing the
notifier chain and introducing a direct API for managing FDT subtrees.
The core kho_finalize() and kho_abort() state machine remains, but
clients now register their data with KHO beforehand.
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/kexec_handover.h | 28 +----
kernel/kexec_handover.c | 177 +++++++++++++++++--------------
kernel/kexec_handover_debug.c | 17 +--
kernel/kexec_handover_internal.h | 5 +-
mm/memblock.c | 56 ++--------
5 files changed, 124 insertions(+), 159 deletions(-)
diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index f98565def593..cabdff5f50a2 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -10,14 +10,7 @@ struct kho_scratch {
phys_addr_t size;
};
-/* KHO Notifier index */
-enum kho_event {
- KEXEC_KHO_FINALIZE = 0,
- KEXEC_KHO_ABORT = 1,
-};
-
struct folio;
-struct notifier_block;
#define DECLARE_KHOSER_PTR(name, type) \
union { \
@@ -36,20 +29,16 @@ struct notifier_block;
(typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \
})
-struct kho_serialization;
-
#ifdef CONFIG_KEXEC_HANDOVER
bool kho_is_enabled(void);
int kho_preserve_folio(struct folio *folio);
int kho_preserve_phys(phys_addr_t phys, size_t size);
struct folio *kho_restore_folio(phys_addr_t phys);
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
+int kho_add_subtree(const char *name, void *fdt);
+void kho_remove_subtree(void *fdt);
int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
-int register_kho_notifier(struct notifier_block *nb);
-int unregister_kho_notifier(struct notifier_block *nb);
-
void kho_memory_init(void);
void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
@@ -79,23 +68,16 @@ static inline struct folio *kho_restore_folio(phys_addr_t phys)
return NULL;
}
-static inline int kho_add_subtree(struct kho_serialization *ser,
- const char *name, void *fdt)
+static inline int kho_add_subtree(const char *name, void *fdt)
{
return -EOPNOTSUPP;
}
-static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+static inline void kho_remove_subtree(void *fdt)
{
- return -EOPNOTSUPP;
}
-static inline int register_kho_notifier(struct notifier_block *nb)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int unregister_kho_notifier(struct notifier_block *nb)
+static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
{
return -EOPNOTSUPP;
}
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 32fdc388752b..30d673f7f68a 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -15,7 +15,6 @@
#include <linux/libfdt.h>
#include <linux/list.h>
#include <linux/memblock.h>
-#include <linux/notifier.h>
#include <linux/page-isolation.h>
#include <asm/early_ioremap.h>
@@ -82,11 +81,35 @@ struct kho_mem_track {
struct khoser_mem_chunk;
-struct kho_serialization {
- struct page *fdt;
+struct kho_sub_fdt {
+ struct list_head l;
+ const char *name;
+ void *fdt;
+};
+
+struct kho_out {
+ void *fdt;
+ bool finalized;
+ struct mutex lock; /* protects KHO FDT finalization */
+
+ struct list_head sub_fdts;
+ struct mutex fdts_lock;
+
struct kho_mem_track track;
/* First chunk of serialized preserved memory map */
struct khoser_mem_chunk *preserved_mem_map;
+
+ struct kho_debugfs dbg;
+};
+
+static struct kho_out kho_out = {
+ .lock = __MUTEX_INITIALIZER(kho_out.lock),
+ .track = {
+ .orders = XARRAY_INIT(kho_out.track.orders, 0),
+ },
+ .sub_fdts = LIST_HEAD_INIT(kho_out.sub_fdts),
+ .fdts_lock = __MUTEX_INITIALIZER(kho_out.fdts_lock),
+ .finalized = false,
};
static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
@@ -285,14 +308,14 @@ static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk)
}
}
-static int kho_mem_serialize(struct kho_serialization *ser)
+static int kho_mem_serialize(struct kho_out *kho_out)
{
struct khoser_mem_chunk *first_chunk = NULL;
struct khoser_mem_chunk *chunk = NULL;
struct kho_mem_phys *physxa;
unsigned long order;
- xa_for_each(&ser->track.orders, order, physxa) {
+ xa_for_each(&kho_out->track.orders, order, physxa) {
struct kho_mem_phys_bits *bits;
unsigned long phys;
@@ -320,7 +343,7 @@ static int kho_mem_serialize(struct kho_serialization *ser)
}
}
- ser->preserved_mem_map = first_chunk;
+ kho_out->preserved_mem_map = first_chunk;
return 0;
@@ -567,28 +590,8 @@ static void __init kho_reserve_scratch(void)
kho_enable = false;
}
-struct kho_out {
- struct blocking_notifier_head chain_head;
- struct mutex lock; /* protects KHO FDT finalization */
- struct kho_serialization ser;
- bool finalized;
- struct kho_debugfs dbg;
-};
-
-static struct kho_out kho_out = {
- .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
- .lock = __MUTEX_INITIALIZER(kho_out.lock),
- .ser = {
- .track = {
- .orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
- },
- },
- .finalized = false,
-};
-
/**
* kho_add_subtree - record the physical address of a sub FDT in KHO root tree.
- * @ser: serialization control object passed by KHO notifiers.
* @name: name of the sub tree.
* @fdt: the sub tree blob.
*
@@ -602,34 +605,45 @@ static struct kho_out kho_out = {
*
* Return: 0 on success, error code on failure
*/
-int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
+int kho_add_subtree(const char *name, void *fdt)
{
- int err = 0;
- u64 phys = (u64)virt_to_phys(fdt);
- void *root = page_to_virt(ser->fdt);
+ struct kho_sub_fdt *sub_fdt;
+ int err;
- err |= fdt_begin_node(root, name);
- err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys));
- err |= fdt_end_node(root);
+ sub_fdt = kmalloc(sizeof(*sub_fdt), GFP_KERNEL);
+ if (!sub_fdt)
+ return -ENOMEM;
- if (err)
- return err;
+ INIT_LIST_HEAD(&sub_fdt->l);
+ sub_fdt->name = name;
+ sub_fdt->fdt = fdt;
+
+ mutex_lock(&kho_out.fdts_lock);
+ list_add_tail(&sub_fdt->l, &kho_out.sub_fdts);
+ err = kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ mutex_unlock(&kho_out.fdts_lock);
- return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false);
+ return err;
}
EXPORT_SYMBOL_GPL(kho_add_subtree);
-int register_kho_notifier(struct notifier_block *nb)
+void kho_remove_subtree(void *fdt)
{
- return blocking_notifier_chain_register(&kho_out.chain_head, nb);
-}
-EXPORT_SYMBOL_GPL(register_kho_notifier);
+ struct kho_sub_fdt *sub_fdt;
+
+ mutex_lock(&kho_out.fdts_lock);
+ list_for_each_entry(sub_fdt, &kho_out.sub_fdts, l) {
+ if (sub_fdt->fdt == fdt) {
+ list_del(&sub_fdt->l);
+ kfree(sub_fdt);
+ kho_debugfs_fdt_remove(&kho_out.dbg, fdt);
+ break;
+ }
+ }
+ mutex_unlock(&kho_out.fdts_lock);
-int unregister_kho_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
}
-EXPORT_SYMBOL_GPL(unregister_kho_notifier);
+EXPORT_SYMBOL_GPL(kho_remove_subtree);
/**
* kho_preserve_folio - preserve a folio across kexec.
@@ -644,7 +658,7 @@ int kho_preserve_folio(struct folio *folio)
{
const unsigned long pfn = folio_pfn(folio);
const unsigned int order = folio_order(folio);
- struct kho_mem_track *track = &kho_out.ser.track;
+ struct kho_mem_track *track = &kho_out.track;
if (kho_out.finalized)
return -EBUSY;
@@ -670,7 +684,7 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
const unsigned long start_pfn = pfn;
const unsigned long end_pfn = PHYS_PFN(phys + size);
int err = 0;
- struct kho_mem_track *track = &kho_out.ser.track;
+ struct kho_mem_track *track = &kho_out.track;
if (kho_out.finalized)
return -EBUSY;
@@ -700,11 +714,11 @@ EXPORT_SYMBOL_GPL(kho_preserve_phys);
static int __kho_abort(void)
{
- int err;
+ int err = 0;
unsigned long order;
struct kho_mem_phys *physxa;
- xa_for_each(&kho_out.ser.track.orders, order, physxa) {
+ xa_for_each(&kho_out.track.orders, order, physxa) {
struct kho_mem_phys_bits *bits;
unsigned long phys;
@@ -714,17 +728,13 @@ static int __kho_abort(void)
xa_destroy(&physxa->phys_bits);
kfree(physxa);
}
- xa_destroy(&kho_out.ser.track.orders);
+ xa_destroy(&kho_out.track.orders);
- if (kho_out.ser.preserved_mem_map) {
- kho_mem_ser_free(kho_out.ser.preserved_mem_map);
- kho_out.ser.preserved_mem_map = NULL;
+ if (kho_out.preserved_mem_map) {
+ kho_mem_ser_free(kho_out.preserved_mem_map);
+ kho_out.preserved_mem_map = NULL;
}
- err = blocking_notifier_call_chain(&kho_out.chain_head, KEXEC_KHO_ABORT,
- NULL);
- err = notifier_to_errno(err);
-
if (err)
pr_err("Failed to abort KHO finalization: %d\n", err);
@@ -751,7 +761,7 @@ int kho_abort(void)
kho_out.finalized = false;
- kho_debugfs_cleanup(&kho_out.dbg);
+ kho_debugfs_fdt_remove(&kho_out.dbg, kho_out.fdt);
unlock:
mutex_unlock(&kho_out.lock);
@@ -763,41 +773,46 @@ static int __kho_finalize(void)
{
int err = 0;
u64 *preserved_mem_map;
- void *fdt = page_to_virt(kho_out.ser.fdt);
+ void *root = kho_out.fdt;
+ struct kho_sub_fdt *fdt;
- err |= fdt_create(fdt, PAGE_SIZE);
- err |= fdt_finish_reservemap(fdt);
- err |= fdt_begin_node(fdt, "");
- err |= fdt_property_string(fdt, "compatible", KHO_FDT_COMPATIBLE);
+ err |= fdt_create(root, PAGE_SIZE);
+ err |= fdt_finish_reservemap(root);
+ err |= fdt_begin_node(root, "");
+ err |= fdt_property_string(root, "compatible", KHO_FDT_COMPATIBLE);
/**
* Reserve the preserved-memory-map property in the root FDT, so
* that all property definitions will precede subnodes created by
* KHO callers.
*/
- err |= fdt_property_placeholder(fdt, PROP_PRESERVED_MEMORY_MAP,
+ err |= fdt_property_placeholder(root, PROP_PRESERVED_MEMORY_MAP,
sizeof(*preserved_mem_map),
(void **)&preserved_mem_map);
if (err)
goto abort;
- err = kho_preserve_folio(page_folio(kho_out.ser.fdt));
+ err = kho_preserve_folio(virt_to_folio(kho_out.fdt));
if (err)
goto abort;
- err = blocking_notifier_call_chain(&kho_out.chain_head,
- KEXEC_KHO_FINALIZE, &kho_out.ser);
- err = notifier_to_errno(err);
+ err = kho_mem_serialize(&kho_out);
if (err)
goto abort;
- err = kho_mem_serialize(&kho_out.ser);
- if (err)
- goto abort;
+ *preserved_mem_map = (u64)virt_to_phys(kho_out.preserved_mem_map);
- *preserved_mem_map = (u64)virt_to_phys(kho_out.ser.preserved_mem_map);
+ mutex_lock(&kho_out.fdts_lock);
+ list_for_each_entry(fdt, &kho_out.sub_fdts, l) {
+ phys_addr_t phys = virt_to_phys(fdt->fdt);
- err |= fdt_end_node(fdt);
- err |= fdt_finish(fdt);
+ err |= fdt_begin_node(root, fdt->name);
+ err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys));
+ err |= fdt_end_node(root);
+ };
+ mutex_unlock(&kho_out.fdts_lock);
+
+ err |= fdt_end_node(root);
+ err |= fdt_finish(root);
abort:
if (err) {
@@ -828,7 +843,7 @@ int kho_finalize(void)
kho_out.finalized = true;
ret = kho_debugfs_fdt_add(&kho_out.dbg, "fdt",
- page_to_virt(kho_out.ser.fdt), true);
+ kho_out.fdt, true);
unlock:
mutex_unlock(&kho_out.lock);
@@ -901,15 +916,17 @@ static __init int kho_init(void)
{
int err = 0;
const void *fdt = kho_get_fdt();
+ struct page *fdt_page;
if (!kho_enable)
return 0;
- kho_out.ser.fdt = alloc_page(GFP_KERNEL);
- if (!kho_out.ser.fdt) {
+ fdt_page = alloc_page(GFP_KERNEL);
+ if (!fdt_page) {
err = -ENOMEM;
goto err_free_scratch;
}
+ kho_out.fdt = page_to_virt(fdt_page);
err = kho_debugfs_init();
if (err)
@@ -937,8 +954,8 @@ static __init int kho_init(void)
return 0;
err_free_fdt:
- put_page(kho_out.ser.fdt);
- kho_out.ser.fdt = NULL;
+ put_page(fdt_page);
+ kho_out.fdt = NULL;
err_free_scratch:
for (int i = 0; i < kho_scratch_cnt; i++) {
void *start = __va(kho_scratch[i].addr);
@@ -949,7 +966,7 @@ static __init int kho_init(void)
kho_enable = false;
return err;
}
-late_initcall(kho_init);
+fs_initcall(kho_init);
static void __init kho_release_scratch(void)
{
@@ -1085,7 +1102,7 @@ int kho_fill_kimage(struct kimage *image)
if (!kho_enable)
return 0;
- image->kho.fdt = page_to_phys(kho_out.ser.fdt);
+ image->kho.fdt = virt_to_phys(kho_out.fdt);
scratch_size = sizeof(*kho_scratch) * kho_scratch_cnt;
scratch = (struct kexec_buf){
diff --git a/kernel/kexec_handover_debug.c b/kernel/kexec_handover_debug.c
index b88d138a97be..af4bad225630 100644
--- a/kernel/kexec_handover_debug.c
+++ b/kernel/kexec_handover_debug.c
@@ -61,14 +61,17 @@ int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
return __kho_debugfs_fdt_add(&dbg->fdt_list, dir, name, fdt);
}
-void kho_debugfs_cleanup(struct kho_debugfs *dbg)
+void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt)
{
- struct fdt_debugfs *ff, *tmp;
-
- list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) {
- debugfs_remove(ff->file);
- list_del(&ff->list);
- kfree(ff);
+ struct fdt_debugfs *ff;
+
+ list_for_each_entry(ff, &dbg->fdt_list, list) {
+ if (ff->wrapper.data == fdt) {
+ debugfs_remove(ff->file);
+ list_del(&ff->list);
+ kfree(ff);
+ break;
+ }
}
}
diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h
index 41e9616fcdd0..240517596ea3 100644
--- a/kernel/kexec_handover_internal.h
+++ b/kernel/kexec_handover_internal.h
@@ -30,7 +30,7 @@ void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt);
int kho_out_debugfs_init(struct kho_debugfs *dbg);
int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
const void *fdt, bool root);
-void kho_debugfs_cleanup(struct kho_debugfs *dbg);
+void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt);
#else
static inline int kho_debugfs_init(void) { return 0; }
static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
@@ -38,7 +38,8 @@ static inline void kho_in_debugfs_init(struct kho_debugfs *dbg,
static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; }
static inline int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name,
const void *fdt, bool root) { return 0; }
-static inline void kho_debugfs_cleanup(struct kho_debugfs *dbg) {}
+static inline void kho_debugfs_fdt_remove(struct kho_debugfs *dbg,
+ void *fdt) { }
#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */
#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */
diff --git a/mm/memblock.c b/mm/memblock.c
index 154f1d73b61f..6af0b51b1bb7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2501,51 +2501,18 @@ int reserve_mem_release_by_name(const char *name)
#define MEMBLOCK_KHO_FDT "memblock"
#define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1"
#define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1"
-static struct page *kho_fdt;
-
-static int reserve_mem_kho_finalize(struct kho_serialization *ser)
-{
- int err = 0, i;
-
- for (i = 0; i < reserved_mem_count; i++) {
- struct reserve_mem_table *map = &reserved_mem_table[i];
-
- err |= kho_preserve_phys(map->start, map->size);
- }
-
- err |= kho_preserve_folio(page_folio(kho_fdt));
- err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt));
-
- return notifier_from_errno(err);
-}
-
-static int reserve_mem_kho_notifier(struct notifier_block *self,
- unsigned long cmd, void *v)
-{
- switch (cmd) {
- case KEXEC_KHO_FINALIZE:
- return reserve_mem_kho_finalize((struct kho_serialization *)v);
- case KEXEC_KHO_ABORT:
- return NOTIFY_DONE;
- default:
- return NOTIFY_BAD;
- }
-}
-
-static struct notifier_block reserve_mem_kho_nb = {
- .notifier_call = reserve_mem_kho_notifier,
-};
static int __init prepare_kho_fdt(void)
{
int err = 0, i;
+ struct page *fdt_page;
void *fdt;
- kho_fdt = alloc_page(GFP_KERNEL);
- if (!kho_fdt)
+ fdt_page = alloc_page(GFP_KERNEL);
+ if (!fdt_page)
return -ENOMEM;
- fdt = page_to_virt(kho_fdt);
+ fdt = page_to_virt(fdt_page);
err |= fdt_create(fdt, PAGE_SIZE);
err |= fdt_finish_reservemap(fdt);
@@ -2555,6 +2522,7 @@ static int __init prepare_kho_fdt(void)
for (i = 0; i < reserved_mem_count; i++) {
struct reserve_mem_table *map = &reserved_mem_table[i];
+ err |= kho_preserve_phys(map->start, map->size);
err |= fdt_begin_node(fdt, map->name);
err |= fdt_property_string(fdt, "compatible", RESERVE_MEM_KHO_NODE_COMPATIBLE);
err |= fdt_property(fdt, "start", &map->start, sizeof(map->start));
@@ -2562,13 +2530,14 @@ static int __init prepare_kho_fdt(void)
err |= fdt_end_node(fdt);
}
err |= fdt_end_node(fdt);
-
err |= fdt_finish(fdt);
+ err |= kho_preserve_folio(page_folio(fdt_page));
+ err |= kho_add_subtree(MEMBLOCK_KHO_FDT, fdt);
+
if (err) {
pr_err("failed to prepare memblock FDT for KHO: %d\n", err);
- put_page(kho_fdt);
- kho_fdt = NULL;
+ put_page(fdt_page);
}
return err;
@@ -2584,13 +2553,6 @@ static int __init reserve_mem_init(void)
err = prepare_kho_fdt();
if (err)
return err;
-
- err = register_kho_notifier(&reserve_mem_kho_nb);
- if (err) {
- put_page(kho_fdt);
- kho_fdt = NULL;
- }
-
return err;
}
late_initcall(reserve_mem_init);
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 07/32] kho: add interfaces to unpreserve folios and physical memory ranges
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
From: Changyuan Lyu <changyuanl@google.com>
Allow users of KHO to cancel the previous preservation by adding the
necessary interfaces to unpreserve folio.
Signed-off-by: Changyuan Lyu <changyuanl@google.com>
Co-developed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/kexec_handover.h | 12 +++++
kernel/kexec_handover.c | 90 +++++++++++++++++++++++++++++-----
2 files changed, 89 insertions(+), 13 deletions(-)
diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index cabdff5f50a2..383e9460edb9 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -33,7 +33,9 @@ struct folio;
bool kho_is_enabled(void);
int kho_preserve_folio(struct folio *folio);
+int kho_unpreserve_folio(struct folio *folio);
int kho_preserve_phys(phys_addr_t phys, size_t size);
+int kho_unpreserve_phys(phys_addr_t phys, size_t size);
struct folio *kho_restore_folio(phys_addr_t phys);
int kho_add_subtree(const char *name, void *fdt);
void kho_remove_subtree(void *fdt);
@@ -58,11 +60,21 @@ static inline int kho_preserve_folio(struct folio *folio)
return -EOPNOTSUPP;
}
+static inline int kho_unpreserve_folio(struct folio *folio)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int kho_preserve_phys(phys_addr_t phys, size_t size)
{
return -EOPNOTSUPP;
}
+static inline int kho_unpreserve_phys(phys_addr_t phys, size_t size)
+{
+ return -EOPNOTSUPP;
+}
+
static inline struct folio *kho_restore_folio(phys_addr_t phys)
{
return NULL;
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 30d673f7f68a..26ad926912a7 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -136,26 +136,33 @@ static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
return elm;
}
-static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn,
- unsigned long end_pfn)
+static void __kho_unpreserve_order(struct kho_mem_track *track, unsigned long pfn,
+ unsigned int order)
{
struct kho_mem_phys_bits *bits;
struct kho_mem_phys *physxa;
+ const unsigned long pfn_high = pfn >> order;
- while (pfn < end_pfn) {
- const unsigned int order =
- min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
- const unsigned long pfn_high = pfn >> order;
+ physxa = xa_load(&track->orders, order);
+ if (!physxa)
+ return;
- physxa = xa_load(&track->orders, order);
- if (!physxa)
- continue;
+ bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
+ if (!bits)
+ return;
- bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
- if (!bits)
- continue;
+ clear_bit(pfn_high % PRESERVE_BITS, bits->preserve);
+}
- clear_bit(pfn_high % PRESERVE_BITS, bits->preserve);
+static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn,
+ unsigned long end_pfn)
+{
+ unsigned int order;
+
+ while (pfn < end_pfn) {
+ order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
+
+ __kho_unpreserve_order(track, pfn, order);
pfn += 1 << order;
}
@@ -667,6 +674,30 @@ int kho_preserve_folio(struct folio *folio)
}
EXPORT_SYMBOL_GPL(kho_preserve_folio);
+/**
+ * kho_unpreserve_folio - unpreserve a folio.
