aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/powernv
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/platforms/powernv')
-rw-r--r--arch/powerpc/platforms/powernv/Makefile4
-rw-r--r--arch/powerpc/platforms/powernv/eeh-ioda.c128
-rw-r--r--arch/powerpc/platforms/powernv/eeh-powernv.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-async.c203
-rw-r--r--arch/powerpc/platforms/powernv/opal-dump.c525
-rw-r--r--arch/powerpc/platforms/powernv/opal-elog.c313
-rw-r--r--arch/powerpc/platforms/powernv/opal-sensor.c64
-rw-r--r--arch/powerpc/platforms/powernv/opal-sysparam.c290
-rw-r--r--arch/powerpc/platforms/powernv/opal-wrappers.S15
-rw-r--r--arch/powerpc/platforms/powernv/opal-xscom.c21
-rw-r--r--arch/powerpc/platforms/powernv/opal.c106
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c84
-rw-r--r--arch/powerpc/platforms/powernv/pci.c230
-rw-r--r--arch/powerpc/platforms/powernv/pci.h6
-rw-r--r--arch/powerpc/platforms/powernv/powernv.h8
-rw-r--r--arch/powerpc/platforms/powernv/setup.c23
16 files changed, 1820 insertions, 202 deletions
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 8d767fde5a6a..f324ea099503 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,6 +1,6 @@
-obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o
+obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o
obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
-obj-y += rng.o
+obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e1e71618b70c..253fefe3d1a0 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb,
/* We simply send special EEH event */
if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
- (events & OPAL_EVENT_PCI_ERROR))
+ (events & OPAL_EVENT_PCI_ERROR) &&
+ eeh_enabled())
eeh_send_failure_event(NULL);
return 0;
@@ -113,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
#endif /* CONFIG_DEBUG_FS */
+
/**
* ioda_eeh_post_init - Chip dependent post initialization
* @hose: PCI controller
@@ -220,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
return ret;
}
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+ struct pnv_phb *phb = hose->private_data;
+ long rc;
+
+ rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+ PNV_PCI_DIAG_BUF_SIZE);
+ if (rc != OPAL_SUCCESS) {
+ pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+ __func__, hose->global_number, rc);
+ return;
+ }
+
+ pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
/**
* ioda_eeh_get_state - Retrieve the state of PE
* @pe: EEH PE
@@ -271,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
result |= EEH_STATE_DMA_ACTIVE;
result |= EEH_STATE_MMIO_ENABLED;
result |= EEH_STATE_DMA_ENABLED;
+ } else if (!(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
}
return result;
@@ -314,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
__func__, fstate, hose->global_number, pe_no);
}
+ /* Dump PHB diag-data for frozen PE */
+ if (result != EEH_STATE_NOT_SUPPORT &&
+ (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+ (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+ !(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
return result;
}
@@ -489,8 +519,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose,
static int ioda_eeh_reset(struct eeh_pe *pe, int option)
{
struct pci_controller *hose = pe->phb;
- struct eeh_dev *edev;
- struct pci_dev *dev;
+ struct pci_bus *bus;
int ret;
/*
@@ -519,73 +548,17 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
if (pe->type & EEH_PE_PHB) {
ret = ioda_eeh_phb_reset(hose, option);
} else {
- if (pe->type & EEH_PE_DEVICE) {
- /*
- * If it's device PE, we didn't refer to the parent
- * PCI bus yet. So we have to figure it out indirectly.
- */
- edev = list_first_entry(&pe->edevs,
- struct eeh_dev, list);
- dev = eeh_dev_to_pci_dev(edev);
- dev = dev->bus->self;
- } else {
- /*
- * If it's bus PE, the parent PCI bus is already there
- * and just pick it up.
- */
- dev = pe->bus->self;
- }
-
- /*
- * Do reset based on the fact that the direct upstream bridge
- * is root bridge (port) or not.
- */
- if (dev->bus->number == 0)
+ bus = eeh_pe_bus_get(pe);
+ if (pci_is_root_bus(bus))
ret = ioda_eeh_root_reset(hose, option);
else
- ret = ioda_eeh_bridge_reset(hose, dev, option);
+ ret = ioda_eeh_bridge_reset(hose, bus->self, option);
}
return ret;
}
/**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
- char *drv_log, unsigned long len)
-{
- s64 ret;
- unsigned long flags;
- struct pci_controller *hose = pe->phb;
- struct pnv_phb *phb = hose->private_data;
-
- spin_lock_irqsave(&phb->lock, flags);
-
- ret = opal_pci_get_phb_diag_data2(phb->opal_id,
- phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
- if (ret) {
- spin_unlock_irqrestore(&phb->lock, flags);
- pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
- __func__, hose->global_number, pe->addr, ret);
- return -EIO;
- }
-
- /* The PHB diag-data is always indicative */
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
- spin_unlock_irqrestore(&phb->lock, flags);
-
- return 0;
-}
-
-/**
* ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
* @pe: EEH PE
*
@@ -666,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
}
}
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
- struct pnv_phb *phb = hose->private_data;
- long rc;
-
- rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
- PNV_PCI_DIAG_BUF_SIZE);
- if (rc != OPAL_SUCCESS) {
- pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
- __func__, hose->global_number, rc);
- return;
- }
-
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
struct eeh_pe **pe)
{
@@ -855,6 +812,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
}
/*
+ * EEH core will try recover from fenced PHB or
+ * frozen PE. In the time for frozen PE, EEH core
+ * enable IO path for that before collecting logs,
+ * but it ruins the site. So we have to dump the
+ * log in advance here.
+ */
+ if ((ret == EEH_NEXT_ERR_FROZEN_PE ||
+ ret == EEH_NEXT_ERR_FENCED_PHB) &&
+ !((*pe)->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
+ /*
* If we have no errors on the specific PHB or only
* informative error there, we continue poking it.
