Message-ID: <20250625231838.1897085-12-pasha.tatashin@soleen.com>
Date: Wed, 25 Jun 2025 23:17:58 +0000
From: Pasha Tatashin <pasha.tatashin@...een.com>
To: pratyush@...nel.org,
	jasonmiu@...gle.com,
	graf@...zon.com,
	changyuanl@...gle.com,
	pasha.tatashin@...een.com,
	rppt@...nel.org,
	dmatlack@...gle.com,
	rientjes@...gle.com,
	corbet@....net,
	rdunlap@...radead.org,
	ilpo.jarvinen@...ux.intel.com,
	kanie@...ux.alibaba.com,
	ojeda@...nel.org,
	aliceryhl@...gle.com,
	masahiroy@...nel.org,
	akpm@...ux-foundation.org,
	tj@...nel.org,
	yoann.congal@...le.fr,
	mmaurer@...gle.com,
	roman.gushchin@...ux.dev,
	chenridong@...wei.com,
	axboe@...nel.dk,
	mark.rutland@....com,
	jannh@...gle.com,
	vincent.guittot@...aro.org,
	hannes@...xchg.org,
	dan.j.williams@...el.com,
	david@...hat.com,
	joel.granados@...nel.org,
	rostedt@...dmis.org,
	anna.schumaker@...cle.com,
	song@...nel.org,
	zhangguopeng@...inos.cn,
	linux@...ssschuh.net,
	linux-kernel@...r.kernel.org,
	linux-doc@...r.kernel.org,
	linux-mm@...ck.org,
	gregkh@...uxfoundation.org,
	tglx@...utronix.de,
	mingo@...hat.com,
	bp@...en8.de,
	dave.hansen@...ux.intel.com,
	x86@...nel.org,
	hpa@...or.com,
	rafael@...nel.org,
	dakr@...nel.org,
	bartosz.golaszewski@...aro.org,
	cw00.choi@...sung.com,
	myungjoo.ham@...sung.com,
	yesanishhere@...il.com,
	Jonathan.Cameron@...wei.com,
	quic_zijuhu@...cinc.com,
	aleksander.lobakin@...el.com,
	ira.weiny@...el.com,
	andriy.shevchenko@...ux.intel.com,
	leon@...nel.org,
	lukas@...ner.de,
	bhelgaas@...gle.com,
	wagi@...nel.org,
	djeffery@...hat.com,
	stuart.w.hayes@...il.com,
	ptyadav@...zon.de,
	lennart@...ttering.net,
	brauner@...nel.org,
	linux-api@...r.kernel.org,
	linux-fsdevel@...r.kernel.org
Subject: [PATCH v1 11/32] liveupdate: luo_core: integrate with KHO

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@...een.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

Powered by blists - more mailing lists