[PATCH v2 00/28] partition suspend updates

@@ -1050,9 +1050,11 @@ static struct rtas_filter rtas_filters[] __ro_after_init = {
 	{ "set-time-for-power-on", -1, -1, -1, -1, -1 },
 	{ "ibm,set-system-parameter", -1, 1, -1, -1, -1 },
 	{ "set-time-of-day", -1, -1, -1, -1, -1 },
+#ifdef CONFIG_CPU_BIG_ENDIAN
 	{ "ibm,suspend-me", -1, -1, -1, -1, -1 },
 	{ "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 },
 	{ "ibm,update-properties", -1, 0, -1, -1, -1, 4096 },
+#endif
 	{ "ibm,physical-attestation", -1, 0, 1, -1, -1 },
 };
 

@@ -257,7 +257,7 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
-extern int rtas_ibm_suspend_me(u64 handle);
+int rtas_ibm_suspend_me_unsafe(u64 handle);
 
 struct rtc_time;
 extern time64_t rtas_get_boot_time(void);

@@ -843,7 +843,7 @@ static void rtas_percpu_suspend_me(void *info)
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
-int rtas_ibm_suspend_me(u64 handle)
+int rtas_ibm_suspend_me_unsafe(u64 handle)
 {
 	long state;
 	long rc;

@@ -949,7 +949,7 @@ int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
 }
 
 #else /* CONFIG_PPC_PSERIES */
-int rtas_ibm_suspend_me(u64 handle)
+int rtas_ibm_suspend_me_unsafe(u64 handle)
 {
 	return -ENOSYS;
 }

@@ -1185,7 +1185,7 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 		int rc = 0;
 		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
 		              | be32_to_cpu(args.args[1]);
-		rc = rtas_ibm_suspend_me(handle);
+		rc = rtas_ibm_suspend_me_unsafe(handle);
 		if (rc == -EAGAIN)
 			args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
 		else if (rc == -EIO)

@@ -370,7 +370,7 @@ static ssize_t migration_store(struct class *class,
 		return rc;
 
 	do {
-		rc = rtas_ibm_suspend_me(streamid);
+		rc = rtas_ibm_suspend_me_unsafe(streamid);
 		if (rc == -EAGAIN)
 			ssleep(1);
 	} while (rc == -EAGAIN);

@@ -258,6 +258,7 @@ extern void rtas_progress(char *s, unsigned short hex);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
 int rtas_ibm_suspend_me_unsafe(u64 handle);
+int rtas_ibm_suspend_me(int *fw_status);
 
 struct rtc_time;
 extern time64_t rtas_get_boot_time(void);

@@ -684,6 +684,63 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value)
 	return rc;
 }
 
+/**
+ * rtas_ibm_suspend_me() - Call ibm,suspend-me to suspend the LPAR.
+ *
+ * @fw_status: RTAS call status will be placed here if not NULL.
+ *
+ * rtas_ibm_suspend_me() should be called only on a CPU which has
+ * received H_CONTINUE from the H_JOIN hcall. All other active CPUs
+ * should be waiting to return from H_JOIN.
+ *
+ * rtas_ibm_suspend_me() may suspend execution of the OS
+ * indefinitely. Callers should take appropriate measures upon return, such as
+ * resetting watchdog facilities.
+ *
+ * Callers may choose to retry this call if @fw_status is
+ * %RTAS_THREADS_ACTIVE.
+ *
+ * Return:
+ * 0          - The partition has resumed from suspend, possibly after
+ *              migration to a different host.
+ * -ECANCELED - The operation was aborted.
+ * -EAGAIN    - There were other CPUs not in H_JOIN at the time of the call.
+ * -EBUSY     - Some other condition prevented the suspend from succeeding.
+ * -EIO       - Hardware/platform error.
+ */
+int rtas_ibm_suspend_me(int *fw_status)
+{
+	int fwrc;
+	int ret;
+
+	fwrc = rtas_call(rtas_token("ibm,suspend-me"), 0, 1, NULL);
+
+	switch (fwrc) {
+	case 0:
+		ret = 0;
+		break;
+	case RTAS_SUSPEND_ABORTED:
+		ret = -ECANCELED;
+		break;
+	case RTAS_THREADS_ACTIVE:
+		ret = -EAGAIN;
+		break;
+	case RTAS_NOT_SUSPENDABLE:
+	case RTAS_OUTSTANDING_COPROC:
+		ret = -EBUSY;
+		break;
+	case -1:
+	default:
+		ret = -EIO;
+		break;
+	}
+
+	if (fw_status)
+		*fw_status = fwrc;
+
+	return ret;
+}
+
 void __noreturn rtas_restart(char *cmd)
 {
 	if (rtas_flash_term_hook)

