5 files changed, 152 insertions, 120 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 09febc582584..75c5dd0138fd 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -359,8 +359,8 @@ int main(void)
 
         DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
         DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
-        DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb));
         DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb));
+        DEFINE(VCPU_SHADOW_MOD, offsetof(struct kvm_vcpu, arch.shadow_tlb_mod));
         DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
         DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
         DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
@@ -372,7 +372,7 @@ int main(void)
         DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
         DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
         DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
-        DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid));
+        DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 
         DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
         DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index a323c9b32ee1..97e056379728 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -27,6 +27,9 @@
 #define DBG(fmt...)
 #endif
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 void __init reserve_kdump_trampoline(void)
 {
         lmb_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -66,7 +69,11 @@ void __init setup_kdump_trampoline(void)
         DBG(" <- setup_kdump_trampoline()\n");
 }
 
-#ifdef CONFIG_PROC_VMCORE
+/*
+ * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
+ * is_kdump_kernel() to determine if we are booting after a panic. Hence
+ * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
+ */
 static int __init parse_elfcorehdr(char *p)
 {
         if (p)
@@ -75,7 +82,6 @@ static int __init parse_elfcorehdr(char *p)
         return 1;
 }
 __setup("elfcorehdr=", parse_elfcorehdr);
-#endif
 
 static int __init parse_savemaxmem(char *p)
 {
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 550a19399bfa..ea1ba89f9c90 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -51,17 +51,6 @@ static int protect4gb = 1;
 
 static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);
 
-static inline unsigned long iommu_num_pages(unsigned long vaddr,
-                                            unsigned long slen)
-{
-        unsigned long npages;
-
-        npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK);
-        npages >>= IOMMU_PAGE_SHIFT;
-
-        return npages;
-}
-
 static int __init setup_protect4gb(char *str)
 {
         if (strcmp(str, "on") == 0)
@@ -325,7 +314,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 }
                 /* Allocate iommu entries for that segment */
                 vaddr = (unsigned long) sg_virt(s);
-                npages = iommu_num_pages(vaddr, slen);
+                npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE);
                 align = 0;
                 if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE &&
                     (vaddr & ~PAGE_MASK) == 0)
@@ -418,7 +407,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                         unsigned long vaddr, npages;
 
                         vaddr = s->dma_address & IOMMU_PAGE_MASK;
-                        npages = iommu_num_pages(s->dma_address, s->dma_length);
+                        npages = iommu_num_pages(s->dma_address, s->dma_length,
+                                                 IOMMU_PAGE_SIZE);
                         __iommu_free(tbl, vaddr, npages);
                         s->dma_address = DMA_ERROR_CODE;
                         s->dma_length = 0;
@@ -452,7 +442,8 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
                 if (sg->dma_length == 0)
                         break;
-                npages = iommu_num_pages(dma_handle, sg->dma_length);
+                npages = iommu_num_pages(dma_handle, sg->dma_length,
+                                         IOMMU_PAGE_SIZE);
                 __iommu_free(tbl, dma_handle, npages);
                 sg = sg_next(sg);
         }
@@ -584,7 +575,7 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl,
         BUG_ON(direction == DMA_NONE);
 
         uaddr = (unsigned long)vaddr;
-        npages = iommu_num_pages(uaddr, size);
+        npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE);
 
         if (tbl) {
                 align = 0;
@@ -617,7 +608,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
         BUG_ON(direction == DMA_NONE);
 
         if (tbl) {
-                npages = iommu_num_pages(dma_handle, size);
+                npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE);
                 iommu_free(tbl, dma_handle, npages);
         }
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 01ce8c38bae6..3815d84a1ef4 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -451,7 +451,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
                 pci_dev_put(pdev);
         }
 
-        DBG("non-PCI map for %lx, prot: %lx\n", offset, prot);
+        DBG("non-PCI map for %llx, prot: %lx\n",
+            (unsigned long long)offset, prot);
 
         return __pgprot(prot);
 }
@@ -490,6 +491,131 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
         return ret;
 }
 