* Otherwise, we need actions to be taken by upper
@@ -872,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
.set_option = ioda_eeh_set_option,
.get_state = ioda_eeh_get_state,
.reset = ioda_eeh_reset,
- .get_log = ioda_eeh_get_log,
.configure_bridge = ioda_eeh_configure_bridge,
.next_error = ioda_eeh_next_error
};
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a79fddc5e74e..a59788e83b8b 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
* Enable EEH explicitly so that we will do EEH check
* while accessing I/O stuff
*/
- eeh_subsystem_enabled = 1;
+ eeh_set_enable(true);
/* Save memory bars */
eeh_save_bars(edev);
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
new file mode 100644
index 000000000000..cd0c1354d404
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -0,0 +1,203 @@
+/*
+ * PowerNV OPAL asynchronous completion interfaces
+ *
+ * Copyright 2013 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/gfp.h>
+#include <linux/of.h>
+#include <asm/opal.h>
+
+#define N_ASYNC_COMPLETIONS 64
+
+static DECLARE_BITMAP(opal_async_complete_map, N_ASYNC_COMPLETIONS) = {~0UL};
+static DECLARE_BITMAP(opal_async_token_map, N_ASYNC_COMPLETIONS);
+static DECLARE_WAIT_QUEUE_HEAD(opal_async_wait);
+static DEFINE_SPINLOCK(opal_async_comp_lock);
+static struct semaphore opal_async_sem;
+static struct opal_msg *opal_async_responses;
+static unsigned int opal_max_async_tokens;
+
+int __opal_async_get_token(void)
+{
+ unsigned long flags;
+ int token;
+
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ token = find_first_bit(opal_async_complete_map, opal_max_async_tokens);
+ if (token >= opal_max_async_tokens) {
+ token = -EBUSY;
+ goto out;
+ }
+
+ if (__test_and_set_bit(token, opal_async_token_map)) {
+ token = -EBUSY;
+ goto out;
+ }
+
+ __clear_bit(token, opal_async_complete_map);
+
+out:
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+ return token;
+}
+
+int opal_async_get_token_interruptible(void)
+{
+ int token;
+
+ /* Wait until a token is available */
+ if (down_interruptible(&opal_async_sem))
+ return -ERESTARTSYS;
+
+ token = __opal_async_get_token();
+ if (token < 0)
+ up(&opal_async_sem);
+
+ return token;
+}
+
+int __opal_async_release_token(int token)
+{
+ unsigned long flags;
+
+ if (token < 0 || token >= opal_max_async_tokens) {
+ pr_err("%s: Passed token is out of range, token %d\n",
+ __func__, token);
+ return -EINVAL;
+ }
+
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ __set_bit(token, opal_async_complete_map);
+ __clear_bit(token, opal_async_token_map);
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+
+ return 0;
+}
+
+int opal_async_release_token(int token)
+{
+ int ret;
+
+ ret = __opal_async_release_token(token);
+ if (ret)
+ return ret;
+
+ up(&opal_async_sem);
+
+ return 0;
+}
+
+int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
+{
+ if (token >= opal_max_async_tokens) {
+ pr_err("%s: Invalid token passed\n", __func__);
+ return -EINVAL;
+ }
+
+ if (!msg) {
+ pr_err("%s: Invalid message pointer passed\n", __func__);
+ return -EINVAL;
+ }
+
+ wait_event(opal_async_wait, test_bit(token, opal_async_complete_map));
+ memcpy(msg, &opal_async_responses[token], sizeof(*msg));
+
+ return 0;
+}
+
+static int opal_async_comp_event(struct notifier_block *nb,
+ unsigned long msg_type, void *msg)
+{
+ struct opal_msg *comp_msg = msg;
+ unsigned long flags;
+
+ if (msg_type != OPAL_MSG_ASYNC_COMP)
+ return 0;
+
+ memcpy(&opal_async_responses[comp_msg->params[0]], comp_msg,
+ sizeof(*comp_msg));
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ __set_bit(comp_msg->params[0], opal_async_complete_map);
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+
+ wake_up(&opal_async_wait);
+
+ return 0;
+}
+
+static struct notifier_block opal_async_comp_nb = {
+ .notifier_call = opal_async_comp_event,
+ .next = NULL,
+ .priority = 0,
+};
+
+static int __init opal_async_comp_init(void)
+{
+ struct device_node *opal_node;
+ const __be32 *async;
+ int err;
+
+ opal_node = of_find_node_by_path("/ibm,opal");
+ if (!opal_node) {
+ pr_err("%s: Opal node not found\n", __func__);
+ err = -ENOENT;
+ goto out;
+ }
+
+ async = of_get_property(opal_node, "opal-msg-async-num", NULL);
+ if (!async) {
+ pr_err("%s: %s has no opal-msg-async-num\n",
+ __func__, opal_node->full_name);
+ err = -ENOENT;
+ goto out_opal_node;
+ }
+
+ opal_max_async_tokens = be32_to_cpup(async);
+ if (opal_max_async_tokens > N_ASYNC_COMPLETIONS)
+ opal_max_async_tokens = N_ASYNC_COMPLETIONS;
+
+ err = opal_message_notifier_register(OPAL_MSG_ASYNC_COMP,
+ &opal_async_comp_nb);
+ if (err) {
+ pr_err("%s: Can't register OPAL event notifier (%d)\n",
+ __func__, err);
+ goto out_opal_node;
+ }
+
+ opal_async_responses = kzalloc(
+ sizeof(*opal_async_responses) * opal_max_async_tokens,
+ GFP_KERNEL);
+ if (!opal_async_responses) {
+ pr_err("%s: Out of memory, failed to do asynchronous "
+ "completion init\n", __func__);
+ err = -ENOMEM;
+ goto out_opal_node;
+ }
+
+ /* Initialize to 1 less than the maximum tokens available, as we may
+ * require to pop one during emergency through synchronous call to
+ * __opal_async_get_token()
+ */
+ sema_init(&opal_async_sem, opal_max_async_tokens - 1);
+
+out_opal_node:
+ of_node_put(opal_node);
+out:
+ return err;
+}
+subsys_initcall(opal_async_comp_init);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
new file mode 100644
index 000000000000..0c767c561dc9
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -0,0 +1,525 @@
+/*
+ * PowerNV OPAL Dump Interface
+ *
+ * Copyright 2013,2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/delay.h>
+
+#include <asm/opal.h>
+
+#define DUMP_TYPE_FSP 0x01
+
+struct dump_obj {
+ struct kobject kobj;
+ struct bin_attribute dump_attr;