@@ -23,11 +23,16 @@
 #define RTAS_RMOBUF_MAX (64 * 1024)
 
 /* RTAS return status codes */
-#define RTAS_NOT_SUSPENDABLE	-9004
 #define RTAS_BUSY		-2    /* RTAS Busy */
 #define RTAS_EXTENDED_DELAY_MIN	9900
 #define RTAS_EXTENDED_DELAY_MAX	9905
 
+/* statuses specific to ibm,suspend-me */
+#define RTAS_SUSPEND_ABORTED     9000 /* Suspension aborted */
+#define RTAS_NOT_SUSPENDABLE    -9004 /* Partition not suspendable */
+#define RTAS_THREADS_ACTIVE     -9005 /* Multiple processor threads active */
+#define RTAS_OUTSTANDING_COPROC -9006 /* Outstanding coprocessor operations */
+
 /*
  * In general to call RTAS use rtas_token("string") to lookup
  * an RTAS token for the given string (e.g. "event-scan").

@@ -247,6 +247,7 @@ extern void __noreturn rtas_restart(char *cmd);
 extern void rtas_power_off(void);
 extern void __noreturn rtas_halt(void);
 extern void rtas_os_term(char *str);
+void rtas_activate_firmware(void);
 extern int rtas_get_sensor(int sensor, int index, int *state);
 extern int rtas_get_sensor_fast(int sensor, int index, int *state);
 extern int rtas_get_power_level(int powerdomain, int *level);

@@ -798,6 +798,36 @@ void rtas_os_term(char *str)
 		printk(KERN_EMERG "ibm,os-term call failed %d\n", status);
 }
 
+/**
+ * rtas_activate_firmware() - Activate a new version of firmware.
+ *
+ * Activate a new version of partition firmware. The OS must call this
+ * after resuming from a partition hibernation or migration in order
+ * to maintain the ability to perform live firmware updates. It's not
+ * catastrophic for this method to be absent or to fail; just log the
+ * condition in that case.
+ *
+ * Context: This function may sleep.
+ */
+void rtas_activate_firmware(void)
+{
+	int token;
+	int fwrc;
+
+	token = rtas_token("ibm,activate-firmware");
+	if (token == RTAS_UNKNOWN_SERVICE) {
+		pr_notice("ibm,activate-firmware method unavailable\n");
+		return;
+	}
+
+	do {
+		fwrc = rtas_call(token, 0, 1, NULL);
+	} while (rtas_busy_delay(fwrc));
+
+	if (fwrc)
+		pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
+}
+
 static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
 static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)

@@ -261,7 +261,7 @@ int pseries_devicetree_update(s32 scope)
 
 	update_nodes_token = rtas_token("ibm,update-nodes");
 	if (update_nodes_token == RTAS_UNKNOWN_SERVICE)
-		return -EINVAL;
+		return 0;
 
 	rtas_buf = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
 	if (!rtas_buf)

@@ -155,6 +155,14 @@
 #define H_VASI_RESUMED          5
 #define H_VASI_COMPLETED        6
 