+/* This provides legacy IO read access on a bus */
+int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size)
+{
+        unsigned long offset;
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        struct resource *rp = &hose->io_resource;
+        void __iomem *addr;
+
+        /* Check if port can be supported by that bus. We only check
+         * the ranges of the PHB though, not the bus itself as the rules
+         * for forwarding legacy cycles down bridges are not our problem
+         * here. So if the host bridge supports it, we do it.
+         */
+        offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+        offset += port;
+
+        if (!(rp->flags & IORESOURCE_IO))
+                return -ENXIO;
+        if (offset < rp->start || (offset + size) > rp->end)
+                return -ENXIO;
+        addr = hose->io_base_virt + port;
+
+        switch(size) {
+        case 1:
+                *((u8 *)val) = in_8(addr);
+                return 1;
+        case 2:
+                if (port & 1)
+                        return -EINVAL;
+                *((u16 *)val) = in_le16(addr);
+                return 2;
+        case 4:
+                if (port & 3)
+                        return -EINVAL;
+                *((u32 *)val) = in_le32(addr);
+                return 4;
+        }
+        return -EINVAL;
+}
+
+/* This provides legacy IO write access on a bus */
+int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size)
+{
+        unsigned long offset;
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        struct resource *rp = &hose->io_resource;
+        void __iomem *addr;
+
+        /* Check if port can be supported by that bus. We only check
+         * the ranges of the PHB though, not the bus itself as the rules
+         * for forwarding legacy cycles down bridges are not our problem
+         * here. So if the host bridge supports it, we do it.
+         */
+        offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+        offset += port;
+
+        if (!(rp->flags & IORESOURCE_IO))
+                return -ENXIO;
+        if (offset < rp->start || (offset + size) > rp->end)
+                return -ENXIO;
+        addr = hose->io_base_virt + port;
+
+        /* WARNING: The generic code is idiotic. It gets passed a pointer
+         * to what can be a 1, 2 or 4 byte quantity and always reads that
+         * as a u32, which means that we have to correct the location of
+         * the data read within those 32 bits for size 1 and 2
+         */
+        switch(size) {
+        case 1:
+                out_8(addr, val >> 24);
+                return 1;
+        case 2:
+                if (port & 1)
+                        return -EINVAL;
+                out_le16(addr, val >> 16);
+                return 2;
+        case 4:
+                if (port & 3)
+                        return -EINVAL;
+                out_le32(addr, val);
+                return 4;
+        }
+        return -EINVAL;
+}
+
+/* This provides legacy IO or memory mmap access on a bus */
+int pci_mmap_legacy_page_range(struct pci_bus *bus,
+                               struct vm_area_struct *vma,
+                               enum pci_mmap_state mmap_state)
+{
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        resource_size_t offset =
+                ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT;
+        resource_size_t size = vma->vm_end - vma->vm_start;
+        struct resource *rp;
+
+        pr_debug("pci_mmap_legacy_page_range(%04x:%02x, %s @%llx..%llx)\n",
+                 pci_domain_nr(bus), bus->number,
+                 mmap_state == pci_mmap_mem ? "MEM" : "IO",
+                 (unsigned long long)offset,
+                 (unsigned long long)(offset + size - 1));
+
+        if (mmap_state == pci_mmap_mem) {
+                if ((offset + size) > hose->isa_mem_size)
+                        return -ENXIO;
+                offset += hose->isa_mem_phys;
+        } else {
+                unsigned long io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+                unsigned long roffset = offset + io_offset;
+                rp = &hose->io_resource;
+                if (!(rp->flags & IORESOURCE_IO))
+                        return -ENXIO;
+                if (roffset < rp->start || (roffset + size) > rp->end)
+                        return -ENXIO;
+                offset += hose->io_base_phys;
+        }
+        pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset);
+
+        vma->vm_pgoff = offset >> PAGE_SHIFT;
+        vma->vm_page_prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+        return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+                               vma->vm_end - vma->vm_start,
+                               vma->vm_page_prot);
+}
+
 void pci_resource_to_user(const struct pci_dev *dev, int bar,
                           const struct resource *rsrc,
                           resource_size_t *start, resource_size_t *end)
@@ -592,6 +718,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
                 cpu_addr = of_translate_address(dev, ranges + 3);
                 size = of_read_number(ranges + pna + 3, 2);
                 ranges += np;
+
+                /* If we failed translation or got a zero-sized region
+                 * (some FW try to feed us with non sensical zero sized regions
+                 * such as power3 which look like some kind of attempt at exposing
+                 * the VGA memory hole)
+                 */
                 if (cpu_addr == OF_BAD_ADDR || size == 0)
                         continue;
 
