Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:
 "Here's a first pull request for powerpc updates for 3.18.

  The bulk of the additions are for the "cxl" driver, for IBM's Coherent
  Accelerator Processor Interface (CAPI).  Most of it's in drivers/misc,
  which Greg & Arnd maintain, Greg said he was happy for us to take it
  through our tree.

  There's the usual minor cleanups and fixes, including a bit of noise
  in drivers from some of those.  A bunch of updates to our EEH code,
  which has been getting more testing.  Several nice speedups from
  Anton, including 20% in clear_page().

  And a bunch of updates for freescale from Scott"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (130 commits)
  cxl: Fix afu_read() not doing finish_wait() on signal or non-blocking
  cxl: Add documentation for userspace APIs
  cxl: Add driver to Kbuild and Makefiles
  cxl: Add userspace header file
  cxl: Driver code for powernv PCIe based cards for userspace access
  cxl: Add base builtin support
  powerpc/mm: Add hooks for cxl
  powerpc/opal: Add PHB to cxl mode call
  powerpc/mm: Add new hash_page_mm()
  powerpc/powerpc: Add new PCIe functions for allocating cxl interrupts
  cxl: Add new header for call backs and structs
  powerpc/powernv: Split out set MSI IRQ chip code
  powerpc/mm: Export mmu_kernel_ssize and mmu_linear_psize
  powerpc/msi: Improve IRQ bitmap allocator
  powerpc/cell: Make spu_flush_all_slbs() generic
  powerpc/cell: Move data segment faulting code out of cell platform
  powerpc/cell: Move spu_handle_mm_fault() out of cell platform
  powerpc/pseries: Use new defines when calling H_SET_MODE
  powerpc: Update contact info in Documentation files
  powerpc/perf/hv-24x7: Simplify catalog_read()
  ...

32 files changed, 641 insertions, 448 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 670c312d914e..502cf69b6c89 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -93,6 +93,9 @@ obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)             += dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)              += kgdb.o
 obj-$(CONFIG_MODULES)           += ppc_ksyms.o
+ifeq ($(CONFIG_PPC32),y)
+obj-$(CONFIG_MODULES)           += ppc_ksyms_32.o
+endif
 obj-$(CONFIG_BOOTX_TEXT)        += btext.o
 obj-$(CONFIG_SMP)               += smp.o
 obj-$(CONFIG_KPROBES)           += kprobes.o
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 7a13f378ca2c..c78e6dac4d7d 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,6 +13,7 @@
 
 #include <linux/crash_dump.h>
 #include <linux/bootmem.h>
+#include <linux/io.h>
 #include <linux/memblock.h>
 #include <asm/code-patching.h>
 #include <asm/kdump.h>
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index bd1a2aba599f..735979764cd4 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -106,10 +106,14 @@ int __init swiotlb_setup_bus_notifier(void)
         return 0;
 }
 
-void swiotlb_detect_4g(void)
+void __init swiotlb_detect_4g(void)
 {
-        if ((memblock_end_of_DRAM() - 1) > 0xffffffff)
+        if ((memblock_end_of_DRAM() - 1) > 0xffffffff) {
                 ppc_swiotlb_enable = 1;
+#ifdef CONFIG_ZONE_DMA32
+                limit_zone_pfn(ZONE_DMA32, (1ULL << 32) >> PAGE_SHIFT);
+#endif
+        }
 }
 
 static int __init swiotlb_late_init(void)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index ee78f6e49d64..adac9dc54aee 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -15,6 +15,7 @@
 #include <asm/vio.h>
 #include <asm/bug.h>
 #include <asm/machdep.h>
+#include <asm/swiotlb.h>
 
 /*
  * Generic direct DMA implementation
@@ -25,6 +26,18 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
+static u64 __maybe_unused get_pfn_limit(struct device *dev)
+{
+        u64 pfn = (dev->coherent_dma_mask >> PAGE_SHIFT) + 1;
+        struct dev_archdata __maybe_unused *sd = &dev->archdata;
+
+#ifdef CONFIG_SWIOTLB
+        if (sd->max_direct_dma_addr && sd->dma_ops == &swiotlb_dma_ops)
+                pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT);
+#endif
+
+        return pfn;
+}
 
 void *dma_direct_alloc_coherent(struct device *dev, size_t size,
                                 dma_addr_t *dma_handle, gfp_t flag,
@@ -40,6 +53,26 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 #else
         struct page *page;
         int node = dev_to_node(dev);
+        u64 pfn = get_pfn_limit(dev);
+        int zone;
+
+        zone = dma_pfn_limit_to_zone(pfn);
+        if (zone < 0) {
+                dev_err(dev, "%s: No suitable zone for pfn %#llx\n",
+                        __func__, pfn);
+                return NULL;
+        }
+
+        switch (zone) {
+        case ZONE_DMA:
+                flag |= GFP_DMA;
+                break;
+#ifdef CONFIG_ZONE_DMA32
+        case ZONE_DMA32:
+                flag |= GFP_DMA32;
+                break;
+#endif
+        };
 
         /* ignore region specifiers */
         flag  &= ~(__GFP_HIGHMEM);
@@ -202,6 +235,7 @@ int __dma_set_mask(struct device *dev, u64 dma_mask)
         *dev->dma_mask = dma_mask;
         return 0;
 }
+
 int dma_set_mask(struct device *dev, u64 dma_mask)
 {
         if (ppc_md.dma_set_mask)
@@ -210,13 +244,10 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-u64 dma_get_required_mask(struct device *dev)
+u64 __dma_get_required_mask(struct device *dev)
 {
         struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-        if (ppc_md.dma_get_required_mask)
-                return ppc_md.dma_get_required_mask(dev);
-
         if (unlikely(dma_ops == NULL))
                 return 0;
 
@@ -225,6 +256,14 @@ u64 dma_get_required_mask(struct device *dev)
 
         return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
 }
+
+u64 dma_get_required_mask(struct device *dev)
+{
+        if (ppc_md.dma_get_required_mask)
+                return ppc_md.dma_get_required_mask(dev);
+
+        return __dma_get_required_mask(dev);
+}
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init dma_init(void)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 59a64f8dc85f..d543e4179c18 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -117,7 +117,7 @@ static DEFINE_MUTEX(eeh_dev_mutex);
  * not dynamically alloced, so that it ends up in RMO where RTAS
  * can access it.
  */
-#define EEH_PCI_REGS_LOG_LEN 4096
+#define EEH_PCI_REGS_LOG_LEN 8192
 static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
 
 /*
@@ -148,16 +148,12 @@ static int __init eeh_setup(char *str)
 }
 __setup("eeh=", eeh_setup);
 
-/**
- * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
- * @edev: device to report data for
- * @buf: point to buffer in which to log
- * @len: amount of room in buffer
- *
- * This routine captures assorted PCI configuration space data,
- * and puts them into a buffer for RTAS error logging.
+/*
+ * This routine captures assorted PCI configuration space data
+ * for the indicated PCI device, and puts them into a buffer
+ * for RTAS error logging.
  */
-static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
+static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 {
         struct device_node *dn = eeh_dev_to_of_node(edev);
         u32 cfg;
@@ -255,6 +251,19 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
         return n;
 }
 
+static void *eeh_dump_pe_log(void *data, void *flag)
+{
+        struct eeh_pe *pe = data;
+        struct eeh_dev *edev, *tmp;
+        size_t *plen = flag;
+
+        eeh_pe_for_each_dev(pe, edev, tmp)
+                *plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen,
+                                          EEH_PCI_REGS_LOG_LEN - *plen);
+
+        return NULL;
+}
+
 /**
  * eeh_slot_error_detail - Generate combined log including driver log and error log
  * @pe: EEH PE
@@ -268,7 +277,6 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
         size_t loglen = 0;
-        struct eeh_dev *edev, *tmp;
 
         /*
          * When the PHB is fenced or dead, it's pointless to collect
@@ -286,10 +294,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
                 eeh_pe_restore_bars(pe);
 
                 pci_regs_buf[0] = 0;
-                eeh_pe_for_each_dev(pe, edev, tmp) {
-                        loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
-                                                      EEH_PCI_REGS_LOG_LEN - loglen);
-                }
+                eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
         }
 
         eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
@@ -410,7 +415,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
         }
         dn = eeh_dev_to_of_node(edev);
         dev = eeh_dev_to_pci_dev(edev);
-        pe = edev->pe;
+        pe = eeh_dev_to_pe(edev);
 
         /* Access to IO BARs might get this far and still not want checking. */
         if (!pe) {
@@ -542,17 +547,16 @@ EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
 