+/* VASI signal codes. Only the Cancel code is valid for H_VASI_SIGNAL. */
+#define H_VASI_SIGNAL_CANCEL    1
+#define H_VASI_SIGNAL_ABORT     2
+#define H_VASI_SIGNAL_SUSPEND   3
+#define H_VASI_SIGNAL_COMPLETE  4
+#define H_VASI_SIGNAL_ENABLE    5
+#define H_VASI_SIGNAL_FAILOVER  6
+
 /* Each control block has to be on a 4K boundary */
 #define H_CB_ALIGNMENT          4096
 

@@ -261,6 +269,7 @@
 #define H_ADD_CONN		0x284
 #define H_DEL_CONN		0x288
 #define H_JOIN			0x298
+#define H_VASI_SIGNAL           0x2A0
 #define H_VASI_STATE            0x2A4
 #define H_VIOCTL		0x2A8
 #define H_ENABLE_CRQ		0x2B0

@@ -213,6 +213,7 @@ static int update_dt_node(__be32 phandle, s32 scope)
 				}
 
 				prop_data += vd;
+				break;
 			}
 
 			cond_resched();

@@ -312,21 +312,8 @@ int pseries_devicetree_update(s32 scope)
 void post_mobility_fixup(void)
 {
 	int rc;
-	int activate_fw_token;
 
-	activate_fw_token = rtas_token("ibm,activate-firmware");
-	if (activate_fw_token == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_ERR "Could not make post-mobility "
-		       "activate-fw call.\n");
-		return;
-	}
-
-	do {
-		rc = rtas_call(activate_fw_token, 0, 1, NULL);
-	} while (rtas_busy_delay(rc));
-
-	if (rc)
-		printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc);
+	rtas_activate_firmware();
 
 	/*
 	 * We don't want CPUs to go online/offline while the device

@@ -12,9 +12,11 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
+#include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/stat.h>
+#include <linux/stop_machine.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/delay.h>

@@ -405,6 +407,128 @@ static int wait_for_vasi_session_suspending(u64 handle)
 	return ret;
 }
 
+static void prod_single(unsigned int target_cpu)
+{
+	long hvrc;
+	int hwid;
+
+	hwid = get_hard_smp_processor_id(target_cpu);
+	hvrc = plpar_hcall_norets(H_PROD, hwid);
+	if (hvrc == H_SUCCESS)
+		return;
+	pr_err_ratelimited("H_PROD of CPU %u (hwid %d) error: %ld\n",
+			   target_cpu, hwid, hvrc);
+}
+
+static void prod_others(void)
+{
+	unsigned int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (cpu != smp_processor_id())
+			prod_single(cpu);
+	}
+}
+
+static u16 clamp_slb_size(void)
+{
+	u16 prev = mmu_slb_size;
+
+	slb_set_size(SLB_MIN_SIZE);
+
+	return prev;
+}
+
+static int do_suspend(void)
+{
+	u16 saved_slb_size;
+	int status;
+	int ret;
+
+	pr_info("calling ibm,suspend-me on CPU %i\n", smp_processor_id());
+
+	/*
+	 * The destination processor model may have fewer SLB entries
+	 * than the source. We reduce mmu_slb_size to a safe minimum
+	 * before suspending in order to minimize the possibility of
+	 * programming non-existent entries on the destination. If
+	 * suspend fails, we restore it before returning. On success
+	 * the OF reconfig path will update it from the new device
+	 * tree after resuming on the destination.
+	 */
+	saved_slb_size = clamp_slb_size();
+
+	ret = rtas_ibm_suspend_me(&status);
+	if (ret != 0) {
+		pr_err("ibm,suspend-me error: %d\n", status);
+		slb_set_size(saved_slb_size);
+	}
+
+	return ret;
+}
+
+static int do_join(void *arg)
+{
+	atomic_t *counter = arg;
+	long hvrc;
+	int ret;
+
+	/* Must ensure MSR.EE off for H_JOIN. */
+	hard_irq_disable();
+	hvrc = plpar_hcall_norets(H_JOIN);
+
+	switch (hvrc) {
+	case H_CONTINUE:
+		/*
+		 * All other CPUs are offline or in H_JOIN. This CPU
+		 * attempts the suspend.
+		 */
+		ret = do_suspend();
+		break;
+	case H_SUCCESS:
+		/*
+		 * The suspend is complete and this cpu has received a
+		 * prod.
+		 */
+		ret = 0;
+		break;
+	case H_BAD_MODE:
+	case H_HARDWARE:
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("H_JOIN error %ld on CPU %i\n",
+				   hvrc, smp_processor_id());
+		break;
+	}
+
+	if (atomic_inc_return(counter) == 1) {
+		pr_info("CPU %u waking all threads\n", smp_processor_id());
+		prod_others();
+	}
+	/*
+	 * Execution may have been suspended for several seconds, so
+	 * reset the watchdog.
+	 */
+	touch_nmi_watchdog();
+	return ret;
+}
+
+static int pseries_migrate_partition(u64 handle)
+{
+	atomic_t counter = ATOMIC_INIT(0);
+	int ret;
+
+	ret = wait_for_vasi_session_suspending(handle);
+	if (ret)
+		return ret;
+
+	ret = stop_machine(do_join, &counter, cpu_online_mask);
+	if (ret == 0)
+		post_mobility_fixup();
+
+	return ret;
+}
+
 static ssize_t migration_store(struct class *class,
 			       struct class_attribute *attr, const char *buf,
 			       size_t count)

@@ -416,16 +540,10 @@ static ssize_t migration_store(struct class *class,
 	if (rc)
 		return rc;
 
-	rc = wait_for_vasi_session_suspending(streamid);
+	rc = pseries_migrate_partition(streamid);
 	if (rc)
 		return rc;
 
-	rc = rtas_ibm_suspend_me_unsafe(streamid);
-	if (rc)
-		return rc;
-
-	post_mobility_fixup();
-
 	return count;
 }
 

@@ -208,8 +208,8 @@ static int update_dt_node(__be32 phandle, s32 scope)
 				rc = update_dt_property(dn, &prop, prop_name,
 							vd, prop_data);
 				if (rc) {
-					printk(KERN_ERR "Could not update %s"
-					       " property\n", prop_name);
+					pr_err("updating %s property failed: %d\n",
+					       prop_name, rc);
 				}
 
 				prop_data += vd;

@@ -343,8 +343,7 @@ void post_mobility_fixup(void)
 
 	rc = pseries_devicetree_update(MIGRATION_SCOPE);
 	if (rc)
-		printk(KERN_ERR "Post-mobility device tree update "
-			"failed: %d\n", rc);
+		pr_err("device tree update failed: %d\n", rc);
 
 	cacheinfo_rebuild();
 

@@ -513,6 +513,35 @@ static int do_join(void *arg)
 	return ret;
 }
 
+/*
+ * Abort reason code byte 0. We use only the 'Migrating partition' value.
+ */
+enum vasi_aborting_entity {
+	ORCHESTRATOR        = 1,
+	VSP_SOURCE          = 2,
+	PARTITION_FIRMWARE  = 3,
+	PLATFORM_FIRMWARE   = 4,
+	VSP_TARGET          = 5,
+	MIGRATING_PARTITION = 6,
+};
+
+static void pseries_cancel_migration(u64 handle, int err)
+{
+	u32 reason_code;
+	u32 detail;
+	u8 entity;
+	long hvrc;
+
+	entity = MIGRATING_PARTITION;
+	detail = abs(err) & 0xffffff;
+	reason_code = (entity << 24) | detail;
+
+	hvrc = plpar_hcall_norets(H_VASI_SIGNAL, handle,
+				  H_VASI_SIGNAL_CANCEL, reason_code);
+	if (hvrc)
+		pr_err("H_VASI_SIGNAL error: %ld\n", hvrc);
+}
+
 static int pseries_migrate_partition(u64 handle)
 {
 	atomic_t counter = ATOMIC_INIT(0);

@@ -525,6 +554,8 @@ static int pseries_migrate_partition(u64 handle)
 	ret = stop_machine(do_join, &counter, cpu_online_mask);
 	if (ret == 0)
 		post_mobility_fixup();
+	else
+		pseries_cancel_migration(handle, ret);
 
 	return ret;
 }

@@ -542,16 +542,71 @@ static void pseries_cancel_migration(u64 handle, int err)
 		pr_err("H_VASI_SIGNAL error: %ld\n", hvrc);
 }
 
+static int pseries_suspend(u64 handle)
+{
+	const unsigned int max_attempts = 5;
+	unsigned int retry_interval_ms = 1;
+	unsigned int attempt = 1;
+	int ret;
+
+	while (true) {
+		atomic_t counter = ATOMIC_INIT(0);
+		unsigned long vasi_state;
+		int vasi_err;
+
+		ret = stop_machine(do_join, &counter, cpu_online_mask);
+		if (ret == 0)
+			break;
+		/*
+		 * Encountered an error. If the VASI stream is still
+		 * in Suspending state, it's likely a transient
+		 * condition related to some device in the partition
+		 * and we can retry in the hope that the cause has
+		 * cleared after some delay.
+		 *
+		 * A better design would allow drivers etc to prepare
+		 * for the suspend and avoid conditions which prevent
+		 * the suspend from succeeding. For now, we have this
+		 * mitigation.
+		 */
+		pr_notice("Partition suspend attempt %u of %u error: %d\n",
+			  attempt, max_attempts, ret);
+
+		if (attempt == max_attempts)
+			break;
+
+		vasi_err = poll_vasi_state(handle, &vasi_state);
+		if (vasi_err == 0) {
+			if (vasi_state != H_VASI_SUSPENDING) {
+				pr_notice("VASI state %lu after failed suspend\n",
+					  vasi_state);
+				break;
+			}
+		} else if (vasi_err != -EOPNOTSUPP) {
+			pr_err("VASI state poll error: %d", vasi_err);
+			break;
+		}
+
+		pr_notice("Will retry partition suspend after %u ms\n",
+			  retry_interval_ms);
+
+		msleep(retry_interval_ms);
+		retry_interval_ms *= 10;
+		attempt++;
+	}
+
+	return ret;
+}
+
 static int pseries_migrate_partition(u64 handle)
 {
-	atomic_t counter = ATOMIC_INIT(0);
 	int ret;
 
 	ret = wait_for_vasi_session_suspending(handle);
 	if (ret)
 		return ret;
 
-	ret = stop_machine(do_join, &counter, cpu_online_mask);
+	ret = pseries_suspend(handle);
 	if (ret == 0)
 		post_mobility_fixup();
 	else

@@ -345,6 +345,66 @@ void post_mobility_fixup(void)
 	return;
 }
 
+static int poll_vasi_state(u64 handle, unsigned long *res)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long hvrc;
+	int ret;
+
+	hvrc = plpar_hcall(H_VASI_STATE, retbuf, handle);
+	switch (hvrc) {
+	case H_SUCCESS:
+		ret = 0;
+		*res = retbuf[0];
+		break;
+	case H_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case H_FUNCTION:
+		ret = -EOPNOTSUPP;
+		break;
+	case H_HARDWARE:
+	default:
+		pr_err("unexpected H_VASI_STATE result %ld\n", hvrc);
+		ret = -EIO;
+		break;
+	}
+	return ret;
+}
+
+static int wait_for_vasi_session_suspending(u64 handle)
+{
+	unsigned long state;
+	int ret;
+
+	/*
+	 * Wait for transition from H_VASI_ENABLED to
+	 * H_VASI_SUSPENDING. Treat anything else as an error.
+	 */
+	while (true) {
+		ret = poll_vasi_state(handle, &state);
+
+		if (ret != 0 || state == H_VASI_SUSPENDING) {
+			break;
+		} else if (state == H_VASI_ENABLED) {
+			ssleep(1);
+		} else {
+			pr_err("unexpected H_VASI_STATE result %lu\n", state);
+			ret = -EIO;
+			break;
+		}
+	}
+
+	/*
+	 * Proceed even if H_VASI_STATE is unavailable. If H_JOIN or
+	 * ibm,suspend-me are also unimplemented, we'll recover then.
+	 */
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
+
+	return ret;
+}
+
 static ssize_t migration_store(struct class *class,
 			       struct class_attribute *attr, const char *buf,
 			       size_t count)

@@ -356,12 +416,11 @@ static ssize_t migration_store(struct class *class,
 	if (rc)
 		return rc;
 
-	do {
-		rc = rtas_ibm_suspend_me_unsafe(streamid);
-		if (rc == -EAGAIN)
-			ssleep(1);
-	} while (rc == -EAGAIN);
+	rc = wait_for_vasi_session_suspending(streamid);
+	if (rc)
+		return rc;
 
+	rc = rtas_ibm_suspend_me_unsafe(streamid);
 	if (rc)
 		return rc;
 

@@ -279,8 +279,13 @@ extern time64_t last_rtas_event;
 extern int clobbering_unread_rtas_event(void);
 extern int pseries_devicetree_update(s32 scope);
 extern void post_mobility_fixup(void);
+int rtas_syscall_dispatch_ibm_suspend_me(u64 handle);
 #else
 static inline int clobbering_unread_rtas_event(void) { return 0; }
+static inline int rtas_syscall_dispatch_ibm_suspend_me(u64 handle)
+{
+	return -EINVAL;
+}
 #endif
 
 #ifdef CONFIG_PPC_RTAS_DAEMON

@@ -1272,7 +1272,7 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 		int rc = 0;
 		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
 		              | be32_to_cpu(args.args[1]);
-		rc = rtas_ibm_suspend_me_unsafe(handle);
+		rc = rtas_syscall_dispatch_ibm_suspend_me(handle);
 		if (rc == -EAGAIN)
 			args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
 		else if (rc == -EIO)

@@ -615,6 +615,11 @@ static int pseries_migrate_partition(u64 handle)
 	return ret;
 }
 
+int rtas_syscall_dispatch_ibm_suspend_me(u64 handle)
+{
+	return pseries_migrate_partition(handle);
+}
+
 static ssize_t migration_store(struct class *class,
 			       struct class_attribute *attr, const char *buf,
 			       size_t count)

@@ -258,7 +258,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
-int rtas_ibm_suspend_me_unsafe(u64 handle);
 int rtas_ibm_suspend_me(int *fw_status);
 
 struct rtc_time;

@@ -925,66 +925,6 @@ int rtas_suspend_cpu(struct rtas_suspend_me_data *data)
 	return __rtas_suspend_cpu(data, 0);
 }
 
-static void rtas_percpu_suspend_me(void *info)
-{
-	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
-}
-
-int rtas_ibm_suspend_me_unsafe(u64 handle)
-{
-	long state;
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-	struct rtas_suspend_me_data data;
-	DECLARE_COMPLETION_ONSTACK(done);
-
-	if (!rtas_service_present("ibm,suspend-me"))
-		return -ENOSYS;
-
-	/* Make sure the state is valid */
-	rc = plpar_hcall(H_VASI_STATE, retbuf, handle);
-
-	state = retbuf[0];
-
-	if (rc) {
-		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc);
-		return rc;
-	} else if (state == H_VASI_ENABLED) {
-		return -EAGAIN;
-	} else if (state != H_VASI_SUSPENDING) {
-		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n",
-		       state);
-		return -EIO;
-	}
-
-	atomic_set(&data.working, 0);
-	atomic_set(&data.done, 0);
-	atomic_set(&data.error, 0);
-	data.token = rtas_token("ibm,suspend-me");
-	data.complete = &done;
-
-	lock_device_hotplug();
-
-	cpu_hotplug_disable();
-
-	/* Call function on all CPUs.  One of us will make the
-	 * rtas call
-	 */
-	on_each_cpu(rtas_percpu_suspend_me, &data, 0);
-
-	wait_for_completion(&done);
-
-	if (atomic_read(&data.error) != 0)
-		printk(KERN_ERR "Error doing global join\n");
-
-
-	cpu_hotplug_enable();
-
-	unlock_device_hotplug();
-
-	return atomic_read(&data.error);
-}
-
 /**
  * rtas_call_reentrant() - Used for reentrant rtas calls
  * @token:	Token for desired reentrant RTAS call

@@ -1035,12 +975,7 @@ int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
 	return ret;
 }
 
-#else /* CONFIG_PPC_PSERIES */
-int rtas_ibm_suspend_me_unsafe(u64 handle)
-{
-	return -ENOSYS;
-}
-#endif
+#endif /* CONFIG_PPC_PSERIES */
 
 /**
  * Find a specific pseries error log in an RTAS extended event log.

@@ -15,7 +15,6 @@
 #include <asm/topology.h>
 #include "../../kernel/cacheinfo.h"
 
-static u64 stream_id;
 static struct device suspend_dev;
 static DECLARE_COMPLETION(suspend_work);
 static struct rtas_suspend_me_data suspend_data;

@@ -29,7 +28,7 @@ static atomic_t suspending;
  * Return value:
  * 	0 on success / other on failure
  **/
-static int pseries_suspend_begin(suspend_state_t state)
+static int pseries_suspend_begin(u64 stream_id)
 {
 	long vasi_state, rc;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];

@@ -132,6 +131,7 @@ static ssize_t store_hibernate(struct device *dev,
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
+	u64 stream_id;
 	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))

@@ -140,7 +140,7 @@ static ssize_t store_hibernate(struct device *dev,
 	stream_id = simple_strtoul(buf, NULL, 16);
 
 	do {
-		rc = pseries_suspend_begin(PM_SUSPEND_MEM);
+		rc = pseries_suspend_begin(stream_id);
 		if (rc == -EAGAIN)
 			ssleep(1);
 	} while (rc == -EAGAIN);

@@ -148,8 +148,6 @@ static ssize_t store_hibernate(struct device *dev,
 	if (!rc)
 		rc = pm_suspend(PM_SUSPEND_MEM);
 
-	stream_id = 0;
-
 	if (!rc)
 		rc = count;
 

@@ -187,7 +187,6 @@ static struct bus_type suspend_subsys = {
 
 static const struct platform_suspend_ops pseries_suspend_ops = {
 	.valid		= suspend_valid_only_mem,
-	.begin		= pseries_suspend_begin,
 	.prepare_late	= pseries_prepare_late,
 	.enter		= pseries_suspend_enter,
 };

@@ -48,20 +48,6 @@ static int pseries_suspend_begin(u64 stream_id)
 		       vasi_state);
 		return -EIO;
 	}
-
-	return 0;
-}
-
-/**
- * pseries_suspend_cpu - Suspend a single CPU
- *
- * Makes the H_JOIN call to suspend the CPU
- *
- **/
-static int pseries_suspend_cpu(void)
-{
-	if (atomic_read(&suspending))
-		return rtas_suspend_cpu(&suspend_data);
 	return 0;
 }
 

@@ -235,7 +221,6 @@ static int __init pseries_suspend_init(void)
 	if ((rc = pseries_suspend_sysfs_register(&suspend_dev)))
 		return rc;
 
-	ppc_md.suspend_disable_cpu = pseries_suspend_cpu;
 	ppc_md.suspend_enable_irqs = pseries_suspend_enable_irqs;
 	suspend_set_ops(&pseries_suspend_ops);
 	return 0;

@@ -207,7 +207,6 @@ struct machdep_calls {
 	void (*suspend_disable_irqs)(void);
 	void (*suspend_enable_irqs)(void);
 #endif
-	int (*suspend_disable_cpu)(void);
 
 #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 	ssize_t (*cpu_probe)(const char *, size_t);

@@ -256,7 +256,6 @@ extern bool rtas_indicator_present(int token, int *maxindex);
 extern int rtas_set_indicator(int indicator, int index, int new_value);
 extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
-extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
 int rtas_ibm_suspend_me(int *fw_status);
 

@@ -873,58 +873,6 @@ int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data)
 	return __rtas_suspend_last_cpu(data, 0);
 }
 
-static int __rtas_suspend_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
-{
-	long rc = H_SUCCESS;
-	unsigned long msr_save;
-	int cpu;
-
-	atomic_inc(&data->working);
-
-	/* really need to ensure MSR.EE is off for H_JOIN */
-	msr_save = mfmsr();
-	mtmsr(msr_save & ~(MSR_EE));
-
-	while (rc == H_SUCCESS && !atomic_read(&data->done) && !atomic_read(&data->error))
-		rc = plpar_hcall_norets(H_JOIN);
-
-	mtmsr(msr_save);
-
-	if (rc == H_SUCCESS) {
-		/* This cpu was prodded and the suspend is complete. */
-		goto out;
-	} else if (rc == H_CONTINUE) {
-		/* All other cpus are in H_JOIN, this cpu does
-		 * the suspend.
-		 */
-		return __rtas_suspend_last_cpu(data, wake_when_done);
-	} else {
-		printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n",
-		       smp_processor_id(), rc);
-		atomic_set(&data->error, rc);
-	}
-
-	if (wake_when_done) {
-		atomic_set(&data->done, 1);
-
-		/* This cpu did the suspend or got an error; in either case,
-		 * we need to prod all other other cpus out of join state.
-		 * Extra prods are harmless.
-		 */
-		for_each_online_cpu(cpu)
-			plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
-	}
-out:
-	if (atomic_dec_return(&data->working) == 0)
-		complete(data->complete);
-	return rc;
-}
-
-int rtas_suspend_cpu(struct rtas_suspend_me_data *data)
-{
-	return __rtas_suspend_cpu(data, 0);
-}
-
 /**
  * rtas_call_reentrant() - Used for reentrant rtas calls
  * @token:	Token for desired reentrant RTAS call

@@ -13,7 +13,6 @@
 #include <asm/mmu.h>
 #include <asm/rtas.h>
 #include <asm/topology.h>
-#include "../../kernel/cacheinfo.h"
 
 static struct device suspend_dev;
 static DECLARE_COMPLETION(suspend_work);

@@ -63,9 +62,7 @@ static void pseries_suspend_enable_irqs(void)
 	 * Update configuration which can be modified based on device tree
 	 * changes during resume.
 	 */
-	cacheinfo_cpu_offline(smp_processor_id());
 	post_mobility_fixup();
-	cacheinfo_cpu_online(smp_processor_id());
 }
 
 /**

@@ -15,9 +15,6 @@
 #include <asm/topology.h>
 
 static struct device suspend_dev;
-static DECLARE_COMPLETION(suspend_work);
-static struct rtas_suspend_me_data suspend_data;
-static atomic_t suspending;
 
 /**
  * pseries_suspend_begin - First phase of hibernation

@@ -61,23 +58,6 @@ static int pseries_suspend_enter(suspend_state_t state)
 	return rtas_ibm_suspend_me(NULL);
 }
 
-/**
- * pseries_prepare_late - Prepare to suspend all other CPUs
- *
- * Return value:
- * 	0 on success / other on failure
- **/
-static int pseries_prepare_late(void)
-{
-	atomic_set(&suspending, 1);
-	atomic_set(&suspend_data.working, 0);
-	atomic_set(&suspend_data.done, 0);
-	atomic_set(&suspend_data.error, 0);
-	suspend_data.complete = &suspend_work;
-	reinit_completion(&suspend_work);
-	return 0;
-}
-
 /**
  * store_hibernate - Initiate partition hibernation
  * @dev:		subsys root device