@@ -665,6 +797,8 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
                                 isa_hole = memno;
                                 if (primary || isa_mem_base == 0)
                                         isa_mem_base = cpu_addr;
+                                hose->isa_mem_phys = cpu_addr;
+                                hose->isa_mem_size = size;
                         }
 
                         /* We get the PCI/Mem offset from the first range or
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index ff7de7b0797e..bb1cfcfdbbbb 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -61,42 +61,6 @@ asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp,
         return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x));
 }
 
-int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf)
-{
-        compat_ino_t ino;
-        long err;
-
-        if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) ||
-            !new_valid_dev(stat->rdev))
-                return -EOVERFLOW;
-
-        ino = stat->ino;
-        if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
-                return -EOVERFLOW;
-
-        err  = access_ok(VERIFY_WRITE, statbuf, sizeof(*statbuf)) ? 0 : -EFAULT;
-        err |= __put_user(new_encode_dev(stat->dev), &statbuf->st_dev);
-        err |= __put_user(ino, &statbuf->st_ino);
-        err |= __put_user(stat->mode, &statbuf->st_mode);
-        err |= __put_user(stat->nlink, &statbuf->st_nlink);
-        err |= __put_user(stat->uid, &statbuf->st_uid);
-        err |= __put_user(stat->gid, &statbuf->st_gid);
-        err |= __put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev);
-        err |= __put_user(stat->size, &statbuf->st_size);
-        err |= __put_user(stat->atime.tv_sec, &statbuf->st_atime);
-        err |= __put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec);
-        err |= __put_user(stat->mtime.tv_sec, &statbuf->st_mtime);
-        err |= __put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec);
-        err |= __put_user(stat->ctime.tv_sec, &statbuf->st_ctime);
-        err |= __put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec);
-        err |= __put_user(stat->blksize, &statbuf->st_blksize);
-        err |= __put_user(stat->blocks, &statbuf->st_blocks);
-        err |= __put_user(0, &statbuf->__unused4[0]);
-        err |= __put_user(0, &statbuf->__unused4[1]);
-
-        return err;
-}
-
 /* Note: it is necessary to treat option as an unsigned int,
  * with the corresponding cast to a signed int to insure that the 
  * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode)
@@ -107,69 +71,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2)
         return sys_sysfs((int)option, arg1, arg2);
 }
 
-static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i)
-{
-        long usec;
-
-        if (!access_ok(VERIFY_READ, i, sizeof(*i)))
-                return -EFAULT;
-        if (__get_user(o->tv_sec, &i->tv_sec))
-                return -EFAULT;
-        if (__get_user(usec, &i->tv_usec))
-                return -EFAULT;
-        o->tv_nsec = usec * 1000;
-        return 0;
-}
-
-static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i)
-{
-        return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) ||
-                (__put_user(i->tv_sec, &o->tv_sec) |
-                 __put_user(i->tv_usec, &o->tv_usec)));
-}
-
-
-
-
-/* Translations due to time_t size differences.  Which affects all
-   sorts of things, like timeval and itimerval.  */
-extern struct timezone sys_tz;
-
-asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
-{
-        if (tv) {
-                struct timeval ktv;
-                do_gettimeofday(&ktv);
-                if (put_tv32(tv, &ktv))
-                        return -EFAULT;
-        }
-        if (tz) {
-                if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
-                        return -EFAULT;
-        }
-        
-        return 0;
-}
-
-
-
-asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
-{
-        struct timespec kts;
-        struct timezone ktz;
-        
-        if (tv) {
-                if (get_ts32(&kts, tv))
-                        return -EFAULT;
-        }
-        if (tz) {
-                if (copy_from_user(&ktz, tz, sizeof(ktz)))
-                        return -EFAULT;
-        }
-
-        return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
-}
-
 #ifdef CONFIG_SYSVIPC
 long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr,
                u32 fifth)