+ uint32_t id; /* becomes object name */
+ uint32_t type;
+ uint32_t size;
+ char *buffer;
+};
+#define to_dump_obj(x) container_of(x, struct dump_obj, kobj)
+
+struct dump_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct dump_obj *dump, struct dump_attribute *attr,
+ char *buf);
+ ssize_t (*store)(struct dump_obj *dump, struct dump_attribute *attr,
+ const char *buf, size_t count);
+};
+#define to_dump_attr(x) container_of(x, struct dump_attribute, attr)
+
+static ssize_t dump_id_show(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0x%x\n", dump_obj->id);
+}
+
+static const char* dump_type_to_string(uint32_t type)
+{
+ switch (type) {
+ case 0x01: return "SP Dump";
+ case 0x02: return "System/Platform Dump";
+ case 0x03: return "SMA Dump";
+ default: return "unknown";
+ }
+}
+
+static ssize_t dump_type_show(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ char *buf)
+{
+
+ return sprintf(buf, "0x%x %s\n", dump_obj->type,
+ dump_type_to_string(dump_obj->type));
+}
+
+static ssize_t dump_ack_show(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "ack - acknowledge dump\n");
+}
+
+/*
+ * Send acknowledgement to OPAL
+ */
+static int64_t dump_send_ack(uint32_t dump_id)
+{
+ int rc;
+
+ rc = opal_dump_ack(dump_id);
+ if (rc)
+ pr_warn("%s: Failed to send ack to Dump ID 0x%x (%d)\n",
+ __func__, dump_id, rc);
+ return rc;
+}
+
+static void delay_release_kobj(void *kobj)
+{
+ kobject_put((struct kobject *)kobj);
+}
+
+static ssize_t dump_ack_store(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ dump_send_ack(dump_obj->id);
+ sysfs_schedule_callback(&dump_obj->kobj, delay_release_kobj,
+ &dump_obj->kobj, THIS_MODULE);
+ return count;
+}
+
+/* Attributes of a dump
+ * The binary attribute of the dump itself is dynamic
+ * due to the dynamic size of the dump
+ */
+static struct dump_attribute id_attribute =
+ __ATTR(id, 0666, dump_id_show, NULL);
+static struct dump_attribute type_attribute =
+ __ATTR(type, 0666, dump_type_show, NULL);
+static struct dump_attribute ack_attribute =
+ __ATTR(acknowledge, 0660, dump_ack_show, dump_ack_store);
+
+static ssize_t init_dump_show(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "1 - initiate dump\n");
+}
+
+static int64_t dump_fips_init(uint8_t type)
+{
+ int rc;
+
+ rc = opal_dump_init(type);
+ if (rc)
+ pr_warn("%s: Failed to initiate FipS dump (%d)\n",
+ __func__, rc);
+ return rc;
+}
+
+static ssize_t init_dump_store(struct dump_obj *dump_obj,
+ struct dump_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ dump_fips_init(DUMP_TYPE_FSP);
+ pr_info("%s: Initiated FSP dump\n", __func__);
+ return count;
+}
+
+static struct dump_attribute initiate_attribute =
+ __ATTR(initiate_dump, 0600, init_dump_show, init_dump_store);
+
+static struct attribute *initiate_attrs[] = {
+ &initiate_attribute.attr,
+ NULL,
+};
+
+static struct attribute_group initiate_attr_group = {
+ .attrs = initiate_attrs,
+};
+
+static struct kset *dump_kset;
+
+static ssize_t dump_attr_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct dump_attribute *attribute;
+ struct dump_obj *dump;
+
+ attribute = to_dump_attr(attr);
+ dump = to_dump_obj(kobj);
+
+ if (!attribute->show)
+ return -EIO;
+
+ return attribute->show(dump, attribute, buf);
+}
+
+static ssize_t dump_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct dump_attribute *attribute;
+ struct dump_obj *dump;
+
+ attribute = to_dump_attr(attr);
+ dump = to_dump_obj(kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(dump, attribute, buf, len);
+}
+
+static const struct sysfs_ops dump_sysfs_ops = {
+ .show = dump_attr_show,
+ .store = dump_attr_store,
+};
+
+static void dump_release(struct kobject *kobj)
+{
+ struct dump_obj *dump;
+
+ dump = to_dump_obj(kobj);
+ vfree(dump->buffer);
+ kfree(dump);
+}
+
+static struct attribute *dump_default_attrs[] = {
+ &id_attribute.attr,
+ &type_attribute.attr,
+ &ack_attribute.attr,
+ NULL,
+};
+
+static struct kobj_type dump_ktype = {
+ .sysfs_ops = &dump_sysfs_ops,
+ .release = &dump_release,
+ .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)
+{
+ int rc;
+ *type = 0xffffffff;
+
+ rc = opal_dump_info2(id, size, type);
+
+ if (rc == OPAL_PARAMETER)
+ rc = opal_dump_info(id, size);
+
+ if (rc)
+ pr_warn("%s: Failed to get dump info (%d)\n",
+ __func__, rc);
+ return rc;
+}
+
+static int64_t dump_read_data(struct dump_obj *dump)
+{
+ struct opal_sg_list *list;
+ uint64_t addr;
+ int64_t rc;
+
+ /* Allocate memory */
+ dump->buffer = vzalloc(PAGE_ALIGN(dump->size));
+ if (!dump->buffer) {
+ pr_err("%s : Failed to allocate memory\n", __func__);
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Generate SG list */
+ list = dump_data_to_sglist(dump);
+ if (!list) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Translate sg list addr to real address */
+ sglist_to_phy_addr(list);
+
+ /* First entry address */
+ addr = __pa(list);
+
+ /* Fetch data */
+ rc = OPAL_BUSY_EVENT;
+ while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+ rc = opal_dump_read(dump->id, addr);
+ if (rc == OPAL_BUSY_EVENT) {
+ opal_poll_events(NULL);
+ msleep(20);
+ }
+ }
+
+ if (rc != OPAL_SUCCESS && rc != OPAL_PARTIAL)
+ pr_warn("%s: Extract dump failed for ID 0x%x\n",
+ __func__, dump->id);
+
+ /* Free SG list */
+ free_dump_sg_list(list);
+
+out:
+ return rc;
+}
+
+static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buffer, loff_t pos, size_t count)
+{
+ ssize_t rc;
+
+ struct dump_obj *dump = to_dump_obj(kobj);
+
+ if (!dump->buffer) {
+ rc = dump_read_data(dump);
+
+ if (rc != OPAL_SUCCESS && rc != OPAL_PARTIAL) {
+ vfree(dump->buffer);
+ dump->buffer = NULL;
+
+ return -EIO;
+ }
+ if (rc == OPAL_PARTIAL) {
+ /* On a partial read, we just return EIO
+ * and rely on userspace to ask us to try
+ * again.
+ */
+ pr_info("%s: Platform dump partially read.ID = 0x%x\n",
+ __func__, dump->id);
+ return -EIO;
+ }
+ }
+
+ memcpy(buffer, dump->buffer + pos, count);
+
+ /* You may think we could free the dump buffer now and retrieve
+ * it again later if needed, but due to current firmware limitation,
+ * that's not the case. So, once read into userspace once,
+ * we keep the dump around until it's acknowledged by userspace.
+ */
+
+ return count;
+}
+
+static struct dump_obj *create_dump_obj(uint32_t id, size_t size,
+ uint32_t type)
+{
+ struct dump_obj *dump;
+ int rc;
+
+ dump = kzalloc(sizeof(*dump), GFP_KERNEL);
+ if (!dump)
+ return NULL;
+
+ dump->kobj.kset = dump_kset;
+
+ kobject_init(&dump->kobj, &dump_ktype);
+
+ sysfs_bin_attr_init(&dump->dump_attr);
+
+ dump->dump_attr.attr.name = "dump";
+ dump->dump_attr.attr.mode = 0400;
+ dump->dump_attr.size = size;
+ dump->dump_attr.read = dump_attr_read;
+
+ dump->id = id;
+ dump->size = size;
+ dump->type = type;
+
+ rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id);
+ if (rc) {
+ kobject_put(&dump->kobj);
+ return NULL;
+ }
+
+ rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr);
+ if (rc) {
+ kobject_put(&dump->kobj);
+ return NULL;
+ }
+
+ pr_info("%s: New platform dump. ID = 0x%x Size %u\n",
+ __func__, dump->id, dump->size);
+
+ kobject_uevent(&dump->kobj, KOBJ_ADD);
+
+ return dump;
+}
+
+static int process_dump(void)
+{
+ int rc;
+ uint32_t dump_id, dump_size, dump_type;
+ struct dump_obj *dump;
+ char name[22];
+
+ rc = dump_read_info(&dump_id, &dump_size, &dump_type);
+ if (rc != OPAL_SUCCESS)
+ return rc;
+
+ sprintf(name, "0x%x-0x%x", dump_type, dump_id);
+
+ /* we may get notified twice, let's handle
+ * that gracefully and not create two conflicting
+ * entries.
+ */
+ if (kset_find_obj(dump_kset, name))
+ return 0;
+
+ dump = create_dump_obj(dump_id, dump_size, dump_type);
+ if (!dump)
+ return -1;
+
+ return 0;
+}
+
+static void dump_work_fn(struct work_struct *work)
+{
+ process_dump();
+}
+
+static DECLARE_WORK(dump_work, dump_work_fn);
+
+static void schedule_process_dump(void)
+{
+ schedule_work(&dump_work);
+}
+
+/*
+ * New dump available notification
+ *
+ * Once we get notification, we add sysfs entries for it.
+ * We only fetch the dump on demand, and create sysfs asynchronously.
+ */
+static int dump_event(struct notifier_block *nb,
+ unsigned long events, void *change)
+{
+ if (events & OPAL_EVENT_DUMP_AVAIL)
+ schedule_process_dump();
+
+ return 0;
+}
+
+static struct notifier_block dump_nb = {
+ .notifier_call = dump_event,
+ .next = NULL,
+ .priority = 0
+};
+
+void __init opal_platform_dump_init(void)
+{
+ int rc;
+
+ dump_kset = kset_create_and_add("dump", NULL, opal_kobj);
+ if (!dump_kset) {
+ pr_warn("%s: Failed to create dump kset\n", __func__);
+ return;
+ }
+
+ rc = sysfs_create_group(&dump_kset->kobj, &initiate_attr_group);
+ if (rc) {
+ pr_warn("%s: Failed to create initiate dump attr group\n",
+ __func__);
+ kobject_put(&dump_kset->kobj);
+ return;
+ }
+
+ rc = opal_notifier_register(&dump_nb);
+ if (rc) {
+ pr_warn("%s: Can't register OPAL event notifier (%d)\n",
+ __func__, rc);
+ return;
+ }
+
+ opal_dump_resend_notification();
+}
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
new file mode 100644
index 000000000000..1d7355bc9db0
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -0,0 +1,313 @@
+/*
+ * Error log support on PowerNV.
+ *
+ * Copyright 2013,2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/fs.h>
+#include <linux/vmalloc.h>
+#include <linux/fcntl.h>
+#include <linux/kobject.h>
+#include <asm/uaccess.h>
+#include <asm/opal.h>
+
+struct elog_obj {
+ struct kobject kobj;
+ struct bin_attribute raw_attr;
+ uint64_t id;
+ uint64_t type;
+ size_t size;
+ char *buffer;
+};
+#define to_elog_obj(x) container_of(x, struct elog_obj, kobj)
+
+struct elog_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct elog_obj *elog, struct elog_attribute *attr,
+ char *buf);
+ ssize_t (*store)(struct elog_obj *elog, struct elog_attribute *attr,
+ const char *buf, size_t count);
+};
+#define to_elog_attr(x) container_of(x, struct elog_attribute, attr)
+
+static ssize_t elog_id_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0x%llx\n", elog_obj->id);
+}
+
+static const char *elog_type_to_string(uint64_t type)
+{
+ switch (type) {
+ case 0: return "PEL";
+ default: return "unknown";
+ }
+}
+
+static ssize_t elog_type_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0x%llx %s\n",
+ elog_obj->type,
+ elog_type_to_string(elog_obj->type));
+}
+
+static ssize_t elog_ack_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "ack - acknowledge log message\n");
+}
+
+static void delay_release_kobj(void *kobj)
+{
+ kobject_put((struct kobject *)kobj);
+}
+
+static ssize_t elog_ack_store(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ opal_send_ack_elog(elog_obj->id);
+ sysfs_schedule_callback(&elog_obj->kobj, delay_release_kobj,
+ &elog_obj->kobj, THIS_MODULE);
+ return count;
+}
+
+static struct elog_attribute id_attribute =
+ __ATTR(id, 0666, elog_id_show, NULL);
+static struct elog_attribute type_attribute =
+ __ATTR(type, 0666, elog_type_show, NULL);
+static struct elog_attribute ack_attribute =
+ __ATTR(acknowledge, 0660, elog_ack_show, elog_ack_store);
+
+static struct kset *elog_kset;
+
+static ssize_t elog_attr_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct elog_attribute *attribute;
+ struct elog_obj *elog;
+
+ attribute = to_elog_attr(attr);
+ elog = to_elog_obj(kobj);
+
+ if (!attribute->show)
+ return -EIO;
+
+ return attribute->show(elog, attribute, buf);
+}
+
+static ssize_t elog_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct elog_attribute *attribute;
+ struct elog_obj *elog;
+
+ attribute = to_elog_attr(attr);
+ elog = to_elog_obj(kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(elog, attribute, buf, len);
+}
+
+static const struct sysfs_ops elog_sysfs_ops = {
+ .show = elog_attr_show,
+ .store = elog_attr_store,
+};
+
+static void elog_release(struct kobject *kobj)
+{
+ struct elog_obj *elog;
+
+ elog = to_elog_obj(kobj);
+ kfree(elog->buffer);
+ kfree(elog);
+}
+
+static struct attribute *elog_default_attrs[] = {
+ &id_attribute.attr,
+ &type_attribute.attr,
+ &ack_attribute.attr,
+ NULL,
+};
+
+static struct kobj_type elog_ktype = {
+ .sysfs_ops = &elog_sysfs_ops,
+ .release = &elog_release,
+ .default_attrs = elog_default_attrs,
+};
+
+/* Maximum size of a single log on FSP is 16KB */
+#define OPAL_MAX_ERRLOG_SIZE 16384
+
+static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buffer, loff_t pos, size_t count)
+{
+ int opal_rc;
+
+ struct elog_obj *elog = to_elog_obj(kobj);
+
+ /* We may have had an error reading before, so let's retry */
+ if (!elog->buffer) {
+ elog->buffer = kzalloc(elog->size, GFP_KERNEL);
+ if (!elog->buffer)
+ return -EIO;
+
+ opal_rc = opal_read_elog(__pa(elog->buffer),
+ elog->size, elog->id);
+ if (opal_rc != OPAL_SUCCESS) {
+ pr_err("ELOG: log read failed for log-id=%llx\n",
+ elog->id);
+ kfree(elog->buffer);
+ elog->buffer = NULL;
+ return -EIO;
+ }
+ }
+
+ memcpy(buffer, elog->buffer + pos, count);
+
+ return count;
+}
+
+static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type)
+{
+ struct elog_obj *elog;
+ int rc;
+
+ elog = kzalloc(sizeof(*elog), GFP_KERNEL);
+ if (!elog)
+ return NULL;
+
+ elog->kobj.kset = elog_kset;
+
+ kobject_init(&elog->kobj, &elog_ktype);
+
+ sysfs_bin_attr_init(&elog->raw_attr);
+
+ elog->raw_attr.attr.name = "raw";
+ elog->raw_attr.attr.mode = 0400;
+ elog->raw_attr.size = size;
+ elog->raw_attr.read = raw_attr_read;
+
+ elog->id = id;
+ elog->size = size;
+ elog->type = type;
+
+ elog->buffer = kzalloc(elog->size, GFP_KERNEL);
+
+ if (elog->buffer) {
+ rc = opal_read_elog(__pa(elog->buffer),
+ elog->size, elog->id);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("ELOG: log read failed for log-id=%llx\n",
+ elog->id);
+ kfree(elog->buffer);
+ elog->buffer = NULL;
+ }
+ }
+
+ rc = kobject_add(&elog->kobj, NULL, "0x%llx", id);
+ if (rc) {
+ kobject_put(&elog->kobj);
+ return NULL;
+ }
+
+ rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr);
+ if (rc) {
+ kobject_put(&elog->kobj);
+ return NULL;
+ }
+
+ kobject_uevent(&elog->kobj, KOBJ_ADD);
+
+ return elog;
+}
+
+static void elog_work_fn(struct work_struct *work)
+{
+ size_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);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("ELOG: Opal log read failed\n");
+ return;
+ }
+
+ BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
+
+ if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
+ elog_size = OPAL_MAX_ERRLOG_SIZE;
+
+ sprintf(name, "0x%llx", log_id);
+
+ /* we may get notified twice, let's handle
+ * that gracefully and not create two conflicting
+ * entries.
+ */
+ if (kset_find_obj(elog_kset, name))
+ return;
+
+ create_elog_obj(log_id, elog_size, elog_type);
+}
+
+static DECLARE_WORK(elog_work, elog_work_fn);
+
+static int elog_event(struct notifier_block *nb,
+ unsigned long events, void *change)
+{
+ /* check for error log event */
+ if (events & OPAL_EVENT_ERROR_LOG_AVAIL)
+ schedule_work(&elog_work);
+ return 0;
+}
+
+static struct notifier_block elog_nb = {
+ .notifier_call = elog_event,
+ .next = NULL,
+ .priority = 0
+};
+
+int __init opal_elog_init(void)
+{
+ int rc = 0;
+
+ elog_kset = kset_create_and_add("elog", NULL, opal_kobj);
+ if (!elog_kset) {
+ pr_warn("%s: failed to create elog kset\n", __func__);
+ return -1;
+ }
+
+ rc = opal_notifier_register(&elog_nb);
+ if (rc) {
+ pr_err("%s: Can't register OPAL event notifier (%d)\n",
+ __func__, rc);
+ return rc;
+ }
+
+ /* We are now ready to pull error logs from opal. */
+ opal_resend_pending_logs();
+
+ return 0;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
new file mode 100644
index 000000000000..663cc9c65613
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -0,0 +1,64 @@
+/*
+ * PowerNV sensor code
+ *
+ * Copyright (C) 2013 IBM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <asm/opal.h>
+
+static DEFINE_MUTEX(opal_sensor_mutex);
+
+/*
+ * This will return sensor information to driver based on the requested sensor
+ * handle. A handle is an opaque id for the powernv, read by the driver from the
+ * device tree..
+ */
+int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
+{
+ int ret, token;
+ struct opal_msg msg;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ pr_err("%s: Couldn't get the token, returning\n", __func__);
+ ret = token;
+ goto out;
+ }
+
+ mutex_lock(&opal_sensor_mutex);
+ ret = opal_sensor_read(sensor_hndl, token, sensor_data);
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ mutex_unlock(&opal_sensor_mutex);
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(opal_get_sensor_data);
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
new file mode 100644
index 000000000000..0bd249a26f30
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -0,0 +1,290 @@
+/*
+ * PowerNV system parameter code
+ *
+ * Copyright (C) 2013 IBM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/gfp.h>
+#include <linux/stat.h>
+#include <asm/opal.h>
+
+#define MAX_PARAM_DATA_LEN 64
+
+static DEFINE_MUTEX(opal_sysparam_mutex);
+static struct kobject *sysparam_kobj;
+static void *param_data_buf;
+
+struct param_attr {
+ struct list_head list;
+ u32 param_id;
+ u32 param_size;
+ struct kobj_attribute kobj_attr;
+};
+
+static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
+{
+ struct opal_msg msg;
+ int ret, token;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ if (token != -ERESTARTSYS)
+ pr_err("%s: Couldn't get the token, returning\n",
+ __func__);
+ ret = token;
+ goto out;
+ }
+
+ ret = opal_get_param(token, param_id, (u64)buffer, length);
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+
+static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
+{
+ struct opal_msg msg;
+ int ret, token;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ if (token != -ERESTARTSYS)
+ pr_err("%s: Couldn't get the token, returning\n",
+ __func__);
+ ret = token;
+ goto out;
+ }
+
+ ret = opal_set_param(token, param_id, (u64)buffer, length);
+
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+
+static ssize_t sys_param_show(struct kobject *kobj,
+ struct kobj_attribute *kobj_attr, char *buf)
+{
+ struct param_attr *attr = container_of(kobj_attr, struct param_attr,
+ kobj_attr);
+ int ret;
+
+ mutex_lock(&opal_sysparam_mutex);
+ ret = opal_get_sys_param(attr->param_id, attr->param_size,
+ param_data_buf);
+ if (ret)
+ goto out;
+
+ memcpy(buf, param_data_buf, attr->param_size);
+
+out:
+ mutex_unlock(&opal_sysparam_mutex);
+ return ret ? ret : attr->param_size;
+}
+
+static ssize_t sys_param_store(struct kobject *kobj,
+ struct kobj_attribute *kobj_attr, const char *buf, size_t count)
+{
+ struct param_attr *attr = container_of(kobj_attr, struct param_attr,
+ kobj_attr);
+ int ret;
+
+ 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;
+}
+
+void __init opal_sys_param_init(void)
+{
+ struct device_node *sysparam;
+ struct param_attr *attr;
+ u32 *id, *size;
+ int count, i;
+ u8 *perm;
+
+ if (!opal_kobj) {
+ pr_warn("SYSPARAM: opal kobject is not available\n");
+ goto out;
+ }
+
+ sysparam_kobj = kobject_create_and_add("sysparams", opal_kobj);
+ if (!sysparam_kobj) {
+ pr_err("SYSPARAM: Failed to create sysparam kobject\n");
+ goto out;
+ }
+
+ /* Allocate big enough buffer for any get/set transactions */
+ param_data_buf = kzalloc(MAX_PARAM_DATA_LEN, GFP_KERNEL);
+ if (!param_data_buf) {
+ pr_err("SYSPARAM: Failed to allocate memory for param data "
+ "buf\n");
+ goto out_kobj_put;
+ }
+
+ sysparam = of_find_node_by_path("/ibm,opal/sysparams");
+ if (!sysparam) {
+ pr_err("SYSPARAM: Opal sysparam node not found\n");
+ goto out_param_buf;
+ }
+
+ if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
+ pr_err("SYSPARAM: Opal sysparam node not compatible\n");
+ goto out_node_put;
+ }
+
+ /* Number of parameters exposed through DT */
+ count = of_property_count_strings(sysparam, "param-name");
+ if (count < 0) {
+ pr_err("SYSPARAM: No string found of property param-name in "
+ "the node %s\n", sysparam->name);
+ goto out_node_put;
+ }
+
+ id = kzalloc(sizeof(*id) * count, GFP_KERNEL);
+ if (!id) {
+ pr_err("SYSPARAM: Failed to allocate memory to read parameter "
+ "id\n");
+ goto out_node_put;
+ }
+
+ size = kzalloc(sizeof(*size) * count, GFP_KERNEL);
+ if (!size) {
+ pr_err("SYSPARAM: Failed to allocate memory to read parameter "
+ "size\n");
+ goto out_free_id;
+ }
+
+ perm = kzalloc(sizeof(*perm) * count, GFP_KERNEL);
+ if (!perm) {
+ pr_err("SYSPARAM: Failed to allocate memory to read supported "
+ "action on the parameter");
+ goto out_free_size;
+ }
+
+ if (of_property_read_u32_array(sysparam, "param-id", id, count)) {
+ pr_err("SYSPARAM: Missing property param-id in the DT\n");
+ goto out_free_perm;
+ }
+
+ if (of_property_read_u32_array(sysparam, "param-len", size, count)) {
+ pr_err("SYSPARAM: Missing propery 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");
+ goto out_free_perm;
+ }
+
+ attr = kzalloc(sizeof(*attr) * count, GFP_KERNEL);
+ if (!attr) {
+ pr_err("SYSPARAM: Failed to allocate memory for parameter "
+ "attributes\n");
+ goto out_free_perm;
+ }
+
+ /* For each of the parameters, populate the parameter attributes */
+ for (i = 0; i < count; i++) {
+ sysfs_attr_init(&attr[i].kobj_attr.attr);
+ attr[i].param_id = id[i];
+ attr[i].param_size = size[i];
+ if (of_property_read_string_index(sysparam, "param-name", i,
+ &attr[i].kobj_attr.attr.name))
+ continue;
+
+ /* If the parameter is read-only or read-write */
+ switch (perm[i] & 3) {
+ case OPAL_SYSPARAM_READ:
+ attr[i].kobj_attr.attr.mode = S_IRUGO;
+ break;
+ case OPAL_SYSPARAM_WRITE:
+ attr[i].kobj_attr.attr.mode = S_IWUGO;
+ break;
+ case OPAL_SYSPARAM_RW:
+ attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUGO;
+ break;
+ default:
+ break;
+ }
+
+ attr[i].kobj_attr.show = sys_param_show;
+ attr[i].kobj_attr.store = sys_param_store;
+
+ if (sysfs_create_file(sysparam_kobj, &attr[i].kobj_attr.attr)) {
+ pr_err("SYSPARAM: Failed to create sysfs file %s\n",
+ attr[i].kobj_attr.attr.name);
+ goto out_free_attr;
+ }
+ }
+
+ kfree(perm);
+ kfree(size);
+ kfree(id);
+ of_node_put(sysparam);
+ return;
+
+out_free_attr:
+ kfree(attr);
+out_free_perm:
+ kfree(perm);
+out_free_size:
+ kfree(size);
+out_free_id:
+ kfree(id);
+out_node_put:
+ of_node_put(sysparam);
+out_param_buf:
+ kfree(param_data_buf);
+out_kobj_put:
+ kobject_put(sysparam_kobj);
+out:
+ return;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 3e8829c40fbb..bb90f9a4e027 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -123,9 +123,24 @@ OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE);
OPAL_CALL(opal_lpc_read, OPAL_LPC_READ);
OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE);
OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU);
+OPAL_CALL(opal_read_elog, OPAL_ELOG_READ);
+OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK);
+OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE);
+OPAL_CALL(opal_resend_pending_logs, OPAL_ELOG_RESEND);
+OPAL_CALL(opal_write_elog, OPAL_ELOG_WRITE);
OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE);
OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE);
OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT);
+OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO);
+OPAL_CALL(opal_dump_info2, OPAL_DUMP_INFO2);
+OPAL_CALL(opal_dump_read, OPAL_DUMP_READ);
+OPAL_CALL(opal_dump_ack, OPAL_DUMP_ACK);
OPAL_CALL(opal_get_msg, OPAL_GET_MSG);
OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND);
OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT);
+OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ);
+OPAL_CALL(opal_get_param, OPAL_GET_PARAM);
+OPAL_CALL(opal_set_param, OPAL_SET_PARAM);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276ac99e..4cd2ea6c0dbe 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc)
}
}
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
{
/*
* XSCOM indirect addresses have the top bit set. Additionally
- * the reset of the top 3 nibbles is always 0.
+ * the rest of the top 3 nibbles is always 0.
*
* Because the debugfs interface uses signed offsets and shifts
* the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg)
* conversion here. To leave room for further xscom address
* expansion, we only clear out the top byte
*
+ * For in-kernel use, we also support the real indirect bit, so
+ * we test for any of the top 5 bits
+ *
*/
- if (reg & (1ull << 59))
- reg = (reg & ~(0xffull << 56)) | (1ull << 63);
- return reg;
+ if (addr & (0x1full << 59))
+ addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+ return addr;
}
static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
int64_t rc;
__be64 v;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
*value = be64_to_cpu(v);
return opal_xscom_err_xlate(rc);
}
@@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
struct opal_scom_map *m = map;
int64_t rc;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_write(m->chip, m->addr + reg, value);
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_write(m->chip, reg, value);
return opal_xscom_err_xlate(rc);
}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 65499adaecff..e92f2f67640f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -21,6 +21,7 @@
#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>
@@ -33,8 +34,18 @@ struct kobject *opal_kobj;
struct opal {
u64 base;
u64 entry;
+ u64 size;
} opal;
+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;
+
static struct device_node *opal_node;
static DEFINE_SPINLOCK(opal_write_lock);
extern u64 opal_mc_secondary_handler[];
@@ -49,25 +60,29 @@ static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
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;
+ unsigned long 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",
opal.base, basep, basesz);
pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
opal.entry, entryp, entrysz);
+ pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%ld)\n",
+ opal.size, sizep, runtimesz);
powerpc_firmware_features |= FW_FEATURE_OPAL;
if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
@@ -84,6 +99,53 @@ int __init early_init_dt_scan_opal(unsigned long node,
return 1;
}
+int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ unsigned long i, size;
+ const __be32 *prop;
+
+ if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "mcheck-recoverable-ranges", &size);
+
+ if (!prop)
+ return 1;
+
+ pr_debug("Found machine check recoverable ranges.\n");
+
+ /*
+ * 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);
+
+ /*
+ * Each recoverable address entry is an (start address,len,
+ * recover address) pair, * 2 cells each, totalling 4 cells per entry.
+ */
+ for (i = 0; i < size / (sizeof(*prop) * 5); 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);
+ }
+ mc_recoverable_range_len = i;
+ return 1;
+}
+
static int __init opal_register_exception_handlers(void)
{
#ifdef __BIG_ENDIAN__
@@ -401,6 +463,38 @@ int opal_machine_check(struct pt_regs *regs)
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)
{
__be64 events;
@@ -472,8 +566,14 @@ static int __init opal_init(void)
/* 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();
}
return 0;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6d5fa9..3b2b4fb3585b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/msi.h>
+#include <linux/memblock.h>
#include <asm/sections.h>
#include <asm/io.h>
@@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
return;
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);
}
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+ struct pci_dev *pdev, u64 dma_mask)
+{
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+ struct pnv_ioda_pe *pe;
+ uint64_t top;
+ bool bypass = false;
+
+ if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+ return -ENODEV;;
+
+ pe = &phb->ioda.pe_array[pdn->pe_number];
+ if (pe->tce_bypass_enabled) {
+ top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+ bypass = (dma_mask >= top);
+ }
+
+ if (bypass) {
+ dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+ set_dma_ops(&pdev->dev, &dma_direct_ops);
+ set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+ } else {
+ dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+ set_dma_ops(&pdev->dev, &dma_iommu_ops);
+ set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+ }
+ return 0;
+}
+
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
{
struct pci_dev *dev;
@@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
}
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+ struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+ tce32_table);
+ uint16_t window_id = (pe->pe_number << 1 ) + 1;
+ int64_t rc;
+
+ pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+ if (enable) {
+ phys_addr_t top = memblock_end_of_DRAM();
+
+ top = roundup_pow_of_two(top);
+ rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+ pe->pe_number,
+ window_id,
+ pe->tce_bypass_base,
+ top);
+ } else {
+ rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+ pe->pe_number,
+ window_id,
+ pe->tce_bypass_base,
+ 0);
+
+ /*
+ * We might want to reset the DMA ops of all devices on
+ * this PE. However in theory, that shouldn't be necessary
+ * as this is used for VFIO/KVM pass-through and the device
+ * hasn't yet been returned to its kernel driver
+ */
+ }
+ if (rc)
+ pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+ else
+ pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe)
+{
+ /* TVE #1 is selected by PCI address bit 59 */
+ pe->tce_bypass_base = 1ull << 59;
+
+ /* Install set_bypass callback for VFIO */
+ pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+ /* Enable bypass by default */
+ pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe)
{
@@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
else
pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ /* Also create a bypass window */
+ pnv_pci_ioda2_setup_bypass_pe(phb, pe);
return;
fail:
if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
/* Setup TCEs */
phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+ phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
/* Setup shutdown function for kexec */
phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc57ef5..8518817dcdfd 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
- pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr);
- pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->p7iocPlssr || data->p7iocCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->p7iocPlssr, data->p7iocCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
@@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
data = (struct OpalIoPhb3ErrorData*)common;
pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
-
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
-
- pr_info(" nFir: %016llx\n", data->nFir);
- pr_info(" nFirMask: %016llx\n", data->nFirMask);
- pr_info(" nFirWOF: %016llx\n", data->nFirWOF);
- pr_info(" PhbPlssr: %016llx\n", data->phbPlssr);
- pr_info(" PhbCsr: %016llx\n", data->phbCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->nFir || data->nFirMask ||
+ data->nFirWOF)
+ pr_info(" nFir: %016llx %016llx %016llx\n",
+ data->nFir, data->nFirMask,
+ data->nFirWOF);
+ if (data->phbPlssr || data->phbCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->phbPlssr, data->phbCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
@@ -634,6 +664,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
pnv_pci_dma_fallback_setup(hose, pdev);
}
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
+
+ if (phb && phb->dma_set_mask)
+ return phb->dma_set_mask(phb, pdev, dma_mask);
+ return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
void pnv_pci_shutdown(void)
{
struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942a9a5f..cde169442775 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@ struct pnv_ioda_pe {
struct iommu_table tce32_table;
phys_addr_t tce_inval_reg_phys;
- /* XXX TODO: Add support for additional 64-bit iommus */
+ /* 64-bit TCE bypass region */
+ bool tce_bypass_enabled;
+ uint64_t tce_bypass_base;
/* MSIs. MVE index is identical for for 32 and 64 bit MSI
* and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@ struct pnv_phb {
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg);
void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+ int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+ u64 dma_mask);
void (*fixup_phb)(struct pci_controller *hose);
u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819be1f95..0051e108ef0f 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@ extern void pnv_smp_init(void);
static inline void pnv_smp_init(void) { }
#endif
+struct pci_dev;
+
#ifdef CONFIG_PCI
extern void pnv_pci_init(void);
extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
#else
static inline void pnv_pci_init(void) { }
static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+ return -ENODEV;
+}
#endif
extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f65c97c..61cf8fa9c61b 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -26,7 +26,7 @@
#include <linux/of_fdt.h>
#include <linux/interrupt.h>
#include <linux/bug.h>
-#include <linux/cpuidle.h>
+#include <linux/pci.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -141,6 +141,13 @@ static void pnv_progress(char *s, unsigned short hex)
{
}
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+ if (dev_is_pci(dev))
+ return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+ return __dma_set_mask(dev, dma_mask);
+}
+
static void pnv_shutdown(void)
{
/* Let the PCI code clear up IODA tables */
@@ -180,6 +187,7 @@ static void __init pnv_setup_machdep_opal(void)
ppc_md.power_off = pnv_power_off;
ppc_md.halt = pnv_halt;
ppc_md.machine_check_exception = opal_machine_check;
+ ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
}
#ifdef CONFIG_PPC_POWERNV_RTAS
@@ -217,16 +225,6 @@ static int __init pnv_probe(void)
return 1;
}
-void powernv_idle(void)
-{
- /* Hook to cpuidle framework if available, else
- * call on default platform idle code
- */
- if (cpuidle_idle_call()) {
- power7_idle();
- }
-}
-
define_machine(powernv) {
.name = "PowerNV",
.probe = pnv_probe,
@@ -236,8 +234,9 @@ define_machine(powernv) {
.show_cpuinfo = pnv_show_cpuinfo,
.progress = pnv_progress,
.machine_shutdown = pnv_shutdown,
- .power_save = powernv_idle,
+ .power_save = power7_idle,
.calibrate_decr = generic_calibrate_decr,
+ .dma_set_mask = pnv_dma_set_mask,
#ifdef CONFIG_KEXEC
.kexec_cpu_down = pnv_kexec_cpu_down,
#endif
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.