+ * @folio: folio to unpreserve.
+ *
+ * Instructs KHO to unpreserve a folio that was preserved by
+ * kho_preserve_folio() before. The provided @folio (pfn and order)
+ * must exactly match a previously preserved folio.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_unpreserve_folio(struct folio *folio)
+{
+ const unsigned long pfn = folio_pfn(folio);
+ const unsigned int order = folio_order(folio);
+ struct kho_mem_track *track = &kho_out.track;
+
+ if (kho_out.finalized)
+ return -EBUSY;
+
+ __kho_unpreserve_order(track, pfn, order);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kho_unpreserve_folio);
+
/**
* kho_preserve_phys - preserve a physically contiguous range across kexec.
* @phys: physical address of the range.
@@ -712,6 +743,39 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
}
EXPORT_SYMBOL_GPL(kho_preserve_phys);
+/**
+ * kho_unpreserve_phys - unpreserve a physically contiguous range.
+ * @phys: physical address of the range.
+ * @size: size of the range.
+ *
+ * Instructs KHO to unpreserve the memory range from @phys to @phys + @size.
+ * The @phys address must be aligned to @size, and @size must be a
+ * power-of-2 multiple of PAGE_SIZE.
+ * This call must exactly match a granularity at which memory was originally
+ * preserved (either by a `kho_preserve_phys` call with the same `phys` and
+ * `size`). Unpreserving arbitrary sub-ranges of larger preserved blocks is not
+ * supported.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_unpreserve_phys(phys_addr_t phys, size_t size)
+{
+ struct kho_mem_track *track = &kho_out.track;
+ unsigned long pfn = PHYS_PFN(phys);
+ unsigned long end_pfn = PHYS_PFN(phys + size);
+
+ if (kho_out.finalized)
+ return -EBUSY;
+
+ if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
+ return -EINVAL;
+
+ __kho_unpreserve(track, pfn, end_pfn);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kho_unpreserve_phys);
+
static int __kho_abort(void)
{
int err = 0;
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 08/32] kho: don't unpreserve memory during abort
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
KHO allows clients to preserve memory regions at any point before the
KHO state is finalized. The finalization process itself involves KHO
performing its own actions, such as serializing the overall
preserved memory map.
If this finalization process is aborted, the current implementation
destroys KHO's internal memory tracking structures
(`kho_out.ser.track.orders`). This behavior effectively unpreserves
all memory from KHO's perspective, regardless of whether those
preservations were made by clients before the finalization attempt
or by KHO itself during finalization.
This premature unpreservation is incorrect. An abort of the
finalization process should only undo actions taken by KHO as part of
that specific finalization attempt. Individual memory regions
preserved by clients prior to finalization should remain preserved,
as their lifecycle is managed by the clients themselves. These
clients might still need to call kho_unpreserve_folio() or
kho_unpreserve_phys() based on their own logic, even after a KHO
finalization attempt is aborted.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/kexec_handover.c | 21 +--------------------
1 file changed, 1 insertion(+), 20 deletions(-)
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 26ad926912a7..7908886170f0 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -778,31 +778,12 @@ EXPORT_SYMBOL_GPL(kho_unpreserve_phys);
static int __kho_abort(void)
{
- int err = 0;
- unsigned long order;
- struct kho_mem_phys *physxa;
-
- xa_for_each(&kho_out.track.orders, order, physxa) {
- struct kho_mem_phys_bits *bits;
- unsigned long phys;
-
- xa_for_each(&physxa->phys_bits, phys, bits)
- kfree(bits);
-
- xa_destroy(&physxa->phys_bits);
- kfree(physxa);
- }
- xa_destroy(&kho_out.track.orders);
-
if (kho_out.preserved_mem_map) {
kho_mem_ser_free(kho_out.preserved_mem_map);
kho_out.preserved_mem_map = NULL;
}
- if (err)
- pr_err("Failed to abort KHO finalization: %d\n", err);
-
- return err;
+ return 0;
}
int kho_abort(void)
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 09/32] liveupdate: kho: move to kernel/liveupdate
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Move KHO to kernel/liveupdate/ in preparation of placing all Live Update
core kernel related files to the same place.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
Documentation/core-api/kho/concepts.rst | 2 +-
MAINTAINERS | 2 +-
init/Kconfig | 2 ++
kernel/Kconfig.kexec | 25 ----------------
kernel/Makefile | 3 +-
kernel/liveupdate/Kconfig | 30 +++++++++++++++++++
kernel/liveupdate/Makefile | 7 +++++
kernel/{ => liveupdate}/kexec_handover.c | 6 ++--
.../{ => liveupdate}/kexec_handover_debug.c | 0
.../kexec_handover_internal.h | 0
10 files changed, 45 insertions(+), 32 deletions(-)
create mode 100644 kernel/liveupdate/Kconfig
create mode 100644 kernel/liveupdate/Makefile
rename kernel/{ => liveupdate}/kexec_handover.c (99%)
rename kernel/{ => liveupdate}/kexec_handover_debug.c (100%)
rename kernel/{ => liveupdate}/kexec_handover_internal.h (100%)
diff --git a/Documentation/core-api/kho/concepts.rst b/Documentation/core-api/kho/concepts.rst
index 36d5c05cfb30..d626d1dbd678 100644
--- a/Documentation/core-api/kho/concepts.rst
+++ b/Documentation/core-api/kho/concepts.rst
@@ -70,5 +70,5 @@ in the FDT. That state is called the KHO finalization phase.
Public API
==========
-.. kernel-doc:: kernel/kexec_handover.c
+.. kernel-doc:: kernel/liveupdate/kexec_handover.c
:export:
diff --git a/MAINTAINERS b/MAINTAINERS
index 00de7c78de86..3b276cfeb038 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13356,7 +13356,7 @@ S: Maintained
F: Documentation/admin-guide/mm/kho.rst
F: Documentation/core-api/kho/*
F: include/linux/kexec_handover.h
-F: kernel/kexec_handover*
+F: kernel/liveupdate/kexec_handover*
KEYS-ENCRYPTED
M: Mimi Zohar <zohar@linux.ibm.com>
diff --git a/init/Kconfig b/init/Kconfig
index 666783eb50ab..fb7ac0e56a87 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2083,6 +2083,8 @@ config TRACEPOINTS
source "kernel/Kconfig.kexec"
+source "kernel/liveupdate/Kconfig"
+
endmenu # General setup
source "arch/Kconfig"
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 9968d3d4dd17..b05f5018ed98 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -94,31 +94,6 @@ config KEXEC_JUMP
Jump between original kernel and kexeced kernel and invoke
code in physical address mode via KEXEC
-config KEXEC_HANDOVER
- bool "kexec handover"
- depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
- depends on !DEFERRED_STRUCT_PAGE_INIT
- select MEMBLOCK_KHO_SCRATCH
- select KEXEC_FILE
- select DEBUG_FS
- select LIBFDT
- select CMA
- help
- Allow kexec to hand over state across kernels by generating and
- passing additional metadata to the target kernel. This is useful
- to keep data or state alive across the kexec. For this to work,
- both source and target kernels need to have this option enabled.
-
-config KEXEC_HANDOVER_DEBUG
- bool "kexec handover debug interface"
- depends on KEXEC_HANDOVER
- depends on DEBUG_FS
- help
- Allow to control kexec handover device tree via debugfs
- interface, i.e. finalize the state or aborting the finalization.
- Also, enables inspecting the KHO fdt trees with the debugfs binary
- blobs.
-
config CRASH_DUMP
bool "kernel crash dumps"
default ARCH_DEFAULT_CRASH_DUMP
diff --git a/kernel/Makefile b/kernel/Makefile
index e4b4afa86a70..632f692512d7 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -53,6 +53,7 @@ obj-y += printk/
obj-y += irq/
obj-y += rcu/
obj-y += livepatch/
+obj-y += liveupdate/
obj-y += dma/
obj-y += entry/
obj-$(CONFIG_MODULES) += module/
@@ -81,8 +82,6 @@ obj-$(CONFIG_CRASH_DM_CRYPT) += crash_dump_dm_crypt.o
obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o
-obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
-obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_CGROUPS) += cgroup/
diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig
new file mode 100644
index 000000000000..eebe564b385d
--- /dev/null
+++ b/kernel/liveupdate/Kconfig
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Live Update"
+
+config KEXEC_HANDOVER
+ bool "kexec handover"
+ depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+ depends on !DEFERRED_STRUCT_PAGE_INIT
+ select MEMBLOCK_KHO_SCRATCH
+ select KEXEC_FILE
+ select DEBUG_FS
+ select LIBFDT
+ select CMA
+ help
+ Allow kexec to hand over state across kernels by generating and
+ passing additional metadata to the target kernel. This is useful
+ to keep data or state alive across the kexec. For this to work,
+ both source and target kernels need to have this option enabled.
+
+config KEXEC_HANDOVER_DEBUG
+ bool "kexec handover debug interface"
+ depends on KEXEC_HANDOVER
+ depends on DEBUG_FS
+ help
+ Allow to control kexec handover device tree via debugfs
+ interface, i.e. finalize the state or aborting the finalization.
+ Also, enables inspecting the KHO fdt trees with the debugfs binary
+ blobs.
+
+endmenu
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
new file mode 100644
index 000000000000..72cf7a8e6739
--- /dev/null
+++ b/kernel/liveupdate/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
+obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
diff --git a/kernel/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
similarity index 99%
rename from kernel/kexec_handover.c
rename to kernel/liveupdate/kexec_handover.c
index 7908886170f0..72900afbdf04 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/liveupdate/kexec_handover.c
@@ -23,8 +23,8 @@
* KHO is tightly coupled with mm init and needs access to some of mm
* internal APIs.
*/
-#include "../mm/internal.h"
-#include "kexec_internal.h"
+#include "../../mm/internal.h"
+#include "../kexec_internal.h"
#include "kexec_handover_internal.h"
#define KHO_FDT_COMPATIBLE "kho-v1"
@@ -825,7 +825,7 @@ static int __kho_finalize(void)
err |= fdt_finish_reservemap(root);
err |= fdt_begin_node(root, "");
err |= fdt_property_string(root, "compatible", KHO_FDT_COMPATIBLE);
- /**
+ /*
* Reserve the preserved-memory-map property in the root FDT, so
* that all property definitions will precede subnodes created by
* KHO callers.
diff --git a/kernel/kexec_handover_debug.c b/kernel/liveupdate/kexec_handover_debug.c
similarity index 100%
rename from kernel/kexec_handover_debug.c
rename to kernel/liveupdate/kexec_handover_debug.c
diff --git a/kernel/kexec_handover_internal.h b/kernel/liveupdate/kexec_handover_internal.h
similarity index 100%
rename from kernel/kexec_handover_internal.h
rename to kernel/liveupdate/kexec_handover_internal.h
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 10/32] liveupdate: luo_core: Live Update Orchestrator
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Introduce LUO, a mechanism intended to facilitate kernel updates while
keeping designated devices operational across the transition (e.g., via
kexec). The primary use case is updating hypervisors with minimal
disruption to running virtual machines. For userspace side of hypervisor
update we have copyless migration. LUO is for updating the kernel.
This initial patch lays the groundwork for the LUO subsystem.
Further functionality, including the implementation of state transition
logic, integration with KHO, and hooks for subsystems and file
descriptors, will be added in subsequent patches.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/liveupdate.h | 140 ++++++++++++++
kernel/liveupdate/Kconfig | 27 +++
kernel/liveupdate/Makefile | 1 +
kernel/liveupdate/luo_core.c | 301 +++++++++++++++++++++++++++++++
kernel/liveupdate/luo_internal.h | 21 +++
5 files changed, 490 insertions(+)
create mode 100644 include/linux/liveupdate.h
create mode 100644 kernel/liveupdate/luo_core.c
create mode 100644 kernel/liveupdate/luo_internal.h
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
new file mode 100644
index 000000000000..da8f05c81e51
--- /dev/null
+++ b/include/linux/liveupdate.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+#ifndef _LINUX_LIVEUPDATE_H
+#define _LINUX_LIVEUPDATE_H
+
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/list.h>
+
+/**
+ * enum liveupdate_event - Events that trigger live update callbacks.
+ * @LIVEUPDATE_PREPARE: PREPARE should happen *before* the blackout window.
+ * Subsystems should prepare for an upcoming reboot by
+ * serializing their states. However, it must be considered
+ * that user applications, e.g. virtual machines are still
+ * running during this phase.
+ * @LIVEUPDATE_FREEZE: FREEZE sent from the reboot() syscall, when the current
+ * kernel is on its way out. This is the final opportunity
+ * for subsystems to save any state that must persist
+ * across the reboot. Callbacks for this event should be as
+ * fast as possible since they are on the critical path of
+ * rebooting into the next kernel.
+ * @LIVEUPDATE_FINISH: FINISH is sent in the newly booted kernel after a
+ * successful live update and normally *after* the blackout
+ * window. Subsystems should perform any final cleanup
+ * during this phase. This phase also provides an
+ * opportunity to clean up devices that were preserved but
+ * never explicitly reclaimed during the live update
+ * process. State restoration should have already occurred
+ * before this event. Callbacks for this event must not
+ * fail. The completion of this call transitions the
+ * machine from ``updated`` to ``normal`` state.
+ * @LIVEUPDATE_CANCEL: CANCEL the live update and go back to normal state. This
+ * event is user initiated, or is done automatically when
+ * LIVEUPDATE_PREPARE or LIVEUPDATE_FREEZE stage fails.
+ * Subsystems should revert any actions taken during the
+ * corresponding prepare event. Callbacks for this event
+ * must not fail.
+ *
+ * These events represent the different stages and actions within the live
+ * update process that subsystems (like device drivers and bus drivers)
+ * need to be aware of to correctly serialize and restore their state.
+ *
+ */
+enum liveupdate_event {
+ LIVEUPDATE_PREPARE,
+ LIVEUPDATE_FREEZE,
+ LIVEUPDATE_FINISH,
+ LIVEUPDATE_CANCEL,
+};
+
+/**
+ * enum liveupdate_state - Defines the possible states of the live update
+ * orchestrator.
+ * @LIVEUPDATE_STATE_UNDEFINED: State has not yet been initialized.
+ * @LIVEUPDATE_STATE_NORMAL: Default state, no live update in progress.
+ * @LIVEUPDATE_STATE_PREPARED: Live update is prepared for reboot; the
+ * LIVEUPDATE_PREPARE callbacks have completed
+ * successfully.
+ * Devices might operate in a limited state
+ * for example the participating devices might
+ * not be allowed to unbind, and also the
+ * setting up of new DMA mappings might be
+ * disabled in this state.
+ * @LIVEUPDATE_STATE_FROZEN: The final reboot event
+ * (%LIVEUPDATE_FREEZE) has been sent, and the
+ * system is performing its final state saving
+ * within the "blackout window". User
+ * workloads must be suspended. The actual
+ * reboot (kexec) into the next kernel is
+ * imminent.
+ * @LIVEUPDATE_STATE_UPDATED: The system has rebooted into the next
+ * kernel via live update the system is now
+ * running the next kernel, awaiting the
+ * finish event.
+ *
+ * These states track the progress and outcome of a live update operation.
+ */
+enum liveupdate_state {
+ LIVEUPDATE_STATE_UNDEFINED = 0,
+ LIVEUPDATE_STATE_NORMAL = 1,
+ LIVEUPDATE_STATE_PREPARED = 2,
+ LIVEUPDATE_STATE_FROZEN = 3,
+ LIVEUPDATE_STATE_UPDATED = 4,
+};
+
+#ifdef CONFIG_LIVEUPDATE
+
+/* Return true if live update orchestrator is enabled */
+bool liveupdate_enabled(void);
+
+/* Called during reboot to tell participants to complete serialization */
+int liveupdate_reboot(void);
+
+/*
+ * Return true if machine is in updated state (i.e. live update boot in
+ * progress)
+ */
+bool liveupdate_state_updated(void);
+
+/*
+ * Return true if machine is in normal state (i.e. no live update in progress).
+ */
+bool liveupdate_state_normal(void);
+
+enum liveupdate_state liveupdate_get_state(void);
+
+#else /* CONFIG_LIVEUPDATE */
+
+static inline int liveupdate_reboot(void)
+{
+ return 0;
+}
+
+static inline bool liveupdate_enabled(void)
+{
+ return false;
+}
+
+static inline bool liveupdate_state_updated(void)
+{
+ return false;
+}
+
+static inline bool liveupdate_state_normal(void)
+{
+ return true;
+}
+
+static inline enum liveupdate_state liveupdate_get_state(void)
+{
+ return LIVEUPDATE_STATE_NORMAL;
+}
+
+#endif /* CONFIG_LIVEUPDATE */
+#endif /* _LINUX_LIVEUPDATE_H */
diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig
index eebe564b385d..f6b0bde188d9 100644
--- a/kernel/liveupdate/Kconfig
+++ b/kernel/liveupdate/Kconfig
@@ -1,7 +1,34 @@
# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (c) 2025, Google LLC.
+# Pasha Tatashin <pasha.tatashin@soleen.com>
+#
+# Live Update Orchestrator
+#
menu "Live Update"
+config LIVEUPDATE
+ bool "Live Update Orchestrator"
+ depends on KEXEC_HANDOVER
+ help
+ Enable the Live Update Orchestrator. Live Update is a mechanism,
+ typically based on kexec, that allows the kernel to be updated
+ while keeping selected devices operational across the transition.
+ These devices are intended to be reclaimed by the new kernel and
+ re-attached to their original workload without requiring a device
+ reset.
+
+ Ability to handover a device from current to the next kernel depends
+ on specific support within device drivers and related kernel
+ subsystems.
+
+ This feature primarily targets virtual machine hosts to quickly update
+ the kernel hypervisor with minimal disruption to the running virtual
+ machines.
+
+ If unsure, say N.
+
config KEXEC_HANDOVER
bool "kexec handover"
depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
index 72cf7a8e6739..b3c72c405780 100644
--- a/kernel/liveupdate/Makefile
+++ b/kernel/liveupdate/Makefile
@@ -5,3 +5,4 @@
obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
+obj-$(CONFIG_LIVEUPDATE) += luo_core.o
diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c
new file mode 100644
index 000000000000..8cee093807ff
--- /dev/null
+++ b/kernel/liveupdate/luo_core.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: Live Update Orchestrator (LUO)
+ *
+ * Live Update is a specialized, kexec-based reboot process that allows a
+ * running kernel to be updated from one version to another while preserving
+ * the state of selected resources and keeping designated hardware devices
+ * operational. For these devices, DMA activity may continue throughout the
+ * kernel transition.
+ *
+ * While the primary use case driving this work is supporting live updates of
+ * the Linux kernel when it is used as a hypervisor in cloud environments, the
+ * LUO framework itself is designed to be workload-agnostic. Much like Kernel
+ * Live Patching, which applies security fixes regardless of the workload,
+ * Live Update facilitates a full kernel version upgrade for any type of system.
+ *
+ * For example, a non-hypervisor system running an in-memory cache like
+ * memcached with many gigabytes of data can use LUO. The userspace service
+ * can place its cache into a memfd, have its state preserved by LUO, and
+ * restore it immediately after the kernel kexec.
+ *
+ * Whether the system is running virtual machines, containers, a
+ * high-performance database, or networking services, LUO's primary goal is to
+ * enable a full kernel update by preserving critical userspace state and
+ * keeping essential devices operational.