 /**
  * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
- * @token: I/O token, should be address in the form 0xA....
- * @val: value, should be all 1's (XXX why do we need this arg??)
+ * @token: I/O address
  *
- * Check for an EEH failure at the given token address.  Call this
+ * Check for an EEH failure at the given I/O address. Call this
  * routine if the result of a read was all 0xff's and you want to
- * find out if this is due to an EEH slot freeze event.  This routine
+ * find out if this is due to an EEH slot freeze event. This routine
  * will query firmware for the EEH status.
  *
  * Note this routine is safe to call in an interrupt context.
  */
-unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+int eeh_check_failure(const volatile void __iomem *token)
 {
         unsigned long addr;
         struct eeh_dev *edev;
@@ -562,13 +566,11 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
         edev = eeh_addr_cache_get_dev(addr);
         if (!edev) {
                 eeh_stats.no_device++;
-                return val;
+                return 0;
         }
 
-        eeh_dev_check_failure(edev);
-        return val;
+        return eeh_dev_check_failure(edev);
 }
-
 EXPORT_SYMBOL(eeh_check_failure);
 
 
@@ -582,25 +584,51 @@ EXPORT_SYMBOL(eeh_check_failure);
  */
 int eeh_pci_enable(struct eeh_pe *pe, int function)
 {
-        int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+        int active_flag, rc;
 
         /*
          * pHyp doesn't allow to enable IO or DMA on unfrozen PE.
          * Also, it's pointless to enable them on unfrozen PE. So
-         * we have the check here.
+         * we have to check before enabling IO or DMA.
          */
-        if (function == EEH_OPT_THAW_MMIO ||
-            function == EEH_OPT_THAW_DMA) {
+        switch (function) {
+        case EEH_OPT_THAW_MMIO:
+                active_flag = EEH_STATE_MMIO_ACTIVE;
+                break;
+        case EEH_OPT_THAW_DMA:
+                active_flag = EEH_STATE_DMA_ACTIVE;
+                break;
+        case EEH_OPT_DISABLE:
+        case EEH_OPT_ENABLE:
+        case EEH_OPT_FREEZE_PE:
+                active_flag = 0;
+                break;
+        default:
+                pr_warn("%s: Invalid function %d\n",
+                        __func__, function);
+                return -EINVAL;
+        }
+
+        /*
+         * Check if IO or DMA has been enabled before
+         * enabling them.
+         */
+        if (active_flag) {
                 rc = eeh_ops->get_state(pe, NULL);
                 if (rc < 0)
                         return rc;
 
-                /* Needn't to enable or already enabled */
-                if ((rc == EEH_STATE_NOT_SUPPORT) ||
-                    ((rc & flags) == flags))
+                /* Needn't enable it at all */
+                if (rc == EEH_STATE_NOT_SUPPORT)
+                        return 0;
+
+                /* It's already enabled */
+                if (rc & active_flag)
                         return 0;
         }
 
+
+        /* Issue the request */
         rc = eeh_ops->set_option(pe, function);
         if (rc)
                 pr_warn("%s: Unexpected state change %d on "
@@ -608,17 +636,17 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
                         __func__, function, pe->phb->global_number,
                         pe->addr, rc);
 
-        rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-        if (rc <= 0)
-                return rc;
+        /* Check if the request is finished successfully */
+        if (active_flag) {
+                rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+                if (rc <= 0)
+                        return rc;
 
-        if ((function == EEH_OPT_THAW_MMIO) &&
-            (rc & EEH_STATE_MMIO_ENABLED))
-                return 0;
+                if (rc & active_flag)
+                        return 0;
 
-        if ((function == EEH_OPT_THAW_DMA) &&
-            (rc & EEH_STATE_DMA_ENABLED))
-                return 0;
+                return -EIO;
+        }
 
         return rc;
 }
@@ -634,7 +662,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
 {
         struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-        struct eeh_pe *pe = edev->pe;
+        struct eeh_pe *pe = eeh_dev_to_pe(edev);
 
         if (!pe) {
                 pr_err("%s: No PE found on PCI device %s\n",
@@ -645,14 +673,18 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
         switch (state) {
         case pcie_deassert_reset:
                 eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+                eeh_pe_state_clear(pe, EEH_PE_RESET);
                 break;
         case pcie_hot_reset:
+                eeh_pe_state_mark(pe, EEH_PE_RESET);
                 eeh_ops->reset(pe, EEH_RESET_HOT);
                 break;
         case pcie_warm_reset:
+                eeh_pe_state_mark(pe, EEH_PE_RESET);
                 eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
                 break;
         default:
+                eeh_pe_state_clear(pe, EEH_PE_RESET);
                 return -EINVAL;
         };
 
@@ -1141,6 +1173,85 @@ void eeh_remove_device(struct pci_dev *dev)
         edev->mode &= ~EEH_DEV_SYSFS;
 }
 
+int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
+{
+        int ret;
+
+        ret = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+        if (ret) {
+                pr_warn("%s: Failure %d enabling IO on PHB#%x-PE#%x\n",
+                        __func__, ret, pe->phb->global_number, pe->addr);
+                return ret;
+        }
+
+        ret = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+        if (ret) {
+                pr_warn("%s: Failure %d enabling DMA on PHB#%x-PE#%x\n",
+                        __func__, ret, pe->phb->global_number, pe->addr);
+                return ret;
+        }
+
+        /* Clear software isolated state */
+        if (sw_state && (pe->state & EEH_PE_ISOLATED))
+                eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+
+        return ret;
+}
+
+
+static struct pci_device_id eeh_reset_ids[] = {
+        { PCI_DEVICE(0x19a2, 0x0710) }, /* Emulex, BE     */
+        { PCI_DEVICE(0x10df, 0xe220) }, /* Emulex, Lancer */
+        { 0 }
+};
+
+static int eeh_pe_change_owner(struct eeh_pe *pe)
+{
+        struct eeh_dev *edev, *tmp;
+        struct pci_dev *pdev;
+        struct pci_device_id *id;
+        int flags, ret;
+
+        /* Check PE state */
+        flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+        ret = eeh_ops->get_state(pe, NULL);
+        if (ret < 0 || ret == EEH_STATE_NOT_SUPPORT)
+                return 0;
+
+        /* Unfrozen PE, nothing to do */
+        if ((ret & flags) == flags)
+                return 0;
+
+        /* Frozen PE, check if it needs PE level reset */
+        eeh_pe_for_each_dev(pe, edev, tmp) {
+                pdev = eeh_dev_to_pci_dev(edev);
+                if (!pdev)
+                        continue;
+
+                for (id = &eeh_reset_ids[0]; id->vendor != 0; id++) {
+                        if (id->vendor != PCI_ANY_ID &&
+                            id->vendor != pdev->vendor)
+                                continue;
+                        if (id->device != PCI_ANY_ID &&
+                            id->device != pdev->device)
+                                continue;
+                        if (id->subvendor != PCI_ANY_ID &&
+                            id->subvendor != pdev->subsystem_vendor)
+                                continue;
+                        if (id->subdevice != PCI_ANY_ID &&
+                            id->subdevice != pdev->subsystem_device)
+                                continue;
+
+                        goto reset;
+                }
+        }
+
+        return eeh_unfreeze_pe(pe, true);
+
+reset:
+        return eeh_pe_reset_and_recover(pe);
+}
+
 /**
  * eeh_dev_open - Increase count of pass through devices for PE
  * @pdev: PCI device
@@ -1153,6 +1264,7 @@ void eeh_remove_device(struct pci_dev *dev)
 int eeh_dev_open(struct pci_dev *pdev)
 {
         struct eeh_dev *edev;
+        int ret = -ENODEV;
 
         mutex_lock(&eeh_dev_mutex);
 
@@ -1165,6 +1277,16 @@ int eeh_dev_open(struct pci_dev *pdev)
         if (!edev || !edev->pe)
                 goto out;
 
+        /*
+         * The PE might have been put into frozen state, but we
+         * didn't detect that yet. The passed through PCI devices
+         * in frozen PE won't work properly. Clear the frozen state
+         * in advance.
+         */
+        ret = eeh_pe_change_owner(edev->pe);
+        if (ret)
+                goto out;
+
         /* Increase PE's pass through count */
         atomic_inc(&edev->pe->pass_dev_cnt);
         mutex_unlock(&eeh_dev_mutex);
@@ -1172,7 +1294,7 @@ int eeh_dev_open(struct pci_dev *pdev)
         return 0;
 out:
         mutex_unlock(&eeh_dev_mutex);
-        return -ENODEV;
+        return ret;
 }
 EXPORT_SYMBOL_GPL(eeh_dev_open);
 
@@ -1202,6 +1324,7 @@ void eeh_dev_release(struct pci_dev *pdev)
         /* Decrease PE's pass through count */
         atomic_dec(&edev->pe->pass_dev_cnt);
         WARN_ON(atomic_read(&edev->pe->pass_dev_cnt) < 0);
+        eeh_pe_change_owner(edev->pe);
 out:
         mutex_unlock(&eeh_dev_mutex);
 }
@@ -1281,8 +1404,10 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option)
          */
         switch (option) {
         case EEH_OPT_ENABLE:
-                if (eeh_enabled())
+                if (eeh_enabled()) {
+                        ret = eeh_pe_change_owner(pe);
                         break;
+                }
                 ret = -EIO;
                 break;
         case EEH_OPT_DISABLE:
@@ -1294,7 +1419,7 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option)
                         break;
                 }
 
