10 files changed, 178 insertions, 215 deletions

diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index b9827b0d87e4..788a1977b9a5 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -209,89 +209,20 @@ static struct kobj_type dump_ktype = {
         .default_attrs = dump_default_attrs,
 };
 
-static void free_dump_sg_list(struct opal_sg_list *list)
-{
-        struct opal_sg_list *sg1;
-        while (list) {
-                sg1 = list->next;
-                kfree(list);
-                list = sg1;
-        }
-        list = NULL;
-}
-
-static struct opal_sg_list *dump_data_to_sglist(struct dump_obj *dump)
-{
-        struct opal_sg_list *sg1, *list = NULL;
-        void *addr;
-        int64_t size;
-
-        addr = dump->buffer;
-        size = dump->size;
-
-        sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
-        if (!sg1)
-                goto nomem;
-
-        list = sg1;
-        sg1->num_entries = 0;
-        while (size > 0) {
-                /* Translate virtual address to physical address */
-                sg1->entry[sg1->num_entries].data =
-                        (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT);
-
-                if (size > PAGE_SIZE)
-                        sg1->entry[sg1->num_entries].length = PAGE_SIZE;
-                else
-                        sg1->entry[sg1->num_entries].length = size;
-
-                sg1->num_entries++;
-                if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-                        sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
-                        if (!sg1->next)
-                                goto nomem;
-
-                        sg1 = sg1->next;
-                        sg1->num_entries = 0;
-                }
-                addr += PAGE_SIZE;
-                size -= PAGE_SIZE;
-        }
-        return list;
-
-nomem:
-        pr_err("%s : Failed to allocate memory\n", __func__);
-        free_dump_sg_list(list);
-        return NULL;
-}
-
-static void sglist_to_phy_addr(struct opal_sg_list *list)
-{
-        struct opal_sg_list *sg, *next;
-
-        for (sg = list; sg; sg = next) {
-                next = sg->next;
-                /* Don't translate NULL pointer for last entry */
-                if (sg->next)
-                        sg->next = (struct opal_sg_list *)__pa(sg->next);
-                else
-                        sg->next = NULL;
-
-                /* Convert num_entries to length */
-                sg->num_entries =
-                        sg->num_entries * sizeof(struct opal_sg_entry) + 16;
-        }
-}
-
-static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type)
+static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type)
 {
+        __be32 id, size, type;
         int rc;
-        *type = 0xffffffff;
 
-        rc = opal_dump_info2(id, size, type);
+        type = cpu_to_be32(0xffffffff);
 
+        rc = opal_dump_info2(&id, &size, &type);
         if (rc == OPAL_PARAMETER)
-                rc = opal_dump_info(id, size);
+                rc = opal_dump_info(&id, &size);
+
+        *dump_id = be32_to_cpu(id);
+        *dump_size = be32_to_cpu(size);
+        *dump_type = be32_to_cpu(type);
 
         if (rc)
                 pr_warn("%s: Failed to get dump info (%d)\n",
@@ -314,15 +245,12 @@ static int64_t dump_read_data(struct dump_obj *dump)
         }
 
         /* Generate SG list */
-        list = dump_data_to_sglist(dump);
+        list = opal_vmalloc_to_sg_list(dump->buffer, dump->size);
         if (!list) {
                 rc = -ENOMEM;
                 goto out;
         }
 
-        /* Translate sg list addr to real address */
-        sglist_to_phy_addr(list);
-
         /* First entry address */
         addr = __pa(list);
 
@@ -341,7 +269,7 @@ static int64_t dump_read_data(struct dump_obj *dump)
                         __func__, dump->id);
 
         /* Free SG list */
-        free_dump_sg_list(list);
+        opal_free_sg_list(list);
 
 out:
         return rc;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index ef7bc2a97862..10268c41d830 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -238,18 +238,25 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type)
 
 static void elog_work_fn(struct work_struct *work)
 {
-        size_t elog_size;
+        __be64 size;
+        __be64 id;
+        __be64 type;
+        uint64_t elog_size;
         uint64_t log_id;
         uint64_t elog_type;
         int rc;
         char name[2+16+1];
 
-        rc = opal_get_elog_size(&log_id, &elog_size, &elog_type);
+        rc = opal_get_elog_size(&id, &size, &type);
         if (rc != OPAL_SUCCESS) {
                 pr_err("ELOG: Opal log read failed\n");
                 return;
         }
 
+        elog_size = be64_to_cpu(size);
+        log_id = be64_to_cpu(id);
+        elog_type = be64_to_cpu(type);
+
         BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
 
         if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 714ef972406b..dc487ff04704 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -79,9 +79,6 @@
 /* XXX: Assume candidate image size is <= 1GB */
 #define MAX_IMAGE_SIZE  0x40000000
 
-/* Flash sg list version */
-#define SG_LIST_VERSION (1UL)
-
 /* Image status */
 enum {
         IMAGE_INVALID,
@@ -131,11 +128,15 @@ static DEFINE_MUTEX(image_data_mutex);
  */
 static inline void opal_flash_validate(void)
 {
-        struct validate_flash_t *args_buf = &validate_flash_data;
+        long ret;
+        void *buf = validate_flash_data.buf;
+        __be32 size, result;
 
-        args_buf->status = opal_validate_flash(__pa(args_buf->buf),
-                                               &(args_buf->buf_size),
-                                               &(args_buf->result));
+        ret = opal_validate_flash(__pa(buf), &size, &result);
+
+        validate_flash_data.status = ret;
+        validate_flash_data.buf_size = be32_to_cpu(size);
+        validate_flash_data.result = be32_to_cpu(result);
 }
 
 /*
@@ -268,93 +269,11 @@ static ssize_t manage_store(struct kobject *kobj,
 }
 
 /*
- * Free sg list
- */
-static void free_sg_list(struct opal_sg_list *list)
-{
-        struct opal_sg_list *sg1;
-        while (list) {
-                sg1 = list->next;
-                kfree(list);
-                list = sg1;
-        }
-        list = NULL;
-}
-
-/*
- * Build candidate image scatter gather list
- *
- * list format:
- *   -----------------------------------
- *  |  VER (8) | Entry length in bytes  |
- *   -----------------------------------
- *  |  Pointer to next entry            |
- *   -----------------------------------
- *  |  Address of memory area 1         |
- *   -----------------------------------
- *  |  Length of memory area 1          |
- *   -----------------------------------
- *  |   .........                       |
- *   -----------------------------------
- *  |   .........                       |
- *   -----------------------------------
- *  |  Address of memory area N         |
- *   -----------------------------------
- *  |  Length of memory area N          |
- *   -----------------------------------
- */
-static struct opal_sg_list *image_data_to_sglist(void)
-{
-        struct opal_sg_list *sg1, *list = NULL;
-        void *addr;
-        int size;
-
-        addr = image_data.data;
-        size = image_data.size;
-
-        sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
-        if (!sg1)
-                return NULL;
-
-        list = sg1;
-        sg1->num_entries = 0;
-        while (size > 0) {
-                /* Translate virtual address to physical address */
-                sg1->entry[sg1->num_entries].data =
-                        (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT);
-
-                if (size > PAGE_SIZE)
-                        sg1->entry[sg1->num_entries].length = PAGE_SIZE;
-                else
-                        sg1->entry[sg1->num_entries].length = size;
-
-                sg1->num_entries++;
-                if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-                        sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
-                        if (!sg1->next) {
-                                pr_err("%s : Failed to allocate memory\n",
-                                       __func__);
-                                goto nomem;
-                        }
-
-                        sg1 = sg1->next;
-                        sg1->num_entries = 0;
-                }
-                addr += PAGE_SIZE;
-                size -= PAGE_SIZE;
-        }
-        return list;
-nomem:
-        free_sg_list(list);
-        return NULL;
-}
-
-/*
  * OPAL update flash
  */
 static int opal_flash_update(int op)
 {
-        struct opal_sg_list *sg, *list, *next;
+        struct opal_sg_list *list;
         unsigned long addr;
         int64_t rc = OPAL_PARAMETER;
 
@@ -364,30 +283,13 @@ static int opal_flash_update(int op)
                 goto flash;
         }
 
-        list = image_data_to_sglist();
+        list = opal_vmalloc_to_sg_list(image_data.data, image_data.size);
         if (!list)
                 goto invalid_img;
 
         /* First entry address */
         addr = __pa(list);
 
-        /* Translate sg list address to absolute */
-        for (sg = list; sg; sg = next) {
-                next = sg->next;
-                /* Don't translate NULL pointer for last entry */
-                if (sg->next)
-                        sg->next = (struct opal_sg_list *)__pa(sg->next);
-                else
-                        sg->next = NULL;
-
-                /*
-                 * Convert num_entries to version/length format
-                 * to satisfy OPAL.
-                 */
-                sg->num_entries = (SG_LIST_VERSION << 56) |
-                        (sg->num_entries * sizeof(struct opal_sg_entry) + 16);
-        }
-
         pr_alert("FLASH: Image is %u bytes\n", image_data.size);
         pr_alert("FLASH: Image update requested\n");
         pr_alert("FLASH: Image will be updated during system reboot\n");
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 6b614726baf2..d202f9bc3683 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -39,10 +39,11 @@ struct param_attr {
         struct kobj_attribute kobj_attr;
 };
 
-static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
+static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 {
         struct opal_msg msg;
-        int ret, token;
+        ssize_t ret;
+        int token;
 
         token = opal_async_get_token_interruptible();
         if (token < 0) {
@@ -59,7 +60,7 @@ static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 
         ret = opal_async_wait_response(token, &msg);
         if (ret) {
-                pr_err("%s: Failed to wait for the async response, %d\n",
+                pr_err("%s: Failed to wait for the async response, %zd\n",
                                 __func__, ret);
                 goto out_token;
         }
@@ -111,7 +112,7 @@ static ssize_t sys_param_show(struct kobject *kobj,
 {
         struct param_attr *attr = container_of(kobj_attr, struct param_attr,
                         kobj_attr);
-        int ret;
+        ssize_t ret;
 
         mutex_lock(&opal_sysparam_mutex);
         ret = opal_get_sys_param(attr->param_id, attr->param_size,
@@ -121,9 +122,10 @@ static ssize_t sys_param_show(struct kobject *kobj,
 
         memcpy(buf, param_data_buf, attr->param_size);
 
+        ret = attr->param_size;
 out:
         mutex_unlock(&opal_sysparam_mutex);
-        return ret ? ret : attr->param_size;
+        return ret;
 }
 
 static ssize_t sys_param_store(struct kobject *kobj,
@@ -131,14 +133,20 @@ static ssize_t sys_param_store(struct kobject *kobj,
 {
         struct param_attr *attr = container_of(kobj_attr, struct param_attr,
                         kobj_attr);
-        int ret;
+        ssize_t ret;
+
+        /* MAX_PARAM_DATA_LEN is sizeof(param_data_buf) */
+        if (count > MAX_PARAM_DATA_LEN)
+                count = MAX_PARAM_DATA_LEN;
 
         mutex_lock(&opal_sysparam_mutex);
         memcpy(param_data_buf, buf, count);
         ret = opal_set_sys_param(attr->param_id, attr->param_size,
                         param_data_buf);
         mutex_unlock(&opal_sysparam_mutex);
-        return ret ? ret : count;
+        if (!ret)
+                ret = count;
+        return ret;
 }
 
 void __init opal_sys_param_init(void)
@@ -214,13 +222,13 @@ void __init opal_sys_param_init(void)
         }
 
         if (of_property_read_u32_array(sysparam, "param-len", size, count)) {
-                pr_err("SYSPARAM: Missing propery param-len in the DT\n");
+                pr_err("SYSPARAM: Missing property param-len in the DT\n");
                 goto out_free_perm;
         }
 
 
         if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) {
-                pr_err("SYSPARAM: Missing propery param-perm in the DT\n");
+                pr_err("SYSPARAM: Missing property param-perm in the DT\n");
                 goto out_free_perm;
         }
 
@@ -233,6 +241,12 @@ void __init opal_sys_param_init(void)
 
         /* For each of the parameters, populate the parameter attributes */
         for (i = 0; i < count; i++) {
+                if (size[i] > MAX_PARAM_DATA_LEN) {
+                        pr_warn("SYSPARAM: Not creating parameter %d as size "
+                                "exceeds buffer length\n", i);
+                        continue;
+                }
+
                 sysfs_attr_init(&attr[i].kobj_attr.attr);
                 attr[i].param_id = id[i];
                 attr[i].param_size = size[i];
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 49d2f00019e5..360ad80c754c 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -242,14 +242,14 @@ 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)
@@ -529,7 +529,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 
         opal_handle_interrupt(virq_to_hw(irq), &events);
 
-        opal_do_notifier(events);
+        opal_do_notifier(be64_to_cpu(events));
 
         return IRQ_HANDLED;
 }
@@ -638,3 +638,66 @@ void opal_shutdown(void)
 
 /* 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;
+        }
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3b2b4fb3585b..98824aa99173 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -343,7 +343,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
                                 pci_name(dev));
                         continue;
                 }
-                pci_dev_get(dev);
                 pdn->pcidev = dev;
                 pdn->pe_number = pe->pe_number;
                 pe->dma_weight += pnv_ioda_dma_weight(dev);
@@ -462,7 +461,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
         pe = &phb->ioda.pe_array[pdn->pe_number];
         WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-        set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
+        set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 61cf8fa9c61b..8723d32632f5 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -162,18 +162,62 @@ static void pnv_shutdown(void)
 }
 
 #ifdef CONFIG_KEXEC
+static void pnv_kexec_wait_secondaries_down(void)
+{
+        int my_cpu, i, notified = -1;
+
+        my_cpu = get_cpu();
+
+        for_each_online_cpu(i) {
+                uint8_t status;
+                int64_t rc;
+
+                if (i == my_cpu)
+                        continue;
+
+                for (;;) {
+                        rc = opal_query_cpu_status(get_hard_smp_processor_id(i),
+                                                   &status);
+                        if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED)
+                                break;
+                        barrier();
+                        if (i != notified) {
+                                printk(KERN_INFO "kexec: waiting for cpu %d "
+                                       "(physical %d) to enter OPAL\n",
+                                       i, paca[i].hw_cpu_id);
+                                notified = i;
+                        }
+                }
+        }
+}
+
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
         xics_kexec_teardown_cpu(secondary);
 
-        /* Return secondary CPUs to firmware on OPAL v3 */
-        if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) {
+        /* On OPAL v3, we return all CPUs to firmware */
+
+        if (!firmware_has_feature(FW_FEATURE_OPALv3))
+                return;
+
+        if (secondary) {
+                /* Return secondary CPUs to firmware on OPAL v3 */
                 mb();
                 get_paca()->kexec_state = KEXEC_STATE_REAL_MODE;
                 mb();
 
                 /* Return the CPU to OPAL */
                 opal_return_cpu();
+        } else if (crash_shutdown) {
+                /*
+                 * On crash, we don't wait for secondaries to go
+                 * down as they might be unreachable or hung, so
+                 * instead we just wait a bit and move on.
+                 */
+                mdelay(1);
+        } else {
+                /* Primary waits for the secondaries to have reached OPAL */
+                pnv_kexec_wait_secondaries_down();
         }
 }
 #endif /* CONFIG_KEXEC */
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 908672bdcea6..bf5fcd452168 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -30,6 +30,7 @@
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
 #include <asm/opal.h>
+#include <asm/runlatch.h>
 
 #include "powernv.h"
 
@@ -156,7 +157,9 @@ static void pnv_smp_cpu_kill_self(void)
          */
         mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
         while (!generic_check_cpu_restart(cpu)) {
+                ppc64_runlatch_off();
                 power7_nap();
+                ppc64_runlatch_on();
                 if (!generic_check_cpu_restart(cpu)) {
                         DBG("CPU%d Unexpected exit while offline !\n", cpu);
                         /* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 9b8e05078a63..20d62975856f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -88,13 +88,14 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-        struct rtas_args args = {
-                .token = cpu_to_be32(rtas_stop_self_token),
+        static struct rtas_args args = {
                 .nargs = 0,
                 .nret = 1,
                 .rets = &args.args[0],
         };
 
+        args.token = cpu_to_be32(rtas_stop_self_token);
+
         local_irq_disable();
 
         BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 573b488fc48b..7f75c94af822 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -100,10 +100,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 
         start_pfn = base >> PAGE_SHIFT;
 
-        if (!pfn_valid(start_pfn)) {
-                memblock_remove(base, memblock_size);
-                return 0;
-        }
+        lock_device_hotplug();
+
+        if (!pfn_valid(start_pfn))
+                goto out;
 
         block_sz = memory_block_size_bytes();
         sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
@@ -114,8 +114,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
                 base += MIN_MEMORY_BLOCK_SIZE;
         }
 
+out:
         /* Update memory regions for memory remove */
         memblock_remove(base, memblock_size);
+        unlock_device_hotplug();
         return 0;
 }