+ *
+ * The core of LUO is a state machine that tracks the progress of a live update,
+ * along with a callback API that allows other kernel subsystems to participate
+ * in the process. Example subsystems that can hook into LUO include: kvm,
+ * iommu, interrupts, vfio, participating filesystems, and memory management.
+ *
+ * LUO uses Kexec Handover to transfer memory state from the current kernel to
+ * the next kernel. For more details see
+ * Documentation/core-api/kho/concepts.rst.
+ *
+ * The LUO state machine ensures that operations are performed in the correct
+ * sequence and provides a mechanism to track and recover from potential
+ * failures.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/kobject.h>
+#include <linux/liveupdate.h>
+#include <linux/rwsem.h>
+#include <linux/string.h>
+#include "luo_internal.h"
+
+static DECLARE_RWSEM(luo_state_rwsem);
+
+static enum liveupdate_state luo_state = LIVEUPDATE_STATE_UNDEFINED;
+
+static const char *const luo_state_str[] = {
+ [LIVEUPDATE_STATE_UNDEFINED] = "undefined",
+ [LIVEUPDATE_STATE_NORMAL] = "normal",
+ [LIVEUPDATE_STATE_PREPARED] = "prepared",
+ [LIVEUPDATE_STATE_FROZEN] = "frozen",
+ [LIVEUPDATE_STATE_UPDATED] = "updated",
+};
+
+static bool luo_enabled;
+
+static int __init early_liveupdate_param(char *buf)
+{
+ return kstrtobool(buf, &luo_enabled);
+}
+early_param("liveupdate", early_liveupdate_param);
+
+/* Return true if the current state is equal to the provided state */
+static inline bool is_current_luo_state(enum liveupdate_state expected_state)
+{
+ return liveupdate_get_state() == expected_state;
+}
+
+static void __luo_set_state(enum liveupdate_state state)
+{
+ WRITE_ONCE(luo_state, state);
+}
+
+static inline void luo_set_state(enum liveupdate_state state)
+{
+ pr_info("Switched from [%s] to [%s] state\n",
+ luo_current_state_str(), luo_state_str[state]);
+ __luo_set_state(state);
+}
+
+static int luo_do_freeze_calls(void)
+{
+ return 0;
+}
+
+static void luo_do_finish_calls(void)
+{
+}
+
+/* Get the current state as a string */
+const char *luo_current_state_str(void)
+{
+ return luo_state_str[liveupdate_get_state()];
+}
+
+enum liveupdate_state liveupdate_get_state(void)
+{
+ return READ_ONCE(luo_state);
+}
+
+int luo_prepare(void)
+{
+ return 0;
+}
+
+/**
+ * luo_freeze() - Initiate the final freeze notification phase for live update.
+ *
+ * Attempts to transition the live update orchestrator state from
+ * %LIVEUPDATE_STATE_PREPARED to %LIVEUPDATE_STATE_FROZEN. This function is
+ * typically called just before the actual reboot system call (e.g., kexec)
+ * is invoked, either directly by the orchestration tool or potentially from
+ * within the reboot syscall path itself.
+ *
+ * @return 0: Success. Negative error otherwise. State is reverted to
+ * %LIVEUPDATE_STATE_NORMAL in case of an error during callbacks, and everything
+ * is canceled via cancel notifcation.
+ */
+int luo_freeze(void)
+{
+ int ret;
+
+ if (down_write_killable(&luo_state_rwsem)) {
+ pr_warn("[freeze] event canceled by user\n");
+ return -EAGAIN;
+ }
+
+ if (!is_current_luo_state(LIVEUPDATE_STATE_PREPARED)) {
+ pr_warn("Can't switch to [%s] from [%s] state\n",
+ luo_state_str[LIVEUPDATE_STATE_FROZEN],
+ luo_current_state_str());
+ up_write(&luo_state_rwsem);
+
+ return -EINVAL;
+ }
+
+ ret = luo_do_freeze_calls();
+ if (!ret)
+ luo_set_state(LIVEUPDATE_STATE_FROZEN);
+ else
+ luo_set_state(LIVEUPDATE_STATE_NORMAL);
+
+ up_write(&luo_state_rwsem);
+
+ return ret;
+}
+
+/**
+ * luo_finish - Finalize the live update process in the new kernel.
+ *
+ * This function is called after a successful live update reboot into a new
+ * kernel, once the new kernel is ready to transition to the normal operational
+ * state. It signals the completion of the live update sequence to subsystems.
+ *
+ * @return 0 on success, ``-EAGAIN`` if the state change was cancelled by the
+ * user while waiting for the lock, or ``-EINVAL`` if the orchestrator is not in
+ * the updated state.
+ */
+int luo_finish(void)
+{
+ if (down_write_killable(&luo_state_rwsem)) {
+ pr_warn("[finish] event canceled by user\n");
+ return -EAGAIN;
+ }
+
+ if (!is_current_luo_state(LIVEUPDATE_STATE_UPDATED)) {
+ pr_warn("Can't switch to [%s] from [%s] state\n",
+ luo_state_str[LIVEUPDATE_STATE_NORMAL],
+ luo_current_state_str());
+ up_write(&luo_state_rwsem);
+
+ return -EINVAL;
+ }
+
+ luo_do_finish_calls();
+ luo_set_state(LIVEUPDATE_STATE_NORMAL);
+
+ up_write(&luo_state_rwsem);
+
+ return 0;
+}
+
+int luo_cancel(void)
+{
+ return 0;
+}
+
+void luo_state_read_enter(void)
+{
+ down_read(&luo_state_rwsem);
+}
+
+void luo_state_read_exit(void)
+{
+ up_read(&luo_state_rwsem);
+}
+
+static int __init luo_startup(void)
+{
+ __luo_set_state(LIVEUPDATE_STATE_NORMAL);
+
+ return 0;
+}
+early_initcall(luo_startup);
+
+/* Public Functions */
+
+/**
+ * liveupdate_reboot() - Kernel reboot notifier for live update final
+ * serialization.
+ *
+ * This function is invoked directly from the reboot() syscall pathway if a
+ * reboot is initiated while the live update state is %LIVEUPDATE_STATE_PREPARED
+ * (i.e., if the user did not explicitly trigger the frozen state). It handles
+ * the implicit transition into the final frozen state.
+ *
+ * It triggers the %LIVEUPDATE_REBOOT event callbacks for participating
+ * subsystems. These callbacks must perform final state saving very quickly as
+ * they execute during the blackout period just before kexec.
+ *
+ * If any %LIVEUPDATE_FREEZE callback fails, this function triggers the
+ * %LIVEUPDATE_CANCEL event for all participants to revert their state, aborts
+ * the live update, and returns an error.
+ */
+int liveupdate_reboot(void)
+{
+ if (!is_current_luo_state(LIVEUPDATE_STATE_PREPARED))
+ return 0;
+
+ return luo_freeze();
+}
+EXPORT_SYMBOL_GPL(liveupdate_reboot);
+
+/**
+ * liveupdate_state_updated - Check if the system is in the live update
+ * 'updated' state.
+ *
+ * This function checks if the live update orchestrator is in the
+ * ``LIVEUPDATE_STATE_UPDATED`` state. This state indicates that the system has
+ * successfully rebooted into a new kernel as part of a live update, and the
+ * preserved devices are expected to be in the process of being reclaimed.
+ *
+ * This is typically used by subsystems during early boot of the new kernel
+ * to determine if they need to attempt to restore state from a previous
+ * live update.
+ *
+ * @return true if the system is in the ``LIVEUPDATE_STATE_UPDATED`` state,
+ * false otherwise.
+ */
+bool liveupdate_state_updated(void)
+{
+ return is_current_luo_state(LIVEUPDATE_STATE_UPDATED);
+}
+EXPORT_SYMBOL_GPL(liveupdate_state_updated);
+
+/**
+ * liveupdate_state_normal - Check if the system is in the live update 'normal'
+ * state.
+ *
+ * This function checks if the live update orchestrator is in the
+ * ``LIVEUPDATE_STATE_NORMAL`` state. This state indicates that no live update
+ * is in progress. It represents the default operational state of the system.
+ *
+ * This can be used to gate actions that should only be performed when no
+ * live update activity is occurring.
+ *
+ * @return true if the system is in the ``LIVEUPDATE_STATE_NORMAL`` state,
+ * false otherwise.
+ */
+bool liveupdate_state_normal(void)
+{
+ return is_current_luo_state(LIVEUPDATE_STATE_NORMAL);
+}
+EXPORT_SYMBOL_GPL(liveupdate_state_normal);
+
+/**
+ * liveupdate_enabled - Check if the live update feature is enabled.
+ *
+ * This function returns the state of the live update feature flag, which
+ * can be controlled via the ``liveupdate`` kernel command-line parameter.
+ *
+ * @return true if live update is enabled, false otherwise.
+ */
+bool liveupdate_enabled(void)
+{
+ return luo_enabled;
+}
+EXPORT_SYMBOL_GPL(liveupdate_enabled);
diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h
new file mode 100644
index 000000000000..3d10f3eb20a7
--- /dev/null
+++ b/kernel/liveupdate/luo_internal.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#ifndef _LINUX_LUO_INTERNAL_H
+#define _LINUX_LUO_INTERNAL_H
+
+int luo_cancel(void);
+int luo_prepare(void);
+int luo_freeze(void);
+int luo_finish(void);
+
+void luo_state_read_enter(void);
+void luo_state_read_exit(void);
+
+const char *luo_current_state_str(void);
+
+#endif /* _LINUX_LUO_INTERNAL_H */
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 11/32] liveupdate: luo_core: integrate with KHO
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Integrate the LUO with the KHO framework to enable passing LUO state
across a kexec reboot.
When LUO is transitioned to a "prepared" state, it tells KHO to
finalize, so all memory segments that were added to KHO preservation
list are getting preserved. After "Prepared" state no new segments
can be preserved. If LUO is canceled, it also tells KHO to cancel the
serialization, and therefore, later LUO can go back into the prepared
state.
This patch introduces the following changes:
- During the KHO finalization phase allocate FDT blob.
- Populate this FDT with a LUO compatibility string ("luo-v1").
- Implement a KHO notifier
LUO now depends on `CONFIG_KEXEC_HANDOVER`. The core state transition
logic (`luo_do_*_calls`) remains unimplemented in this patch.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/liveupdate/luo_core.c | 214 ++++++++++++++++++++++++++++++++++-
1 file changed, 211 insertions(+), 3 deletions(-)
diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c
index 8cee093807ff..c80a1f188359 100644
--- a/kernel/liveupdate/luo_core.c
+++ b/kernel/liveupdate/luo_core.c
@@ -47,9 +47,12 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/err.h>
+#include <linux/kexec_handover.h>
#include <linux/kobject.h>
+#include <linux/libfdt.h>
#include <linux/liveupdate.h>
#include <linux/rwsem.h>
+#include <linux/sizes.h>
#include <linux/string.h>
#include "luo_internal.h"
@@ -67,6 +70,21 @@ static const char *const luo_state_str[] = {
static bool luo_enabled;
+static void *luo_fdt_out;
+static void *luo_fdt_in;
+
+/*
+ * The LUO FDT size depends on the number of participating subsystems,
+ *
+ * The current fixed size (4K) is large enough to handle reasonable number of
+ * preserved entities. If this size ever becomes insufficient, it can either be
+ * increased, or a dynamic size calculation mechanism could be implemented in
+ * the future.
+ */
+#define LUO_FDT_SIZE PAGE_SIZE
+#define LUO_KHO_ENTRY_NAME "LUO"
+#define LUO_COMPATIBLE "luo-v1"
+
static int __init early_liveupdate_param(char *buf)
{
return kstrtobool(buf, &luo_enabled);
@@ -91,6 +109,60 @@ static inline void luo_set_state(enum liveupdate_state state)
__luo_set_state(state);
}
+/* Called during the prepare phase, to create LUO fdt tree */
+static int luo_fdt_setup(void)
+{
+ void *fdt_out;
+ int ret;
+
+ fdt_out = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(LUO_FDT_SIZE));
+ if (!fdt_out) {
+ pr_err("failed to allocate FDT memory\n");
+ return -ENOMEM;
+ }
+
+ ret = fdt_create_empty_tree(fdt_out, LUO_FDT_SIZE);
+ if (ret)
+ goto exit_free;
+
+ ret = fdt_setprop_string(fdt_out, 0, "compatible", LUO_COMPATIBLE);
+ if (ret)
+ goto exit_free;
+
+ ret = kho_preserve_phys(__pa(fdt_out), LUO_FDT_SIZE);
+ if (ret)
+ goto exit_free;
+
+ ret = kho_add_subtree(LUO_KHO_ENTRY_NAME, fdt_out);
+ if (ret)
+ goto exit_unpreserve;
+ luo_fdt_out = fdt_out;
+
+ return 0;
+
+exit_unpreserve:
+ WARN_ON_ONCE(kho_unpreserve_phys(__pa(fdt_out), LUO_FDT_SIZE));
+exit_free:
+ free_pages((unsigned long)fdt_out, get_order(LUO_FDT_SIZE));
+ pr_err("failed to prepare LUO FDT: %d\n", ret);
+
+ return ret;
+}
+
+static void luo_fdt_destroy(void)
+{
+ WARN_ON_ONCE(kho_unpreserve_phys(__pa(luo_fdt_out), LUO_FDT_SIZE));
+ kho_remove_subtree(luo_fdt_out);
+ free_pages((unsigned long)luo_fdt_out, get_order(LUO_FDT_SIZE));
+ luo_fdt_out = NULL;
+}
+
+static int luo_do_prepare_calls(void)
+{
+ return 0;
+}
+
static int luo_do_freeze_calls(void)
{
return 0;
@@ -100,6 +172,71 @@ static void luo_do_finish_calls(void)
{
}
+static void luo_do_cancel_calls(void)
+{
+}
+
+static int __luo_prepare(void)
+{
+ int ret;
+
+ if (down_write_killable(&luo_state_rwsem)) {
+ pr_warn("[prepare] event canceled by user\n");
+ return -EAGAIN;
+ }
+
+ if (!is_current_luo_state(LIVEUPDATE_STATE_NORMAL)) {
+ pr_warn("Can't switch to [%s] from [%s] state\n",
+ luo_state_str[LIVEUPDATE_STATE_PREPARED],
+ luo_current_state_str());
+ ret = -EINVAL;
+ goto exit_unlock;
+ }
+
+ ret = luo_fdt_setup();
+ if (ret)
+ goto exit_unlock;
+
+ ret = luo_do_prepare_calls();
+ if (ret) {
+ luo_fdt_destroy();
+ goto exit_unlock;
+ }
+
+ luo_set_state(LIVEUPDATE_STATE_PREPARED);
+
+exit_unlock:
+ up_write(&luo_state_rwsem);
+
+ return ret;
+}
+
+static int __luo_cancel(void)
+{
+ if (down_write_killable(&luo_state_rwsem)) {
+ pr_warn("[cancel] event canceled by user\n");
+ return -EAGAIN;
+ }
+
+ if (!is_current_luo_state(LIVEUPDATE_STATE_PREPARED) &&
+ !is_current_luo_state(LIVEUPDATE_STATE_FROZEN)) {
+ pr_warn("Can't switch to [%s] from [%s] state\n",
+ luo_state_str[LIVEUPDATE_STATE_NORMAL],
+ luo_current_state_str());
+ up_write(&luo_state_rwsem);
+
+ return -EINVAL;
+ }
+
+ luo_do_cancel_calls();
+ luo_fdt_destroy();
+ luo_set_state(LIVEUPDATE_STATE_NORMAL);
+
+ up_write(&luo_state_rwsem);
+
+ return 0;
+}
+
/* Get the current state as a string */
const char *luo_current_state_str(void)
{
@@ -111,9 +248,28 @@ enum liveupdate_state liveupdate_get_state(void)
return READ_ONCE(luo_state);
}
+/**
+ * luo_prepare - Initiate the live update preparation phase.
+ *
+ * This function is called to begin the live update process. It attempts to
+ * transition the luo to the ``LIVEUPDATE_STATE_PREPARED`` state.
+ *
+ * If the calls complete successfully, the orchestrator state is set
+ * to ``LIVEUPDATE_STATE_PREPARED``. If any call fails a
+ * ``LIVEUPDATE_CANCEL`` is sent to roll back any actions.
+ *
+ * @return 0 on success, ``-EAGAIN`` if the state change was cancelled by the
+ * user while waiting for the lock, ``-EINVAL`` if the orchestrator is not in
+ * the normal state, or a negative error code returned by the calls.
+ */
int luo_prepare(void)
{
- return 0;
+ int err = __luo_prepare();
+
+ if (err)
+ return err;
+
+ return kho_finalize();
}
/**
@@ -193,9 +349,28 @@ int luo_finish(void)
return 0;
}
+/**
+ * luo_cancel - Cancel the ongoing live update from prepared or frozen states.
+ *
+ * This function is called to abort a live update that is currently in the
+ * ``LIVEUPDATE_STATE_PREPARED`` state.
+ *
+ * If the state is correct, it triggers the ``LIVEUPDATE_CANCEL`` notifier chain
+ * to allow subsystems to undo any actions performed during the prepare or
+ * freeze events. Finally, the orchestrator state is transitioned back to
+ * ``LIVEUPDATE_STATE_NORMAL``.
+ *
+ * @return 0 on success, or ``-EAGAIN`` if the state change was cancelled by the
+ * user while waiting for the lock.
+ */
int luo_cancel(void)
{
- return 0;
+ int err = kho_abort();
+
+ if (err)
+ return err;
+
+ return __luo_cancel();
}
void luo_state_read_enter(void)
@@ -210,7 +385,40 @@ void luo_state_read_exit(void)
static int __init luo_startup(void)
{
- __luo_set_state(LIVEUPDATE_STATE_NORMAL);
+ phys_addr_t fdt_phys;
+ int ret;
+
+ if (!kho_is_enabled()) {
+ if (luo_enabled)
+ pr_warn("Disabling liveupdate because KHO is disabled\n");
+ luo_enabled = false;
+ return 0;
+ }
+
+ /*
+ * Retrieve LUO subtree, and verify its format. Panic in case of
+ * exceptions, since machine devices and memory is in unpredictable
+ * state.
+ */
+ ret = kho_retrieve_subtree(LUO_KHO_ENTRY_NAME, &fdt_phys);
+ if (ret) {
+ if (ret != -ENOENT) {
+ panic("failed to retrieve FDT '%s' from KHO: %d\n",
+ LUO_KHO_ENTRY_NAME, ret);
+ }
+ __luo_set_state(LIVEUPDATE_STATE_NORMAL);
+
+ return 0;
+ }
+
+ luo_fdt_in = __va(fdt_phys);
+ ret = fdt_node_check_compatible(luo_fdt_in, 0, LUO_COMPATIBLE);
+ if (ret) {
+ panic("FDT '%s' is incompatible with '%s' [%d]\n",
+ LUO_KHO_ENTRY_NAME, LUO_COMPATIBLE, ret);
+ }
+
+ __luo_set_state(LIVEUPDATE_STATE_UPDATED);
return 0;
}
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 12/32] liveupdate: luo_subsystems: add subsystem registration
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Introduce the framework for kernel subsystems (e.g., KVM, IOMMU, device
drivers) to register with LUO and participate in the live update process
via callbacks.
Subsystem Registration:
- Defines struct liveupdate_subsystem in linux/liveupdate.h,
which subsystems use to provide their name and optional callbacks
(prepare, freeze, cancel, finish). The callbacks accept
a u64 *data intended for passing state/handles.
- Exports liveupdate_register_subsystem() and
liveupdate_unregister_subsystem() API functions.
- Adds drivers/misc/liveupdate/luo_subsystems.c to manage a list
of registered subsystems.
Registration/unregistration is restricted to
specific LUO states (NORMAL/UPDATED).
Callback Framework:
- The main luo_core.c state transition functions
now delegate to new luo_do_subsystems_*_calls() functions
defined in luo_subsystems.c.
- These new functions are intended to iterate through the registered
subsystems and invoke their corresponding callbacks.
FDT Integration:
- Adds a /subsystems subnode within the main LUO FDT created in
luo_core.c. This node has its own compatibility string
(subsystems-v1).
- luo_subsystems_fdt_setup() populates this node by adding a
property for each registered subsystem, using the subsystem's
name.
Currently, these properties are initialized with a placeholder
u64 value (0).
- luo_subsystems_startup() is called from luo_core.c on boot to
find and validate the /subsystems node in the FDT received via
KHO. It panics if the node is missing or incompatible.