-                ret = eeh_ops->set_option(pe, option);
+                ret = eeh_pci_enable(pe, option);
                 break;
         default:
                 pr_debug("%s: Option %d out of range (%d, %d)\n",
@@ -1345,6 +1470,36 @@ int eeh_pe_get_state(struct eeh_pe *pe)
 }
 EXPORT_SYMBOL_GPL(eeh_pe_get_state);
 
+static int eeh_pe_reenable_devices(struct eeh_pe *pe)
+{
+        struct eeh_dev *edev, *tmp;
+        struct pci_dev *pdev;
+        int ret = 0;
+
+        /* Restore config space */
+        eeh_pe_restore_bars(pe);
+
+        /*
+         * Reenable PCI devices as the devices passed
+         * through are always enabled before the reset.
+         */
+        eeh_pe_for_each_dev(pe, edev, tmp) {
+                pdev = eeh_dev_to_pci_dev(edev);
+                if (!pdev)
+                        continue;
+
+                ret = pci_reenable_device(pdev);
+                if (ret) {
+                        pr_warn("%s: Failure %d reenabling %s\n",
+                                __func__, ret, pci_name(pdev));
+                        return ret;
+                }
+        }
+
+        /* The PE is still in frozen state */
+        return eeh_unfreeze_pe(pe, true);
+}
+
 /**
  * eeh_pe_reset - Issue PE reset according to specified type
  * @pe: EEH PE
@@ -1368,23 +1523,22 @@ int eeh_pe_reset(struct eeh_pe *pe, int option)
         switch (option) {
         case EEH_RESET_DEACTIVATE:
                 ret = eeh_ops->reset(pe, option);
+                eeh_pe_state_clear(pe, EEH_PE_RESET);
                 if (ret)
                         break;
 
-                /*
-                 * The PE is still in frozen state and we need to clear
-                 * that. It's good to clear frozen state after deassert
-                 * to avoid messy IO access during reset, which might
-                 * cause recursive frozen PE.
-                 */
-                ret = eeh_ops->set_option(pe, EEH_OPT_THAW_MMIO);
-                if (!ret)
-                        ret = eeh_ops->set_option(pe, EEH_OPT_THAW_DMA);
-                if (!ret)
-                        eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+                ret = eeh_pe_reenable_devices(pe);
                 break;
         case EEH_RESET_HOT:
         case EEH_RESET_FUNDAMENTAL:
+                /*
+                 * Proactively freeze the PE to drop all MMIO access
+                 * during reset, which should be banned as it's always
+                 * cause recursive EEH error.
+                 */
+                eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+
+                eeh_pe_state_mark(pe, EEH_PE_RESET);
                 ret = eeh_ops->reset(pe, option);
                 break;
         default:
@@ -1413,9 +1567,6 @@ int eeh_pe_configure(struct eeh_pe *pe)
         if (!pe)
                 return -ENODEV;
 
-        /* Restore config space for the affected devices */
-        eeh_pe_restore_bars(pe);
-
         return ret;
 }
 EXPORT_SYMBOL_GPL(eeh_pe_configure);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6a0dcee8e931..3fd514f8e4b2 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -180,6 +180,22 @@ static bool eeh_dev_removed(struct eeh_dev *edev)
         return false;
 }
 
+static void *eeh_dev_save_state(void *data, void *userdata)
+{
+        struct eeh_dev *edev = data;
+        struct pci_dev *pdev;
+
+        if (!edev)
+                return NULL;
+
+        pdev = eeh_dev_to_pci_dev(edev);
+        if (!pdev)
+                return NULL;
+
+        pci_save_state(pdev);
+        return NULL;
+}
+
 /**
  * eeh_report_error - Report pci error to each device driver
  * @data: eeh device
@@ -303,6 +319,22 @@ static void *eeh_report_reset(void *data, void *userdata)
         return NULL;
 }
 
+static void *eeh_dev_restore_state(void *data, void *userdata)
+{
+        struct eeh_dev *edev = data;
+        struct pci_dev *pdev;
+
+        if (!edev)
+                return NULL;
+
+        pdev = eeh_dev_to_pci_dev(edev);
+        if (!pdev)
+                return NULL;
+
+        pci_restore_state(pdev);
+        return NULL;
+}
+
 /**
  * eeh_report_resume - Tell device to resume normal operations
  * @data: eeh device
@@ -450,38 +482,82 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
         struct eeh_pe *pe = (struct eeh_pe *)data;
-        int i, rc;
+        bool *clear_sw_state = flag;
+        int i, rc = 1;
 
-        for (i = 0; i < 3; i++) {
-                rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-                if (rc)
-                        continue;
-                rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
-                if (!rc)
-                        break;
-        }
+        for (i = 0; rc && i < 3; i++)
+                rc = eeh_unfreeze_pe(pe, clear_sw_state);
 
-        /* The PE has been isolated, clear it */
+        /* Stop immediately on any errors */
         if (rc) {
-                pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n",
-                        __func__, pe->phb->global_number, pe->addr, rc);
+                pr_warn("%s: Failure %d unfreezing PHB#%x-PE#%x\n",
+                        __func__, rc, pe->phb->global_number, pe->addr);
                 return (void *)pe;
         }
 
         return NULL;
 }
 
-static int eeh_clear_pe_frozen_state(struct eeh_pe *pe)
+static int eeh_clear_pe_frozen_state(struct eeh_pe *pe,
+                                     bool clear_sw_state)
 {
         void *rc;
 
-        rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL);
+        rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, &clear_sw_state);
         if (!rc)
                 eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 
         return rc ? -EIO : 0;
 }
 
+int eeh_pe_reset_and_recover(struct eeh_pe *pe)
+{
+        int result, ret;
+
+        /* Bail if the PE is being recovered */
+        if (pe->state & EEH_PE_RECOVERING)
+                return 0;
+
+        /* Put the PE into recovery mode */
+        eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+
+        /* Save states */
+        eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
+
+        /* Report error */
+        eeh_pe_dev_traverse(pe, eeh_report_error, &result);
+
+        /* Issue reset */
+        eeh_pe_state_mark(pe, EEH_PE_RESET);
+        ret = eeh_reset_pe(pe);
+        if (ret) {
+                eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_RESET);
+                return ret;
+        }
+        eeh_pe_state_clear(pe, EEH_PE_RESET);
+
+        /* Unfreeze the PE */
+        ret = eeh_clear_pe_frozen_state(pe, true);
+        if (ret) {
+                eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+                return ret;
+        }
+
+        /* Notify completion of reset */
+        eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
+
+        /* Restore device state */
+        eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL);
+
+        /* Resume */
+        eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+
+        /* Clear recovery mode */
+        eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+
+        return 0;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -540,7 +616,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
         eeh_pe_state_clear(pe, EEH_PE_RESET);
 
         /* Clear frozen state */
-        rc = eeh_clear_pe_frozen_state(pe);
+        rc = eeh_clear_pe_frozen_state(pe, false);
         if (rc)
                 return rc;
 
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 00e3844525a6..53dd0915e690 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -428,7 +428,7 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
         }
 
         /* Remove the EEH device */
-        pe = edev->pe;
+        pe = eeh_dev_to_pe(edev);
         edev->pe = NULL;
         list_del(&edev->list);
 
@@ -584,6 +584,8 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 {
         struct eeh_pe *pe = (struct eeh_pe *)data;
         int state = *((int *)flag);
+        struct eeh_dev *edev, *tmp;
+        struct pci_dev *pdev;
 
         /* Keep the state of permanently removed PE intact */
         if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
@@ -592,9 +594,22 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 
         pe->state &= ~state;
 
-        /* Clear check count since last isolation */
-        if (state & EEH_PE_ISOLATED)
-                pe->check_count = 0;
+        /*
+         * Special treatment on clearing isolated state. Clear
+         * check count since last isolation and put all affected
+         * devices to normal state.
+         */
+        if (!(state & EEH_PE_ISOLATED))
+                return NULL;
+
+        pe->check_count = 0;
+        eeh_pe_for_each_dev(pe, edev, tmp) {
+                pdev = eeh_dev_to_pci_dev(edev);
+                if (!pdev)
+                        continue;
+
+                pdev->error_state = pci_channel_io_normal;
+        }
 
         return NULL;
 }
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index e2595ba4b720..f19b1e5cb060 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -54,6 +54,43 @@ EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
 EEH_SHOW_ATTR(eeh_config_addr,     config_addr,     "0x%x");
 EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
 
+static ssize_t eeh_pe_state_show(struct device *dev,
+                                 struct device_attribute *attr, char *buf)
+{
+        struct pci_dev *pdev = to_pci_dev(dev);
+        struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+        int state;
+
+        if (!edev || !edev->pe)
+                return -ENODEV;
+
+        state = eeh_ops->get_state(edev->pe, NULL);
+        return sprintf(buf, "%0x08x %0x08x\n",
+                       state, edev->pe->state);
+}
+
+static ssize_t eeh_pe_state_store(struct device *dev,
+                                  struct device_attribute *attr,
+                                  const char *buf, size_t count)
+{
+        struct pci_dev *pdev = to_pci_dev(dev);
+        struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+        if (!edev || !edev->pe)
+                return -ENODEV;
+
+        /* Nothing to do if it's not frozen */
+        if (!(edev->pe->state & EEH_PE_ISOLATED))
+                return count;
+
+        if (eeh_unfreeze_pe(edev->pe, true))
+                return -EIO;
+
+        return count;
+}
+
+static DEVICE_ATTR_RW(eeh_pe_state);
+
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
         struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
@@ -68,9 +105,10 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
         rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
         rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
         rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+        rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
         if (rc)
-                printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+                pr_warn("EEH: Unable to create sysfs entries\n");
         else if (edev)
                 edev->mode |= EEH_DEV_SYSFS;
 }
@@ -92,6 +130,7 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev)
         device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
         device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
         device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+        device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
         if (edev)
                 edev->mode &= ~EEH_DEV_SYSFS;
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 7ee876d2adb5..fafff8dbd5d9 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -104,12 +104,15 @@ turn_on_mmu:
  * task's thread_struct.
  */
 #define EXCEPTION_PROLOG        \
-        mtspr   SPRN_SPRG_SCRATCH0,r10; \
-        mtspr   SPRN_SPRG_SCRATCH1,r11; \
-        mfcr    r10;            \
+        EXCEPTION_PROLOG_0;     \
         EXCEPTION_PROLOG_1;     \
         EXCEPTION_PROLOG_2
 
+#define EXCEPTION_PROLOG_0      \
+        mtspr   SPRN_SPRG_SCRATCH0,r10; \
+        mtspr   SPRN_SPRG_SCRATCH1,r11; \
+        mfcr    r10
+
 #define EXCEPTION_PROLOG_1      \
         mfspr   r11,SPRN_SRR1;          /* check whether user or kernel */ \
         andi.   r11,r11,MSR_PR; \
@@ -145,6 +148,14 @@ turn_on_mmu:
         SAVE_2GPRS(7, r11)
 
 /*
+ * Exception exit code.
+ */
+#define EXCEPTION_EPILOG_0      \
+        mtcr    r10;            \
+        mfspr   r10,SPRN_SPRG_SCRATCH0; \
+        mfspr   r11,SPRN_SPRG_SCRATCH1
+
+/*
  * Note: code which follows this uses cr0.eq (set if from kernel),
  * r11, r12 (SRR0), and r9 (SRR1).
  *
@@ -293,16 +304,8 @@ InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
         stw     r3, 8(r0)
 #endif
-        DO_8xx_CPU6(0x3f80, r3)
-        mtspr   SPRN_M_TW, r10  /* Save a couple of working registers */
-        mfcr    r10
-#ifdef CONFIG_8xx_CPU6
-        stw     r10, 0(r0)
-        stw     r11, 4(r0)
-#else
-        mtspr   SPRN_DAR, r10
-        mtspr   SPRN_SPRG2, r11
-#endif
+        EXCEPTION_PROLOG_0
+        mtspr   SPRN_SPRG_SCRATCH2, r10
         mfspr   r10, SPRN_SRR0  /* Get effective address of fault */
 #ifdef CONFIG_8xx_CPU15
         addi    r11, r10, 0x1000
@@ -359,18 +362,11 @@ InstructionTLBMiss:
         mtspr   SPRN_MI_RPN, r10        /* Update TLB entry */
 
         /* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-        mfspr   r10, SPRN_DAR
-        mtcr    r10
-        mtspr   SPRN_DAR, r11   /* Tag DAR */
-        mfspr   r11, SPRN_SPRG2
-#else
-        lwz     r11, 0(r0)
-        mtcr    r11
-        lwz     r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
         lwz     r3, 8(r0)
 #endif
-        mfspr   r10, SPRN_M_TW
+        mfspr   r10, SPRN_SPRG_SCRATCH2
+        EXCEPTION_EPILOG_0
         rfi
 2:
         mfspr   r11, SPRN_SRR1
@@ -381,19 +377,11 @@ InstructionTLBMiss:
         mtspr   SPRN_SRR1, r11
 
         /* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-        mfspr   r10, SPRN_DAR
-        mtcr    r10
-        li      r11, 0x00f0
-        mtspr   SPRN_DAR, r11   /* Tag DAR */
-        mfspr   r11, SPRN_SPRG2
-#else
-        lwz     r11, 0(r0)
-        mtcr    r11
-        lwz     r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
         lwz     r3, 8(r0)
 #endif
-        mfspr   r10, SPRN_M_TW
+        mfspr   r10, SPRN_SPRG_SCRATCH2
+        EXCEPTION_EPILOG_0
         b       InstructionAccess
 
         . = 0x1200
@@ -401,16 +389,8 @@ DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
         stw     r3, 8(r0)
 #endif
-        DO_8xx_CPU6(0x3f80, r3)
-        mtspr   SPRN_M_TW, r10  /* Save a couple of working registers */
-        mfcr    r10
-#ifdef CONFIG_8xx_CPU6
-        stw     r10, 0(r0)
-        stw     r11, 4(r0)
-#else
-        mtspr   SPRN_DAR, r10
-        mtspr   SPRN_SPRG2, r11
-#endif
+        EXCEPTION_PROLOG_0
+        mtspr   SPRN_SPRG_SCRATCH2, r10
         mfspr   r10, SPRN_M_TWB /* Get level 1 table entry address */
 
         /* If we are faulting a kernel address, we have to use the
@@ -483,19 +463,12 @@ DataStoreTLBMiss:
         mtspr   SPRN_MD_RPN, r10        /* Update TLB entry */
 
         /* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-        mfspr   r10, SPRN_DAR
-        mtcr    r10
-        mtspr   SPRN_DAR, r11   /* Tag DAR */
-        mfspr   r11, SPRN_SPRG2
-#else
-        mtspr   SPRN_DAR, r11   /* Tag DAR */
-        lwz     r11, 0(r0)
-        mtcr    r11
-        lwz     r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
         lwz     r3, 8(r0)
 #endif
-        mfspr   r10, SPRN_M_TW
+        mtspr   SPRN_DAR, r11   /* Tag DAR */
+        mfspr   r10, SPRN_SPRG_SCRATCH2
+        EXCEPTION_EPILOG_0
         rfi
 
 /* This is an instruction TLB error on the MPC8xx.  This could be due
@@ -507,35 +480,18 @@ InstructionTLBError:
         b       InstructionAccess
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
- * many reasons, including a dirty update to a pte.  We can catch that
- * one here, but anything else is an error.  First, we track down the
- * Linux pte.  If it is valid, write access is allowed, but the
- * page dirty bit is not set, we will set it and reload the TLB.  For
- * any other case, we bail out to a higher level function that can
- * handle it.
+ * many reasons, including a dirty update to a pte.  We bail out to
+ * a higher level function that can handle it.
  */
         . = 0x1400
 DataTLBError:
-#ifdef CONFIG_8xx_CPU6
-        stw     r3, 8(r0)
-#endif
-        DO_8xx_CPU6(0x3f80, r3)
-        mtspr   SPRN_M_TW, r10  /* Save a couple of working registers */
-        mfcr    r10
-        stw     r10, 0(r0)
-        stw     r11, 4(r0)
+        EXCEPTION_PROLOG_0
 
-        mfspr   r10, SPRN_DAR
-        cmpwi   cr0, r10, 0x00f0
+        mfspr   r11, SPRN_DAR
+        cmpwi   cr0, r11, 0x00f0
         beq-    FixupDAR        /* must be a buggy dcbX, icbi insn. */
-DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR */
-        mfspr   r10, SPRN_M_TW  /* Restore registers */
-        lwz     r11, 0(r0)
-        mtcr    r11
-        lwz     r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
-        lwz     r3, 8(r0)
-#endif
+DARFixed:/* Return from dcbx instruction bug workaround */
+        EXCEPTION_EPILOG_0
         b       DataAccess
 
         EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
@@ -559,11 +515,15 @@ DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR
 
 /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
  * by decoding the registers used by the dcbx instruction and adding them.
- * DAR is set to the calculated address and r10 also holds the EA on exit.
+ * DAR is set to the calculated address.
  */
  /* define if you don't want to use self modifying code */
 #define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
+#ifdef CONFIG_8xx_CPU6
+        stw     r3, 8(r0)
+#endif
+        mtspr   SPRN_SPRG_SCRATCH2, r10
         /* fetch instruction from memory. */
         mfspr   r10, SPRN_SRR0
         andis.  r11, r10, 0x8000        /* Address >= 0x80000000 */
@@ -579,16 +539,17 @@ FixupDAR:/* Entry point for dcbx workaround. */
         mtspr   SPRN_MD_TWC, r11        /* Load pte table base address */
         mfspr   r11, SPRN_MD_TWC        /* ....and get the pte address */
         lwz     r11, 0(r11)     /* Get the pte */
+#ifdef CONFIG_8xx_CPU6
+        lwz     r3, 8(r0)       /* restore r3 from memory */
+#endif
         /* concat physical page address(r11) and page offset(r10) */
         rlwimi  r11, r10, 0, 20, 31
         lwz     r11,0(r11)
 /* Check if it really is a dcbx instruction. */
 /* dcbt and dcbtst does not generate DTLB Misses/Errors,
  * no need to include them here */
-        srwi    r10, r11, 26    /* check if major OP code is 31 */
-        cmpwi   cr0, r10, 31
-        bne-    141f
-        rlwinm  r10, r11, 0, 21, 30
+        xoris   r10, r11, 0x7c00        /* check if major OP code is 31 */
+        rlwinm  r10, r10, 0, 21, 5
         cmpwi   cr0, r10, 2028  /* Is dcbz? */
         beq+    142f
         cmpwi   cr0, r10, 940   /* Is dcbi? */
@@ -599,16 +560,13 @@ FixupDAR:/* Entry point for dcbx workaround. */
         beq+    142f
         cmpwi   cr0, r10, 1964  /* Is icbi? */
         beq+    142f
-141:    mfspr   r10, SPRN_DAR   /* r10 must hold DAR at exit */
+141:    mfspr   r10,SPRN_SPRG_SCRATCH2
         b       DARFixed        /* Nope, go back to normal TLB processing */
 
 144:    mfspr   r10, SPRN_DSISR
         rlwinm  r10, r10,0,7,5  /* Clear store bit for buggy dcbst insn */
         mtspr   SPRN_DSISR, r10
 142:    /* continue, it was a dcbx, dcbi instruction. */
-#ifdef CONFIG_8xx_CPU6
-        lwz     r3, 8(r0)       /* restore r3 from memory */
-#endif
 #ifndef NO_SELF_MODIFYING_CODE
         andis.  r10,r11,0x1f    /* test if reg RA is r0 */
         li      r10,modified_instr@l
@@ -619,14 +577,15 @@ FixupDAR:/* Entry point for dcbx workaround. */
         stw     r11,0(r10)      /* store add/and instruction */
         dcbf    0,r10           /* flush new instr. to memory. */
         icbi    0,r10           /* invalidate instr. cache line */
-        lwz     r11, 4(r0)      /* restore r11 from memory */
-        mfspr   r10, SPRN_M_TW  /* restore r10 from M_TW */
+        mfspr   r11, SPRN_SPRG_SCRATCH1 /* restore r11 */
+        mfspr   r10, SPRN_SPRG_SCRATCH0 /* restore r10 */
         isync                   /* Wait until new instr is loaded from memory */
 modified_instr:
         .space  4               /* this is where the add instr. is stored */
         bne+    143f
         subf    r10,r0,r10      /* r10=r10-r0, only if reg RA is r0 */
 143:    mtdar   r10             /* store faulting EA in DAR */
+        mfspr   r10,SPRN_SPRG_SCRATCH2
         b       DARFixed        /* Go back to normal TLB handling */
 #else
         mfctr   r10
@@ -680,13 +639,16 @@ modified_instr:
         mfdar   r11
         mtctr   r11                     /* restore ctr reg from DAR */
         mtdar   r10                     /* save fault EA to DAR */
+        mfspr   r10,SPRN_SPRG_SCRATCH2
         b       DARFixed                /* Go back to normal TLB handling */
 
         /* special handling for r10,r11 since these are modified already */
-153:    lwz     r11, 4(r0)      /* load r11 from memory */
-        b       155f
-154:    mfspr   r11, SPRN_M_TW  /* load r10 from M_TW */
-155:    add     r10, r10, r11   /* add it */
+153:    mfspr   r11, SPRN_SPRG_SCRATCH1 /* load r11 from SPRN_SPRG_SCRATCH1 */
+        add     r10, r10, r11   /* add it */
+        mfctr   r11             /* restore r11 */
+        b       151b
+154:    mfspr   r11, SPRN_SPRG_SCRATCH0 /* load r10 from SPRN_SPRG_SCRATCH0 */
+        add     r10, r10, r11   /* add it */
         mfctr   r11             /* restore r11 */
         b       151b
 #endif
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 0bb5918faaaf..1f7d84e2e8b2 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -293,7 +293,7 @@ out:
 /*
  * Handle single-step exceptions following a DABR hit.
  */
-int __kprobes single_step_dabr_instruction(struct die_args *args)
+static int __kprobes single_step_dabr_instruction(struct die_args *args)
 {
         struct pt_regs *regs = args->regs;
         struct perf_event *bp = NULL;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 1114d13ac19f..ac86c53e2542 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -55,7 +55,7 @@ static struct device ibmebus_bus_device = { /* fake "parent" device */
 struct bus_type ibmebus_bus_type;
 
 /* These devices will automatically be added to the bus during init */
-static struct of_device_id __initdata ibmebus_matches[] = {
+static const struct of_device_id ibmebus_matches[] __initconst = {
         { .compatible = "IBM,lhca" },
         { .compatible = "IBM,lhea" },
         {},
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index be05841396cf..c0754bbf8118 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -73,7 +73,7 @@ _GLOBAL(power7_powersave_common)
 
         /* Check if something happened while soft-disabled */
         lbz     r0,PACAIRQHAPPENED(r13)
-        cmpwi   cr0,r0,0
+        andi.   r0,r0,~PACA_IRQ_HARD_DIS@l
         beq     1f
         cmpwi   cr0,r4,0
         beq     1f
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4c5891de162e..8eb857f216c1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -444,13 +444,13 @@ void migrate_irqs(void)
 
                 cpumask_and(mask, data->affinity, map);
                 if (cpumask_any(mask) >= nr_cpu_ids) {
-                        printk("Breaking affinity for irq %i\n", irq);
+                        pr_warn("Breaking affinity for irq %i\n", irq);
                         cpumask_copy(mask, map);
                 }
                 if (chip->irq_set_affinity)
                         chip->irq_set_affinity(data, mask, true);
                 else if (desc->action && !(warned++))
-                        printk("Cannot set affinity for irq %i\n", irq);
+                        pr_err("Cannot set affinity for irq %i\n", irq);
         }
 
         free_cpumask_var(mask);
@@ -470,7 +470,7 @@ static inline void check_stack_overflow(void)
 
         /* check for stack overflow: is there less than 2KB free? */
         if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-                printk("do_IRQ: stack overflow: %ld\n",
+                pr_err("do_IRQ: stack overflow: %ld\n",
                         sp - sizeof(struct thread_info));
                 dump_stack();
         }
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 936258881c98..7b750c4ed5c7 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -35,7 +35,7 @@ static struct legacy_serial_info {
         phys_addr_t                     taddr;
 } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
 
-static struct of_device_id legacy_serial_parents[] __initdata = {
+static const struct of_device_id legacy_serial_parents[] __initconst = {
         {.type = "soc",},
         {.type = "tsi-bridge",},
         {.type = "opb", },
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 6cff040bf456..c94d2e018d84 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -15,6 +15,9 @@
     along with this program; if not, write to the Free Software
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/elf.h>
@@ -28,12 +31,6 @@
 #include <linux/sort.h>
 #include <asm/setup.h>
 
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt , ...)
-#endif
-
 /* Count how many different relocations (different symbol, different
    addend) */
 static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
@@ -121,8 +118,8 @@ static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
                         continue;
 
                 if (sechdrs[i].sh_type == SHT_RELA) {
-                        DEBUGP("Found relocations in section %u\n", i);
-                        DEBUGP("Ptr: %p.  Number: %u\n",
+                        pr_debug("Found relocations in section %u\n", i);
+                        pr_debug("Ptr: %p.  Number: %u\n",
                                (void *)hdr + sechdrs[i].sh_offset,
                                sechdrs[i].sh_size / sizeof(Elf32_Rela));
 
@@ -161,7 +158,7 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr,
                         me->arch.core_plt_section = i;
         }
         if (!me->arch.core_plt_section || !me->arch.init_plt_section) {
-                printk("Module doesn't contain .plt or .init.plt sections.\n");
+                pr_err("Module doesn't contain .plt or .init.plt sections.\n");
                 return -ENOEXEC;
         }
 
@@ -189,7 +186,7 @@ static uint32_t do_plt_call(void *location,
 {
         struct ppc_plt_entry *entry;
 
-        DEBUGP("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
+        pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
         /* Init, or core PLT? */
         if (location >= mod->module_core
             && location < mod->module_core + mod->core_size)
@@ -208,7 +205,7 @@ static uint32_t do_plt_call(void *location,
         entry->jump[2] = 0x7d8903a6;                    /* mtctr r12 */
         entry->jump[3] = 0x4e800420;                    /* bctr */
 
-        DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
+        pr_debug("Initialized plt for 0x%x at %p\n", val, entry);
         return (uint32_t)entry;
 }
 
@@ -224,7 +221,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
         uint32_t *location;
         uint32_t value;
 
-        DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
+        pr_debug("Applying ADD relocate section %u to %u\n", relsec,
                sechdrs[relsec].sh_info);
         for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
                 /* This is where to make the change */
@@ -268,17 +265,17 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
                                                     sechdrs, module);
 
                         /* Only replace bits 2 through 26 */
-                        DEBUGP("REL24 value = %08X. location = %08X\n",
+                        pr_debug("REL24 value = %08X. location = %08X\n",
                                value, (uint32_t)location);
-                        DEBUGP("Location before: %08X.\n",
+                        pr_debug("Location before: %08X.\n",
                                *(uint32_t *)location);
                         *(uint32_t *)location
                                 = (*(uint32_t *)location & ~0x03fffffc)
                                 | ((value - (uint32_t)location)
                                    & 0x03fffffc);
-                        DEBUGP("Location after: %08X.\n",
+                        pr_debug("Location after: %08X.\n",
                                *(uint32_t *)location);
-                        DEBUGP("ie. jump to %08X+%08X = %08X\n",
+                        pr_debug("ie. jump to %08X+%08X = %08X\n",
                                *(uint32_t *)location & 0x03fffffc,
                                (uint32_t)location,
                                (*(uint32_t *)location & 0x03fffffc)
@@ -291,7 +288,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
                         break;
 
                 default:
-                        printk("%s: unknown ADD relocation: %u\n",
+                        pr_err("%s: unknown ADD relocation: %u\n",
                                module->name,
                                ELF32_R_TYPE(rela[i].r_info));
                         return -ENOEXEC;
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index d807ee626af9..68384514506b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -15,6 +15,9 @@
     along with this program; if not, write to the Free Software
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
@@ -36,11 +39,6 @@
    Using a magic allocator which places modules within 32MB solves
    this, and makes other things simpler.  Anton?
    --RR.  */
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt , ...)
-#endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
 #define R2_STACK_OFFSET 24
@@ -279,8 +277,8 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
         /* Every relocated section... */
         for (i = 1; i < hdr->e_shnum; i++) {
                 if (sechdrs[i].sh_type == SHT_RELA) {
-                        DEBUGP("Found relocations in section %u\n", i);
-                        DEBUGP("Ptr: %p.  Number: %lu\n",
+                        pr_debug("Found relocations in section %u\n", i);
+                        pr_debug("Ptr: %p.  Number: %Lu\n",
                                (void *)sechdrs[i].sh_addr,
                                sechdrs[i].sh_size / sizeof(Elf64_Rela));
 
@@ -304,7 +302,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
         relocs++;
 #endif
 
-        DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
+        pr_debug("Looks like a total of %lu stubs, max\n", relocs);
         return relocs * sizeof(struct ppc64_stub_entry);
 }
 
@@ -390,7 +388,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
         }
 
         if (!me->arch.stubs_section) {
-                printk("%s: doesn't contain .stubs.\n", me->name);
+                pr_err("%s: doesn't contain .stubs.\n", me->name);
                 return -ENOEXEC;
         }
 
@@ -434,11 +432,11 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
         /* Stub uses address relative to r2. */
         reladdr = (unsigned long)entry - my_r2(sechdrs, me);
         if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
-                printk("%s: Address %p of stub out of range of %p.\n",
+                pr_err("%s: Address %p of stub out of range of %p.\n",
                        me->name, (void *)reladdr, (void *)my_r2);
                 return 0;
         }
-        DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr);
+        pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
 
         entry->jump[0] |= PPC_HA(reladdr);
         entry->jump[1] |= PPC_LO(reladdr);
@@ -477,7 +475,7 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
         if (*instruction != PPC_INST_NOP) {
-                printk("%s: Expect noop after relocate, got %08x\n",
+                pr_err("%s: Expect noop after relocate, got %08x\n",
                        me->name, *instruction);
                 return 0;
         }
@@ -498,7 +496,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
         unsigned long *location;
         unsigned long value;
 
-        DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
+        pr_debug("Applying ADD relocate section %u to %u\n", relsec,
                sechdrs[relsec].sh_info);
 
         /* First time we're called, we can fix up .TOC. */
@@ -519,7 +517,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                 sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
                         + ELF64_R_SYM(rela[i].r_info);
 
-                DEBUGP("RELOC at %p: %li-type as %s (%lu) + %li\n",
+                pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
                        location, (long)ELF64_R_TYPE(rela[i].r_info),
                        strtab + sym->st_name, (unsigned long)sym->st_value,
                        (long)rela[i].r_addend);
@@ -546,7 +544,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                         /* Subtract TOC pointer */
                         value -= my_r2(sechdrs, me);
                         if (value + 0x8000 > 0xffff) {
-                                printk("%s: bad TOC16 relocation (%lu)\n",
+                                pr_err("%s: bad TOC16 relocation (0x%lx)\n",
                                        me->name, value);
                                 return -ENOEXEC;
                         }
@@ -567,7 +565,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                         /* Subtract TOC pointer */
                         value -= my_r2(sechdrs, me);
                         if ((value & 3) != 0 || value + 0x8000 > 0xffff) {
-                                printk("%s: bad TOC16_DS relocation (%lu)\n",
+                                pr_err("%s: bad TOC16_DS relocation (0x%lx)\n",
                                        me->name, value);
                                 return -ENOEXEC;
                         }
@@ -580,7 +578,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                         /* Subtract TOC pointer */
                         value -= my_r2(sechdrs, me);
                         if ((value & 3) != 0) {
-                                printk("%s: bad TOC16_LO_DS relocation (%lu)\n",
+                                pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n",
                                        me->name, value);
                                 return -ENOEXEC;
                         }
@@ -613,7 +611,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                         /* Convert value to relative */
                         value -= (unsigned long)location;
                         if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
-                                printk("%s: REL24 %li out of range!\n",
+                                pr_err("%s: REL24 %li out of range!\n",
                                        me->name, (long int)value);
                                 return -ENOEXEC;
                         }
@@ -655,7 +653,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                         break;
 
                 default:
-                        printk("%s: Unknown ADD relocation: %lu\n",
+                        pr_err("%s: Unknown ADD relocation: %lu\n",
                                me->name,
                                (unsigned long)ELF64_R_TYPE(rela[i].r_info));
                         return -ENOEXEC;
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 28b898e68185..34f7c9b7cd96 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -567,7 +567,7 @@ static int __init nvram_init(void)
         return rc;
 }
 
-void __exit nvram_cleanup(void)
+static void __exit nvram_cleanup(void)
 {
         misc_deregister( &nvram_dev );
 }
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index a7b743076720..f87bc1b4bdda 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -97,7 +97,7 @@ static int of_pci_phb_probe(struct platform_device *dev)
         return 0;
 }
 
-static struct of_device_id of_pci_phb_ids[] = {
+static const struct of_device_id of_pci_phb_ids[] = {
         { .type = "pci", },
         { .type = "pcix", },
         { .type = "pcie", },
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index b2814e23e1ed..bd70a51d5747 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1140,7 +1140,7 @@ static int reparent_resources(struct resource *parent,
  *          as well.
  */
 
-void pcibios_allocate_bus_resources(struct pci_bus *bus)
+static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 {
         struct pci_bus *b;
         int i;
@@ -1561,7 +1561,6 @@ EARLY_PCI_OP(write, byte, u8)
 EARLY_PCI_OP(write, word, u16)
 EARLY_PCI_OP(write, dword, u32)
 
-extern int pci_bus_find_capability (struct pci_bus *bus, unsigned int devfn, int cap);
 int early_find_capability(struct pci_controller *hose, int bus, int devfn,
                           int cap)
 {
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 44562aa97f16..e6245e9c7d8d 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -38,7 +38,7 @@ static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
  * @addr0: value of 1st cell of a device tree PCI address.
  * @bridge: Set this flag if the address is from a bridge 'ranges' property
  */
-unsigned int pci_parse_of_flags(u32 addr0, int bridge)
+static unsigned int pci_parse_of_flags(u32 addr0, int bridge)
 {
         unsigned int flags = 0;
 
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 48d17d6fca5b..c4dfff6c2719 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -1,207 +1,41 @@
-#include <linux/export.h>
-#include <linux/threads.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/elfcore.h>
-#include <linux/string.h>
-#include <linux/interrupt.h>
-#include <linux/screen_info.h>
-#include <linux/vt_kern.h>
-#include <linux/nvram.h>
-#include <linux/irq.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
+#include <linux/ftrace.h>
+#include <linux/mm.h>
 
-#include <asm/page.h>
 #include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <linux/atomic.h>
-#include <asm/checksum.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <linux/adb.h>
-#include <linux/cuda.h>
-#include <linux/pmu.h>
-#include <asm/prom.h>
-#include <asm/pci-bridge.h>
-#include <asm/irq.h>
-#include <asm/pmac_feature.h>
-#include <asm/dma.h>
-#include <asm/machdep.h>
-#include <asm/hw_irq.h>
-#include <asm/nvram.h>
-#include <asm/mmu_context.h>
-#include <asm/backlight.h>
-#include <asm/time.h>
-#include <asm/cputable.h>
-#include <asm/btext.h>
-#include <asm/div64.h>
-#include <asm/signal.h>
-#include <asm/dcr.h>
-#include <asm/ftrace.h>
 #include <asm/switch_to.h>
+#include <asm/cacheflush.h>
 #include <asm/epapr_hcalls.h>
 
-#ifdef CONFIG_PPC32
-extern void transfer_to_handler(void);
-extern void do_IRQ(struct pt_regs *regs);
-extern void machine_check_exception(struct pt_regs *regs);
-extern void alignment_exception(struct pt_regs *regs);
-extern void program_check_exception(struct pt_regs *regs);
-extern void single_step_exception(struct pt_regs *regs);
-extern int sys_sigreturn(struct pt_regs *regs);
+EXPORT_SYMBOL(flush_dcache_range);
+EXPORT_SYMBOL(flush_icache_range);
 
-EXPORT_SYMBOL(clear_pages);
-EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
-EXPORT_SYMBOL(DMA_MODE_READ);
-EXPORT_SYMBOL(DMA_MODE_WRITE);
+EXPORT_SYMBOL(empty_zero_page);
 
-EXPORT_SYMBOL(transfer_to_handler);
-EXPORT_SYMBOL(do_IRQ);
-EXPORT_SYMBOL(machine_check_exception);
-EXPORT_SYMBOL(alignment_exception);
-EXPORT_SYMBOL(program_check_exception);
-EXPORT_SYMBOL(single_step_exception);
-EXPORT_SYMBOL(sys_sigreturn);
-#endif
+long long __bswapdi2(long long);
+EXPORT_SYMBOL(__bswapdi2);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
 
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
-
-#ifndef CONFIG_GENERIC_CSUM
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_generic);
-EXPORT_SYMBOL(ip_fast_csum);
-EXPORT_SYMBOL(csum_tcpudp_magic);
-#endif
-
-EXPORT_SYMBOL(__copy_tofrom_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(copy_page);
-
-#if defined(CONFIG_PCI) && defined(CONFIG_PPC32)
-EXPORT_SYMBOL(isa_io_base);
-EXPORT_SYMBOL(isa_mem_base);
-EXPORT_SYMBOL(pci_dram_offset);
-#endif /* CONFIG_PCI */
-
-EXPORT_SYMBOL(start_thread);
-
 #ifdef CONFIG_PPC_FPU
 EXPORT_SYMBOL(giveup_fpu);
 EXPORT_SYMBOL(load_fp_state);
 EXPORT_SYMBOL(store_fp_state);
 #endif
+
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
 EXPORT_SYMBOL(load_vr_state);
 EXPORT_SYMBOL(store_vr_state);
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-EXPORT_SYMBOL(giveup_vsx);
-EXPORT_SYMBOL_GPL(__giveup_vsx);
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-EXPORT_SYMBOL(giveup_spe);
-#endif /* CONFIG_SPE */
-
-#ifndef CONFIG_PPC64
-EXPORT_SYMBOL(flush_instruction_cache);
 #endif
-EXPORT_SYMBOL(flush_dcache_range);
-EXPORT_SYMBOL(flush_icache_range);
 
-#ifdef CONFIG_SMP
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(smp_hw_index);
-#endif
-#endif
-
-#ifdef CONFIG_ADB
-EXPORT_SYMBOL(adb_request);
-EXPORT_SYMBOL(adb_register);
-EXPORT_SYMBOL(adb_unregister);
-EXPORT_SYMBOL(adb_poll);
-EXPORT_SYMBOL(adb_try_handler_change);
-#endif /* CONFIG_ADB */
-#ifdef CONFIG_ADB_CUDA
-EXPORT_SYMBOL(cuda_request);
-EXPORT_SYMBOL(cuda_poll);
-#endif /* CONFIG_ADB_CUDA */
-EXPORT_SYMBOL(to_tm);
-
-#ifdef CONFIG_PPC32
-long long __ashrdi3(long long, int);
-long long __ashldi3(long long, int);
-long long __lshrdi3(long long, int);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__lshrdi3);
-int __ucmpdi2(unsigned long long, unsigned long long);
-EXPORT_SYMBOL(__ucmpdi2);
-int __cmpdi2(long long, long long);
-EXPORT_SYMBOL(__cmpdi2);
-#endif
-long long __bswapdi2(long long);
-EXPORT_SYMBOL(__bswapdi2);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memchr);
-
-#if defined(CONFIG_FB_VGA16_MODULE)
-EXPORT_SYMBOL(screen_info);
-#endif
-
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(timer_interrupt);
-EXPORT_SYMBOL(tb_ticks_per_jiffy);
-EXPORT_SYMBOL(cacheable_memcpy);
-EXPORT_SYMBOL(cacheable_memzero);
-#endif
-
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(switch_mmu_context);
-#endif
-
-#ifdef CONFIG_PPC_STD_MMU_32
-extern long mol_trampoline;
-EXPORT_SYMBOL(mol_trampoline); /* For MOL */
-EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
-#ifdef CONFIG_SMP
-extern int mmu_hash_lock;
-EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
-#endif /* CONFIG_SMP */
-extern long *intercept_table;
-EXPORT_SYMBOL(intercept_table);
-#endif /* CONFIG_PPC_STD_MMU_32 */
-#ifdef CONFIG_PPC_DCR_NATIVE
-EXPORT_SYMBOL(__mtdcr);
-EXPORT_SYMBOL(__mfdcr);
-#endif
-EXPORT_SYMBOL(empty_zero_page);
-
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(__arch_hweight8);
-EXPORT_SYMBOL(__arch_hweight16);
-EXPORT_SYMBOL(__arch_hweight32);
-EXPORT_SYMBOL(__arch_hweight64);
+#ifdef CONFIG_VSX
+EXPORT_SYMBOL_GPL(__giveup_vsx);
 #endif
 
-#ifdef CONFIG_PPC_BOOK3S_64
-EXPORT_SYMBOL_GPL(mmu_psize_defs);
+#ifdef CONFIG_SPE
+EXPORT_SYMBOL(giveup_spe);
 #endif
 
 #ifdef CONFIG_EPAPR_PARAVIRT
diff --git a/arch/powerpc/kernel/ppc_ksyms_32.c b/arch/powerpc/kernel/ppc_ksyms_32.c
new file mode 100644
index 000000000000..30ddd8a24eee
--- /dev/null
+++ b/arch/powerpc/kernel/ppc_ksyms_32.c
@@ -0,0 +1,61 @@
+#include <linux/export.h>
+#include <linux/smp.h>
+
+#include <asm/page.h>
+#include <asm/dma.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/time.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/dcr.h>
+
+EXPORT_SYMBOL(clear_pages);
+EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+
+#if defined(CONFIG_PCI)
+EXPORT_SYMBOL(isa_io_base);
+EXPORT_SYMBOL(isa_mem_base);
+EXPORT_SYMBOL(pci_dram_offset);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(smp_hw_index);
+#endif
+
+long long __ashrdi3(long long, int);
+long long __ashldi3(long long, int);
+long long __lshrdi3(long long, int);
+int __ucmpdi2(unsigned long long, unsigned long long);
+int __cmpdi2(long long, long long);
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(__ucmpdi2);
+EXPORT_SYMBOL(__cmpdi2);
+
+EXPORT_SYMBOL(timer_interrupt);
+EXPORT_SYMBOL(tb_ticks_per_jiffy);
+
+EXPORT_SYMBOL(switch_mmu_context);
+
+#ifdef CONFIG_PPC_STD_MMU_32
+extern long mol_trampoline;
+EXPORT_SYMBOL(mol_trampoline); /* For MOL */
+EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
+#ifdef CONFIG_SMP
+extern int mmu_hash_lock;
+EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
+#endif /* CONFIG_SMP */
+extern long *intercept_table;
+EXPORT_SYMBOL(intercept_table);
+#endif /* CONFIG_PPC_STD_MMU_32 */
+
+#ifdef CONFIG_PPC_DCR_NATIVE
+EXPORT_SYMBOL(__mtdcr);
+EXPORT_SYMBOL(__mfdcr);
+#endif
+
+EXPORT_SYMBOL(flush_instruction_cache);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index bf44ae962ab8..aa1df89c8b2a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -228,6 +228,7 @@ void giveup_vsx(struct task_struct *tsk)
         giveup_altivec_maybe_transactional(tsk);
         __giveup_vsx(tsk);
 }
+EXPORT_SYMBOL(giveup_vsx);
 
 void flush_vsx_to_thread(struct task_struct *tsk)
 {
@@ -1316,6 +1317,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
         current->thread.tm_tfiar = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
+EXPORT_SYMBOL(start_thread);
 
 #define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \
                 | PR_FP_EXC_RES | PR_FP_EXC_INV)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 4e139f8a69ef..099f27e6d1b0 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -386,8 +386,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
         return 0;
 }
 
-int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
-                                         int depth, void *data)
+static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
+                                                const char *uname,
+                                                int depth, void *data)
 {
         const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
@@ -641,6 +642,10 @@ void __init early_init_devtree(void *params)
 
         DBG(" -> early_init_devtree(%p)\n", params);
 
+        /* Too early to BUG_ON(), do it by hand */
+        if (!early_init_dt_verify(params))
+                panic("BUG: Failed verifying flat device tree, bad version?");
+
         /* Setup flat device-tree pointer */
         initial_boot_params = params;
 
@@ -663,14 +668,12 @@ void __init early_init_devtree(void *params)
          * device-tree, including the platform type, initrd location and
          * size, TCE reserve, and more ...
          */
-        of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line);
+        of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
 
         /* Scan memory nodes and rebuild MEMBLOCKs */
         of_scan_flat_dt(early_init_dt_scan_root, NULL);
         of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
-        /* Save command line for /proc/cmdline and then parse parameters */
-        strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
         parse_early_param();
 
         /* make sure we've parsed cmdline for mem= before this */
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index fe8e54b9ef7d..12640f7e726b 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -50,24 +50,14 @@ do
         done
 
         # ignore register save/restore funcitons
-        if [ "${UNDEF:0:9}" = "_restgpr_" ]; then
+        case $UNDEF in
+        _restgpr_*|_restgpr0_*|_rest32gpr_*)
                 OK=1
-        fi
-        if [ "${UNDEF:0:10}" = "_restgpr0_" ]; then
-                OK=1
-        fi
-        if [ "${UNDEF:0:11}" = "_rest32gpr_" ]; then
-                OK=1
-        fi
-        if [ "${UNDEF:0:9}" = "_savegpr_" ]; then
+                ;;
+        _savegpr_*|_savegpr0_*|_save32gpr_*)
                 OK=1
-        fi
-        if [ "${UNDEF:0:10}" = "_savegpr0_" ]; then
-                OK=1
-        fi
-        if [ "${UNDEF:0:11}" = "_save32gpr_" ]; then
-                OK=1
-        fi
+                ;;
+        esac
 
         if [ $OK -eq 0 ]; then
                 ERROR=1
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 2e3d2bf536c5..cdb404ea3468 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -932,7 +932,7 @@ void ptrace_triggered(struct perf_event *bp,
 }
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
-int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
+static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
                                unsigned long data)
 {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index e736387fee6a..5a2c049c1c61 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -286,7 +286,7 @@ static void prrn_work_fn(struct work_struct *work)
 
 static DECLARE_WORK(prrn_work, prrn_work_fn);
 
-void prrn_schedule_update(u32 scope)
+static void prrn_schedule_update(u32 scope)
 {
         flush_work(&prrn_work);
         prrn_update_scope = scope;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1b0e26013a62..1362cd62b3fa 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -81,8 +81,6 @@ EXPORT_SYMBOL_GPL(boot_cpuid);
 
 unsigned long klimit = (unsigned long) _end;
 
-char cmd_line[COMMAND_LINE_SIZE];
-
 /*
  * This still seems to be needed... -- paulus
  */ 
@@ -94,6 +92,9 @@ struct screen_info screen_info = {
         .orig_video_isVGA = 1,
         .orig_video_points = 16
 };
+#if defined(CONFIG_FB_VGA16_MODULE)
+EXPORT_SYMBOL(screen_info);
+#endif
 
 /* Variables required to store legacy IO irq routing */
 int of_i8042_kbd_irq;
@@ -382,7 +383,7 @@ void __init check_for_initrd(void)
                 initrd_start = initrd_end = 0;
 
         if (initrd_start)
-                printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
+                pr_info("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
 
         DBG(" <- check_for_initrd()\n");
 #endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ea4fda60e57b..07831ed0d9ef 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -268,7 +268,7 @@ static void __init exc_lvl_early_init(void)
 /* Warning, IO base is not yet inited */
 void __init setup_arch(char **cmdline_p)
 {
-        *cmdline_p = cmd_line;
+        *cmdline_p = boot_command_line;
 
         /* so udelay does something sensible, assume <= 1000 bogomips */
         loops_per_jiffy = 500000000 / HZ;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 75d62d63fe68..cd07d79ad21c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -525,21 +525,31 @@ void __init setup_system(void)
         printk("Starting Linux PPC64 %s\n", init_utsname()->version);
 
         printk("-----------------------------------------------------\n");
-        printk("ppc64_pft_size                = 0x%llx\n", ppc64_pft_size);
-        printk("physicalMemorySize            = 0x%llx\n", memblock_phys_mem_size());
+        printk("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
+        printk("phys_mem_size     = 0x%llx\n", memblock_phys_mem_size());
+
         if (ppc64_caches.dline_size != 0x80)
-                printk("ppc64_caches.dcache_line_size = 0x%x\n",
-                       ppc64_caches.dline_size);
+                printk("dcache_line_size  = 0x%x\n", ppc64_caches.dline_size);
         if (ppc64_caches.iline_size != 0x80)
-                printk("ppc64_caches.icache_line_size = 0x%x\n",
-                       ppc64_caches.iline_size);
+                printk("icache_line_size  = 0x%x\n", ppc64_caches.iline_size);
+
+        printk("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
+        printk("  possible        = 0x%016lx\n", CPU_FTRS_POSSIBLE);
+        printk("  always          = 0x%016lx\n", CPU_FTRS_ALWAYS);
+        printk("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features,
+                cur_cpu_spec->cpu_user_features2);
+        printk("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
+        printk("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+
 #ifdef CONFIG_PPC_STD_MMU_64
         if (htab_address)
-                printk("htab_address                  = 0x%p\n", htab_address);
-        printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
-#endif /* CONFIG_PPC_STD_MMU_64 */
+                printk("htab_address      = 0x%p\n", htab_address);
+
+        printk("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
+#endif
+
         if (PHYSICAL_START > 0)
-                printk("physical_start                = 0x%llx\n",
+                printk("physical_start    = 0x%llx\n",
                        (unsigned long long)PHYSICAL_START);
         printk("-----------------------------------------------------\n");
 
@@ -657,7 +667,7 @@ void __init setup_arch(char **cmdline_p)
 {
         ppc64_boot_msg(0x12, "Setup Arch");
 
-        *cmdline_p = cmd_line;
+        *cmdline_p = boot_command_line;
 
         /*
          * Set cache line size based on type of cpu as a default.
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a0738af4aba6..71e186d5f331 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -52,6 +52,7 @@
 #endif
 #include <asm/vdso.h>
 #include <asm/debug.h>
+#include <asm/kexec.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -379,8 +380,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                 /*
                  * numa_node_id() works after this.
                  */
-                set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
-                set_cpu_numa_mem(cpu, local_memory_node(numa_cpu_lookup_table[cpu]));
+                if (cpu_present(cpu)) {
+                        set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
+                        set_cpu_numa_mem(cpu,
+                                local_memory_node(numa_cpu_lookup_table[cpu]));
+                }
         }
 
         cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
@@ -728,6 +732,9 @@ void start_secondary(void *unused)
         }
         traverse_core_siblings(cpu, true);
 
+        set_numa_node(numa_cpu_lookup_table[cpu]);
+        set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
+
         smp_wmb();
         notify_cpu_starting(cpu);
         set_cpu_online(cpu, true);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 368ab374d33c..7505599c2593 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -479,7 +479,7 @@ void arch_irq_work_raise(void)
 
 #endif /* CONFIG_IRQ_WORK */
 
-void __timer_interrupt(void)
+static void __timer_interrupt(void)
 {
         struct pt_regs *regs = get_irq_regs();
         u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
@@ -643,7 +643,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
         return found;
 }
 
-void start_cpu_decrementer(void)
+static void start_cpu_decrementer(void)
 {
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
         /* Clear any pending timer interrupts */
@@ -1024,6 +1024,7 @@ void to_tm(int tim, struct rtc_time * tm)
          */
         GregorianDay(tm);
 }
+EXPORT_SYMBOL(to_tm);
 
 /*
  * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit