1 files changed, 427 insertions, 132 deletions

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2911abe550f..199975613fe 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -13,52 +13,91 @@
 
 #include <linux/types.h>
 #include <linux/of.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/kobject.h>
+#include <linux/delay.h>
+#include <linux/memblock.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
+#include <asm/mce.h>
 
 #include "powernv.h"
 
+/* /sys/firmware/opal */
+struct kobject *opal_kobj;
+
 struct opal {
 	u64 base;
 	u64 entry;
+	u64 size;
 } opal;
 
-static struct device_node *opal_node;
+struct mcheck_recoverable_range {
+	u64 start_addr;
+	u64 end_addr;
+	u64 recover_addr;
+};
+
+static struct mcheck_recoverable_range *mc_recoverable_range;
+static int mc_recoverable_range_len;
+
+struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
+static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
 static DEFINE_SPINLOCK(opal_notifier_lock);
 static uint64_t last_notified_mask = 0x0ul;
 static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
 
+static void opal_reinit_cores(void)
+{
+	/* Do the actual re-init, This will clobber all FPRs, VRs, etc...
+	 *
+	 * It will preserve non volatile GPRs and HSPRG0/1. It will
+	 * also restore HIDs and other SPRs to their original value
+	 * but it might clobber a bunch.
+	 */
+#ifdef __BIG_ENDIAN__
+	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE);
+#else
+	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE);
+#endif
+}
+
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
 {
-	const void *basep, *entryp;
-	unsigned long basesz, entrysz;
+	const void *basep, *entryp, *sizep;
+	int basesz, entrysz, runtimesz;
 
 	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
 		return 0;
 
 	basep  = of_get_flat_dt_prop(node, "opal-base-address", &basesz);
 	entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz);
+	sizep = of_get_flat_dt_prop(node, "opal-runtime-size", &runtimesz);
 
-	if (!basep || !entryp)
+	if (!basep || !entryp || !sizep)
 		return 1;
 
 	opal.base = of_read_number(basep, basesz/4);
 	opal.entry = of_read_number(entryp, entrysz/4);
+	opal.size = of_read_number(sizep, runtimesz/4);
 
-	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%ld)\n",
+	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%d)\n",
 		 opal.base, basep, basesz);
-	pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
+	pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%d)\n",
 		 opal.entry, entryp, entrysz);
+	pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n",
+		 opal.size, sizep, runtimesz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
@@ -72,28 +111,92 @@ int __init early_init_dt_scan_opal(unsigned long node,
 		printk("OPAL V1 detected !\n");
 	}
 
+	/* Reinit all cores with the right endian */
+	opal_reinit_cores();
+
+	/* Restore some bits */
+	if (cur_cpu_spec->cpu_restore)
+		cur_cpu_spec->cpu_restore();
+
+	return 1;
+}
+
+int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
+				   const char *uname, int depth, void *data)
+{
+	int i, psize, size;
+	const __be32 *prop;
+
+	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "mcheck-recoverable-ranges", &psize);
+
+	if (!prop)
+		return 1;
+
+	pr_debug("Found machine check recoverable ranges.\n");
+
+	/*
+	 * Calculate number of available entries.
+	 *
+	 * Each recoverable address range entry is (start address, len,
+	 * recovery address), 2 cells each for start and recovery address,
+	 * 1 cell for len, totalling 5 cells per entry.
+	 */
+	mc_recoverable_range_len = psize / (sizeof(*prop) * 5);
+
+	/* Sanity check */
+	if (!mc_recoverable_range_len)
+		return 1;
+
+	/* Size required to hold all the entries. */
+	size = mc_recoverable_range_len *
+			sizeof(struct mcheck_recoverable_range);
+
+	/*
+	 * Allocate a buffer to hold the MC recoverable ranges. We would be
+	 * accessing them in real mode, hence it needs to be within
+	 * RMO region.
+	 */
+	mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64),
+							ppc64_rma_size));
+	memset(mc_recoverable_range, 0, size);
+
+	for (i = 0; i < mc_recoverable_range_len; i++) {
+		mc_recoverable_range[i].start_addr =
+					of_read_number(prop + (i * 5) + 0, 2);
+		mc_recoverable_range[i].end_addr =
+					mc_recoverable_range[i].start_addr +
+					of_read_number(prop + (i * 5) + 2, 1);
+		mc_recoverable_range[i].recover_addr =
+					of_read_number(prop + (i * 5) + 3, 2);
+
+		pr_debug("Machine check recoverable range: %llx..%llx: %llx\n",
+				mc_recoverable_range[i].start_addr,
+				mc_recoverable_range[i].end_addr,
+				mc_recoverable_range[i].recover_addr);
+	}
 	return 1;
 }
 
 static int __init opal_register_exception_handlers(void)
 {
+#ifdef __BIG_ENDIAN__
 	u64 glue;
 
 	if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
 		return -ENODEV;
 
-	/* Hookup some exception handlers. We use the fwnmi area at 0x7000
-	 * to provide the glue space to OPAL
+	/* Hookup some exception handlers except machine check. We use the
+	 * fwnmi area at 0x7000 to provide the glue space to OPAL
 	 */
 	glue = 0x7000;
-	opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
-					__pa(opal_mc_secondary_handler[0]),
-					glue);
-	glue += 128;
 	opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
 					0, glue);
 	glue += 128;
 	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+#endif
 
 	return 0;
 }
@@ -111,6 +214,20 @@ int opal_notifier_register(struct notifier_block *nb)
 	atomic_notifier_chain_register(&opal_notifier_head, nb);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_notifier_register);
+
+int opal_notifier_unregister(struct notifier_block *nb)
+{
+	if (!nb) {
+		pr_warning("%s: Invalid argument (%p)\n",
+			   __func__, nb);
+		return -EINVAL;
+	}
+
+	atomic_notifier_chain_unregister(&opal_notifier_head, nb);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(opal_notifier_unregister);
 
 static void opal_do_notifier(uint64_t events)
 {
@@ -147,14 +264,14 @@ void opal_notifier_update_evt(uint64_t evt_mask,
 void opal_notifier_enable(void)
 {
 	int64_t rc;
-	uint64_t evt = 0;
+	__be64 evt = 0;
 
 	atomic_set(&opal_notifier_hold, 0);
 
 	/* Process pending events */
 	rc = opal_poll_events(&evt);
 	if (rc == OPAL_SUCCESS && evt)
-		opal_do_notifier(evt);
+		opal_do_notifier(be64_to_cpu(evt));
 }
 
 void opal_notifier_disable(void)
@@ -162,29 +279,121 @@ void opal_notifier_disable(void)
 	atomic_set(&opal_notifier_hold, 1);
 }
 
+/*
+ * Opal message notifier based on message type. Allow subscribers to get
+ * notified for specific messgae type.
+ */
+int opal_message_notifier_register(enum OpalMessageType msg_type,
+					struct notifier_block *nb)
+{
+	if (!nb) {
+		pr_warning("%s: Invalid argument (%p)\n",
+			   __func__, nb);
+		return -EINVAL;
+	}
+	if (msg_type > OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Invalid message type argument (%d)\n",
+			   __func__, msg_type);
+		return -EINVAL;
+	}
+	return atomic_notifier_chain_register(
+				&opal_msg_notifier_head[msg_type], nb);
+}
+
+static void opal_message_do_notify(uint32_t msg_type, void *msg)
+{
+	/* notify subscribers */
+	atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type],
+					msg_type, msg);
+}
+
+static void opal_handle_message(void)
+{
+	s64 ret;
+	/*
+	 * TODO: pre-allocate a message buffer depending on opal-msg-size
+	 * value in /proc/device-tree.
+	 */
+	static struct opal_msg msg;
+	u32 type;
+
+	ret = opal_get_msg(__pa(&msg), sizeof(msg));
+	/* No opal message pending. */
+	if (ret == OPAL_RESOURCE)
+		return;
+
+	/* check for errors. */
+	if (ret) {
+		pr_warning("%s: Failed to retrive opal message, err=%lld\n",
+				__func__, ret);
+		return;
+	}
+
+	type = be32_to_cpu(msg.msg_type);
+
+	/* Sanity check */
+	if (type > OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Unknown message type: %u\n", __func__, type);
+		return;
+	}
+	opal_message_do_notify(type, (void *)&msg);
+}
+
+static int opal_message_notify(struct notifier_block *nb,
+			  unsigned long events, void *change)
+{
+	if (events & OPAL_EVENT_MSG_PENDING)
+		opal_handle_message();
+	return 0;
+}
+
+static struct notifier_block opal_message_nb = {
+	.notifier_call	= opal_message_notify,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int __init opal_message_init(void)
+{
+	int ret, i;
+
+	for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
+		ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
+
+	ret = opal_notifier_register(&opal_message_nb);
+	if (ret) {
+		pr_err("%s: Can't register OPAL event notifier (%d)\n",
+		       __func__, ret);
+		return ret;
+	}
+	return 0;
+}
+early_initcall(opal_message_init);
+
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
-	s64 len, rc;
-	u64 evt;
+	s64 rc;
+	__be64 evt, len;
 
 	if (!opal.entry)
 		return -ENODEV;
 	opal_poll_events(&evt);
-	if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
+	if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0)
 		return 0;
-	len = count;
+	len = cpu_to_be64(count);
 	rc = opal_console_read(vtermno, &len, buf);
 	if (rc == OPAL_SUCCESS)
-		return len;
+		return be64_to_cpu(len);
 	return 0;
 }
 
 int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 {
 	int written = 0;
+	__be64 olen;
 	s64 len, rc;
 	unsigned long flags;
-	u64 evt;
+	__be64 evt;
 
 	if (!opal.entry)
 		return -ENODEV;
@@ -199,13 +408,14 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	 */
 	spin_lock_irqsave(&opal_write_lock, flags);
 	if (firmware_has_feature(FW_FEATURE_OPALv2)) {
-		rc = opal_console_write_buffer_space(vtermno, &len);
+		rc = opal_console_write_buffer_space(vtermno, &olen);
+		len = be64_to_cpu(olen);
 		if (rc || len < total_len) {
 			spin_unlock_irqrestore(&opal_write_lock, flags);
 			/* Closed -> drop characters */
 			if (rc)
 				return total_len;
-			opal_poll_events(&evt);
+			opal_poll_events(NULL);
 			return -EAGAIN;
 		}
 	}
@@ -216,8 +426,9 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	rc = OPAL_BUSY;
 	while(total_len > 0 && (rc == OPAL_BUSY ||
 				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
-		len = total_len;
-		rc = opal_console_write(vtermno, &len, data);
+		olen = cpu_to_be64(total_len);
+		rc = opal_console_write(vtermno, &olen, data);
+		len = be64_to_cpu(olen);
 
 		/* Closed or other error drop */
 		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
@@ -237,142 +448,129 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 		 */
 		do
 			opal_poll_events(&evt);
-		while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT));
+		while(rc == OPAL_SUCCESS &&
+			(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT));
 	}
 	spin_unlock_irqrestore(&opal_write_lock, flags);
 	return written;
 }
 
+static int opal_recover_mce(struct pt_regs *regs,
+					struct machine_check_event *evt)
+{
+	int recovered = 0;
+	uint64_t ea = get_mce_fault_addr(evt);
+
+	if (!(regs->msr & MSR_RI)) {
+		/* If MSR_RI isn't set, we cannot recover */
+		recovered = 0;
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
+		/* Platform corrected itself */
+		recovered = 1;
+	} else if (ea && !is_kernel_addr(ea)) {
+		/*
+		 * Faulting address is not in kernel text. We should be fine.
+		 * We need to find which process uses this address.
+		 * For now, kill the task if we have received exception when
+		 * in userspace.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 */
+		if (user_mode(regs) && !is_global_init(current)) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else
+			recovered = 0;
+	} else if (user_mode(regs) && !is_global_init(current) &&
+		evt->severity == MCE_SEV_ERROR_SYNC) {
+		/*
+		 * If we have received a synchronous error when in userspace
+		 * kill the task.
+		 */
+		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+		recovered = 1;
+	}
+	return recovered;
+}
+
 int opal_machine_check(struct pt_regs *regs)
 {
-	struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
-	struct opal_machine_check_event evt;
-	const char *level, *sevstr, *subtype;
-	static const char *opal_mc_ue_types[] = {
-		"Indeterminate",
-		"Instruction fetch",
-		"Page table walk ifetch",
-		"Load/Store",
-		"Page table walk Load/Store",
-	};
-	static const char *opal_mc_slb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_erat_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_tlb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-
-	/* Copy the event structure and release the original */
-	evt = *opal_evt;
-	opal_evt->in_use = 0;
+	struct machine_check_event evt;
+
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return 0;
 
 	/* Print things out */
-	if (evt.version != OpalMCE_V1) {
+	if (evt.version != MCE_V1) {
 		pr_err("Machine Check Exception, Unknown event version %d !\n",
 		       evt.version);
 		return 0;
 	}
-	switch(evt.severity) {
-	case OpalMCE_SEV_NO_ERROR:
-		level = KERN_INFO;
-		sevstr = "Harmless";
-		break;
-	case OpalMCE_SEV_WARNING:
-		level = KERN_WARNING;
-		sevstr = "";
-		break;
-	case OpalMCE_SEV_ERROR_SYNC:
-		level = KERN_ERR;
-		sevstr = "Severe";
-		break;
-	case OpalMCE_SEV_FATAL:
-	default:
-		level = KERN_ERR;
-		sevstr = "Fatal";
-		break;
-	}
+	machine_check_print_event_info(&evt);
 
-	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
-	       evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
-	       "Recovered" : "[Not recovered");
-	printk("%s  Initiator: %s\n", level,
-	       evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
-	switch(evt.error_type) {
-	case OpalMCE_ERROR_TYPE_UE:
-		subtype = evt.u.ue_error.ue_error_type <
-			ARRAY_SIZE(opal_mc_ue_types) ?
-			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
-			: "Unknown";
-		printk("%s  Error type: UE [%s]\n", level, subtype);
-		if (evt.u.ue_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.ue_error.effective_address);
-		if (evt.u.ue_error.physical_address_provided)
-			printk("%s      Physial address: %016llx\n",
-			       level, evt.u.ue_error.physical_address);
-		break;
-	case OpalMCE_ERROR_TYPE_SLB:
-		subtype = evt.u.slb_error.slb_error_type <
-			ARRAY_SIZE(opal_mc_slb_types) ?
-			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
-			: "Unknown";
-		printk("%s  Error type: SLB [%s]\n", level, subtype);
-		if (evt.u.slb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.slb_error.effective_address);
-		break;
-	case OpalMCE_ERROR_TYPE_ERAT:
-		subtype = evt.u.erat_error.erat_error_type <
-			ARRAY_SIZE(opal_mc_erat_types) ?
-			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
-			: "Unknown";
-		printk("%s  Error type: ERAT [%s]\n", level, subtype);
-		if (evt.u.erat_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.erat_error.effective_address);
-		break;
-	case OpalMCE_ERROR_TYPE_TLB:
-		subtype = evt.u.tlb_error.tlb_error_type <
-			ARRAY_SIZE(opal_mc_tlb_types) ?
-			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
-			: "Unknown";
-		printk("%s  Error type: TLB [%s]\n", level, subtype);
-		if (evt.u.tlb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.tlb_error.effective_address);
-		break;
-	default:
-	case OpalMCE_ERROR_TYPE_UNKNOWN:
-		printk("%s  Error type: Unknown\n", level);
-		break;
-	}
-	return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+	if (opal_recover_mce(regs, &evt))
+		return 1;
+	return 0;
+}
+
+static uint64_t find_recovery_address(uint64_t nip)
+{
+	int i;
+
+	for (i = 0; i < mc_recoverable_range_len; i++)
+		if ((nip >= mc_recoverable_range[i].start_addr) &&
+		    (nip < mc_recoverable_range[i].end_addr))
+		    return mc_recoverable_range[i].recover_addr;
+	return 0;
+}
+
+bool opal_mce_check_early_recovery(struct pt_regs *regs)
+{
+	uint64_t recover_addr = 0;
+
+	if (!opal.base || !opal.size)
+		goto out;
+
+	if ((regs->nip >= opal.base) &&
+			(regs->nip <= (opal.base + opal.size)))
+		recover_addr = find_recovery_address(regs->nip);
+
+	/*
+	 * Setup regs->nip to rfi into fixup address.
+	 */
+	if (recover_addr)
+		regs->nip = recover_addr;
+
+out:
+	return !!recover_addr;
 }
 
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
-	uint64_t events;
+	__be64 events;
 
 	opal_handle_interrupt(virq_to_hw(irq), &events);
 
-	opal_do_notifier(events);
+	opal_do_notifier(be64_to_cpu(events));
 
 	return IRQ_HANDLED;
 }
 
+static int opal_sysfs_init(void)
+{
+	opal_kobj = kobject_create_and_add("opal", firmware_kobj);
+	if (!opal_kobj) {
+		pr_warn("kobject_create_and_add opal failed\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
-	const u32 *irqs;
+	const __be32 *irqs;
 	int rc, i, irqlen;
 
 	opal_node = of_find_node_by_path("/ibm,opal");
@@ -414,6 +612,22 @@ static int __init opal_init(void)
 				   " (0x%x)\n", rc, irq, hwirq);
 		opal_irqs[i] = irq;
 	}
+
+	/* Create "opal" kobject under /sys/firmware */
+	rc = opal_sysfs_init();
+	if (rc == 0) {
+		/* Setup error log interface */
+		rc = opal_elog_init();
+		/* Setup code update interface */
+		opal_flash_init();
+		/* Setup platform dump extract interface */
+		opal_platform_dump_init();
+		/* Setup system parameters interface */
+		opal_sys_param_init();
+		/* Setup message log interface. */
+		opal_msglog_init();
+	}
+
 	return 0;
 }
 subsys_initcall(opal_init);
@@ -421,10 +635,91 @@ subsys_initcall(opal_init);
 void opal_shutdown(void)
 {
 	unsigned int i;
+	long rc = OPAL_BUSY;
 
+	/* First free interrupts, which will also mask them */
 	for (i = 0; i < opal_irq_count; i++) {
 		if (opal_irqs[i])
 			free_irq(opal_irqs[i], NULL);
 		opal_irqs[i] = 0;
 	}
+
+	/*
+	 * Then sync with OPAL which ensure anything that can
+	 * potentially write to our memory has completed such
+	 * as an ongoing dump retrieval
+	 */
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_sync_host_reboot();
+		if (rc == OPAL_BUSY)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+}
+
+/* Export this so that test modules can use it */
+EXPORT_SYMBOL_GPL(opal_invalid_call);
+
+/* Convert a region of vmalloc memory to an opal sg list */
+struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
+					     unsigned long vmalloc_size)
+{
+	struct opal_sg_list *sg, *first = NULL;
+	unsigned long i = 0;
+
+	sg = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!sg)
+		goto nomem;
+
+	first = sg;
+
+	while (vmalloc_size > 0) {
+		uint64_t data = vmalloc_to_pfn(vmalloc_addr) << PAGE_SHIFT;
+		uint64_t length = min(vmalloc_size, PAGE_SIZE);
+
+		sg->entry[i].data = cpu_to_be64(data);
+		sg->entry[i].length = cpu_to_be64(length);
+		i++;
+
+		if (i >= SG_ENTRIES_PER_NODE) {
+			struct opal_sg_list *next;
+
+			next = kzalloc(PAGE_SIZE, GFP_KERNEL);
+			if (!next)
+				goto nomem;
+
+			sg->length = cpu_to_be64(
+					i * sizeof(struct opal_sg_entry) + 16);
+			i = 0;
+			sg->next = cpu_to_be64(__pa(next));
+			sg = next;
+		}
+
+		vmalloc_addr += length;
+		vmalloc_size -= length;
+	}
+
+	sg->length = cpu_to_be64(i * sizeof(struct opal_sg_entry) + 16);
+
+	return first;
+
+nomem:
+	pr_err("%s : Failed to allocate memory\n", __func__);
+	opal_free_sg_list(first);
+	return NULL;
+}
+
+void opal_free_sg_list(struct opal_sg_list *sg)
+{
+	while (sg) {
+		uint64_t next = be64_to_cpu(sg->next);
+
+		kfree(sg);
+
+		if (next)
+			sg = __va(next);
+		else
+			sg = NULL;
+	}
 }