- Adds a stub API function liveupdate_get_subsystem_data() intended
for subsystems to retrieve their persisted u64 data from the FDT
in the new kernel.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/liveupdate.h | 61 +++++++
kernel/liveupdate/Makefile | 1 +
kernel/liveupdate/luo_core.c | 19 +-
kernel/liveupdate/luo_internal.h | 7 +
kernel/liveupdate/luo_subsystems.c | 284 +++++++++++++++++++++++++++++
5 files changed, 370 insertions(+), 2 deletions(-)
create mode 100644 kernel/liveupdate/luo_subsystems.c
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index da8f05c81e51..fed68b9ab32b 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -88,6 +88,47 @@ enum liveupdate_state {
LIVEUPDATE_STATE_UPDATED = 4,
};
+/**
+ * struct liveupdate_subsystem_ops - LUO events callback functions
+ * @prepare: Optional. Called during LUO prepare phase. Should perform
+ * preparatory actions and can store a u64 handle/state
+ * via the 'data' pointer for use in later callbacks.
+ * Return 0 on success, negative error code on failure.
+ * @freeze: Optional. Called during LUO freeze event (before actual jump
+ * to new kernel). Should perform final state saving actions and
+ * can update the u64 handle/state via the 'data' pointer. Retur:
+ * 0 on success, negative error code on failure.
+ * @cancel: Optional. Called if the live update process is canceled after
+ * prepare (or freeze) was called. Receives the u64 data
+ * set by prepare/freeze. Used for cleanup.
+ * @finish: Optional. Called after the live update is finished in the new
+ * kernel.
+ * Receives the u64 data set by prepare/freeze. Used for cleanup.
+ */
+struct liveupdate_subsystem_ops {
+ int (*prepare)(void *arg, u64 *data);
+ int (*freeze)(void *arg, u64 *data);
+ void (*cancel)(void *arg, u64 data);
+ void (*finish)(void *arg, u64 data);
+};
+
+/**
+ * struct liveupdate_subsystem - Represents a subsystem participating in LUO
+ * @ops: Callback functions
+ * @name: Unique name identifying the subsystem.
+ * @arg: Add this argument to callback functions.
+ * @list: List head used internally by LUO. Should not be modified by
+ * caller after registration.
+ * @private_data: For LUO internal use, cached value of data field.
+ */
+struct liveupdate_subsystem {
+ const struct liveupdate_subsystem_ops *ops;
+ const char *name;
+ void *arg;
+ struct list_head list;
+ u64 private_data;
+};
+
#ifdef CONFIG_LIVEUPDATE
/* Return true if live update orchestrator is enabled */
@@ -109,6 +150,10 @@ bool liveupdate_state_normal(void);
enum liveupdate_state liveupdate_get_state(void);
+int liveupdate_register_subsystem(struct liveupdate_subsystem *h);
+int liveupdate_unregister_subsystem(struct liveupdate_subsystem *h);
+int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h, u64 *data);
+
#else /* CONFIG_LIVEUPDATE */
static inline int liveupdate_reboot(void)
@@ -136,5 +181,21 @@ static inline enum liveupdate_state liveupdate_get_state(void)
return LIVEUPDATE_STATE_NORMAL;
}
+static inline int liveupdate_register_subsystem(struct liveupdate_subsystem *h)
+{
+ return 0;
+}
+
+static inline int liveupdate_unregister_subsystem(struct liveupdate_subsystem *h)
+{
+ return 0;
+}
+
+static inline int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h,
+ u64 *data)
+{
+ return -ENODATA;
+}
+
#endif /* CONFIG_LIVEUPDATE */
#endif /* _LINUX_LIVEUPDATE_H */
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
index b3c72c405780..999208a1fdbb 100644
--- a/kernel/liveupdate/Makefile
+++ b/kernel/liveupdate/Makefile
@@ -6,3 +6,4 @@
obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
obj-$(CONFIG_LIVEUPDATE) += luo_core.o
+obj-$(CONFIG_LIVEUPDATE) += luo_subsystems.o
diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c
index c80a1f188359..fff84c51d986 100644
--- a/kernel/liveupdate/luo_core.c
+++ b/kernel/liveupdate/luo_core.c
@@ -130,6 +130,10 @@ static int luo_fdt_setup(void)
if (ret)
goto exit_free;
+ ret = luo_subsystems_fdt_setup(fdt_out);
+ if (ret)
+ goto exit_free;
+
ret = kho_preserve_phys(__pa(fdt_out), LUO_FDT_SIZE);
if (ret)
goto exit_free;
@@ -160,20 +164,30 @@ static void luo_fdt_destroy(void)
static int luo_do_prepare_calls(void)
{
- return 0;
+ int ret;
+
+ ret = luo_do_subsystems_prepare_calls();
+
+ return ret;
}
static int luo_do_freeze_calls(void)
{
- return 0;
+ int ret;
+
+ ret = luo_do_subsystems_freeze_calls();
+
+ return ret;
}
static void luo_do_finish_calls(void)
{
+ luo_do_subsystems_finish_calls();
}
static void luo_do_cancel_calls(void)
{
+ luo_do_subsystems_cancel_calls();
}
static int __luo_prepare(void)
@@ -419,6 +433,7 @@ static int __init luo_startup(void)
}
__luo_set_state(LIVEUPDATE_STATE_UPDATED);
+ luo_subsystems_startup(luo_fdt_in);
return 0;
}
diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h
index 3d10f3eb20a7..98bf799adb61 100644
--- a/kernel/liveupdate/luo_internal.h
+++ b/kernel/liveupdate/luo_internal.h
@@ -18,4 +18,11 @@ void luo_state_read_exit(void);
const char *luo_current_state_str(void);
+void luo_subsystems_startup(void *fdt);
+int luo_subsystems_fdt_setup(void *fdt);
+int luo_do_subsystems_prepare_calls(void);
+int luo_do_subsystems_freeze_calls(void);
+void luo_do_subsystems_finish_calls(void);
+void luo_do_subsystems_cancel_calls(void);
+
#endif /* _LINUX_LUO_INTERNAL_H */
diff --git a/kernel/liveupdate/luo_subsystems.c b/kernel/liveupdate/luo_subsystems.c
new file mode 100644
index 000000000000..436929a17de0
--- /dev/null
+++ b/kernel/liveupdate/luo_subsystems.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO Subsystems support
+ *
+ * Various kernel subsystems register with the Live Update Orchestrator to
+ * participate in the live update process. These subsystems are notified at
+ * different stages of the live update sequence, allowing them to serialize
+ * device state before the reboot and restore it afterwards. Examples include
+ * the device layer, interrupt controllers, KVM, IOMMU, and specific device
+ * drivers.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/libfdt.h>
+#include <linux/liveupdate.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include "luo_internal.h"
+
+#define LUO_SUBSYSTEMS_NODE_NAME "subsystems"
+#define LUO_SUBSYSTEMS_COMPATIBLE "subsystems-v1"
+
+static DEFINE_MUTEX(luo_subsystem_list_mutex);
+static LIST_HEAD(luo_subsystems_list);
+static void *luo_fdt_out;
+static void *luo_fdt_in;
+
+/**
+ * luo_subsystems_fdt_setup - Adds and populates the 'subsystems' node in the
+ * FDT.
+ * @fdt: Pointer to the LUO FDT blob.
+ *
+ * Add subsystems node and each subsystem to the LUO FDT blob.
+ *
+ * Returns: 0 on success, negative errno on failure.
+ */
+int luo_subsystems_fdt_setup(void *fdt)
+{
+ struct liveupdate_subsystem *subsystem;
+ const u64 zero_data = 0;
+ int ret, node_offset;
+
+ ret = fdt_add_subnode(fdt, 0, LUO_SUBSYSTEMS_NODE_NAME);
+ if (ret < 0)
+ goto exit_error;
+
+ node_offset = ret;
+ ret = fdt_setprop_string(fdt, node_offset, "compatible",
+ LUO_SUBSYSTEMS_COMPATIBLE);
+ if (ret < 0)
+ goto exit_error;
+
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ ret = fdt_setprop(fdt, node_offset, subsystem->name,
+ &zero_data, sizeof(zero_data));
+ if (ret < 0)
+ goto exit_error;
+ }
+
+ luo_fdt_out = fdt;
+ return 0;
+exit_error:
+ pr_err("Failed to setup 'subsystems' node to FDT: %s\n",
+ fdt_strerror(ret));
+ return -ENOSPC;
+}
+
+/**
+ * luo_subsystems_startup - Validates the LUO subsystems FDT node at startup.
+ * @fdt: Pointer to the LUO FDT blob passed from the previous kernel.
+ *
+ * This __init function checks the existence and validity of the '/subsystems'
+ * node in the FDT. This node is considered mandatory. It calls panic() if
+ * the node is missing, inaccessible, or invalid (e.g., missing compatible,
+ * wrong compatible string), indicating a critical configuration error for LUO.
+ */
+void __init luo_subsystems_startup(void *fdt)
+{
+ int ret, node_offset;
+
+ node_offset = fdt_subnode_offset(fdt, 0, LUO_SUBSYSTEMS_NODE_NAME);
+ if (node_offset < 0)
+ panic("Failed to find /subsystems node\n");
+
+ ret = fdt_node_check_compatible(fdt, node_offset,
+ LUO_SUBSYSTEMS_COMPATIBLE);
+ if (ret) {
+ panic("FDT '%s' is incompatible with '%s' [%d]\n",
+ LUO_SUBSYSTEMS_NODE_NAME, LUO_SUBSYSTEMS_COMPATIBLE, ret);
+ }
+ luo_fdt_in = fdt;
+}
+
+/**
+ * luo_do_subsystems_prepare_calls - Calls prepare callbacks and updates FDT
+ * if all prepares succeed. Handles cancellation on failure.
+ *
+ * Phase 1: Calls 'prepare' for all subsystems and stores results temporarily.
+ * If any 'prepare' fails, calls 'cancel' on previously prepared subsystems
+ * and returns the error.
+ * Phase 2: If all 'prepare' calls succeeded, writes the stored data to the FDT.
+ * If any FDT write fails, calls 'cancel' on *all* prepared subsystems and
+ * returns the FDT error.
+ *
+ * Returns: 0 on success. Negative errno on failure.
+ */
+int luo_do_subsystems_prepare_calls(void)
+{
+ return 0;
+}
+
+/**
+ * luo_do_subsystems_freeze_calls - Calls freeze callbacks and updates FDT
+ * if all freezes succeed. Handles cancellation on failure.
+ *
+ * Phase 1: Calls 'freeze' for all subsystems and stores results temporarily.
+ * If any 'freeze' fails, calls 'cancel' on previously called subsystems
+ * and returns the error.
+ * Phase 2: If all 'freeze' calls succeeded, writes the stored data to the FDT.
+ * If any FDT write fails, calls 'cancel' on *all* subsystems and
+ * returns the FDT error.
+ *
+ * Returns: 0 on success. Negative errno on failure.
+ */
+int luo_do_subsystems_freeze_calls(void)
+{
+ return 0;
+}
+
+/**
+ * luo_do_subsystems_finish_calls- Calls finish callbacks for all subsystems.
+ *
+ * This function is called at the end of live update cycle to do the final
+ * clean-up or housekeeping of the post-live update states.
+ */
+void luo_do_subsystems_finish_calls(void)
+{
+}
+
+/**
+ * luo_do_subsystems_cancel_calls - Calls cancel callbacks for all subsystems.
+ *
+ * This function is typically called when the live update process needs to be
+ * aborted externally, for example, after the prepare phase may have run but
+ * before actual reboot. It iterates through all registered subsystems and calls
+ * the 'cancel' callback for those that implement it and likely completed
+ * prepare.
+ */
+void luo_do_subsystems_cancel_calls(void)
+{
+}
+
+/**
+ * liveupdate_register_subsystem - Register a kernel subsystem handler with LUO
+ * @h: Pointer to the liveupdate_subsystem structure allocated and populated
+ * by the calling subsystem.
+ *
+ * Registers a subsystem handler that provides callbacks for different events
+ * of the live update cycle. Registration is typically done during the
+ * subsystem's module init or core initialization.
+ *
+ * Can only be called when LUO is in the NORMAL or UPDATED states.
+ * The provided name (@h->name) must be unique among registered subsystems.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int liveupdate_register_subsystem(struct liveupdate_subsystem *h)
+{
+ struct liveupdate_subsystem *iter;
+ int ret = 0;
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ mutex_lock(&luo_subsystem_list_mutex);
+ list_for_each_entry(iter, &luo_subsystems_list, list) {
+ if (iter == h) {
+ pr_warn("Subsystem '%s' (%p) already registered.\n",
+ h->name, h);
+ ret = -EEXIST;
+ goto out_unlock;
+ }
+
+ if (!strcmp(iter->name, h->name)) {
+ pr_err("Subsystem with name '%s' already registered.\n",
+ h->name);
+ ret = -EEXIST;
+ goto out_unlock;
+ }
+ }
+
+ INIT_LIST_HEAD(&h->list);
+ list_add_tail(&h->list, &luo_subsystems_list);
+
+out_unlock:
+ mutex_unlock(&luo_subsystem_list_mutex);
+ luo_state_read_exit();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(liveupdate_register_subsystem);
+
+/**
+ * liveupdate_unregister_subsystem - Unregister a kernel subsystem handler from
+ * LUO
+ * @h: Pointer to the same liveupdate_subsystem structure that was used during
+ * registration.
+ *
+ * Unregisters a previously registered subsystem handler. Typically called
+ * during module exit or subsystem teardown. LUO removes the structure from its
+ * internal list; the caller is responsible for any necessary memory cleanup
+ * of the structure itself.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ * -EINVAL if h is NULL.
+ * -ENOENT if the specified handler @h is not found in the registration list.
+ * -EBUSY if LUO is not in the NORMAL state.
+ */
+int liveupdate_unregister_subsystem(struct liveupdate_subsystem *h)
+{
+ struct liveupdate_subsystem *iter;
+ bool found = false;
+ int ret = 0;
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ mutex_lock(&luo_subsystem_list_mutex);
+ list_for_each_entry(iter, &luo_subsystems_list, list) {
+ if (iter == h) {
+ found = true;
+ break;
+ }
+ }
+
+ if (found) {
+ list_del_init(&h->list);
+ } else {
+ pr_warn("Subsystem handler '%s' not found for unregistration.\n",
+ h->name);
+ ret = -ENOENT;
+ }
+
+ mutex_unlock(&luo_subsystem_list_mutex);
+ luo_state_read_exit();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(liveupdate_unregister_subsystem);
+
+/**
+ * liveupdate_get_subsystem_data - Retrieve raw private data for a subsystem
+ * from FDT.
+ * @h: Pointer to the liveupdate_subsystem structure representing the
+ * subsystem instance. The 'name' field is used to find the property.
+ * @data: Output pointer where the subsystem's raw private u64 data will be
+ * stored via memcpy.
+ *
+ * Reads the 8-byte data property associated with the subsystem @h->name
+ * directly from the '/subsystems' node within the globally accessible
+ * 'luo_fdt_in' blob. Returns appropriate error codes if inputs are invalid, or
+ * nodes/properties are missing or invalid.
+ *
+ * Return: 0 on success. -ENOENT on error.
+ */
+int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h, u64 *data)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(liveupdate_get_subsystem_data);
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 13/32] liveupdate: luo_subsystems: implement subsystem callbacks
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Implement the core logic within luo_subsystems.c to handle the
invocation of registered subsystem callbacks and manage the persistence
of their state via the LUO FDT. This replaces the stub implementations
from the previous patch.
This completes the core mechanism enabling subsystems to actively
participate in the LUO state machine, execute phase-specific logic, and
persist/restore a u64 state across the live update transition
using the FDT.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/liveupdate/luo_subsystems.c | 140 ++++++++++++++++++++++++++++-
1 file changed, 138 insertions(+), 2 deletions(-)
diff --git a/kernel/liveupdate/luo_subsystems.c b/kernel/liveupdate/luo_subsystems.c
index 436929a17de0..0e0070d01584 100644
--- a/kernel/liveupdate/luo_subsystems.c
+++ b/kernel/liveupdate/luo_subsystems.c
@@ -99,6 +99,66 @@ void __init luo_subsystems_startup(void *fdt)
luo_fdt_in = fdt;
}
+static void __luo_do_subsystems_cancel_calls(struct liveupdate_subsystem *boundary_subsystem)
+{
+ struct liveupdate_subsystem *subsystem;
+
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ if (subsystem == boundary_subsystem)
+ break;
+
+ if (subsystem->ops->cancel) {
+ subsystem->ops->cancel(subsystem->arg,
+ subsystem->private_data);
+ }
+ subsystem->private_data = 0;
+ }
+}
+
+static void luo_subsystems_retrieve_data_from_fdt(void)
+{
+ struct liveupdate_subsystem *subsystem;
+ int node_offset, prop_len;
+ const void *prop;
+
+ if (!luo_fdt_in)
+ return;
+
+ node_offset = fdt_subnode_offset(luo_fdt_in, 0,
+ LUO_SUBSYSTEMS_NODE_NAME);
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ prop = fdt_getprop(luo_fdt_in, node_offset,
+ subsystem->name, &prop_len);
+
+ if (!prop || prop_len != sizeof(u64)) {
+ panic("In FDT node '/%s' can't find property '%s': %s\n",
+ LUO_SUBSYSTEMS_NODE_NAME, subsystem->name,
+ fdt_strerror(node_offset));
+ }
+ memcpy(&subsystem->private_data, prop, sizeof(u64));
+ }
+}
+
+static int luo_subsystems_commit_data_to_fdt(void)
+{
+ struct liveupdate_subsystem *subsystem;
+ int ret, node_offset;
+
+ node_offset = fdt_subnode_offset(luo_fdt_out, 0,
+ LUO_SUBSYSTEMS_NODE_NAME);
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ ret = fdt_setprop(luo_fdt_out, node_offset, subsystem->name,
+ &subsystem->private_data, sizeof(u64));
+ if (ret < 0) {
+ pr_err("Failed to set FDT property for subsystem '%s' %s\n",
+ subsystem->name, fdt_strerror(ret));
+ return -ENOENT;
+ }
+ }
+
+ return 0;
+}
+
/**
* luo_do_subsystems_prepare_calls - Calls prepare callbacks and updates FDT
* if all prepares succeed. Handles cancellation on failure.
@@ -114,7 +174,29 @@ void __init luo_subsystems_startup(void *fdt)
*/
int luo_do_subsystems_prepare_calls(void)
{
- return 0;
+ struct liveupdate_subsystem *subsystem;
+ int ret;
+
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ if (!subsystem->ops->prepare)
+ continue;
+
+ ret = subsystem->ops->prepare(subsystem->arg,
+ &subsystem->private_data);
+ if (ret < 0) {
+ pr_err("Subsystem '%s' prepare callback failed [%d]\n",
+ subsystem->name, ret);
+ __luo_do_subsystems_cancel_calls(subsystem);
+
+ return ret;
+ }
+ }
+
+ ret = luo_subsystems_commit_data_to_fdt();
+ if (ret)
+ __luo_do_subsystems_cancel_calls(NULL);
+
+ return ret;
}
/**
@@ -132,7 +214,29 @@ int luo_do_subsystems_prepare_calls(void)
*/
int luo_do_subsystems_freeze_calls(void)
{
- return 0;
+ struct liveupdate_subsystem *subsystem;
+ int ret;
+
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ if (!subsystem->ops->freeze)
+ continue;
+
+ ret = subsystem->ops->freeze(subsystem->arg,
+ &subsystem->private_data);
+ if (ret < 0) {
+ pr_err("Subsystem '%s' freeze callback failed [%d]\n",
+ subsystem->name, ret);
+ __luo_do_subsystems_cancel_calls(subsystem);
+
+ return ret;
+ }
+ }
+
+ ret = luo_subsystems_commit_data_to_fdt();
+ if (ret)
+ __luo_do_subsystems_cancel_calls(NULL);
+
+ return ret;
}
/**
@@ -143,6 +247,17 @@ int luo_do_subsystems_freeze_calls(void)
*/
void luo_do_subsystems_finish_calls(void)
{
+ struct liveupdate_subsystem *subsystem;
+
+ luo_subsystems_retrieve_data_from_fdt();
+
+ list_for_each_entry(subsystem, &luo_subsystems_list, list) {
+ if (subsystem->ops->finish) {
+ subsystem->ops->finish(subsystem->arg,
+ subsystem->private_data);
+ }
+ subsystem->private_data = 0;
+ }
}
/**
@@ -156,6 +271,8 @@ void luo_do_subsystems_finish_calls(void)
*/
void luo_do_subsystems_cancel_calls(void)
{
+ __luo_do_subsystems_cancel_calls(NULL);
+ luo_subsystems_commit_data_to_fdt();
}
/**
@@ -279,6 +396,25 @@ EXPORT_SYMBOL_GPL(liveupdate_unregister_subsystem);
*/
int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h, u64 *data)
{
+ int node_offset, prop_len;
+ const void *prop;
+
+ luo_state_read_enter();
+ if (WARN_ON_ONCE(!luo_fdt_in || !liveupdate_state_updated())) {
+ luo_state_read_exit();
+ return -ENOENT;
+ }
+
+ node_offset = fdt_subnode_offset(luo_fdt_in, 0,
+ LUO_SUBSYSTEMS_NODE_NAME);
+ prop = fdt_getprop(luo_fdt_in, node_offset, h->name, &prop_len);
+ if (!prop || prop_len != sizeof(u64)) {
+ luo_state_read_exit();
+ return -ENOENT;
+ }
+ memcpy(data, prop, sizeof(u64));
+ luo_state_read_exit();
+
return 0;
}
EXPORT_SYMBOL_GPL(liveupdate_get_subsystem_data);
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 14/32] liveupdate: luo_files: add infrastructure for FDs
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Introduce the framework within LUO to support preserving specific types
of file descriptors across a live update transition. This allows
stateful FDs (like memfds or vfio FDs used by VMs) to be recreated in
the new kernel.
Note: The core logic for iterating through the luo_files_list and
invoking the handler callbacks (prepare, freeze, cancel, finish)
within luo_do_files_*_calls, as well as managing the u64 data
persistence via the FDT for individual files, is currently implemented
as stubs in this patch. This patch sets up the registration, FDT layout,
and retrieval framework.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
include/linux/liveupdate.h | 68 ++++
kernel/liveupdate/Makefile | 1 +
kernel/liveupdate/luo_files.c | 663 +++++++++++++++++++++++++++++++
kernel/liveupdate/luo_internal.h | 4 +
4 files changed, 736 insertions(+)
create mode 100644 kernel/liveupdate/luo_files.c
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index fed68b9ab32b..28a8aa4cafca 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -88,6 +88,61 @@ enum liveupdate_state {
LIVEUPDATE_STATE_UPDATED = 4,
};
+struct file;
+
+/**
+ * struct liveupdate_file_ops - Callbacks for for live-updatable files.
+ * @prepare: Optional. Saves state for a specific file instance (@file,
+ * @arg) before update, potentially returning value via @data.
+ * Returns 0 on success, negative errno on failure.
+ * @freeze: Optional. Performs final actions just before kernel
+ * transition, potentially reading/updating the handle via
+ * @data.
+ * Returns 0 on success, negative errno on failure.
+ * @cancel: Optional. Cleans up state/resources if update is aborted
+ * after prepare/freeze succeeded, using the @data handle (by
+ * value) from the successful prepare. Returns void.
+ * @finish: Optional. Performs final cleanup in the new kernel using the
+ * preserved @data handle (by value). Returns void.
+ * @retrieve: Retrieve the preserved file. Must be called before finish.
+ * @can_preserve: callback to determine if @file with associated context (@arg)
+ * can be preserved by this handler.
+ * Return bool (true if preservable, false otherwise).
+ */
+struct liveupdate_file_ops {
+ int (*prepare)(struct file *file, void *arg, u64 *data);
+ int (*freeze)(struct file *file, void *arg, u64 *data);
+ void (*cancel)(struct file *file, void *arg, u64 data);
+ void (*finish)(struct file *file, void *arg, u64 data, bool reclaimed);
+ int (*retrieve)(void *arg, u64 data, struct file **file);
+ bool (*can_preserve)(struct file *file, void *arg);
+};
+
+/**
+ * struct liveupdate_file_handler - Represents a handler for a live-updatable
+ * file type.
+ * @ops: Callback functions
+ * @compatible: The compatibility string (e.g., "memfd-v1", "vfiofd-v1")
+ * that uniquely identifies the file type this handler supports.
+ * This is matched against the compatible string associated with
+ * individual &struct liveupdate_file instances.
+ * @arg: An opaque pointer to implementation-specific context data
+ * associated with this file handler registration.
+ * @list: used for linking this handler instance into a global list of
+ * registered file handlers.
+ *
+ * Modules that want to support live update for specific file types should
+ * register an instance of this structure. LUO uses this registration to
+ * determine if a given file can be preserved and to find the appropriate
+ * operations to manage its state across the update.
+ */
+struct liveupdate_file_handler {
+ const struct liveupdate_file_ops *ops;
+ const char *compatible;
+ void *arg;
+ struct list_head list;
+};
+
/**
* struct liveupdate_subsystem_ops - LUO events callback functions
* @prepare: Optional. Called during LUO prepare phase. Should perform
@@ -154,6 +209,9 @@ int liveupdate_register_subsystem(struct liveupdate_subsystem *h);
int liveupdate_unregister_subsystem(struct liveupdate_subsystem *h);
int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h, u64 *data);
+int liveupdate_register_file_handler(struct liveupdate_file_handler *h);
+int liveupdate_unregister_file_handler(struct liveupdate_file_handler *h);
+
#else /* CONFIG_LIVEUPDATE */
static inline int liveupdate_reboot(void)
@@ -197,5 +255,15 @@ static inline int liveupdate_get_subsystem_data(struct liveupdate_subsystem *h,
return -ENODATA;
}
+static inline int liveupdate_register_file_handler(struct liveupdate_file_handler *h)
+{
+ return 0;
+}
+
+static inline int liveupdate_unregister_file_handler(struct liveupdate_file_handler *h)
+{
+ return 0;
+}
+
#endif /* CONFIG_LIVEUPDATE */
#endif /* _LINUX_LIVEUPDATE_H */
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
index 999208a1fdbb..b5054140b9a9 100644
--- a/kernel/liveupdate/Makefile
+++ b/kernel/liveupdate/Makefile
@@ -6,4 +6,5 @@
obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
obj-$(CONFIG_LIVEUPDATE) += luo_core.o
+obj-$(CONFIG_LIVEUPDATE) += luo_files.o
obj-$(CONFIG_LIVEUPDATE) += luo_subsystems.o
diff --git a/kernel/liveupdate/luo_files.c b/kernel/liveupdate/luo_files.c
new file mode 100644
index 000000000000..3582f1ec96c4
--- /dev/null
+++ b/kernel/liveupdate/luo_files.c
@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO file descriptors
+ *
+ * LUO provides the infrastructure necessary to preserve
+ * specific types of stateful file descriptors across a kernel live
+ * update transition. The primary goal is to allow workloads, such as virtual
+ * machines using vfio, memfd, or iommufd to retain access to their essential
+ * resources without interruption after the underlying kernel is updated.
+ *
+ * The framework operates based on handler registration and instance tracking:
+ *
+ * 1. Handler Registration: Kernel modules responsible for specific file
+ * types (e.g., memfd, vfio) register a &struct liveupdate_file_handler
+ * handler. This handler contains callbacks
+ * (&liveupdate_file_handler.ops->prepare,
+ * &liveupdate_file_handler.ops->freeze,
+ * &liveupdate_file_handler.ops->finish, etc.) and a unique 'compatible' string
+ * identifying the file type. Registration occurs via
+ * liveupdate_register_file_handler().
+ *
+ * 2. File Instance Tracking: When a potentially preservable file needs to be
+ * managed for live update, the core LUO logic (luo_register_file()) finds a
+ * compatible registered handler using its
+ * &liveupdate_file_handler.ops->can_preserve callback. If found, an internal
+ * &struct luo_file instance is created, assigned a unique u64 'token', and
+ * added to a list.
+ *
+ * 3. State Persistence (FDT): During the LUO prepare/freeze phases, the
+ * registered handler callbacks are invoked for each tracked file instance.
+ * These callbacks can generate a u64 data payload representing the minimal
+ * state needed for restoration. This payload, along with the handler's
+ * compatible string and the unique token, is stored in a dedicated
+ * '/file-descriptors' node within the main LUO FDT blob passed via
+ * Kexec Handover (KHO).
+ *
+ * 4. Restoration: In the new kernel, the LUO framework parses the incoming
+ * FDT to reconstruct the list of &struct luo_file instances. When the
+ * original owner requests the file, luo_retrieve_file() uses the corresponding
+ * handler's &liveupdate_file_handler.ops->retrieve callback, passing the
+ * persisted u64 data, to recreate or find the appropriate &struct file object.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/file.h>
+#include <linux/kexec_handover.h>
+#include <linux/libfdt.h>
+#include <linux/liveupdate.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/xarray.h>
+#include "luo_internal.h"
+
+#define LUO_FILES_NODE_NAME "file-descriptors"
+#define LUO_FILES_COMPATIBLE "file-descriptors-v1"
+
+static DEFINE_XARRAY(luo_files_xa_in);
+static DEFINE_XARRAY(luo_files_xa_out);
+static bool luo_files_xa_in_recreated;
+
+/* Registered files. */
+static DECLARE_RWSEM(luo_register_file_list_rwsem);
+static LIST_HEAD(luo_register_file_list);
+
+static void *luo_file_fdt_out;
+static void *luo_file_fdt_in;
+
+static size_t luo_file_fdt_out_size;
+
+static atomic64_t luo_files_count;
+
+/**
+ * struct luo_file - Represents a file descriptor instance preserved
+ * across live update.
+ * @fh: Pointer to the &struct liveupdate_file_handler containing
+ * the implementation of prepare, freeze, cancel, and finish
+ * operations specific to this file's type.
+ * @file: A pointer to the kernel's &struct file object representing
+ * the open file descriptor that is being preserved.
+ * @private_data: Internal storage used by the live update core framework
+ * between phases.
+ * @reclaimed: Flag indicating whether this preserved file descriptor has
+ * been successfully 'reclaimed' (e.g., requested via an ioctl)
+ * by user-space or the owning kernel subsystem in the new
+ * kernel after the live update.
+ * @state: The current state of file descriptor, it is allowed to
+ * prepare, freeze, and finish FDs before the global state
+ * switch.
+ * @mutex: Lock to protect FD state, and allow independently to change
+ * the FD state compared to global state.
+ *
+ * This structure holds the necessary callbacks and context for managing a
+ * specific open file descriptor throughout the different phases of a live
+ * update process. Instances of this structure are typically allocated,
+ * populated with file-specific details (&file, &arg, callbacks, compatibility
+ * string, token), and linked into a central list managed by the LUO. The
+ * private_data field is used internally by the core logic to store state
+ * between phases.
+ */
+struct luo_file {
+ struct liveupdate_file_handler *fh;
+ struct file *file;
+ u64 private_data;
+ bool reclaimed;
+ enum liveupdate_state state;
+ struct mutex mutex;
+};
+
+static void luo_files_recreate_luo_files_xa_in(void)
+{
+ const char *node_name, *fdt_compat_str;
+ struct liveupdate_file_handler *fh;
+ struct luo_file *luo_file;
+ const void *data_ptr;
+ int file_node_offset;
+ int ret = 0;
+
+ if (luo_files_xa_in_recreated || !luo_file_fdt_in)
+ return;
+
+ /* Take write in order to guarantee that we re-create list once */
+ down_write(&luo_register_file_list_rwsem);
+ if (luo_files_xa_in_recreated)
+ goto exit_unlock;
+
+ fdt_for_each_subnode(file_node_offset, luo_file_fdt_in, 0) {
+ bool handler_found = false;
+ u64 token;
+
+ node_name = fdt_get_name(luo_file_fdt_in, file_node_offset,
+ NULL);
+ if (!node_name) {
+ panic("FDT subnode at offset %d: Cannot get name\n",
+ file_node_offset);
+ }
+
+ ret = kstrtou64(node_name, 0, &token);
+ if (ret < 0) {
+ panic("FDT node '%s': Failed to parse token\n",
+ node_name);
+ }
+
+ if (xa_load(&luo_files_xa_in, token)) {
+ panic("Duplicate token %llu found in incoming FDT for file descriptors.\n",
+ token);
+ }
+
+ fdt_compat_str = fdt_getprop(luo_file_fdt_in, file_node_offset,
+ "compatible", NULL);
+ if (!fdt_compat_str) {
+ panic("FDT node '%s': Missing 'compatible' property\n",
+ node_name);
+ }
+
+ data_ptr = fdt_getprop(luo_file_fdt_in, file_node_offset, "data",
+ NULL);
+ if (!data_ptr) {
+ panic("Can't recover property 'data' for FDT node '%s'\n",
+ node_name);
+ }
+
+ list_for_each_entry(fh, &luo_register_file_list, list) {
+ if (!strcmp(fh->compatible, fdt_compat_str)) {
+ handler_found = true;
+ break;
+ }
+ }
+
+ if (!handler_found) {
+ panic("FDT node '%s': No registered handler for compatible '%s'\n",
+ node_name, fdt_compat_str);
+ }
+
+ luo_file = kmalloc(sizeof(*luo_file),
+ GFP_KERNEL | __GFP_NOFAIL);
+ luo_file->fh = fh;
+ luo_file->file = NULL;
+ memcpy(&luo_file->private_data, data_ptr, sizeof(u64));
+ luo_file->reclaimed = false;
+ mutex_init(&luo_file->mutex);
+ luo_file->state = LIVEUPDATE_STATE_UPDATED;
+ ret = xa_err(xa_store(&luo_files_xa_in, token, luo_file,
+ GFP_KERNEL | __GFP_NOFAIL));
+ if (ret < 0) {
+ panic("Failed to store luo_file for token %llu in XArray: %d\n",
+ token, ret);
+ }
+ }
+ luo_files_xa_in_recreated = true;
+
+exit_unlock:
+ up_write(&luo_register_file_list_rwsem);
+}
+
+static size_t luo_files_fdt_size(void)
+{
+ u64 num_files = atomic64_read(&luo_files_count);
+
+ /* Estimate a 1K overhead, + 128 bytes per file entry */
+ return PAGE_SIZE << get_order(SZ_1K + (num_files * 128));
+}
+
+static void luo_files_fdt_cleanup(void)
+{
+ WARN_ON_ONCE(kho_unpreserve_phys(__pa(luo_file_fdt_out),
+ luo_file_fdt_out_size));
+
+ free_pages((unsigned long)luo_file_fdt_out,
+ get_order(luo_file_fdt_out_size));
+
+ luo_file_fdt_out_size = 0;
+ luo_file_fdt_out = NULL;
+}
+
+static int luo_files_to_fdt(struct xarray *files_xa_out)
+{
+ const u64 zero_data = 0;
+ unsigned long token;
+ struct luo_file *h;
+ char token_str[19];
+ int ret = 0;
+
+ xa_for_each(files_xa_out, token, h) {
+ snprintf(token_str, sizeof(token_str), "%#0llx", (u64)token);
+
+ ret = fdt_begin_node(luo_file_fdt_out, token_str);
+ if (ret < 0)
+ break;
+
+ ret = fdt_property_string(luo_file_fdt_out, "compatible",
+ h->fh->compatible);
+ if (ret < 0) {
+ fdt_end_node(luo_file_fdt_out);
+ break;
+ }
+
+ ret = fdt_property_u64(luo_file_fdt_out, "data", zero_data);
+ if (ret < 0) {
+ fdt_end_node(luo_file_fdt_out);
+ break;
+ }
+
+ ret = fdt_end_node(luo_file_fdt_out);
+ if (ret < 0)
+ break;
+ }
+
+ return ret;
+}
+
+static int luo_files_fdt_setup(void)
+{
+ int ret;
+
+ luo_file_fdt_out_size = luo_files_fdt_size();
+ luo_file_fdt_out = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(luo_file_fdt_out_size));
+ if (!luo_file_fdt_out) {
+ pr_err("Failed to allocate FDT memory (%zu bytes)\n",
+ luo_file_fdt_out_size);
+ luo_file_fdt_out_size = 0;
+ return -ENOMEM;
+ }
+
+ ret = kho_preserve_phys(__pa(luo_file_fdt_out), luo_file_fdt_out_size);
+ if (ret) {
+ pr_err("Failed to kho preserve FDT memory (%zu bytes)\n",
+ luo_file_fdt_out_size);
+ luo_file_fdt_out_size = 0;
+ luo_file_fdt_out = NULL;
+ return ret;
+ }
+
+ ret = fdt_create(luo_file_fdt_out, luo_file_fdt_out_size);
+ if (ret < 0)
+ goto exit_cleanup;
+
+ ret = fdt_finish_reservemap(luo_file_fdt_out);
+ if (ret < 0)
+ goto exit_finish;
+
+ ret = fdt_begin_node(luo_file_fdt_out, LUO_FILES_NODE_NAME);
+ if (ret < 0)
+ goto exit_finish;
+
+ ret = fdt_property_string(luo_file_fdt_out, "compatible",
+ LUO_FILES_COMPATIBLE);
+ if (ret < 0)
+ goto exit_end_node;
+
+ ret = luo_files_to_fdt(&luo_files_xa_out);
+ if (ret < 0)
+ goto exit_end_node;
+
+ ret = fdt_end_node(luo_file_fdt_out);
+ if (ret < 0)
+ goto exit_finish;
+
+ ret = fdt_finish(luo_file_fdt_out);
+ if (ret < 0)
+ goto exit_cleanup;
+
+ return 0;
+
+exit_end_node:
+ fdt_end_node(luo_file_fdt_out);
+exit_finish:
+ fdt_finish(luo_file_fdt_out);
+exit_cleanup:
+ pr_err("Failed to setup FDT: %s (ret %d)\n", fdt_strerror(ret), ret);
+ luo_files_fdt_cleanup();
+
+ return ret;
+}
+
+static int luo_files_prepare(void *arg, u64 *data)
+{
+ int ret;
+
+ ret = luo_files_fdt_setup();
+ if (ret)
+ return ret;
+
+ *data = __pa(luo_file_fdt_out);
+
+ return ret;
+}
+
+static int luo_files_freeze(void *arg, u64 *data)
+{
+ return 0;
+}
+
+static void luo_files_finish(void *arg, u64 data)
+{
+ luo_files_recreate_luo_files_xa_in();
+}
+
+static void luo_files_cancel(void *arg, u64 data)
+{
+}
+
+static const struct liveupdate_subsystem_ops luo_file_subsys_ops = {
+ .prepare = luo_files_prepare,
+ .freeze = luo_files_freeze,
+ .cancel = luo_files_cancel,
+ .finish = luo_files_finish,
+};
+
+static struct liveupdate_subsystem luo_file_subsys = {
+ .ops = &luo_file_subsys_ops,
+ .name = LUO_FILES_NODE_NAME,
+};
+
+static int __init luo_files_startup(void)
+{
+ int ret;
+
+ if (!liveupdate_enabled())
+ return 0;
+
+ ret = liveupdate_register_subsystem(&luo_file_subsys);
+ if (ret) {
+ pr_warn("Failed to register luo_file subsystem [%d]\n", ret);
+ return ret;
+ }
+
+ if (liveupdate_state_updated()) {
+ u64 fdt_pa;
+
+ ret = liveupdate_get_subsystem_data(&luo_file_subsys, &fdt_pa);
+ if (ret)
+ panic("Failed to retrieve luo_file data [%d]\n", ret);
+
+ ret = fdt_node_check_compatible(__va(fdt_pa), 0,
+ LUO_FILES_COMPATIBLE);
+ if (ret) {
+ panic("FDT '%s' is incompatible with '%s' [%d]\n",
+ LUO_FILES_NODE_NAME, LUO_FILES_COMPATIBLE, ret);
+ }
+ luo_file_fdt_in = __va(fdt_pa);
+ }
+
+ return ret;
+}
+late_initcall(luo_files_startup);
+
+/**
+ * luo_register_file - Register a file descriptor for live update management.
+ * @token: Token value for this file descriptor.
+ * @fd: file descriptor to be preserved.
+ *
+ * Context: Must be called when LUO is in 'normal' state.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int luo_register_file(u64 token, int fd)
+{
+ struct liveupdate_file_handler *fh;
+ struct luo_file *luo_file;
+ bool found = false;
+ int ret = -ENOENT;
+ struct file *file;
+
+ file = fget(fd);
+ if (!file) {
+ pr_err("Bad file descriptor\n");
+ return -EBADF;
+ }
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ pr_warn("File can be registered only in normal or updated state\n");
+ luo_state_read_exit();
+ fput(file);
+ return -EBUSY;
+ }
+
+ down_read(&luo_register_file_list_rwsem);
+ list_for_each_entry(fh, &luo_register_file_list, list) {
+ if (fh->ops->can_preserve(file, fh->arg)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found)
+ goto exit_unlock;
+
+ luo_file = kmalloc(sizeof(*luo_file), GFP_KERNEL);
+ if (!luo_file) {
+ ret = -ENOMEM;
+ goto exit_unlock;
+ }
+
+ luo_file->private_data = 0;
+ luo_file->reclaimed = false;
+
+ luo_file->file = file;
+ luo_file->fh = fh;
+ mutex_init(&luo_file->mutex);
+ luo_file->state = LIVEUPDATE_STATE_NORMAL;
+
+ if (xa_load(&luo_files_xa_out, token)) {
+ ret = -EEXIST;
+ pr_warn("Token %llu is already taken\n", token);
+ mutex_destroy(&luo_file->mutex);
+ kfree(luo_file);
+ goto exit_unlock;
+ }
+
+ ret = xa_err(xa_store(&luo_files_xa_out, token, luo_file,
+ GFP_KERNEL));
+ if (ret < 0) {
+ pr_warn("Failed to store file for token %llu in XArray: %d\n",
+ token, ret);
+ mutex_destroy(&luo_file->mutex);
+ kfree(luo_file);
+ goto exit_unlock;
+ }
+ atomic64_inc(&luo_files_count);
+
+exit_unlock:
+ up_read(&luo_register_file_list_rwsem);
+ luo_state_read_exit();
+
+ if (ret)
+ fput(file);
+
+ return ret;
+}
+
+/**
+ * luo_unregister_file - Unregister a file instance using its token.
+ * @token: The unique token of the file instance to unregister.
+ *
+ * Finds the &struct luo_file associated with the @token in the
+ * global list and removes it. This function *only* removes the entry from the
+ * list; it does *not* free the memory allocated for the &struct luo_file
+ * itself. The caller is responsible for freeing the structure after this
+ * function returns successfully.
+ *
+ * Context: Can be called when a preserved file descriptor is closed or
+ * no longer needs live update management.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int luo_unregister_file(u64 token)
+{
+ struct luo_file *luo_file;
+ int ret = 0;
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ pr_warn("File can be unregistered only in normal or updates state\n");
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ luo_file = xa_erase(&luo_files_xa_out, token);
+ if (luo_file) {
+ fput(luo_file->file);
+ mutex_destroy(&luo_file->mutex);
+ kfree(luo_file);
+ atomic64_dec(&luo_files_count);
+ } else {
+ pr_warn("Failed to unregister: token %llu not found.\n",
+ token);
+ ret = -ENOENT;
+ }
+ luo_state_read_exit();
+
+ return ret;
+}
+
+/**
+ * luo_retrieve_file - Find a registered file instance by its token.
+ * @token: The unique token of the file instance to retrieve.
+ * @filep: Output parameter. On success (return value 0), this will point
+ * to the retrieved "struct file".
+ *
+ * Searches the global list for a &struct luo_file matching the @token. Uses a
+ * read lock, allowing concurrent retrievals.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int luo_retrieve_file(u64 token, struct file **filep)
+{
+ struct luo_file *luo_file;
+ int ret = 0;
+
+ luo_files_recreate_luo_files_xa_in();
+ luo_state_read_enter();
+ if (!liveupdate_state_updated()) {
+ pr_warn("File can be retrieved only in updated state\n");
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ luo_file = xa_load(&luo_files_xa_in, token);
+ if (luo_file && !luo_file->reclaimed) {
+ mutex_lock(&luo_file->mutex);
+ if (!luo_file->reclaimed) {
+ luo_file->reclaimed = true;
+ ret = luo_file->fh->ops->retrieve(luo_file->fh->arg,
+ luo_file->private_data,
+ filep);
+ if (!ret)
+ luo_file->file = *filep;
+ }
+ mutex_unlock(&luo_file->mutex);
+ } else if (luo_file && luo_file->reclaimed) {
+ pr_err("The file descriptor for token %lld has already been retrieved\n",
+ token);
+ ret = -EINVAL;
+ } else {
+ ret = -ENOENT;
+ }
+
+ luo_state_read_exit();
+
+ return ret;
+}
+
+/**
+ * liveupdate_register_file_handler - Register a file handler with LUO.
+ * @fh: Pointer to a caller-allocated &struct liveupdate_file_handler.
+ * The caller must initialize this structure, including a unique
+ * 'compatible' string and a valid 'fh' callbacks. This function adds the
+ * handler to the global list of supported file handlers.
+ *
+ * Context: Typically called during module initialization for file types that
+ * support live update preservation.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int liveupdate_register_file_handler(struct liveupdate_file_handler *fh)
+{
+ struct liveupdate_file_handler *fh_iter;
+ int ret = 0;
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ down_write(&luo_register_file_list_rwsem);
+ list_for_each_entry(fh_iter, &luo_register_file_list, list) {
+ if (!strcmp(fh_iter->compatible, fh->compatible)) {
+ pr_err("File handler registration failed: Compatible string '%s' already registered.\n",
+ fh->compatible);
+ ret = -EEXIST;
+ goto exit_unlock;
+ }
+ }
+
+ INIT_LIST_HEAD(&fh->list);
+ list_add_tail(&fh->list, &luo_register_file_list);
+
+exit_unlock:
+ up_write(&luo_register_file_list_rwsem);
+ luo_state_read_exit();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(liveupdate_register_file_handler);
+
+/**
+ * liveupdate_unregister_file - Unregister a file handler.
+ * @fh: Pointer to the specific &struct liveupdate_file_handler instance
+ * that was previously returned by or passed to
+ * liveupdate_register_file_handler.
+ *
+ * Removes the specified handler instance @fh from the global list of
+ * registered file handlers. This function only removes the entry from the
+ * list; it does not free the memory associated with @fh itself. The caller
+ * is responsible for freeing the structure memory after this function returns
+ * successfully.
+ *
+ * Return: 0 on success. Negative errno on failure.
+ */
+int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh)
+{
+ unsigned long token;
+ struct luo_file *h;
+ int ret = 0;
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+
+ down_write(&luo_register_file_list_rwsem);
+
+ xa_for_each(&luo_files_xa_out, token, h) {
+ if (h->fh == fh) {
+ up_write(&luo_register_file_list_rwsem);
+ luo_state_read_exit();
+ return -EBUSY;
+ }
+ }
+
+ list_del_init(&fh->list);
+ up_write(&luo_register_file_list_rwsem);
+ luo_state_read_exit();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(liveupdate_unregister_file_handler);
diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h
index 98bf799adb61..f77e8b3044f9 100644
--- a/kernel/liveupdate/luo_internal.h
+++ b/kernel/liveupdate/luo_internal.h
@@ -25,4 +25,8 @@ int luo_do_subsystems_freeze_calls(void);
void luo_do_subsystems_finish_calls(void);
void luo_do_subsystems_cancel_calls(void);
+int luo_retrieve_file(u64 token, struct file **filep);
+int luo_register_file(u64 token, int fd);
+int luo_unregister_file(u64 token);
+
#endif /* _LINUX_LUO_INTERNAL_H */
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 15/32] liveupdate: luo_files: implement file systems callbacks
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Implements the core logic within luo_files.c to invoke the prepare,
reboot, finish, and cancel callbacks for preserved file instances,
replacing the previous stub implementations. It also handles
the persistence and retrieval of the u64 data payload associated with
each file via the LUO FDT.
This completes the core mechanism enabling registered files handlers to actively
manage file state across the live update transition using the LUO framework.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/liveupdate/luo_files.c | 166 +++++++++++++++++++++++++++++++++-
1 file changed, 164 insertions(+), 2 deletions(-)
diff --git a/kernel/liveupdate/luo_files.c b/kernel/liveupdate/luo_files.c
index 3582f1ec96c4..cd956ea69f43 100644
--- a/kernel/liveupdate/luo_files.c
+++ b/kernel/liveupdate/luo_files.c
@@ -325,31 +325,193 @@ static int luo_files_fdt_setup(void)
return ret;
}
+static int luo_files_prepare_one(struct luo_file *h)
+{
+ int ret = 0;
+
+ mutex_lock(&h->mutex);
+ if (h->state == LIVEUPDATE_STATE_NORMAL) {
+ if (h->fh->ops->prepare) {
+ ret = h->fh->ops->prepare(h->file, h->fh->arg,
+ &h->private_data);
+ }
+ if (!ret)
+ h->state = LIVEUPDATE_STATE_PREPARED;
+ } else {
+ WARN_ON_ONCE(h->state != LIVEUPDATE_STATE_PREPARED &&
+ h->state != LIVEUPDATE_STATE_FROZEN);
+ }
+ mutex_unlock(&h->mutex);
+
+ return ret;
+}
+
+static int luo_files_freeze_one(struct luo_file *h)
+{
+ int ret = 0;
+
+ mutex_lock(&h->mutex);
+ if (h->state == LIVEUPDATE_STATE_PREPARED) {
+ if (h->fh->ops->freeze) {
+ ret = h->fh->ops->freeze(h->file, h->fh->arg,
+ &h->private_data);
+ }
+ if (!ret)
+ h->state = LIVEUPDATE_STATE_FROZEN;
+ } else {
+ WARN_ON_ONCE(h->state != LIVEUPDATE_STATE_FROZEN);
+ }
+ mutex_unlock(&h->mutex);
+
+ return ret;
+}
+
+static void luo_files_finish_one(struct luo_file *h)
+{
+ mutex_lock(&h->mutex);
+ if (h->state == LIVEUPDATE_STATE_UPDATED) {
+ if (h->fh->ops->finish) {
+ h->fh->ops->finish(h->file, h->fh->arg, h->private_data,
+ h->reclaimed);
+ }
+ h->state = LIVEUPDATE_STATE_NORMAL;
+ } else {
+ WARN_ON_ONCE(h->state != LIVEUPDATE_STATE_NORMAL);
+ }
+ mutex_unlock(&h->mutex);
+}
+
+static void luo_files_cancel_one(struct luo_file *h)
+{
+ int ret;
+
+ mutex_lock(&h->mutex);
+ if (h->state == LIVEUPDATE_STATE_NORMAL)
+ goto exit_unlock;
+
+ ret = WARN_ON_ONCE(h->state != LIVEUPDATE_STATE_PREPARED &&
+ h->state != LIVEUPDATE_STATE_FROZEN);
+ if (ret)
+ goto exit_unlock;
+
+ if (h->fh->ops->cancel)
+ h->fh->ops->cancel(h->file, h->fh->arg, h->private_data);
+ h->private_data = 0;
+ h->state = LIVEUPDATE_STATE_NORMAL;
+
+exit_unlock:
+ mutex_unlock(&h->mutex);
+}
+
+static void __luo_files_cancel(struct luo_file *boundary_file)
+{
+ unsigned long token;
+ struct luo_file *h;
+
+ xa_for_each(&luo_files_xa_out, token, h) {
+ if (h == boundary_file)
+ break;
+
+ luo_files_cancel_one(h);
+ }
+ luo_files_fdt_cleanup();
+}
+
+static int luo_files_commit_data_to_fdt(void)
+{
+ int node_offset, ret;
+ unsigned long token;
+ char token_str[19];
+ struct luo_file *h;
+
+ xa_for_each(&luo_files_xa_out, token, h) {
+ snprintf(token_str, sizeof(token_str), "%#0llx", (u64)token);
+ node_offset = fdt_subnode_offset(luo_file_fdt_out,
+ 0,
+ token_str);
+ ret = fdt_setprop(luo_file_fdt_out, node_offset, "data",
+ &h->private_data, sizeof(h->private_data));
+ if (ret < 0) {
+ pr_err("Failed to set data property for token %s: %s\n",
+ token_str, fdt_strerror(ret));
+ return -ENOSPC;
+ }
+ }
+
+ return 0;
+}
+
static int luo_files_prepare(void *arg, u64 *data)
{
+ unsigned long token;
+ struct luo_file *h;
int ret;
ret = luo_files_fdt_setup();
if (ret)
return ret;
- *data = __pa(luo_file_fdt_out);
+ xa_for_each(&luo_files_xa_out, token, h) {
+ ret = luo_files_prepare_one(h);
+ if (ret < 0) {
+ pr_err("Prepare failed for file token %#0llx handler '%s' [%d]\n",
+ (u64)token, h->fh->compatible, ret);
+ __luo_files_cancel(h);
+
+ return ret;
+ }
+ }
+
+ ret = luo_files_commit_data_to_fdt();
+ if (ret)
+ __luo_files_cancel(NULL);
+ else
+ *data = __pa(luo_file_fdt_out);
return ret;
}
static int luo_files_freeze(void *arg, u64 *data)
{
- return 0;
+ unsigned long token;
+ struct luo_file *h;
+ int ret;
+
+ xa_for_each(&luo_files_xa_out, token, h) {
+ ret = luo_files_freeze_one(h);
+ if (ret < 0) {
+ pr_err("Freeze callback failed for file token %#0llx handler '%s' [%d]\n",
+ (u64)token, h->fh->compatible, ret);
+ __luo_files_cancel(h);
+
+ return ret;
+ }
+ }
+
+ ret = luo_files_commit_data_to_fdt();
+ if (ret)
+ __luo_files_cancel(NULL);
+
+ return ret;
}
static void luo_files_finish(void *arg, u64 data)
{
+ unsigned long token;
+ struct luo_file *h;
+
luo_files_recreate_luo_files_xa_in();
+ xa_for_each(&luo_files_xa_in, token, h) {
+ luo_files_finish_one(h);
+ mutex_destroy(&h->mutex);
+ kfree(h);
+ }
+ xa_destroy(&luo_files_xa_in);
}
static void luo_files_cancel(void *arg, u64 data)
{
+ __luo_files_cancel(NULL);
}
static const struct liveupdate_subsystem_ops luo_file_subsys_ops = {
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 16/32] liveupdate: luo_ioctl: add ioctl interface
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Introduce the user-space interface for the Live Update Orchestrator
via ioctl commands, enabling external control over the live update
process and management of preserved resources.
Create a character device at /dev/liveupdate. Access
to this device requires the CAP_SYS_ADMIN capability.
A new uAPI header, <uapi/linux/liveupdate.h>, defines the necessary
structures. The magic number is registered in
Documentation/userspace-api/ioctl/ioctl-number.rst.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
.../userspace-api/ioctl/ioctl-number.rst | 2 +
include/linux/liveupdate.h | 36 +--
include/uapi/linux/liveupdate.h | 265 ++++++++++++++++++
kernel/liveupdate/Makefile | 1 +
kernel/liveupdate/luo_ioctl.c | 178 ++++++++++++
5 files changed, 447 insertions(+), 35 deletions(-)
create mode 100644 include/uapi/linux/liveupdate.h
create mode 100644 kernel/liveupdate/luo_ioctl.c
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index bc91756bde73..8368aa05b4df 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -380,6 +380,8 @@ Code Seq# Include File Comments
0xB8 01-02 uapi/misc/mrvl_cn10k_dpi.h Marvell CN10K DPI driver
0xB8 all uapi/linux/mshv.h Microsoft Hyper-V /dev/mshv driver
<mailto:linux-hyperv@vger.kernel.org>
+0xBA all uapi/linux/liveupdate.h Pasha Tatashin
+ <mailto:pasha.tatashin@soleen.com>
0xC0 00-0F linux/usb/iowarrior.h
0xCA 00-0F uapi/misc/cxl.h Dead since 6.15
0xCA 10-2F uapi/misc/ocxl.h
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index 28a8aa4cafca..970447de5d8c 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -10,6 +10,7 @@
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/list.h>
+#include <uapi/linux/liveupdate.h>
/**
* enum liveupdate_event - Events that trigger live update callbacks.
@@ -53,41 +54,6 @@ enum liveupdate_event {
LIVEUPDATE_CANCEL,
};
-/**
- * enum liveupdate_state - Defines the possible states of the live update
- * orchestrator.
- * @LIVEUPDATE_STATE_UNDEFINED: State has not yet been initialized.
- * @LIVEUPDATE_STATE_NORMAL: Default state, no live update in progress.
- * @LIVEUPDATE_STATE_PREPARED: Live update is prepared for reboot; the
- * LIVEUPDATE_PREPARE callbacks have completed
- * successfully.
- * Devices might operate in a limited state
- * for example the participating devices might
- * not be allowed to unbind, and also the
- * setting up of new DMA mappings might be
- * disabled in this state.
- * @LIVEUPDATE_STATE_FROZEN: The final reboot event
- * (%LIVEUPDATE_FREEZE) has been sent, and the
- * system is performing its final state saving
- * within the "blackout window". User
- * workloads must be suspended. The actual
- * reboot (kexec) into the next kernel is
- * imminent.
- * @LIVEUPDATE_STATE_UPDATED: The system has rebooted into the next
- * kernel via live update the system is now
- * running the next kernel, awaiting the
- * finish event.
- *
- * These states track the progress and outcome of a live update operation.
- */
-enum liveupdate_state {
- LIVEUPDATE_STATE_UNDEFINED = 0,
- LIVEUPDATE_STATE_NORMAL = 1,
- LIVEUPDATE_STATE_PREPARED = 2,
- LIVEUPDATE_STATE_FROZEN = 3,
- LIVEUPDATE_STATE_UPDATED = 4,
-};
-
struct file;
/**
diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h
new file mode 100644
index 000000000000..7b12a1073c3c
--- /dev/null
+++ b/include/uapi/linux/liveupdate.h
@@ -0,0 +1,265 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+/*
+ * Userspace interface for /dev/liveupdate
+ * Live Update Orchestrator
+ *
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#ifndef _UAPI_LIVEUPDATE_H
+#define _UAPI_LIVEUPDATE_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * enum liveupdate_state - Defines the possible states of the live update
+ * orchestrator.
+ * @LIVEUPDATE_STATE_UNDEFINED: State has not yet been initialized.
+ * @LIVEUPDATE_STATE_NORMAL: Default state, no live update in progress.
+ * @LIVEUPDATE_STATE_PREPARED: Live update is prepared for reboot; the
+ * LIVEUPDATE_PREPARE callbacks have completed
+ * successfully.
+ * Devices might operate in a limited state
+ * for example the participating devices might
+ * not be allowed to unbind, and also the
+ * setting up of new DMA mappings might be
+ * disabled in this state.
+ * @LIVEUPDATE_STATE_FROZEN: The final reboot event
+ * (%LIVEUPDATE_FREEZE) has been sent, and the
+ * system is performing its final state saving
+ * within the "blackout window". User
+ * workloads must be suspended. The actual
+ * reboot (kexec) into the next kernel is
+ * imminent.
+ * @LIVEUPDATE_STATE_UPDATED: The system has rebooted into the next
+ * kernel via live update the system is now
+ * running the next kernel, awaiting the
+ * finish event.
+ *
+ * These states track the progress and outcome of a live update operation.
+ */
+enum liveupdate_state {
+ LIVEUPDATE_STATE_UNDEFINED = 0,
+ LIVEUPDATE_STATE_NORMAL = 1,
+ LIVEUPDATE_STATE_PREPARED = 2,
+ LIVEUPDATE_STATE_FROZEN = 3,
+ LIVEUPDATE_STATE_UPDATED = 4,
+};
+
+/**
+ * struct liveupdate_fd - Holds parameters for preserving and restoring file
+ * descriptors across live update.
+ * @fd: Input for %LIVEUPDATE_IOCTL_FD_PRESERVE: The user-space file
+ * descriptor to be preserved.
+ * Output for %LIVEUPDATE_IOCTL_FD_RESTORE: The new file descriptor
+ * representing the fully restored kernel resource.
+ * @flags: Unused, reserved for future expansion, must be set to 0.
+ * @token: Input for %LIVEUPDATE_IOCTL_FD_PRESERVE: An opaque, unique token
+ * preserved for preserved resource.
+ * Input for %LIVEUPDATE_IOCTL_FD_RESTORE: The token previously
+ * provided to the preserve ioctl for the resource to be restored.
+ *
+ * This structure is used as the argument for the %LIVEUPDATE_IOCTL_FD_PRESERVE
+ * and %LIVEUPDATE_IOCTL_FD_RESTORE ioctls. These ioctls allow specific types
+ * of file descriptors (for example memfd, kvm, iommufd, and VFIO) to have their
+ * underlying kernel state preserved across a live update cycle.
+ *
+ * To preserve an FD, user space passes this struct to
+ * %LIVEUPDATE_IOCTL_FD_PRESERVE with the @fd field set. On success, the
+ * kernel uses the @token field to uniquly associate the preserved FD.
+ *
+ * After the live update transition, user space passes the struct populated with
+ * the *same* @token to %LIVEUPDATE_IOCTL_FD_RESTORE. The kernel uses the @token
+ * to find the preserved state and, on success, populates the @fd field with a
+ * new file descriptor referring to the restored resource.
+ */
+struct liveupdate_fd {
+ int fd;
+ __u32 flags;
+ __aligned_u64 token;
+};
+
+/* The ioctl type, documented in ioctl-number.rst */
+#define LIVEUPDATE_IOCTL_TYPE 0xBA
+
+/**
+ * LIVEUPDATE_IOCTL_FD_PRESERVE - Validate and initiate preservation for a file
+ * descriptor.
+ *
+ * Argument: Pointer to &struct liveupdate_fd.
+ *
+ * User sets the @fd field identifying the file descriptor to preserve
+ * (e.g., memfd, kvm, iommufd, VFIO). The kernel validates if this FD type
+ * and its dependencies are supported for preservation. If validation passes,
+ * the kernel marks the FD internally and *initiates the process* of preparing
+ * its state for saving. The actual snapshotting of the state typically occurs
+ * during the subsequent %LIVEUPDATE_IOCTL_PREPARE execution phase, though
+ * some finalization might occur during freeze.
+ * On successful validation and initiation, the kernel uses the @token
+ * field with an opaque identifier representing the resource being preserved.
+ * This token confirms the FD is targeted for preservation and is required for
+ * the subsequent %LIVEUPDATE_IOCTL_FD_RESTORE call after the live update.
+ *
+ * Return: 0 on success (validation passed, preservation initiated), negative
+ * error code on failure (e.g., unsupported FD type, dependency issue,
+ * validation failed).
+ */
+#define LIVEUPDATE_IOCTL_FD_PRESERVE \
+ _IOW(LIVEUPDATE_IOCTL_TYPE, 0x00, struct liveupdate_fd)
+
+/**
+ * LIVEUPDATE_IOCTL_FD_UNPRESERVE - Remove a file descriptor from the
+ * preservation list.
+ *
+ * Argument: Pointer to __u64 token.
+ *
+ * Allows user space to explicitly remove a file descriptor from the set of
+ * items marked as potentially preservable. User space provides a pointer to the
+ * __u64 @token that was previously returned by a successful
+ * %LIVEUPDATE_IOCTL_FD_PRESERVE call (potentially from a prior, possibly
+ * cancelled, live update attempt). The kernel reads the token value from the
+ * provided user-space address.
+ *
+ * On success, the kernel removes the corresponding entry (identified by the
+ * token value read from the user pointer) from its internal preservation list.
+ * The provided @token (representing the now-removed entry) becomes invalid
+ * after this call.
+ *
+ * Return: 0 on success, negative error code on failure (e.g., -EBUSY or -EINVAL
+ * if not in %LIVEUPDATE_STATE_NORMAL, bad address provided, invalid token value
+ * read, token not found).
+ */
+#define LIVEUPDATE_IOCTL_FD_UNPRESERVE \
+ _IOW(LIVEUPDATE_IOCTL_TYPE, 0x01, __u64)
+
+/**
+ * LIVEUPDATE_IOCTL_FD_RESTORE - Restore a previously preserved file descriptor.
+ *
+ * Argument: Pointer to &struct liveupdate_fd.
+ *
+ * User sets the @token field to the value obtained from a successful
+ * %LIVEUPDATE_IOCTL_FD_PRESERVE call before the live update. On success,
+ * the kernel restores the state (saved during the PREPARE/FREEZE phases)
+ * associated with the token and populates the @fd field with a new file
+ * descriptor referencing the restored resource in the current (new) kernel.
+ * This operation must be performed *before* signaling completion via
+ * %LIVEUPDATE_IOCTL_FINISH.
+ *
+ * Return: 0 on success, negative error code on failure (e.g., invalid token).
+ */
+#define LIVEUPDATE_IOCTL_FD_RESTORE \
+ _IOWR(LIVEUPDATE_IOCTL_TYPE, 0x02, struct liveupdate_fd)
+
+/**
+ * LIVEUPDATE_IOCTL_GET_STATE - Query the current state of the live update
+ * orchestrator.
+ *
+ * Argument: Pointer to &enum liveupdate_state.
+ *
+ * The kernel fills the enum value pointed to by the argument with the current
+ * state of the live update subsystem. Possible states are:
+ *
+ * - %LIVEUPDATE_STATE_NORMAL: Default state; no live update operation is
+ * currently in progress.
+ * - %LIVEUPDATE_STATE_PREPARED: The preparation phase (triggered by
+ * %LIVEUPDATE_IOCTL_PREPARE) has completed
+ * successfully. The system is ready for the
+ * reboot transition. Note that some
+ * device operations (e.g., unbinding, new DMA
+ * mappings) might be restricted in this state.
+ * - %LIVEUPDATE_STATE_UPDATED: The system has successfully rebooted into the
+ * new kernel via live update. It is now running
+ * the new kernel code and is awaiting the
+ * completion signal from user space via
+ * %LIVEUPDATE_IOCTL_FINISH after
+ * restoration tasks are done.
+ *
+ * See the definition of &enum liveupdate_state for more details on each state.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+#define LIVEUPDATE_IOCTL_GET_STATE \
+ _IOR(LIVEUPDATE_IOCTL_TYPE, 0x03, enum liveupdate_state)
+
+/**
+ * LIVEUPDATE_IOCTL_PREPARE - Initiate preparation phase and trigger state
+ * saving.
+ *
+ * Argument: None.
+ *
+ * Initiates the live update preparation phase. This action corresponds to
+ * the internal %LIVEUPDATE_PREPARE. This typically triggers the saving process
+ * for items marked via the PRESERVE ioctls. This typically occurs *before*
+ * the "blackout window", while user applications (e.g., VMs) may still be
+ * running. Kernel subsystems receiving the %LIVEUPDATE_PREPARE event should
+ * serialize necessary state. This command does not transfer data.
+ *
+ * Return: 0 on success, negative error code on failure. Transitions state
+ * towards %LIVEUPDATE_STATE_PREPARED on success.
+ */
+#define LIVEUPDATE_IOCTL_PREPARE \
+ _IO(LIVEUPDATE_IOCTL_TYPE, 0x04)
+
+/**
+ * LIVEUPDATE_IOCTL_CANCEL - Cancel the live update preparation phase.
+ *
+ * Argument: None.
+ *
+ * Notifies the live update subsystem to abort the preparation sequence
+ * potentially initiated by %LIVEUPDATE_IOCTL_PREPARE. This action
+ * typically corresponds to the internal %LIVEUPDATE_CANCEL kernel event,
+ * which might also be triggered automatically if the PREPARE stage fails
+ * internally.
+ *
+ * When triggered, subsystems receiving the %LIVEUPDATE_CANCEL event should
+ * revert any state changes or actions taken specifically for the aborted
+ * prepare phase (e.g., discard partially serialized state). The kernel
+ * releases resources allocated specifically for this *aborted preparation
+ * attempt*.
+ *
+ * This operation cancels the current *attempt* to prepare for a live update
+ * but does **not** remove previously validated items from the internal list
+ * of potentially preservable resources. Consequently, preservation tokens
+ * previously generated by successful %LIVEUPDATE_IOCTL_FD_PRESERVE or calls
+ * generally **remain valid** as identifiers for those potentially preservable
+ * resources. However, since the system state returns towards
+ * %LIVEUPDATE_STATE_NORMAL, user space must initiate a new live update sequence
+ * (starting with %LIVEUPDATE_IOCTL_PREPARE) to proceed with an update
+ * using these (or other) tokens.
+ *
+ * This command does not transfer data. Kernel callbacks for the
+ * %LIVEUPDATE_CANCEL event must not fail.
+ *
+ * Return: 0 on success, negative error code on failure. Transitions state back
+ * towards %LIVEUPDATE_STATE_NORMAL on success.
+ */
+#define LIVEUPDATE_IOCTL_CANCEL \
+ _IO(LIVEUPDATE_IOCTL_TYPE, 0x06)
+
+/**
+ * LIVEUPDATE_IOCTL_EVENT_FINISH - Signal restoration completion and trigger
+ * cleanup.
+ *
+ * Argument: None.
+ *
+ * Signals that user space has completed all necessary restoration actions in
+ * the new kernel (after a live update reboot). This action corresponds to the
+ * internal %LIVEUPDATE_FINISH kernel event. Calling this ioctl triggers the
+ * cleanup phase: any resources that were successfully preserved but were *not*
+ * subsequently restored (reclaimed) via the RESTORE ioctls will have their
+ * preserved state discarded and associated kernel resources released. Involved
+ * devices may be reset. All desired restorations *must* be completed *before*
+ * this. Kernel callbacks for the %LIVEUPDATE_FINISH event must not fail.
+ * Successfully completing this phase transitions the system state from
+ * %LIVEUPDATE_STATE_UPDATED back to %LIVEUPDATE_STATE_NORMAL. This command does
+ * not transfer data.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+#define LIVEUPDATE_IOCTL_FINISH \
+ _IO(LIVEUPDATE_IOCTL_TYPE, 0x07)
+
+#endif /* _UAPI_LIVEUPDATE_H */
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
index b5054140b9a9..cb3ea380f6b9 100644
--- a/kernel/liveupdate/Makefile
+++ b/kernel/liveupdate/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
obj-$(CONFIG_LIVEUPDATE) += luo_core.o
obj-$(CONFIG_LIVEUPDATE) += luo_files.o
+obj-$(CONFIG_LIVEUPDATE) += luo_ioctl.o
obj-$(CONFIG_LIVEUPDATE) += luo_subsystems.o
diff --git a/kernel/liveupdate/luo_ioctl.c b/kernel/liveupdate/luo_ioctl.c
new file mode 100644
index 000000000000..3de1d243df5a
--- /dev/null
+++ b/kernel/liveupdate/luo_ioctl.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO ioctl Interface
+ *
+ * The IOCTL user-space control interface for the LUO subsystem.
+ * It registers a misc character device, typically found at ``/dev/liveupdate``,
+ * which allows privileged userspace applications (requiring %CAP_SYS_ADMIN) to
+ * manage and monitor the LUO state machine and associated resources like
+ * preservable file descriptors.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/liveupdate.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/liveupdate.h>
+#include "luo_internal.h"
+
+static int luo_ioctl_fd_restore(struct liveupdate_fd *luo_fd)
+{
+ struct file *file;
+ int ret;
+ int fd;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0) {
+ pr_err("Failed to allocate new fd: %d\n", fd);
+ return fd;
+ }
+
+ ret = luo_retrieve_file(luo_fd->token, &file);
+ if (ret < 0) {
+ put_unused_fd(fd);
+
+ return ret;
+ }
+
+ fd_install(fd, file);
+ luo_fd->fd = fd;
+
+ return 0;
+}
+
+static int luo_open(struct inode *inodep, struct file *filep)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ if (filep->f_flags & O_EXCL)
+ return -EINVAL;
+
+ return 0;
+}
+
+static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct liveupdate_fd luo_fd;
+ enum liveupdate_state state;
+ int ret = 0;
+ u64 token;
+
+ if (_IOC_TYPE(cmd) != LIVEUPDATE_IOCTL_TYPE)
+ return -ENOTTY;
+
+ switch (cmd) {
+ case LIVEUPDATE_IOCTL_GET_STATE:
+ state = liveupdate_get_state();
+ if (copy_to_user(argp, &state, sizeof(state)))
+ ret = -EFAULT;
+ break;
+
+ case LIVEUPDATE_IOCTL_PREPARE:
+ ret = luo_prepare();
+ break;
+
+ case LIVEUPDATE_IOCTL_FINISH:
+ ret = luo_finish();
+ break;
+
+ case LIVEUPDATE_IOCTL_CANCEL:
+ ret = luo_cancel();
+ break;
+
+ case LIVEUPDATE_IOCTL_FD_PRESERVE:
+ if (copy_from_user(&luo_fd, argp, sizeof(luo_fd))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = luo_register_file(luo_fd.token, luo_fd.fd);
+ if (!ret && copy_to_user(argp, &luo_fd, sizeof(luo_fd))) {
+ WARN_ON_ONCE(luo_unregister_file(luo_fd.token));
+ ret = -EFAULT;
+ }
+ break;
+
+ case LIVEUPDATE_IOCTL_FD_UNPRESERVE:
+ if (copy_from_user(&token, argp, sizeof(u64))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = luo_unregister_file(token);
+ break;
+
+ case LIVEUPDATE_IOCTL_FD_RESTORE:
+ if (copy_from_user(&luo_fd, argp, sizeof(luo_fd))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = luo_ioctl_fd_restore(&luo_fd);
+ if (!ret && copy_to_user(argp, &luo_fd, sizeof(luo_fd)))
+ ret = -EFAULT;
+ break;
+
+ default:
+ pr_warn("ioctl: unknown command nr: 0x%x\n", _IOC_NR(cmd));
+ ret = -ENOTTY;
+ break;
+ }
+
+ return ret;
+}
+
+static const struct file_operations fops = {
+ .owner = THIS_MODULE,
+ .open = luo_open,
+ .unlocked_ioctl = luo_ioctl,
+};
+
+static struct miscdevice liveupdate_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "liveupdate",
+ .fops = &fops,
+};
+
+static int __init liveupdate_init(void)
+{
+ int err;
+
+ if (!liveupdate_enabled())
+ return 0;
+
+ err = misc_register(&liveupdate_miscdev);
+ if (err < 0) {
+ pr_err("Failed to register misc device '%s': %d\n",
+ liveupdate_miscdev.name, err);
+ }
+
+ return err;
+}
+module_init(liveupdate_init);
+
+static void __exit liveupdate_exit(void)
+{
+ misc_deregister(&liveupdate_miscdev);
+}
+module_exit(liveupdate_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pasha Tatashin");
+MODULE_DESCRIPTION("Live Update Orchestrator");
+MODULE_VERSION("0.1");
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 17/32] liveupdate: luo_sysfs: add sysfs state monitoring
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Introduce a sysfs interface for the Live Update Orchestrator
under /sys/kernel/liveupdate/. This interface provides a way for
userspace tools and scripts to monitor the current state of the LUO
state machine.
The main feature is a read-only file, state, which displays the
current LUO state as a string ("normal", "prepared", "frozen",
"updated"). The interface uses sysfs_notify to allow userspace
listeners (e.g., via poll) to be efficiently notified of state changes.
ABI documentation for this new sysfs interface is added in
Documentation/ABI/testing/sysfs-kernel-liveupdate.
This read-only sysfs interface complements the main ioctl interface
provided by /dev/liveupdate, which handles LUO control operations and
resource management.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
.../ABI/testing/sysfs-kernel-liveupdate | 51 ++++++++++
kernel/liveupdate/Kconfig | 18 ++++
kernel/liveupdate/Makefile | 1 +
kernel/liveupdate/luo_core.c | 1 +
kernel/liveupdate/luo_internal.h | 6 ++
kernel/liveupdate/luo_sysfs.c | 92 +++++++++++++++++++
6 files changed, 169 insertions(+)
create mode 100644 Documentation/ABI/testing/sysfs-kernel-liveupdate
create mode 100644 kernel/liveupdate/luo_sysfs.c
diff --git a/Documentation/ABI/testing/sysfs-kernel-liveupdate b/Documentation/ABI/testing/sysfs-kernel-liveupdate
new file mode 100644
index 000000000000..bb85cbae4943
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-liveupdate
@@ -0,0 +1,51 @@
+What: /sys/kernel/liveupdate/
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: pasha.tatashin@soleen.com
+Description: Directory containing interfaces to query the live
+ update orchestrator. Live update is the ability to reboot the
+ host kernel (e.g., via kexec, without a full power cycle) while
+ keeping specifically designated devices operational ("alive")
+ across the transition. After the new kernel boots, these devices
+ can be re-attached to their original workloads (e.g., virtual
+ machines) with their state preserved. This is particularly
+ useful, for example, for quick hypervisor updates without
+ terminating running virtual machines.
+
+
+What: /sys/kernel/liveupdate/state
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: pasha.tatashin@soleen.com
+Description: Read-only file that displays the current state of the live
+ update orchestrator as a string. Possible values are:
+
+ "normal" No live update operation is in progress. This is
+ the default operational state.
+
+ "prepared" The live update preparation phase has completed
+ successfully (e.g., triggered via the
+ /dev/liveupdate event). Kernel subsystems have
+ been notified via the %LIVEUPDATE_PREPARE
+ event/callback and should have initiated state
+ saving. User workloads (e.g., VMs) are generally
+ still running, but some operations (like device
+ unbinding or new DMA mappings) might be
+ restricted. The system is ready for the reboot
+ trigger.
+
+ "frozen" The final reboot notification has been sent
+ (e.g., triggered via the 'reboot()' syscall),
+ corresponding to the %LIVEUPDATE_REBOOT kernel
+ event. Subsystems have had their final chance to
+ save state. User workloads must be suspended.
+ The system is about to execute the reboot into
+ the new kernel (imminent kexec). This state
+ corresponds to the "blackout window".
+
+ "updated" The system has successfully rebooted into the
+ new kernel via live update. Restoration of
+ preserved resources can now occur (typically via
+ ioctl commands). The system is awaiting the
+ final 'finish' signal after user space completes
+ restoration tasks.
diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig
index f6b0bde188d9..75a17ca8a592 100644
--- a/kernel/liveupdate/Kconfig
+++ b/kernel/liveupdate/Kconfig
@@ -29,6 +29,24 @@ config LIVEUPDATE
If unsure, say N.
+config LIVEUPDATE_SYSFS_API
+ bool "Live Update sysfs monitoring interface"
+ depends on SYSFS
+ depends on LIVEUPDATE
+ help
+ Enable a sysfs interface for the Live Update Orchestrator
+ at /sys/kernel/liveupdate/.
+
+ This allows monitoring the LUO state ('normal', 'prepared',
+ 'frozen', 'updated') via the read-only 'state' file.
+
+ This interface complements the primary /dev/liveupdate ioctl
+ interface, which handles the full update process.
+ This sysfs API may be useful for scripting, or userspace monitoring
+ needed to coordinate application restarts and minimize downtime.
+
+ If unsure, say N.
+
config KEXEC_HANDOVER
bool "kexec handover"
depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile
index cb3ea380f6b9..e35ddc51ab2b 100644
--- a/kernel/liveupdate/Makefile
+++ b/kernel/liveupdate/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_LIVEUPDATE) += luo_core.o
obj-$(CONFIG_LIVEUPDATE) += luo_files.o
obj-$(CONFIG_LIVEUPDATE) += luo_ioctl.o
obj-$(CONFIG_LIVEUPDATE) += luo_subsystems.o
+obj-$(CONFIG_LIVEUPDATE_SYSFS_API) += luo_sysfs.o
diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c
index fff84c51d986..41dbe784445e 100644
--- a/kernel/liveupdate/luo_core.c
+++ b/kernel/liveupdate/luo_core.c
@@ -100,6 +100,7 @@ static inline bool is_current_luo_state(enum liveupdate_state expected_state)
static void __luo_set_state(enum liveupdate_state state)
{
WRITE_ONCE(luo_state, state);
+ luo_sysfs_notify();
}
static inline void luo_set_state(enum liveupdate_state state)
diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h
index f77e8b3044f9..05cd861ed2a8 100644
--- a/kernel/liveupdate/luo_internal.h
+++ b/kernel/liveupdate/luo_internal.h
@@ -29,4 +29,10 @@ int luo_retrieve_file(u64 token, struct file **filep);
int luo_register_file(u64 token, int fd);
int luo_unregister_file(u64 token);
+#ifdef CONFIG_LIVEUPDATE_SYSFS_API
+void luo_sysfs_notify(void);
+#else
+static inline void luo_sysfs_notify(void) {}
+#endif
+
#endif /* _LINUX_LUO_INTERNAL_H */
diff --git a/kernel/liveupdate/luo_sysfs.c b/kernel/liveupdate/luo_sysfs.c
new file mode 100644
index 000000000000..935946bb741b
--- /dev/null
+++ b/kernel/liveupdate/luo_sysfs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: LUO sysfs interface
+ *
+ * Provides a sysfs interface at ``/sys/kernel/liveupdate/`` for monitoring LUO
+ * state. Live update allows rebooting the kernel (via kexec) while preserving
+ * designated device state for attached workloads (e.g., VMs), useful for
+ * minimizing downtime during hypervisor updates.
+ *
+ * /sys/kernel/liveupdate/state
+ * ----------------------------
+ * - Permissions: Read-only
+ * - Description: Displays the current LUO state string.
+ * - Valid States:
+ * @normal
+ * Idle state.
+ * @prepared
+ * Preparation phase complete (triggered via '/dev/liveupdate'). Resources
+ * checked, state saving initiated via %LIVEUPDATE_PREPARE event.
+ * Workloads mostly running but may be restricted. Ready forreboot
+ * trigger.
+ * @frozen
+ * Final reboot notification sent (triggered via 'reboot'). Corresponds to
+ * %LIVEUPDATE_REBOOT event. Final state saving. Workloads must be
+ * suspended. System about to kexec ("blackout window").
+ * @updated
+ * New kernel booted via live update. Awaiting 'finish' signal.
+ *
+ * Userspace Interaction & Blackout Window Reduction
+ * -------------------------------------------------
+ * Userspace monitors the ``state`` file to coordinate actions:
+ * - Suspend workloads before @frozen state is entered.
+ * - Initiate resource restoration upon entering @updated state.
+ * - Resume workloads after restoration, minimizing downtime.
+ */
+
+#include <linux/kobject.h>
+#include <linux/liveupdate.h>
+#include <linux/sysfs.h>
+#include "luo_internal.h"
+
+static bool luo_sysfs_initialized;
+
+#define LUO_DIR_NAME "liveupdate"
+
+void luo_sysfs_notify(void)
+{
+ if (luo_sysfs_initialized)
+ sysfs_notify(kernel_kobj, LUO_DIR_NAME, "state");
+}
+
+/* Show the current live update state */
+static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", luo_current_state_str());
+}
+
+static struct kobj_attribute state_attribute = __ATTR_RO(state);
+
+static struct attribute *luo_attrs[] = {
+ &state_attribute.attr,
+ NULL
+};
+
+static struct attribute_group luo_attr_group = {
+ .attrs = luo_attrs,
+ .name = LUO_DIR_NAME,
+};
+
+static int __init luo_init(void)
+{
+ int ret;
+
+ ret = sysfs_create_group(kernel_kobj, &luo_attr_group);
+ if (ret) {
+ pr_err("Failed to create group\n");
+ return ret;
+ }
+
+ luo_sysfs_initialized = true;
+ pr_info("Initialized\n");
+
+ return 0;
+}
+subsys_initcall(luo_init);
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 18/32] reboot: call liveupdate_reboot() before kexec
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Modify the reboot() syscall handler in kernel/reboot.c to call
liveupdate_reboot() when processing the LINUX_REBOOT_CMD_KEXEC
command.
This ensures that the Live Update Orchestrator is notified just
before the kernel executes the kexec jump. The liveupdate_reboot()
function triggers the final LIVEUPDATE_FREEZE event, allowing
participating subsystems to perform last-minute state saving within
the blackout window, and transitions the LUO state machine to FROZEN.
The call is placed immediately before kernel_kexec() to ensure LUO
finalization happens at the latest possible moment before the kernel
transition.
If liveupdate_reboot() returns an error (indicating a failure during
LUO finalization), the kexec operation is aborted to prevent proceeding
with an inconsistent state.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/reboot.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index ec087827c85c..bdeb04a773db 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -13,6 +13,7 @@
#include <linux/kexec.h>
#include <linux/kmod.h>
#include <linux/kmsg_dump.h>
+#include <linux/liveupdate.h>
#include <linux/reboot.h>
#include <linux/suspend.h>
#include <linux/syscalls.h>
@@ -797,6 +798,9 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
#ifdef CONFIG_KEXEC_CORE
case LINUX_REBOOT_CMD_KEXEC:
+ ret = liveupdate_reboot();
+ if (ret)
+ break;
ret = kernel_kexec();
break;
#endif
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
* [PATCH v2 19/32] liveupdate: luo_files: luo_ioctl: session-based file descriptor tracking
From: Pasha Tatashin @ 2025-07-23 14:46 UTC (permalink / raw)
To: pratyush, jasonmiu, graf, changyuanl, pasha.tatashin, rppt,
dmatlack, rientjes, corbet, rdunlap, ilpo.jarvinen, kanie, ojeda,
aliceryhl, masahiroy, akpm, tj, yoann.congal, mmaurer,
roman.gushchin, chenridong, axboe, mark.rutland, jannh,
vincent.guittot, hannes, dan.j.williams, david, joel.granados,
rostedt, anna.schumaker, song, zhangguopeng, linux, linux-kernel,
linux-doc, linux-mm, gregkh, tglx, mingo, bp, dave.hansen, x86,
hpa, rafael, dakr, bartosz.golaszewski, cw00.choi, myungjoo.ham,
yesanishhere, Jonathan.Cameron, quic_zijuhu, aleksander.lobakin,
ira.weiny, andriy.shevchenko, leon, lukas, bhelgaas, wagi,
djeffery, stuart.w.hayes, ptyadav, lennart, brauner, linux-api,
linux-fsdevel, saeedm, ajayachandra, jgg, parav, leonro, witu
In-Reply-To: <20250723144649.1696299-1-pasha.tatashin@soleen.com>
Currently, file descriptors registered for preservation via
/dev/liveupdate remain globally registered with the LUO core until
explicitly unregistered. This behavior can lead to unintended
consequences: if a userspace process (e.g., a VMM or
an agent managing FDs) registers FDs for preservation and then crashes
or exits prematurely before LUO transitions to a PREPARED state (and
without explicitly unregistering them), these FDs would remain marked
for preservation. This could result in unnecessary resources being
carried over to the next kernel or stale state or leaks.
Introduce a session-based approach to FD preservation to address this
issue. Each open instance of /dev/liveupdate now corresponds to a "LUO
session," which tracks the FDs registered through it. If a LUO session
is closed (i.e., the file descriptor for /dev/liveupdate is closed by
userspace) while LUO is still in the NORMAL or UPDATED state, all FDs
registered during that specific session are automatically unregistered.
This ensures that FD preservations are tied to the lifetime of the
controlling userspace entity's session, preventing unintentional leakage
of preserved FD state into the next kernel if the live update process
is not fully initiated and completed for those FDs. FDs are only
globally committed for preservation if the LUO state machine progresses
beyond NORMAL (i.e., into PREPARED or FROZEN) before the managing
session is closed. In the future, we can relax this even further, and
preserve only when the session is still open while we are already in
reboot() system call.
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
kernel/liveupdate/luo_files.c | 225 ++++++++++++++++++++++++-------
kernel/liveupdate/luo_internal.h | 9 +-
kernel/liveupdate/luo_ioctl.c | 20 ++-
3 files changed, 197 insertions(+), 57 deletions(-)
diff --git a/kernel/liveupdate/luo_files.c b/kernel/liveupdate/luo_files.c
index cd956ea69f43..256b5261f81e 100644
--- a/kernel/liveupdate/luo_files.c
+++ b/kernel/liveupdate/luo_files.c
@@ -67,7 +67,6 @@
#define LUO_FILES_COMPATIBLE "file-descriptors-v1"
static DEFINE_XARRAY(luo_files_xa_in);
-static DEFINE_XARRAY(luo_files_xa_out);
static bool luo_files_xa_in_recreated;
/* Registered files. */
@@ -81,6 +80,15 @@ static size_t luo_file_fdt_out_size;
static atomic64_t luo_files_count;
+/* Opened sessions */
+static DECLARE_RWSEM(luo_sessions_list_rwsem);
+static LIST_HEAD(luo_sessions_list);
+
+struct luo_session {
+ struct xarray files_xa_out;
+ struct list_head list;
+};
+
/**
* struct luo_file - Represents a file descriptor instance preserved
* across live update.
@@ -262,6 +270,7 @@ static int luo_files_to_fdt(struct xarray *files_xa_out)
static int luo_files_fdt_setup(void)
{
+ struct luo_session *s;
int ret;
luo_file_fdt_out_size = luo_files_fdt_size();
@@ -300,9 +309,15 @@ static int luo_files_fdt_setup(void)
if (ret < 0)
goto exit_end_node;
- ret = luo_files_to_fdt(&luo_files_xa_out);
- if (ret < 0)
- goto exit_end_node;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ ret = luo_files_to_fdt(&s->files_xa_out);
+ if (ret < 0) {
+ up_read(&luo_sessions_list_rwsem);
+ goto exit_end_node;
+ }
+ }
+ up_read(&luo_sessions_list_rwsem);
ret = fdt_end_node(luo_file_fdt_out);
if (ret < 0)
@@ -405,44 +420,59 @@ static void luo_files_cancel_one(struct luo_file *h)
static void __luo_files_cancel(struct luo_file *boundary_file)
{
+ struct luo_session *s;
unsigned long token;
struct luo_file *h;
- xa_for_each(&luo_files_xa_out, token, h) {
- if (h == boundary_file)
- break;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ xa_for_each(&s->files_xa_out, token, h) {
+ if (h == boundary_file)
+ goto exit;
- luo_files_cancel_one(h);
+ luo_files_cancel_one(h);
+ }
}
+exit:
+ up_read(&luo_sessions_list_rwsem);
luo_files_fdt_cleanup();
}
static int luo_files_commit_data_to_fdt(void)
{
+ struct luo_session *s;
int node_offset, ret;
unsigned long token;
char token_str[19];
struct luo_file *h;
- xa_for_each(&luo_files_xa_out, token, h) {
- snprintf(token_str, sizeof(token_str), "%#0llx", (u64)token);
- node_offset = fdt_subnode_offset(luo_file_fdt_out,
- 0,
- token_str);
- ret = fdt_setprop(luo_file_fdt_out, node_offset, "data",
- &h->private_data, sizeof(h->private_data));
- if (ret < 0) {
- pr_err("Failed to set data property for token %s: %s\n",
- token_str, fdt_strerror(ret));
- return -ENOSPC;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ xa_for_each(&s->files_xa_out, token, h) {
+ snprintf(token_str, sizeof(token_str), "%#0llx",
+ (u64)token);
+ node_offset = fdt_subnode_offset(luo_file_fdt_out,
+ 0, token_str);
+ ret = fdt_setprop(luo_file_fdt_out, node_offset, "data",
+ &h->private_data,
+ sizeof(h->private_data));
+ if (ret < 0) {
+ up_read(&luo_sessions_list_rwsem);
+ pr_err("Failed to set data property for token %s: %s\n",
+ token_str, fdt_strerror(ret));
+ up_read(&luo_sessions_list_rwsem);
+ return -ENOSPC;
+ }
}
}
+ up_read(&luo_sessions_list_rwsem);
return 0;
}
static int luo_files_prepare(void *arg, u64 *data)
{
+ struct luo_session *s;
unsigned long token;
struct luo_file *h;
int ret;
@@ -451,16 +481,21 @@ static int luo_files_prepare(void *arg, u64 *data)
if (ret)
return ret;
- xa_for_each(&luo_files_xa_out, token, h) {
- ret = luo_files_prepare_one(h);
- if (ret < 0) {
- pr_err("Prepare failed for file token %#0llx handler '%s' [%d]\n",
- (u64)token, h->fh->compatible, ret);
- __luo_files_cancel(h);
-
- return ret;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ xa_for_each(&s->files_xa_out, token, h) {
+ ret = luo_files_prepare_one(h);
+ if (ret < 0) {
+ pr_err("Prepare failed for file token %#0llx handler '%s' [%d]\n",
+ (u64)token, h->fh->compatible, ret);
+ __luo_files_cancel(h);
+ up_read(&luo_sessions_list_rwsem);
+
+ return ret;
+ }
}
}
+ up_read(&luo_sessions_list_rwsem);
ret = luo_files_commit_data_to_fdt();
if (ret)
@@ -473,20 +508,26 @@ static int luo_files_prepare(void *arg, u64 *data)
static int luo_files_freeze(void *arg, u64 *data)
{
+ struct luo_session *s;
unsigned long token;
struct luo_file *h;
int ret;
- xa_for_each(&luo_files_xa_out, token, h) {
- ret = luo_files_freeze_one(h);
- if (ret < 0) {
- pr_err("Freeze callback failed for file token %#0llx handler '%s' [%d]\n",
- (u64)token, h->fh->compatible, ret);
- __luo_files_cancel(h);
-
- return ret;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ xa_for_each(&s->files_xa_out, token, h) {
+ ret = luo_files_freeze_one(h);
+ if (ret < 0) {
+ pr_err("Freeze callback failed for file token %#0llx handler '%s' [%d]\n",
+ (u64)token, h->fh->compatible, ret);
+ __luo_files_cancel(h);
+ up_read(&luo_sessions_list_rwsem);
+
+ return ret;
+ }
}
}
+ up_read(&luo_sessions_list_rwsem);
ret = luo_files_commit_data_to_fdt();
if (ret)
@@ -561,6 +602,7 @@ late_initcall(luo_files_startup);
/**
* luo_register_file - Register a file descriptor for live update management.
+ * @s: Session for the file that is being registered
* @token: Token value for this file descriptor.
* @fd: file descriptor to be preserved.
*
@@ -568,10 +610,11 @@ late_initcall(luo_files_startup);
*
* Return: 0 on success. Negative errno on failure.
*/
-int luo_register_file(u64 token, int fd)
+int luo_register_file(struct luo_session *s, u64 token, int fd)
{
struct liveupdate_file_handler *fh;
struct luo_file *luo_file;
+ struct luo_session *_s;
bool found = false;
int ret = -ENOENT;
struct file *file;
@@ -615,15 +658,20 @@ int luo_register_file(u64 token, int fd)
mutex_init(&luo_file->mutex);
luo_file->state = LIVEUPDATE_STATE_NORMAL;
- if (xa_load(&luo_files_xa_out, token)) {
- ret = -EEXIST;
- pr_warn("Token %llu is already taken\n", token);
- mutex_destroy(&luo_file->mutex);
- kfree(luo_file);
- goto exit_unlock;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(_s, &luo_sessions_list, list) {
+ if (xa_load(&_s->files_xa_out, token)) {
+ up_read(&luo_sessions_list_rwsem);
+ ret = -EEXIST;
+ pr_warn("Token %llu is already taken\n", token);
+ mutex_destroy(&luo_file->mutex);
+ kfree(luo_file);
+ goto exit_unlock;
+ }
}
+ up_read(&luo_sessions_list_rwsem);
- ret = xa_err(xa_store(&luo_files_xa_out, token, luo_file,
+ ret = xa_err(xa_store(&s->files_xa_out, token, luo_file,
GFP_KERNEL));
if (ret < 0) {
pr_warn("Failed to store file for token %llu in XArray: %d\n",
@@ -646,6 +694,7 @@ int luo_register_file(u64 token, int fd)
/**
* luo_unregister_file - Unregister a file instance using its token.
+ * @s: Session for the file that is being registered.
* @token: The unique token of the file instance to unregister.
*
* Finds the &struct luo_file associated with the @token in the
@@ -659,7 +708,7 @@ int luo_register_file(u64 token, int fd)
*
* Return: 0 on success. Negative errno on failure.
*/
-int luo_unregister_file(u64 token)
+int luo_unregister_file(struct luo_session *s, u64 token)
{
struct luo_file *luo_file;
int ret = 0;
@@ -671,7 +720,7 @@ int luo_unregister_file(u64 token)
return -EBUSY;
}
- luo_file = xa_erase(&luo_files_xa_out, token);
+ luo_file = xa_erase(&s->files_xa_out, token);
if (luo_file) {
fput(luo_file->file);
mutex_destroy(&luo_file->mutex);
@@ -736,6 +785,74 @@ int luo_retrieve_file(u64 token, struct file **filep)
return ret;
}
+/**
+ * luo_create_session - Create and register a new LUO file preservation session.
+ *
+ * This function is called when a userspace process opens the /dev/liveupdate
+ * character device.
+ *
+ * Each session allows a specific open instance of /dev/liveupdate to
+ * independently register file descriptors for preservation. These registrations
+ * are local to the session until LUO's prepare phase aggregates them.
+ * If the /dev/liveupdate file descriptor is closed while LUO is still in
+ * the NORMAL or UPDATES states, all file descriptors registered within that
+ * session will be automatically unregistered by luo_destroy_session().
+ *
+ * Return: Pointer to the newly allocated &struct luo_session on success,
+ * NULL on memory allocation failure.
+ */
+struct luo_session *luo_create_session(void)
+{
+ struct luo_session *s;
+
+ s = kmalloc(sizeof(struct luo_session), GFP_KERNEL);
+ if (s) {
+ xa_init(&s->files_xa_out);
+ INIT_LIST_HEAD(&s->list);
+
+ down_write(&luo_sessions_list_rwsem);
+ list_add_tail(&s->list, &luo_sessions_list);
+ up_write(&luo_sessions_list_rwsem);
+ }
+
+ return s;
+}
+
+/**
+ * luo_destroy_session - Release a LUO file preservation session.
+ * @s: Pointer to the &struct luo_session to be destroyed, previously obtained
+ * from luo_create_session().
+ *
+ * This function must be called when a userspace file descriptor for
+ * /dev/liveupdate is being closed (typically from the .release file
+ * operation). It is responsible for cleaning up all resources associated
+ * with the given LUO session @s.
+ */
+void luo_destroy_session(struct luo_session *s)
+{
+ unsigned long token;
+ struct luo_file *h;
+
+ down_write(&luo_sessions_list_rwsem);
+ list_del(&s->list);
+ up_write(&luo_sessions_list_rwsem);
+
+ luo_state_read_enter();
+ if (!liveupdate_state_normal() && !liveupdate_state_updated()) {
+ luo_state_read_exit();
+ goto skip_unregister;
+ }
+
+ xa_for_each(&s->files_xa_out, token, h)
+ luo_unregister_file(s, token);
+
+ luo_state_read_exit();
+
+skip_unregister:
+ xa_destroy(&s->files_xa_out);
+ kfree(s);
+}
+
/**
* liveupdate_register_file_handler - Register a file handler with LUO.
* @fh: Pointer to a caller-allocated &struct liveupdate_file_handler.
@@ -796,6 +913,7 @@ EXPORT_SYMBOL_GPL(liveupdate_register_file_handler);
*/
int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh)
{
+ struct luo_session *s;
unsigned long token;
struct luo_file *h;
int ret = 0;
@@ -807,15 +925,18 @@ int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh)
}
down_write(&luo_register_file_list_rwsem);
-
- xa_for_each(&luo_files_xa_out, token, h) {
- if (h->fh == fh) {
- up_write(&luo_register_file_list_rwsem);
- luo_state_read_exit();
- return -EBUSY;
+ down_read(&luo_sessions_list_rwsem);
+ list_for_each_entry(s, &luo_sessions_list, list) {
+ xa_for_each(&s->files_xa_out, token, h) {
+ if (h->fh == fh) {
+ up_read(&luo_sessions_list_rwsem);
+ up_write(&luo_register_file_list_rwsem);
+ luo_state_read_exit();
+ return -EBUSY;
+ }
}
}
-
+ up_read(&luo_sessions_list_rwsem);
list_del_init(&fh->list);
up_write(&luo_register_file_list_rwsem);
luo_state_read_exit();
diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h
index 05cd861ed2a8..8fef414e7e3e 100644
--- a/kernel/liveupdate/luo_internal.h
+++ b/kernel/liveupdate/luo_internal.h
@@ -25,9 +25,14 @@ int luo_do_subsystems_freeze_calls(void);
void luo_do_subsystems_finish_calls(void);
void luo_do_subsystems_cancel_calls(void);
+struct luo_session;
+
int luo_retrieve_file(u64 token, struct file **filep);
-int luo_register_file(u64 token, int fd);
-int luo_unregister_file(u64 token);
+int luo_register_file(struct luo_session *s, u64 token, int fd);
+int luo_unregister_file(struct luo_session *s, u64 token);
+
+struct luo_session *luo_create_session(void);
+void luo_destroy_session(struct luo_session *s);
#ifdef CONFIG_LIVEUPDATE_SYSFS_API
void luo_sysfs_notify(void);
diff --git a/kernel/liveupdate/luo_ioctl.c b/kernel/liveupdate/luo_ioctl.c
index 3de1d243df5a..d2c49cf33dd3 100644
--- a/kernel/liveupdate/luo_ioctl.c
+++ b/kernel/liveupdate/luo_ioctl.c
@@ -62,6 +62,17 @@ static int luo_open(struct inode *inodep, struct file *filep)
if (filep->f_flags & O_EXCL)
return -EINVAL;
+ filep->private_data = luo_create_session();
+ if (!filep->private_data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int luo_release(struct inode *inodep, struct file *filep)
+{
+ luo_destroy_session(filep->private_data);
+
return 0;
}
@@ -101,9 +112,11 @@ static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
break;
}
- ret = luo_register_file(luo_fd.token, luo_fd.fd);
+ ret = luo_register_file(filep->private_data, luo_fd.token,
+ luo_fd.fd);
if (!ret && copy_to_user(argp, &luo_fd, sizeof(luo_fd))) {
- WARN_ON_ONCE(luo_unregister_file(luo_fd.token));
+ WARN_ON_ONCE(luo_unregister_file(filep->private_data,
+ luo_fd.token));
ret = -EFAULT;
}
break;
@@ -114,7 +127,7 @@ static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
break;
}
- ret = luo_unregister_file(token);
+ ret = luo_unregister_file(filep->private_data, token);
break;
case LIVEUPDATE_IOCTL_FD_RESTORE:
@@ -140,6 +153,7 @@ static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
static const struct file_operations fops = {
.owner = THIS_MODULE,
.open = luo_open,
+ .release = luo_release,
.unlocked_ioctl = luo_ioctl,
};
--
2.50.0.727.gbf7dc18ff4-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox