From: Paul Mackerras Date: Mon, 14 Nov 2005 06:30:17 +0000 (+1100) Subject: powerpc: Move most remaining ppc64 files over to arch/powerpc X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=7568cb4ef6c507164b65b01f972a3bd026898ae1;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git powerpc: Move most remaining ppc64 files over to arch/powerpc Also deletes files in arch/ppc64 that are no longer used now that we don't compile with ARCH=ppc64 any more. Signed-off-by: Paul Mackerras --- diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c523029674e6..c5c3f4213cd9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -932,6 +932,7 @@ source "arch/powerpc/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" + depends on PPC64 help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 046b4bf1f21e..4970e3721a84 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,12 +49,23 @@ extra-y += vmlinux.lds obj-y += process.o init_task.o time.o \ prom.o traps.o setup-common.o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o misc_32.o systbl.o -obj-$(CONFIG_PPC64) += misc_64.o +obj-$(CONFIG_PPC64) += misc_64.o dma_64.o iommu.o obj-$(CONFIG_PPC_OF) += prom_init.o obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o obj-$(CONFIG_6xx) += idle_6xx.o obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_KPROBES) += kprobes.o + +module-$(CONFIG_PPC64) += module_64.o +obj-$(CONFIG_MODULES) += $(module-y) + +pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o pci_iommu.o \ + pci_direct_iommu.o iomap.o +obj-$(CONFIG_PCI) += $(pci64-y) + +kexec64-$(CONFIG_PPC64) += machine_kexec_64.o +obj-$(CONFIG_KEXEC) += $(kexec64-y) ifeq ($(CONFIG_PPC_ISERIES),y) $(obj)/head_64.o: $(obj)/lparmap.s @@ -62,11 +73,8 @@ AFLAGS_head_64.o += -I$(obj) endif else -# stuff used from here for ARCH=ppc or ARCH=ppc64 +# stuff used from here for ARCH=ppc smpobj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_PPC64) += traps.o process.o init_task.o time.o \ - setup-common.o $(smpobj-y) - endif diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c new file mode 100644 index 000000000000..7c3419656ccc --- /dev/null +++ b/arch/powerpc/kernel/dma_64.c @@ -0,0 +1,151 @@ +/* + * Copyright (C) 2004 IBM Corporation + * + * Implements the generic device dma API for ppc64. Handles + * the pci and vio busses + */ + +#include +#include +/* Include the busses we support */ +#include +#include +#include +#include + +static struct dma_mapping_ops *get_dma_ops(struct device *dev) +{ +#ifdef CONFIG_PCI + if (dev->bus == &pci_bus_type) + return &pci_dma_ops; +#endif +#ifdef CONFIG_IBMVIO + if (dev->bus == &vio_bus_type) + return &vio_dma_ops; +#endif + return NULL; +} + +int dma_supported(struct device *dev, u64 mask) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + return dma_ops->dma_supported(dev, mask); + BUG(); + return 0; +} +EXPORT_SYMBOL(dma_supported); + +int dma_set_mask(struct device *dev, u64 dma_mask) +{ +#ifdef CONFIG_PCI + if (dev->bus == &pci_bus_type) + return pci_set_dma_mask(to_pci_dev(dev), dma_mask); +#endif +#ifdef CONFIG_IBMVIO + if (dev->bus == &vio_bus_type) + return -EIO; +#endif /* CONFIG_IBMVIO */ + BUG(); + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + +void *dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + return dma_ops->alloc_coherent(dev, size, dma_handle, flag); + BUG(); + return NULL; +} +EXPORT_SYMBOL(dma_alloc_coherent); + +void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); + else + BUG(); +} +EXPORT_SYMBOL(dma_free_coherent); + +dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + return dma_ops->map_single(dev, cpu_addr, size, direction); + BUG(); + return (dma_addr_t)0; +} +EXPORT_SYMBOL(dma_map_single); + +void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + dma_ops->unmap_single(dev, dma_addr, size, direction); + else + BUG(); +} +EXPORT_SYMBOL(dma_unmap_single); + +dma_addr_t dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + return dma_ops->map_single(dev, + (page_address(page) + offset), size, direction); + BUG(); + return (dma_addr_t)0; +} +EXPORT_SYMBOL(dma_map_page); + +void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + dma_ops->unmap_single(dev, dma_address, size, direction); + else + BUG(); +} +EXPORT_SYMBOL(dma_unmap_page); + +int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + return dma_ops->map_sg(dev, sg, nents, direction); + BUG(); + return 0; +} +EXPORT_SYMBOL(dma_map_sg); + +void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops) + dma_ops->unmap_sg(dev, sg, nhwentries, direction); + else + BUG(); +} +EXPORT_SYMBOL(dma_unmap_sg); diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c new file mode 100644 index 000000000000..6160c8dbb7c5 --- /dev/null +++ b/arch/powerpc/kernel/iomap.c @@ -0,0 +1,146 @@ +/* + * arch/ppc64/kernel/iomap.c + * + * ppc64 "iomap" interface implementation. + * + * (C) Copyright 2004 Linus Torvalds + */ +#include +#include +#include +#include + +/* + * Here comes the ppc64 implementation of the IOMAP + * interfaces. + */ +unsigned int fastcall ioread8(void __iomem *addr) +{ + return readb(addr); +} +unsigned int fastcall ioread16(void __iomem *addr) +{ + return readw(addr); +} +unsigned int fastcall ioread16be(void __iomem *addr) +{ + return in_be16(addr); +} +unsigned int fastcall ioread32(void __iomem *addr) +{ + return readl(addr); +} +unsigned int fastcall ioread32be(void __iomem *addr) +{ + return in_be32(addr); +} +EXPORT_SYMBOL(ioread8); +EXPORT_SYMBOL(ioread16); +EXPORT_SYMBOL(ioread16be); +EXPORT_SYMBOL(ioread32); +EXPORT_SYMBOL(ioread32be); + +void fastcall iowrite8(u8 val, void __iomem *addr) +{ + writeb(val, addr); +} +void fastcall iowrite16(u16 val, void __iomem *addr) +{ + writew(val, addr); +} +void fastcall iowrite16be(u16 val, void __iomem *addr) +{ + out_be16(addr, val); +} +void fastcall iowrite32(u32 val, void __iomem *addr) +{ + writel(val, addr); +} +void fastcall iowrite32be(u32 val, void __iomem *addr) +{ + out_be32(addr, val); +} +EXPORT_SYMBOL(iowrite8); +EXPORT_SYMBOL(iowrite16); +EXPORT_SYMBOL(iowrite16be); +EXPORT_SYMBOL(iowrite32); +EXPORT_SYMBOL(iowrite32be); + +/* + * These are the "repeat read/write" functions. Note the + * non-CPU byte order. We do things in "IO byteorder" + * here. + * + * FIXME! We could make these do EEH handling if we really + * wanted. Not clear if we do. + */ +void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +{ + _insb((u8 __iomem *) addr, dst, count); +} +void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +{ + _insw_ns((u16 __iomem *) addr, dst, count); +} +void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +{ + _insl_ns((u32 __iomem *) addr, dst, count); +} +EXPORT_SYMBOL(ioread8_rep); +EXPORT_SYMBOL(ioread16_rep); +EXPORT_SYMBOL(ioread32_rep); + +void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) +{ + _outsb((u8 __iomem *) addr, src, count); +} +void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) +{ + _outsw_ns((u16 __iomem *) addr, src, count); +} +void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) +{ + _outsl_ns((u32 __iomem *) addr, src, count); +} +EXPORT_SYMBOL(iowrite8_rep); +EXPORT_SYMBOL(iowrite16_rep); +EXPORT_SYMBOL(iowrite32_rep); + +void __iomem *ioport_map(unsigned long port, unsigned int len) +{ + if (!_IO_IS_VALID(port)) + return NULL; + return (void __iomem *) (port+pci_io_base); +} + +void ioport_unmap(void __iomem *addr) +{ + /* Nothing to do */ +} +EXPORT_SYMBOL(ioport_map); +EXPORT_SYMBOL(ioport_unmap); + +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) +{ + unsigned long start = pci_resource_start(dev, bar); + unsigned long len = pci_resource_len(dev, bar); + unsigned long flags = pci_resource_flags(dev, bar); + + if (!len) + return NULL; + if (max && len > max) + len = max; + if (flags & IORESOURCE_IO) + return ioport_map(start, len); + if (flags & IORESOURCE_MEM) + return ioremap(start, len); + /* What? */ + return NULL; +} + +void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ + /* Nothing to do */ +} +EXPORT_SYMBOL(pci_iomap); +EXPORT_SYMBOL(pci_iounmap); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c new file mode 100644 index 000000000000..4d9b4388918b --- /dev/null +++ b/arch/powerpc/kernel/iommu.c @@ -0,0 +1,572 @@ +/* + * arch/ppc64/kernel/iommu.c + * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation + * + * Rewrite, cleanup, new allocation schemes, virtual merging: + * Copyright (C) 2004 Olof Johansson, IBM Corporation + * and Ben. Herrenschmidt, IBM Corporation + * + * Dynamic DMA mapping support, bus-independent parts. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DBG(...) + +#ifdef CONFIG_IOMMU_VMERGE +static int novmerge = 0; +#else +static int novmerge = 1; +#endif + +static int __init setup_iommu(char *str) +{ + if (!strcmp(str, "novmerge")) + novmerge = 1; + else if (!strcmp(str, "vmerge")) + novmerge = 0; + return 1; +} + +__setup("iommu=", setup_iommu); + +static unsigned long iommu_range_alloc(struct iommu_table *tbl, + unsigned long npages, + unsigned long *handle, + unsigned int align_order) +{ + unsigned long n, end, i, start; + unsigned long limit; + int largealloc = npages > 15; + int pass = 0; + unsigned long align_mask; + + align_mask = 0xffffffffffffffffl >> (64 - align_order); + + /* This allocator was derived from x86_64's bit string search */ + + /* Sanity check */ + if (unlikely(npages) == 0) { + if (printk_ratelimit()) + WARN_ON(1); + return DMA_ERROR_CODE; + } + + if (handle && *handle) + start = *handle; + else + start = largealloc ? tbl->it_largehint : tbl->it_hint; + + /* Use only half of the table for small allocs (15 pages or less) */ + limit = largealloc ? tbl->it_size : tbl->it_halfpoint; + + if (largealloc && start < tbl->it_halfpoint) + start = tbl->it_halfpoint; + + /* The case below can happen if we have a small segment appended + * to a large, or when the previous alloc was at the very end of + * the available space. If so, go back to the initial start. + */ + if (start >= limit) + start = largealloc ? tbl->it_largehint : tbl->it_hint; + + again: + + n = find_next_zero_bit(tbl->it_map, limit, start); + + /* Align allocation */ + n = (n + align_mask) & ~align_mask; + + end = n + npages; + + if (unlikely(end >= limit)) { + if (likely(pass < 2)) { + /* First failure, just rescan the half of the table. + * Second failure, rescan the other half of the table. + */ + start = (largealloc ^ pass) ? tbl->it_halfpoint : 0; + limit = pass ? tbl->it_size : limit; + pass++; + goto again; + } else { + /* Third failure, give up */ + return DMA_ERROR_CODE; + } + } + + for (i = n; i < end; i++) + if (test_bit(i, tbl->it_map)) { + start = i+1; + goto again; + } + + for (i = n; i < end; i++) + __set_bit(i, tbl->it_map); + + /* Bump the hint to a new block for small allocs. */ + if (largealloc) { + /* Don't bump to new block to avoid fragmentation */ + tbl->it_largehint = end; + } else { + /* Overflow will be taken care of at the next allocation */ + tbl->it_hint = (end + tbl->it_blocksize - 1) & + ~(tbl->it_blocksize - 1); + } + + /* Update handle for SG allocations */ + if (handle) + *handle = end; + + return n; +} + +static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page, + unsigned int npages, enum dma_data_direction direction, + unsigned int align_order) +{ + unsigned long entry, flags; + dma_addr_t ret = DMA_ERROR_CODE; + + spin_lock_irqsave(&(tbl->it_lock), flags); + + entry = iommu_range_alloc(tbl, npages, NULL, align_order); + + if (unlikely(entry == DMA_ERROR_CODE)) { + spin_unlock_irqrestore(&(tbl->it_lock), flags); + return DMA_ERROR_CODE; + } + + entry += tbl->it_offset; /* Offset into real TCE table */ + ret = entry << PAGE_SHIFT; /* Set the return dma address */ + + /* Put the TCEs in the HW table */ + ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & PAGE_MASK, + direction); + + + /* Flush/invalidate TLB caches if necessary */ + if (ppc_md.tce_flush) + ppc_md.tce_flush(tbl); + + spin_unlock_irqrestore(&(tbl->it_lock), flags); + + /* Make sure updates are seen by hardware */ + mb(); + + return ret; +} + +static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, + unsigned int npages) +{ + unsigned long entry, free_entry; + unsigned long i; + + entry = dma_addr >> PAGE_SHIFT; + free_entry = entry - tbl->it_offset; + + if (((free_entry + npages) > tbl->it_size) || + (entry < tbl->it_offset)) { + if (printk_ratelimit()) { + printk(KERN_INFO "iommu_free: invalid entry\n"); + printk(KERN_INFO "\tentry = 0x%lx\n", entry); + printk(KERN_INFO "\tdma_addr = 0x%lx\n", (u64)dma_addr); + printk(KERN_INFO "\tTable = 0x%lx\n", (u64)tbl); + printk(KERN_INFO "\tbus# = 0x%lx\n", (u64)tbl->it_busno); + printk(KERN_INFO "\tsize = 0x%lx\n", (u64)tbl->it_size); + printk(KERN_INFO "\tstartOff = 0x%lx\n", (u64)tbl->it_offset); + printk(KERN_INFO "\tindex = 0x%lx\n", (u64)tbl->it_index); + WARN_ON(1); + } + return; + } + + ppc_md.tce_free(tbl, entry, npages); + + for (i = 0; i < npages; i++) + __clear_bit(free_entry+i, tbl->it_map); +} + +static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, + unsigned int npages) +{ + unsigned long flags; + + spin_lock_irqsave(&(tbl->it_lock), flags); + + __iommu_free(tbl, dma_addr, npages); + + /* Make sure TLB cache is flushed if the HW needs it. We do + * not do an mb() here on purpose, it is not needed on any of + * the current platforms. + */ + if (ppc_md.tce_flush) + ppc_md.tce_flush(tbl); + + spin_unlock_irqrestore(&(tbl->it_lock), flags); +} + +int iommu_map_sg(struct device *dev, struct iommu_table *tbl, + struct scatterlist *sglist, int nelems, + enum dma_data_direction direction) +{ + dma_addr_t dma_next = 0, dma_addr; + unsigned long flags; + struct scatterlist *s, *outs, *segstart; + int outcount, incount; + unsigned long handle; + + BUG_ON(direction == DMA_NONE); + + if ((nelems == 0) || !tbl) + return 0; + + outs = s = segstart = &sglist[0]; + outcount = 1; + incount = nelems; + handle = 0; + + /* Init first segment length for backout at failure */ + outs->dma_length = 0; + + DBG("mapping %d elements:\n", nelems); + + spin_lock_irqsave(&(tbl->it_lock), flags); + + for (s = outs; nelems; nelems--, s++) { + unsigned long vaddr, npages, entry, slen; + + slen = s->length; + /* Sanity check */ + if (slen == 0) { + dma_next = 0; + continue; + } + /* Allocate iommu entries for that segment */ + vaddr = (unsigned long)page_address(s->page) + s->offset; + npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK); + npages >>= PAGE_SHIFT; + entry = iommu_range_alloc(tbl, npages, &handle, 0); + + DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); + + /* Handle failure */ + if (unlikely(entry == DMA_ERROR_CODE)) { + if (printk_ratelimit()) + printk(KERN_INFO "iommu_alloc failed, tbl %p vaddr %lx" + " npages %lx\n", tbl, vaddr, npages); + goto failure; + } + + /* Convert entry to a dma_addr_t */ + entry += tbl->it_offset; + dma_addr = entry << PAGE_SHIFT; + dma_addr |= s->offset; + + DBG(" - %lx pages, entry: %lx, dma_addr: %lx\n", + npages, entry, dma_addr); + + /* Insert into HW table */ + ppc_md.tce_build(tbl, entry, npages, vaddr & PAGE_MASK, direction); + + /* If we are in an open segment, try merging */ + if (segstart != s) { + DBG(" - trying merge...\n"); + /* We cannot merge if: + * - allocated dma_addr isn't contiguous to previous allocation + */ + if (novmerge || (dma_addr != dma_next)) { + /* Can't merge: create a new segment */ + segstart = s; + outcount++; outs++; + DBG(" can't merge, new segment.\n"); + } else { + outs->dma_length += s->length; + DBG(" merged, new len: %lx\n", outs->dma_length); + } + } + + if (segstart == s) { + /* This is a new segment, fill entries */ + DBG(" - filling new segment.\n"); + outs->dma_address = dma_addr; + outs->dma_length = slen; + } + + /* Calculate next page pointer for contiguous check */ + dma_next = dma_addr + slen; + + DBG(" - dma next is: %lx\n", dma_next); + } + + /* Flush/invalidate TLB caches if necessary */ + if (ppc_md.tce_flush) + ppc_md.tce_flush(tbl); + + spin_unlock_irqrestore(&(tbl->it_lock), flags); + + /* Make sure updates are seen by hardware */ + mb(); + + DBG("mapped %d elements:\n", outcount); + + /* For the sake of iommu_unmap_sg, we clear out the length in the + * next entry of the sglist if we didn't fill the list completely + */ + if (outcount < incount) { + outs++; + outs->dma_address = DMA_ERROR_CODE; + outs->dma_length = 0; + } + return outcount; + + failure: + for (s = &sglist[0]; s <= outs; s++) { + if (s->dma_length != 0) { + unsigned long vaddr, npages; + + vaddr = s->dma_address & PAGE_MASK; + npages = (PAGE_ALIGN(s->dma_address + s->dma_length) - vaddr) + >> PAGE_SHIFT; + __iommu_free(tbl, vaddr, npages); + } + } + spin_unlock_irqrestore(&(tbl->it_lock), flags); + return 0; +} + + +void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction) +{ + unsigned long flags; + + BUG_ON(direction == DMA_NONE); + + if (!tbl) + return; + + spin_lock_irqsave(&(tbl->it_lock), flags); + + while (nelems--) { + unsigned int npages; + dma_addr_t dma_handle = sglist->dma_address; + + if (sglist->dma_length == 0) + break; + npages = (PAGE_ALIGN(dma_handle + sglist->dma_length) + - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT; + __iommu_free(tbl, dma_handle, npages); + sglist++; + } + + /* Flush/invalidate TLBs if necessary. As for iommu_free(), we + * do not do an mb() here, the affected platforms do not need it + * when freeing. + */ + if (ppc_md.tce_flush) + ppc_md.tce_flush(tbl); + + spin_unlock_irqrestore(&(tbl->it_lock), flags); +} + +/* + * Build a iommu_table structure. This contains a bit map which + * is used to manage allocation of the tce space. + */ +struct iommu_table *iommu_init_table(struct iommu_table *tbl) +{ + unsigned long sz; + static int welcomed = 0; + + /* Set aside 1/4 of the table for large allocations. */ + tbl->it_halfpoint = tbl->it_size * 3 / 4; + + /* number of bytes needed for the bitmap */ + sz = (tbl->it_size + 7) >> 3; + + tbl->it_map = (unsigned long *)__get_free_pages(GFP_ATOMIC, get_order(sz)); + if (!tbl->it_map) + panic("iommu_init_table: Can't allocate %ld bytes\n", sz); + + memset(tbl->it_map, 0, sz); + + tbl->it_hint = 0; + tbl->it_largehint = tbl->it_halfpoint; + spin_lock_init(&tbl->it_lock); + + /* Clear the hardware table in case firmware left allocations in it */ + ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); + + if (!welcomed) { + printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", + novmerge ? "disabled" : "enabled"); + welcomed = 1; + } + + return tbl; +} + +void iommu_free_table(struct device_node *dn) +{ + struct pci_dn *pdn = dn->data; + struct iommu_table *tbl = pdn->iommu_table; + unsigned long bitmap_sz, i; + unsigned int order; + + if (!tbl || !tbl->it_map) { + printk(KERN_ERR "%s: expected TCE map for %s\n", __FUNCTION__, + dn->full_name); + return; + } + + /* verify that table contains no entries */ + /* it_size is in entries, and we're examining 64 at a time */ + for (i = 0; i < (tbl->it_size/64); i++) { + if (tbl->it_map[i] != 0) { + printk(KERN_WARNING "%s: Unexpected TCEs for %s\n", + __FUNCTION__, dn->full_name); + break; + } + } + + /* calculate bitmap size in bytes */ + bitmap_sz = (tbl->it_size + 7) / 8; + + /* free bitmap */ + order = get_order(bitmap_sz); + free_pages((unsigned long) tbl->it_map, order); + + /* free table */ + kfree(tbl); +} + +/* Creates TCEs for a user provided buffer. The user buffer must be + * contiguous real kernel storage (not vmalloc). The address of the buffer + * passed here is the kernel (virtual) address of the buffer. The buffer + * need not be page aligned, the dma_addr_t returned will point to the same + * byte within the page as vaddr. + */ +dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr, + size_t size, enum dma_data_direction direction) +{ + dma_addr_t dma_handle = DMA_ERROR_CODE; + unsigned long uaddr; + unsigned int npages; + + BUG_ON(direction == DMA_NONE); + + uaddr = (unsigned long)vaddr; + npages = PAGE_ALIGN(uaddr + size) - (uaddr & PAGE_MASK); + npages >>= PAGE_SHIFT; + + if (tbl) { + dma_handle = iommu_alloc(tbl, vaddr, npages, direction, 0); + if (dma_handle == DMA_ERROR_CODE) { + if (printk_ratelimit()) { + printk(KERN_INFO "iommu_alloc failed, " + "tbl %p vaddr %p npages %d\n", + tbl, vaddr, npages); + } + } else + dma_handle |= (uaddr & ~PAGE_MASK); + } + + return dma_handle; +} + +void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, + size_t size, enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + + if (tbl) + iommu_free(tbl, dma_handle, (PAGE_ALIGN(dma_handle + size) - + (dma_handle & PAGE_MASK)) >> PAGE_SHIFT); +} + +/* Allocates a contiguous real buffer and creates mappings over it. + * Returns the virtual address of the buffer and sets dma_handle + * to the dma address (mapping) of the first page. + */ +void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + void *ret = NULL; + dma_addr_t mapping; + unsigned int npages, order; + + size = PAGE_ALIGN(size); + npages = size >> PAGE_SHIFT; + order = get_order(size); + + /* + * Client asked for way too much space. This is checked later + * anyway. It is easier to debug here for the drivers than in + * the tce tables. + */ + if (order >= IOMAP_MAX_ORDER) { + printk("iommu_alloc_consistent size too large: 0x%lx\n", size); + return NULL; + } + + if (!tbl) + return NULL; + + /* Alloc enough pages (and possibly more) */ + ret = (void *)__get_free_pages(flag, order); + if (!ret) + return NULL; + memset(ret, 0, size); + + /* Set up tces to cover the allocated range */ + mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL, order); + if (mapping == DMA_ERROR_CODE) { + free_pages((unsigned long)ret, order); + ret = NULL; + } else + *dma_handle = mapping; + return ret; +} + +void iommu_free_coherent(struct iommu_table *tbl, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + unsigned int npages; + + if (tbl) { + size = PAGE_ALIGN(size); + npages = size >> PAGE_SHIFT; + iommu_free(tbl, dma_handle, npages); + free_pages((unsigned long)vaddr, get_order(size)); + } +} diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c new file mode 100644 index 000000000000..511af54e6230 --- /dev/null +++ b/arch/powerpc/kernel/kprobes.c @@ -0,0 +1,459 @@ +/* + * Kernel Probes (KProbes) + * arch/ppc64/kernel/kprobes.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * 2002-Oct Created by Vamsi Krishna S Kernel + * Probes initial implementation ( includes contributions from + * Rusty Russell). + * 2004-July Suparna Bhattacharya added jumper probes + * interface to access function arguments. + * 2004-Nov Ananth N Mavinakayanahalli kprobes port + * for PPC64 + */ + +#include +#include +#include +#include +#include +#include +#include + +static DECLARE_MUTEX(kprobe_mutex); +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + int ret = 0; + kprobe_opcode_t insn = *p->addr; + + if ((unsigned long)p->addr & 0x03) { + printk("Attempt to register kprobe at an unaligned address\n"); + ret = -EINVAL; + } else if (IS_MTMSRD(insn) || IS_RFID(insn)) { + printk("Cannot register a kprobe on rfid or mtmsrd\n"); + ret = -EINVAL; + } + + /* insn must be on a special executable page on ppc64 */ + if (!ret) { + down(&kprobe_mutex); + p->ainsn.insn = get_insn_slot(); + up(&kprobe_mutex); + if (!p->ainsn.insn) + ret = -ENOMEM; + } + return ret; +} + +void __kprobes arch_copy_kprobe(struct kprobe *p) +{ + memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + p->opcode = *p->addr; +} + +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + *p->addr = BREAKPOINT_INSTRUCTION; + flush_icache_range((unsigned long) p->addr, + (unsigned long) p->addr + sizeof(kprobe_opcode_t)); +} + +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + *p->addr = p->opcode; + flush_icache_range((unsigned long) p->addr, + (unsigned long) p->addr + sizeof(kprobe_opcode_t)); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + down(&kprobe_mutex); + free_insn_slot(p->ainsn.insn); + up(&kprobe_mutex); +} + +static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = *p->ainsn.insn; + + regs->msr |= MSR_SE; + + /* single step inline if it is a trap variant */ + if (is_trap(insn)) + regs->nip = (unsigned long)p->addr; + else + regs->nip = (unsigned long)p->ainsn.insn; +} + +static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; + kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr; +} + +static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr; +} + +static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + __get_cpu_var(current_kprobe) = p; + kcb->kprobe_saved_msr = regs->msr; +} + +/* Called with kretprobe_lock held */ +void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) +{ + struct kretprobe_instance *ri; + + if ((ri = get_free_rp_inst(rp)) != NULL) { + ri->rp = rp; + ri->task = current; + ri->ret_addr = (kprobe_opcode_t *)regs->link; + + /* Replace the return addr with trampoline addr */ + regs->link = (unsigned long)kretprobe_trampoline; + add_rp_inst(ri); + } else { + rp->nmissed++; + } +} + +static inline int kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *p; + int ret = 0; + unsigned int *addr = (unsigned int *)regs->nip; + struct kprobe_ctlblk *kcb; + + /* + * We don't want to be preempted for the entire + * duration of kprobe processing + */ + preempt_disable(); + kcb = get_kprobe_ctlblk(); + + /* Check we're not actually recursing */ + if (kprobe_running()) { + p = get_kprobe(addr); + if (p) { + kprobe_opcode_t insn = *p->ainsn.insn; + if (kcb->kprobe_status == KPROBE_HIT_SS && + is_trap(insn)) { + regs->msr &= ~MSR_SE; + regs->msr |= kcb->kprobe_saved_msr; + goto no_kprobe; + } + /* We have reentered the kprobe_handler(), since + * another probe was hit while within the handler. + * We here save the original kprobes variables and + * just single step on the instruction of the new probe + * without calling any user handlers. + */ + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_saved_msr = regs->msr; + p->nmissed++; + prepare_singlestep(p, regs); + kcb->kprobe_status = KPROBE_REENTER; + return 1; + } else { + p = __get_cpu_var(current_kprobe); + if (p->break_handler && p->break_handler(p, regs)) { + goto ss_probe; + } + } + goto no_kprobe; + } + + p = get_kprobe(addr); + if (!p) { + if (*addr != BREAKPOINT_INSTRUCTION) { + /* + * PowerPC has multiple variants of the "trap" + * instruction. If the current instruction is a + * trap variant, it could belong to someone else + */ + kprobe_opcode_t cur_insn = *addr; + if (is_trap(cur_insn)) + goto no_kprobe; + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + */ + ret = 1; + } + /* Not one of ours: let kernel handle it */ + goto no_kprobe; + } + + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + set_current_kprobe(p, regs, kcb); + if (p->pre_handler && p->pre_handler(p, regs)) + /* handler has already set things up, so skip ss setup */ + return 1; + +ss_probe: + prepare_singlestep(p, regs); + kcb->kprobe_status = KPROBE_HIT_SS; + return 1; + +no_kprobe: + preempt_enable_no_resched(); + return ret; +} + +/* + * Function return probe trampoline: + * - init_kprobes() establishes a probepoint here + * - When the probed function returns, this probe + * causes the handlers to fire + */ +void kretprobe_trampoline_holder(void) +{ + asm volatile(".global kretprobe_trampoline\n" + "kretprobe_trampoline:\n" + "nop\n"); +} + +/* + * Called when the probe at kretprobe trampoline is hit + */ +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kretprobe_instance *ri = NULL; + struct hlist_head *head; + struct hlist_node *node, *tmp; + unsigned long flags, orig_ret_address = 0; + unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; + + spin_lock_irqsave(&kretprobe_lock, flags); + head = kretprobe_inst_table_head(current); + + /* + * It is possible to have multiple instances associated with a given + * task either because an multiple functions in the call path + * have a return probe installed on them, and/or more then one return + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always inserted at the head of the list + * - when multiple return probes are registered for the same + * function, the first instance's ret_addr will point to the + * real return address, and all the rest will point to + * kretprobe_trampoline + */ + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + if (ri->rp && ri->rp->handler) + ri->rp->handler(ri, regs); + + orig_ret_address = (unsigned long)ri->ret_addr; + recycle_rp_inst(ri); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); + regs->nip = orig_ret_address; + + reset_current_kprobe(); + spin_unlock_irqrestore(&kretprobe_lock, flags); + preempt_enable_no_resched(); + + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we don't want the post_handler + * to run (and have re-enabled preemption) + */ + return 1; +} + +/* + * Called after single-stepping. p->addr is the address of the + * instruction whose first byte has been replaced by the "breakpoint" + * instruction. To avoid the SMP problems that can occur when we + * temporarily put back the original opcode to single-step, we + * single-stepped a copy of the instruction. The address of this + * copy is p->ainsn.insn. + */ +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) +{ + int ret; + unsigned int insn = *p->ainsn.insn; + + regs->nip = (unsigned long)p->addr; + ret = emulate_step(regs, insn); + if (ret == 0) + regs->nip = (unsigned long)p->addr + 4; +} + +static inline int post_kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (!cur) + return 0; + + if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + cur->post_handler(cur, regs, 0); + } + + resume_execution(cur, regs); + regs->msr |= kcb->kprobe_saved_msr; + + /*Restore back the original saved kprobes variables and continue. */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + goto out; + } + reset_current_kprobe(); +out: + preempt_enable_no_resched(); + + /* + * if somebody else is singlestepping across a probe point, msr + * will have SE set, in which case, continue the remaining processing + * of do_debug, as if this is not a probe hit. + */ + if (regs->msr & MSR_SE) + return 0; + + return 1; +} + +static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + if (kcb->kprobe_status & KPROBE_HIT_SS) { + resume_execution(cur, regs); + regs->msr &= ~MSR_SE; + regs->msr |= kcb->kprobe_saved_msr; + + reset_current_kprobe(); + preempt_enable_no_resched(); + } + return 0; +} + +/* + * Wrapper routine to for handling exceptions. + */ +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct die_args *args = (struct die_args *)data; + int ret = NOTIFY_DONE; + + switch (val) { + case DIE_BPT: + if (kprobe_handler(args->regs)) + ret = NOTIFY_STOP; + break; + case DIE_SSTEP: + if (post_kprobe_handler(args->regs)) + ret = NOTIFY_STOP; + break; + case DIE_PAGE_FAULT: + /* kprobe_running() needs smp_processor_id() */ + preempt_disable(); + if (kprobe_running() && + kprobe_fault_handler(args->regs, args->trapnr)) + ret = NOTIFY_STOP; + preempt_enable(); + break; + default: + break; + } + return ret; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); + + /* setup return addr to the jprobe handler routine */ + regs->nip = (unsigned long)(((func_descr_t *)jp->entry)->entry); + regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); + + return 1; +} + +void __kprobes jprobe_return(void) +{ + asm volatile("trap" ::: "memory"); +} + +void __kprobes jprobe_return_end(void) +{ +}; + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + /* + * FIXME - we should ideally be validating that we got here 'cos + * of the "trap" in jprobe_return() above, before restoring the + * saved regs... + */ + memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); + preempt_enable_no_resched(); + return 1; +} + +static struct kprobe trampoline_p = { + .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .pre_handler = trampoline_probe_handler +}; + +int __init arch_init_kprobes(void) +{ + return register_kprobe(&trampoline_p); +} diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c new file mode 100644 index 000000000000..97c51e452be7 --- /dev/null +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -0,0 +1,358 @@ +/* + * machine_kexec.c - handle transition of Linux booting another kernel + * + * Copyright (C) 2004-2005, IBM Corp. + * + * Created by: Milton D Miller II + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include /* _end */ +#include +#include + +#define HASH_GROUP_SIZE 0x80 /* size of each hash group, asm/mmu.h */ + +/* Have this around till we move it into crash specific file */ +note_buf_t crash_notes[NR_CPUS]; + +/* Dummy for now. Not sure if we need to have a crash shutdown in here + * and if what it will achieve. Letting it be now to compile the code + * in generic kexec environment + */ +void machine_crash_shutdown(struct pt_regs *regs) +{ + /* do nothing right now */ + /* smp_relase_cpus() if we want smp on panic kernel */ + /* cpu_irq_down to isolate us until we are ready */ +} + +int machine_kexec_prepare(struct kimage *image) +{ + int i; + unsigned long begin, end; /* limits of segment */ + unsigned long low, high; /* limits of blocked memory range */ + struct device_node *node; + unsigned long *basep; + unsigned int *sizep; + + if (!ppc_md.hpte_clear_all) + return -ENOENT; + + /* + * Since we use the kernel fault handlers and paging code to + * handle the virtual mode, we must make sure no destination + * overlaps kernel static data or bss. + */ + for (i = 0; i < image->nr_segments; i++) + if (image->segment[i].mem < __pa(_end)) + return -ETXTBSY; + + /* + * For non-LPAR, we absolutely can not overwrite the mmu hash + * table, since we are still using the bolted entries in it to + * do the copy. Check that here. + * + * It is safe if the end is below the start of the blocked + * region (end <= low), or if the beginning is after the + * end of the blocked region (begin >= high). Use the + * boolean identity !(a || b) === (!a && !b). + */ + if (htab_address) { + low = __pa(htab_address); + high = low + (htab_hash_mask + 1) * HASH_GROUP_SIZE; + + for (i = 0; i < image->nr_segments; i++) { + begin = image->segment[i].mem; + end = begin + image->segment[i].memsz; + + if ((begin < high) && (end > low)) + return -ETXTBSY; + } + } + + /* We also should not overwrite the tce tables */ + for (node = of_find_node_by_type(NULL, "pci"); node != NULL; + node = of_find_node_by_type(node, "pci")) { + basep = (unsigned long *)get_property(node, "linux,tce-base", + NULL); + sizep = (unsigned int *)get_property(node, "linux,tce-size", + NULL); + if (basep == NULL || sizep == NULL) + continue; + + low = *basep; + high = low + (*sizep); + + for (i = 0; i < image->nr_segments; i++) { + begin = image->segment[i].mem; + end = begin + image->segment[i].memsz; + + if ((begin < high) && (end > low)) + return -ETXTBSY; + } + } + + return 0; +} + +void machine_kexec_cleanup(struct kimage *image) +{ + /* we do nothing in prepare that needs to be undone */ +} + +#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE) + +static void copy_segments(unsigned long ind) +{ + unsigned long entry; + unsigned long *ptr; + void *dest; + void *addr; + + /* + * We rely on kexec_load to create a lists that properly + * initializes these pointers before they are used. + * We will still crash if the list is wrong, but at least + * the compiler will be quiet. + */ + ptr = NULL; + dest = NULL; + + for (entry = ind; !(entry & IND_DONE); entry = *ptr++) { + addr = __va(entry & PAGE_MASK); + + switch (entry & IND_FLAGS) { + case IND_DESTINATION: + dest = addr; + break; + case IND_INDIRECTION: + ptr = addr; + break; + case IND_SOURCE: + copy_page(dest, addr); + dest += PAGE_SIZE; + } + } +} + +void kexec_copy_flush(struct kimage *image) +{ + long i, nr_segments = image->nr_segments; + struct kexec_segment ranges[KEXEC_SEGMENT_MAX]; + + /* save the ranges on the stack to efficiently flush the icache */ + memcpy(ranges, image->segment, sizeof(ranges)); + + /* + * After this call we may not use anything allocated in dynamic + * memory, including *image. + * + * Only globals and the stack are allowed. + */ + copy_segments(image->head); + + /* + * we need to clear the icache for all dest pages sometime, + * including ones that were in place on the original copy + */ + for (i = 0; i < nr_segments; i++) + flush_icache_range(ranges[i].mem + KERNELBASE, + ranges[i].mem + KERNELBASE + + ranges[i].memsz); +} + +#ifdef CONFIG_SMP + +/* FIXME: we should schedule this function to be called on all cpus based + * on calling the interrupts, but we would like to call it off irq level + * so that the interrupt controller is clean. + */ +void kexec_smp_down(void *arg) +{ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 1); + + local_irq_disable(); + kexec_smp_wait(); + /* NOTREACHED */ +} + +static void kexec_prepare_cpus(void) +{ + int my_cpu, i, notified=-1; + + smp_call_function(kexec_smp_down, NULL, 0, /* wait */0); + my_cpu = get_cpu(); + + /* check the others cpus are now down (via paca hw cpu id == -1) */ + for (i=0; i < NR_CPUS; i++) { + if (i == my_cpu) + continue; + + while (paca[i].hw_cpu_id != -1) { + barrier(); + if (!cpu_possible(i)) { + printk("kexec: cpu %d hw_cpu_id %d is not" + " possible, ignoring\n", + i, paca[i].hw_cpu_id); + break; + } + if (!cpu_online(i)) { + /* Fixme: this can be spinning in + * pSeries_secondary_wait with a paca + * waiting for it to go online. + */ + printk("kexec: cpu %d hw_cpu_id %d is not" + " online, ignoring\n", + i, paca[i].hw_cpu_id); + break; + } + if (i != notified) { + printk( "kexec: waiting for cpu %d (physical" + " %d) to go down\n", + i, paca[i].hw_cpu_id); + notified = i; + } + } + } + + /* after we tell the others to go down */ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + + put_cpu(); + + local_irq_disable(); +} + +#else /* ! SMP */ + +static void kexec_prepare_cpus(void) +{ + /* + * move the secondarys to us so that we can copy + * the new kernel 0-0x100 safely + * + * do this if kexec in setup.c ? + * + * We need to release the cpus if we are ever going from an + * UP to an SMP kernel. + */ + smp_release_cpus(); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + local_irq_disable(); +} + +#endif /* SMP */ + +/* + * kexec thread structure and stack. + * + * We need to make sure that this is 16384-byte aligned due to the + * way process stacks are handled. It also must be statically allocated + * or allocated as part of the kimage, because everything else may be + * overwritten when we copy the kexec image. We piggyback on the + * "init_task" linker section here to statically allocate a stack. + * + * We could use a smaller stack if we don't care about anything using + * current, but that audit has not been performed. + */ +union thread_union kexec_stack + __attribute__((__section__(".data.init_task"))) = { }; + +/* Our assembly helper, in kexec_stub.S */ +extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start, + void *image, void *control, + void (*clear_all)(void)) ATTRIB_NORET; + +/* too late to fail here */ +void machine_kexec(struct kimage *image) +{ + + /* prepare control code if any */ + + /* shutdown other cpus into our wait loop and quiesce interrupts */ + kexec_prepare_cpus(); + + /* switch to a staticly allocated stack. Based on irq stack code. + * XXX: the task struct will likely be invalid once we do the copy! + */ + kexec_stack.thread_info.task = current_thread_info()->task; + kexec_stack.thread_info.flags = 0; + + /* Some things are best done in assembly. Finding globals with + * a toc is easier in C, so pass in what we can. + */ + kexec_sequence(&kexec_stack, image->start, image, + page_address(image->control_code_page), + ppc_md.hpte_clear_all); + /* NOTREACHED */ +} + +/* Values we need to export to the second kernel via the device tree. */ +static unsigned long htab_base, htab_size, kernel_end; + +static struct property htab_base_prop = { + .name = "linux,htab-base", + .length = sizeof(unsigned long), + .value = (unsigned char *)&htab_base, +}; + +static struct property htab_size_prop = { + .name = "linux,htab-size", + .length = sizeof(unsigned long), + .value = (unsigned char *)&htab_size, +}; + +static struct property kernel_end_prop = { + .name = "linux,kernel-end", + .length = sizeof(unsigned long), + .value = (unsigned char *)&kernel_end, +}; + +static void __init export_htab_values(void) +{ + struct device_node *node; + + node = of_find_node_by_path("/chosen"); + if (!node) + return; + + kernel_end = __pa(_end); + prom_add_property(node, &kernel_end_prop); + + /* On machines with no htab htab_address is NULL */ + if (NULL == htab_address) + goto out; + + htab_base = __pa(htab_address); + prom_add_property(node, &htab_base_prop); + + htab_size = 1UL << ppc64_pft_size; + prom_add_property(node, &htab_size_prop); + + out: + of_node_put(node); +} + +void __init kexec_setup(void) +{ + export_htab_values(); +} diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c new file mode 100644 index 000000000000..928b8581fcb0 --- /dev/null +++ b/arch/powerpc/kernel/module_64.c @@ -0,0 +1,455 @@ +/* Kernel module help for PPC64. + Copyright (C) 2001, 2003 Rusty Russell IBM Corporation. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include +#include + +/* FIXME: We don't do .init separately. To do this, we'd need to have + a separate r2 value in the init and core section, and stub between + them, too. + + 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 + +/* There's actually a third entry here, but it's unused */ +struct ppc64_opd_entry +{ + unsigned long funcaddr; + unsigned long r2; +}; + +/* Like PPC32, we need little trampolines to do > 24-bit jumps (into + the kernel itself). But on PPC64, these need to be used for every + jump, actually, to reset r2 (TOC+0x8000). */ +struct ppc64_stub_entry +{ + /* 28 byte jump instruction sequence (7 instructions) */ + unsigned char jump[28]; + unsigned char unused[4]; + /* Data for the above code */ + struct ppc64_opd_entry opd; +}; + +/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external) + function which may be more than 24-bits away. We could simply + patch the new r2 value and function pointer into the stub, but it's + significantly shorter to put these values at the end of the stub + code, and patch the stub address (32-bits relative to the TOC ptr, + r2) into the stub. */ +static struct ppc64_stub_entry ppc64_stub = +{ .jump = { + 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, */ + 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, */ + /* Save current r2 value in magic place on the stack. */ + 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */ + 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */ + 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ + 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ + 0x4e, 0x80, 0x04, 0x20 /* bctr */ +} }; + +/* Count how many different 24-bit relocations (different symbol, + different addend) */ +static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num) +{ + unsigned int i, j, ret = 0; + + /* FIXME: Only count external ones --RR */ + /* Sure, this is order(n^2), but it's usually short, and not + time critical */ + for (i = 0; i < num; i++) { + /* Only count 24-bit relocs, others don't need stubs */ + if (ELF64_R_TYPE(rela[i].r_info) != R_PPC_REL24) + continue; + for (j = 0; j < i; j++) { + /* If this addend appeared before, it's + already been counted */ + if (rela[i].r_info == rela[j].r_info + && rela[i].r_addend == rela[j].r_addend) + break; + } + if (j == i) ret++; + } + return ret; +} + +void *module_alloc(unsigned long size) +{ + if (size == 0) + return NULL; + + return vmalloc_exec(size); +} + +/* Free memory returned from module_alloc */ +void module_free(struct module *mod, void *module_region) +{ + vfree(module_region); + /* FIXME: If module_region == mod->init_region, trim exception + table entries. */ +} + +/* Get size of potential trampolines required. */ +static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, + const Elf64_Shdr *sechdrs) +{ + /* One extra reloc so it's always 0-funcaddr terminated */ + unsigned long relocs = 1; + unsigned i; + + /* 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", + (void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size / sizeof(Elf64_Rela)); + relocs += count_relocs((void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size + / sizeof(Elf64_Rela)); + } + } + + DEBUGP("Looks like a total of %lu stubs, max\n", relocs); + return relocs * sizeof(struct ppc64_stub_entry); +} + +static void dedotify_versions(struct modversion_info *vers, + unsigned long size) +{ + struct modversion_info *end; + + for (end = (void *)vers + size; vers < end; vers++) + if (vers->name[0] == '.') + memmove(vers->name, vers->name+1, strlen(vers->name)); +} + +/* Undefined symbols which refer to .funcname, hack to funcname */ +static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) +{ + unsigned int i; + + for (i = 1; i < numsyms; i++) { + if (syms[i].st_shndx == SHN_UNDEF) { + char *name = strtab + syms[i].st_name; + if (name[0] == '.') + memmove(name, name+1, strlen(name)); + } + } +} + +int module_frob_arch_sections(Elf64_Ehdr *hdr, + Elf64_Shdr *sechdrs, + char *secstrings, + struct module *me) +{ + unsigned int i; + + /* Find .toc and .stubs sections, symtab and strtab */ + for (i = 1; i < hdr->e_shnum; i++) { + char *p; + if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) + me->arch.stubs_section = i; + else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) + me->arch.toc_section = i; + else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0) + dedotify_versions((void *)hdr + sechdrs[i].sh_offset, + sechdrs[i].sh_size); + + /* We don't handle .init for the moment: rename to _init */ + while ((p = strstr(secstrings + sechdrs[i].sh_name, ".init"))) + p[0] = '_'; + + if (sechdrs[i].sh_type == SHT_SYMTAB) + dedotify((void *)hdr + sechdrs[i].sh_offset, + sechdrs[i].sh_size / sizeof(Elf64_Sym), + (void *)hdr + + sechdrs[sechdrs[i].sh_link].sh_offset); + } + if (!me->arch.stubs_section || !me->arch.toc_section) { + printk("%s: doesn't contain .toc or .stubs.\n", me->name); + return -ENOEXEC; + } + + /* Override the stubs size */ + sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs); + return 0; +} + +int apply_relocate(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", me->name); + return -ENOEXEC; +} + +/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this + gives the value maximum span in an instruction which uses a signed + offset) */ +static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) +{ + return sechdrs[me->arch.toc_section].sh_addr + 0x8000; +} + +/* Both low and high 16 bits are added as SIGNED additions, so if low + 16 bits has high bit set, high 16 bits must be adjusted. These + macros do that (stolen from binutils). */ +#define PPC_LO(v) ((v) & 0xffff) +#define PPC_HI(v) (((v) >> 16) & 0xffff) +#define PPC_HA(v) PPC_HI ((v) + 0x8000) + +/* Patch stub to reference function and correct r2 value. */ +static inline int create_stub(Elf64_Shdr *sechdrs, + struct ppc64_stub_entry *entry, + struct ppc64_opd_entry *opd, + struct module *me) +{ + Elf64_Half *loc1, *loc2; + long reladdr; + + *entry = ppc64_stub; + + loc1 = (Elf64_Half *)&entry->jump[2]; + loc2 = (Elf64_Half *)&entry->jump[6]; + + /* 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", + me->name, (void *)reladdr, (void *)my_r2); + return 0; + } + DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr); + + *loc1 = PPC_HA(reladdr); + *loc2 = PPC_LO(reladdr); + entry->opd.funcaddr = opd->funcaddr; + entry->opd.r2 = opd->r2; + return 1; +} + +/* Create stub to jump to function described in this OPD: we need the + stub to set up the TOC ptr (r2) for the function. */ +static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, + unsigned long opdaddr, + struct module *me) +{ + struct ppc64_stub_entry *stubs; + struct ppc64_opd_entry *opd = (void *)opdaddr; + unsigned int i, num_stubs; + + num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs); + + /* Find this stub, or if that fails, the next avail. entry */ + stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; + for (i = 0; stubs[i].opd.funcaddr; i++) { + BUG_ON(i >= num_stubs); + + if (stubs[i].opd.funcaddr == opd->funcaddr) + return (unsigned long)&stubs[i]; + } + + if (!create_stub(sechdrs, &stubs[i], opd, me)) + return 0; + + return (unsigned long)&stubs[i]; +} + +/* We expect a noop next: if it is, replace it with instruction to + restore r2. */ +static int restore_r2(u32 *instruction, struct module *me) +{ + if (*instruction != 0x60000000) { + printk("%s: Expect noop after relocate, got %08x\n", + me->name, *instruction); + return 0; + } + *instruction = 0xe8410028; /* ld r2,40(r1) */ + return 1; +} + +int apply_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + unsigned int i; + Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr; + Elf64_Sym *sym; + unsigned long *location; + unsigned long value; + + DEBUGP("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 */ + location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr + + rela[i].r_offset; + /* This is the symbol it is referring to */ + 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", + location, (long)ELF64_R_TYPE(rela[i].r_info), + strtab + sym->st_name, (unsigned long)sym->st_value, + (long)rela[i].r_addend); + + /* `Everything is relative'. */ + value = sym->st_value + rela[i].r_addend; + + switch (ELF64_R_TYPE(rela[i].r_info)) { + case R_PPC64_ADDR32: + /* Simply set it */ + *(u32 *)location = value; + break; + + case R_PPC64_ADDR64: + /* Simply set it */ + *(unsigned long *)location = value; + break; + + case R_PPC64_TOC: + *(unsigned long *)location = my_r2(sechdrs, me); + break; + + case R_PPC64_TOC16: + /* Subtact TOC pointer */ + value -= my_r2(sechdrs, me); + if (value + 0x8000 > 0xffff) { + printk("%s: bad TOC16 relocation (%lu)\n", + me->name, value); + return -ENOEXEC; + } + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_TOC16_DS: + /* Subtact TOC pointer */ + value -= my_r2(sechdrs, me); + if ((value & 3) != 0 || value + 0x8000 > 0xffff) { + printk("%s: bad TOC16_DS relocation (%lu)\n", + me->name, value); + return -ENOEXEC; + } + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xfffc) + | (value & 0xfffc); + break; + + case R_PPC_REL24: + /* FIXME: Handle weak symbols here --RR */ + if (sym->st_shndx == SHN_UNDEF) { + /* External: go via stub */ + value = stub_for_addr(sechdrs, value, me); + if (!value) + return -ENOENT; + if (!restore_r2((u32 *)location + 1, me)) + return -ENOEXEC; + } + + /* Convert value to relative */ + value -= (unsigned long)location; + if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){ + printk("%s: REL24 %li out of range!\n", + me->name, (long int)value); + return -ENOEXEC; + } + + /* Only replace bits 2 through 26 */ + *(uint32_t *)location + = (*(uint32_t *)location & ~0x03fffffc) + | (value & 0x03fffffc); + break; + + default: + printk("%s: Unknown ADD relocation: %lu\n", + me->name, + (unsigned long)ELF64_R_TYPE(rela[i].r_info)); + return -ENOEXEC; + } + } + + return 0; +} + +LIST_HEAD(module_bug_list); + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, struct module *me) +{ + char *secstrings; + unsigned int i; + + me->arch.bug_table = NULL; + me->arch.num_bugs = 0; + + /* Find the __bug_table section, if present */ + secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + for (i = 1; i < hdr->e_shnum; i++) { + if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table")) + continue; + me->arch.bug_table = (void *) sechdrs[i].sh_addr; + me->arch.num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry); + break; + } + + /* + * Strictly speaking this should have a spinlock to protect against + * traversals, but since we only traverse on BUG()s, a spinlock + * could potentially lead to deadlock and thus be counter-productive. + */ + list_add(&me->arch.bug_list, &module_bug_list); + + return 0; +} + +void module_arch_cleanup(struct module *mod) +{ + list_del(&mod->arch.bug_list); +} + +struct bug_entry *module_find_bug(unsigned long bugaddr) +{ + struct mod_arch_specific *mod; + unsigned int i; + struct bug_entry *bug; + + list_for_each_entry(mod, &module_bug_list, bug_list) { + bug = mod->bug_table; + for (i = 0; i < mod->num_bugs; ++i, ++bug) + if (bugaddr == bug->bug_addr) + return bug; + } + return NULL; +} diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c new file mode 100644 index 000000000000..3cef1b8f57f0 --- /dev/null +++ b/arch/powerpc/kernel/pci_64.c @@ -0,0 +1,1319 @@ +/* + * Port for PPC64 David Engebretsen, IBM Corp. + * Contains common pci routines for ppc64 platform, pSeries and iSeries brands. + * + * Copyright (C) 2003 Anton Blanchard , IBM + * Rework, based on alpha PCI code. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#undef DEBUG + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef DEBUG +#define DBG(fmt...) udbg_printf(fmt) +#else +#define DBG(fmt...) +#endif + +unsigned long pci_probe_only = 1; +unsigned long pci_assign_all_buses = 0; + +/* + * legal IO pages under MAX_ISA_PORT. This is to ensure we don't touch + * devices we don't have access to. + */ +unsigned long io_page_mask; + +EXPORT_SYMBOL(io_page_mask); + +#ifdef CONFIG_PPC_MULTIPLATFORM +static void fixup_resource(struct resource *res, struct pci_dev *dev); +static void do_bus_setup(struct pci_bus *bus); +#endif + +unsigned int pcibios_assign_all_busses(void) +{ + return pci_assign_all_buses; +} + +/* pci_io_base -- the base address from which io bars are offsets. + * This is the lowest I/O base address (so bar values are always positive), + * and it *must* be the start of ISA space if an ISA bus exists because + * ISA drivers use hard coded offsets. If no ISA bus exists a dummy + * page is mapped and isa_io_limit prevents access to it. + */ +unsigned long isa_io_base; /* NULL if no ISA bus */ +EXPORT_SYMBOL(isa_io_base); +unsigned long pci_io_base; +EXPORT_SYMBOL(pci_io_base); + +void iSeries_pcibios_init(void); + +LIST_HEAD(hose_list); + +struct dma_mapping_ops pci_dma_ops; +EXPORT_SYMBOL(pci_dma_ops); + +int global_phb_number; /* Global phb counter */ + +/* Cached ISA bridge dev. */ +struct pci_dev *ppc64_isabridge_dev = NULL; + +static void fixup_broken_pcnet32(struct pci_dev* dev) +{ + if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) { + dev->vendor = PCI_VENDOR_ID_AMD; + pci_write_config_word(dev, PCI_VENDOR_ID, PCI_VENDOR_ID_AMD); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TRIDENT, PCI_ANY_ID, fixup_broken_pcnet32); + +void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, + struct resource *res) +{ + unsigned long offset = 0; + struct pci_controller *hose = pci_bus_to_host(dev->bus); + + if (!hose) + return; + + if (res->flags & IORESOURCE_IO) + offset = (unsigned long)hose->io_base_virt - pci_io_base; + + if (res->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; + + region->start = res->start - offset; + region->end = res->end - offset; +} + +void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + unsigned long offset = 0; + struct pci_controller *hose = pci_bus_to_host(dev->bus); + + if (!hose) + return; + + if (res->flags & IORESOURCE_IO) + offset = (unsigned long)hose->io_base_virt - pci_io_base; + + if (res->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; + + res->start = region->start + offset; + res->end = region->end + offset; +} + +#ifdef CONFIG_HOTPLUG +EXPORT_SYMBOL(pcibios_resource_to_bus); +EXPORT_SYMBOL(pcibios_bus_to_resource); +#endif + +/* + * We need to avoid collisions with `mirrored' VGA ports + * and other strange ISA hardware, so we always want the + * addresses to be allocated in the 0x000-0x0ff region + * modulo 0x400. + * + * Why? Because some silly external IO cards only decode + * the low 10 bits of the IO address. The 0x00-0xff region + * is reserved for motherboard devices that decode all 16 + * bits, so it's ok to allocate at, say, 0x2800-0x28ff, + * but we want to try to avoid allocating at 0x2900-0x2bff + * which might have be mirrored at 0x0100-0x03ff.. + */ +void pcibios_align_resource(void *data, struct resource *res, + unsigned long size, unsigned long align) +{ + struct pci_dev *dev = data; + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned long start = res->start; + unsigned long alignto; + + if (res->flags & IORESOURCE_IO) { + unsigned long offset = (unsigned long)hose->io_base_virt - + pci_io_base; + /* Make sure we start at our min on all hoses */ + if (start - offset < PCIBIOS_MIN_IO) + start = PCIBIOS_MIN_IO + offset; + + /* + * Put everything into 0x00-0xff region modulo 0x400 + */ + if (start & 0x300) + start = (start + 0x3ff) & ~0x3ff; + + } else if (res->flags & IORESOURCE_MEM) { + /* Make sure we start at our min on all hoses */ + if (start - hose->pci_mem_offset < PCIBIOS_MIN_MEM) + start = PCIBIOS_MIN_MEM + hose->pci_mem_offset; + + /* Align to multiple of size of minimum base. */ + alignto = max(0x1000UL, align); + start = ALIGN(start, alignto); + } + + res->start = start; +} + +static DEFINE_SPINLOCK(hose_spinlock); + +/* + * pci_controller(phb) initialized common variables. + */ +void __devinit pci_setup_pci_controller(struct pci_controller *hose) +{ + memset(hose, 0, sizeof(struct pci_controller)); + + spin_lock(&hose_spinlock); + hose->global_number = global_phb_number++; + list_add_tail(&hose->list_node, &hose_list); + spin_unlock(&hose_spinlock); +} + +static void __init pcibios_claim_one_bus(struct pci_bus *b) +{ + struct pci_dev *dev; + struct pci_bus *child_bus; + + list_for_each_entry(dev, &b->devices, bus_list) { + int i; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct resource *r = &dev->resource[i]; + + if (r->parent || !r->start || !r->flags) + continue; + pci_claim_resource(dev, i); + } + } + + list_for_each_entry(child_bus, &b->children, node) + pcibios_claim_one_bus(child_bus); +} + +#ifndef CONFIG_PPC_ISERIES +static void __init pcibios_claim_of_setup(void) +{ + struct pci_bus *b; + + list_for_each_entry(b, &pci_root_buses, node) + pcibios_claim_one_bus(b); +} +#endif + +#ifdef CONFIG_PPC_MULTIPLATFORM +static u32 get_int_prop(struct device_node *np, const char *name, u32 def) +{ + u32 *prop; + int len; + + prop = (u32 *) get_property(np, name, &len); + if (prop && len >= 4) + return *prop; + return def; +} + +static unsigned int pci_parse_of_flags(u32 addr0) +{ + unsigned int flags = 0; + + if (addr0 & 0x02000000) { + flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; + flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; + flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; + if (addr0 & 0x40000000) + flags |= IORESOURCE_PREFETCH + | PCI_BASE_ADDRESS_MEM_PREFETCH; + } else if (addr0 & 0x01000000) + flags = IORESOURCE_IO | PCI_BASE_ADDRESS_SPACE_IO; + return flags; +} + +#define GET_64BIT(prop, i) ((((u64) (prop)[(i)]) << 32) | (prop)[(i)+1]) + +static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) +{ + u64 base, size; + unsigned int flags; + struct resource *res; + u32 *addrs, i; + int proplen; + + addrs = (u32 *) get_property(node, "assigned-addresses", &proplen); + if (!addrs) + return; + for (; proplen >= 20; proplen -= 20, addrs += 5) { + flags = pci_parse_of_flags(addrs[0]); + if (!flags) + continue; + base = GET_64BIT(addrs, 1); + size = GET_64BIT(addrs, 3); + if (!size) + continue; + i = addrs[0] & 0xff; + if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) { + res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; + } else if (i == dev->rom_base_reg) { + res = &dev->resource[PCI_ROM_RESOURCE]; + flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE; + } else { + printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i); + continue; + } + res->start = base; + res->end = base + size - 1; + res->flags = flags; + res->name = pci_name(dev); + fixup_resource(res, dev); + } +} + +struct pci_dev *of_create_pci_dev(struct device_node *node, + struct pci_bus *bus, int devfn) +{ + struct pci_dev *dev; + const char *type; + + dev = kmalloc(sizeof(struct pci_dev), GFP_KERNEL); + if (!dev) + return NULL; + type = get_property(node, "device_type", NULL); + if (type == NULL) + type = ""; + + memset(dev, 0, sizeof(struct pci_dev)); + dev->bus = bus; + dev->sysdata = node; + dev->dev.parent = bus->bridge; + dev->dev.bus = &pci_bus_type; + dev->devfn = devfn; + dev->multifunction = 0; /* maybe a lie? */ + + dev->vendor = get_int_prop(node, "vendor-id", 0xffff); + dev->device = get_int_prop(node, "device-id", 0xffff); + dev->subsystem_vendor = get_int_prop(node, "subsystem-vendor-id", 0); + dev->subsystem_device = get_int_prop(node, "subsystem-id", 0); + + dev->cfg_size = 256; /*pci_cfg_space_size(dev);*/ + + sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), + dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); + dev->class = get_int_prop(node, "class-code", 0); + + dev->current_state = 4; /* unknown power state */ + + if (!strcmp(type, "pci")) { + /* a PCI-PCI bridge */ + dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; + dev->rom_base_reg = PCI_ROM_ADDRESS1; + } else if (!strcmp(type, "cardbus")) { + dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; + } else { + dev->hdr_type = PCI_HEADER_TYPE_NORMAL; + dev->rom_base_reg = PCI_ROM_ADDRESS; + dev->irq = NO_IRQ; + if (node->n_intrs > 0) { + dev->irq = node->intrs[0].line; + pci_write_config_byte(dev, PCI_INTERRUPT_LINE, + dev->irq); + } + } + + pci_parse_of_addrs(node, dev); + + pci_device_add(dev, bus); + + /* XXX pci_scan_msi_device(dev); */ + + return dev; +} +EXPORT_SYMBOL(of_create_pci_dev); + +void __devinit of_scan_bus(struct device_node *node, + struct pci_bus *bus) +{ + struct device_node *child = NULL; + u32 *reg; + int reglen, devfn; + struct pci_dev *dev; + + while ((child = of_get_next_child(node, child)) != NULL) { + reg = (u32 *) get_property(child, "reg", ®len); + if (reg == NULL || reglen < 20) + continue; + devfn = (reg[0] >> 8) & 0xff; + /* create a new pci_dev for this device */ + dev = of_create_pci_dev(child, bus, devfn); + if (!dev) + continue; + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + of_scan_pci_bridge(child, dev); + } + + do_bus_setup(bus); +} +EXPORT_SYMBOL(of_scan_bus); + +void __devinit of_scan_pci_bridge(struct device_node *node, + struct pci_dev *dev) +{ + struct pci_bus *bus; + u32 *busrange, *ranges; + int len, i, mode; + struct resource *res; + unsigned int flags; + u64 size; + + /* parse bus-range property */ + busrange = (u32 *) get_property(node, "bus-range", &len); + if (busrange == NULL || len != 8) { + printk(KERN_ERR "Can't get bus-range for PCI-PCI bridge %s\n", + node->full_name); + return; + } + ranges = (u32 *) get_property(node, "ranges", &len); + if (ranges == NULL) { + printk(KERN_ERR "Can't get ranges for PCI-PCI bridge %s\n", + node->full_name); + return; + } + + bus = pci_add_new_bus(dev->bus, dev, busrange[0]); + if (!bus) { + printk(KERN_ERR "Failed to create pci bus for %s\n", + node->full_name); + return; + } + + bus->primary = dev->bus->number; + bus->subordinate = busrange[1]; + bus->bridge_ctl = 0; + bus->sysdata = node; + + /* parse ranges property */ + /* PCI #address-cells == 3 and #size-cells == 2 always */ + res = &dev->resource[PCI_BRIDGE_RESOURCES]; + for (i = 0; i < PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES; ++i) { + res->flags = 0; + bus->resource[i] = res; + ++res; + } + i = 1; + for (; len >= 32; len -= 32, ranges += 8) { + flags = pci_parse_of_flags(ranges[0]); + size = GET_64BIT(ranges, 6); + if (flags == 0 || size == 0) + continue; + if (flags & IORESOURCE_IO) { + res = bus->resource[0]; + if (res->flags) { + printk(KERN_ERR "PCI: ignoring extra I/O range" + " for bridge %s\n", node->full_name); + continue; + } + } else { + if (i >= PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES) { + printk(KERN_ERR "PCI: too many memory ranges" + " for bridge %s\n", node->full_name); + continue; + } + res = bus->resource[i]; + ++i; + } + res->start = GET_64BIT(ranges, 1); + res->end = res->start + size - 1; + res->flags = flags; + fixup_resource(res, dev); + } + sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus), + bus->number); + + mode = PCI_PROBE_NORMAL; + if (ppc_md.pci_probe_mode) + mode = ppc_md.pci_probe_mode(bus); + if (mode == PCI_PROBE_DEVTREE) + of_scan_bus(node, bus); + else if (mode == PCI_PROBE_NORMAL) + pci_scan_child_bus(bus); +} +EXPORT_SYMBOL(of_scan_pci_bridge); +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +void __devinit scan_phb(struct pci_controller *hose) +{ + struct pci_bus *bus; + struct device_node *node = hose->arch_data; + int i, mode; + struct resource *res; + + bus = pci_create_bus(NULL, hose->first_busno, hose->ops, node); + if (bus == NULL) { + printk(KERN_ERR "Failed to create bus for PCI domain %04x\n", + hose->global_number); + return; + } + bus->secondary = hose->first_busno; + hose->bus = bus; + + bus->resource[0] = res = &hose->io_resource; + if (res->flags && request_resource(&ioport_resource, res)) + printk(KERN_ERR "Failed to request PCI IO region " + "on PCI domain %04x\n", hose->global_number); + + for (i = 0; i < 3; ++i) { + res = &hose->mem_resources[i]; + bus->resource[i+1] = res; + if (res->flags && request_resource(&iomem_resource, res)) + printk(KERN_ERR "Failed to request PCI memory region " + "on PCI domain %04x\n", hose->global_number); + } + + mode = PCI_PROBE_NORMAL; +#ifdef CONFIG_PPC_MULTIPLATFORM + if (ppc_md.pci_probe_mode) + mode = ppc_md.pci_probe_mode(bus); + if (mode == PCI_PROBE_DEVTREE) { + bus->subordinate = hose->last_busno; + of_scan_bus(node, bus); + } +#endif /* CONFIG_PPC_MULTIPLATFORM */ + if (mode == PCI_PROBE_NORMAL) + hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); + pci_bus_add_devices(bus); +} + +static int __init pcibios_init(void) +{ + struct pci_controller *hose, *tmp; + + /* For now, override phys_mem_access_prot. If we need it, + * later, we may move that initialization to each ppc_md + */ + ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot; + +#ifdef CONFIG_PPC_ISERIES + iSeries_pcibios_init(); +#endif + + printk("PCI: Probing PCI hardware\n"); + + /* Scan all of the recorded PCI controllers. */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + scan_phb(hose); + +#ifndef CONFIG_PPC_ISERIES + if (pci_probe_only) + pcibios_claim_of_setup(); + else + /* FIXME: `else' will be removed when + pci_assign_unassigned_resources() is able to work + correctly with [partially] allocated PCI tree. */ + pci_assign_unassigned_resources(); +#endif /* !CONFIG_PPC_ISERIES */ + + /* Call machine dependent final fixup */ + if (ppc_md.pcibios_fixup) + ppc_md.pcibios_fixup(); + + /* Cache the location of the ISA bridge (if we have one) */ + ppc64_isabridge_dev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); + if (ppc64_isabridge_dev != NULL) + printk("ISA bridge at %s\n", pci_name(ppc64_isabridge_dev)); + +#ifdef CONFIG_PPC_MULTIPLATFORM + /* map in PCI I/O space */ + phbs_remap_io(); +#endif + + printk("PCI: Probing PCI hardware done\n"); + + return 0; +} + +subsys_initcall(pcibios_init); + +char __init *pcibios_setup(char *str) +{ + return str; +} + +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + u16 cmd, oldcmd; + int i; + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + oldcmd = cmd; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct resource *res = &dev->resource[i]; + + /* Only set up the requested stuff */ + if (!(mask & (1<flags & IORESOURCE_IO) + cmd |= PCI_COMMAND_IO; + if (res->flags & IORESOURCE_MEM) + cmd |= PCI_COMMAND_MEMORY; + } + + if (cmd != oldcmd) { + printk(KERN_DEBUG "PCI: Enabling device: (%s), cmd %x\n", + pci_name(dev), cmd); + /* Enable the appropriate bits in the PCI command register. */ + pci_write_config_word(dev, PCI_COMMAND, cmd); + } + return 0; +} + +/* + * Return the domain number for this bus. + */ +int pci_domain_nr(struct pci_bus *bus) +{ +#ifdef CONFIG_PPC_ISERIES + return 0; +#else + struct pci_controller *hose = pci_bus_to_host(bus); + + return hose->global_number; +#endif +} + +EXPORT_SYMBOL(pci_domain_nr); + +/* Decide whether to display the domain number in /proc */ +int pci_proc_domain(struct pci_bus *bus) +{ +#ifdef CONFIG_PPC_ISERIES + return 0; +#else + struct pci_controller *hose = pci_bus_to_host(bus); + return hose->buid; +#endif +} + +/* + * Platform support for /proc/bus/pci/X/Y mmap()s, + * modelled on the sparc64 implementation by Dave Miller. + * -- paulus. + */ + +/* + * Adjust vm_pgoff of VMA such that it is the physical page offset + * corresponding to the 32-bit pci bus offset for DEV requested by the user. + * + * Basically, the user finds the base address for his device which he wishes + * to mmap. They read the 32-bit value from the config space base register, + * add whatever PAGE_SIZE multiple offset they wish, and feed this into the + * offset parameter of mmap on /proc/bus/pci/XXX for that device. + * + * Returns negative error code on failure, zero on success. + */ +static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, + unsigned long *offset, + enum pci_mmap_state mmap_state) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned long io_offset = 0; + int i, res_bit; + + if (hose == 0) + return NULL; /* should never happen */ + + /* If memory, add on the PCI bridge address offset */ + if (mmap_state == pci_mmap_mem) { + *offset += hose->pci_mem_offset; + res_bit = IORESOURCE_MEM; + } else { + io_offset = (unsigned long)hose->io_base_virt - pci_io_base; + *offset += io_offset; + res_bit = IORESOURCE_IO; + } + + /* + * Check that the offset requested corresponds to one of the + * resources of the device. + */ + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { + struct resource *rp = &dev->resource[i]; + int flags = rp->flags; + + /* treat ROM as memory (should be already) */ + if (i == PCI_ROM_RESOURCE) + flags |= IORESOURCE_MEM; + + /* Active and same type? */ + if ((flags & res_bit) == 0) + continue; + + /* In the range of this resource? */ + if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) + continue; + + /* found it! construct the final physical address */ + if (mmap_state == pci_mmap_io) + *offset += hose->io_base_phys - io_offset; + return rp; + } + + return NULL; +} + +/* + * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci + * device mapping. + */ +static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, + pgprot_t protection, + enum pci_mmap_state mmap_state, + int write_combine) +{ + unsigned long prot = pgprot_val(protection); + + /* Write combine is always 0 on non-memory space mappings. On + * memory space, if the user didn't pass 1, we check for a + * "prefetchable" resource. This is a bit hackish, but we use + * this to workaround the inability of /sysfs to provide a write + * combine bit + */ + if (mmap_state != pci_mmap_mem) + write_combine = 0; + else if (write_combine == 0) { + if (rp->flags & IORESOURCE_PREFETCH) + write_combine = 1; + } + + /* XXX would be nice to have a way to ask for write-through */ + prot |= _PAGE_NO_CACHE; + if (write_combine) + prot &= ~_PAGE_GUARDED; + else + prot |= _PAGE_GUARDED; + + printk("PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, + prot); + + return __pgprot(prot); +} + +/* + * This one is used by /dev/mem and fbdev who have no clue about the + * PCI device, it tries to find the PCI device first and calls the + * above routine + */ +pgprot_t pci_phys_mem_access_prot(struct file *file, + unsigned long pfn, + unsigned long size, + pgprot_t protection) +{ + struct pci_dev *pdev = NULL; + struct resource *found = NULL; + unsigned long prot = pgprot_val(protection); + unsigned long offset = pfn << PAGE_SHIFT; + int i; + + if (page_is_ram(pfn)) + return __pgprot(prot); + + prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; + + for_each_pci_dev(pdev) { + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { + struct resource *rp = &pdev->resource[i]; + int flags = rp->flags; + + /* Active and same type? */ + if ((flags & IORESOURCE_MEM) == 0) + continue; + /* In the range of this resource? */ + if (offset < (rp->start & PAGE_MASK) || + offset > rp->end) + continue; + found = rp; + break; + } + if (found) + break; + } + if (found) { + if (found->flags & IORESOURCE_PREFETCH) + prot &= ~_PAGE_GUARDED; + pci_dev_put(pdev); + } + + DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); + + return __pgprot(prot); +} + + +/* + * Perform the actual remap of the pages for a PCI device mapping, as + * appropriate for this architecture. The region in the process to map + * is described by vm_start and vm_end members of VMA, the base physical + * address is found in vm_pgoff. + * The pci device structure is provided so that architectures may make mapping + * decisions on a per-device or per-bus basis. + * + * Returns a negative error code on failure, zero on success. + */ +int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, + int write_combine) +{ + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + struct resource *rp; + int ret; + + rp = __pci_mmap_make_offset(dev, &offset, mmap_state); + if (rp == NULL) + return -EINVAL; + + vma->vm_pgoff = offset >> PAGE_SHIFT; + vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; + vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, + vma->vm_page_prot, + mmap_state, write_combine); + + ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, vma->vm_page_prot); + + return ret; +} + +#ifdef CONFIG_PPC_MULTIPLATFORM +static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev; + struct device_node *np; + + pdev = to_pci_dev (dev); + np = pci_device_to_OF_node(pdev); + if (np == NULL || np->full_name == NULL) + return 0; + return sprintf(buf, "%s", np->full_name); +} +static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +void pcibios_add_platform_entries(struct pci_dev *pdev) +{ +#ifdef CONFIG_PPC_MULTIPLATFORM + device_create_file(&pdev->dev, &dev_attr_devspec); +#endif /* CONFIG_PPC_MULTIPLATFORM */ +} + +#ifdef CONFIG_PPC_MULTIPLATFORM + +#define ISA_SPACE_MASK 0x1 +#define ISA_SPACE_IO 0x1 + +static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, + unsigned long phb_io_base_phys, + void __iomem * phb_io_base_virt) +{ + struct isa_range *range; + unsigned long pci_addr; + unsigned int isa_addr; + unsigned int size; + int rlen = 0; + + range = (struct isa_range *) get_property(isa_node, "ranges", &rlen); + if (range == NULL || (rlen < sizeof(struct isa_range))) { + printk(KERN_ERR "no ISA ranges or unexpected isa range size," + "mapping 64k\n"); + __ioremap_explicit(phb_io_base_phys, + (unsigned long)phb_io_base_virt, + 0x10000, _PAGE_NO_CACHE | _PAGE_GUARDED); + return; + } + + /* From "ISA Binding to 1275" + * The ranges property is laid out as an array of elements, + * each of which comprises: + * cells 0 - 1: an ISA address + * cells 2 - 4: a PCI address + * (size depending on dev->n_addr_cells) + * cell 5: the size of the range + */ + if ((range->isa_addr.a_hi && ISA_SPACE_MASK) == ISA_SPACE_IO) { + isa_addr = range->isa_addr.a_lo; + pci_addr = (unsigned long) range->pci_addr.a_mid << 32 | + range->pci_addr.a_lo; + + /* Assume these are both zero */ + if ((pci_addr != 0) || (isa_addr != 0)) { + printk(KERN_ERR "unexpected isa to pci mapping: %s\n", + __FUNCTION__); + return; + } + + size = PAGE_ALIGN(range->size); + + __ioremap_explicit(phb_io_base_phys, + (unsigned long) phb_io_base_virt, + size, _PAGE_NO_CACHE | _PAGE_GUARDED); + } +} + +void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, + struct device_node *dev, int prim) +{ + unsigned int *ranges, pci_space; + unsigned long size; + int rlen = 0; + int memno = 0; + struct resource *res; + int np, na = prom_n_addr_cells(dev); + unsigned long pci_addr, cpu_phys_addr; + + np = na + 5; + + /* From "PCI Binding to 1275" + * The ranges property is laid out as an array of elements, + * each of which comprises: + * cells 0 - 2: a PCI address + * cells 3 or 3+4: a CPU physical address + * (size depending on dev->n_addr_cells) + * cells 4+5 or 5+6: the size of the range + */ + rlen = 0; + hose->io_base_phys = 0; + ranges = (unsigned int *) get_property(dev, "ranges", &rlen); + while ((rlen -= np * sizeof(unsigned int)) >= 0) { + res = NULL; + pci_space = ranges[0]; + pci_addr = ((unsigned long)ranges[1] << 32) | ranges[2]; + + cpu_phys_addr = ranges[3]; + if (na >= 2) + cpu_phys_addr = (cpu_phys_addr << 32) | ranges[4]; + + size = ((unsigned long)ranges[na+3] << 32) | ranges[na+4]; + ranges += np; + if (size == 0) + continue; + + /* Now consume following elements while they are contiguous */ + while (rlen >= np * sizeof(unsigned int)) { + unsigned long addr, phys; + + if (ranges[0] != pci_space) + break; + addr = ((unsigned long)ranges[1] << 32) | ranges[2]; + phys = ranges[3]; + if (na >= 2) + phys = (phys << 32) | ranges[4]; + if (addr != pci_addr + size || + phys != cpu_phys_addr + size) + break; + + size += ((unsigned long)ranges[na+3] << 32) + | ranges[na+4]; + ranges += np; + rlen -= np * sizeof(unsigned int); + } + + switch ((pci_space >> 24) & 0x3) { + case 1: /* I/O space */ + hose->io_base_phys = cpu_phys_addr; + hose->pci_io_size = size; + + res = &hose->io_resource; + res->flags = IORESOURCE_IO; + res->start = pci_addr; + DBG("phb%d: IO 0x%lx -> 0x%lx\n", hose->global_number, + res->start, res->start + size - 1); + break; + case 2: /* memory space */ + memno = 0; + while (memno < 3 && hose->mem_resources[memno].flags) + ++memno; + + if (memno == 0) + hose->pci_mem_offset = cpu_phys_addr - pci_addr; + if (memno < 3) { + res = &hose->mem_resources[memno]; + res->flags = IORESOURCE_MEM; + res->start = cpu_phys_addr; + DBG("phb%d: MEM 0x%lx -> 0x%lx\n", hose->global_number, + res->start, res->start + size - 1); + } + break; + } + if (res != NULL) { + res->name = dev->full_name; + res->end = res->start + size - 1; + res->parent = NULL; + res->sibling = NULL; + res->child = NULL; + } + } +} + +void __init pci_setup_phb_io(struct pci_controller *hose, int primary) +{ + unsigned long size = hose->pci_io_size; + unsigned long io_virt_offset; + struct resource *res; + struct device_node *isa_dn; + + hose->io_base_virt = reserve_phb_iospace(size); + DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", + hose->global_number, hose->io_base_phys, + (unsigned long) hose->io_base_virt); + + if (primary) { + pci_io_base = (unsigned long)hose->io_base_virt; + isa_dn = of_find_node_by_type(NULL, "isa"); + if (isa_dn) { + isa_io_base = pci_io_base; + pci_process_ISA_OF_ranges(isa_dn, hose->io_base_phys, + hose->io_base_virt); + of_node_put(isa_dn); + /* Allow all IO */ + io_page_mask = -1; + } + } + + io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; + res = &hose->io_resource; + res->start += io_virt_offset; + res->end += io_virt_offset; +} + +void __devinit pci_setup_phb_io_dynamic(struct pci_controller *hose, + int primary) +{ + unsigned long size = hose->pci_io_size; + unsigned long io_virt_offset; + struct resource *res; + + hose->io_base_virt = __ioremap(hose->io_base_phys, size, + _PAGE_NO_CACHE | _PAGE_GUARDED); + DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", + hose->global_number, hose->io_base_phys, + (unsigned long) hose->io_base_virt); + + if (primary) + pci_io_base = (unsigned long)hose->io_base_virt; + + io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; + res = &hose->io_resource; + res->start += io_virt_offset; + res->end += io_virt_offset; +} + + +static int get_bus_io_range(struct pci_bus *bus, unsigned long *start_phys, + unsigned long *start_virt, unsigned long *size) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + struct pci_bus_region region; + struct resource *res; + + if (bus->self) { + res = bus->resource[0]; + pcibios_resource_to_bus(bus->self, ®ion, res); + *start_phys = hose->io_base_phys + region.start; + *start_virt = (unsigned long) hose->io_base_virt + + region.start; + if (region.end > region.start) + *size = region.end - region.start + 1; + else { + printk("%s(): unexpected region 0x%lx->0x%lx\n", + __FUNCTION__, region.start, region.end); + return 1; + } + + } else { + /* Root Bus */ + res = &hose->io_resource; + *start_phys = hose->io_base_phys; + *start_virt = (unsigned long) hose->io_base_virt; + if (res->end > res->start) + *size = res->end - res->start + 1; + else { + printk("%s(): unexpected region 0x%lx->0x%lx\n", + __FUNCTION__, res->start, res->end); + return 1; + } + } + + return 0; +} + +int unmap_bus_range(struct pci_bus *bus) +{ + unsigned long start_phys; + unsigned long start_virt; + unsigned long size; + + if (!bus) { + printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); + return 1; + } + + if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) + return 1; + if (iounmap_explicit((void __iomem *) start_virt, size)) + return 1; + + return 0; +} +EXPORT_SYMBOL(unmap_bus_range); + +int remap_bus_range(struct pci_bus *bus) +{ + unsigned long start_phys; + unsigned long start_virt; + unsigned long size; + + if (!bus) { + printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); + return 1; + } + + + if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) + return 1; + printk("mapping IO %lx -> %lx, size: %lx\n", start_phys, start_virt, size); + if (__ioremap_explicit(start_phys, start_virt, size, + _PAGE_NO_CACHE | _PAGE_GUARDED)) + return 1; + + return 0; +} +EXPORT_SYMBOL(remap_bus_range); + +void phbs_remap_io(void) +{ + struct pci_controller *hose, *tmp; + + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + remap_bus_range(hose->bus); +} + +/* + * ppc64 can have multifunction devices that do not respond to function 0. + * In this case we must scan all functions. + * XXX this can go now, we use the OF device tree in all the + * cases that caused problems. -- paulus + */ +int pcibios_scan_all_fns(struct pci_bus *bus, int devfn) +{ + return 0; +} + +static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned long start, end, mask, offset; + + if (res->flags & IORESOURCE_IO) { + offset = (unsigned long)hose->io_base_virt - pci_io_base; + + start = res->start += offset; + end = res->end += offset; + + /* Need to allow IO access to pages that are in the + ISA range */ + if (start < MAX_ISA_PORT) { + if (end > MAX_ISA_PORT) + end = MAX_ISA_PORT; + + start >>= PAGE_SHIFT; + end >>= PAGE_SHIFT; + + /* get the range of pages for the map */ + mask = ((1 << (end+1)) - 1) ^ ((1 << start) - 1); + io_page_mask |= mask; + } + } else if (res->flags & IORESOURCE_MEM) { + res->start += hose->pci_mem_offset; + res->end += hose->pci_mem_offset; + } +} + +void __devinit pcibios_fixup_device_resources(struct pci_dev *dev, + struct pci_bus *bus) +{ + /* Update device resources. */ + int i; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) + if (dev->resource[i].flags) + fixup_resource(&dev->resource[i], dev); +} +EXPORT_SYMBOL(pcibios_fixup_device_resources); + +static void __devinit do_bus_setup(struct pci_bus *bus) +{ + struct pci_dev *dev; + + ppc_md.iommu_bus_setup(bus); + + list_for_each_entry(dev, &bus->devices, bus_list) + ppc_md.iommu_dev_setup(dev); + + if (ppc_md.irq_bus_setup) + ppc_md.irq_bus_setup(bus); +} + +void __devinit pcibios_fixup_bus(struct pci_bus *bus) +{ + struct pci_dev *dev = bus->self; + + if (dev && pci_probe_only && + (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { + /* This is a subordinate bridge */ + + pci_read_bridge_bases(bus); + pcibios_fixup_device_resources(dev, bus); + } + + do_bus_setup(bus); + + if (!pci_probe_only) + return; + + list_for_each_entry(dev, &bus->devices, bus_list) + if ((dev->class >> 8) != PCI_CLASS_BRIDGE_PCI) + pcibios_fixup_device_resources(dev, bus); +} +EXPORT_SYMBOL(pcibios_fixup_bus); + +/* + * Reads the interrupt pin to determine if interrupt is use by card. + * If the interrupt is used, then gets the interrupt line from the + * openfirmware and sets it in the pci_dev and pci_config line. + */ +int pci_read_irq_line(struct pci_dev *pci_dev) +{ + u8 intpin; + struct device_node *node; + + pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &intpin); + if (intpin == 0) + return 0; + + node = pci_device_to_OF_node(pci_dev); + if (node == NULL) + return -1; + + if (node->n_intrs == 0) + return -1; + + pci_dev->irq = node->intrs[0].line; + + pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, pci_dev->irq); + + return 0; +} +EXPORT_SYMBOL(pci_read_irq_line); + +void pci_resource_to_user(const struct pci_dev *dev, int bar, + const struct resource *rsrc, + u64 *start, u64 *end) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned long offset = 0; + + if (hose == NULL) + return; + + if (rsrc->flags & IORESOURCE_IO) + offset = pci_io_base - (unsigned long)hose->io_base_virt + + hose->io_base_phys; + + *start = rsrc->start + offset; + *end = rsrc->end + offset; +} + +#endif /* CONFIG_PPC_MULTIPLATFORM */ + + +#define IOBASE_BRIDGE_NUMBER 0 +#define IOBASE_MEMORY 1 +#define IOBASE_IO 2 +#define IOBASE_ISA_IO 3 +#define IOBASE_ISA_MEM 4 + +long sys_pciconfig_iobase(long which, unsigned long in_bus, + unsigned long in_devfn) +{ + struct pci_controller* hose; + struct list_head *ln; + struct pci_bus *bus = NULL; + struct device_node *hose_node; + + /* Argh ! Please forgive me for that hack, but that's the + * simplest way to get existing XFree to not lockup on some + * G5 machines... So when something asks for bus 0 io base + * (bus 0 is HT root), we return the AGP one instead. + */ + if (machine_is_compatible("MacRISC4")) + if (in_bus == 0) + in_bus = 0xf0; + + /* That syscall isn't quite compatible with PCI domains, but it's + * used on pre-domains setup. We return the first match + */ + + for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) { + bus = pci_bus_b(ln); + if (in_bus >= bus->number && in_bus < (bus->number + bus->subordinate)) + break; + bus = NULL; + } + if (bus == NULL || bus->sysdata == NULL) + return -ENODEV; + + hose_node = (struct device_node *)bus->sysdata; + hose = PCI_DN(hose_node)->phb; + + switch (which) { + case IOBASE_BRIDGE_NUMBER: + return (long)hose->first_busno; + case IOBASE_MEMORY: + return (long)hose->pci_mem_offset; + case IOBASE_IO: + return (long)hose->io_base_phys; + case IOBASE_ISA_IO: + return (long)isa_io_base; + case IOBASE_ISA_MEM: + return -EINVAL; + } + + return -EOPNOTSUPP; +} diff --git a/arch/powerpc/kernel/pci_direct_iommu.c b/arch/powerpc/kernel/pci_direct_iommu.c new file mode 100644 index 000000000000..e1a32f802c0b --- /dev/null +++ b/arch/powerpc/kernel/pci_direct_iommu.c @@ -0,0 +1,94 @@ +/* + * Support for DMA from PCI devices to main memory on + * machines without an iommu or with directly addressable + * RAM (typically a pmac with 2Gb of RAM or less) + * + * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +static void *pci_direct_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + void *ret; + + ret = (void *)__get_free_pages(flag, get_order(size)); + if (ret != NULL) { + memset(ret, 0, size); + *dma_handle = virt_to_abs(ret); + } + return ret; +} + +static void pci_direct_free_coherent(struct device *hwdev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + free_pages((unsigned long)vaddr, get_order(size)); +} + +static dma_addr_t pci_direct_map_single(struct device *hwdev, void *ptr, + size_t size, enum dma_data_direction direction) +{ + return virt_to_abs(ptr); +} + +static void pci_direct_unmap_single(struct device *hwdev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction direction) +{ +} + +static int pci_direct_map_sg(struct device *hwdev, struct scatterlist *sg, + int nents, enum dma_data_direction direction) +{ + int i; + + for (i = 0; i < nents; i++, sg++) { + sg->dma_address = page_to_phys(sg->page) + sg->offset; + sg->dma_length = sg->length; + } + + return nents; +} + +static void pci_direct_unmap_sg(struct device *hwdev, struct scatterlist *sg, + int nents, enum dma_data_direction direction) +{ +} + +static int pci_direct_dma_supported(struct device *dev, u64 mask) +{ + return mask < 0x100000000ull; +} + +void __init pci_direct_iommu_init(void) +{ + pci_dma_ops.alloc_coherent = pci_direct_alloc_coherent; + pci_dma_ops.free_coherent = pci_direct_free_coherent; + pci_dma_ops.map_single = pci_direct_map_single; + pci_dma_ops.unmap_single = pci_direct_unmap_single; + pci_dma_ops.map_sg = pci_direct_map_sg; + pci_dma_ops.unmap_sg = pci_direct_unmap_sg; + pci_dma_ops.dma_supported = pci_direct_dma_supported; +} diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c new file mode 100644 index 000000000000..12c4c9e9bbc7 --- /dev/null +++ b/arch/powerpc/kernel/pci_dn.c @@ -0,0 +1,230 @@ +/* + * pci_dn.c + * + * Copyright (C) 2001 Todd Inglett, IBM Corporation + * + * PCI manipulation via device_nodes. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +/* + * Traverse_func that inits the PCI fields of the device node. + * NOTE: this *must* be done before read/write config to the device. + */ +static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) +{ + struct pci_controller *phb = data; + int *type = (int *)get_property(dn, "ibm,pci-config-space-type", NULL); + u32 *regs; + struct pci_dn *pdn; + + if (mem_init_done) + pdn = kmalloc(sizeof(*pdn), GFP_KERNEL); + else + pdn = alloc_bootmem(sizeof(*pdn)); + if (pdn == NULL) + return NULL; + memset(pdn, 0, sizeof(*pdn)); + dn->data = pdn; + pdn->node = dn; + pdn->phb = phb; + regs = (u32 *)get_property(dn, "reg", NULL); + if (regs) { + /* First register entry is addr (00BBSS00) */ + pdn->busno = (regs[0] >> 16) & 0xff; + pdn->devfn = (regs[0] >> 8) & 0xff; + } + + pdn->pci_ext_config_space = (type && *type == 1); + return NULL; +} + +/* + * Traverse a device tree stopping each PCI device in the tree. + * This is done depth first. As each node is processed, a "pre" + * function is called and the children are processed recursively. + * + * The "pre" func returns a value. If non-zero is returned from + * the "pre" func, the traversal stops and this value is returned. + * This return value is useful when using traverse as a method of + * finding a device. + * + * NOTE: we do not run the func for devices that do not appear to + * be PCI except for the start node which we assume (this is good + * because the start node is often a phb which may be missing PCI + * properties). + * We use the class-code as an indicator. If we run into + * one of these nodes we also assume its siblings are non-pci for + * performance. + */ +void *traverse_pci_devices(struct device_node *start, traverse_func pre, + void *data) +{ + struct device_node *dn, *nextdn; + void *ret; + + /* We started with a phb, iterate all childs */ + for (dn = start->child; dn; dn = nextdn) { + u32 *classp, class; + + nextdn = NULL; + classp = (u32 *)get_property(dn, "class-code", NULL); + class = classp ? *classp : 0; + + if (pre && ((ret = pre(dn, data)) != NULL)) + return ret; + + /* If we are a PCI bridge, go down */ + if (dn->child && ((class >> 8) == PCI_CLASS_BRIDGE_PCI || + (class >> 8) == PCI_CLASS_BRIDGE_CARDBUS)) + /* Depth first...do children */ + nextdn = dn->child; + else if (dn->sibling) + /* ok, try next sibling instead. */ + nextdn = dn->sibling; + if (!nextdn) { + /* Walk up to next valid sibling. */ + do { + dn = dn->parent; + if (dn == start) + return NULL; + } while (dn->sibling == NULL); + nextdn = dn->sibling; + } + } + return NULL; +} + +/** + * pci_devs_phb_init_dynamic - setup pci devices under this PHB + * phb: pci-to-host bridge (top-level bridge connecting to cpu) + * + * This routine is called both during boot, (before the memory + * subsystem is set up, before kmalloc is valid) and during the + * dynamic lpar operation of adding a PHB to a running system. + */ +void __devinit pci_devs_phb_init_dynamic(struct pci_controller *phb) +{ + struct device_node * dn = (struct device_node *) phb->arch_data; + struct pci_dn *pdn; + + /* PHB nodes themselves must not match */ + update_dn_pci_info(dn, phb); + pdn = dn->data; + if (pdn) { + pdn->devfn = pdn->busno = -1; + pdn->phb = phb; + } + + /* Update dn->phb ptrs for new phb and children devices */ + traverse_pci_devices(dn, update_dn_pci_info, phb); +} + +/* + * Traversal func that looks for a value. + * If found, the pci_dn is returned (thus terminating the traversal). + */ +static void *is_devfn_node(struct device_node *dn, void *data) +{ + int busno = ((unsigned long)data >> 8) & 0xff; + int devfn = ((unsigned long)data) & 0xff; + struct pci_dn *pci = dn->data; + + if (pci && (devfn == pci->devfn) && (busno == pci->busno)) + return dn; + return NULL; +} + +/* + * This is the "slow" path for looking up a device_node from a + * pci_dev. It will hunt for the device under its parent's + * phb and then update sysdata for a future fastpath. + * + * It may also do fixups on the actual device since this happens + * on the first read/write. + * + * Note that it also must deal with devices that don't exist. + * In this case it may probe for real hardware ("just in case") + * and add a device_node to the device tree if necessary. + * + */ +struct device_node *fetch_dev_dn(struct pci_dev *dev) +{ + struct device_node *orig_dn = dev->sysdata; + struct device_node *dn; + unsigned long searchval = (dev->bus->number << 8) | dev->devfn; + + dn = traverse_pci_devices(orig_dn, is_devfn_node, (void *)searchval); + if (dn) + dev->sysdata = dn; + return dn; +} +EXPORT_SYMBOL(fetch_dev_dn); + +static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node) +{ + struct device_node *np = node; + struct pci_dn *pci = NULL; + int err = NOTIFY_OK; + + switch (action) { + case PSERIES_RECONFIG_ADD: + pci = np->parent->data; + if (pci) + update_dn_pci_info(np, pci->phb); + break; + default: + err = NOTIFY_DONE; + break; + } + return err; +} + +static struct notifier_block pci_dn_reconfig_nb = { + .notifier_call = pci_dn_reconfig_notifier, +}; + +/** + * pci_devs_phb_init - Initialize phbs and pci devs under them. + * + * This routine walks over all phb's (pci-host bridges) on the + * system, and sets up assorted pci-related structures + * (including pci info in the device node structs) for each + * pci device found underneath. This routine runs once, + * early in the boot sequence. + */ +void __init pci_devs_phb_init(void) +{ + struct pci_controller *phb, *tmp; + + /* This must be done first so the device nodes have valid pci info! */ + list_for_each_entry_safe(phb, tmp, &hose_list, list_node) + pci_devs_phb_init_dynamic(phb); + + pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb); +} diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c new file mode 100644 index 000000000000..bdf15dbbf4f0 --- /dev/null +++ b/arch/powerpc/kernel/pci_iommu.c @@ -0,0 +1,128 @@ +/* + * arch/ppc64/kernel/pci_iommu.c + * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation + * + * Rewrite, cleanup, new allocation schemes: + * Copyright (C) 2004 Olof Johansson, IBM Corporation + * + * Dynamic DMA mapping support, platform-independent parts. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * We can use ->sysdata directly and avoid the extra work in + * pci_device_to_OF_node since ->sysdata will have been initialised + * in the iommu init code for all devices. + */ +#define PCI_GET_DN(dev) ((struct device_node *)((dev)->sysdata)) + +static inline struct iommu_table *devnode_table(struct device *dev) +{ + struct pci_dev *pdev; + + if (!dev) { + pdev = ppc64_isabridge_dev; + if (!pdev) + return NULL; + } else + pdev = to_pci_dev(dev); + + return PCI_DN(PCI_GET_DN(pdev))->iommu_table; +} + + +/* Allocates a contiguous real buffer and creates mappings over it. + * Returns the virtual address of the buffer and sets dma_handle + * to the dma address (mapping) of the first page. + */ +static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + return iommu_alloc_coherent(devnode_table(hwdev), size, dma_handle, + flag); +} + +static void pci_iommu_free_coherent(struct device *hwdev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + iommu_free_coherent(devnode_table(hwdev), size, vaddr, dma_handle); +} + +/* Creates TCEs for a user provided buffer. The user buffer must be + * contiguous real kernel storage (not vmalloc). The address of the buffer + * passed here is the kernel (virtual) address of the buffer. The buffer + * need not be page aligned, the dma_addr_t returned will point to the same + * byte within the page as vaddr. + */ +static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr, + size_t size, enum dma_data_direction direction) +{ + return iommu_map_single(devnode_table(hwdev), vaddr, size, direction); +} + + +static void pci_iommu_unmap_single(struct device *hwdev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction direction) +{ + iommu_unmap_single(devnode_table(hwdev), dma_handle, size, direction); +} + + +static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction) +{ + return iommu_map_sg(pdev, devnode_table(pdev), sglist, + nelems, direction); +} + +static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction) +{ + iommu_unmap_sg(devnode_table(pdev), sglist, nelems, direction); +} + +/* We support DMA to/from any memory page via the iommu */ +static int pci_iommu_dma_supported(struct device *dev, u64 mask) +{ + return 1; +} + +void pci_iommu_init(void) +{ + pci_dma_ops.alloc_coherent = pci_iommu_alloc_coherent; + pci_dma_ops.free_coherent = pci_iommu_free_coherent; + pci_dma_ops.map_single = pci_iommu_map_single; + pci_dma_ops.unmap_single = pci_iommu_unmap_single; + pci_dma_ops.map_sg = pci_iommu_map_sg; + pci_dma_ops.unmap_sg = pci_iommu_unmap_sg; + pci_dma_ops.dma_supported = pci_iommu_dma_supported; +} diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index e7ca5b1f591e..06d5ef501218 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -4,4 +4,7 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_XICS) += xics.o obj-$(CONFIG_SCANLOG) += scanlog.o -obj-$(CONFIG_EEH) += eeh.o eeh_event.o +obj-$(CONFIG_EEH) += eeh.o eeh_event.o + +obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o +obj-$(CONFIG_HVCS) += hvcserver.o diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c new file mode 100644 index 000000000000..138e128a3886 --- /dev/null +++ b/arch/powerpc/platforms/pseries/hvconsole.c @@ -0,0 +1,74 @@ +/* + * hvconsole.c + * Copyright (C) 2004 Hollis Blanchard, IBM Corporation + * Copyright (C) 2004 IBM Corporation + * + * Additional Author(s): + * Ryan S. Arnold + * + * LPAR console support. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include +#include +#include + +/** + * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper + * @vtermno: The vtermno or unit_address of the adapter from which to fetch the + * data. + * @buf: The character buffer into which to put the character data fetched from + * firmware. + * @count: not used? + */ +int hvc_get_chars(uint32_t vtermno, char *buf, int count) +{ + unsigned long got; + + if (plpar_hcall(H_GET_TERM_CHAR, vtermno, 0, 0, 0, &got, + (unsigned long *)buf, (unsigned long *)buf+1) == H_Success) + return got; + return 0; +} + +EXPORT_SYMBOL(hvc_get_chars); + + +/** + * hvc_put_chars: send characters to firmware for denoted vterm adapter + * @vtermno: The vtermno or unit_address of the adapter from which the data + * originated. + * @buf: The character buffer that contains the character data to send to + * firmware. + * @count: Send this number of characters. + */ +int hvc_put_chars(uint32_t vtermno, const char *buf, int count) +{ + unsigned long *lbuf = (unsigned long *) buf; + long ret; + + ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0], + lbuf[1]); + if (ret == H_Success) + return count; + if (ret == H_Busy) + return 0; + return -EIO; +} + +EXPORT_SYMBOL(hvc_put_chars); diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c new file mode 100644 index 000000000000..4d584172055a --- /dev/null +++ b/arch/powerpc/platforms/pseries/hvcserver.c @@ -0,0 +1,251 @@ +/* + * hvcserver.c + * Copyright (C) 2004 Ryan S Arnold, IBM Corporation + * + * PPC64 virtual I/O console server support. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include +#include +#include + +#include +#include +#include + +#define HVCS_ARCH_VERSION "1.0.0" + +MODULE_AUTHOR("Ryan S. Arnold "); +MODULE_DESCRIPTION("IBM hvcs ppc64 API"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(HVCS_ARCH_VERSION); + +/* + * Convert arch specific return codes into relevant errnos. The hvcs + * functions aren't performance sensitive, so this conversion isn't an + * issue. + */ +int hvcs_convert(long to_convert) +{ + switch (to_convert) { + case H_Success: + return 0; + case H_Parameter: + return -EINVAL; + case H_Hardware: + return -EIO; + case H_Busy: + case H_LongBusyOrder1msec: + case H_LongBusyOrder10msec: + case H_LongBusyOrder100msec: + case H_LongBusyOrder1sec: + case H_LongBusyOrder10sec: + case H_LongBusyOrder100sec: + return -EBUSY; + case H_Function: /* fall through */ + default: + return -EPERM; + } +} + +/** + * hvcs_free_partner_info - free pi allocated by hvcs_get_partner_info + * @head: list_head pointer for an allocated list of partner info structs to + * free. + * + * This function is used to free the partner info list that was returned by + * calling hvcs_get_partner_info(). + */ +int hvcs_free_partner_info(struct list_head *head) +{ + struct hvcs_partner_info *pi; + struct list_head *element; + + if (!head) + return -EINVAL; + + while (!list_empty(head)) { + element = head->next; + pi = list_entry(element, struct hvcs_partner_info, node); + list_del(element); + kfree(pi); + } + + return 0; +} +EXPORT_SYMBOL(hvcs_free_partner_info); + +/* Helper function for hvcs_get_partner_info */ +int hvcs_next_partner(uint32_t unit_address, + unsigned long last_p_partition_ID, + unsigned long last_p_unit_address, unsigned long *pi_buff) + +{ + long retval; + retval = plpar_hcall_norets(H_VTERM_PARTNER_INFO, unit_address, + last_p_partition_ID, + last_p_unit_address, virt_to_phys(pi_buff)); + return hvcs_convert(retval); +} + +/** + * hvcs_get_partner_info - Get all of the partner info for a vty-server adapter + * @unit_address: The unit_address of the vty-server adapter for which this + * function is fetching partner info. + * @head: An initialized list_head pointer to an empty list to use to return the + * list of partner info fetched from the hypervisor to the caller. + * @pi_buff: A page sized buffer pre-allocated prior to calling this function + * that is to be used to be used by firmware as an iterator to keep track + * of the partner info retrieval. + * + * This function returns non-zero on success, or if there is no partner info. + * + * The pi_buff is pre-allocated prior to calling this function because this + * function may be called with a spin_lock held and kmalloc of a page is not + * recommended as GFP_ATOMIC. + * + * The first long of this buffer is used to store a partner unit address. The + * second long is used to store a partner partition ID and starting at + * pi_buff[2] is the 79 character Converged Location Code (diff size than the + * unsigned longs, hence the casting mumbo jumbo you see later). + * + * Invocation of this function should always be followed by an invocation of + * hvcs_free_partner_info() using a pointer to the SAME list head instance + * that was passed as a parameter to this function. + */ +int hvcs_get_partner_info(uint32_t unit_address, struct list_head *head, + unsigned long *pi_buff) +{ + /* + * Dealt with as longs because of the hcall interface even though the + * values are uint32_t. + */ + unsigned long last_p_partition_ID; + unsigned long last_p_unit_address; + struct hvcs_partner_info *next_partner_info = NULL; + int more = 1; + int retval; + + memset(pi_buff, 0x00, PAGE_SIZE); + /* invalid parameters */ + if (!head || !pi_buff) + return -EINVAL; + + last_p_partition_ID = last_p_unit_address = ~0UL; + INIT_LIST_HEAD(head); + + do { + retval = hvcs_next_partner(unit_address, last_p_partition_ID, + last_p_unit_address, pi_buff); + if (retval) { + /* + * Don't indicate that we've failed if we have + * any list elements. + */ + if (!list_empty(head)) + return 0; + return retval; + } + + last_p_partition_ID = pi_buff[0]; + last_p_unit_address = pi_buff[1]; + + /* This indicates that there are no further partners */ + if (last_p_partition_ID == ~0UL + && last_p_unit_address == ~0UL) + break; + + /* This is a very small struct and will be freed soon in + * hvcs_free_partner_info(). */ + next_partner_info = kmalloc(sizeof(struct hvcs_partner_info), + GFP_ATOMIC); + + if (!next_partner_info) { + printk(KERN_WARNING "HVCONSOLE: kmalloc() failed to" + " allocate partner info struct.\n"); + hvcs_free_partner_info(head); + return -ENOMEM; + } + + next_partner_info->unit_address + = (unsigned int)last_p_unit_address; + next_partner_info->partition_ID + = (unsigned int)last_p_partition_ID; + + /* copy the Null-term char too */ + strncpy(&next_partner_info->location_code[0], + (char *)&pi_buff[2], + strlen((char *)&pi_buff[2]) + 1); + + list_add_tail(&(next_partner_info->node), head); + next_partner_info = NULL; + + } while (more); + + return 0; +} +EXPORT_SYMBOL(hvcs_get_partner_info); + +/** + * hvcs_register_connection - establish a connection between this vty-server and + * a vty. + * @unit_address: The unit address of the vty-server adapter that is to be + * establish a connection. + * @p_partition_ID: The partition ID of the vty adapter that is to be connected. + * @p_unit_address: The unit address of the vty adapter to which the vty-server + * is to be connected. + * + * If this function is called once and -EINVAL is returned it may + * indicate that the partner info needs to be refreshed for the + * target unit address at which point the caller must invoke + * hvcs_get_partner_info() and then call this function again. If, + * for a second time, -EINVAL is returned then it indicates that + * there is probably already a partner connection registered to a + * different vty-server adapter. It is also possible that a second + * -EINVAL may indicate that one of the parms is not valid, for + * instance if the link was removed between the vty-server adapter + * and the vty adapter that you are trying to open. Don't shoot the + * messenger. Firmware implemented it this way. + */ +int hvcs_register_connection( uint32_t unit_address, + uint32_t p_partition_ID, uint32_t p_unit_address) +{ + long retval; + retval = plpar_hcall_norets(H_REGISTER_VTERM, unit_address, + p_partition_ID, p_unit_address); + return hvcs_convert(retval); +} +EXPORT_SYMBOL(hvcs_register_connection); + +/** + * hvcs_free_connection - free the connection between a vty-server and vty + * @unit_address: The unit address of the vty-server that is to have its + * connection severed. + * + * This function is used to free the partner connection between a vty-server + * adapter and a vty adapter. + * + * If -EBUSY is returned continue to call this function until 0 is returned. + */ +int hvcs_free_connection(uint32_t unit_address) +{ + long retval; + retval = plpar_hcall_norets(H_FREE_VTERM, unit_address); + return hvcs_convert(retval); +} +EXPORT_SYMBOL(hvcs_free_connection); diff --git a/arch/ppc64/Kconfig b/arch/ppc64/Kconfig deleted file mode 100644 index 9d10c12e87fe..000000000000 --- a/arch/ppc64/Kconfig +++ /dev/null @@ -1,520 +0,0 @@ -# -# For a description of the syntax of this configuration file, -# see Documentation/kbuild/kconfig-language.txt. -# - -config 64BIT - def_bool y - -config MMU - bool - default y - -config PPC_STD_MMU - def_bool y - -config UID16 - bool - -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - -config GENERIC_CALIBRATE_DELAY - bool - default y - -config GENERIC_ISA_DMA - bool - default y - -config EARLY_PRINTK - bool - default y - -config COMPAT - bool - default y - -config SCHED_NO_NO_OMIT_FRAME_POINTER - bool - default y - -config ARCH_MAY_HAVE_PC_FDC - bool - default y - -config PPC_STD_MMU - bool - default y - -# We optimistically allocate largepages from the VM, so make the limit -# large enough (16MB). This badly named config option is actually -# max order + 1 -config FORCE_MAX_ZONEORDER - int - default "9" if PPC_64K_PAGES - default "13" - -source "init/Kconfig" - -config SYSVIPC_COMPAT - bool - depends on COMPAT && SYSVIPC - default y - -menu "Platform support" - -choice - prompt "Platform Type" - default PPC_MULTIPLATFORM - -config PPC_ISERIES - bool "IBM Legacy iSeries" - -config PPC_MULTIPLATFORM - bool "Generic" - -endchoice - -config PPC_PSERIES - depends on PPC_MULTIPLATFORM - bool " IBM pSeries & new iSeries" - default y - -config PPC_BPA - bool " Broadband Processor Architecture" - depends on PPC_MULTIPLATFORM - -config PPC_PMAC - depends on PPC_MULTIPLATFORM - bool " Apple G5 based machines" - default y - select U3_DART - select GENERIC_TBSYNC - -config PPC_MAPLE - depends on PPC_MULTIPLATFORM - bool " Maple 970FX Evaluation Board" - select U3_DART - select MPIC_BROKEN_U3 - select GENERIC_TBSYNC - default n - help - This option enables support for the Maple 970FX Evaluation Board. - For more informations, refer to - -config PPC - bool - default y - -config PPC64 - bool - default y - -config PPC_OF - depends on PPC_MULTIPLATFORM - bool - default y - -config XICS - depends on PPC_PSERIES - bool - default y - -config MPIC - depends on PPC_PSERIES || PPC_PMAC || PPC_MAPLE - bool - default y - -config PPC_I8259 - depends on PPC_PSERIES - bool - default y - -config BPA_IIC - depends on PPC_BPA - bool - default y - -# VMX is pSeries only for now until somebody writes the iSeries -# exception vectors for it -config ALTIVEC - bool "Support for VMX (Altivec) vector unit" - depends on PPC_MULTIPLATFORM - default y - -config PPC_SPLPAR - depends on PPC_PSERIES - bool "Support for shared-processor logical partitions" - default n - help - Enabling this option will make the kernel run more efficiently - on logically-partitioned pSeries systems which use shared - processors, that is, which share physical processors between - two or more partitions. - -config KEXEC - bool "kexec system call (EXPERIMENTAL)" - depends on PPC_MULTIPLATFORM && EXPERIMENTAL - help - kexec is a system call that implements the ability to shutdown your - current kernel, and to start another kernel. It is like a reboot - but it is indepedent of the system firmware. And like a reboot - you can start any kernel with it, not just Linux. - - The name comes from the similiarity to the exec system call. - - It is an ongoing process to be certain the hardware in a machine - is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. - -source "drivers/cpufreq/Kconfig" - -config CPU_FREQ_PMAC64 - bool "Support for some Apple G5s" - depends on CPU_FREQ && PMAC_SMU && PPC64 - select CPU_FREQ_TABLE - help - This adds support for frequency switching on Apple iMac G5, - and some of the more recent desktop G5 machines as well. - -config IBMVIO - depends on PPC_PSERIES || PPC_ISERIES - bool - default y - -config U3_DART - bool - depends on PPC_MULTIPLATFORM - default n - -config MPIC_BROKEN_U3 - bool - depends on PPC_MAPLE - default y - -config GENERIC_TBSYNC - def_bool n - -config PPC_PMAC64 - bool - depends on PPC_PMAC - default y - -config BOOTX_TEXT - bool "Support for early boot text console" - depends PPC_OF - help - Say Y here to see progress messages from the boot firmware in text - mode. Requires an Open Firmware compatible video card. - -config POWER4 - def_bool y - -config PPC_FPU - def_bool y - -config POWER4_ONLY - bool "Optimize for POWER4" - default n - ---help--- - Cause the compiler to optimize for POWER4 processors. The resulting - binary will not work on POWER3 or RS64 processors when compiled with - binutils 2.15 or later. - -config IOMMU_VMERGE - bool "Enable IOMMU virtual merging (EXPERIMENTAL)" - depends on EXPERIMENTAL - default n - help - Cause IO segments sent to a device for DMA to be merged virtually - by the IOMMU when they happen to have been allocated contiguously. - This doesn't add pressure to the IOMMU allocator. However, some - drivers don't support getting large merged segments coming back - from *_map_sg(). Say Y if you know the drivers you are using are - properly handling this case. - -config SMP - bool "Symmetric multi-processing support" - ---help--- - This enables support for systems with more than one CPU. If you have - a system with only one CPU, say N. If you have a system with more - than one CPU, say Y. - - If you say N here, the kernel will run on single and multiprocessor - machines, but will use only one CPU of a multiprocessor machine. If - you say Y here, the kernel will run on single-processor machines. - On a single-processor machine, the kernel will run faster if you say - N here. - - If you don't know what to do here, say Y. - -config NR_CPUS - int "Maximum number of CPUs (2-128)" - range 2 128 - depends on SMP - default "32" - -config HMT - bool "Hardware multithreading" - depends on SMP && PPC_PSERIES && BROKEN - help - This option enables hardware multithreading on RS64 cpus. - pSeries systems p620 and p660 have such a cpu type. - -config NUMA - bool "NUMA support" - default y if SMP && PPC_PSERIES - -config ARCH_SELECT_MEMORY_MODEL - def_bool y - -config ARCH_FLATMEM_ENABLE - def_bool y - depends on !NUMA - -config ARCH_SPARSEMEM_ENABLE - def_bool y - -config ARCH_SPARSEMEM_DEFAULT - def_bool y - depends on NUMA - -source "mm/Kconfig" - -config HAVE_ARCH_EARLY_PFN_TO_NID - def_bool y - depends on NEED_MULTIPLE_NODES - -config ARCH_MEMORY_PROBE - def_bool y - depends on MEMORY_HOTPLUG - -# Some NUMA nodes have memory ranges that span -# other nodes. Even though a pfn is valid and -# between a node's start and end pfns, it may not -# reside on that node. -# -# This is a relatively temporary hack that should -# be able to go away when sparsemem is fully in -# place -config NODES_SPAN_OTHER_NODES - def_bool y - depends on NEED_MULTIPLE_NODES - -config PPC_64K_PAGES - bool "64k page size" - help - This option changes the kernel logical page size to 64k. On machines - without processor support for 64k pages, the kernel will simulate - them by loading each individual 4k page on demand transparently, - while on hardware with such support, it will be used to map - normal application pages. - -config SCHED_SMT - bool "SMT (Hyperthreading) scheduler support" - depends on SMP - default off - help - SMT scheduler support improves the CPU scheduler's decision making - when dealing with POWER5 cpus at a cost of slightly increased - overhead in some places. If unsure say N here. - -source "kernel/Kconfig.preempt" -source kernel/Kconfig.hz - -config EEH - bool "PCI Extended Error Handling (EEH)" if EMBEDDED - depends on PPC_PSERIES - default y if !EMBEDDED - -# -# Use the generic interrupt handling code in kernel/irq/: -# -config GENERIC_HARDIRQS - bool - default y - -config PPC_RTAS - bool - depends on PPC_PSERIES || PPC_BPA - default y - -config RTAS_ERROR_LOGGING - bool - depends on PPC_RTAS - default y - -config RTAS_PROC - bool "Proc interface to RTAS" - depends on PPC_RTAS - default y - -config RTAS_FLASH - tristate "Firmware flash interface" - depends on RTAS_PROC - -config SCANLOG - tristate "Scanlog dump interface" - depends on RTAS_PROC && PPC_PSERIES - -config LPARCFG - tristate "LPAR Configuration Data" - depends on PPC_PSERIES || PPC_ISERIES - help - Provide system capacity information via human readable - = pairs through a /proc/ppc64/lparcfg interface. - -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc//seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - -source "fs/Kconfig.binfmt" - -config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" - depends on SMP && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC) - select HOTPLUG - ---help--- - Say Y here to be able to turn CPUs off and on. - - Say N if you are unsure. - -config PROC_DEVICETREE - bool "Support for Open Firmware device tree in /proc" - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware. If unsure, say Y here. - -config CMDLINE_BOOL - bool "Default bootloader kernel arguments" - depends on !PPC_ISERIES - -config CMDLINE - string "Initial kernel command string" - depends on CMDLINE_BOOL - default "console=ttyS0,9600 console=tty0 root=/dev/sda2" - help - On some platforms, there is currently no way for the boot loader to - pass arguments to the kernel. For these platforms, you can supply - some command-line options at build time by entering them here. In - most cases you will need to specify the root device here. - -endmenu - -config ISA_DMA_API - bool - default y - -menu "Bus Options" - -config ISA - bool - help - Find out whether you have ISA slots on your motherboard. ISA is the - name of a bus system, i.e. the way the CPU talks to the other stuff - inside your box. If you have an Apple machine, say N here; if you - have an IBM RS/6000 or pSeries machine or a PReP machine, say Y. If - you have an embedded board, consult your board documentation. - -config SBUS - bool - -config MCA - bool - -config EISA - bool - -config PCI - bool "support for PCI devices" if (EMBEDDED && PPC_ISERIES) - default y - help - Find out whether your system includes a PCI bus. PCI is the name of - a bus system, i.e. the way the CPU talks to the other stuff inside - your box. If you say Y here, the kernel will include drivers and - infrastructure code to support PCI bus devices. - -config PCI_DOMAINS - bool - default PCI - -source "drivers/pci/Kconfig" - -source "drivers/pcmcia/Kconfig" - -source "drivers/pci/hotplug/Kconfig" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -menu "iSeries device drivers" - depends on PPC_ISERIES - -config VIOCONS - tristate "iSeries Virtual Console Support" - -config VIODASD - tristate "iSeries Virtual I/O disk support" - help - If you are running on an iSeries system and you want to use - virtual disks created and managed by OS/400, say Y. - -config VIOCD - tristate "iSeries Virtual I/O CD support" - help - If you are running Linux on an IBM iSeries system and you want to - read a CD drive owned by OS/400, say Y here. - -config VIOTAPE - tristate "iSeries Virtual Tape Support" - help - If you are running Linux on an iSeries system and you want Linux - to read and/or write a tape drive owned by OS/400, say Y here. - -endmenu - -config VIOPATH - bool - depends on VIOCONS || VIODASD || VIOCD || VIOTAPE || VETH - default y - -source "arch/powerpc/oprofile/Kconfig" - -source "arch/ppc64/Kconfig.debug" - -source "security/Kconfig" - -config KEYS_COMPAT - bool - depends on COMPAT && KEYS - default y - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/ppc64/kernel/Makefile b/arch/ppc64/kernel/Makefile index d0edea503c49..e876c213f5ce 100644 --- a/arch/ppc64/kernel/Makefile +++ b/arch/ppc64/kernel/Makefile @@ -2,44 +2,6 @@ # Makefile for the linux ppc64 kernel. # -ifneq ($(CONFIG_PPC_MERGE),y) - -EXTRA_CFLAGS += -mno-minimal-toc -extra-y := head.o vmlinux.lds - -obj-y := misc.o prom.o - -endif - -obj-y += idle.o dma.o \ - align.o \ - iommu.o - -pci-obj-$(CONFIG_PPC_MULTIPLATFORM) += pci_dn.o pci_direct_iommu.o - -obj-$(CONFIG_PCI) += pci.o pci_iommu.o iomap.o $(pci-obj-y) +obj-y += idle.o align.o obj-$(CONFIG_PPC_MULTIPLATFORM) += nvram.o -ifneq ($(CONFIG_PPC_MERGE),y) -obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o -endif - -obj-$(CONFIG_KEXEC) += machine_kexec.o -obj-$(CONFIG_MODULES) += module.o -ifneq ($(CONFIG_PPC_MERGE),y) -obj-$(CONFIG_MODULES) += ppc_ksyms.o -endif -obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o -ifneq ($(CONFIG_PPC_MERGE),y) -obj-$(CONFIG_BOOTX_TEXT) += btext.o -endif -obj-$(CONFIG_HVCS) += hvcserver.o - -obj-$(CONFIG_KPROBES) += kprobes.o - -ifneq ($(CONFIG_PPC_MERGE),y) -ifeq ($(CONFIG_PPC_ISERIES),y) -arch/ppc64/kernel/head.o: arch/powerpc/kernel/lparmap.s -AFLAGS_head.o += -Iarch/powerpc/kernel -endif -endif diff --git a/arch/ppc64/kernel/asm-offsets.c b/arch/ppc64/kernel/asm-offsets.c deleted file mode 100644 index 84ab5c18ef52..000000000000 --- a/arch/ppc64/kernel/asm-offsets.c +++ /dev/null @@ -1,195 +0,0 @@ -/* - * This program is used to generate definitions needed by - * assembly language modules. - * - * We use the technique used in the OSF Mach kernel code: - * generate asm statements containing #defines, - * compile this file to assembler, and then extract the - * #defines from the assembly-language output. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include - -#define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) - -#define BLANK() asm volatile("\n->" : : ) - -int main(void) -{ - /* thread struct on stack */ - DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); - DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); - DEFINE(TI_SC_NOERR, offsetof(struct thread_info, syscall_noerror)); - - /* task_struct->thread */ - DEFINE(THREAD, offsetof(struct task_struct, thread)); - DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); - DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode)); - DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0])); - DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr)); - DEFINE(KSP, offsetof(struct thread_struct, ksp)); - DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid)); - -#ifdef CONFIG_ALTIVEC - DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0])); - DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave)); - DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr)); - DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr)); -#endif /* CONFIG_ALTIVEC */ - DEFINE(MM, offsetof(struct task_struct, mm)); - DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); - - DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size)); - DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size)); - DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page)); - DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size)); - DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size)); - DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page)); - DEFINE(PLATFORM_LPAR, PLATFORM_LPAR); - - /* paca */ - DEFINE(PACA_SIZE, sizeof(struct paca_struct)); - DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); - DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start)); - DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack)); - DEFINE(PACACURRENT, offsetof(struct paca_struct, __current)); - DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr)); - DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real)); - DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr)); - DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr)); - DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1)); - DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc)); - DEFINE(PACAPROCENABLED, offsetof(struct paca_struct, proc_enabled)); - DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); - DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr)); - DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); -#ifdef CONFIG_PPC_64K_PAGES - DEFINE(PACAPGDIR, offsetof(struct paca_struct, pgdir)); -#endif -#ifdef CONFIG_HUGETLB_PAGE - DEFINE(PACALOWHTLBAREAS, offsetof(struct paca_struct, context.low_htlb_areas)); - DEFINE(PACAHIGHHTLBAREAS, offsetof(struct paca_struct, context.high_htlb_areas)); -#endif /* CONFIG_HUGETLB_PAGE */ - DEFINE(PACADEFAULTDECR, offsetof(struct paca_struct, default_decr)); - DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen)); - DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc)); - DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb)); - DEFINE(PACA_EXDSI, offsetof(struct paca_struct, exdsi)); - DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); - DEFINE(PACALPPACA, offsetof(struct paca_struct, lppaca)); - DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); - DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); - DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); - DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); - DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); - - /* RTAS */ - DEFINE(RTASBASE, offsetof(struct rtas_t, base)); - DEFINE(RTASENTRY, offsetof(struct rtas_t, entry)); - - /* Interrupt register frame */ - DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD); - - DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); - - /* 288 = # of volatile regs, int & fp, for leaf routines */ - /* which do not stack a frame. See the PPC64 ABI. */ - DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 288); - /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ - DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); - DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); - DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0])); - DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1])); - DEFINE(GPR2, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[2])); - DEFINE(GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[3])); - DEFINE(GPR4, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[4])); - DEFINE(GPR5, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[5])); - DEFINE(GPR6, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[6])); - DEFINE(GPR7, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[7])); - DEFINE(GPR8, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[8])); - DEFINE(GPR9, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[9])); - DEFINE(GPR10, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[10])); - DEFINE(GPR11, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[11])); - DEFINE(GPR12, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[12])); - DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13])); - /* - * Note: these symbols include _ because they overlap with special - * register names - */ - DEFINE(_NIP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, nip)); - DEFINE(_MSR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, msr)); - DEFINE(_CTR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ctr)); - DEFINE(_LINK, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, link)); - DEFINE(_CCR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ccr)); - DEFINE(_XER, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, xer)); - DEFINE(_DAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar)); - DEFINE(_DSISR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr)); - DEFINE(ORIG_GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, orig_gpr3)); - DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result)); - DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap)); - DEFINE(SOFTE, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, softe)); - - /* These _only_ to be used with {PROM,RTAS}_FRAME_SIZE!!! */ - DEFINE(_SRR0, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)); - DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8); - - DEFINE(CLONE_VM, CLONE_VM); - DEFINE(CLONE_UNTRACED, CLONE_UNTRACED); - - /* About the CPU features table */ - DEFINE(CPU_SPEC_ENTRY_SIZE, sizeof(struct cpu_spec)); - DEFINE(CPU_SPEC_PVR_MASK, offsetof(struct cpu_spec, pvr_mask)); - DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value)); - DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features)); - DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup)); - - /* systemcfg offsets for use by vdso */ - DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp)); - DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec)); - DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs)); - DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec)); - DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count)); - DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest)); - DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime)); - DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32)); - DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64)); - - /* timeval/timezone offsets for use by vdso */ - DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec)); - DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec)); - DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec)); - DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec)); - DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); - DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); - - return 0; -} diff --git a/arch/ppc64/kernel/btext.c b/arch/ppc64/kernel/btext.c deleted file mode 100644 index 506a37885c5c..000000000000 --- a/arch/ppc64/kernel/btext.c +++ /dev/null @@ -1,792 +0,0 @@ -/* - * Procedures for drawing on the screen early on in the boot process. - * - * Benjamin Herrenschmidt - */ -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#undef NO_SCROLL - -#ifndef NO_SCROLL -static void scrollscreen(void); -#endif - -static void draw_byte(unsigned char c, long locX, long locY); -static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb); -static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb); -static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb); - -static int g_loc_X; -static int g_loc_Y; -static int g_max_loc_X; -static int g_max_loc_Y; - -static int dispDeviceRowBytes; -static int dispDeviceDepth; -static int dispDeviceRect[4]; -static unsigned char *dispDeviceBase, *logicalDisplayBase; - -unsigned long disp_BAT[2] __initdata = {0, 0}; - -#define cmapsz (16*256) - -static unsigned char vga_font[cmapsz]; - -int boot_text_mapped; -int force_printk_to_btext = 0; - - -/* Here's a small text engine to use during early boot - * or for debugging purposes - * - * todo: - * - * - build some kind of vgacon with it to enable early printk - * - move to a separate file - * - add a few video driver hooks to keep in sync with display - * changes. - */ - -void map_boot_text(void) -{ - unsigned long base, offset, size; - unsigned char *vbase; - - /* By default, we are no longer mapped */ - boot_text_mapped = 0; - if (dispDeviceBase == 0) - return; - base = ((unsigned long) dispDeviceBase) & 0xFFFFF000UL; - offset = ((unsigned long) dispDeviceBase) - base; - size = dispDeviceRowBytes * dispDeviceRect[3] + offset - + dispDeviceRect[0]; - vbase = __ioremap(base, size, _PAGE_NO_CACHE); - if (vbase == 0) - return; - logicalDisplayBase = vbase + offset; - boot_text_mapped = 1; -} - -int btext_initialize(struct device_node *np) -{ - unsigned int width, height, depth, pitch; - unsigned long address = 0; - u32 *prop; - - prop = (u32 *)get_property(np, "width", NULL); - if (prop == NULL) - return -EINVAL; - width = *prop; - prop = (u32 *)get_property(np, "height", NULL); - if (prop == NULL) - return -EINVAL; - height = *prop; - prop = (u32 *)get_property(np, "depth", NULL); - if (prop == NULL) - return -EINVAL; - depth = *prop; - pitch = width * ((depth + 7) / 8); - prop = (u32 *)get_property(np, "linebytes", NULL); - if (prop) - pitch = *prop; - if (pitch == 1) - pitch = 0x1000; - prop = (u32 *)get_property(np, "address", NULL); - if (prop) - address = *prop; - - /* FIXME: Add support for PCI reg properties */ - - if (address == 0) - return -EINVAL; - - g_loc_X = 0; - g_loc_Y = 0; - g_max_loc_X = width / 8; - g_max_loc_Y = height / 16; - logicalDisplayBase = (unsigned char *)address; - dispDeviceBase = (unsigned char *)address; - dispDeviceRowBytes = pitch; - dispDeviceDepth = depth; - dispDeviceRect[0] = dispDeviceRect[1] = 0; - dispDeviceRect[2] = width; - dispDeviceRect[3] = height; - - map_boot_text(); - - return 0; -} - -static void btext_putc(unsigned char c) -{ - btext_drawchar(c); -} - -void __init init_boot_display(void) -{ - char *name; - struct device_node *np = NULL; - int rc = -ENODEV; - - printk("trying to initialize btext ...\n"); - - name = (char *)get_property(of_chosen, "linux,stdout-path", NULL); - if (name != NULL) { - np = of_find_node_by_path(name); - if (np != NULL) { - if (strcmp(np->type, "display") != 0) { - printk("boot stdout isn't a display !\n"); - of_node_put(np); - np = NULL; - } - } - } - if (np) - rc = btext_initialize(np); - if (rc) { - for (np = NULL; (np = of_find_node_by_type(np, "display"));) { - if (get_property(np, "linux,opened", NULL)) { - printk("trying %s ...\n", np->full_name); - rc = btext_initialize(np); - printk("result: %d\n", rc); - } - if (rc == 0) - break; - } - } - if (rc == 0 && udbg_putc == NULL) - udbg_putc = btext_putc; -} - - -/* Calc the base address of a given point (x,y) */ -static unsigned char * calc_base(int x, int y) -{ - unsigned char *base; - - base = logicalDisplayBase; - if (base == 0) - base = dispDeviceBase; - base += (x + dispDeviceRect[0]) * (dispDeviceDepth >> 3); - base += (y + dispDeviceRect[1]) * dispDeviceRowBytes; - return base; -} - -/* Adjust the display to a new resolution */ -void btext_update_display(unsigned long phys, int width, int height, - int depth, int pitch) -{ - if (dispDeviceBase == 0) - return; - - /* check it's the same frame buffer (within 256MB) */ - if ((phys ^ (unsigned long)dispDeviceBase) & 0xf0000000) - return; - - dispDeviceBase = (__u8 *) phys; - dispDeviceRect[0] = 0; - dispDeviceRect[1] = 0; - dispDeviceRect[2] = width; - dispDeviceRect[3] = height; - dispDeviceDepth = depth; - dispDeviceRowBytes = pitch; - if (boot_text_mapped) { - iounmap(logicalDisplayBase); - boot_text_mapped = 0; - } - map_boot_text(); - g_loc_X = 0; - g_loc_Y = 0; - g_max_loc_X = width / 8; - g_max_loc_Y = height / 16; -} - -void btext_clearscreen(void) -{ - unsigned long *base = (unsigned long *)calc_base(0, 0); - unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * - (dispDeviceDepth >> 3)) >> 3; - int i,j; - - for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++) - { - unsigned long *ptr = base; - for(j=width; j; --j) - *(ptr++) = 0; - base += (dispDeviceRowBytes >> 3); - } -} - -#ifndef NO_SCROLL -static void scrollscreen(void) -{ - unsigned long *src = (unsigned long *)calc_base(0,16); - unsigned long *dst = (unsigned long *)calc_base(0,0); - unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * - (dispDeviceDepth >> 3)) >> 3; - int i,j; - - for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++) - { - unsigned long *src_ptr = src; - unsigned long *dst_ptr = dst; - for(j=width; j; --j) - *(dst_ptr++) = *(src_ptr++); - src += (dispDeviceRowBytes >> 3); - dst += (dispDeviceRowBytes >> 3); - } - for (i=0; i<16; i++) - { - unsigned long *dst_ptr = dst; - for(j=width; j; --j) - *(dst_ptr++) = 0; - dst += (dispDeviceRowBytes >> 3); - } -} -#endif /* ndef NO_SCROLL */ - -void btext_drawchar(char c) -{ - int cline = 0; -#ifdef NO_SCROLL - int x; -#endif - if (!boot_text_mapped) - return; - - switch (c) { - case '\b': - if (g_loc_X > 0) - --g_loc_X; - break; - case '\t': - g_loc_X = (g_loc_X & -8) + 8; - break; - case '\r': - g_loc_X = 0; - break; - case '\n': - g_loc_X = 0; - g_loc_Y++; - cline = 1; - break; - default: - draw_byte(c, g_loc_X++, g_loc_Y); - } - if (g_loc_X >= g_max_loc_X) { - g_loc_X = 0; - g_loc_Y++; - cline = 1; - } -#ifndef NO_SCROLL - while (g_loc_Y >= g_max_loc_Y) { - scrollscreen(); - g_loc_Y--; - } -#else - /* wrap around from bottom to top of screen so we don't - waste time scrolling each line. -- paulus. */ - if (g_loc_Y >= g_max_loc_Y) - g_loc_Y = 0; - if (cline) { - for (x = 0; x < g_max_loc_X; ++x) - draw_byte(' ', x, g_loc_Y); - } -#endif -} - -void btext_drawstring(const char *c) -{ - if (!boot_text_mapped) - return; - while (*c) - btext_drawchar(*c++); -} - -void btext_drawhex(unsigned long v) -{ - char *hex_table = "0123456789abcdef"; - - if (!boot_text_mapped) - return; - btext_drawchar(hex_table[(v >> 60) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 56) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 52) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 48) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 44) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 40) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 36) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 32) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 28) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 24) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 20) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 16) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 12) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 8) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 4) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 0) & 0x0000000FUL]); - btext_drawchar(' '); -} - -static void draw_byte(unsigned char c, long locX, long locY) -{ - unsigned char *base = calc_base(locX << 3, locY << 4); - unsigned char *font = &vga_font[((unsigned int)c) * 16]; - int rb = dispDeviceRowBytes; - - switch(dispDeviceDepth) { - case 24: - case 32: - draw_byte_32(font, (unsigned int *)base, rb); - break; - case 15: - case 16: - draw_byte_16(font, (unsigned int *)base, rb); - break; - case 8: - draw_byte_8(font, (unsigned int *)base, rb); - break; - } -} - -static unsigned int expand_bits_8[16] = { - 0x00000000, - 0x000000ff, - 0x0000ff00, - 0x0000ffff, - 0x00ff0000, - 0x00ff00ff, - 0x00ffff00, - 0x00ffffff, - 0xff000000, - 0xff0000ff, - 0xff00ff00, - 0xff00ffff, - 0xffff0000, - 0xffff00ff, - 0xffffff00, - 0xffffffff -}; - -static unsigned int expand_bits_16[4] = { - 0x00000000, - 0x0000ffff, - 0xffff0000, - 0xffffffff -}; - - -static void draw_byte_32(unsigned char *font, unsigned int *base, int rb) -{ - int l, bits; - int fg = 0xFFFFFFFFUL; - int bg = 0x00000000UL; - - for (l = 0; l < 16; ++l) - { - bits = *font++; - base[0] = (-(bits >> 7) & fg) ^ bg; - base[1] = (-((bits >> 6) & 1) & fg) ^ bg; - base[2] = (-((bits >> 5) & 1) & fg) ^ bg; - base[3] = (-((bits >> 4) & 1) & fg) ^ bg; - base[4] = (-((bits >> 3) & 1) & fg) ^ bg; - base[5] = (-((bits >> 2) & 1) & fg) ^ bg; - base[6] = (-((bits >> 1) & 1) & fg) ^ bg; - base[7] = (-(bits & 1) & fg) ^ bg; - base = (unsigned int *) ((char *)base + rb); - } -} - -static void draw_byte_16(unsigned char *font, unsigned int *base, int rb) -{ - int l, bits; - int fg = 0xFFFFFFFFUL; - int bg = 0x00000000UL; - unsigned int *eb = (int *)expand_bits_16; - - for (l = 0; l < 16; ++l) - { - bits = *font++; - base[0] = (eb[bits >> 6] & fg) ^ bg; - base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg; - base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg; - base[3] = (eb[bits & 3] & fg) ^ bg; - base = (unsigned int *) ((char *)base + rb); - } -} - -static void draw_byte_8(unsigned char *font, unsigned int *base, int rb) -{ - int l, bits; - int fg = 0x0F0F0F0FUL; - int bg = 0x00000000UL; - unsigned int *eb = (int *)expand_bits_8; - - for (l = 0; l < 16; ++l) - { - bits = *font++; - base[0] = (eb[bits >> 4] & fg) ^ bg; - base[1] = (eb[bits & 0xf] & fg) ^ bg; - base = (unsigned int *) ((char *)base + rb); - } -} - -static unsigned char vga_font[cmapsz] = { -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd, -0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff, -0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe, -0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, -0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, -0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, -0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00, -0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd, -0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e, -0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30, -0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63, -0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8, -0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e, -0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, -0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb, -0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6, -0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, -0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0, -0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c, -0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c, -0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, -0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c, -0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18, -0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, -0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30, -0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18, -0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, -0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe, -0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, -0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18, -0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, -0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, -0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, -0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde, -0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, -0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0, -0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c, -0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, -0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, -0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c, -0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60, -0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7, -0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, -0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c, -0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c, -0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, -0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, -0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18, -0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, -0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30, -0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, -0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00, -0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06, -0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60, -0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb, -0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66, -0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60, -0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30, -0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3, -0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18, -0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, -0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, -0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00, -0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe, -0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, -0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, -0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06, -0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe, -0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, -0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18, -0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66, -0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6, -0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00, -0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b, -0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c, -0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00, -0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, -0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, -0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, -0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00, -0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, -0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, -0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18, -0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, -0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00, -0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, -0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, -0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc, -0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, -0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, -0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, -0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, -0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06, -0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, -0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, -0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36, -0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44, -0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, -0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, -0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, -0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, -0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, -0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, -0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, -0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, -0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, -0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0, -0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, -0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, -0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0, -0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8, -0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66, -0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, -0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66, -0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60, -0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, -0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18, -0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, -0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, -0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00, -0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, -0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c, -0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00, -0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, -}; diff --git a/arch/ppc64/kernel/dma.c b/arch/ppc64/kernel/dma.c deleted file mode 100644 index 7c3419656ccc..000000000000 --- a/arch/ppc64/kernel/dma.c +++ /dev/null @@ -1,151 +0,0 @@ -/* - * Copyright (C) 2004 IBM Corporation - * - * Implements the generic device dma API for ppc64. Handles - * the pci and vio busses - */ - -#include -#include -/* Include the busses we support */ -#include -#include -#include -#include - -static struct dma_mapping_ops *get_dma_ops(struct device *dev) -{ -#ifdef CONFIG_PCI - if (dev->bus == &pci_bus_type) - return &pci_dma_ops; -#endif -#ifdef CONFIG_IBMVIO - if (dev->bus == &vio_bus_type) - return &vio_dma_ops; -#endif - return NULL; -} - -int dma_supported(struct device *dev, u64 mask) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - return dma_ops->dma_supported(dev, mask); - BUG(); - return 0; -} -EXPORT_SYMBOL(dma_supported); - -int dma_set_mask(struct device *dev, u64 dma_mask) -{ -#ifdef CONFIG_PCI - if (dev->bus == &pci_bus_type) - return pci_set_dma_mask(to_pci_dev(dev), dma_mask); -#endif -#ifdef CONFIG_IBMVIO - if (dev->bus == &vio_bus_type) - return -EIO; -#endif /* CONFIG_IBMVIO */ - BUG(); - return 0; -} -EXPORT_SYMBOL(dma_set_mask); - -void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - return dma_ops->alloc_coherent(dev, size, dma_handle, flag); - BUG(); - return NULL; -} -EXPORT_SYMBOL(dma_alloc_coherent); - -void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); - else - BUG(); -} -EXPORT_SYMBOL(dma_free_coherent); - -dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - return dma_ops->map_single(dev, cpu_addr, size, direction); - BUG(); - return (dma_addr_t)0; -} -EXPORT_SYMBOL(dma_map_single); - -void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - dma_ops->unmap_single(dev, dma_addr, size, direction); - else - BUG(); -} -EXPORT_SYMBOL(dma_unmap_single); - -dma_addr_t dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - return dma_ops->map_single(dev, - (page_address(page) + offset), size, direction); - BUG(); - return (dma_addr_t)0; -} -EXPORT_SYMBOL(dma_map_page); - -void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - dma_ops->unmap_single(dev, dma_address, size, direction); - else - BUG(); -} -EXPORT_SYMBOL(dma_unmap_page); - -int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - return dma_ops->map_sg(dev, sg, nents, direction); - BUG(); - return 0; -} -EXPORT_SYMBOL(dma_map_sg); - -void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops) - dma_ops->unmap_sg(dev, sg, nhwentries, direction); - else - BUG(); -} -EXPORT_SYMBOL(dma_unmap_sg); diff --git a/arch/ppc64/kernel/head.S b/arch/ppc64/kernel/head.S deleted file mode 100644 index 1c869ea72d28..000000000000 --- a/arch/ppc64/kernel/head.S +++ /dev/null @@ -1,2007 +0,0 @@ -/* - * arch/ppc64/kernel/head.S - * - * PowerPC version - * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) - * - * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP - * Copyright (C) 1996 Cort Dougan - * Adapted for Power Macintosh by Paul Mackerras. - * Low-level exception handlers and MMU support - * rewritten by Paul Mackerras. - * Copyright (C) 1996 Paul Mackerras. - * - * Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and - * Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com - * - * This file contains the low-level support and setup for the - * PowerPC-64 platform, including trap and interrupt dispatch. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef CONFIG_PPC_ISERIES -#define DO_SOFT_DISABLE -#endif - -/* - * We layout physical memory as follows: - * 0x0000 - 0x00ff : Secondary processor spin code - * 0x0100 - 0x2fff : pSeries Interrupt prologs - * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs - * 0x6000 - 0x6fff : Initial (CPU0) segment table - * 0x7000 - 0x7fff : FWNMI data area - * 0x8000 - : Early init and support code - */ - -/* - * SPRG Usage - * - * Register Definition - * - * SPRG0 reserved for hypervisor - * SPRG1 temp - used to save gpr - * SPRG2 temp - used to save gpr - * SPRG3 virt addr of paca - */ - -/* - * Entering into this code we make the following assumptions: - * For pSeries: - * 1. The MMU is off & open firmware is running in real mode. - * 2. The kernel is entered at __start - * - * For iSeries: - * 1. The MMU is on (as it always is for iSeries) - * 2. The kernel is entered at system_reset_iSeries - */ - - .text - .globl _stext -_stext: -#ifdef CONFIG_PPC_MULTIPLATFORM -_GLOBAL(__start) - /* NOP this out unconditionally */ -BEGIN_FTR_SECTION - b .__start_initialization_multiplatform -END_FTR_SECTION(0, 1) -#endif /* CONFIG_PPC_MULTIPLATFORM */ - - /* Catch branch to 0 in real mode */ - trap - -#ifdef CONFIG_PPC_ISERIES - /* - * At offset 0x20, there is a pointer to iSeries LPAR data. - * This is required by the hypervisor - */ - . = 0x20 - .llong hvReleaseData-KERNELBASE - - /* - * At offset 0x28 and 0x30 are offsets to the mschunks_map - * array (used by the iSeries LPAR debugger to do translation - * between physical addresses and absolute addresses) and - * to the pidhash table (also used by the debugger) - */ - .llong mschunks_map-KERNELBASE - .llong 0 /* pidhash-KERNELBASE SFRXXX */ - - /* Offset 0x38 - Pointer to start of embedded System.map */ - .globl embedded_sysmap_start -embedded_sysmap_start: - .llong 0 - /* Offset 0x40 - Pointer to end of embedded System.map */ - .globl embedded_sysmap_end -embedded_sysmap_end: - .llong 0 - -#endif /* CONFIG_PPC_ISERIES */ - - /* Secondary processors spin on this value until it goes to 1. */ - .globl __secondary_hold_spinloop -__secondary_hold_spinloop: - .llong 0x0 - - /* Secondary processors write this value with their cpu # */ - /* after they enter the spin loop immediately below. */ - .globl __secondary_hold_acknowledge -__secondary_hold_acknowledge: - .llong 0x0 - - . = 0x60 -/* - * The following code is used on pSeries to hold secondary processors - * in a spin loop after they have been freed from OpenFirmware, but - * before the bulk of the kernel has been relocated. This code - * is relocated to physical address 0x60 before prom_init is run. - * All of it must fit below the first exception vector at 0x100. - */ -_GLOBAL(__secondary_hold) - mfmsr r24 - ori r24,r24,MSR_RI - mtmsrd r24 /* RI on */ - - /* Grab our linux cpu number */ - mr r24,r3 - - /* Tell the master cpu we're here */ - /* Relocation is off & we are located at an address less */ - /* than 0x100, so only need to grab low order offset. */ - std r24,__secondary_hold_acknowledge@l(0) - sync - - /* All secondary cpus wait here until told to start. */ -100: ld r4,__secondary_hold_spinloop@l(0) - cmpdi 0,r4,1 - bne 100b - -#ifdef CONFIG_HMT - b .hmt_init -#else -#ifdef CONFIG_SMP - mr r3,r24 - b .pSeries_secondary_smp_init -#else - BUG_OPCODE -#endif -#endif - -/* This value is used to mark exception frames on the stack. */ - .section ".toc","aw" -exception_marker: - .tc ID_72656773_68657265[TC],0x7265677368657265 - .text - -/* - * The following macros define the code that appears as - * the prologue to each of the exception handlers. They - * are split into two parts to allow a single kernel binary - * to be used for pSeries and iSeries. - * LOL. One day... - paulus - */ - -/* - * We make as much of the exception code common between native - * exception handlers (including pSeries LPAR) and iSeries LPAR - * implementations as possible. - */ - -/* - * This is the start of the interrupt handlers for pSeries - * This code runs with relocation off. - */ -#define EX_R9 0 -#define EX_R10 8 -#define EX_R11 16 -#define EX_R12 24 -#define EX_R13 32 -#define EX_SRR0 40 -#define EX_DAR 48 -#define EX_DSISR 56 -#define EX_CCR 60 -#define EX_R3 64 -#define EX_LR 72 - -#define EXCEPTION_PROLOG_PSERIES(area, label) \ - mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ - std r9,area+EX_R9(r13); /* save r9 - r12 */ \ - std r10,area+EX_R10(r13); \ - std r11,area+EX_R11(r13); \ - std r12,area+EX_R12(r13); \ - mfspr r9,SPRN_SPRG1; \ - std r9,area+EX_R13(r13); \ - mfcr r9; \ - clrrdi r12,r13,32; /* get high part of &label */ \ - mfmsr r10; \ - mfspr r11,SPRN_SRR0; /* save SRR0 */ \ - ori r12,r12,(label)@l; /* virt addr of handler */ \ - ori r10,r10,MSR_IR|MSR_DR|MSR_RI; \ - mtspr SPRN_SRR0,r12; \ - mfspr r12,SPRN_SRR1; /* and SRR1 */ \ - mtspr SPRN_SRR1,r10; \ - rfid; \ - b . /* prevent speculative execution */ - -/* - * This is the start of the interrupt handlers for iSeries - * This code runs with relocation on. - */ -#define EXCEPTION_PROLOG_ISERIES_1(area) \ - mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ - std r9,area+EX_R9(r13); /* save r9 - r12 */ \ - std r10,area+EX_R10(r13); \ - std r11,area+EX_R11(r13); \ - std r12,area+EX_R12(r13); \ - mfspr r9,SPRN_SPRG1; \ - std r9,area+EX_R13(r13); \ - mfcr r9 - -#define EXCEPTION_PROLOG_ISERIES_2 \ - mfmsr r10; \ - ld r11,PACALPPACA+LPPACASRR0(r13); \ - ld r12,PACALPPACA+LPPACASRR1(r13); \ - ori r10,r10,MSR_RI; \ - mtmsrd r10,1 - -/* - * The common exception prolog is used for all except a few exceptions - * such as a segment miss on a kernel address. We have to be prepared - * to take another exception from the point where we first touch the - * kernel stack onwards. - * - * On entry r13 points to the paca, r9-r13 are saved in the paca, - * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and - * SRR1, and relocation is on. - */ -#define EXCEPTION_PROLOG_COMMON(n, area) \ - andi. r10,r12,MSR_PR; /* See if coming from user */ \ - mr r10,r1; /* Save r1 */ \ - subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ - beq- 1f; \ - ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ -1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ - bge- cr1,bad_stack; /* abort if it is */ \ - std r9,_CCR(r1); /* save CR in stackframe */ \ - std r11,_NIP(r1); /* save SRR0 in stackframe */ \ - std r12,_MSR(r1); /* save SRR1 in stackframe */ \ - std r10,0(r1); /* make stack chain pointer */ \ - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r10,GPR1(r1); /* save r1 in stackframe */ \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ - ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ - ld r10,area+EX_R10(r13); \ - std r9,GPR9(r1); \ - std r10,GPR10(r1); \ - ld r9,area+EX_R11(r13); /* move r11 - r13 to stackframe */ \ - ld r10,area+EX_R12(r13); \ - ld r11,area+EX_R13(r13); \ - std r9,GPR11(r1); \ - std r10,GPR12(r1); \ - std r11,GPR13(r1); \ - ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ - mflr r9; /* save LR in stackframe */ \ - std r9,_LINK(r1); \ - mfctr r10; /* save CTR in stackframe */ \ - std r10,_CTR(r1); \ - mfspr r11,SPRN_XER; /* save XER in stackframe */ \ - std r11,_XER(r1); \ - li r9,(n)+1; \ - std r9,_TRAP(r1); /* set trap number */ \ - li r10,0; \ - ld r11,exception_marker@toc(r2); \ - std r10,RESULT(r1); /* clear regs->result */ \ - std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ - -/* - * Exception vectors. - */ -#define STD_EXCEPTION_PSERIES(n, label) \ - . = n; \ - .globl label##_pSeries; \ -label##_pSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r13; /* save r13 */ \ - RUNLATCH_ON(r13); \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) - -#define STD_EXCEPTION_ISERIES(n, label, area) \ - .globl label##_iSeries; \ -label##_iSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r13; /* save r13 */ \ - RUNLATCH_ON(r13); \ - EXCEPTION_PROLOG_ISERIES_1(area); \ - EXCEPTION_PROLOG_ISERIES_2; \ - b label##_common - -#define MASKABLE_EXCEPTION_ISERIES(n, label) \ - .globl label##_iSeries; \ -label##_iSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r13; /* save r13 */ \ - RUNLATCH_ON(r13); \ - EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN); \ - lbz r10,PACAPROCENABLED(r13); \ - cmpwi 0,r10,0; \ - beq- label##_iSeries_masked; \ - EXCEPTION_PROLOG_ISERIES_2; \ - b label##_common; \ - -#ifdef DO_SOFT_DISABLE -#define DISABLE_INTS \ - lbz r10,PACAPROCENABLED(r13); \ - li r11,0; \ - std r10,SOFTE(r1); \ - mfmsr r10; \ - stb r11,PACAPROCENABLED(r13); \ - ori r10,r10,MSR_EE; \ - mtmsrd r10,1 - -#define ENABLE_INTS \ - lbz r10,PACAPROCENABLED(r13); \ - mfmsr r11; \ - std r10,SOFTE(r1); \ - ori r11,r11,MSR_EE; \ - mtmsrd r11,1 - -#else /* hard enable/disable interrupts */ -#define DISABLE_INTS - -#define ENABLE_INTS \ - ld r12,_MSR(r1); \ - mfmsr r11; \ - rlwimi r11,r12,0,MSR_EE; \ - mtmsrd r11,1 - -#endif - -#define STD_EXCEPTION_COMMON(trap, label, hdlr) \ - .align 7; \ - .globl label##_common; \ -label##_common: \ - EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ - DISABLE_INTS; \ - bl .save_nvgprs; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - bl hdlr; \ - b .ret_from_except - -#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr) \ - .align 7; \ - .globl label##_common; \ -label##_common: \ - EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ - DISABLE_INTS; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - bl hdlr; \ - b .ret_from_except_lite - -/* - * Start of pSeries system interrupt routines - */ - . = 0x100 - .globl __start_interrupts -__start_interrupts: - - STD_EXCEPTION_PSERIES(0x100, system_reset) - - . = 0x200 -_machine_check_pSeries: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 /* save r13 */ - RUNLATCH_ON(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) - - . = 0x300 - .globl data_access_pSeries -data_access_pSeries: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 -BEGIN_FTR_SECTION - mtspr SPRN_SPRG2,r12 - mfspr r13,SPRN_DAR - mfspr r12,SPRN_DSISR - srdi r13,r13,60 - rlwimi r13,r12,16,0x20 - mfcr r12 - cmpwi r13,0x2c - beq .do_stab_bolted_pSeries - mtcrf 0x80,r12 - mfspr r12,SPRN_SPRG2 -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common) - - . = 0x380 - .globl data_access_slb_pSeries -data_access_slb_pSeries: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 - RUNLATCH_ON(r13) - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 -#ifdef __DISABLED__ - /* Keep that around for when we re-implement dynamic VSIDs */ - cmpdi r3,0 - bge slb_miss_user_pseries -#endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ - b .slb_miss_realmode /* Rel. branch works in real mode */ - - STD_EXCEPTION_PSERIES(0x400, instruction_access) - - . = 0x480 - .globl instruction_access_slb_pSeries -instruction_access_slb_pSeries: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 - RUNLATCH_ON(r13) - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 -#ifdef __DISABLED__ - /* Keep that around for when we re-implement dynamic VSIDs */ - cmpdi r3,0 - bge slb_miss_user_pseries -#endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ - b .slb_miss_realmode /* Rel. branch works in real mode */ - - STD_EXCEPTION_PSERIES(0x500, hardware_interrupt) - STD_EXCEPTION_PSERIES(0x600, alignment) - STD_EXCEPTION_PSERIES(0x700, program_check) - STD_EXCEPTION_PSERIES(0x800, fp_unavailable) - STD_EXCEPTION_PSERIES(0x900, decrementer) - STD_EXCEPTION_PSERIES(0xa00, trap_0a) - STD_EXCEPTION_PSERIES(0xb00, trap_0b) - - . = 0xc00 - .globl system_call_pSeries -system_call_pSeries: - HMT_MEDIUM - RUNLATCH_ON(r9) - mr r9,r13 - mfmsr r10 - mfspr r13,SPRN_SPRG3 - mfspr r11,SPRN_SRR0 - clrrdi r12,r13,32 - oris r12,r12,system_call_common@h - ori r12,r12,system_call_common@l - mtspr SPRN_SRR0,r12 - ori r10,r10,MSR_IR|MSR_DR|MSR_RI - mfspr r12,SPRN_SRR1 - mtspr SPRN_SRR1,r10 - rfid - b . /* prevent speculative execution */ - - STD_EXCEPTION_PSERIES(0xd00, single_step) - STD_EXCEPTION_PSERIES(0xe00, trap_0e) - - /* We need to deal with the Altivec unavailable exception - * here which is at 0xf20, thus in the middle of the - * prolog code of the PerformanceMonitor one. A little - * trickery is thus necessary - */ - . = 0xf00 - b performance_monitor_pSeries - - STD_EXCEPTION_PSERIES(0xf20, altivec_unavailable) - - STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) - STD_EXCEPTION_PSERIES(0x1700, altivec_assist) - - . = 0x3000 - -/*** pSeries interrupt support ***/ - - /* moved from 0xf00 */ - STD_EXCEPTION_PSERIES(., performance_monitor) - - .align 7 -_GLOBAL(do_stab_bolted_pSeries) - mtcrf 0x80,r12 - mfspr r12,SPRN_SPRG2 - EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted) - -/* - * We have some room here we use that to put - * the peries slb miss user trampoline code so it's reasonably - * away from slb_miss_user_common to avoid problems with rfid - * - * This is used for when the SLB miss handler has to go virtual, - * which doesn't happen for now anymore but will once we re-implement - * dynamic VSIDs for shared page tables - */ -#ifdef __DISABLED__ -slb_miss_user_pseries: - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - std r12,PACA_EXGEN+EX_R12(r13) - mfspr r10,SPRG1 - ld r11,PACA_EXSLB+EX_R9(r13) - ld r12,PACA_EXSLB+EX_R3(r13) - std r10,PACA_EXGEN+EX_R13(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R3(r13) - clrrdi r12,r13,32 - mfmsr r10 - mfspr r11,SRR0 /* save SRR0 */ - ori r12,r12,slb_miss_user_common@l /* virt addr of handler */ - ori r10,r10,MSR_IR|MSR_DR|MSR_RI - mtspr SRR0,r12 - mfspr r12,SRR1 /* and SRR1 */ - mtspr SRR1,r10 - rfid - b . /* prevent spec. execution */ -#endif /* __DISABLED__ */ - -/* - * Vectors for the FWNMI option. Share common code. - */ - .globl system_reset_fwnmi -system_reset_fwnmi: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 /* save r13 */ - RUNLATCH_ON(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) - - .globl machine_check_fwnmi -machine_check_fwnmi: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 /* save r13 */ - RUNLATCH_ON(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) - -#ifdef CONFIG_PPC_ISERIES -/*** ISeries-LPAR interrupt handlers ***/ - - STD_EXCEPTION_ISERIES(0x200, machine_check, PACA_EXMC) - - .globl data_access_iSeries -data_access_iSeries: - mtspr SPRN_SPRG1,r13 -BEGIN_FTR_SECTION - mtspr SPRN_SPRG2,r12 - mfspr r13,SPRN_DAR - mfspr r12,SPRN_DSISR - srdi r13,r13,60 - rlwimi r13,r12,16,0x20 - mfcr r12 - cmpwi r13,0x2c - beq .do_stab_bolted_iSeries - mtcrf 0x80,r12 - mfspr r12,SPRN_SPRG2 -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) - EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN) - EXCEPTION_PROLOG_ISERIES_2 - b data_access_common - -.do_stab_bolted_iSeries: - mtcrf 0x80,r12 - mfspr r12,SPRN_SPRG2 - EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) - EXCEPTION_PROLOG_ISERIES_2 - b .do_stab_bolted - - .globl data_access_slb_iSeries -data_access_slb_iSeries: - mtspr SPRN_SPRG1,r13 /* save r13 */ - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - std r9,PACA_EXSLB+EX_R9(r13) - mfcr r9 -#ifdef __DISABLED__ - cmpdi r3,0 - bge slb_miss_user_iseries -#endif - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACA+LPPACASRR1(r13); - b .slb_miss_realmode - - STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN) - - .globl instruction_access_slb_iSeries -instruction_access_slb_iSeries: - mtspr SPRN_SPRG1,r13 /* save r13 */ - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - ld r3,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ - std r9,PACA_EXSLB+EX_R9(r13) - mfcr r9 -#ifdef __DISABLED__ - cmpdi r3,0 - bge .slb_miss_user_iseries -#endif - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACA+LPPACASRR1(r13); - b .slb_miss_realmode - -#ifdef __DISABLED__ -slb_miss_user_iseries: - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - std r12,PACA_EXGEN+EX_R12(r13) - mfspr r10,SPRG1 - ld r11,PACA_EXSLB+EX_R9(r13) - ld r12,PACA_EXSLB+EX_R3(r13) - std r10,PACA_EXGEN+EX_R13(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R3(r13) - EXCEPTION_PROLOG_ISERIES_2 - b slb_miss_user_common -#endif - - MASKABLE_EXCEPTION_ISERIES(0x500, hardware_interrupt) - STD_EXCEPTION_ISERIES(0x600, alignment, PACA_EXGEN) - STD_EXCEPTION_ISERIES(0x700, program_check, PACA_EXGEN) - STD_EXCEPTION_ISERIES(0x800, fp_unavailable, PACA_EXGEN) - MASKABLE_EXCEPTION_ISERIES(0x900, decrementer) - STD_EXCEPTION_ISERIES(0xa00, trap_0a, PACA_EXGEN) - STD_EXCEPTION_ISERIES(0xb00, trap_0b, PACA_EXGEN) - - .globl system_call_iSeries -system_call_iSeries: - mr r9,r13 - mfspr r13,SPRN_SPRG3 - EXCEPTION_PROLOG_ISERIES_2 - b system_call_common - - STD_EXCEPTION_ISERIES( 0xd00, single_step, PACA_EXGEN) - STD_EXCEPTION_ISERIES( 0xe00, trap_0e, PACA_EXGEN) - STD_EXCEPTION_ISERIES( 0xf00, performance_monitor, PACA_EXGEN) - - .globl system_reset_iSeries -system_reset_iSeries: - mfspr r13,SPRN_SPRG3 /* Get paca address */ - mfmsr r24 - ori r24,r24,MSR_RI - mtmsrd r24 /* RI on */ - lhz r24,PACAPACAINDEX(r13) /* Get processor # */ - cmpwi 0,r24,0 /* Are we processor 0? */ - beq .__start_initialization_iSeries /* Start up the first processor */ - mfspr r4,SPRN_CTRLF - li r5,CTRL_RUNLATCH /* Turn off the run light */ - andc r4,r4,r5 - mtspr SPRN_CTRLT,r4 - -1: - HMT_LOW -#ifdef CONFIG_SMP - lbz r23,PACAPROCSTART(r13) /* Test if this processor - * should start */ - sync - LOADADDR(r3,current_set) - sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r3,r3,r28 - addi r1,r3,THREAD_SIZE - subi r1,r1,STACK_FRAME_OVERHEAD - - cmpwi 0,r23,0 - beq iSeries_secondary_smp_loop /* Loop until told to go */ - bne .__secondary_start /* Loop until told to go */ -iSeries_secondary_smp_loop: - /* Let the Hypervisor know we are alive */ - /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ - lis r3,0x8002 - rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ -#else /* CONFIG_SMP */ - /* Yield the processor. This is required for non-SMP kernels - which are running on multi-threaded machines. */ - lis r3,0x8000 - rldicr r3,r3,32,15 /* r3 = (r3 << 32) & 0xffff000000000000 */ - addi r3,r3,18 /* r3 = 0x8000000000000012 which is "yield" */ - li r4,0 /* "yield timed" */ - li r5,-1 /* "yield forever" */ -#endif /* CONFIG_SMP */ - li r0,-1 /* r0=-1 indicates a Hypervisor call */ - sc /* Invoke the hypervisor via a system call */ - mfspr r13,SPRN_SPRG3 /* Put r13 back ???? */ - b 1b /* If SMP not configured, secondaries - * loop forever */ - - .globl decrementer_iSeries_masked -decrementer_iSeries_masked: - li r11,1 - stb r11,PACALPPACA+LPPACADECRINT(r13) - lwz r12,PACADEFAULTDECR(r13) - mtspr SPRN_DEC,r12 - /* fall through */ - - .globl hardware_interrupt_iSeries_masked -hardware_interrupt_iSeries_masked: - mtcrf 0x80,r9 /* Restore regs */ - ld r11,PACALPPACA+LPPACASRR0(r13) - ld r12,PACALPPACA+LPPACASRR1(r13) - mtspr SPRN_SRR0,r11 - mtspr SPRN_SRR1,r12 - ld r9,PACA_EXGEN+EX_R9(r13) - ld r10,PACA_EXGEN+EX_R10(r13) - ld r11,PACA_EXGEN+EX_R11(r13) - ld r12,PACA_EXGEN+EX_R12(r13) - ld r13,PACA_EXGEN+EX_R13(r13) - rfid - b . /* prevent speculative execution */ -#endif /* CONFIG_PPC_ISERIES */ - -/*** Common interrupt handlers ***/ - - STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) - - /* - * Machine check is different because we use a different - * save area: PACA_EXMC instead of PACA_EXGEN. - */ - .align 7 - .globl machine_check_common -machine_check_common: - EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) - DISABLE_INTS - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except - - STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt) - STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception) - STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) - STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception) - STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) -#ifdef CONFIG_ALTIVEC - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) -#else - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) -#endif - -/* - * Here we have detected that the kernel stack pointer is bad. - * R9 contains the saved CR, r13 points to the paca, - * r10 contains the (bad) kernel stack pointer, - * r11 and r12 contain the saved SRR0 and SRR1. - * We switch to using an emergency stack, save the registers there, - * and call kernel_bad_stack(), which panics. - */ -bad_stack: - ld r1,PACAEMERGSP(r13) - subi r1,r1,64+INT_FRAME_SIZE - std r9,_CCR(r1) - std r10,GPR1(r1) - std r11,_NIP(r1) - std r12,_MSR(r1) - mfspr r11,SPRN_DAR - mfspr r12,SPRN_DSISR - std r11,_DAR(r1) - std r12,_DSISR(r1) - mflr r10 - mfctr r11 - mfxer r12 - std r10,_LINK(r1) - std r11,_CTR(r1) - std r12,_XER(r1) - SAVE_GPR(0,r1) - SAVE_GPR(2,r1) - SAVE_4GPRS(3,r1) - SAVE_2GPRS(7,r1) - SAVE_10GPRS(12,r1) - SAVE_10GPRS(22,r1) - addi r11,r1,INT_FRAME_SIZE - std r11,0(r1) - li r12,0 - std r12,0(r11) - ld r2,PACATOC(r13) -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack - b 1b - -/* - * Return from an exception with minimal checks. - * The caller is assumed to have done EXCEPTION_PROLOG_COMMON. - * If interrupts have been enabled, or anything has been - * done that might have changed the scheduling status of - * any task or sent any task a signal, you should use - * ret_from_except or ret_from_except_lite instead of this. - */ - .globl fast_exception_return -fast_exception_return: - ld r12,_MSR(r1) - ld r11,_NIP(r1) - andi. r3,r12,MSR_RI /* check if RI is set */ - beq- unrecov_fer - ld r3,_CCR(r1) - ld r4,_LINK(r1) - ld r5,_CTR(r1) - ld r6,_XER(r1) - mtcr r3 - mtlr r4 - mtctr r5 - mtxer r6 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - - mfmsr r10 - clrrdi r10,r10,2 /* clear RI (LE is 0 already) */ - mtmsrd r10,1 - - mtspr SPRN_SRR1,r12 - mtspr SPRN_SRR0,r11 - REST_4GPRS(10, r1) - ld r1,GPR1(r1) - rfid - b . /* prevent speculative execution */ - -unrecov_fer: - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - -/* - * Here r13 points to the paca, r9 contains the saved CR, - * SRR0 and SRR1 are saved in r11 and r12, - * r9 - r13 are saved in paca->exgen. - */ - .align 7 - .globl data_access_common -data_access_common: - RUNLATCH_ON(r10) /* It wont fit in the 0x300 handler */ - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - li r5,0x300 - b .do_hash_page /* Try to handle as hpte fault */ - - .align 7 - .globl instruction_access_common -instruction_access_common: - EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) - ld r3,_NIP(r1) - andis. r4,r12,0x5820 - li r5,0x400 - b .do_hash_page /* Try to handle as hpte fault */ - -/* - * Here is the common SLB miss user that is used when going to virtual - * mode for SLB misses, that is currently not used - */ -#ifdef __DISABLED__ - .align 7 - .globl slb_miss_user_common -slb_miss_user_common: - mflr r10 - std r3,PACA_EXGEN+EX_DAR(r13) - stw r9,PACA_EXGEN+EX_CCR(r13) - std r10,PACA_EXGEN+EX_LR(r13) - std r11,PACA_EXGEN+EX_SRR0(r13) - bl .slb_allocate_user - - ld r10,PACA_EXGEN+EX_LR(r13) - ld r3,PACA_EXGEN+EX_R3(r13) - lwz r9,PACA_EXGEN+EX_CCR(r13) - ld r11,PACA_EXGEN+EX_SRR0(r13) - mtlr r10 - beq- slb_miss_fault - - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ - beq- unrecov_user_slb - mfmsr r10 - -.machine push -.machine "power4" - mtcrf 0x80,r9 -.machine pop - - clrrdi r10,r10,2 /* clear RI before setting SRR0/1 */ - mtmsrd r10,1 - - mtspr SRR0,r11 - mtspr SRR1,r12 - - ld r9,PACA_EXGEN+EX_R9(r13) - ld r10,PACA_EXGEN+EX_R10(r13) - ld r11,PACA_EXGEN+EX_R11(r13) - ld r12,PACA_EXGEN+EX_R12(r13) - ld r13,PACA_EXGEN+EX_R13(r13) - rfid - b . - -slb_miss_fault: - EXCEPTION_PROLOG_COMMON(0x380, PACA_EXGEN) - ld r4,PACA_EXGEN+EX_DAR(r13) - li r5,0 - std r4,_DAR(r1) - std r5,_DSISR(r1) - b .handle_page_fault - -unrecov_user_slb: - EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) - DISABLE_INTS - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - -#endif /* __DISABLED__ */ - - -/* - * r13 points to the PACA, r9 contains the saved CR, - * r12 contain the saved SRR1, SRR0 is still ready for return - * r3 has the faulting address - * r9 - r13 are saved in paca->exslb. - * r3 is saved in paca->slb_r3 - * We assume we aren't going to take any exceptions during this procedure. - */ -_GLOBAL(slb_miss_realmode) - mflr r10 - - stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ - std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - - bl .slb_allocate_realmode - - /* All done -- return from exception. */ - - ld r10,PACA_EXSLB+EX_LR(r13) - ld r3,PACA_EXSLB+EX_R3(r13) - lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ -#ifdef CONFIG_PPC_ISERIES - ld r11,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ -#endif /* CONFIG_PPC_ISERIES */ - - mtlr r10 - - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ - beq- unrecov_slb - -.machine push -.machine "power4" - mtcrf 0x80,r9 - mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ -.machine pop - -#ifdef CONFIG_PPC_ISERIES - mtspr SPRN_SRR0,r11 - mtspr SPRN_SRR1,r12 -#endif /* CONFIG_PPC_ISERIES */ - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - ld r11,PACA_EXSLB+EX_R11(r13) - ld r12,PACA_EXSLB+EX_R12(r13) - ld r13,PACA_EXSLB+EX_R13(r13) - rfid - b . /* prevent speculative execution */ - -unrecov_slb: - EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) - DISABLE_INTS - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - - .align 7 - .globl hardware_interrupt_common - .globl hardware_interrupt_entry -hardware_interrupt_common: - EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN) -hardware_interrupt_entry: - DISABLE_INTS - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_IRQ - b .ret_from_except_lite - - .align 7 - .globl alignment_common -alignment_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS - bl .alignment_exception - b .ret_from_except - - .align 7 - .globl program_check_common -program_check_common: - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS - bl .program_check_exception - b .ret_from_except - - .align 7 - .globl fp_unavailable_common -fp_unavailable_common: - EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) - bne .load_up_fpu /* if from user, just load it up */ - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS - bl .kernel_fp_unavailable_exception - BUG_OPCODE - - .align 7 - .globl altivec_unavailable_common -altivec_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) -#ifdef CONFIG_ALTIVEC -BEGIN_FTR_SECTION - bne .load_up_altivec /* if from user, just load it up */ -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS - bl .altivec_unavailable_exception - b .ret_from_except - -#ifdef CONFIG_ALTIVEC -/* - * load_up_altivec(unused, unused, tsk) - * Disable VMX for the task which had it previously, - * and save its vector registers in its thread_struct. - * Enables the VMX for use in the kernel on return. - * On SMP we know the VMX is free, since we give it up every - * switch (ie, no lazy save of the vector registers). - * On entry: r13 == 'current' && last_task_used_altivec != 'current' - */ -_STATIC(load_up_altivec) - mfmsr r5 /* grab the current MSR */ - oris r5,r5,MSR_VEC@h - mtmsrd r5 /* enable use of VMX now */ - isync - -/* - * For SMP, we don't do lazy VMX switching because it just gets too - * horrendously complex, especially when a task switches from one CPU - * to another. Instead we call giveup_altvec in switch_to. - * VRSAVE isn't dealt with here, that is done in the normal context - * switch code. Note that we could rely on vrsave value to eventually - * avoid saving all of the VREGs here... - */ -#ifndef CONFIG_SMP - ld r3,last_task_used_altivec@got(r2) - ld r4,0(r3) - cmpdi 0,r4,0 - beq 1f - /* Save VMX state to last_task_used_altivec's THREAD struct */ - addi r4,r4,THREAD - SAVE_32VRS(0,r5,r4) - mfvscr vr0 - li r10,THREAD_VSCR - stvx vr0,r10,r4 - /* Disable VMX for last_task_used_altivec */ - ld r5,PT_REGS(r4) - ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r6,MSR_VEC@h - andc r4,r4,r6 - std r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#endif /* CONFIG_SMP */ - /* Hack: if we get an altivec unavailable trap with VRSAVE - * set to all zeros, we assume this is a broken application - * that fails to set it properly, and thus we switch it to - * all 1's - */ - mfspr r4,SPRN_VRSAVE - cmpdi 0,r4,0 - bne+ 1f - li r4,-1 - mtspr SPRN_VRSAVE,r4 -1: - /* enable use of VMX after return */ - ld r4,PACACURRENT(r13) - addi r5,r4,THREAD /* Get THREAD */ - oris r12,r12,MSR_VEC@h - std r12,_MSR(r1) - li r4,1 - li r10,THREAD_VSCR - stw r4,THREAD_USED_VR(r5) - lvx vr0,r10,r5 - mtvscr vr0 - REST_32VRS(0,r4,r5) -#ifndef CONFIG_SMP - /* Update last_task_used_math to 'current' */ - subi r4,r5,THREAD /* Back to 'current' */ - std r4,0(r3) -#endif /* CONFIG_SMP */ - /* restore registers and return */ - b fast_exception_return -#endif /* CONFIG_ALTIVEC */ - -/* - * Hash table stuff - */ - .align 7 -_GLOBAL(do_hash_page) - std r3,_DAR(r1) - std r4,_DSISR(r1) - - andis. r0,r4,0xa450 /* weird error? */ - bne- .handle_page_fault /* if not, try to insert a HPTE */ -BEGIN_FTR_SECTION - andis. r0,r4,0x0020 /* Is it a segment table fault? */ - bne- .do_ste_alloc /* If so handle it */ -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) - - /* - * We need to set the _PAGE_USER bit if MSR_PR is set or if we are - * accessing a userspace segment (even from the kernel). We assume - * kernel addresses always have the high bit set. - */ - rlwinm r4,r4,32-25+9,31-9,31-9 /* DSISR_STORE -> _PAGE_RW */ - rotldi r0,r3,15 /* Move high bit into MSR_PR posn */ - orc r0,r12,r0 /* MSR_PR | ~high_bit */ - rlwimi r4,r0,32-13,30,30 /* becomes _PAGE_USER access bit */ - ori r4,r4,1 /* add _PAGE_PRESENT */ - rlwimi r4,r5,22+2,31-2,31-2 /* Set _PAGE_EXEC if trap is 0x400 */ - - /* - * On iSeries, we soft-disable interrupts here, then - * hard-enable interrupts so that the hash_page code can spin on - * the hash_table_lock without problems on a shared processor. - */ - DISABLE_INTS - - /* - * r3 contains the faulting address - * r4 contains the required access permissions - * r5 contains the trap number - * - * at return r3 = 0 for success - */ - bl .hash_page /* build HPTE if possible */ - cmpdi r3,0 /* see if hash_page succeeded */ - -#ifdef DO_SOFT_DISABLE - /* - * If we had interrupts soft-enabled at the point where the - * DSI/ISI occurred, and an interrupt came in during hash_page, - * handle it now. - * We jump to ret_from_except_lite rather than fast_exception_return - * because ret_from_except_lite will check for and handle pending - * interrupts if necessary. - */ - beq .ret_from_except_lite - /* For a hash failure, we don't bother re-enabling interrupts */ - ble- 12f - - /* - * hash_page couldn't handle it, set soft interrupt enable back - * to what it was before the trap. Note that .local_irq_restore - * handles any interrupts pending at this point. - */ - ld r3,SOFTE(r1) - bl .local_irq_restore - b 11f -#else - beq fast_exception_return /* Return from exception on success */ - ble- 12f /* Failure return from hash_page */ - - /* fall through */ -#endif - -/* Here we have a page fault that hash_page can't handle. */ -_GLOBAL(handle_page_fault) - ENABLE_INTS -11: ld r4,_DAR(r1) - ld r5,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_page_fault - cmpdi r3,0 - beq+ .ret_from_except_lite - bl .save_nvgprs - mr r5,r3 - addi r3,r1,STACK_FRAME_OVERHEAD - lwz r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except - -/* We have a page fault that hash_page could handle but HV refused - * the PTE insertion - */ -12: bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - lwz r4,_DAR(r1) - bl .low_hash_fault - b .ret_from_except - - /* here we have a segment miss */ -_GLOBAL(do_ste_alloc) - bl .ste_allocate /* try to insert stab entry */ - cmpdi r3,0 - beq+ fast_exception_return - b .handle_page_fault - -/* - * r13 points to the PACA, r9 contains the saved CR, - * r11 and r12 contain the saved SRR0 and SRR1. - * r9 - r13 are saved in paca->exslb. - * We assume we aren't going to take any exceptions during this procedure. - * We assume (DAR >> 60) == 0xc. - */ - .align 7 -_GLOBAL(do_stab_bolted) - stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ - std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ - - /* Hash to the primary group */ - ld r10,PACASTABVIRT(r13) - mfspr r11,SPRN_DAR - srdi r11,r11,28 - rldimi r10,r11,7,52 /* r10 = first ste of the group */ - - /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID */ - ASM_VSID_SCRAMBLE(r11, r9) - rldic r9,r11,12,16 /* r9 = vsid << 12 */ - - /* Search the primary group for a free entry */ -1: ld r11,0(r10) /* Test valid bit of the current ste */ - andi. r11,r11,0x80 - beq 2f - addi r10,r10,16 - andi. r11,r10,0x70 - bne 1b - - /* Stick for only searching the primary group for now. */ - /* At least for now, we use a very simple random castout scheme */ - /* Use the TB as a random number ; OR in 1 to avoid entry 0 */ - mftb r11 - rldic r11,r11,4,57 /* r11 = (r11 << 4) & 0x70 */ - ori r11,r11,0x10 - - /* r10 currently points to an ste one past the group of interest */ - /* make it point to the randomly selected entry */ - subi r10,r10,128 - or r10,r10,r11 /* r10 is the entry to invalidate */ - - isync /* mark the entry invalid */ - ld r11,0(r10) - rldicl r11,r11,56,1 /* clear the valid bit */ - rotldi r11,r11,8 - std r11,0(r10) - sync - - clrrdi r11,r11,28 /* Get the esid part of the ste */ - slbie r11 - -2: std r9,8(r10) /* Store the vsid part of the ste */ - eieio - - mfspr r11,SPRN_DAR /* Get the new esid */ - clrrdi r11,r11,28 /* Permits a full 32b of ESID */ - ori r11,r11,0x90 /* Turn on valid and kp */ - std r11,0(r10) /* Put new entry back into the stab */ - - sync - - /* All done -- return from exception. */ - lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - ld r11,PACA_EXSLB+EX_SRR0(r13) /* get saved SRR0 */ - - andi. r10,r12,MSR_RI - beq- unrecov_slb - - mtcrf 0x80,r9 /* restore CR */ - - mfmsr r10 - clrrdi r10,r10,2 - mtmsrd r10,1 - - mtspr SPRN_SRR0,r11 - mtspr SPRN_SRR1,r12 - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - ld r11,PACA_EXSLB+EX_R11(r13) - ld r12,PACA_EXSLB+EX_R12(r13) - ld r13,PACA_EXSLB+EX_R13(r13) - rfid - b . /* prevent speculative execution */ - -/* - * Space for CPU0's segment table. - * - * On iSeries, the hypervisor must fill in at least one entry before - * we get control (with relocate on). The address is give to the hv - * as a page number (see xLparMap in lpardata.c), so this must be at a - * fixed address (the linker can't compute (u64)&initial_stab >> - * PAGE_SHIFT). - */ - . = STAB0_PHYS_ADDR /* 0x6000 */ - .globl initial_stab -initial_stab: - .space 4096 - -/* - * Data area reserved for FWNMI option. - * This address (0x7000) is fixed by the RPA. - */ - .= 0x7000 - .globl fwnmi_data_area -fwnmi_data_area: - - /* iSeries does not use the FWNMI stuff, so it is safe to put - * this here, even if we later allow kernels that will boot on - * both pSeries and iSeries */ -#ifdef CONFIG_PPC_ISERIES - . = LPARMAP_PHYS -#include "lparmap.s" -/* - * This ".text" is here for old compilers that generate a trailing - * .note section when compiling .c files to .s - */ - .text -#endif /* CONFIG_PPC_ISERIES */ - - . = 0x8000 - -/* - * On pSeries, secondary processors spin in the following code. - * At entry, r3 = this processor's number (physical cpu id) - */ -_GLOBAL(pSeries_secondary_smp_init) - mr r24,r3 - - /* turn on 64-bit mode */ - bl .enable_64b_mode - isync - - /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_setup - - /* Set up a paca value for this processor. Since we have the - * physical cpu id in r24, we need to search the pacas to find - * which logical id maps to our physical one. - */ - LOADADDR(r13, paca) /* Get base vaddr of paca array */ - li r5,0 /* logical cpu id */ -1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ - cmpw r6,r24 /* Compare to our id */ - beq 2f - addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ - addi r5,r5,1 - cmpwi r5,NR_CPUS - blt 1b - - mr r3,r24 /* not found, copy phys to r3 */ - b .kexec_wait /* next kernel might do better */ - -2: mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ - /* From now on, r24 is expected to be logical cpuid */ - mr r24,r5 -3: HMT_LOW - lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ - /* start. */ - sync - - /* Create a temp kernel stack for use before relocation is on. */ - ld r1,PACAEMERGSP(r13) - subi r1,r1,STACK_FRAME_OVERHEAD - - cmpwi 0,r23,0 -#ifdef CONFIG_SMP - bne .__secondary_start -#endif - b 3b /* Loop until told to go */ - -#ifdef CONFIG_PPC_ISERIES -_STATIC(__start_initialization_iSeries) - /* Clear out the BSS */ - LOADADDR(r11,__bss_stop) - LOADADDR(r8,__bss_start) - sub r11,r11,r8 /* bss size */ - addi r11,r11,7 /* round up to an even double word */ - rldicl. r11,r11,61,3 /* shift right by 3 */ - beq 4f - addi r8,r8,-8 - li r0,0 - mtctr r11 /* zero this many doublewords */ -3: stdu r0,8(r8) - bdnz 3b -4: - LOADADDR(r1,init_thread_union) - addi r1,r1,THREAD_SIZE - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - - LOADADDR(r3,cpu_specs) - LOADADDR(r4,cur_cpu_spec) - li r5,0 - bl .identify_cpu - - LOADADDR(r2,__toc_start) - addi r2,r2,0x4000 - addi r2,r2,0x4000 - - bl .iSeries_early_setup - bl .early_setup - - /* relocation is on at this point */ - - b .start_here_common -#endif /* CONFIG_PPC_ISERIES */ - -#ifdef CONFIG_PPC_MULTIPLATFORM - -_STATIC(__mmu_off) - mfmsr r3 - andi. r0,r3,MSR_IR|MSR_DR - beqlr - andc r3,r3,r0 - mtspr SPRN_SRR0,r4 - mtspr SPRN_SRR1,r3 - sync - rfid - b . /* prevent speculative execution */ - - -/* - * Here is our main kernel entry point. We support currently 2 kind of entries - * depending on the value of r5. - * - * r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content - * in r3...r7 - * - * r5 == NULL -> kexec style entry. r3 is a physical pointer to the - * DT block, r4 is a physical pointer to the kernel itself - * - */ -_GLOBAL(__start_initialization_multiplatform) - /* - * Are we booted from a PROM Of-type client-interface ? - */ - cmpldi cr0,r5,0 - bne .__boot_from_prom /* yes -> prom */ - - /* Save parameters */ - mr r31,r3 - mr r30,r4 - - /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode - - /* Setup some critical 970 SPRs before switching MMU off */ - bl .__970_cpu_preinit - - /* cpu # */ - li r24,0 - - /* Switch off MMU if not already */ - LOADADDR(r4, .__after_prom_start - KERNELBASE) - add r4,r4,r30 - bl .__mmu_off - b .__after_prom_start - -_STATIC(__boot_from_prom) - /* Save parameters */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 - - /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode - - /* put a relocation offset into r3 */ - bl .reloc_offset - - LOADADDR(r2,__toc_start) - addi r2,r2,0x4000 - addi r2,r2,0x4000 - - /* Relocate the TOC from a virt addr to a real addr */ - sub r2,r2,r3 - - /* Restore parameters */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 - - /* Do all of the interaction with OF client interface */ - bl .prom_init - /* We never return */ - trap - -/* - * At this point, r3 contains the physical address we are running at, - * returned by prom_init() - */ -_STATIC(__after_prom_start) - -/* - * We need to run with __start at physical address 0. - * This will leave some code in the first 256B of - * real memory, which are reserved for software use. - * The remainder of the first page is loaded with the fixed - * interrupt vectors. The next two pages are filled with - * unknown exception placeholders. - * - * Note: This process overwrites the OF exception vectors. - * r26 == relocation offset - * r27 == KERNELBASE - */ - bl .reloc_offset - mr r26,r3 - SET_REG_TO_CONST(r27,KERNELBASE) - - li r3,0 /* target addr */ - - // XXX FIXME: Use phys returned by OF (r30) - sub r4,r27,r26 /* source addr */ - /* current address of _start */ - /* i.e. where we are running */ - /* the source addr */ - - LOADADDR(r5,copy_to_here) /* # bytes of memory to copy */ - sub r5,r5,r27 - - li r6,0x100 /* Start offset, the first 0x100 */ - /* bytes were copied earlier. */ - - bl .copy_and_flush /* copy the first n bytes */ - /* this includes the code being */ - /* executed here. */ - - LOADADDR(r0, 4f) /* Jump to the copy of this code */ - mtctr r0 /* that we just made/relocated */ - bctr - -4: LOADADDR(r5,klimit) - sub r5,r5,r26 - ld r5,0(r5) /* get the value of klimit */ - sub r5,r5,r27 - bl .copy_and_flush /* copy the rest */ - b .start_here_multiplatform - -#endif /* CONFIG_PPC_MULTIPLATFORM */ - -/* - * Copy routine used to copy the kernel to start at physical address 0 - * and flush and invalidate the caches as needed. - * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset - * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. - * - * Note: this routine *only* clobbers r0, r6 and lr - */ -_GLOBAL(copy_and_flush) - addi r5,r5,-8 - addi r6,r6,-8 -4: li r0,16 /* Use the least common */ - /* denominator cache line */ - /* size. This results in */ - /* extra cache line flushes */ - /* but operation is correct. */ - /* Can't get cache line size */ - /* from NACA as it is being */ - /* moved too. */ - - mtctr r0 /* put # words/line in ctr */ -3: addi r6,r6,8 /* copy a cache line */ - ldx r0,r6,r4 - stdx r0,r6,r3 - bdnz 3b - dcbst r6,r3 /* write it to memory */ - sync - icbi r6,r3 /* flush the icache line */ - cmpld 0,r6,r5 - blt 4b - sync - addi r5,r5,8 - addi r6,r6,8 - blr - -.align 8 -copy_to_here: - -#ifdef CONFIG_SMP -#ifdef CONFIG_PPC_PMAC -/* - * On PowerMac, secondary processors starts from the reset vector, which - * is temporarily turned into a call to one of the functions below. - */ - .section ".text"; - .align 2 ; - - .globl __secondary_start_pmac_0 -__secondary_start_pmac_0: - /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */ - li r24,0 - b 1f - li r24,1 - b 1f - li r24,2 - b 1f - li r24,3 -1: - -_GLOBAL(pmac_secondary_start) - /* turn on 64-bit mode */ - bl .enable_64b_mode - isync - - /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_setup - - /* pSeries do that early though I don't think we really need it */ - mfmsr r3 - ori r3,r3,MSR_RI - mtmsrd r3 /* RI on */ - - /* Set up a paca value for this processor. */ - LOADADDR(r4, paca) /* Get base vaddr of paca array */ - mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r13,r4 /* for this processor. */ - mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ - - /* Create a temp kernel stack for use before relocation is on. */ - ld r1,PACAEMERGSP(r13) - subi r1,r1,STACK_FRAME_OVERHEAD - - b .__secondary_start - -#endif /* CONFIG_PPC_PMAC */ - -/* - * This function is called after the master CPU has released the - * secondary processors. The execution environment is relocation off. - * The paca for this processor has the following fields initialized at - * this point: - * 1. Processor number - * 2. Segment table pointer (virtual address) - * On entry the following are set: - * r1 = stack pointer. vaddr for iSeries, raddr (temp stack) for pSeries - * r24 = cpu# (in Linux terms) - * r13 = paca virtual address - * SPRG3 = paca virtual address - */ -_GLOBAL(__secondary_start) - - HMT_MEDIUM /* Set thread priority to MEDIUM */ - - ld r2,PACATOC(r13) - - /* Do early setup for that CPU */ - bl .early_setup_secondary - - /* Initialize the kernel stack. Just a repeat for iSeries. */ - LOADADDR(r3,current_set) - sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r1,r3,r28 - addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD - std r1,PACAKSAVE(r13) - - li r7,0 - mtlr r7 - - /* enable MMU and jump to start_secondary */ - LOADADDR(r3,.start_secondary_prolog) - SET_REG_TO_CONST(r4, MSR_KERNEL) -#ifdef DO_SOFT_DISABLE - ori r4,r4,MSR_EE -#endif - mtspr SPRN_SRR0,r3 - mtspr SPRN_SRR1,r4 - rfid - b . /* prevent speculative execution */ - -/* - * Running with relocation on at this point. All we want to do is - * zero the stack back-chain pointer before going into C code. - */ -_GLOBAL(start_secondary_prolog) - li r3,0 - std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary -#endif - -/* - * This subroutine clobbers r11 and r12 - */ -_GLOBAL(enable_64b_mode) - mfmsr r11 /* grab the current MSR */ - li r12,1 - rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) - or r11,r11,r12 - li r12,1 - rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) - or r11,r11,r12 - mtmsrd r11 - isync - blr - -#ifdef CONFIG_PPC_MULTIPLATFORM -/* - * This is where the main kernel code starts. - */ -_STATIC(start_here_multiplatform) - /* get a new offset, now that the kernel has moved. */ - bl .reloc_offset - mr r26,r3 - - /* Clear out the BSS. It may have been done in prom_init, - * already but that's irrelevant since prom_init will soon - * be detached from the kernel completely. Besides, we need - * to clear it now for kexec-style entry. - */ - LOADADDR(r11,__bss_stop) - LOADADDR(r8,__bss_start) - sub r11,r11,r8 /* bss size */ - addi r11,r11,7 /* round up to an even double word */ - rldicl. r11,r11,61,3 /* shift right by 3 */ - beq 4f - addi r8,r8,-8 - li r0,0 - mtctr r11 /* zero this many doublewords */ -3: stdu r0,8(r8) - bdnz 3b -4: - - mfmsr r6 - ori r6,r6,MSR_RI - mtmsrd r6 /* RI on */ - -#ifdef CONFIG_HMT - /* Start up the second thread on cpu 0 */ - mfspr r3,SPRN_PVR - srwi r3,r3,16 - cmpwi r3,0x34 /* Pulsar */ - beq 90f - cmpwi r3,0x36 /* Icestar */ - beq 90f - cmpwi r3,0x37 /* SStar */ - beq 90f - b 91f /* HMT not supported */ -90: li r3,0 - bl .hmt_start_secondary -91: -#endif - - /* The following gets the stack and TOC set up with the regs */ - /* pointing to the real addr of the kernel stack. This is */ - /* all done to support the C function call below which sets */ - /* up the htab. This is done because we have relocated the */ - /* kernel but are still running in real mode. */ - - LOADADDR(r3,init_thread_union) - sub r3,r3,r26 - - /* set up a stack pointer (physical address) */ - addi r1,r3,THREAD_SIZE - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - - /* set up the TOC (physical address) */ - LOADADDR(r2,__toc_start) - addi r2,r2,0x4000 - addi r2,r2,0x4000 - sub r2,r2,r26 - - LOADADDR(r3,cpu_specs) - sub r3,r3,r26 - LOADADDR(r4,cur_cpu_spec) - sub r4,r4,r26 - mr r5,r26 - bl .identify_cpu - - /* Save some low level config HIDs of CPU0 to be copied to - * other CPUs later on, or used for suspend/resume - */ - bl .__save_cpu_setup - sync - - /* Setup a valid physical PACA pointer in SPRG3 for early_setup - * note that boot_cpuid can always be 0 nowadays since there is - * nowhere it can be initialized differently before we reach this - * code - */ - LOADADDR(r27, boot_cpuid) - sub r27,r27,r26 - lwz r27,0(r27) - - LOADADDR(r24, paca) /* Get base vaddr of paca array */ - mulli r13,r27,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r13,r24 /* for this processor. */ - sub r13,r13,r26 /* convert to physical addr */ - mtspr SPRN_SPRG3,r13 /* PPPBBB: Temp... -Peter */ - - /* Do very early kernel initializations, including initial hash table, - * stab and slb setup before we turn on relocation. */ - - /* Restore parameters passed from prom_init/kexec */ - mr r3,r31 - bl .early_setup - - LOADADDR(r3,.start_here_common) - SET_REG_TO_CONST(r4, MSR_KERNEL) - mtspr SPRN_SRR0,r3 - mtspr SPRN_SRR1,r4 - rfid - b . /* prevent speculative execution */ -#endif /* CONFIG_PPC_MULTIPLATFORM */ - - /* This is where all platforms converge execution */ -_STATIC(start_here_common) - /* relocation is on at this point */ - - /* The following code sets up the SP and TOC now that we are */ - /* running with translation enabled. */ - - LOADADDR(r3,init_thread_union) - - /* set up the stack */ - addi r1,r3,THREAD_SIZE - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - - /* Apply the CPUs-specific fixups (nop out sections not relevant - * to this CPU - */ - li r3,0 - bl .do_cpu_ftr_fixups - - LOADADDR(r26, boot_cpuid) - lwz r26,0(r26) - - LOADADDR(r24, paca) /* Get base vaddr of paca array */ - mulli r13,r26,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r13,r24 /* for this processor. */ - mtspr SPRN_SPRG3,r13 - - /* ptr to current */ - LOADADDR(r4,init_task) - std r4,PACACURRENT(r13) - - /* Load the TOC */ - ld r2,PACATOC(r13) - std r1,PACAKSAVE(r13) - - bl .setup_system - - /* Load up the kernel context */ -5: -#ifdef DO_SOFT_DISABLE - li r5,0 - stb r5,PACAPROCENABLED(r13) /* Soft Disabled */ - mfmsr r5 - ori r5,r5,MSR_EE /* Hard Enabled */ - mtmsrd r5 -#endif - - bl .start_kernel - -_GLOBAL(hmt_init) -#ifdef CONFIG_HMT - LOADADDR(r5, hmt_thread_data) - mfspr r7,SPRN_PVR - srwi r7,r7,16 - cmpwi r7,0x34 /* Pulsar */ - beq 90f - cmpwi r7,0x36 /* Icestar */ - beq 91f - cmpwi r7,0x37 /* SStar */ - beq 91f - b 101f -90: mfspr r6,SPRN_PIR - andi. r6,r6,0x1f - b 92f -91: mfspr r6,SPRN_PIR - andi. r6,r6,0x3ff -92: sldi r4,r24,3 - stwx r6,r5,r4 - bl .hmt_start_secondary - b 101f - -__hmt_secondary_hold: - LOADADDR(r5, hmt_thread_data) - clrldi r5,r5,4 - li r7,0 - mfspr r6,SPRN_PIR - mfspr r8,SPRN_PVR - srwi r8,r8,16 - cmpwi r8,0x34 - bne 93f - andi. r6,r6,0x1f - b 103f -93: andi. r6,r6,0x3f - -103: lwzx r8,r5,r7 - cmpw r8,r6 - beq 104f - addi r7,r7,8 - b 103b - -104: addi r7,r7,4 - lwzx r9,r5,r7 - mr r24,r9 -101: -#endif - mr r3,r24 - b .pSeries_secondary_smp_init - -#ifdef CONFIG_HMT -_GLOBAL(hmt_start_secondary) - LOADADDR(r4,__hmt_secondary_hold) - clrldi r4,r4,4 - mtspr SPRN_NIADORM, r4 - mfspr r4, SPRN_MSRDORM - li r5, -65 - and r4, r4, r5 - mtspr SPRN_MSRDORM, r4 - lis r4,0xffef - ori r4,r4,0x7403 - mtspr SPRN_TSC, r4 - li r4,0x1f4 - mtspr SPRN_TST, r4 - mfspr r4, SPRN_HID0 - ori r4, r4, 0x1 - mtspr SPRN_HID0, r4 - mfspr r4, SPRN_CTRLF - oris r4, r4, 0x40 - mtspr SPRN_CTRLT, r4 - blr -#endif - -/* - * We put a few things here that have to be page-aligned. - * This stuff goes at the beginning of the bss, which is page-aligned. - */ - .section ".bss" - - .align PAGE_SHIFT - - .globl empty_zero_page -empty_zero_page: - .space PAGE_SIZE - - .globl swapper_pg_dir -swapper_pg_dir: - .space PAGE_SIZE - -/* - * This space gets a copy of optional info passed to us by the bootstrap - * Used to pass parameters into the kernel like root=/dev/sda1, etc. - */ - .globl cmd_line -cmd_line: - .space COMMAND_LINE_SIZE diff --git a/arch/ppc64/kernel/hvconsole.c b/arch/ppc64/kernel/hvconsole.c deleted file mode 100644 index 138e128a3886..000000000000 --- a/arch/ppc64/kernel/hvconsole.c +++ /dev/null @@ -1,74 +0,0 @@ -/* - * hvconsole.c - * Copyright (C) 2004 Hollis Blanchard, IBM Corporation - * Copyright (C) 2004 IBM Corporation - * - * Additional Author(s): - * Ryan S. Arnold - * - * LPAR console support. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include -#include -#include -#include - -/** - * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper - * @vtermno: The vtermno or unit_address of the adapter from which to fetch the - * data. - * @buf: The character buffer into which to put the character data fetched from - * firmware. - * @count: not used? - */ -int hvc_get_chars(uint32_t vtermno, char *buf, int count) -{ - unsigned long got; - - if (plpar_hcall(H_GET_TERM_CHAR, vtermno, 0, 0, 0, &got, - (unsigned long *)buf, (unsigned long *)buf+1) == H_Success) - return got; - return 0; -} - -EXPORT_SYMBOL(hvc_get_chars); - - -/** - * hvc_put_chars: send characters to firmware for denoted vterm adapter - * @vtermno: The vtermno or unit_address of the adapter from which the data - * originated. - * @buf: The character buffer that contains the character data to send to - * firmware. - * @count: Send this number of characters. - */ -int hvc_put_chars(uint32_t vtermno, const char *buf, int count) -{ - unsigned long *lbuf = (unsigned long *) buf; - long ret; - - ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0], - lbuf[1]); - if (ret == H_Success) - return count; - if (ret == H_Busy) - return 0; - return -EIO; -} - -EXPORT_SYMBOL(hvc_put_chars); diff --git a/arch/ppc64/kernel/hvcserver.c b/arch/ppc64/kernel/hvcserver.c deleted file mode 100644 index 4d584172055a..000000000000 --- a/arch/ppc64/kernel/hvcserver.c +++ /dev/null @@ -1,251 +0,0 @@ -/* - * hvcserver.c - * Copyright (C) 2004 Ryan S Arnold, IBM Corporation - * - * PPC64 virtual I/O console server support. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include -#include -#include -#include - -#include -#include -#include - -#define HVCS_ARCH_VERSION "1.0.0" - -MODULE_AUTHOR("Ryan S. Arnold "); -MODULE_DESCRIPTION("IBM hvcs ppc64 API"); -MODULE_LICENSE("GPL"); -MODULE_VERSION(HVCS_ARCH_VERSION); - -/* - * Convert arch specific return codes into relevant errnos. The hvcs - * functions aren't performance sensitive, so this conversion isn't an - * issue. - */ -int hvcs_convert(long to_convert) -{ - switch (to_convert) { - case H_Success: - return 0; - case H_Parameter: - return -EINVAL; - case H_Hardware: - return -EIO; - case H_Busy: - case H_LongBusyOrder1msec: - case H_LongBusyOrder10msec: - case H_LongBusyOrder100msec: - case H_LongBusyOrder1sec: - case H_LongBusyOrder10sec: - case H_LongBusyOrder100sec: - return -EBUSY; - case H_Function: /* fall through */ - default: - return -EPERM; - } -} - -/** - * hvcs_free_partner_info - free pi allocated by hvcs_get_partner_info - * @head: list_head pointer for an allocated list of partner info structs to - * free. - * - * This function is used to free the partner info list that was returned by - * calling hvcs_get_partner_info(). - */ -int hvcs_free_partner_info(struct list_head *head) -{ - struct hvcs_partner_info *pi; - struct list_head *element; - - if (!head) - return -EINVAL; - - while (!list_empty(head)) { - element = head->next; - pi = list_entry(element, struct hvcs_partner_info, node); - list_del(element); - kfree(pi); - } - - return 0; -} -EXPORT_SYMBOL(hvcs_free_partner_info); - -/* Helper function for hvcs_get_partner_info */ -int hvcs_next_partner(uint32_t unit_address, - unsigned long last_p_partition_ID, - unsigned long last_p_unit_address, unsigned long *pi_buff) - -{ - long retval; - retval = plpar_hcall_norets(H_VTERM_PARTNER_INFO, unit_address, - last_p_partition_ID, - last_p_unit_address, virt_to_phys(pi_buff)); - return hvcs_convert(retval); -} - -/** - * hvcs_get_partner_info - Get all of the partner info for a vty-server adapter - * @unit_address: The unit_address of the vty-server adapter for which this - * function is fetching partner info. - * @head: An initialized list_head pointer to an empty list to use to return the - * list of partner info fetched from the hypervisor to the caller. - * @pi_buff: A page sized buffer pre-allocated prior to calling this function - * that is to be used to be used by firmware as an iterator to keep track - * of the partner info retrieval. - * - * This function returns non-zero on success, or if there is no partner info. - * - * The pi_buff is pre-allocated prior to calling this function because this - * function may be called with a spin_lock held and kmalloc of a page is not - * recommended as GFP_ATOMIC. - * - * The first long of this buffer is used to store a partner unit address. The - * second long is used to store a partner partition ID and starting at - * pi_buff[2] is the 79 character Converged Location Code (diff size than the - * unsigned longs, hence the casting mumbo jumbo you see later). - * - * Invocation of this function should always be followed by an invocation of - * hvcs_free_partner_info() using a pointer to the SAME list head instance - * that was passed as a parameter to this function. - */ -int hvcs_get_partner_info(uint32_t unit_address, struct list_head *head, - unsigned long *pi_buff) -{ - /* - * Dealt with as longs because of the hcall interface even though the - * values are uint32_t. - */ - unsigned long last_p_partition_ID; - unsigned long last_p_unit_address; - struct hvcs_partner_info *next_partner_info = NULL; - int more = 1; - int retval; - - memset(pi_buff, 0x00, PAGE_SIZE); - /* invalid parameters */ - if (!head || !pi_buff) - return -EINVAL; - - last_p_partition_ID = last_p_unit_address = ~0UL; - INIT_LIST_HEAD(head); - - do { - retval = hvcs_next_partner(unit_address, last_p_partition_ID, - last_p_unit_address, pi_buff); - if (retval) { - /* - * Don't indicate that we've failed if we have - * any list elements. - */ - if (!list_empty(head)) - return 0; - return retval; - } - - last_p_partition_ID = pi_buff[0]; - last_p_unit_address = pi_buff[1]; - - /* This indicates that there are no further partners */ - if (last_p_partition_ID == ~0UL - && last_p_unit_address == ~0UL) - break; - - /* This is a very small struct and will be freed soon in - * hvcs_free_partner_info(). */ - next_partner_info = kmalloc(sizeof(struct hvcs_partner_info), - GFP_ATOMIC); - - if (!next_partner_info) { - printk(KERN_WARNING "HVCONSOLE: kmalloc() failed to" - " allocate partner info struct.\n"); - hvcs_free_partner_info(head); - return -ENOMEM; - } - - next_partner_info->unit_address - = (unsigned int)last_p_unit_address; - next_partner_info->partition_ID - = (unsigned int)last_p_partition_ID; - - /* copy the Null-term char too */ - strncpy(&next_partner_info->location_code[0], - (char *)&pi_buff[2], - strlen((char *)&pi_buff[2]) + 1); - - list_add_tail(&(next_partner_info->node), head); - next_partner_info = NULL; - - } while (more); - - return 0; -} -EXPORT_SYMBOL(hvcs_get_partner_info); - -/** - * hvcs_register_connection - establish a connection between this vty-server and - * a vty. - * @unit_address: The unit address of the vty-server adapter that is to be - * establish a connection. - * @p_partition_ID: The partition ID of the vty adapter that is to be connected. - * @p_unit_address: The unit address of the vty adapter to which the vty-server - * is to be connected. - * - * If this function is called once and -EINVAL is returned it may - * indicate that the partner info needs to be refreshed for the - * target unit address at which point the caller must invoke - * hvcs_get_partner_info() and then call this function again. If, - * for a second time, -EINVAL is returned then it indicates that - * there is probably already a partner connection registered to a - * different vty-server adapter. It is also possible that a second - * -EINVAL may indicate that one of the parms is not valid, for - * instance if the link was removed between the vty-server adapter - * and the vty adapter that you are trying to open. Don't shoot the - * messenger. Firmware implemented it this way. - */ -int hvcs_register_connection( uint32_t unit_address, - uint32_t p_partition_ID, uint32_t p_unit_address) -{ - long retval; - retval = plpar_hcall_norets(H_REGISTER_VTERM, unit_address, - p_partition_ID, p_unit_address); - return hvcs_convert(retval); -} -EXPORT_SYMBOL(hvcs_register_connection); - -/** - * hvcs_free_connection - free the connection between a vty-server and vty - * @unit_address: The unit address of the vty-server that is to have its - * connection severed. - * - * This function is used to free the partner connection between a vty-server - * adapter and a vty adapter. - * - * If -EBUSY is returned continue to call this function until 0 is returned. - */ -int hvcs_free_connection(uint32_t unit_address) -{ - long retval; - retval = plpar_hcall_norets(H_FREE_VTERM, unit_address); - return hvcs_convert(retval); -} -EXPORT_SYMBOL(hvcs_free_connection); diff --git a/arch/ppc64/kernel/iomap.c b/arch/ppc64/kernel/iomap.c deleted file mode 100644 index 6160c8dbb7c5..000000000000 --- a/arch/ppc64/kernel/iomap.c +++ /dev/null @@ -1,146 +0,0 @@ -/* - * arch/ppc64/kernel/iomap.c - * - * ppc64 "iomap" interface implementation. - * - * (C) Copyright 2004 Linus Torvalds - */ -#include -#include -#include -#include - -/* - * Here comes the ppc64 implementation of the IOMAP - * interfaces. - */ -unsigned int fastcall ioread8(void __iomem *addr) -{ - return readb(addr); -} -unsigned int fastcall ioread16(void __iomem *addr) -{ - return readw(addr); -} -unsigned int fastcall ioread16be(void __iomem *addr) -{ - return in_be16(addr); -} -unsigned int fastcall ioread32(void __iomem *addr) -{ - return readl(addr); -} -unsigned int fastcall ioread32be(void __iomem *addr) -{ - return in_be32(addr); -} -EXPORT_SYMBOL(ioread8); -EXPORT_SYMBOL(ioread16); -EXPORT_SYMBOL(ioread16be); -EXPORT_SYMBOL(ioread32); -EXPORT_SYMBOL(ioread32be); - -void fastcall iowrite8(u8 val, void __iomem *addr) -{ - writeb(val, addr); -} -void fastcall iowrite16(u16 val, void __iomem *addr) -{ - writew(val, addr); -} -void fastcall iowrite16be(u16 val, void __iomem *addr) -{ - out_be16(addr, val); -} -void fastcall iowrite32(u32 val, void __iomem *addr) -{ - writel(val, addr); -} -void fastcall iowrite32be(u32 val, void __iomem *addr) -{ - out_be32(addr, val); -} -EXPORT_SYMBOL(iowrite8); -EXPORT_SYMBOL(iowrite16); -EXPORT_SYMBOL(iowrite16be); -EXPORT_SYMBOL(iowrite32); -EXPORT_SYMBOL(iowrite32be); - -/* - * These are the "repeat read/write" functions. Note the - * non-CPU byte order. We do things in "IO byteorder" - * here. - * - * FIXME! We could make these do EEH handling if we really - * wanted. Not clear if we do. - */ -void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) -{ - _insb((u8 __iomem *) addr, dst, count); -} -void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) -{ - _insw_ns((u16 __iomem *) addr, dst, count); -} -void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) -{ - _insl_ns((u32 __iomem *) addr, dst, count); -} -EXPORT_SYMBOL(ioread8_rep); -EXPORT_SYMBOL(ioread16_rep); -EXPORT_SYMBOL(ioread32_rep); - -void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) -{ - _outsb((u8 __iomem *) addr, src, count); -} -void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) -{ - _outsw_ns((u16 __iomem *) addr, src, count); -} -void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) -{ - _outsl_ns((u32 __iomem *) addr, src, count); -} -EXPORT_SYMBOL(iowrite8_rep); -EXPORT_SYMBOL(iowrite16_rep); -EXPORT_SYMBOL(iowrite32_rep); - -void __iomem *ioport_map(unsigned long port, unsigned int len) -{ - if (!_IO_IS_VALID(port)) - return NULL; - return (void __iomem *) (port+pci_io_base); -} - -void ioport_unmap(void __iomem *addr) -{ - /* Nothing to do */ -} -EXPORT_SYMBOL(ioport_map); -EXPORT_SYMBOL(ioport_unmap); - -void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) -{ - unsigned long start = pci_resource_start(dev, bar); - unsigned long len = pci_resource_len(dev, bar); - unsigned long flags = pci_resource_flags(dev, bar); - - if (!len) - return NULL; - if (max && len > max) - len = max; - if (flags & IORESOURCE_IO) - return ioport_map(start, len); - if (flags & IORESOURCE_MEM) - return ioremap(start, len); - /* What? */ - return NULL; -} - -void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ - /* Nothing to do */ -} -EXPORT_SYMBOL(pci_iomap); -EXPORT_SYMBOL(pci_iounmap); diff --git a/arch/ppc64/kernel/iommu.c b/arch/ppc64/kernel/iommu.c deleted file mode 100644 index 4d9b4388918b..000000000000 --- a/arch/ppc64/kernel/iommu.c +++ /dev/null @@ -1,572 +0,0 @@ -/* - * arch/ppc64/kernel/iommu.c - * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation - * - * Rewrite, cleanup, new allocation schemes, virtual merging: - * Copyright (C) 2004 Olof Johansson, IBM Corporation - * and Ben. Herrenschmidt, IBM Corporation - * - * Dynamic DMA mapping support, bus-independent parts. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DBG(...) - -#ifdef CONFIG_IOMMU_VMERGE -static int novmerge = 0; -#else -static int novmerge = 1; -#endif - -static int __init setup_iommu(char *str) -{ - if (!strcmp(str, "novmerge")) - novmerge = 1; - else if (!strcmp(str, "vmerge")) - novmerge = 0; - return 1; -} - -__setup("iommu=", setup_iommu); - -static unsigned long iommu_range_alloc(struct iommu_table *tbl, - unsigned long npages, - unsigned long *handle, - unsigned int align_order) -{ - unsigned long n, end, i, start; - unsigned long limit; - int largealloc = npages > 15; - int pass = 0; - unsigned long align_mask; - - align_mask = 0xffffffffffffffffl >> (64 - align_order); - - /* This allocator was derived from x86_64's bit string search */ - - /* Sanity check */ - if (unlikely(npages) == 0) { - if (printk_ratelimit()) - WARN_ON(1); - return DMA_ERROR_CODE; - } - - if (handle && *handle) - start = *handle; - else - start = largealloc ? tbl->it_largehint : tbl->it_hint; - - /* Use only half of the table for small allocs (15 pages or less) */ - limit = largealloc ? tbl->it_size : tbl->it_halfpoint; - - if (largealloc && start < tbl->it_halfpoint) - start = tbl->it_halfpoint; - - /* The case below can happen if we have a small segment appended - * to a large, or when the previous alloc was at the very end of - * the available space. If so, go back to the initial start. - */ - if (start >= limit) - start = largealloc ? tbl->it_largehint : tbl->it_hint; - - again: - - n = find_next_zero_bit(tbl->it_map, limit, start); - - /* Align allocation */ - n = (n + align_mask) & ~align_mask; - - end = n + npages; - - if (unlikely(end >= limit)) { - if (likely(pass < 2)) { - /* First failure, just rescan the half of the table. - * Second failure, rescan the other half of the table. - */ - start = (largealloc ^ pass) ? tbl->it_halfpoint : 0; - limit = pass ? tbl->it_size : limit; - pass++; - goto again; - } else { - /* Third failure, give up */ - return DMA_ERROR_CODE; - } - } - - for (i = n; i < end; i++) - if (test_bit(i, tbl->it_map)) { - start = i+1; - goto again; - } - - for (i = n; i < end; i++) - __set_bit(i, tbl->it_map); - - /* Bump the hint to a new block for small allocs. */ - if (largealloc) { - /* Don't bump to new block to avoid fragmentation */ - tbl->it_largehint = end; - } else { - /* Overflow will be taken care of at the next allocation */ - tbl->it_hint = (end + tbl->it_blocksize - 1) & - ~(tbl->it_blocksize - 1); - } - - /* Update handle for SG allocations */ - if (handle) - *handle = end; - - return n; -} - -static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page, - unsigned int npages, enum dma_data_direction direction, - unsigned int align_order) -{ - unsigned long entry, flags; - dma_addr_t ret = DMA_ERROR_CODE; - - spin_lock_irqsave(&(tbl->it_lock), flags); - - entry = iommu_range_alloc(tbl, npages, NULL, align_order); - - if (unlikely(entry == DMA_ERROR_CODE)) { - spin_unlock_irqrestore(&(tbl->it_lock), flags); - return DMA_ERROR_CODE; - } - - entry += tbl->it_offset; /* Offset into real TCE table */ - ret = entry << PAGE_SHIFT; /* Set the return dma address */ - - /* Put the TCEs in the HW table */ - ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & PAGE_MASK, - direction); - - - /* Flush/invalidate TLB caches if necessary */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); - - /* Make sure updates are seen by hardware */ - mb(); - - return ret; -} - -static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, - unsigned int npages) -{ - unsigned long entry, free_entry; - unsigned long i; - - entry = dma_addr >> PAGE_SHIFT; - free_entry = entry - tbl->it_offset; - - if (((free_entry + npages) > tbl->it_size) || - (entry < tbl->it_offset)) { - if (printk_ratelimit()) { - printk(KERN_INFO "iommu_free: invalid entry\n"); - printk(KERN_INFO "\tentry = 0x%lx\n", entry); - printk(KERN_INFO "\tdma_addr = 0x%lx\n", (u64)dma_addr); - printk(KERN_INFO "\tTable = 0x%lx\n", (u64)tbl); - printk(KERN_INFO "\tbus# = 0x%lx\n", (u64)tbl->it_busno); - printk(KERN_INFO "\tsize = 0x%lx\n", (u64)tbl->it_size); - printk(KERN_INFO "\tstartOff = 0x%lx\n", (u64)tbl->it_offset); - printk(KERN_INFO "\tindex = 0x%lx\n", (u64)tbl->it_index); - WARN_ON(1); - } - return; - } - - ppc_md.tce_free(tbl, entry, npages); - - for (i = 0; i < npages; i++) - __clear_bit(free_entry+i, tbl->it_map); -} - -static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, - unsigned int npages) -{ - unsigned long flags; - - spin_lock_irqsave(&(tbl->it_lock), flags); - - __iommu_free(tbl, dma_addr, npages); - - /* Make sure TLB cache is flushed if the HW needs it. We do - * not do an mb() here on purpose, it is not needed on any of - * the current platforms. - */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); -} - -int iommu_map_sg(struct device *dev, struct iommu_table *tbl, - struct scatterlist *sglist, int nelems, - enum dma_data_direction direction) -{ - dma_addr_t dma_next = 0, dma_addr; - unsigned long flags; - struct scatterlist *s, *outs, *segstart; - int outcount, incount; - unsigned long handle; - - BUG_ON(direction == DMA_NONE); - - if ((nelems == 0) || !tbl) - return 0; - - outs = s = segstart = &sglist[0]; - outcount = 1; - incount = nelems; - handle = 0; - - /* Init first segment length for backout at failure */ - outs->dma_length = 0; - - DBG("mapping %d elements:\n", nelems); - - spin_lock_irqsave(&(tbl->it_lock), flags); - - for (s = outs; nelems; nelems--, s++) { - unsigned long vaddr, npages, entry, slen; - - slen = s->length; - /* Sanity check */ - if (slen == 0) { - dma_next = 0; - continue; - } - /* Allocate iommu entries for that segment */ - vaddr = (unsigned long)page_address(s->page) + s->offset; - npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK); - npages >>= PAGE_SHIFT; - entry = iommu_range_alloc(tbl, npages, &handle, 0); - - DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); - - /* Handle failure */ - if (unlikely(entry == DMA_ERROR_CODE)) { - if (printk_ratelimit()) - printk(KERN_INFO "iommu_alloc failed, tbl %p vaddr %lx" - " npages %lx\n", tbl, vaddr, npages); - goto failure; - } - - /* Convert entry to a dma_addr_t */ - entry += tbl->it_offset; - dma_addr = entry << PAGE_SHIFT; - dma_addr |= s->offset; - - DBG(" - %lx pages, entry: %lx, dma_addr: %lx\n", - npages, entry, dma_addr); - - /* Insert into HW table */ - ppc_md.tce_build(tbl, entry, npages, vaddr & PAGE_MASK, direction); - - /* If we are in an open segment, try merging */ - if (segstart != s) { - DBG(" - trying merge...\n"); - /* We cannot merge if: - * - allocated dma_addr isn't contiguous to previous allocation - */ - if (novmerge || (dma_addr != dma_next)) { - /* Can't merge: create a new segment */ - segstart = s; - outcount++; outs++; - DBG(" can't merge, new segment.\n"); - } else { - outs->dma_length += s->length; - DBG(" merged, new len: %lx\n", outs->dma_length); - } - } - - if (segstart == s) { - /* This is a new segment, fill entries */ - DBG(" - filling new segment.\n"); - outs->dma_address = dma_addr; - outs->dma_length = slen; - } - - /* Calculate next page pointer for contiguous check */ - dma_next = dma_addr + slen; - - DBG(" - dma next is: %lx\n", dma_next); - } - - /* Flush/invalidate TLB caches if necessary */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); - - /* Make sure updates are seen by hardware */ - mb(); - - DBG("mapped %d elements:\n", outcount); - - /* For the sake of iommu_unmap_sg, we clear out the length in the - * next entry of the sglist if we didn't fill the list completely - */ - if (outcount < incount) { - outs++; - outs->dma_address = DMA_ERROR_CODE; - outs->dma_length = 0; - } - return outcount; - - failure: - for (s = &sglist[0]; s <= outs; s++) { - if (s->dma_length != 0) { - unsigned long vaddr, npages; - - vaddr = s->dma_address & PAGE_MASK; - npages = (PAGE_ALIGN(s->dma_address + s->dma_length) - vaddr) - >> PAGE_SHIFT; - __iommu_free(tbl, vaddr, npages); - } - } - spin_unlock_irqrestore(&(tbl->it_lock), flags); - return 0; -} - - -void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction) -{ - unsigned long flags; - - BUG_ON(direction == DMA_NONE); - - if (!tbl) - return; - - spin_lock_irqsave(&(tbl->it_lock), flags); - - while (nelems--) { - unsigned int npages; - dma_addr_t dma_handle = sglist->dma_address; - - if (sglist->dma_length == 0) - break; - npages = (PAGE_ALIGN(dma_handle + sglist->dma_length) - - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT; - __iommu_free(tbl, dma_handle, npages); - sglist++; - } - - /* Flush/invalidate TLBs if necessary. As for iommu_free(), we - * do not do an mb() here, the affected platforms do not need it - * when freeing. - */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); -} - -/* - * Build a iommu_table structure. This contains a bit map which - * is used to manage allocation of the tce space. - */ -struct iommu_table *iommu_init_table(struct iommu_table *tbl) -{ - unsigned long sz; - static int welcomed = 0; - - /* Set aside 1/4 of the table for large allocations. */ - tbl->it_halfpoint = tbl->it_size * 3 / 4; - - /* number of bytes needed for the bitmap */ - sz = (tbl->it_size + 7) >> 3; - - tbl->it_map = (unsigned long *)__get_free_pages(GFP_ATOMIC, get_order(sz)); - if (!tbl->it_map) - panic("iommu_init_table: Can't allocate %ld bytes\n", sz); - - memset(tbl->it_map, 0, sz); - - tbl->it_hint = 0; - tbl->it_largehint = tbl->it_halfpoint; - spin_lock_init(&tbl->it_lock); - - /* Clear the hardware table in case firmware left allocations in it */ - ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); - - if (!welcomed) { - printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", - novmerge ? "disabled" : "enabled"); - welcomed = 1; - } - - return tbl; -} - -void iommu_free_table(struct device_node *dn) -{ - struct pci_dn *pdn = dn->data; - struct iommu_table *tbl = pdn->iommu_table; - unsigned long bitmap_sz, i; - unsigned int order; - - if (!tbl || !tbl->it_map) { - printk(KERN_ERR "%s: expected TCE map for %s\n", __FUNCTION__, - dn->full_name); - return; - } - - /* verify that table contains no entries */ - /* it_size is in entries, and we're examining 64 at a time */ - for (i = 0; i < (tbl->it_size/64); i++) { - if (tbl->it_map[i] != 0) { - printk(KERN_WARNING "%s: Unexpected TCEs for %s\n", - __FUNCTION__, dn->full_name); - break; - } - } - - /* calculate bitmap size in bytes */ - bitmap_sz = (tbl->it_size + 7) / 8; - - /* free bitmap */ - order = get_order(bitmap_sz); - free_pages((unsigned long) tbl->it_map, order); - - /* free table */ - kfree(tbl); -} - -/* Creates TCEs for a user provided buffer. The user buffer must be - * contiguous real kernel storage (not vmalloc). The address of the buffer - * passed here is the kernel (virtual) address of the buffer. The buffer - * need not be page aligned, the dma_addr_t returned will point to the same - * byte within the page as vaddr. - */ -dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr, - size_t size, enum dma_data_direction direction) -{ - dma_addr_t dma_handle = DMA_ERROR_CODE; - unsigned long uaddr; - unsigned int npages; - - BUG_ON(direction == DMA_NONE); - - uaddr = (unsigned long)vaddr; - npages = PAGE_ALIGN(uaddr + size) - (uaddr & PAGE_MASK); - npages >>= PAGE_SHIFT; - - if (tbl) { - dma_handle = iommu_alloc(tbl, vaddr, npages, direction, 0); - if (dma_handle == DMA_ERROR_CODE) { - if (printk_ratelimit()) { - printk(KERN_INFO "iommu_alloc failed, " - "tbl %p vaddr %p npages %d\n", - tbl, vaddr, npages); - } - } else - dma_handle |= (uaddr & ~PAGE_MASK); - } - - return dma_handle; -} - -void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - - if (tbl) - iommu_free(tbl, dma_handle, (PAGE_ALIGN(dma_handle + size) - - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT); -} - -/* Allocates a contiguous real buffer and creates mappings over it. - * Returns the virtual address of the buffer and sets dma_handle - * to the dma address (mapping) of the first page. - */ -void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - void *ret = NULL; - dma_addr_t mapping; - unsigned int npages, order; - - size = PAGE_ALIGN(size); - npages = size >> PAGE_SHIFT; - order = get_order(size); - - /* - * Client asked for way too much space. This is checked later - * anyway. It is easier to debug here for the drivers than in - * the tce tables. - */ - if (order >= IOMAP_MAX_ORDER) { - printk("iommu_alloc_consistent size too large: 0x%lx\n", size); - return NULL; - } - - if (!tbl) - return NULL; - - /* Alloc enough pages (and possibly more) */ - ret = (void *)__get_free_pages(flag, order); - if (!ret) - return NULL; - memset(ret, 0, size); - - /* Set up tces to cover the allocated range */ - mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL, order); - if (mapping == DMA_ERROR_CODE) { - free_pages((unsigned long)ret, order); - ret = NULL; - } else - *dma_handle = mapping; - return ret; -} - -void iommu_free_coherent(struct iommu_table *tbl, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - unsigned int npages; - - if (tbl) { - size = PAGE_ALIGN(size); - npages = size >> PAGE_SHIFT; - iommu_free(tbl, dma_handle, npages); - free_pages((unsigned long)vaddr, get_order(size)); - } -} diff --git a/arch/ppc64/kernel/kprobes.c b/arch/ppc64/kernel/kprobes.c deleted file mode 100644 index 511af54e6230..000000000000 --- a/arch/ppc64/kernel/kprobes.c +++ /dev/null @@ -1,459 +0,0 @@ -/* - * Kernel Probes (KProbes) - * arch/ppc64/kernel/kprobes.c - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) IBM Corporation, 2002, 2004 - * - * 2002-Oct Created by Vamsi Krishna S Kernel - * Probes initial implementation ( includes contributions from - * Rusty Russell). - * 2004-July Suparna Bhattacharya added jumper probes - * interface to access function arguments. - * 2004-Nov Ananth N Mavinakayanahalli kprobes port - * for PPC64 - */ - -#include -#include -#include -#include -#include -#include -#include - -static DECLARE_MUTEX(kprobe_mutex); -DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; -DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); - -int __kprobes arch_prepare_kprobe(struct kprobe *p) -{ - int ret = 0; - kprobe_opcode_t insn = *p->addr; - - if ((unsigned long)p->addr & 0x03) { - printk("Attempt to register kprobe at an unaligned address\n"); - ret = -EINVAL; - } else if (IS_MTMSRD(insn) || IS_RFID(insn)) { - printk("Cannot register a kprobe on rfid or mtmsrd\n"); - ret = -EINVAL; - } - - /* insn must be on a special executable page on ppc64 */ - if (!ret) { - down(&kprobe_mutex); - p->ainsn.insn = get_insn_slot(); - up(&kprobe_mutex); - if (!p->ainsn.insn) - ret = -ENOMEM; - } - return ret; -} - -void __kprobes arch_copy_kprobe(struct kprobe *p) -{ - memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - p->opcode = *p->addr; -} - -void __kprobes arch_arm_kprobe(struct kprobe *p) -{ - *p->addr = BREAKPOINT_INSTRUCTION; - flush_icache_range((unsigned long) p->addr, - (unsigned long) p->addr + sizeof(kprobe_opcode_t)); -} - -void __kprobes arch_disarm_kprobe(struct kprobe *p) -{ - *p->addr = p->opcode; - flush_icache_range((unsigned long) p->addr, - (unsigned long) p->addr + sizeof(kprobe_opcode_t)); -} - -void __kprobes arch_remove_kprobe(struct kprobe *p) -{ - down(&kprobe_mutex); - free_insn_slot(p->ainsn.insn); - up(&kprobe_mutex); -} - -static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = *p->ainsn.insn; - - regs->msr |= MSR_SE; - - /* single step inline if it is a trap variant */ - if (is_trap(insn)) - regs->nip = (unsigned long)p->addr; - else - regs->nip = (unsigned long)p->ainsn.insn; -} - -static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) -{ - kcb->prev_kprobe.kp = kprobe_running(); - kcb->prev_kprobe.status = kcb->kprobe_status; - kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr; -} - -static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb) -{ - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; - kcb->kprobe_status = kcb->prev_kprobe.status; - kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr; -} - -static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - __get_cpu_var(current_kprobe) = p; - kcb->kprobe_saved_msr = regs->msr; -} - -/* Called with kretprobe_lock held */ -void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, - struct pt_regs *regs) -{ - struct kretprobe_instance *ri; - - if ((ri = get_free_rp_inst(rp)) != NULL) { - ri->rp = rp; - ri->task = current; - ri->ret_addr = (kprobe_opcode_t *)regs->link; - - /* Replace the return addr with trampoline addr */ - regs->link = (unsigned long)kretprobe_trampoline; - add_rp_inst(ri); - } else { - rp->nmissed++; - } -} - -static inline int kprobe_handler(struct pt_regs *regs) -{ - struct kprobe *p; - int ret = 0; - unsigned int *addr = (unsigned int *)regs->nip; - struct kprobe_ctlblk *kcb; - - /* - * We don't want to be preempted for the entire - * duration of kprobe processing - */ - preempt_disable(); - kcb = get_kprobe_ctlblk(); - - /* Check we're not actually recursing */ - if (kprobe_running()) { - p = get_kprobe(addr); - if (p) { - kprobe_opcode_t insn = *p->ainsn.insn; - if (kcb->kprobe_status == KPROBE_HIT_SS && - is_trap(insn)) { - regs->msr &= ~MSR_SE; - regs->msr |= kcb->kprobe_saved_msr; - goto no_kprobe; - } - /* We have reentered the kprobe_handler(), since - * another probe was hit while within the handler. - * We here save the original kprobes variables and - * just single step on the instruction of the new probe - * without calling any user handlers. - */ - save_previous_kprobe(kcb); - set_current_kprobe(p, regs, kcb); - kcb->kprobe_saved_msr = regs->msr; - p->nmissed++; - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_REENTER; - return 1; - } else { - p = __get_cpu_var(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } - } - goto no_kprobe; - } - - p = get_kprobe(addr); - if (!p) { - if (*addr != BREAKPOINT_INSTRUCTION) { - /* - * PowerPC has multiple variants of the "trap" - * instruction. If the current instruction is a - * trap variant, it could belong to someone else - */ - kprobe_opcode_t cur_insn = *addr; - if (is_trap(cur_insn)) - goto no_kprobe; - /* - * The breakpoint instruction was removed right - * after we hit it. Another cpu has removed - * either a probepoint or a debugger breakpoint - * at this address. In either case, no further - * handling of this interrupt is appropriate. - */ - ret = 1; - } - /* Not one of ours: let kernel handle it */ - goto no_kprobe; - } - - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - set_current_kprobe(p, regs, kcb); - if (p->pre_handler && p->pre_handler(p, regs)) - /* handler has already set things up, so skip ss setup */ - return 1; - -ss_probe: - prepare_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; - return 1; - -no_kprobe: - preempt_enable_no_resched(); - return ret; -} - -/* - * Function return probe trampoline: - * - init_kprobes() establishes a probepoint here - * - When the probed function returns, this probe - * causes the handlers to fire - */ -void kretprobe_trampoline_holder(void) -{ - asm volatile(".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n" - "nop\n"); -} - -/* - * Called when the probe at kretprobe trampoline is hit - */ -int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kretprobe_instance *ri = NULL; - struct hlist_head *head; - struct hlist_node *node, *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; - - spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); - - /* - * It is possible to have multiple instances associated with a given - * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always inserted at the head of the list - * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the - * real return address, and all the rest will point to - * kretprobe_trampoline - */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - if (ri->rp && ri->rp->handler) - ri->rp->handler(ri, regs); - - orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); - regs->nip = orig_ret_address; - - reset_current_kprobe(); - spin_unlock_irqrestore(&kretprobe_lock, flags); - preempt_enable_no_resched(); - - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler - * to run (and have re-enabled preemption) - */ - return 1; -} - -/* - * Called after single-stepping. p->addr is the address of the - * instruction whose first byte has been replaced by the "breakpoint" - * instruction. To avoid the SMP problems that can occur when we - * temporarily put back the original opcode to single-step, we - * single-stepped a copy of the instruction. The address of this - * copy is p->ainsn.insn. - */ -static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) -{ - int ret; - unsigned int insn = *p->ainsn.insn; - - regs->nip = (unsigned long)p->addr; - ret = emulate_step(regs, insn); - if (ret == 0) - regs->nip = (unsigned long)p->addr + 4; -} - -static inline int post_kprobe_handler(struct pt_regs *regs) -{ - struct kprobe *cur = kprobe_running(); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (!cur) - return 0; - - if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - cur->post_handler(cur, regs, 0); - } - - resume_execution(cur, regs); - regs->msr |= kcb->kprobe_saved_msr; - - /*Restore back the original saved kprobes variables and continue. */ - if (kcb->kprobe_status == KPROBE_REENTER) { - restore_previous_kprobe(kcb); - goto out; - } - reset_current_kprobe(); -out: - preempt_enable_no_resched(); - - /* - * if somebody else is singlestepping across a probe point, msr - * will have SE set, in which case, continue the remaining processing - * of do_debug, as if this is not a probe hit. - */ - if (regs->msr & MSR_SE) - return 0; - - return 1; -} - -static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) -{ - struct kprobe *cur = kprobe_running(); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs); - regs->msr &= ~MSR_SE; - regs->msr |= kcb->kprobe_saved_msr; - - reset_current_kprobe(); - preempt_enable_no_resched(); - } - return 0; -} - -/* - * Wrapper routine to for handling exceptions. - */ -int __kprobes kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - struct die_args *args = (struct die_args *)data; - int ret = NOTIFY_DONE; - - switch (val) { - case DIE_BPT: - if (kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_SSTEP: - if (post_kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_PAGE_FAULT: - /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && - kprobe_fault_handler(args->regs, args->trapnr)) - ret = NOTIFY_STOP; - preempt_enable(); - break; - default: - break; - } - return ret; -} - -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->nip = (unsigned long)(((func_descr_t *)jp->entry)->entry); - regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - asm volatile("trap" ::: "memory"); -} - -void __kprobes jprobe_return_end(void) -{ -}; - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* - * FIXME - we should ideally be validating that we got here 'cos - * of the "trap" in jprobe_return() above, before restoring the - * saved regs... - */ - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - preempt_enable_no_resched(); - return 1; -} - -static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, - .pre_handler = trampoline_probe_handler -}; - -int __init arch_init_kprobes(void) -{ - return register_kprobe(&trampoline_p); -} diff --git a/arch/ppc64/kernel/machine_kexec.c b/arch/ppc64/kernel/machine_kexec.c deleted file mode 100644 index 97c51e452be7..000000000000 --- a/arch/ppc64/kernel/machine_kexec.c +++ /dev/null @@ -1,358 +0,0 @@ -/* - * machine_kexec.c - handle transition of Linux booting another kernel - * - * Copyright (C) 2004-2005, IBM Corp. - * - * Created by: Milton D Miller II - * - * This source code is licensed under the GNU General Public License, - * Version 2. See the file COPYING for more details. - */ - - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include /* _end */ -#include -#include - -#define HASH_GROUP_SIZE 0x80 /* size of each hash group, asm/mmu.h */ - -/* Have this around till we move it into crash specific file */ -note_buf_t crash_notes[NR_CPUS]; - -/* Dummy for now. Not sure if we need to have a crash shutdown in here - * and if what it will achieve. Letting it be now to compile the code - * in generic kexec environment - */ -void machine_crash_shutdown(struct pt_regs *regs) -{ - /* do nothing right now */ - /* smp_relase_cpus() if we want smp on panic kernel */ - /* cpu_irq_down to isolate us until we are ready */ -} - -int machine_kexec_prepare(struct kimage *image) -{ - int i; - unsigned long begin, end; /* limits of segment */ - unsigned long low, high; /* limits of blocked memory range */ - struct device_node *node; - unsigned long *basep; - unsigned int *sizep; - - if (!ppc_md.hpte_clear_all) - return -ENOENT; - - /* - * Since we use the kernel fault handlers and paging code to - * handle the virtual mode, we must make sure no destination - * overlaps kernel static data or bss. - */ - for (i = 0; i < image->nr_segments; i++) - if (image->segment[i].mem < __pa(_end)) - return -ETXTBSY; - - /* - * For non-LPAR, we absolutely can not overwrite the mmu hash - * table, since we are still using the bolted entries in it to - * do the copy. Check that here. - * - * It is safe if the end is below the start of the blocked - * region (end <= low), or if the beginning is after the - * end of the blocked region (begin >= high). Use the - * boolean identity !(a || b) === (!a && !b). - */ - if (htab_address) { - low = __pa(htab_address); - high = low + (htab_hash_mask + 1) * HASH_GROUP_SIZE; - - for (i = 0; i < image->nr_segments; i++) { - begin = image->segment[i].mem; - end = begin + image->segment[i].memsz; - - if ((begin < high) && (end > low)) - return -ETXTBSY; - } - } - - /* We also should not overwrite the tce tables */ - for (node = of_find_node_by_type(NULL, "pci"); node != NULL; - node = of_find_node_by_type(node, "pci")) { - basep = (unsigned long *)get_property(node, "linux,tce-base", - NULL); - sizep = (unsigned int *)get_property(node, "linux,tce-size", - NULL); - if (basep == NULL || sizep == NULL) - continue; - - low = *basep; - high = low + (*sizep); - - for (i = 0; i < image->nr_segments; i++) { - begin = image->segment[i].mem; - end = begin + image->segment[i].memsz; - - if ((begin < high) && (end > low)) - return -ETXTBSY; - } - } - - return 0; -} - -void machine_kexec_cleanup(struct kimage *image) -{ - /* we do nothing in prepare that needs to be undone */ -} - -#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE) - -static void copy_segments(unsigned long ind) -{ - unsigned long entry; - unsigned long *ptr; - void *dest; - void *addr; - - /* - * We rely on kexec_load to create a lists that properly - * initializes these pointers before they are used. - * We will still crash if the list is wrong, but at least - * the compiler will be quiet. - */ - ptr = NULL; - dest = NULL; - - for (entry = ind; !(entry & IND_DONE); entry = *ptr++) { - addr = __va(entry & PAGE_MASK); - - switch (entry & IND_FLAGS) { - case IND_DESTINATION: - dest = addr; - break; - case IND_INDIRECTION: - ptr = addr; - break; - case IND_SOURCE: - copy_page(dest, addr); - dest += PAGE_SIZE; - } - } -} - -void kexec_copy_flush(struct kimage *image) -{ - long i, nr_segments = image->nr_segments; - struct kexec_segment ranges[KEXEC_SEGMENT_MAX]; - - /* save the ranges on the stack to efficiently flush the icache */ - memcpy(ranges, image->segment, sizeof(ranges)); - - /* - * After this call we may not use anything allocated in dynamic - * memory, including *image. - * - * Only globals and the stack are allowed. - */ - copy_segments(image->head); - - /* - * we need to clear the icache for all dest pages sometime, - * including ones that were in place on the original copy - */ - for (i = 0; i < nr_segments; i++) - flush_icache_range(ranges[i].mem + KERNELBASE, - ranges[i].mem + KERNELBASE + - ranges[i].memsz); -} - -#ifdef CONFIG_SMP - -/* FIXME: we should schedule this function to be called on all cpus based - * on calling the interrupts, but we would like to call it off irq level - * so that the interrupt controller is clean. - */ -void kexec_smp_down(void *arg) -{ - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(0, 1); - - local_irq_disable(); - kexec_smp_wait(); - /* NOTREACHED */ -} - -static void kexec_prepare_cpus(void) -{ - int my_cpu, i, notified=-1; - - smp_call_function(kexec_smp_down, NULL, 0, /* wait */0); - my_cpu = get_cpu(); - - /* check the others cpus are now down (via paca hw cpu id == -1) */ - for (i=0; i < NR_CPUS; i++) { - if (i == my_cpu) - continue; - - while (paca[i].hw_cpu_id != -1) { - barrier(); - if (!cpu_possible(i)) { - printk("kexec: cpu %d hw_cpu_id %d is not" - " possible, ignoring\n", - i, paca[i].hw_cpu_id); - break; - } - if (!cpu_online(i)) { - /* Fixme: this can be spinning in - * pSeries_secondary_wait with a paca - * waiting for it to go online. - */ - printk("kexec: cpu %d hw_cpu_id %d is not" - " online, ignoring\n", - i, paca[i].hw_cpu_id); - break; - } - if (i != notified) { - printk( "kexec: waiting for cpu %d (physical" - " %d) to go down\n", - i, paca[i].hw_cpu_id); - notified = i; - } - } - } - - /* after we tell the others to go down */ - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(0, 0); - - put_cpu(); - - local_irq_disable(); -} - -#else /* ! SMP */ - -static void kexec_prepare_cpus(void) -{ - /* - * move the secondarys to us so that we can copy - * the new kernel 0-0x100 safely - * - * do this if kexec in setup.c ? - * - * We need to release the cpus if we are ever going from an - * UP to an SMP kernel. - */ - smp_release_cpus(); - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(0, 0); - local_irq_disable(); -} - -#endif /* SMP */ - -/* - * kexec thread structure and stack. - * - * We need to make sure that this is 16384-byte aligned due to the - * way process stacks are handled. It also must be statically allocated - * or allocated as part of the kimage, because everything else may be - * overwritten when we copy the kexec image. We piggyback on the - * "init_task" linker section here to statically allocate a stack. - * - * We could use a smaller stack if we don't care about anything using - * current, but that audit has not been performed. - */ -union thread_union kexec_stack - __attribute__((__section__(".data.init_task"))) = { }; - -/* Our assembly helper, in kexec_stub.S */ -extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start, - void *image, void *control, - void (*clear_all)(void)) ATTRIB_NORET; - -/* too late to fail here */ -void machine_kexec(struct kimage *image) -{ - - /* prepare control code if any */ - - /* shutdown other cpus into our wait loop and quiesce interrupts */ - kexec_prepare_cpus(); - - /* switch to a staticly allocated stack. Based on irq stack code. - * XXX: the task struct will likely be invalid once we do the copy! - */ - kexec_stack.thread_info.task = current_thread_info()->task; - kexec_stack.thread_info.flags = 0; - - /* Some things are best done in assembly. Finding globals with - * a toc is easier in C, so pass in what we can. - */ - kexec_sequence(&kexec_stack, image->start, image, - page_address(image->control_code_page), - ppc_md.hpte_clear_all); - /* NOTREACHED */ -} - -/* Values we need to export to the second kernel via the device tree. */ -static unsigned long htab_base, htab_size, kernel_end; - -static struct property htab_base_prop = { - .name = "linux,htab-base", - .length = sizeof(unsigned long), - .value = (unsigned char *)&htab_base, -}; - -static struct property htab_size_prop = { - .name = "linux,htab-size", - .length = sizeof(unsigned long), - .value = (unsigned char *)&htab_size, -}; - -static struct property kernel_end_prop = { - .name = "linux,kernel-end", - .length = sizeof(unsigned long), - .value = (unsigned char *)&kernel_end, -}; - -static void __init export_htab_values(void) -{ - struct device_node *node; - - node = of_find_node_by_path("/chosen"); - if (!node) - return; - - kernel_end = __pa(_end); - prom_add_property(node, &kernel_end_prop); - - /* On machines with no htab htab_address is NULL */ - if (NULL == htab_address) - goto out; - - htab_base = __pa(htab_address); - prom_add_property(node, &htab_base_prop); - - htab_size = 1UL << ppc64_pft_size; - prom_add_property(node, &htab_size_prop); - - out: - of_node_put(node); -} - -void __init kexec_setup(void) -{ - export_htab_values(); -} diff --git a/arch/ppc64/kernel/misc.S b/arch/ppc64/kernel/misc.S deleted file mode 100644 index 5e089deb0a2b..000000000000 --- a/arch/ppc64/kernel/misc.S +++ /dev/null @@ -1,940 +0,0 @@ -/* - * arch/ppc/kernel/misc.S - * - * - * - * This file contains miscellaneous low-level functions. - * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) - * - * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) - * and Paul Mackerras. - * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) - * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - - .text - -/* - * Returns (address we were linked at) - (address we are running at) - * for use before the text and data are mapped to KERNELBASE. - */ - -_GLOBAL(reloc_offset) - mflr r0 - bl 1f -1: mflr r3 - LOADADDR(r4,1b) - sub r3,r4,r3 - mtlr r0 - blr - -_GLOBAL(get_msr) - mfmsr r3 - blr - -_GLOBAL(get_dar) - mfdar r3 - blr - -_GLOBAL(get_srr0) - mfsrr0 r3 - blr - -_GLOBAL(get_srr1) - mfsrr1 r3 - blr - -_GLOBAL(get_sp) - mr r3,r1 - blr - -#ifdef CONFIG_IRQSTACKS -_GLOBAL(call_do_softirq) - mflr r0 - std r0,16(r1) - stdu r1,THREAD_SIZE-112(r3) - mr r1,r3 - bl .__do_softirq - ld r1,0(r1) - ld r0,16(r1) - mtlr r0 - blr - -_GLOBAL(call___do_IRQ) - mflr r0 - std r0,16(r1) - stdu r1,THREAD_SIZE-112(r5) - mr r1,r5 - bl .__do_IRQ - ld r1,0(r1) - ld r0,16(r1) - mtlr r0 - blr -#endif /* CONFIG_IRQSTACKS */ - - /* - * To be called by C code which needs to do some operations with MMU - * disabled. Note that interrupts have to be disabled by the caller - * prior to calling us. The code called _MUST_ be in the RMO of course - * and part of the linear mapping as we don't attempt to translate the - * stack pointer at all. The function is called with the stack switched - * to this CPU emergency stack - * - * prototype is void *call_with_mmu_off(void *func, void *data); - * - * the called function is expected to be of the form - * - * void *called(void *data); - */ -_GLOBAL(call_with_mmu_off) - mflr r0 /* get link, save it on stackframe */ - std r0,16(r1) - mr r1,r5 /* save old stack ptr */ - ld r1,PACAEMERGSP(r13) /* get emerg. stack */ - subi r1,r1,STACK_FRAME_OVERHEAD - std r0,16(r1) /* save link on emerg. stack */ - std r5,0(r1) /* save old stack ptr in backchain */ - ld r3,0(r3) /* get to real function ptr (assume same TOC) */ - bl 2f /* we need LR to return, continue at label 2 */ - - ld r0,16(r1) /* we return here from the call, get LR and */ - ld r1,0(r1) /* .. old stack ptr */ - mtspr SPRN_SRR0,r0 /* and get back to virtual mode with these */ - mfmsr r4 - ori r4,r4,MSR_IR|MSR_DR - mtspr SPRN_SRR1,r4 - rfid - -2: mtspr SPRN_SRR0,r3 /* coming from above, enter real mode */ - mr r3,r4 /* get parameter */ - mfmsr r0 - ori r0,r0,MSR_IR|MSR_DR - xori r0,r0,MSR_IR|MSR_DR - mtspr SPRN_SRR1,r0 - rfid - - - .section ".toc","aw" -PPC64_CACHES: - .tc ppc64_caches[TC],ppc64_caches - .section ".text" - -/* - * Write any modified data cache blocks out to memory - * and invalidate the corresponding instruction cache blocks. - * - * flush_icache_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start through stop-1 inclusive - */ - -_KPROBE(__flush_icache_range) - -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - * and in some cases i-cache and d-cache line sizes differ from - * each other. - */ - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10)/* Get cache line size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of cache line size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -1: dcbst 0,r6 - add r6,r6,r7 - bdnz 1b - sync - -/* Now invalidate the instruction cache */ - - lwz r7,ICACHEL1LINESIZE(r10) /* Get Icache line size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 - lwz r9,ICACHEL1LOGLINESIZE(r10) /* Get log-2 of Icache line size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -2: icbi 0,r6 - add r6,r6,r7 - bdnz 2b - isync - blr - - .text -/* - * Like above, but only do the D-cache. - * - * flush_dcache_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start to stop-1 inclusive - */ -_GLOBAL(flush_dcache_range) - -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - */ - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -0: dcbst 0,r6 - add r6,r6,r7 - bdnz 0b - sync - blr - -/* - * Like above, but works on non-mapped physical addresses. - * Use only for non-LPAR setups ! It also assumes real mode - * is cacheable. Used for flushing out the DART before using - * it as uncacheable memory - * - * flush_dcache_phys_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start to stop-1 inclusive - */ -_GLOBAL(flush_dcache_phys_range) - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mfmsr r5 /* Disable MMU Data Relocation */ - ori r0,r5,MSR_DR - xori r0,r0,MSR_DR - sync - mtmsr r0 - sync - isync - mtctr r8 -0: dcbst 0,r6 - add r6,r6,r7 - bdnz 0b - sync - isync - mtmsr r5 /* Re-enable MMU Data Relocation */ - sync - isync - blr - -_GLOBAL(flush_inval_dcache_range) - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10)/* Get log-2 of dcache line size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - sync - isync - mtctr r8 -0: dcbf 0,r6 - add r6,r6,r7 - bdnz 0b - sync - isync - blr - - -/* - * Flush a particular page from the data cache to RAM. - * Note: this is necessary because the instruction cache does *not* - * snoop from the data cache. - * - * void __flush_dcache_icache(void *page) - */ -_GLOBAL(__flush_dcache_icache) -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - */ - -/* Flush the dcache */ - ld r7,PPC64_CACHES@toc(r2) - clrrdi r3,r3,PAGE_SHIFT /* Page align */ - lwz r4,DCACHEL1LINESPERPAGE(r7) /* Get # dcache lines per page */ - lwz r5,DCACHEL1LINESIZE(r7) /* Get dcache line size */ - mr r6,r3 - mtctr r4 -0: dcbst 0,r6 - add r6,r6,r5 - bdnz 0b - sync - -/* Now invalidate the icache */ - - lwz r4,ICACHEL1LINESPERPAGE(r7) /* Get # icache lines per page */ - lwz r5,ICACHEL1LINESIZE(r7) /* Get icache line size */ - mtctr r4 -1: icbi 0,r3 - add r3,r3,r5 - bdnz 1b - isync - blr - -/* - * I/O string operations - * - * insb(port, buf, len) - * outsb(port, buf, len) - * insw(port, buf, len) - * outsw(port, buf, len) - * insl(port, buf, len) - * outsl(port, buf, len) - * insw_ns(port, buf, len) - * outsw_ns(port, buf, len) - * insl_ns(port, buf, len) - * outsl_ns(port, buf, len) - * - * The *_ns versions don't do byte-swapping. - */ -_GLOBAL(_insb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbz r5,0(r3) - eieio - stbu r5,1(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbzu r5,1(r4) - stb r5,0(r3) - bdnz 00b - sync - blr - -_GLOBAL(_insw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhbrx r5,0,r3 - eieio - sthu r5,2(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - sthbrx r5,0,r3 - bdnz 00b - sync - blr - -_GLOBAL(_insl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwbrx r5,0,r3 - eieio - stwu r5,4(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stwbrx r5,0,r3 - bdnz 00b - sync - blr - -/* _GLOBAL(ide_insw) now in drivers/ide/ide-iops.c */ -_GLOBAL(_insw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhz r5,0(r3) - eieio - sthu r5,2(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -/* _GLOBAL(ide_outsw) now in drivers/ide/ide-iops.c */ -_GLOBAL(_outsw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - sth r5,0(r3) - bdnz 00b - sync - blr - -_GLOBAL(_insl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwz r5,0(r3) - eieio - stwu r5,4(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stw r5,0(r3) - bdnz 00b - sync - blr - -/* - * identify_cpu and calls setup_cpu - * In: r3 = base of the cpu_specs array - * r4 = address of cur_cpu_spec - * r5 = relocation offset - */ -_GLOBAL(identify_cpu) - mfpvr r7 -1: - lwz r8,CPU_SPEC_PVR_MASK(r3) - and r8,r8,r7 - lwz r9,CPU_SPEC_PVR_VALUE(r3) - cmplw 0,r9,r8 - beq 1f - addi r3,r3,CPU_SPEC_ENTRY_SIZE - b 1b -1: - add r0,r3,r5 - std r0,0(r4) - ld r4,CPU_SPEC_SETUP(r3) - sub r4,r4,r5 - ld r4,0(r4) - sub r4,r4,r5 - mtctr r4 - /* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */ - mr r4,r3 - mr r3,r5 - bctr - -/* - * do_cpu_ftr_fixups - goes through the list of CPU feature fixups - * and writes nop's over sections of code that don't apply for this cpu. - * r3 = data offset (not changed) - */ -_GLOBAL(do_cpu_ftr_fixups) - /* Get CPU 0 features */ - LOADADDR(r6,cur_cpu_spec) - sub r6,r6,r3 - ld r4,0(r6) - sub r4,r4,r3 - ld r4,CPU_SPEC_FEATURES(r4) - /* Get the fixup table */ - LOADADDR(r6,__start___ftr_fixup) - sub r6,r6,r3 - LOADADDR(r7,__stop___ftr_fixup) - sub r7,r7,r3 - /* Do the fixup */ -1: cmpld r6,r7 - bgelr - addi r6,r6,32 - ld r8,-32(r6) /* mask */ - and r8,r8,r4 - ld r9,-24(r6) /* value */ - cmpld r8,r9 - beq 1b - ld r8,-16(r6) /* section begin */ - ld r9,-8(r6) /* section end */ - subf. r9,r8,r9 - beq 1b - /* write nops over the section of code */ - /* todo: if large section, add a branch at the start of it */ - srwi r9,r9,2 - mtctr r9 - sub r8,r8,r3 - lis r0,0x60000000@h /* nop */ -3: stw r0,0(r8) - andi. r10,r4,CPU_FTR_SPLIT_ID_CACHE@l - beq 2f - dcbst 0,r8 /* suboptimal, but simpler */ - sync - icbi 0,r8 -2: addi r8,r8,4 - bdnz 3b - sync /* additional sync needed on g4 */ - isync - b 1b - -#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) -/* - * Do an IO access in real mode - */ -_GLOBAL(real_readb) - mfmsr r7 - ori r0,r7,MSR_DR - xori r0,r0,MSR_DR - sync - mtmsrd r0 - sync - isync - mfspr r6,SPRN_HID4 - rldicl r5,r6,32,0 - ori r5,r5,0x100 - rldicl r5,r5,32,0 - sync - mtspr SPRN_HID4,r5 - isync - slbia - isync - lbz r3,0(r3) - sync - mtspr SPRN_HID4,r6 - isync - slbia - isync - mtmsrd r7 - sync - isync - blr - -/* - * Do an IO access in real mode - */ -_GLOBAL(real_writeb) - mfmsr r7 - ori r0,r7,MSR_DR - xori r0,r0,MSR_DR - sync - mtmsrd r0 - sync - isync - mfspr r6,SPRN_HID4 - rldicl r5,r6,32,0 - ori r5,r5,0x100 - rldicl r5,r5,32,0 - sync - mtspr SPRN_HID4,r5 - isync - slbia - isync - stb r3,0(r4) - sync - mtspr SPRN_HID4,r6 - isync - slbia - isync - mtmsrd r7 - sync - isync - blr -#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */ - -/* - * SCOM access functions for 970 (FX only for now) - * - * unsigned long scom970_read(unsigned int address); - * void scom970_write(unsigned int address, unsigned long value); - * - * The address passed in is the 24 bits register address. This code - * is 970 specific and will not check the status bits, so you should - * know what you are doing. - */ -_GLOBAL(scom970_read) - /* interrupts off */ - mfmsr r4 - ori r0,r4,MSR_EE - xori r0,r0,MSR_EE - mtmsrd r0,1 - - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits - * (including parity). On current CPUs they must be 0'd, - * and finally or in RW bit - */ - rlwinm r3,r3,8,0,15 - ori r3,r3,0x8000 - - /* do the actual scom read */ - sync - mtspr SPRN_SCOMC,r3 - isync - mfspr r3,SPRN_SCOMD - isync - mfspr r0,SPRN_SCOMC - isync - - /* XXX: fixup result on some buggy 970's (ouch ! we lost a bit, bah - * that's the best we can do). Not implemented yet as we don't use - * the scom on any of the bogus CPUs yet, but may have to be done - * ultimately - */ - - /* restore interrupts */ - mtmsrd r4,1 - blr - - -_GLOBAL(scom970_write) - /* interrupts off */ - mfmsr r5 - ori r0,r5,MSR_EE - xori r0,r0,MSR_EE - mtmsrd r0,1 - - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits - * (including parity). On current CPUs they must be 0'd. - */ - - rlwinm r3,r3,8,0,15 - - sync - mtspr SPRN_SCOMD,r4 /* write data */ - isync - mtspr SPRN_SCOMC,r3 /* write command */ - isync - mfspr 3,SPRN_SCOMC - isync - - /* restore interrupts */ - mtmsrd r5,1 - blr - - -/* - * Create a kernel thread - * kernel_thread(fn, arg, flags) - */ -_GLOBAL(kernel_thread) - std r29,-24(r1) - std r30,-16(r1) - stdu r1,-STACK_FRAME_OVERHEAD(r1) - mr r29,r3 - mr r30,r4 - ori r3,r5,CLONE_VM /* flags */ - oris r3,r3,(CLONE_UNTRACED>>16) - li r4,0 /* new sp (unused) */ - li r0,__NR_clone - sc - cmpdi 0,r3,0 /* parent or child? */ - bne 1f /* return if parent */ - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - ld r2,8(r29) - ld r29,0(r29) - mtlr r29 /* fn addr in lr */ - mr r3,r30 /* load arg and call fn */ - blrl - li r0,__NR_exit /* exit after child exits */ - li r3,0 - sc -1: addi r1,r1,STACK_FRAME_OVERHEAD - ld r29,-24(r1) - ld r30,-16(r1) - blr - -/* - * disable_kernel_fp() - * Disable the FPU. - */ -_GLOBAL(disable_kernel_fp) - mfmsr r3 - rldicl r0,r3,(63-MSR_FP_LG),1 - rldicl r3,r0,(MSR_FP_LG+1),0 - mtmsrd r3 /* disable use of fpu now */ - isync - blr - -#ifdef CONFIG_ALTIVEC - -#if 0 /* this has no callers for now */ -/* - * disable_kernel_altivec() - * Disable the VMX. - */ -_GLOBAL(disable_kernel_altivec) - mfmsr r3 - rldicl r0,r3,(63-MSR_VEC_LG),1 - rldicl r3,r0,(MSR_VEC_LG+1),0 - mtmsrd r3 /* disable use of VMX now */ - isync - blr -#endif /* 0 */ - -/* - * giveup_altivec(tsk) - * Disable VMX for the task given as the argument, - * and save the vector registers in its thread_struct. - * Enables the VMX for use in the kernel on return. - */ -_GLOBAL(giveup_altivec) - mfmsr r5 - oris r5,r5,MSR_VEC@h - mtmsrd r5 /* enable use of VMX now */ - isync - cmpdi 0,r3,0 - beqlr- /* if no previous owner, done */ - addi r3,r3,THREAD /* want THREAD of task */ - ld r5,PT_REGS(r3) - cmpdi 0,r5,0 - SAVE_32VRS(0,r4,r3) - mfvscr vr0 - li r4,THREAD_VSCR - stvx vr0,r4,r3 - beq 1f - ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r3,MSR_VEC@h - andc r4,r4,r3 /* disable FP for previous task */ - std r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#ifndef CONFIG_SMP - li r5,0 - ld r4,last_task_used_altivec@got(r2) - std r5,0(r4) -#endif /* CONFIG_SMP */ - blr - -#endif /* CONFIG_ALTIVEC */ - -_GLOBAL(__setup_cpu_power3) - blr - -_GLOBAL(execve) - li r0,__NR_execve - sc - bnslr - neg r3,r3 - blr - -/* kexec_wait(phys_cpu) - * - * wait for the flag to change, indicating this kernel is going away but - * the slave code for the next one is at addresses 0 to 100. - * - * This is used by all slaves. - * - * Physical (hardware) cpu id should be in r3. - */ -_GLOBAL(kexec_wait) - bl 1f -1: mflr r5 - addi r5,r5,kexec_flag-1b - -99: HMT_LOW -#ifdef CONFIG_KEXEC /* use no memory without kexec */ - lwz r4,0(r5) - cmpwi 0,r4,0 - bnea 0x60 -#endif - b 99b - -/* this can be in text because we won't change it until we are - * running in real anyways - */ -kexec_flag: - .long 0 - - -#ifdef CONFIG_KEXEC - -/* kexec_smp_wait(void) - * - * call with interrupts off - * note: this is a terminal routine, it does not save lr - * - * get phys id from paca - * set paca id to -1 to say we got here - * switch to real mode - * join other cpus in kexec_wait(phys_id) - */ -_GLOBAL(kexec_smp_wait) - lhz r3,PACAHWCPUID(r13) - li r4,-1 - sth r4,PACAHWCPUID(r13) /* let others know we left */ - bl real_mode - b .kexec_wait - -/* - * switch to real mode (turn mmu off) - * we use the early kernel trick that the hardware ignores bits - * 0 and 1 (big endian) of the effective address in real mode - * - * don't overwrite r3 here, it is live for kexec_wait above. - */ -real_mode: /* assume normal blr return */ -1: li r9,MSR_RI - li r10,MSR_DR|MSR_IR - mflr r11 /* return address to SRR0 */ - mfmsr r12 - andc r9,r12,r9 - andc r10,r12,r10 - - mtmsrd r9,1 - mtspr SPRN_SRR1,r10 - mtspr SPRN_SRR0,r11 - rfid - - -/* - * kexec_sequence(newstack, start, image, control, clear_all()) - * - * does the grungy work with stack switching and real mode switches - * also does simple calls to other code - */ - -_GLOBAL(kexec_sequence) - mflr r0 - std r0,16(r1) - - /* switch stacks to newstack -- &kexec_stack.stack */ - stdu r1,THREAD_SIZE-112(r3) - mr r1,r3 - - li r0,0 - std r0,16(r1) - - /* save regs for local vars on new stack. - * yes, we won't go back, but ... - */ - std r31,-8(r1) - std r30,-16(r1) - std r29,-24(r1) - std r28,-32(r1) - std r27,-40(r1) - std r26,-48(r1) - std r25,-56(r1) - - stdu r1,-112-64(r1) - - /* save args into preserved regs */ - mr r31,r3 /* newstack (both) */ - mr r30,r4 /* start (real) */ - mr r29,r5 /* image (virt) */ - mr r28,r6 /* control, unused */ - mr r27,r7 /* clear_all() fn desc */ - mr r26,r8 /* spare */ - lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ - - /* disable interrupts, we are overwriting kernel data next */ - mfmsr r3 - rlwinm r3,r3,0,17,15 - mtmsrd r3,1 - - /* copy dest pages, flush whole dest image */ - mr r3,r29 - bl .kexec_copy_flush /* (image) */ - - /* turn off mmu */ - bl real_mode - - /* clear out hardware hash page table and tlb */ - ld r5,0(r27) /* deref function descriptor */ - mtctr r5 - bctrl /* ppc_md.hash_clear_all(void); */ - -/* - * kexec image calling is: - * the first 0x100 bytes of the entry point are copied to 0 - * - * all slaves branch to slave = 0x60 (absolute) - * slave(phys_cpu_id); - * - * master goes to start = entry point - * start(phys_cpu_id, start, 0); - * - * - * a wrapper is needed to call existing kernels, here is an approximate - * description of one method: - * - * v2: (2.6.10) - * start will be near the boot_block (maybe 0x100 bytes before it?) - * it will have a 0x60, which will b to boot_block, where it will wait - * and 0 will store phys into struct boot-block and load r3 from there, - * copy kernel 0-0x100 and tell slaves to back down to 0x60 again - * - * v1: (2.6.9) - * boot block will have all cpus scanning device tree to see if they - * are the boot cpu ????? - * other device tree differences (prop sizes, va vs pa, etc)... - */ - - /* copy 0x100 bytes starting at start to 0 */ - li r3,0 - mr r4,r30 - li r5,0x100 - li r6,0 - bl .copy_and_flush /* (dest, src, copy limit, start offset) */ -1: /* assume normal blr return */ - - /* release other cpus to the new kernel secondary start at 0x60 */ - mflr r5 - li r6,1 - stw r6,kexec_flag-1b(5) - mr r3,r25 # my phys cpu - mr r4,r30 # start, aka phys mem offset - mtlr 4 - li r5,0 - blr /* image->start(physid, image->start, 0); */ -#endif /* CONFIG_KEXEC */ diff --git a/arch/ppc64/kernel/module.c b/arch/ppc64/kernel/module.c deleted file mode 100644 index 928b8581fcb0..000000000000 --- a/arch/ppc64/kernel/module.c +++ /dev/null @@ -1,455 +0,0 @@ -/* Kernel module help for PPC64. - Copyright (C) 2001, 2003 Rusty Russell IBM Corporation. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -*/ -#include -#include -#include -#include -#include -#include -#include - -/* FIXME: We don't do .init separately. To do this, we'd need to have - a separate r2 value in the init and core section, and stub between - them, too. - - 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 - -/* There's actually a third entry here, but it's unused */ -struct ppc64_opd_entry -{ - unsigned long funcaddr; - unsigned long r2; -}; - -/* Like PPC32, we need little trampolines to do > 24-bit jumps (into - the kernel itself). But on PPC64, these need to be used for every - jump, actually, to reset r2 (TOC+0x8000). */ -struct ppc64_stub_entry -{ - /* 28 byte jump instruction sequence (7 instructions) */ - unsigned char jump[28]; - unsigned char unused[4]; - /* Data for the above code */ - struct ppc64_opd_entry opd; -}; - -/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external) - function which may be more than 24-bits away. We could simply - patch the new r2 value and function pointer into the stub, but it's - significantly shorter to put these values at the end of the stub - code, and patch the stub address (32-bits relative to the TOC ptr, - r2) into the stub. */ -static struct ppc64_stub_entry ppc64_stub = -{ .jump = { - 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, */ - 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, */ - /* Save current r2 value in magic place on the stack. */ - 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */ - 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */ - 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ - 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ - 0x4e, 0x80, 0x04, 0x20 /* bctr */ -} }; - -/* Count how many different 24-bit relocations (different symbol, - different addend) */ -static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num) -{ - unsigned int i, j, ret = 0; - - /* FIXME: Only count external ones --RR */ - /* Sure, this is order(n^2), but it's usually short, and not - time critical */ - for (i = 0; i < num; i++) { - /* Only count 24-bit relocs, others don't need stubs */ - if (ELF64_R_TYPE(rela[i].r_info) != R_PPC_REL24) - continue; - for (j = 0; j < i; j++) { - /* If this addend appeared before, it's - already been counted */ - if (rela[i].r_info == rela[j].r_info - && rela[i].r_addend == rela[j].r_addend) - break; - } - if (j == i) ret++; - } - return ret; -} - -void *module_alloc(unsigned long size) -{ - if (size == 0) - return NULL; - - return vmalloc_exec(size); -} - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) -{ - vfree(module_region); - /* FIXME: If module_region == mod->init_region, trim exception - table entries. */ -} - -/* Get size of potential trampolines required. */ -static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, - const Elf64_Shdr *sechdrs) -{ - /* One extra reloc so it's always 0-funcaddr terminated */ - unsigned long relocs = 1; - unsigned i; - - /* 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", - (void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size / sizeof(Elf64_Rela)); - relocs += count_relocs((void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size - / sizeof(Elf64_Rela)); - } - } - - DEBUGP("Looks like a total of %lu stubs, max\n", relocs); - return relocs * sizeof(struct ppc64_stub_entry); -} - -static void dedotify_versions(struct modversion_info *vers, - unsigned long size) -{ - struct modversion_info *end; - - for (end = (void *)vers + size; vers < end; vers++) - if (vers->name[0] == '.') - memmove(vers->name, vers->name+1, strlen(vers->name)); -} - -/* Undefined symbols which refer to .funcname, hack to funcname */ -static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) -{ - unsigned int i; - - for (i = 1; i < numsyms; i++) { - if (syms[i].st_shndx == SHN_UNDEF) { - char *name = strtab + syms[i].st_name; - if (name[0] == '.') - memmove(name, name+1, strlen(name)); - } - } -} - -int module_frob_arch_sections(Elf64_Ehdr *hdr, - Elf64_Shdr *sechdrs, - char *secstrings, - struct module *me) -{ - unsigned int i; - - /* Find .toc and .stubs sections, symtab and strtab */ - for (i = 1; i < hdr->e_shnum; i++) { - char *p; - if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) - me->arch.stubs_section = i; - else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) - me->arch.toc_section = i; - else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0) - dedotify_versions((void *)hdr + sechdrs[i].sh_offset, - sechdrs[i].sh_size); - - /* We don't handle .init for the moment: rename to _init */ - while ((p = strstr(secstrings + sechdrs[i].sh_name, ".init"))) - p[0] = '_'; - - if (sechdrs[i].sh_type == SHT_SYMTAB) - dedotify((void *)hdr + sechdrs[i].sh_offset, - sechdrs[i].sh_size / sizeof(Elf64_Sym), - (void *)hdr - + sechdrs[sechdrs[i].sh_link].sh_offset); - } - if (!me->arch.stubs_section || !me->arch.toc_section) { - printk("%s: doesn't contain .toc or .stubs.\n", me->name); - return -ENOEXEC; - } - - /* Override the stubs size */ - sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs); - return 0; -} - -int apply_relocate(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", me->name); - return -ENOEXEC; -} - -/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this - gives the value maximum span in an instruction which uses a signed - offset) */ -static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) -{ - return sechdrs[me->arch.toc_section].sh_addr + 0x8000; -} - -/* Both low and high 16 bits are added as SIGNED additions, so if low - 16 bits has high bit set, high 16 bits must be adjusted. These - macros do that (stolen from binutils). */ -#define PPC_LO(v) ((v) & 0xffff) -#define PPC_HI(v) (((v) >> 16) & 0xffff) -#define PPC_HA(v) PPC_HI ((v) + 0x8000) - -/* Patch stub to reference function and correct r2 value. */ -static inline int create_stub(Elf64_Shdr *sechdrs, - struct ppc64_stub_entry *entry, - struct ppc64_opd_entry *opd, - struct module *me) -{ - Elf64_Half *loc1, *loc2; - long reladdr; - - *entry = ppc64_stub; - - loc1 = (Elf64_Half *)&entry->jump[2]; - loc2 = (Elf64_Half *)&entry->jump[6]; - - /* 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", - me->name, (void *)reladdr, (void *)my_r2); - return 0; - } - DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr); - - *loc1 = PPC_HA(reladdr); - *loc2 = PPC_LO(reladdr); - entry->opd.funcaddr = opd->funcaddr; - entry->opd.r2 = opd->r2; - return 1; -} - -/* Create stub to jump to function described in this OPD: we need the - stub to set up the TOC ptr (r2) for the function. */ -static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, - unsigned long opdaddr, - struct module *me) -{ - struct ppc64_stub_entry *stubs; - struct ppc64_opd_entry *opd = (void *)opdaddr; - unsigned int i, num_stubs; - - num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs); - - /* Find this stub, or if that fails, the next avail. entry */ - stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stubs[i].opd.funcaddr; i++) { - BUG_ON(i >= num_stubs); - - if (stubs[i].opd.funcaddr == opd->funcaddr) - return (unsigned long)&stubs[i]; - } - - if (!create_stub(sechdrs, &stubs[i], opd, me)) - return 0; - - return (unsigned long)&stubs[i]; -} - -/* We expect a noop next: if it is, replace it with instruction to - restore r2. */ -static int restore_r2(u32 *instruction, struct module *me) -{ - if (*instruction != 0x60000000) { - printk("%s: Expect noop after relocate, got %08x\n", - me->name, *instruction); - return 0; - } - *instruction = 0xe8410028; /* ld r2,40(r1) */ - return 1; -} - -int apply_relocate_add(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - unsigned int i; - Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr; - Elf64_Sym *sym; - unsigned long *location; - unsigned long value; - - DEBUGP("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 */ - location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr - + rela[i].r_offset; - /* This is the symbol it is referring to */ - 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", - location, (long)ELF64_R_TYPE(rela[i].r_info), - strtab + sym->st_name, (unsigned long)sym->st_value, - (long)rela[i].r_addend); - - /* `Everything is relative'. */ - value = sym->st_value + rela[i].r_addend; - - switch (ELF64_R_TYPE(rela[i].r_info)) { - case R_PPC64_ADDR32: - /* Simply set it */ - *(u32 *)location = value; - break; - - case R_PPC64_ADDR64: - /* Simply set it */ - *(unsigned long *)location = value; - break; - - case R_PPC64_TOC: - *(unsigned long *)location = my_r2(sechdrs, me); - break; - - case R_PPC64_TOC16: - /* Subtact TOC pointer */ - value -= my_r2(sechdrs, me); - if (value + 0x8000 > 0xffff) { - printk("%s: bad TOC16 relocation (%lu)\n", - me->name, value); - return -ENOEXEC; - } - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - case R_PPC64_TOC16_DS: - /* Subtact TOC pointer */ - value -= my_r2(sechdrs, me); - if ((value & 3) != 0 || value + 0x8000 > 0xffff) { - printk("%s: bad TOC16_DS relocation (%lu)\n", - me->name, value); - return -ENOEXEC; - } - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xfffc) - | (value & 0xfffc); - break; - - case R_PPC_REL24: - /* FIXME: Handle weak symbols here --RR */ - if (sym->st_shndx == SHN_UNDEF) { - /* External: go via stub */ - value = stub_for_addr(sechdrs, value, me); - if (!value) - return -ENOENT; - if (!restore_r2((u32 *)location + 1, me)) - return -ENOEXEC; - } - - /* Convert value to relative */ - value -= (unsigned long)location; - if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){ - printk("%s: REL24 %li out of range!\n", - me->name, (long int)value); - return -ENOEXEC; - } - - /* Only replace bits 2 through 26 */ - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) - | (value & 0x03fffffc); - break; - - default: - printk("%s: Unknown ADD relocation: %lu\n", - me->name, - (unsigned long)ELF64_R_TYPE(rela[i].r_info)); - return -ENOEXEC; - } - } - - return 0; -} - -LIST_HEAD(module_bug_list); - -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, struct module *me) -{ - char *secstrings; - unsigned int i; - - me->arch.bug_table = NULL; - me->arch.num_bugs = 0; - - /* Find the __bug_table section, if present */ - secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - for (i = 1; i < hdr->e_shnum; i++) { - if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table")) - continue; - me->arch.bug_table = (void *) sechdrs[i].sh_addr; - me->arch.num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry); - break; - } - - /* - * Strictly speaking this should have a spinlock to protect against - * traversals, but since we only traverse on BUG()s, a spinlock - * could potentially lead to deadlock and thus be counter-productive. - */ - list_add(&me->arch.bug_list, &module_bug_list); - - return 0; -} - -void module_arch_cleanup(struct module *mod) -{ - list_del(&mod->arch.bug_list); -} - -struct bug_entry *module_find_bug(unsigned long bugaddr) -{ - struct mod_arch_specific *mod; - unsigned int i; - struct bug_entry *bug; - - list_for_each_entry(mod, &module_bug_list, bug_list) { - bug = mod->bug_table; - for (i = 0; i < mod->num_bugs; ++i, ++bug) - if (bugaddr == bug->bug_addr) - return bug; - } - return NULL; -} diff --git a/arch/ppc64/kernel/pci.c b/arch/ppc64/kernel/pci.c deleted file mode 100644 index 3cef1b8f57f0..000000000000 --- a/arch/ppc64/kernel/pci.c +++ /dev/null @@ -1,1319 +0,0 @@ -/* - * Port for PPC64 David Engebretsen, IBM Corp. - * Contains common pci routines for ppc64 platform, pSeries and iSeries brands. - * - * Copyright (C) 2003 Anton Blanchard , IBM - * Rework, based on alpha PCI code. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#undef DEBUG - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -unsigned long pci_probe_only = 1; -unsigned long pci_assign_all_buses = 0; - -/* - * legal IO pages under MAX_ISA_PORT. This is to ensure we don't touch - * devices we don't have access to. - */ -unsigned long io_page_mask; - -EXPORT_SYMBOL(io_page_mask); - -#ifdef CONFIG_PPC_MULTIPLATFORM -static void fixup_resource(struct resource *res, struct pci_dev *dev); -static void do_bus_setup(struct pci_bus *bus); -#endif - -unsigned int pcibios_assign_all_busses(void) -{ - return pci_assign_all_buses; -} - -/* pci_io_base -- the base address from which io bars are offsets. - * This is the lowest I/O base address (so bar values are always positive), - * and it *must* be the start of ISA space if an ISA bus exists because - * ISA drivers use hard coded offsets. If no ISA bus exists a dummy - * page is mapped and isa_io_limit prevents access to it. - */ -unsigned long isa_io_base; /* NULL if no ISA bus */ -EXPORT_SYMBOL(isa_io_base); -unsigned long pci_io_base; -EXPORT_SYMBOL(pci_io_base); - -void iSeries_pcibios_init(void); - -LIST_HEAD(hose_list); - -struct dma_mapping_ops pci_dma_ops; -EXPORT_SYMBOL(pci_dma_ops); - -int global_phb_number; /* Global phb counter */ - -/* Cached ISA bridge dev. */ -struct pci_dev *ppc64_isabridge_dev = NULL; - -static void fixup_broken_pcnet32(struct pci_dev* dev) -{ - if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) { - dev->vendor = PCI_VENDOR_ID_AMD; - pci_write_config_word(dev, PCI_VENDOR_ID, PCI_VENDOR_ID_AMD); - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TRIDENT, PCI_ANY_ID, fixup_broken_pcnet32); - -void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, - struct resource *res) -{ - unsigned long offset = 0; - struct pci_controller *hose = pci_bus_to_host(dev->bus); - - if (!hose) - return; - - if (res->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - pci_io_base; - - if (res->flags & IORESOURCE_MEM) - offset = hose->pci_mem_offset; - - region->start = res->start - offset; - region->end = res->end - offset; -} - -void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, - struct pci_bus_region *region) -{ - unsigned long offset = 0; - struct pci_controller *hose = pci_bus_to_host(dev->bus); - - if (!hose) - return; - - if (res->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - pci_io_base; - - if (res->flags & IORESOURCE_MEM) - offset = hose->pci_mem_offset; - - res->start = region->start + offset; - res->end = region->end + offset; -} - -#ifdef CONFIG_HOTPLUG -EXPORT_SYMBOL(pcibios_resource_to_bus); -EXPORT_SYMBOL(pcibios_bus_to_resource); -#endif - -/* - * We need to avoid collisions with `mirrored' VGA ports - * and other strange ISA hardware, so we always want the - * addresses to be allocated in the 0x000-0x0ff region - * modulo 0x400. - * - * Why? Because some silly external IO cards only decode - * the low 10 bits of the IO address. The 0x00-0xff region - * is reserved for motherboard devices that decode all 16 - * bits, so it's ok to allocate at, say, 0x2800-0x28ff, - * but we want to try to avoid allocating at 0x2900-0x2bff - * which might have be mirrored at 0x0100-0x03ff.. - */ -void pcibios_align_resource(void *data, struct resource *res, - unsigned long size, unsigned long align) -{ - struct pci_dev *dev = data; - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long start = res->start; - unsigned long alignto; - - if (res->flags & IORESOURCE_IO) { - unsigned long offset = (unsigned long)hose->io_base_virt - - pci_io_base; - /* Make sure we start at our min on all hoses */ - if (start - offset < PCIBIOS_MIN_IO) - start = PCIBIOS_MIN_IO + offset; - - /* - * Put everything into 0x00-0xff region modulo 0x400 - */ - if (start & 0x300) - start = (start + 0x3ff) & ~0x3ff; - - } else if (res->flags & IORESOURCE_MEM) { - /* Make sure we start at our min on all hoses */ - if (start - hose->pci_mem_offset < PCIBIOS_MIN_MEM) - start = PCIBIOS_MIN_MEM + hose->pci_mem_offset; - - /* Align to multiple of size of minimum base. */ - alignto = max(0x1000UL, align); - start = ALIGN(start, alignto); - } - - res->start = start; -} - -static DEFINE_SPINLOCK(hose_spinlock); - -/* - * pci_controller(phb) initialized common variables. - */ -void __devinit pci_setup_pci_controller(struct pci_controller *hose) -{ - memset(hose, 0, sizeof(struct pci_controller)); - - spin_lock(&hose_spinlock); - hose->global_number = global_phb_number++; - list_add_tail(&hose->list_node, &hose_list); - spin_unlock(&hose_spinlock); -} - -static void __init pcibios_claim_one_bus(struct pci_bus *b) -{ - struct pci_dev *dev; - struct pci_bus *child_bus; - - list_for_each_entry(dev, &b->devices, bus_list) { - int i; - - for (i = 0; i < PCI_NUM_RESOURCES; i++) { - struct resource *r = &dev->resource[i]; - - if (r->parent || !r->start || !r->flags) - continue; - pci_claim_resource(dev, i); - } - } - - list_for_each_entry(child_bus, &b->children, node) - pcibios_claim_one_bus(child_bus); -} - -#ifndef CONFIG_PPC_ISERIES -static void __init pcibios_claim_of_setup(void) -{ - struct pci_bus *b; - - list_for_each_entry(b, &pci_root_buses, node) - pcibios_claim_one_bus(b); -} -#endif - -#ifdef CONFIG_PPC_MULTIPLATFORM -static u32 get_int_prop(struct device_node *np, const char *name, u32 def) -{ - u32 *prop; - int len; - - prop = (u32 *) get_property(np, name, &len); - if (prop && len >= 4) - return *prop; - return def; -} - -static unsigned int pci_parse_of_flags(u32 addr0) -{ - unsigned int flags = 0; - - if (addr0 & 0x02000000) { - flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; - flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; - flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; - if (addr0 & 0x40000000) - flags |= IORESOURCE_PREFETCH - | PCI_BASE_ADDRESS_MEM_PREFETCH; - } else if (addr0 & 0x01000000) - flags = IORESOURCE_IO | PCI_BASE_ADDRESS_SPACE_IO; - return flags; -} - -#define GET_64BIT(prop, i) ((((u64) (prop)[(i)]) << 32) | (prop)[(i)+1]) - -static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) -{ - u64 base, size; - unsigned int flags; - struct resource *res; - u32 *addrs, i; - int proplen; - - addrs = (u32 *) get_property(node, "assigned-addresses", &proplen); - if (!addrs) - return; - for (; proplen >= 20; proplen -= 20, addrs += 5) { - flags = pci_parse_of_flags(addrs[0]); - if (!flags) - continue; - base = GET_64BIT(addrs, 1); - size = GET_64BIT(addrs, 3); - if (!size) - continue; - i = addrs[0] & 0xff; - if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) { - res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; - } else if (i == dev->rom_base_reg) { - res = &dev->resource[PCI_ROM_RESOURCE]; - flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE; - } else { - printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i); - continue; - } - res->start = base; - res->end = base + size - 1; - res->flags = flags; - res->name = pci_name(dev); - fixup_resource(res, dev); - } -} - -struct pci_dev *of_create_pci_dev(struct device_node *node, - struct pci_bus *bus, int devfn) -{ - struct pci_dev *dev; - const char *type; - - dev = kmalloc(sizeof(struct pci_dev), GFP_KERNEL); - if (!dev) - return NULL; - type = get_property(node, "device_type", NULL); - if (type == NULL) - type = ""; - - memset(dev, 0, sizeof(struct pci_dev)); - dev->bus = bus; - dev->sysdata = node; - dev->dev.parent = bus->bridge; - dev->dev.bus = &pci_bus_type; - dev->devfn = devfn; - dev->multifunction = 0; /* maybe a lie? */ - - dev->vendor = get_int_prop(node, "vendor-id", 0xffff); - dev->device = get_int_prop(node, "device-id", 0xffff); - dev->subsystem_vendor = get_int_prop(node, "subsystem-vendor-id", 0); - dev->subsystem_device = get_int_prop(node, "subsystem-id", 0); - - dev->cfg_size = 256; /*pci_cfg_space_size(dev);*/ - - sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), - dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); - dev->class = get_int_prop(node, "class-code", 0); - - dev->current_state = 4; /* unknown power state */ - - if (!strcmp(type, "pci")) { - /* a PCI-PCI bridge */ - dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; - dev->rom_base_reg = PCI_ROM_ADDRESS1; - } else if (!strcmp(type, "cardbus")) { - dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; - } else { - dev->hdr_type = PCI_HEADER_TYPE_NORMAL; - dev->rom_base_reg = PCI_ROM_ADDRESS; - dev->irq = NO_IRQ; - if (node->n_intrs > 0) { - dev->irq = node->intrs[0].line; - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, - dev->irq); - } - } - - pci_parse_of_addrs(node, dev); - - pci_device_add(dev, bus); - - /* XXX pci_scan_msi_device(dev); */ - - return dev; -} -EXPORT_SYMBOL(of_create_pci_dev); - -void __devinit of_scan_bus(struct device_node *node, - struct pci_bus *bus) -{ - struct device_node *child = NULL; - u32 *reg; - int reglen, devfn; - struct pci_dev *dev; - - while ((child = of_get_next_child(node, child)) != NULL) { - reg = (u32 *) get_property(child, "reg", ®len); - if (reg == NULL || reglen < 20) - continue; - devfn = (reg[0] >> 8) & 0xff; - /* create a new pci_dev for this device */ - dev = of_create_pci_dev(child, bus, devfn); - if (!dev) - continue; - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) - of_scan_pci_bridge(child, dev); - } - - do_bus_setup(bus); -} -EXPORT_SYMBOL(of_scan_bus); - -void __devinit of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev) -{ - struct pci_bus *bus; - u32 *busrange, *ranges; - int len, i, mode; - struct resource *res; - unsigned int flags; - u64 size; - - /* parse bus-range property */ - busrange = (u32 *) get_property(node, "bus-range", &len); - if (busrange == NULL || len != 8) { - printk(KERN_ERR "Can't get bus-range for PCI-PCI bridge %s\n", - node->full_name); - return; - } - ranges = (u32 *) get_property(node, "ranges", &len); - if (ranges == NULL) { - printk(KERN_ERR "Can't get ranges for PCI-PCI bridge %s\n", - node->full_name); - return; - } - - bus = pci_add_new_bus(dev->bus, dev, busrange[0]); - if (!bus) { - printk(KERN_ERR "Failed to create pci bus for %s\n", - node->full_name); - return; - } - - bus->primary = dev->bus->number; - bus->subordinate = busrange[1]; - bus->bridge_ctl = 0; - bus->sysdata = node; - - /* parse ranges property */ - /* PCI #address-cells == 3 and #size-cells == 2 always */ - res = &dev->resource[PCI_BRIDGE_RESOURCES]; - for (i = 0; i < PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES; ++i) { - res->flags = 0; - bus->resource[i] = res; - ++res; - } - i = 1; - for (; len >= 32; len -= 32, ranges += 8) { - flags = pci_parse_of_flags(ranges[0]); - size = GET_64BIT(ranges, 6); - if (flags == 0 || size == 0) - continue; - if (flags & IORESOURCE_IO) { - res = bus->resource[0]; - if (res->flags) { - printk(KERN_ERR "PCI: ignoring extra I/O range" - " for bridge %s\n", node->full_name); - continue; - } - } else { - if (i >= PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES) { - printk(KERN_ERR "PCI: too many memory ranges" - " for bridge %s\n", node->full_name); - continue; - } - res = bus->resource[i]; - ++i; - } - res->start = GET_64BIT(ranges, 1); - res->end = res->start + size - 1; - res->flags = flags; - fixup_resource(res, dev); - } - sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus), - bus->number); - - mode = PCI_PROBE_NORMAL; - if (ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); - if (mode == PCI_PROBE_DEVTREE) - of_scan_bus(node, bus); - else if (mode == PCI_PROBE_NORMAL) - pci_scan_child_bus(bus); -} -EXPORT_SYMBOL(of_scan_pci_bridge); -#endif /* CONFIG_PPC_MULTIPLATFORM */ - -void __devinit scan_phb(struct pci_controller *hose) -{ - struct pci_bus *bus; - struct device_node *node = hose->arch_data; - int i, mode; - struct resource *res; - - bus = pci_create_bus(NULL, hose->first_busno, hose->ops, node); - if (bus == NULL) { - printk(KERN_ERR "Failed to create bus for PCI domain %04x\n", - hose->global_number); - return; - } - bus->secondary = hose->first_busno; - hose->bus = bus; - - bus->resource[0] = res = &hose->io_resource; - if (res->flags && request_resource(&ioport_resource, res)) - printk(KERN_ERR "Failed to request PCI IO region " - "on PCI domain %04x\n", hose->global_number); - - for (i = 0; i < 3; ++i) { - res = &hose->mem_resources[i]; - bus->resource[i+1] = res; - if (res->flags && request_resource(&iomem_resource, res)) - printk(KERN_ERR "Failed to request PCI memory region " - "on PCI domain %04x\n", hose->global_number); - } - - mode = PCI_PROBE_NORMAL; -#ifdef CONFIG_PPC_MULTIPLATFORM - if (ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); - if (mode == PCI_PROBE_DEVTREE) { - bus->subordinate = hose->last_busno; - of_scan_bus(node, bus); - } -#endif /* CONFIG_PPC_MULTIPLATFORM */ - if (mode == PCI_PROBE_NORMAL) - hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); - pci_bus_add_devices(bus); -} - -static int __init pcibios_init(void) -{ - struct pci_controller *hose, *tmp; - - /* For now, override phys_mem_access_prot. If we need it, - * later, we may move that initialization to each ppc_md - */ - ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot; - -#ifdef CONFIG_PPC_ISERIES - iSeries_pcibios_init(); -#endif - - printk("PCI: Probing PCI hardware\n"); - - /* Scan all of the recorded PCI controllers. */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - scan_phb(hose); - -#ifndef CONFIG_PPC_ISERIES - if (pci_probe_only) - pcibios_claim_of_setup(); - else - /* FIXME: `else' will be removed when - pci_assign_unassigned_resources() is able to work - correctly with [partially] allocated PCI tree. */ - pci_assign_unassigned_resources(); -#endif /* !CONFIG_PPC_ISERIES */ - - /* Call machine dependent final fixup */ - if (ppc_md.pcibios_fixup) - ppc_md.pcibios_fixup(); - - /* Cache the location of the ISA bridge (if we have one) */ - ppc64_isabridge_dev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); - if (ppc64_isabridge_dev != NULL) - printk("ISA bridge at %s\n", pci_name(ppc64_isabridge_dev)); - -#ifdef CONFIG_PPC_MULTIPLATFORM - /* map in PCI I/O space */ - phbs_remap_io(); -#endif - - printk("PCI: Probing PCI hardware done\n"); - - return 0; -} - -subsys_initcall(pcibios_init); - -char __init *pcibios_setup(char *str) -{ - return str; -} - -int pcibios_enable_device(struct pci_dev *dev, int mask) -{ - u16 cmd, oldcmd; - int i; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - oldcmd = cmd; - - for (i = 0; i < PCI_NUM_RESOURCES; i++) { - struct resource *res = &dev->resource[i]; - - /* Only set up the requested stuff */ - if (!(mask & (1<flags & IORESOURCE_IO) - cmd |= PCI_COMMAND_IO; - if (res->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; - } - - if (cmd != oldcmd) { - printk(KERN_DEBUG "PCI: Enabling device: (%s), cmd %x\n", - pci_name(dev), cmd); - /* Enable the appropriate bits in the PCI command register. */ - pci_write_config_word(dev, PCI_COMMAND, cmd); - } - return 0; -} - -/* - * Return the domain number for this bus. - */ -int pci_domain_nr(struct pci_bus *bus) -{ -#ifdef CONFIG_PPC_ISERIES - return 0; -#else - struct pci_controller *hose = pci_bus_to_host(bus); - - return hose->global_number; -#endif -} - -EXPORT_SYMBOL(pci_domain_nr); - -/* Decide whether to display the domain number in /proc */ -int pci_proc_domain(struct pci_bus *bus) -{ -#ifdef CONFIG_PPC_ISERIES - return 0; -#else - struct pci_controller *hose = pci_bus_to_host(bus); - return hose->buid; -#endif -} - -/* - * Platform support for /proc/bus/pci/X/Y mmap()s, - * modelled on the sparc64 implementation by Dave Miller. - * -- paulus. - */ - -/* - * Adjust vm_pgoff of VMA such that it is the physical page offset - * corresponding to the 32-bit pci bus offset for DEV requested by the user. - * - * Basically, the user finds the base address for his device which he wishes - * to mmap. They read the 32-bit value from the config space base register, - * add whatever PAGE_SIZE multiple offset they wish, and feed this into the - * offset parameter of mmap on /proc/bus/pci/XXX for that device. - * - * Returns negative error code on failure, zero on success. - */ -static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - unsigned long *offset, - enum pci_mmap_state mmap_state) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long io_offset = 0; - int i, res_bit; - - if (hose == 0) - return NULL; /* should never happen */ - - /* If memory, add on the PCI bridge address offset */ - if (mmap_state == pci_mmap_mem) { - *offset += hose->pci_mem_offset; - res_bit = IORESOURCE_MEM; - } else { - io_offset = (unsigned long)hose->io_base_virt - pci_io_base; - *offset += io_offset; - res_bit = IORESOURCE_IO; - } - - /* - * Check that the offset requested corresponds to one of the - * resources of the device. - */ - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &dev->resource[i]; - int flags = rp->flags; - - /* treat ROM as memory (should be already) */ - if (i == PCI_ROM_RESOURCE) - flags |= IORESOURCE_MEM; - - /* Active and same type? */ - if ((flags & res_bit) == 0) - continue; - - /* In the range of this resource? */ - if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) - continue; - - /* found it! construct the final physical address */ - if (mmap_state == pci_mmap_io) - *offset += hose->io_base_phys - io_offset; - return rp; - } - - return NULL; -} - -/* - * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci - * device mapping. - */ -static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, - pgprot_t protection, - enum pci_mmap_state mmap_state, - int write_combine) -{ - unsigned long prot = pgprot_val(protection); - - /* Write combine is always 0 on non-memory space mappings. On - * memory space, if the user didn't pass 1, we check for a - * "prefetchable" resource. This is a bit hackish, but we use - * this to workaround the inability of /sysfs to provide a write - * combine bit - */ - if (mmap_state != pci_mmap_mem) - write_combine = 0; - else if (write_combine == 0) { - if (rp->flags & IORESOURCE_PREFETCH) - write_combine = 1; - } - - /* XXX would be nice to have a way to ask for write-through */ - prot |= _PAGE_NO_CACHE; - if (write_combine) - prot &= ~_PAGE_GUARDED; - else - prot |= _PAGE_GUARDED; - - printk("PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, - prot); - - return __pgprot(prot); -} - -/* - * This one is used by /dev/mem and fbdev who have no clue about the - * PCI device, it tries to find the PCI device first and calls the - * above routine - */ -pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, - unsigned long size, - pgprot_t protection) -{ - struct pci_dev *pdev = NULL; - struct resource *found = NULL; - unsigned long prot = pgprot_val(protection); - unsigned long offset = pfn << PAGE_SHIFT; - int i; - - if (page_is_ram(pfn)) - return __pgprot(prot); - - prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; - - for_each_pci_dev(pdev) { - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &pdev->resource[i]; - int flags = rp->flags; - - /* Active and same type? */ - if ((flags & IORESOURCE_MEM) == 0) - continue; - /* In the range of this resource? */ - if (offset < (rp->start & PAGE_MASK) || - offset > rp->end) - continue; - found = rp; - break; - } - if (found) - break; - } - if (found) { - if (found->flags & IORESOURCE_PREFETCH) - prot &= ~_PAGE_GUARDED; - pci_dev_put(pdev); - } - - DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); - - return __pgprot(prot); -} - - -/* - * Perform the actual remap of the pages for a PCI device mapping, as - * appropriate for this architecture. The region in the process to map - * is described by vm_start and vm_end members of VMA, the base physical - * address is found in vm_pgoff. - * The pci device structure is provided so that architectures may make mapping - * decisions on a per-device or per-bus basis. - * - * Returns a negative error code on failure, zero on success. - */ -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, - int write_combine) -{ - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; - struct resource *rp; - int ret; - - rp = __pci_mmap_make_offset(dev, &offset, mmap_state); - if (rp == NULL) - return -EINVAL; - - vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; - vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, - vma->vm_page_prot, - mmap_state, write_combine); - - ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, vma->vm_page_prot); - - return ret; -} - -#ifdef CONFIG_PPC_MULTIPLATFORM -static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev; - struct device_node *np; - - pdev = to_pci_dev (dev); - np = pci_device_to_OF_node(pdev); - if (np == NULL || np->full_name == NULL) - return 0; - return sprintf(buf, "%s", np->full_name); -} -static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); -#endif /* CONFIG_PPC_MULTIPLATFORM */ - -void pcibios_add_platform_entries(struct pci_dev *pdev) -{ -#ifdef CONFIG_PPC_MULTIPLATFORM - device_create_file(&pdev->dev, &dev_attr_devspec); -#endif /* CONFIG_PPC_MULTIPLATFORM */ -} - -#ifdef CONFIG_PPC_MULTIPLATFORM - -#define ISA_SPACE_MASK 0x1 -#define ISA_SPACE_IO 0x1 - -static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, - unsigned long phb_io_base_phys, - void __iomem * phb_io_base_virt) -{ - struct isa_range *range; - unsigned long pci_addr; - unsigned int isa_addr; - unsigned int size; - int rlen = 0; - - range = (struct isa_range *) get_property(isa_node, "ranges", &rlen); - if (range == NULL || (rlen < sizeof(struct isa_range))) { - printk(KERN_ERR "no ISA ranges or unexpected isa range size," - "mapping 64k\n"); - __ioremap_explicit(phb_io_base_phys, - (unsigned long)phb_io_base_virt, - 0x10000, _PAGE_NO_CACHE | _PAGE_GUARDED); - return; - } - - /* From "ISA Binding to 1275" - * The ranges property is laid out as an array of elements, - * each of which comprises: - * cells 0 - 1: an ISA address - * cells 2 - 4: a PCI address - * (size depending on dev->n_addr_cells) - * cell 5: the size of the range - */ - if ((range->isa_addr.a_hi && ISA_SPACE_MASK) == ISA_SPACE_IO) { - isa_addr = range->isa_addr.a_lo; - pci_addr = (unsigned long) range->pci_addr.a_mid << 32 | - range->pci_addr.a_lo; - - /* Assume these are both zero */ - if ((pci_addr != 0) || (isa_addr != 0)) { - printk(KERN_ERR "unexpected isa to pci mapping: %s\n", - __FUNCTION__); - return; - } - - size = PAGE_ALIGN(range->size); - - __ioremap_explicit(phb_io_base_phys, - (unsigned long) phb_io_base_virt, - size, _PAGE_NO_CACHE | _PAGE_GUARDED); - } -} - -void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, - struct device_node *dev, int prim) -{ - unsigned int *ranges, pci_space; - unsigned long size; - int rlen = 0; - int memno = 0; - struct resource *res; - int np, na = prom_n_addr_cells(dev); - unsigned long pci_addr, cpu_phys_addr; - - np = na + 5; - - /* From "PCI Binding to 1275" - * The ranges property is laid out as an array of elements, - * each of which comprises: - * cells 0 - 2: a PCI address - * cells 3 or 3+4: a CPU physical address - * (size depending on dev->n_addr_cells) - * cells 4+5 or 5+6: the size of the range - */ - rlen = 0; - hose->io_base_phys = 0; - ranges = (unsigned int *) get_property(dev, "ranges", &rlen); - while ((rlen -= np * sizeof(unsigned int)) >= 0) { - res = NULL; - pci_space = ranges[0]; - pci_addr = ((unsigned long)ranges[1] << 32) | ranges[2]; - - cpu_phys_addr = ranges[3]; - if (na >= 2) - cpu_phys_addr = (cpu_phys_addr << 32) | ranges[4]; - - size = ((unsigned long)ranges[na+3] << 32) | ranges[na+4]; - ranges += np; - if (size == 0) - continue; - - /* Now consume following elements while they are contiguous */ - while (rlen >= np * sizeof(unsigned int)) { - unsigned long addr, phys; - - if (ranges[0] != pci_space) - break; - addr = ((unsigned long)ranges[1] << 32) | ranges[2]; - phys = ranges[3]; - if (na >= 2) - phys = (phys << 32) | ranges[4]; - if (addr != pci_addr + size || - phys != cpu_phys_addr + size) - break; - - size += ((unsigned long)ranges[na+3] << 32) - | ranges[na+4]; - ranges += np; - rlen -= np * sizeof(unsigned int); - } - - switch ((pci_space >> 24) & 0x3) { - case 1: /* I/O space */ - hose->io_base_phys = cpu_phys_addr; - hose->pci_io_size = size; - - res = &hose->io_resource; - res->flags = IORESOURCE_IO; - res->start = pci_addr; - DBG("phb%d: IO 0x%lx -> 0x%lx\n", hose->global_number, - res->start, res->start + size - 1); - break; - case 2: /* memory space */ - memno = 0; - while (memno < 3 && hose->mem_resources[memno].flags) - ++memno; - - if (memno == 0) - hose->pci_mem_offset = cpu_phys_addr - pci_addr; - if (memno < 3) { - res = &hose->mem_resources[memno]; - res->flags = IORESOURCE_MEM; - res->start = cpu_phys_addr; - DBG("phb%d: MEM 0x%lx -> 0x%lx\n", hose->global_number, - res->start, res->start + size - 1); - } - break; - } - if (res != NULL) { - res->name = dev->full_name; - res->end = res->start + size - 1; - res->parent = NULL; - res->sibling = NULL; - res->child = NULL; - } - } -} - -void __init pci_setup_phb_io(struct pci_controller *hose, int primary) -{ - unsigned long size = hose->pci_io_size; - unsigned long io_virt_offset; - struct resource *res; - struct device_node *isa_dn; - - hose->io_base_virt = reserve_phb_iospace(size); - DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", - hose->global_number, hose->io_base_phys, - (unsigned long) hose->io_base_virt); - - if (primary) { - pci_io_base = (unsigned long)hose->io_base_virt; - isa_dn = of_find_node_by_type(NULL, "isa"); - if (isa_dn) { - isa_io_base = pci_io_base; - pci_process_ISA_OF_ranges(isa_dn, hose->io_base_phys, - hose->io_base_virt); - of_node_put(isa_dn); - /* Allow all IO */ - io_page_mask = -1; - } - } - - io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; - res = &hose->io_resource; - res->start += io_virt_offset; - res->end += io_virt_offset; -} - -void __devinit pci_setup_phb_io_dynamic(struct pci_controller *hose, - int primary) -{ - unsigned long size = hose->pci_io_size; - unsigned long io_virt_offset; - struct resource *res; - - hose->io_base_virt = __ioremap(hose->io_base_phys, size, - _PAGE_NO_CACHE | _PAGE_GUARDED); - DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", - hose->global_number, hose->io_base_phys, - (unsigned long) hose->io_base_virt); - - if (primary) - pci_io_base = (unsigned long)hose->io_base_virt; - - io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; - res = &hose->io_resource; - res->start += io_virt_offset; - res->end += io_virt_offset; -} - - -static int get_bus_io_range(struct pci_bus *bus, unsigned long *start_phys, - unsigned long *start_virt, unsigned long *size) -{ - struct pci_controller *hose = pci_bus_to_host(bus); - struct pci_bus_region region; - struct resource *res; - - if (bus->self) { - res = bus->resource[0]; - pcibios_resource_to_bus(bus->self, ®ion, res); - *start_phys = hose->io_base_phys + region.start; - *start_virt = (unsigned long) hose->io_base_virt + - region.start; - if (region.end > region.start) - *size = region.end - region.start + 1; - else { - printk("%s(): unexpected region 0x%lx->0x%lx\n", - __FUNCTION__, region.start, region.end); - return 1; - } - - } else { - /* Root Bus */ - res = &hose->io_resource; - *start_phys = hose->io_base_phys; - *start_virt = (unsigned long) hose->io_base_virt; - if (res->end > res->start) - *size = res->end - res->start + 1; - else { - printk("%s(): unexpected region 0x%lx->0x%lx\n", - __FUNCTION__, res->start, res->end); - return 1; - } - } - - return 0; -} - -int unmap_bus_range(struct pci_bus *bus) -{ - unsigned long start_phys; - unsigned long start_virt; - unsigned long size; - - if (!bus) { - printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); - return 1; - } - - if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) - return 1; - if (iounmap_explicit((void __iomem *) start_virt, size)) - return 1; - - return 0; -} -EXPORT_SYMBOL(unmap_bus_range); - -int remap_bus_range(struct pci_bus *bus) -{ - unsigned long start_phys; - unsigned long start_virt; - unsigned long size; - - if (!bus) { - printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); - return 1; - } - - - if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) - return 1; - printk("mapping IO %lx -> %lx, size: %lx\n", start_phys, start_virt, size); - if (__ioremap_explicit(start_phys, start_virt, size, - _PAGE_NO_CACHE | _PAGE_GUARDED)) - return 1; - - return 0; -} -EXPORT_SYMBOL(remap_bus_range); - -void phbs_remap_io(void) -{ - struct pci_controller *hose, *tmp; - - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - remap_bus_range(hose->bus); -} - -/* - * ppc64 can have multifunction devices that do not respond to function 0. - * In this case we must scan all functions. - * XXX this can go now, we use the OF device tree in all the - * cases that caused problems. -- paulus - */ -int pcibios_scan_all_fns(struct pci_bus *bus, int devfn) -{ - return 0; -} - -static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long start, end, mask, offset; - - if (res->flags & IORESOURCE_IO) { - offset = (unsigned long)hose->io_base_virt - pci_io_base; - - start = res->start += offset; - end = res->end += offset; - - /* Need to allow IO access to pages that are in the - ISA range */ - if (start < MAX_ISA_PORT) { - if (end > MAX_ISA_PORT) - end = MAX_ISA_PORT; - - start >>= PAGE_SHIFT; - end >>= PAGE_SHIFT; - - /* get the range of pages for the map */ - mask = ((1 << (end+1)) - 1) ^ ((1 << start) - 1); - io_page_mask |= mask; - } - } else if (res->flags & IORESOURCE_MEM) { - res->start += hose->pci_mem_offset; - res->end += hose->pci_mem_offset; - } -} - -void __devinit pcibios_fixup_device_resources(struct pci_dev *dev, - struct pci_bus *bus) -{ - /* Update device resources. */ - int i; - - for (i = 0; i < PCI_NUM_RESOURCES; i++) - if (dev->resource[i].flags) - fixup_resource(&dev->resource[i], dev); -} -EXPORT_SYMBOL(pcibios_fixup_device_resources); - -static void __devinit do_bus_setup(struct pci_bus *bus) -{ - struct pci_dev *dev; - - ppc_md.iommu_bus_setup(bus); - - list_for_each_entry(dev, &bus->devices, bus_list) - ppc_md.iommu_dev_setup(dev); - - if (ppc_md.irq_bus_setup) - ppc_md.irq_bus_setup(bus); -} - -void __devinit pcibios_fixup_bus(struct pci_bus *bus) -{ - struct pci_dev *dev = bus->self; - - if (dev && pci_probe_only && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - /* This is a subordinate bridge */ - - pci_read_bridge_bases(bus); - pcibios_fixup_device_resources(dev, bus); - } - - do_bus_setup(bus); - - if (!pci_probe_only) - return; - - list_for_each_entry(dev, &bus->devices, bus_list) - if ((dev->class >> 8) != PCI_CLASS_BRIDGE_PCI) - pcibios_fixup_device_resources(dev, bus); -} -EXPORT_SYMBOL(pcibios_fixup_bus); - -/* - * Reads the interrupt pin to determine if interrupt is use by card. - * If the interrupt is used, then gets the interrupt line from the - * openfirmware and sets it in the pci_dev and pci_config line. - */ -int pci_read_irq_line(struct pci_dev *pci_dev) -{ - u8 intpin; - struct device_node *node; - - pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &intpin); - if (intpin == 0) - return 0; - - node = pci_device_to_OF_node(pci_dev); - if (node == NULL) - return -1; - - if (node->n_intrs == 0) - return -1; - - pci_dev->irq = node->intrs[0].line; - - pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, pci_dev->irq); - - return 0; -} -EXPORT_SYMBOL(pci_read_irq_line); - -void pci_resource_to_user(const struct pci_dev *dev, int bar, - const struct resource *rsrc, - u64 *start, u64 *end) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long offset = 0; - - if (hose == NULL) - return; - - if (rsrc->flags & IORESOURCE_IO) - offset = pci_io_base - (unsigned long)hose->io_base_virt + - hose->io_base_phys; - - *start = rsrc->start + offset; - *end = rsrc->end + offset; -} - -#endif /* CONFIG_PPC_MULTIPLATFORM */ - - -#define IOBASE_BRIDGE_NUMBER 0 -#define IOBASE_MEMORY 1 -#define IOBASE_IO 2 -#define IOBASE_ISA_IO 3 -#define IOBASE_ISA_MEM 4 - -long sys_pciconfig_iobase(long which, unsigned long in_bus, - unsigned long in_devfn) -{ - struct pci_controller* hose; - struct list_head *ln; - struct pci_bus *bus = NULL; - struct device_node *hose_node; - - /* Argh ! Please forgive me for that hack, but that's the - * simplest way to get existing XFree to not lockup on some - * G5 machines... So when something asks for bus 0 io base - * (bus 0 is HT root), we return the AGP one instead. - */ - if (machine_is_compatible("MacRISC4")) - if (in_bus == 0) - in_bus = 0xf0; - - /* That syscall isn't quite compatible with PCI domains, but it's - * used on pre-domains setup. We return the first match - */ - - for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) { - bus = pci_bus_b(ln); - if (in_bus >= bus->number && in_bus < (bus->number + bus->subordinate)) - break; - bus = NULL; - } - if (bus == NULL || bus->sysdata == NULL) - return -ENODEV; - - hose_node = (struct device_node *)bus->sysdata; - hose = PCI_DN(hose_node)->phb; - - switch (which) { - case IOBASE_BRIDGE_NUMBER: - return (long)hose->first_busno; - case IOBASE_MEMORY: - return (long)hose->pci_mem_offset; - case IOBASE_IO: - return (long)hose->io_base_phys; - case IOBASE_ISA_IO: - return (long)isa_io_base; - case IOBASE_ISA_MEM: - return -EINVAL; - } - - return -EOPNOTSUPP; -} diff --git a/arch/ppc64/kernel/pci_direct_iommu.c b/arch/ppc64/kernel/pci_direct_iommu.c deleted file mode 100644 index e1a32f802c0b..000000000000 --- a/arch/ppc64/kernel/pci_direct_iommu.c +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Support for DMA from PCI devices to main memory on - * machines without an iommu or with directly addressable - * RAM (typically a pmac with 2Gb of RAM or less) - * - * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include - -static void *pci_direct_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - void *ret; - - ret = (void *)__get_free_pages(flag, get_order(size)); - if (ret != NULL) { - memset(ret, 0, size); - *dma_handle = virt_to_abs(ret); - } - return ret; -} - -static void pci_direct_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} - -static dma_addr_t pci_direct_map_single(struct device *hwdev, void *ptr, - size_t size, enum dma_data_direction direction) -{ - return virt_to_abs(ptr); -} - -static void pci_direct_unmap_single(struct device *hwdev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static int pci_direct_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction direction) -{ - int i; - - for (i = 0; i < nents; i++, sg++) { - sg->dma_address = page_to_phys(sg->page) + sg->offset; - sg->dma_length = sg->length; - } - - return nents; -} - -static void pci_direct_unmap_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction direction) -{ -} - -static int pci_direct_dma_supported(struct device *dev, u64 mask) -{ - return mask < 0x100000000ull; -} - -void __init pci_direct_iommu_init(void) -{ - pci_dma_ops.alloc_coherent = pci_direct_alloc_coherent; - pci_dma_ops.free_coherent = pci_direct_free_coherent; - pci_dma_ops.map_single = pci_direct_map_single; - pci_dma_ops.unmap_single = pci_direct_unmap_single; - pci_dma_ops.map_sg = pci_direct_map_sg; - pci_dma_ops.unmap_sg = pci_direct_unmap_sg; - pci_dma_ops.dma_supported = pci_direct_dma_supported; -} diff --git a/arch/ppc64/kernel/pci_dn.c b/arch/ppc64/kernel/pci_dn.c deleted file mode 100644 index 12c4c9e9bbc7..000000000000 --- a/arch/ppc64/kernel/pci_dn.c +++ /dev/null @@ -1,230 +0,0 @@ -/* - * pci_dn.c - * - * Copyright (C) 2001 Todd Inglett, IBM Corporation - * - * PCI manipulation via device_nodes. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -/* - * Traverse_func that inits the PCI fields of the device node. - * NOTE: this *must* be done before read/write config to the device. - */ -static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) -{ - struct pci_controller *phb = data; - int *type = (int *)get_property(dn, "ibm,pci-config-space-type", NULL); - u32 *regs; - struct pci_dn *pdn; - - if (mem_init_done) - pdn = kmalloc(sizeof(*pdn), GFP_KERNEL); - else - pdn = alloc_bootmem(sizeof(*pdn)); - if (pdn == NULL) - return NULL; - memset(pdn, 0, sizeof(*pdn)); - dn->data = pdn; - pdn->node = dn; - pdn->phb = phb; - regs = (u32 *)get_property(dn, "reg", NULL); - if (regs) { - /* First register entry is addr (00BBSS00) */ - pdn->busno = (regs[0] >> 16) & 0xff; - pdn->devfn = (regs[0] >> 8) & 0xff; - } - - pdn->pci_ext_config_space = (type && *type == 1); - return NULL; -} - -/* - * Traverse a device tree stopping each PCI device in the tree. - * This is done depth first. As each node is processed, a "pre" - * function is called and the children are processed recursively. - * - * The "pre" func returns a value. If non-zero is returned from - * the "pre" func, the traversal stops and this value is returned. - * This return value is useful when using traverse as a method of - * finding a device. - * - * NOTE: we do not run the func for devices that do not appear to - * be PCI except for the start node which we assume (this is good - * because the start node is often a phb which may be missing PCI - * properties). - * We use the class-code as an indicator. If we run into - * one of these nodes we also assume its siblings are non-pci for - * performance. - */ -void *traverse_pci_devices(struct device_node *start, traverse_func pre, - void *data) -{ - struct device_node *dn, *nextdn; - void *ret; - - /* We started with a phb, iterate all childs */ - for (dn = start->child; dn; dn = nextdn) { - u32 *classp, class; - - nextdn = NULL; - classp = (u32 *)get_property(dn, "class-code", NULL); - class = classp ? *classp : 0; - - if (pre && ((ret = pre(dn, data)) != NULL)) - return ret; - - /* If we are a PCI bridge, go down */ - if (dn->child && ((class >> 8) == PCI_CLASS_BRIDGE_PCI || - (class >> 8) == PCI_CLASS_BRIDGE_CARDBUS)) - /* Depth first...do children */ - nextdn = dn->child; - else if (dn->sibling) - /* ok, try next sibling instead. */ - nextdn = dn->sibling; - if (!nextdn) { - /* Walk up to next valid sibling. */ - do { - dn = dn->parent; - if (dn == start) - return NULL; - } while (dn->sibling == NULL); - nextdn = dn->sibling; - } - } - return NULL; -} - -/** - * pci_devs_phb_init_dynamic - setup pci devices under this PHB - * phb: pci-to-host bridge (top-level bridge connecting to cpu) - * - * This routine is called both during boot, (before the memory - * subsystem is set up, before kmalloc is valid) and during the - * dynamic lpar operation of adding a PHB to a running system. - */ -void __devinit pci_devs_phb_init_dynamic(struct pci_controller *phb) -{ - struct device_node * dn = (struct device_node *) phb->arch_data; - struct pci_dn *pdn; - - /* PHB nodes themselves must not match */ - update_dn_pci_info(dn, phb); - pdn = dn->data; - if (pdn) { - pdn->devfn = pdn->busno = -1; - pdn->phb = phb; - } - - /* Update dn->phb ptrs for new phb and children devices */ - traverse_pci_devices(dn, update_dn_pci_info, phb); -} - -/* - * Traversal func that looks for a value. - * If found, the pci_dn is returned (thus terminating the traversal). - */ -static void *is_devfn_node(struct device_node *dn, void *data) -{ - int busno = ((unsigned long)data >> 8) & 0xff; - int devfn = ((unsigned long)data) & 0xff; - struct pci_dn *pci = dn->data; - - if (pci && (devfn == pci->devfn) && (busno == pci->busno)) - return dn; - return NULL; -} - -/* - * This is the "slow" path for looking up a device_node from a - * pci_dev. It will hunt for the device under its parent's - * phb and then update sysdata for a future fastpath. - * - * It may also do fixups on the actual device since this happens - * on the first read/write. - * - * Note that it also must deal with devices that don't exist. - * In this case it may probe for real hardware ("just in case") - * and add a device_node to the device tree if necessary. - * - */ -struct device_node *fetch_dev_dn(struct pci_dev *dev) -{ - struct device_node *orig_dn = dev->sysdata; - struct device_node *dn; - unsigned long searchval = (dev->bus->number << 8) | dev->devfn; - - dn = traverse_pci_devices(orig_dn, is_devfn_node, (void *)searchval); - if (dn) - dev->sysdata = dn; - return dn; -} -EXPORT_SYMBOL(fetch_dev_dn); - -static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node) -{ - struct device_node *np = node; - struct pci_dn *pci = NULL; - int err = NOTIFY_OK; - - switch (action) { - case PSERIES_RECONFIG_ADD: - pci = np->parent->data; - if (pci) - update_dn_pci_info(np, pci->phb); - break; - default: - err = NOTIFY_DONE; - break; - } - return err; -} - -static struct notifier_block pci_dn_reconfig_nb = { - .notifier_call = pci_dn_reconfig_notifier, -}; - -/** - * pci_devs_phb_init - Initialize phbs and pci devs under them. - * - * This routine walks over all phb's (pci-host bridges) on the - * system, and sets up assorted pci-related structures - * (including pci info in the device node structs) for each - * pci device found underneath. This routine runs once, - * early in the boot sequence. - */ -void __init pci_devs_phb_init(void) -{ - struct pci_controller *phb, *tmp; - - /* This must be done first so the device nodes have valid pci info! */ - list_for_each_entry_safe(phb, tmp, &hose_list, list_node) - pci_devs_phb_init_dynamic(phb); - - pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb); -} diff --git a/arch/ppc64/kernel/pci_iommu.c b/arch/ppc64/kernel/pci_iommu.c deleted file mode 100644 index bdf15dbbf4f0..000000000000 --- a/arch/ppc64/kernel/pci_iommu.c +++ /dev/null @@ -1,128 +0,0 @@ -/* - * arch/ppc64/kernel/pci_iommu.c - * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation - * - * Rewrite, cleanup, new allocation schemes: - * Copyright (C) 2004 Olof Johansson, IBM Corporation - * - * Dynamic DMA mapping support, platform-independent parts. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * We can use ->sysdata directly and avoid the extra work in - * pci_device_to_OF_node since ->sysdata will have been initialised - * in the iommu init code for all devices. - */ -#define PCI_GET_DN(dev) ((struct device_node *)((dev)->sysdata)) - -static inline struct iommu_table *devnode_table(struct device *dev) -{ - struct pci_dev *pdev; - - if (!dev) { - pdev = ppc64_isabridge_dev; - if (!pdev) - return NULL; - } else - pdev = to_pci_dev(dev); - - return PCI_DN(PCI_GET_DN(pdev))->iommu_table; -} - - -/* Allocates a contiguous real buffer and creates mappings over it. - * Returns the virtual address of the buffer and sets dma_handle - * to the dma address (mapping) of the first page. - */ -static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - return iommu_alloc_coherent(devnode_table(hwdev), size, dma_handle, - flag); -} - -static void pci_iommu_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - iommu_free_coherent(devnode_table(hwdev), size, vaddr, dma_handle); -} - -/* Creates TCEs for a user provided buffer. The user buffer must be - * contiguous real kernel storage (not vmalloc). The address of the buffer - * passed here is the kernel (virtual) address of the buffer. The buffer - * need not be page aligned, the dma_addr_t returned will point to the same - * byte within the page as vaddr. - */ -static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr, - size_t size, enum dma_data_direction direction) -{ - return iommu_map_single(devnode_table(hwdev), vaddr, size, direction); -} - - -static void pci_iommu_unmap_single(struct device *hwdev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction) -{ - iommu_unmap_single(devnode_table(hwdev), dma_handle, size, direction); -} - - -static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction) -{ - return iommu_map_sg(pdev, devnode_table(pdev), sglist, - nelems, direction); -} - -static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction) -{ - iommu_unmap_sg(devnode_table(pdev), sglist, nelems, direction); -} - -/* We support DMA to/from any memory page via the iommu */ -static int pci_iommu_dma_supported(struct device *dev, u64 mask) -{ - return 1; -} - -void pci_iommu_init(void) -{ - pci_dma_ops.alloc_coherent = pci_iommu_alloc_coherent; - pci_dma_ops.free_coherent = pci_iommu_free_coherent; - pci_dma_ops.map_single = pci_iommu_map_single; - pci_dma_ops.unmap_single = pci_iommu_unmap_single; - pci_dma_ops.map_sg = pci_iommu_map_sg; - pci_dma_ops.unmap_sg = pci_iommu_unmap_sg; - pci_dma_ops.dma_supported = pci_iommu_dma_supported; -} diff --git a/arch/ppc64/kernel/ppc_ksyms.c b/arch/ppc64/kernel/ppc_ksyms.c deleted file mode 100644 index 84006e26342c..000000000000 --- a/arch/ppc64/kernel/ppc_ksyms.c +++ /dev/null @@ -1,76 +0,0 @@ -/* - * c 2001 PPC 64 Team, IBM Corp - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -EXPORT_SYMBOL(strcpy); -EXPORT_SYMBOL(strncpy); -EXPORT_SYMBOL(strcat); -EXPORT_SYMBOL(strncat); -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strrchr); -EXPORT_SYMBOL(strpbrk); -EXPORT_SYMBOL(strstr); -EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strcmp); -EXPORT_SYMBOL(strncmp); - -EXPORT_SYMBOL(csum_partial); -EXPORT_SYMBOL(csum_partial_copy_generic); -EXPORT_SYMBOL(ip_fast_csum); -EXPORT_SYMBOL(csum_tcpudp_magic); - -EXPORT_SYMBOL(__copy_tofrom_user); -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__strncpy_from_user); -EXPORT_SYMBOL(__strnlen_user); - -EXPORT_SYMBOL(reloc_offset); - -EXPORT_SYMBOL(_insb); -EXPORT_SYMBOL(_outsb); -EXPORT_SYMBOL(_insw); -EXPORT_SYMBOL(_outsw); -EXPORT_SYMBOL(_insl); -EXPORT_SYMBOL(_outsl); -EXPORT_SYMBOL(_insw_ns); -EXPORT_SYMBOL(_outsw_ns); -EXPORT_SYMBOL(_insl_ns); -EXPORT_SYMBOL(_outsl_ns); - -EXPORT_SYMBOL(kernel_thread); - -EXPORT_SYMBOL(giveup_fpu); -#ifdef CONFIG_ALTIVEC -EXPORT_SYMBOL(giveup_altivec); -#endif -EXPORT_SYMBOL(__flush_icache_range); -EXPORT_SYMBOL(flush_dcache_range); - -EXPORT_SYMBOL(memcpy); -EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(memscan); -EXPORT_SYMBOL(memcmp); -EXPORT_SYMBOL(memchr); - -EXPORT_SYMBOL(timer_interrupt); -EXPORT_SYMBOL(console_drivers); diff --git a/arch/ppc64/kernel/prom.c b/arch/ppc64/kernel/prom.c deleted file mode 100644 index 47cc26e78957..000000000000 --- a/arch/ppc64/kernel/prom.c +++ /dev/null @@ -1,1956 +0,0 @@ -/* - * - * - * Procedures for interfacing to Open Firmware. - * - * Paul Mackerras August 1996. - * Copyright (C) 1996 Paul Mackerras. - * - * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner. - * {engebret|bergner}@us.ibm.com - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#undef DEBUG - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -struct pci_reg_property { - struct pci_address addr; - u32 size_hi; - u32 size_lo; -}; - -struct isa_reg_property { - u32 space; - u32 address; - u32 size; -}; - - -typedef int interpret_func(struct device_node *, unsigned long *, - int, int, int); - -extern struct rtas_t rtas; -extern struct lmb lmb; -extern unsigned long klimit; -extern unsigned long memory_limit; - -static int __initdata dt_root_addr_cells; -static int __initdata dt_root_size_cells; -static int __initdata iommu_is_off; -int __initdata iommu_force_on; -unsigned long tce_alloc_start, tce_alloc_end; - -typedef u32 cell_t; - -#if 0 -static struct boot_param_header *initial_boot_params __initdata; -#else -struct boot_param_header *initial_boot_params; -#endif - -static struct device_node *allnodes = NULL; - -/* use when traversing tree through the allnext, child, sibling, - * or parent members of struct device_node. - */ -static DEFINE_RWLOCK(devtree_lock); - -/* export that to outside world */ -struct device_node *of_chosen; - -/* - * Wrapper for allocating memory for various data that needs to be - * attached to device nodes as they are processed at boot or when - * added to the device tree later (e.g. DLPAR). At boot there is - * already a region reserved so we just increment *mem_start by size; - * otherwise we call kmalloc. - */ -static void * prom_alloc(unsigned long size, unsigned long *mem_start) -{ - unsigned long tmp; - - if (!mem_start) - return kmalloc(size, GFP_KERNEL); - - tmp = *mem_start; - *mem_start += size; - return (void *)tmp; -} - -/* - * Find the device_node with a given phandle. - */ -static struct device_node * find_phandle(phandle ph) -{ - struct device_node *np; - - for (np = allnodes; np != 0; np = np->allnext) - if (np->linux_phandle == ph) - return np; - return NULL; -} - -/* - * Find the interrupt parent of a node. - */ -static struct device_node * __devinit intr_parent(struct device_node *p) -{ - phandle *parp; - - parp = (phandle *) get_property(p, "interrupt-parent", NULL); - if (parp == NULL) - return p->parent; - return find_phandle(*parp); -} - -/* - * Find out the size of each entry of the interrupts property - * for a node. - */ -int __devinit prom_n_intr_cells(struct device_node *np) -{ - struct device_node *p; - unsigned int *icp; - - for (p = np; (p = intr_parent(p)) != NULL; ) { - icp = (unsigned int *) - get_property(p, "#interrupt-cells", NULL); - if (icp != NULL) - return *icp; - if (get_property(p, "interrupt-controller", NULL) != NULL - || get_property(p, "interrupt-map", NULL) != NULL) { - printk("oops, node %s doesn't have #interrupt-cells\n", - p->full_name); - return 1; - } - } -#ifdef DEBUG_IRQ - printk("prom_n_intr_cells failed for %s\n", np->full_name); -#endif - return 1; -} - -/* - * Map an interrupt from a device up to the platform interrupt - * descriptor. - */ -static int __devinit map_interrupt(unsigned int **irq, struct device_node **ictrler, - struct device_node *np, unsigned int *ints, - int nintrc) -{ - struct device_node *p, *ipar; - unsigned int *imap, *imask, *ip; - int i, imaplen, match; - int newintrc = 0, newaddrc = 0; - unsigned int *reg; - int naddrc; - - reg = (unsigned int *) get_property(np, "reg", NULL); - naddrc = prom_n_addr_cells(np); - p = intr_parent(np); - while (p != NULL) { - if (get_property(p, "interrupt-controller", NULL) != NULL) - /* this node is an interrupt controller, stop here */ - break; - imap = (unsigned int *) - get_property(p, "interrupt-map", &imaplen); - if (imap == NULL) { - p = intr_parent(p); - continue; - } - imask = (unsigned int *) - get_property(p, "interrupt-map-mask", NULL); - if (imask == NULL) { - printk("oops, %s has interrupt-map but no mask\n", - p->full_name); - return 0; - } - imaplen /= sizeof(unsigned int); - match = 0; - ipar = NULL; - while (imaplen > 0 && !match) { - /* check the child-interrupt field */ - match = 1; - for (i = 0; i < naddrc && match; ++i) - match = ((reg[i] ^ imap[i]) & imask[i]) == 0; - for (; i < naddrc + nintrc && match; ++i) - match = ((ints[i-naddrc] ^ imap[i]) & imask[i]) == 0; - imap += naddrc + nintrc; - imaplen -= naddrc + nintrc; - /* grab the interrupt parent */ - ipar = find_phandle((phandle) *imap++); - --imaplen; - if (ipar == NULL) { - printk("oops, no int parent %x in map of %s\n", - imap[-1], p->full_name); - return 0; - } - /* find the parent's # addr and intr cells */ - ip = (unsigned int *) - get_property(ipar, "#interrupt-cells", NULL); - if (ip == NULL) { - printk("oops, no #interrupt-cells on %s\n", - ipar->full_name); - return 0; - } - newintrc = *ip; - ip = (unsigned int *) - get_property(ipar, "#address-cells", NULL); - newaddrc = (ip == NULL)? 0: *ip; - imap += newaddrc + newintrc; - imaplen -= newaddrc + newintrc; - } - if (imaplen < 0) { - printk("oops, error decoding int-map on %s, len=%d\n", - p->full_name, imaplen); - return 0; - } - if (!match) { -#ifdef DEBUG_IRQ - printk("oops, no match in %s int-map for %s\n", - p->full_name, np->full_name); -#endif - return 0; - } - p = ipar; - naddrc = newaddrc; - nintrc = newintrc; - ints = imap - nintrc; - reg = ints - naddrc; - } - if (p == NULL) { -#ifdef DEBUG_IRQ - printk("hmmm, int tree for %s doesn't have ctrler\n", - np->full_name); -#endif - return 0; - } - *irq = ints; - *ictrler = p; - return nintrc; -} - -static int __devinit finish_node_interrupts(struct device_node *np, - unsigned long *mem_start, - int measure_only) -{ - unsigned int *ints; - int intlen, intrcells, intrcount; - int i, j, n; - unsigned int *irq, virq; - struct device_node *ic; - - ints = (unsigned int *) get_property(np, "interrupts", &intlen); - if (ints == NULL) - return 0; - intrcells = prom_n_intr_cells(np); - intlen /= intrcells * sizeof(unsigned int); - - np->intrs = prom_alloc(intlen * sizeof(*(np->intrs)), mem_start); - if (!np->intrs) - return -ENOMEM; - - if (measure_only) - return 0; - - intrcount = 0; - for (i = 0; i < intlen; ++i, ints += intrcells) { - n = map_interrupt(&irq, &ic, np, ints, intrcells); - if (n <= 0) - continue; - - /* don't map IRQ numbers under a cascaded 8259 controller */ - if (ic && device_is_compatible(ic, "chrp,iic")) { - np->intrs[intrcount].line = irq[0]; - } else { - virq = virt_irq_create_mapping(irq[0]); - if (virq == NO_IRQ) { - printk(KERN_CRIT "Could not allocate interrupt" - " number for %s\n", np->full_name); - continue; - } - np->intrs[intrcount].line = irq_offset_up(virq); - } - - /* We offset irq numbers for the u3 MPIC by 128 in PowerMac */ - if (_machine == PLATFORM_POWERMAC && ic && ic->parent) { - char *name = get_property(ic->parent, "name", NULL); - if (name && !strcmp(name, "u3")) - np->intrs[intrcount].line += 128; - else if (!(name && !strcmp(name, "mac-io"))) - /* ignore other cascaded controllers, such as - the k2-sata-root */ - break; - } - np->intrs[intrcount].sense = 1; - if (n > 1) - np->intrs[intrcount].sense = irq[1]; - if (n > 2) { - printk("hmmm, got %d intr cells for %s:", n, - np->full_name); - for (j = 0; j < n; ++j) - printk(" %d", irq[j]); - printk("\n"); - } - ++intrcount; - } - np->n_intrs = intrcount; - - return 0; -} - -static int __devinit interpret_pci_props(struct device_node *np, - unsigned long *mem_start, - int naddrc, int nsizec, - int measure_only) -{ - struct address_range *adr; - struct pci_reg_property *pci_addrs; - int i, l, n_addrs; - - pci_addrs = (struct pci_reg_property *) - get_property(np, "assigned-addresses", &l); - if (!pci_addrs) - return 0; - - n_addrs = l / sizeof(*pci_addrs); - - adr = prom_alloc(n_addrs * sizeof(*adr), mem_start); - if (!adr) - return -ENOMEM; - - if (measure_only) - return 0; - - np->addrs = adr; - np->n_addrs = n_addrs; - - for (i = 0; i < n_addrs; i++) { - adr[i].space = pci_addrs[i].addr.a_hi; - adr[i].address = pci_addrs[i].addr.a_lo | - ((u64)pci_addrs[i].addr.a_mid << 32); - adr[i].size = pci_addrs[i].size_lo; - } - - return 0; -} - -static int __init interpret_dbdma_props(struct device_node *np, - unsigned long *mem_start, - int naddrc, int nsizec, - int measure_only) -{ - struct reg_property32 *rp; - struct address_range *adr; - unsigned long base_address; - int i, l; - struct device_node *db; - - base_address = 0; - if (!measure_only) { - for (db = np->parent; db != NULL; db = db->parent) { - if (!strcmp(db->type, "dbdma") && db->n_addrs != 0) { - base_address = db->addrs[0].address; - break; - } - } - } - - rp = (struct reg_property32 *) get_property(np, "reg", &l); - if (rp != 0 && l >= sizeof(struct reg_property32)) { - i = 0; - adr = (struct address_range *) (*mem_start); - while ((l -= sizeof(struct reg_property32)) >= 0) { - if (!measure_only) { - adr[i].space = 2; - adr[i].address = rp[i].address + base_address; - adr[i].size = rp[i].size; - } - ++i; - } - np->addrs = adr; - np->n_addrs = i; - (*mem_start) += i * sizeof(struct address_range); - } - - return 0; -} - -static int __init interpret_macio_props(struct device_node *np, - unsigned long *mem_start, - int naddrc, int nsizec, - int measure_only) -{ - struct reg_property32 *rp; - struct address_range *adr; - unsigned long base_address; - int i, l; - struct device_node *db; - - base_address = 0; - if (!measure_only) { - for (db = np->parent; db != NULL; db = db->parent) { - if (!strcmp(db->type, "mac-io") && db->n_addrs != 0) { - base_address = db->addrs[0].address; - break; - } - } - } - - rp = (struct reg_property32 *) get_property(np, "reg", &l); - if (rp != 0 && l >= sizeof(struct reg_property32)) { - i = 0; - adr = (struct address_range *) (*mem_start); - while ((l -= sizeof(struct reg_property32)) >= 0) { - if (!measure_only) { - adr[i].space = 2; - adr[i].address = rp[i].address + base_address; - adr[i].size = rp[i].size; - } - ++i; - } - np->addrs = adr; - np->n_addrs = i; - (*mem_start) += i * sizeof(struct address_range); - } - - return 0; -} - -static int __init interpret_isa_props(struct device_node *np, - unsigned long *mem_start, - int naddrc, int nsizec, - int measure_only) -{ - struct isa_reg_property *rp; - struct address_range *adr; - int i, l; - - rp = (struct isa_reg_property *) get_property(np, "reg", &l); - if (rp != 0 && l >= sizeof(struct isa_reg_property)) { - i = 0; - adr = (struct address_range *) (*mem_start); - while ((l -= sizeof(struct isa_reg_property)) >= 0) { - if (!measure_only) { - adr[i].space = rp[i].space; - adr[i].address = rp[i].address; - adr[i].size = rp[i].size; - } - ++i; - } - np->addrs = adr; - np->n_addrs = i; - (*mem_start) += i * sizeof(struct address_range); - } - - return 0; -} - -static int __init interpret_root_props(struct device_node *np, - unsigned long *mem_start, - int naddrc, int nsizec, - int measure_only) -{ - struct address_range *adr; - int i, l; - unsigned int *rp; - int rpsize = (naddrc + nsizec) * sizeof(unsigned int); - - rp = (unsigned int *) get_property(np, "reg", &l); - if (rp != 0 && l >= rpsize) { - i = 0; - adr = (struct address_range *) (*mem_start); - while ((l -= rpsize) >= 0) { - if (!measure_only) { - adr[i].space = 0; - adr[i].address = rp[naddrc - 1]; - adr[i].size = rp[naddrc + nsizec - 1]; - } - ++i; - rp += naddrc + nsizec; - } - np->addrs = adr; - np->n_addrs = i; - (*mem_start) += i * sizeof(struct address_range); - } - - return 0; -} - -static int __devinit finish_node(struct device_node *np, - unsigned long *mem_start, - interpret_func *ifunc, - int naddrc, int nsizec, - int measure_only) -{ - struct device_node *child; - int *ip, rc = 0; - - /* get the device addresses and interrupts */ - if (ifunc != NULL) - rc = ifunc(np, mem_start, naddrc, nsizec, measure_only); - if (rc) - goto out; - - rc = finish_node_interrupts(np, mem_start, measure_only); - if (rc) - goto out; - - /* Look for #address-cells and #size-cells properties. */ - ip = (int *) get_property(np, "#address-cells", NULL); - if (ip != NULL) - naddrc = *ip; - ip = (int *) get_property(np, "#size-cells", NULL); - if (ip != NULL) - nsizec = *ip; - - if (!strcmp(np->name, "device-tree") || np->parent == NULL) - ifunc = interpret_root_props; - else if (np->type == 0) - ifunc = NULL; - else if (!strcmp(np->type, "pci") || !strcmp(np->type, "vci")) - ifunc = interpret_pci_props; - else if (!strcmp(np->type, "dbdma")) - ifunc = interpret_dbdma_props; - else if (!strcmp(np->type, "mac-io") || ifunc == interpret_macio_props) - ifunc = interpret_macio_props; - else if (!strcmp(np->type, "isa")) - ifunc = interpret_isa_props; - else if (!strcmp(np->name, "uni-n") || !strcmp(np->name, "u3")) - ifunc = interpret_root_props; - else if (!((ifunc == interpret_dbdma_props - || ifunc == interpret_macio_props) - && (!strcmp(np->type, "escc") - || !strcmp(np->type, "media-bay")))) - ifunc = NULL; - - for (child = np->child; child != NULL; child = child->sibling) { - rc = finish_node(child, mem_start, ifunc, - naddrc, nsizec, measure_only); - if (rc) - goto out; - } -out: - return rc; -} - -/** - * finish_device_tree is called once things are running normally - * (i.e. with text and data mapped to the address they were linked at). - * It traverses the device tree and fills in some of the additional, - * fields in each node like {n_}addrs and {n_}intrs, the virt interrupt - * mapping is also initialized at this point. - */ -void __init finish_device_tree(void) -{ - unsigned long start, end, size = 0; - - DBG(" -> finish_device_tree\n"); - - if (ppc64_interrupt_controller == IC_INVALID) { - DBG("failed to configure interrupt controller type\n"); - panic("failed to configure interrupt controller type\n"); - } - - /* Initialize virtual IRQ map */ - virt_irq_init(); - - /* - * Finish device-tree (pre-parsing some properties etc...) - * We do this in 2 passes. One with "measure_only" set, which - * will only measure the amount of memory needed, then we can - * allocate that memory, and call finish_node again. However, - * we must be careful as most routines will fail nowadays when - * prom_alloc() returns 0, so we must make sure our first pass - * doesn't start at 0. We pre-initialize size to 16 for that - * reason and then remove those additional 16 bytes - */ - size = 16; - finish_node(allnodes, &size, NULL, 0, 0, 1); - size -= 16; - end = start = (unsigned long)abs_to_virt(lmb_alloc(size, 128)); - finish_node(allnodes, &end, NULL, 0, 0, 0); - BUG_ON(end != start + size); - - DBG(" <- finish_device_tree\n"); -} - -#ifdef DEBUG -#define printk udbg_printf -#endif - -static inline char *find_flat_dt_string(u32 offset) -{ - return ((char *)initial_boot_params) + - initial_boot_params->off_dt_strings + offset; -} - -/** - * This function is used to scan the flattened device-tree, it is - * used to extract the memory informations at boot before we can - * unflatten the tree - */ -int __init of_scan_flat_dt(int (*it)(unsigned long node, - const char *uname, int depth, - void *data), - void *data) -{ - unsigned long p = ((unsigned long)initial_boot_params) + - initial_boot_params->off_dt_struct; - int rc = 0; - int depth = -1; - - do { - u32 tag = *((u32 *)p); - char *pathp; - - p += 4; - if (tag == OF_DT_END_NODE) { - depth --; - continue; - } - if (tag == OF_DT_NOP) - continue; - if (tag == OF_DT_END) - break; - if (tag == OF_DT_PROP) { - u32 sz = *((u32 *)p); - p += 8; - if (initial_boot_params->version < 0x10) - p = _ALIGN(p, sz >= 8 ? 8 : 4); - p += sz; - p = _ALIGN(p, 4); - continue; - } - if (tag != OF_DT_BEGIN_NODE) { - printk(KERN_WARNING "Invalid tag %x scanning flattened" - " device tree !\n", tag); - return -EINVAL; - } - depth++; - pathp = (char *)p; - p = _ALIGN(p + strlen(pathp) + 1, 4); - if ((*pathp) == '/') { - char *lp, *np; - for (lp = NULL, np = pathp; *np; np++) - if ((*np) == '/') - lp = np+1; - if (lp != NULL) - pathp = lp; - } - rc = it(p, pathp, depth, data); - if (rc != 0) - break; - } while(1); - - return rc; -} - -/** - * This function can be used within scan_flattened_dt callback to get - * access to properties - */ -void* __init of_get_flat_dt_prop(unsigned long node, const char *name, - unsigned long *size) -{ - unsigned long p = node; - - do { - u32 tag = *((u32 *)p); - u32 sz, noff; - const char *nstr; - - p += 4; - if (tag == OF_DT_NOP) - continue; - if (tag != OF_DT_PROP) - return NULL; - - sz = *((u32 *)p); - noff = *((u32 *)(p + 4)); - p += 8; - if (initial_boot_params->version < 0x10) - p = _ALIGN(p, sz >= 8 ? 8 : 4); - - nstr = find_flat_dt_string(noff); - if (nstr == NULL) { - printk(KERN_WARNING "Can't find property index" - " name !\n"); - return NULL; - } - if (strcmp(name, nstr) == 0) { - if (size) - *size = sz; - return (void *)p; - } - p += sz; - p = _ALIGN(p, 4); - } while(1); -} - -static void *__init unflatten_dt_alloc(unsigned long *mem, unsigned long size, - unsigned long align) -{ - void *res; - - *mem = _ALIGN(*mem, align); - res = (void *)*mem; - *mem += size; - - return res; -} - -static unsigned long __init unflatten_dt_node(unsigned long mem, - unsigned long *p, - struct device_node *dad, - struct device_node ***allnextpp, - unsigned long fpsize) -{ - struct device_node *np; - struct property *pp, **prev_pp = NULL; - char *pathp; - u32 tag; - unsigned int l, allocl; - int has_name = 0; - int new_format = 0; - - tag = *((u32 *)(*p)); - if (tag != OF_DT_BEGIN_NODE) { - printk("Weird tag at start of node: %x\n", tag); - return mem; - } - *p += 4; - pathp = (char *)*p; - l = allocl = strlen(pathp) + 1; - *p = _ALIGN(*p + l, 4); - - /* version 0x10 has a more compact unit name here instead of the full - * path. we accumulate the full path size using "fpsize", we'll rebuild - * it later. We detect this because the first character of the name is - * not '/'. - */ - if ((*pathp) != '/') { - new_format = 1; - if (fpsize == 0) { - /* root node: special case. fpsize accounts for path - * plus terminating zero. root node only has '/', so - * fpsize should be 2, but we want to avoid the first - * level nodes to have two '/' so we use fpsize 1 here - */ - fpsize = 1; - allocl = 2; - } else { - /* account for '/' and path size minus terminal 0 - * already in 'l' - */ - fpsize += l; - allocl = fpsize; - } - } - - - np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl, - __alignof__(struct device_node)); - if (allnextpp) { - memset(np, 0, sizeof(*np)); - np->full_name = ((char*)np) + sizeof(struct device_node); - if (new_format) { - char *p = np->full_name; - /* rebuild full path for new format */ - if (dad && dad->parent) { - strcpy(p, dad->full_name); -#ifdef DEBUG - if ((strlen(p) + l + 1) != allocl) { - DBG("%s: p: %d, l: %d, a: %d\n", - pathp, strlen(p), l, allocl); - } -#endif - p += strlen(p); - } - *(p++) = '/'; - memcpy(p, pathp, l); - } else - memcpy(np->full_name, pathp, l); - prev_pp = &np->properties; - **allnextpp = np; - *allnextpp = &np->allnext; - if (dad != NULL) { - np->parent = dad; - /* we temporarily use the next field as `last_child'*/ - if (dad->next == 0) - dad->child = np; - else - dad->next->sibling = np; - dad->next = np; - } - kref_init(&np->kref); - } - while(1) { - u32 sz, noff; - char *pname; - - tag = *((u32 *)(*p)); - if (tag == OF_DT_NOP) { - *p += 4; - continue; - } - if (tag != OF_DT_PROP) - break; - *p += 4; - sz = *((u32 *)(*p)); - noff = *((u32 *)((*p) + 4)); - *p += 8; - if (initial_boot_params->version < 0x10) - *p = _ALIGN(*p, sz >= 8 ? 8 : 4); - - pname = find_flat_dt_string(noff); - if (pname == NULL) { - printk("Can't find property name in list !\n"); - break; - } - if (strcmp(pname, "name") == 0) - has_name = 1; - l = strlen(pname) + 1; - pp = unflatten_dt_alloc(&mem, sizeof(struct property), - __alignof__(struct property)); - if (allnextpp) { - if (strcmp(pname, "linux,phandle") == 0) { - np->node = *((u32 *)*p); - if (np->linux_phandle == 0) - np->linux_phandle = np->node; - } - if (strcmp(pname, "ibm,phandle") == 0) - np->linux_phandle = *((u32 *)*p); - pp->name = pname; - pp->length = sz; - pp->value = (void *)*p; - *prev_pp = pp; - prev_pp = &pp->next; - } - *p = _ALIGN((*p) + sz, 4); - } - /* with version 0x10 we may not have the name property, recreate - * it here from the unit name if absent - */ - if (!has_name) { - char *p = pathp, *ps = pathp, *pa = NULL; - int sz; - - while (*p) { - if ((*p) == '@') - pa = p; - if ((*p) == '/') - ps = p + 1; - p++; - } - if (pa < ps) - pa = p; - sz = (pa - ps) + 1; - pp = unflatten_dt_alloc(&mem, sizeof(struct property) + sz, - __alignof__(struct property)); - if (allnextpp) { - pp->name = "name"; - pp->length = sz; - pp->value = (unsigned char *)(pp + 1); - *prev_pp = pp; - prev_pp = &pp->next; - memcpy(pp->value, ps, sz - 1); - ((char *)pp->value)[sz - 1] = 0; - DBG("fixed up name for %s -> %s\n", pathp, pp->value); - } - } - if (allnextpp) { - *prev_pp = NULL; - np->name = get_property(np, "name", NULL); - np->type = get_property(np, "device_type", NULL); - - if (!np->name) - np->name = ""; - if (!np->type) - np->type = ""; - } - while (tag == OF_DT_BEGIN_NODE) { - mem = unflatten_dt_node(mem, p, np, allnextpp, fpsize); - tag = *((u32 *)(*p)); - } - if (tag != OF_DT_END_NODE) { - printk("Weird tag at end of node: %x\n", tag); - return mem; - } - *p += 4; - return mem; -} - - -/** - * unflattens the device-tree passed by the firmware, creating the - * tree of struct device_node. It also fills the "name" and "type" - * pointers of the nodes so the normal device-tree walking functions - * can be used (this used to be done by finish_device_tree) - */ -void __init unflatten_device_tree(void) -{ - unsigned long start, mem, size; - struct device_node **allnextp = &allnodes; - char *p = NULL; - int l = 0; - - DBG(" -> unflatten_device_tree()\n"); - - /* First pass, scan for size */ - start = ((unsigned long)initial_boot_params) + - initial_boot_params->off_dt_struct; - size = unflatten_dt_node(0, &start, NULL, NULL, 0); - size = (size | 3) + 1; - - DBG(" size is %lx, allocating...\n", size); - - /* Allocate memory for the expanded device tree */ - mem = lmb_alloc(size + 4, __alignof__(struct device_node)); - if (!mem) { - DBG("Couldn't allocate memory with lmb_alloc()!\n"); - panic("Couldn't allocate memory with lmb_alloc()!\n"); - } - mem = (unsigned long)abs_to_virt(mem); - - ((u32 *)mem)[size / 4] = 0xdeadbeef; - - DBG(" unflattening...\n", mem); - - /* Second pass, do actual unflattening */ - start = ((unsigned long)initial_boot_params) + - initial_boot_params->off_dt_struct; - unflatten_dt_node(mem, &start, NULL, &allnextp, 0); - if (*((u32 *)start) != OF_DT_END) - printk(KERN_WARNING "Weird tag at end of tree: %08x\n", *((u32 *)start)); - if (((u32 *)mem)[size / 4] != 0xdeadbeef) - printk(KERN_WARNING "End of tree marker overwritten: %08x\n", - ((u32 *)mem)[size / 4] ); - *allnextp = NULL; - - /* Get pointer to OF "/chosen" node for use everywhere */ - of_chosen = of_find_node_by_path("/chosen"); - - /* Retreive command line */ - if (of_chosen != NULL) { - p = (char *)get_property(of_chosen, "bootargs", &l); - if (p != NULL && l > 0) - strlcpy(cmd_line, p, min(l, COMMAND_LINE_SIZE)); - } -#ifdef CONFIG_CMDLINE - if (l == 0 || (l == 1 && (*p) == 0)) - strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#endif /* CONFIG_CMDLINE */ - - DBG("Command line is: %s\n", cmd_line); - - DBG(" <- unflatten_device_tree()\n"); -} - - -static int __init early_init_dt_scan_cpus(unsigned long node, - const char *uname, int depth, void *data) -{ - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; - unsigned long size; - - /* We are scanning "cpu" nodes only */ - if (type == NULL || strcmp(type, "cpu") != 0) - return 0; - - if (initial_boot_params && initial_boot_params->version >= 2) { - /* version 2 of the kexec param format adds the phys cpuid - * of booted proc. - */ - boot_cpuid_phys = initial_boot_params->boot_cpuid_phys; - boot_cpuid = 0; - } else { - /* Check if it's the boot-cpu, set it's hw index in paca now */ - if (of_get_flat_dt_prop(node, "linux,boot-cpu", NULL) - != NULL) { - u32 *prop = of_get_flat_dt_prop(node, "reg", NULL); - set_hard_smp_processor_id(0, prop == NULL ? 0 : *prop); - boot_cpuid_phys = get_hard_smp_processor_id(0); - } - } - -#ifdef CONFIG_ALTIVEC - /* Check if we have a VMX and eventually update CPU features */ - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", NULL); - if (prop && (*prop) > 0) { - cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; - cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; - } - - /* Same goes for Apple's "altivec" property */ - prop = (u32 *)of_get_flat_dt_prop(node, "altivec", NULL); - if (prop) { - cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; - cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; - } -#endif /* CONFIG_ALTIVEC */ - - /* - * Check for an SMT capable CPU and set the CPU feature. We do - * this by looking at the size of the ibm,ppc-interrupt-server#s - * property - */ - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", - &size); - cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; - if (prop && ((size / sizeof(u32)) > 1)) - cur_cpu_spec->cpu_features |= CPU_FTR_SMT; - - return 0; -} - -static int __init early_init_dt_scan_chosen(unsigned long node, - const char *uname, int depth, void *data) -{ - u32 *prop; - u64 *prop64; - - DBG("search \"chosen\", depth: %d, uname: %s\n", depth, uname); - - if (depth != 1 || strcmp(uname, "chosen") != 0) - return 0; - - /* get platform type */ - prop = (u32 *)of_get_flat_dt_prop(node, "linux,platform", NULL); - if (prop == NULL) - return 0; - _machine = *prop; - - /* check if iommu is forced on or off */ - if (of_get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL) - iommu_is_off = 1; - if (of_get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL) - iommu_force_on = 1; - - prop64 = (u64*)of_get_flat_dt_prop(node, "linux,memory-limit", NULL); - if (prop64) - memory_limit = *prop64; - - prop64 = (u64*)of_get_flat_dt_prop(node, "linux,tce-alloc-start",NULL); - if (prop64) - tce_alloc_start = *prop64; - - prop64 = (u64*)of_get_flat_dt_prop(node, "linux,tce-alloc-end", NULL); - if (prop64) - tce_alloc_end = *prop64; - -#ifdef CONFIG_PPC_RTAS - /* To help early debugging via the front panel, we retreive a minimal - * set of RTAS infos now if available - */ - { - u64 *basep, *entryp; - - basep = (u64*)of_get_flat_dt_prop(node, - "linux,rtas-base", NULL); - entryp = (u64*)of_get_flat_dt_prop(node, - "linux,rtas-entry", NULL); - prop = (u32*)of_get_flat_dt_prop(node, - "linux,rtas-size", NULL); - if (basep && entryp && prop) { - rtas.base = *basep; - rtas.entry = *entryp; - rtas.size = *prop; - } - } -#endif /* CONFIG_PPC_RTAS */ - - /* break now */ - return 1; -} - -static int __init early_init_dt_scan_root(unsigned long node, - const char *uname, int depth, void *data) -{ - u32 *prop; - - if (depth != 0) - return 0; - - prop = (u32 *)of_get_flat_dt_prop(node, "#size-cells", NULL); - dt_root_size_cells = (prop == NULL) ? 1 : *prop; - DBG("dt_root_size_cells = %x\n", dt_root_size_cells); - - prop = (u32 *)of_get_flat_dt_prop(node, "#address-cells", NULL); - dt_root_addr_cells = (prop == NULL) ? 2 : *prop; - DBG("dt_root_addr_cells = %x\n", dt_root_addr_cells); - - /* break now */ - return 1; -} - -static unsigned long __init dt_mem_next_cell(int s, cell_t **cellp) -{ - cell_t *p = *cellp; - unsigned long r = 0; - - /* Ignore more than 2 cells */ - while (s > 2) { - p++; - s--; - } - while (s) { - r <<= 32; - r |= *(p++); - s--; - } - - *cellp = p; - return r; -} - - -static int __init early_init_dt_scan_memory(unsigned long node, - const char *uname, int depth, void *data) -{ - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - cell_t *reg, *endp; - unsigned long l; - - /* We are scanning "memory" nodes only */ - if (type == NULL || strcmp(type, "memory") != 0) - return 0; - - reg = (cell_t *)of_get_flat_dt_prop(node, "reg", &l); - if (reg == NULL) - return 0; - - endp = reg + (l / sizeof(cell_t)); - - DBG("memory scan node %s ..., reg size %ld, data: %x %x %x %x, ...\n", - uname, l, reg[0], reg[1], reg[2], reg[3]); - - while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { - unsigned long base, size; - - base = dt_mem_next_cell(dt_root_addr_cells, ®); - size = dt_mem_next_cell(dt_root_size_cells, ®); - - if (size == 0) - continue; - DBG(" - %lx , %lx\n", base, size); - if (iommu_is_off) { - if (base >= 0x80000000ul) - continue; - if ((base + size) > 0x80000000ul) - size = 0x80000000ul - base; - } - lmb_add(base, size); - } - return 0; -} - -static void __init early_reserve_mem(void) -{ - u64 base, size; - u64 *reserve_map = (u64 *)(((unsigned long)initial_boot_params) + - initial_boot_params->off_mem_rsvmap); - while (1) { - base = *(reserve_map++); - size = *(reserve_map++); - if (size == 0) - break; - DBG("reserving: %lx -> %lx\n", base, size); - lmb_reserve(base, size); - } - -#if 0 - DBG("memory reserved, lmbs :\n"); - lmb_dump_all(); -#endif -} - -void __init early_init_devtree(void *params) -{ - DBG(" -> early_init_devtree()\n"); - - /* Setup flat device-tree pointer */ - initial_boot_params = params; - - /* Retreive various informations from the /chosen node of the - * device-tree, including the platform type, initrd location and - * size, TCE reserve, and more ... - */ - of_scan_flat_dt(early_init_dt_scan_chosen, NULL); - - /* Scan memory nodes and rebuild LMBs */ - lmb_init(); - of_scan_flat_dt(early_init_dt_scan_root, NULL); - of_scan_flat_dt(early_init_dt_scan_memory, NULL); - lmb_enforce_memory_limit(memory_limit); - lmb_analyze(); - lmb_reserve(0, __pa(klimit)); - - /* Reserve LMB regions used by kernel, initrd, dt, etc... */ - early_reserve_mem(); - - DBG("Scanning CPUs ...\n"); - - /* Retreive hash table size from flattened tree plus other - * CPU related informations (altivec support, boot CPU ID, ...) - */ - of_scan_flat_dt(early_init_dt_scan_cpus, NULL); - - DBG(" <- early_init_devtree()\n"); -} - -#undef printk - -int -prom_n_addr_cells(struct device_node* np) -{ - int* ip; - do { - if (np->parent) - np = np->parent; - ip = (int *) get_property(np, "#address-cells", NULL); - if (ip != NULL) - return *ip; - } while (np->parent); - /* No #address-cells property for the root node, default to 1 */ - return 1; -} -EXPORT_SYMBOL_GPL(prom_n_addr_cells); - -int -prom_n_size_cells(struct device_node* np) -{ - int* ip; - do { - if (np->parent) - np = np->parent; - ip = (int *) get_property(np, "#size-cells", NULL); - if (ip != NULL) - return *ip; - } while (np->parent); - /* No #size-cells property for the root node, default to 1 */ - return 1; -} -EXPORT_SYMBOL_GPL(prom_n_size_cells); - -/** - * Work out the sense (active-low level / active-high edge) - * of each interrupt from the device tree. - */ -void __init prom_get_irq_senses(unsigned char *senses, int off, int max) -{ - struct device_node *np; - int i, j; - - /* default to level-triggered */ - memset(senses, 1, max - off); - - for (np = allnodes; np != 0; np = np->allnext) { - for (j = 0; j < np->n_intrs; j++) { - i = np->intrs[j].line; - if (i >= off && i < max) - senses[i-off] = np->intrs[j].sense ? - IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE : - IRQ_SENSE_EDGE | IRQ_POLARITY_POSITIVE; - } - } -} - -/** - * Construct and return a list of the device_nodes with a given name. - */ -struct device_node * -find_devices(const char *name) -{ - struct device_node *head, **prevp, *np; - - prevp = &head; - for (np = allnodes; np != 0; np = np->allnext) { - if (np->name != 0 && strcasecmp(np->name, name) == 0) { - *prevp = np; - prevp = &np->next; - } - } - *prevp = NULL; - return head; -} -EXPORT_SYMBOL(find_devices); - -/** - * Construct and return a list of the device_nodes with a given type. - */ -struct device_node * -find_type_devices(const char *type) -{ - struct device_node *head, **prevp, *np; - - prevp = &head; - for (np = allnodes; np != 0; np = np->allnext) { - if (np->type != 0 && strcasecmp(np->type, type) == 0) { - *prevp = np; - prevp = &np->next; - } - } - *prevp = NULL; - return head; -} -EXPORT_SYMBOL(find_type_devices); - -/** - * Returns all nodes linked together - */ -struct device_node * -find_all_nodes(void) -{ - struct device_node *head, **prevp, *np; - - prevp = &head; - for (np = allnodes; np != 0; np = np->allnext) { - *prevp = np; - prevp = &np->next; - } - *prevp = NULL; - return head; -} -EXPORT_SYMBOL(find_all_nodes); - -/** Checks if the given "compat" string matches one of the strings in - * the device's "compatible" property - */ -int -device_is_compatible(struct device_node *device, const char *compat) -{ - const char* cp; - int cplen, l; - - cp = (char *) get_property(device, "compatible", &cplen); - if (cp == NULL) - return 0; - while (cplen > 0) { - if (strncasecmp(cp, compat, strlen(compat)) == 0) - return 1; - l = strlen(cp) + 1; - cp += l; - cplen -= l; - } - - return 0; -} -EXPORT_SYMBOL(device_is_compatible); - - -/** - * Indicates whether the root node has a given value in its - * compatible property. - */ -int -machine_is_compatible(const char *compat) -{ - struct device_node *root; - int rc = 0; - - root = of_find_node_by_path("/"); - if (root) { - rc = device_is_compatible(root, compat); - of_node_put(root); - } - return rc; -} -EXPORT_SYMBOL(machine_is_compatible); - -/** - * Construct and return a list of the device_nodes with a given type - * and compatible property. - */ -struct device_node * -find_compatible_devices(const char *type, const char *compat) -{ - struct device_node *head, **prevp, *np; - - prevp = &head; - for (np = allnodes; np != 0; np = np->allnext) { - if (type != NULL - && !(np->type != 0 && strcasecmp(np->type, type) == 0)) - continue; - if (device_is_compatible(np, compat)) { - *prevp = np; - prevp = &np->next; - } - } - *prevp = NULL; - return head; -} -EXPORT_SYMBOL(find_compatible_devices); - -/** - * Find the device_node with a given full_name. - */ -struct device_node * -find_path_device(const char *path) -{ - struct device_node *np; - - for (np = allnodes; np != 0; np = np->allnext) - if (np->full_name != 0 && strcasecmp(np->full_name, path) == 0) - return np; - return NULL; -} -EXPORT_SYMBOL(find_path_device); - -/******* - * - * New implementation of the OF "find" APIs, return a refcounted - * object, call of_node_put() when done. The device tree and list - * are protected by a rw_lock. - * - * Note that property management will need some locking as well, - * this isn't dealt with yet. - * - *******/ - -/** - * of_find_node_by_name - Find a node by its "name" property - * @from: The node to start searching from or NULL, the node - * you pass will not be searched, only the next one - * will; typically, you pass what the previous call - * returned. of_node_put() will be called on it - * @name: The name string to match against - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_node_by_name(struct device_node *from, - const char *name) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = from ? from->allnext : allnodes; - for (; np != 0; np = np->allnext) - if (np->name != 0 && strcasecmp(np->name, name) == 0 - && of_node_get(np)) - break; - if (from) - of_node_put(from); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_node_by_name); - -/** - * of_find_node_by_type - Find a node by its "device_type" property - * @from: The node to start searching from or NULL, the node - * you pass will not be searched, only the next one - * will; typically, you pass what the previous call - * returned. of_node_put() will be called on it - * @name: The type string to match against - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_node_by_type(struct device_node *from, - const char *type) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = from ? from->allnext : allnodes; - for (; np != 0; np = np->allnext) - if (np->type != 0 && strcasecmp(np->type, type) == 0 - && of_node_get(np)) - break; - if (from) - of_node_put(from); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_node_by_type); - -/** - * of_find_compatible_node - Find a node based on type and one of the - * tokens in its "compatible" property - * @from: The node to start searching from or NULL, the node - * you pass will not be searched, only the next one - * will; typically, you pass what the previous call - * returned. of_node_put() will be called on it - * @type: The type string to match "device_type" or NULL to ignore - * @compatible: The string to match to one of the tokens in the device - * "compatible" list. - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_compatible_node(struct device_node *from, - const char *type, const char *compatible) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = from ? from->allnext : allnodes; - for (; np != 0; np = np->allnext) { - if (type != NULL - && !(np->type != 0 && strcasecmp(np->type, type) == 0)) - continue; - if (device_is_compatible(np, compatible) && of_node_get(np)) - break; - } - if (from) - of_node_put(from); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_compatible_node); - -/** - * of_find_node_by_path - Find a node matching a full OF path - * @path: The full path to match - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_node_by_path(const char *path) -{ - struct device_node *np = allnodes; - - read_lock(&devtree_lock); - for (; np != 0; np = np->allnext) { - if (np->full_name != 0 && strcasecmp(np->full_name, path) == 0 - && of_node_get(np)) - break; - } - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_node_by_path); - -/** - * of_find_node_by_phandle - Find a node given a phandle - * @handle: phandle of the node to find - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_node_by_phandle(phandle handle) -{ - struct device_node *np; - - read_lock(&devtree_lock); - for (np = allnodes; np != 0; np = np->allnext) - if (np->linux_phandle == handle) - break; - if (np) - of_node_get(np); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_node_by_phandle); - -/** - * of_find_all_nodes - Get next node in global list - * @prev: Previous node or NULL to start iteration - * of_node_put() will be called on it - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_all_nodes(struct device_node *prev) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = prev ? prev->allnext : allnodes; - for (; np != 0; np = np->allnext) - if (of_node_get(np)) - break; - if (prev) - of_node_put(prev); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_all_nodes); - -/** - * of_get_parent - Get a node's parent if any - * @node: Node to get parent - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_get_parent(const struct device_node *node) -{ - struct device_node *np; - - if (!node) - return NULL; - - read_lock(&devtree_lock); - np = of_node_get(node->parent); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_get_parent); - -/** - * of_get_next_child - Iterate a node childs - * @node: parent node - * @prev: previous child of the parent node, or NULL to get first - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_get_next_child(const struct device_node *node, - struct device_node *prev) -{ - struct device_node *next; - - read_lock(&devtree_lock); - next = prev ? prev->sibling : node->child; - for (; next != 0; next = next->sibling) - if (of_node_get(next)) - break; - if (prev) - of_node_put(prev); - read_unlock(&devtree_lock); - return next; -} -EXPORT_SYMBOL(of_get_next_child); - -/** - * of_node_get - Increment refcount of a node - * @node: Node to inc refcount, NULL is supported to - * simplify writing of callers - * - * Returns node. - */ -struct device_node *of_node_get(struct device_node *node) -{ - if (node) - kref_get(&node->kref); - return node; -} -EXPORT_SYMBOL(of_node_get); - -static inline struct device_node * kref_to_device_node(struct kref *kref) -{ - return container_of(kref, struct device_node, kref); -} - -/** - * of_node_release - release a dynamically allocated node - * @kref: kref element of the node to be released - * - * In of_node_put() this function is passed to kref_put() - * as the destructor. - */ -static void of_node_release(struct kref *kref) -{ - struct device_node *node = kref_to_device_node(kref); - struct property *prop = node->properties; - - if (!OF_IS_DYNAMIC(node)) - return; - while (prop) { - struct property *next = prop->next; - kfree(prop->name); - kfree(prop->value); - kfree(prop); - prop = next; - } - kfree(node->intrs); - kfree(node->addrs); - kfree(node->full_name); - kfree(node->data); - kfree(node); -} - -/** - * of_node_put - Decrement refcount of a node - * @node: Node to dec refcount, NULL is supported to - * simplify writing of callers - * - */ -void of_node_put(struct device_node *node) -{ - if (node) - kref_put(&node->kref, of_node_release); -} -EXPORT_SYMBOL(of_node_put); - -/* - * Fix up the uninitialized fields in a new device node: - * name, type, n_addrs, addrs, n_intrs, intrs, and pci-specific fields - * - * A lot of boot-time code is duplicated here, because functions such - * as finish_node_interrupts, interpret_pci_props, etc. cannot use the - * slab allocator. - * - * This should probably be split up into smaller chunks. - */ - -static int of_finish_dynamic_node(struct device_node *node, - unsigned long *unused1, int unused2, - int unused3, int unused4) -{ - struct device_node *parent = of_get_parent(node); - int err = 0; - phandle *ibm_phandle; - - node->name = get_property(node, "name", NULL); - node->type = get_property(node, "device_type", NULL); - - if (!parent) { - err = -ENODEV; - goto out; - } - - /* We don't support that function on PowerMac, at least - * not yet - */ - if (_machine == PLATFORM_POWERMAC) - return -ENODEV; - - /* fix up new node's linux_phandle field */ - if ((ibm_phandle = (unsigned int *)get_property(node, "ibm,phandle", NULL))) - node->linux_phandle = *ibm_phandle; - -out: - of_node_put(parent); - return err; -} - -/* - * Plug a device node into the tree and global list. - */ -void of_attach_node(struct device_node *np) -{ - write_lock(&devtree_lock); - np->sibling = np->parent->child; - np->allnext = allnodes; - np->parent->child = np; - allnodes = np; - write_unlock(&devtree_lock); -} - -/* - * "Unplug" a node from the device tree. The caller must hold - * a reference to the node. The memory associated with the node - * is not freed until its refcount goes to zero. - */ -void of_detach_node(const struct device_node *np) -{ - struct device_node *parent; - - write_lock(&devtree_lock); - - parent = np->parent; - - if (allnodes == np) - allnodes = np->allnext; - else { - struct device_node *prev; - for (prev = allnodes; - prev->allnext != np; - prev = prev->allnext) - ; - prev->allnext = np->allnext; - } - - if (parent->child == np) - parent->child = np->sibling; - else { - struct device_node *prevsib; - for (prevsib = np->parent->child; - prevsib->sibling != np; - prevsib = prevsib->sibling) - ; - prevsib->sibling = np->sibling; - } - - write_unlock(&devtree_lock); -} - -static int prom_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node) -{ - int err; - - switch (action) { - case PSERIES_RECONFIG_ADD: - err = finish_node(node, NULL, of_finish_dynamic_node, 0, 0, 0); - if (err < 0) { - printk(KERN_ERR "finish_node returned %d\n", err); - err = NOTIFY_BAD; - } - break; - default: - err = NOTIFY_DONE; - break; - } - return err; -} - -static struct notifier_block prom_reconfig_nb = { - .notifier_call = prom_reconfig_notifier, - .priority = 10, /* This one needs to run first */ -}; - -static int __init prom_reconfig_setup(void) -{ - return pSeries_reconfig_notifier_register(&prom_reconfig_nb); -} -__initcall(prom_reconfig_setup); - -/* - * Find a property with a given name for a given node - * and return the value. - */ -unsigned char * -get_property(struct device_node *np, const char *name, int *lenp) -{ - struct property *pp; - - for (pp = np->properties; pp != 0; pp = pp->next) - if (strcmp(pp->name, name) == 0) { - if (lenp != 0) - *lenp = pp->length; - return pp->value; - } - return NULL; -} -EXPORT_SYMBOL(get_property); - -/* - * Add a property to a node. - */ -int -prom_add_property(struct device_node* np, struct property* prop) -{ - struct property **next; - - prop->next = NULL; - write_lock(&devtree_lock); - next = &np->properties; - while (*next) { - if (strcmp(prop->name, (*next)->name) == 0) { - /* duplicate ! don't insert it */ - write_unlock(&devtree_lock); - return -1; - } - next = &(*next)->next; - } - *next = prop; - write_unlock(&devtree_lock); - - /* try to add to proc as well if it was initialized */ - if (np->pde) - proc_device_tree_add_prop(np->pde, prop); - - return 0; -} - -#if 0 -void -print_properties(struct device_node *np) -{ - struct property *pp; - char *cp; - int i, n; - - for (pp = np->properties; pp != 0; pp = pp->next) { - printk(KERN_INFO "%s", pp->name); - for (i = strlen(pp->name); i < 16; ++i) - printk(" "); - cp = (char *) pp->value; - for (i = pp->length; i > 0; --i, ++cp) - if ((i > 1 && (*cp < 0x20 || *cp > 0x7e)) - || (i == 1 && *cp != 0)) - break; - if (i == 0 && pp->length > 1) { - /* looks like a string */ - printk(" %s\n", (char *) pp->value); - } else { - /* dump it in hex */ - n = pp->length; - if (n > 64) - n = 64; - if (pp->length % 4 == 0) { - unsigned int *p = (unsigned int *) pp->value; - - n /= 4; - for (i = 0; i < n; ++i) { - if (i != 0 && (i % 4) == 0) - printk("\n "); - printk(" %08x", *p++); - } - } else { - unsigned char *bp = pp->value; - - for (i = 0; i < n; ++i) { - if (i != 0 && (i % 16) == 0) - printk("\n "); - printk(" %02x", *bp++); - } - } - printk("\n"); - if (pp->length > 64) - printk(" ... (length = %d)\n", - pp->length); - } - } -} -#endif - - - - - - - - - - diff --git a/arch/ppc64/kernel/prom_init.c b/arch/ppc64/kernel/prom_init.c deleted file mode 100644 index 6375f40b23db..000000000000 --- a/arch/ppc64/kernel/prom_init.c +++ /dev/null @@ -1,2051 +0,0 @@ -/* - * - * - * Procedures for interfacing to Open Firmware. - * - * Paul Mackerras August 1996. - * Copyright (C) 1996 Paul Mackerras. - * - * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner. - * {engebret|bergner}@us.ibm.com - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#undef DEBUG_PROM - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef CONFIG_LOGO_LINUX_CLUT224 -#include -extern const struct linux_logo logo_linux_clut224; -#endif - -/* - * Properties whose value is longer than this get excluded from our - * copy of the device tree. This value does need to be big enough to - * ensure that we don't lose things like the interrupt-map property - * on a PCI-PCI bridge. - */ -#define MAX_PROPERTY_LENGTH (1UL * 1024 * 1024) - -/* - * Eventually bump that one up - */ -#define DEVTREE_CHUNK_SIZE 0x100000 - -/* - * This is the size of the local memory reserve map that gets copied - * into the boot params passed to the kernel. That size is totally - * flexible as the kernel just reads the list until it encounters an - * entry with size 0, so it can be changed without breaking binary - * compatibility - */ -#define MEM_RESERVE_MAP_SIZE 8 - -/* - * prom_init() is called very early on, before the kernel text - * and data have been mapped to KERNELBASE. At this point the code - * is running at whatever address it has been loaded at, so - * references to extern and static variables must be relocated - * explicitly. The procedure reloc_offset() returns the address - * we're currently running at minus the address we were linked at. - * (Note that strings count as static variables.) - * - * Because OF may have mapped I/O devices into the area starting at - * KERNELBASE, particularly on CHRP machines, we can't safely call - * OF once the kernel has been mapped to KERNELBASE. Therefore all - * OF calls should be done within prom_init(), and prom_init() - * and all routines called within it must be careful to relocate - * references as necessary. - * - * Note that the bss is cleared *after* prom_init runs, so we have - * to make sure that any static or extern variables it accesses - * are put in the data segment. - */ - - -#define PROM_BUG() do { \ - prom_printf("kernel BUG at %s line 0x%x!\n", \ - RELOC(__FILE__), __LINE__); \ - __asm__ __volatile__(".long " BUG_ILLEGAL_INSTR); \ -} while (0) - -#ifdef DEBUG_PROM -#define prom_debug(x...) prom_printf(x) -#else -#define prom_debug(x...) -#endif - - -typedef u32 prom_arg_t; - -struct prom_args { - u32 service; - u32 nargs; - u32 nret; - prom_arg_t args[10]; - prom_arg_t *rets; /* Pointer to return values in args[16]. */ -}; - -struct prom_t { - unsigned long entry; - ihandle root; - ihandle chosen; - int cpu; - ihandle stdout; - ihandle disp_node; - struct prom_args args; - unsigned long version; - unsigned long root_size_cells; - unsigned long root_addr_cells; -}; - -struct pci_reg_property { - struct pci_address addr; - u32 size_hi; - u32 size_lo; -}; - -struct mem_map_entry { - u64 base; - u64 size; -}; - -typedef u32 cell_t; - -extern void __start(unsigned long r3, unsigned long r4, unsigned long r5); - -extern void enter_prom(struct prom_args *args, unsigned long entry); -extern void copy_and_flush(unsigned long dest, unsigned long src, - unsigned long size, unsigned long offset); - -extern unsigned long klimit; - -/* prom structure */ -static struct prom_t __initdata prom; - -#define PROM_SCRATCH_SIZE 256 - -static char __initdata of_stdout_device[256]; -static char __initdata prom_scratch[PROM_SCRATCH_SIZE]; - -static unsigned long __initdata dt_header_start; -static unsigned long __initdata dt_struct_start, dt_struct_end; -static unsigned long __initdata dt_string_start, dt_string_end; - -static unsigned long __initdata prom_initrd_start, prom_initrd_end; - -static int __initdata iommu_force_on; -static int __initdata ppc64_iommu_off; -static int __initdata of_platform; - -static char __initdata prom_cmd_line[COMMAND_LINE_SIZE]; - -static unsigned long __initdata prom_memory_limit; -static unsigned long __initdata prom_tce_alloc_start; -static unsigned long __initdata prom_tce_alloc_end; - -static unsigned long __initdata alloc_top; -static unsigned long __initdata alloc_top_high; -static unsigned long __initdata alloc_bottom; -static unsigned long __initdata rmo_top; -static unsigned long __initdata ram_top; - -static struct mem_map_entry __initdata mem_reserve_map[MEM_RESERVE_MAP_SIZE]; -static int __initdata mem_reserve_cnt; - -static cell_t __initdata regbuf[1024]; - - -#define MAX_CPU_THREADS 2 - -/* TO GO */ -#ifdef CONFIG_HMT -struct { - unsigned int pir; - unsigned int threadid; -} hmt_thread_data[NR_CPUS]; -#endif /* CONFIG_HMT */ - -/* - * This are used in calls to call_prom. The 4th and following - * arguments to call_prom should be 32-bit values. 64 bit values - * are truncated to 32 bits (and fortunately don't get interpreted - * as two arguments). - */ -#define ADDR(x) (u32) ((unsigned long)(x) - offset) - -/* - * Error results ... some OF calls will return "-1" on error, some - * will return 0, some will return either. To simplify, here are - * macros to use with any ihandle or phandle return value to check if - * it is valid - */ - -#define PROM_ERROR (-1u) -#define PHANDLE_VALID(p) ((p) != 0 && (p) != PROM_ERROR) -#define IHANDLE_VALID(i) ((i) != 0 && (i) != PROM_ERROR) - - -/* This is the one and *ONLY* place where we actually call open - * firmware from, since we need to make sure we're running in 32b - * mode when we do. We switch back to 64b mode upon return. - */ - -static int __init call_prom(const char *service, int nargs, int nret, ...) -{ - int i; - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - va_list list; - - _prom->args.service = ADDR(service); - _prom->args.nargs = nargs; - _prom->args.nret = nret; - _prom->args.rets = (prom_arg_t *)&(_prom->args.args[nargs]); - - va_start(list, nret); - for (i=0; i < nargs; i++) - _prom->args.args[i] = va_arg(list, prom_arg_t); - va_end(list); - - for (i=0; i < nret ;i++) - _prom->args.rets[i] = 0; - - enter_prom(&_prom->args, _prom->entry); - - return (nret > 0) ? _prom->args.rets[0] : 0; -} - - -static unsigned int __init prom_claim(unsigned long virt, unsigned long size, - unsigned long align) -{ - return (unsigned int)call_prom("claim", 3, 1, - (prom_arg_t)virt, (prom_arg_t)size, - (prom_arg_t)align); -} - -static void __init prom_print(const char *msg) -{ - const char *p, *q; - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - - if (_prom->stdout == 0) - return; - - for (p = msg; *p != 0; p = q) { - for (q = p; *q != 0 && *q != '\n'; ++q) - ; - if (q > p) - call_prom("write", 3, 1, _prom->stdout, p, q - p); - if (*q == 0) - break; - ++q; - call_prom("write", 3, 1, _prom->stdout, ADDR("\r\n"), 2); - } -} - - -static void __init prom_print_hex(unsigned long val) -{ - unsigned long offset = reloc_offset(); - int i, nibbles = sizeof(val)*2; - char buf[sizeof(val)*2+1]; - struct prom_t *_prom = PTRRELOC(&prom); - - for (i = nibbles-1; i >= 0; i--) { - buf[i] = (val & 0xf) + '0'; - if (buf[i] > '9') - buf[i] += ('a'-'0'-10); - val >>= 4; - } - buf[nibbles] = '\0'; - call_prom("write", 3, 1, _prom->stdout, buf, nibbles); -} - - -static void __init prom_printf(const char *format, ...) -{ - unsigned long offset = reloc_offset(); - const char *p, *q, *s; - va_list args; - unsigned long v; - struct prom_t *_prom = PTRRELOC(&prom); - - va_start(args, format); - for (p = PTRRELOC(format); *p != 0; p = q) { - for (q = p; *q != 0 && *q != '\n' && *q != '%'; ++q) - ; - if (q > p) - call_prom("write", 3, 1, _prom->stdout, p, q - p); - if (*q == 0) - break; - if (*q == '\n') { - ++q; - call_prom("write", 3, 1, _prom->stdout, - ADDR("\r\n"), 2); - continue; - } - ++q; - if (*q == 0) - break; - switch (*q) { - case 's': - ++q; - s = va_arg(args, const char *); - prom_print(s); - break; - case 'x': - ++q; - v = va_arg(args, unsigned long); - prom_print_hex(v); - break; - } - } -} - - -static void __init __attribute__((noreturn)) prom_panic(const char *reason) -{ - unsigned long offset = reloc_offset(); - - prom_print(PTRRELOC(reason)); - /* ToDo: should put up an SRC here */ - call_prom("exit", 0, 0); - - for (;;) /* should never get here */ - ; -} - - -static int __init prom_next_node(phandle *nodep) -{ - phandle node; - - if ((node = *nodep) != 0 - && (*nodep = call_prom("child", 1, 1, node)) != 0) - return 1; - if ((*nodep = call_prom("peer", 1, 1, node)) != 0) - return 1; - for (;;) { - if ((node = call_prom("parent", 1, 1, node)) == 0) - return 0; - if ((*nodep = call_prom("peer", 1, 1, node)) != 0) - return 1; - } -} - -static int __init prom_getprop(phandle node, const char *pname, - void *value, size_t valuelen) -{ - unsigned long offset = reloc_offset(); - - return call_prom("getprop", 4, 1, node, ADDR(pname), - (u32)(unsigned long) value, (u32) valuelen); -} - -static int __init prom_getproplen(phandle node, const char *pname) -{ - unsigned long offset = reloc_offset(); - - return call_prom("getproplen", 2, 1, node, ADDR(pname)); -} - -static int __init prom_setprop(phandle node, const char *pname, - void *value, size_t valuelen) -{ - unsigned long offset = reloc_offset(); - - return call_prom("setprop", 4, 1, node, ADDR(pname), - (u32)(unsigned long) value, (u32) valuelen); -} - -/* We can't use the standard versions because of RELOC headaches. */ -#define isxdigit(c) (('0' <= (c) && (c) <= '9') \ - || ('a' <= (c) && (c) <= 'f') \ - || ('A' <= (c) && (c) <= 'F')) - -#define isdigit(c) ('0' <= (c) && (c) <= '9') -#define islower(c) ('a' <= (c) && (c) <= 'z') -#define toupper(c) (islower(c) ? ((c) - 'a' + 'A') : (c)) - -unsigned long prom_strtoul(const char *cp, const char **endp) -{ - unsigned long result = 0, base = 10, value; - - if (*cp == '0') { - base = 8; - cp++; - if (toupper(*cp) == 'X') { - cp++; - base = 16; - } - } - - while (isxdigit(*cp) && - (value = isdigit(*cp) ? *cp - '0' : toupper(*cp) - 'A' + 10) < base) { - result = result * base + value; - cp++; - } - - if (endp) - *endp = cp; - - return result; -} - -unsigned long prom_memparse(const char *ptr, const char **retptr) -{ - unsigned long ret = prom_strtoul(ptr, retptr); - int shift = 0; - - /* - * We can't use a switch here because GCC *may* generate a - * jump table which won't work, because we're not running at - * the address we're linked at. - */ - if ('G' == **retptr || 'g' == **retptr) - shift = 30; - - if ('M' == **retptr || 'm' == **retptr) - shift = 20; - - if ('K' == **retptr || 'k' == **retptr) - shift = 10; - - if (shift) { - ret <<= shift; - (*retptr)++; - } - - return ret; -} - -/* - * Early parsing of the command line passed to the kernel, used for - * "mem=x" and the options that affect the iommu - */ -static void __init early_cmdline_parse(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - char *opt, *p; - int l = 0; - - RELOC(prom_cmd_line[0]) = 0; - p = RELOC(prom_cmd_line); - if ((long)_prom->chosen > 0) - l = prom_getprop(_prom->chosen, "bootargs", p, COMMAND_LINE_SIZE-1); -#ifdef CONFIG_CMDLINE - if (l == 0) /* dbl check */ - strlcpy(RELOC(prom_cmd_line), - RELOC(CONFIG_CMDLINE), sizeof(prom_cmd_line)); -#endif /* CONFIG_CMDLINE */ - prom_printf("command line: %s\n", RELOC(prom_cmd_line)); - - opt = strstr(RELOC(prom_cmd_line), RELOC("iommu=")); - if (opt) { - prom_printf("iommu opt is: %s\n", opt); - opt += 6; - while (*opt && *opt == ' ') - opt++; - if (!strncmp(opt, RELOC("off"), 3)) - RELOC(ppc64_iommu_off) = 1; - else if (!strncmp(opt, RELOC("force"), 5)) - RELOC(iommu_force_on) = 1; - } - - opt = strstr(RELOC(prom_cmd_line), RELOC("mem=")); - if (opt) { - opt += 4; - RELOC(prom_memory_limit) = prom_memparse(opt, (const char **)&opt); - /* Align to 16 MB == size of large page */ - RELOC(prom_memory_limit) = ALIGN(RELOC(prom_memory_limit), 0x1000000); - } -} - -/* - * To tell the firmware what our capabilities are, we have to pass - * it a fake 32-bit ELF header containing a couple of PT_NOTE sections - * that contain structures that contain the actual values. - */ -static struct fake_elf { - Elf32_Ehdr elfhdr; - Elf32_Phdr phdr[2]; - struct chrpnote { - u32 namesz; - u32 descsz; - u32 type; - char name[8]; /* "PowerPC" */ - struct chrpdesc { - u32 real_mode; - u32 real_base; - u32 real_size; - u32 virt_base; - u32 virt_size; - u32 load_base; - } chrpdesc; - } chrpnote; - struct rpanote { - u32 namesz; - u32 descsz; - u32 type; - char name[24]; /* "IBM,RPA-Client-Config" */ - struct rpadesc { - u32 lpar_affinity; - u32 min_rmo_size; - u32 min_rmo_percent; - u32 max_pft_size; - u32 splpar; - u32 min_load; - u32 new_mem_def; - u32 ignore_me; - } rpadesc; - } rpanote; -} fake_elf = { - .elfhdr = { - .e_ident = { 0x7f, 'E', 'L', 'F', - ELFCLASS32, ELFDATA2MSB, EV_CURRENT }, - .e_type = ET_EXEC, /* yeah right */ - .e_machine = EM_PPC, - .e_version = EV_CURRENT, - .e_phoff = offsetof(struct fake_elf, phdr), - .e_phentsize = sizeof(Elf32_Phdr), - .e_phnum = 2 - }, - .phdr = { - [0] = { - .p_type = PT_NOTE, - .p_offset = offsetof(struct fake_elf, chrpnote), - .p_filesz = sizeof(struct chrpnote) - }, [1] = { - .p_type = PT_NOTE, - .p_offset = offsetof(struct fake_elf, rpanote), - .p_filesz = sizeof(struct rpanote) - } - }, - .chrpnote = { - .namesz = sizeof("PowerPC"), - .descsz = sizeof(struct chrpdesc), - .type = 0x1275, - .name = "PowerPC", - .chrpdesc = { - .real_mode = ~0U, /* ~0 means "don't care" */ - .real_base = ~0U, - .real_size = ~0U, - .virt_base = ~0U, - .virt_size = ~0U, - .load_base = ~0U - }, - }, - .rpanote = { - .namesz = sizeof("IBM,RPA-Client-Config"), - .descsz = sizeof(struct rpadesc), - .type = 0x12759999, - .name = "IBM,RPA-Client-Config", - .rpadesc = { - .lpar_affinity = 0, - .min_rmo_size = 64, /* in megabytes */ - .min_rmo_percent = 0, - .max_pft_size = 48, /* 2^48 bytes max PFT size */ - .splpar = 1, - .min_load = ~0U, - .new_mem_def = 0 - } - } -}; - -static void __init prom_send_capabilities(void) -{ - unsigned long offset = reloc_offset(); - ihandle elfloader; - - elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader")); - if (elfloader == 0) { - prom_printf("couldn't open /packages/elf-loader\n"); - return; - } - call_prom("call-method", 3, 1, ADDR("process-elf-header"), - elfloader, ADDR(&fake_elf)); - call_prom("close", 1, 0, elfloader); -} - -/* - * Memory allocation strategy... our layout is normally: - * - * at 14Mb or more we vmlinux, then a gap and initrd. In some rare cases, initrd - * might end up beeing before the kernel though. We assume this won't override - * the final kernel at 0, we have no provision to handle that in this version, - * but it should hopefully never happen. - * - * alloc_top is set to the top of RMO, eventually shrink down if the TCEs overlap - * alloc_bottom is set to the top of kernel/initrd - * - * from there, allocations are done that way : rtas is allocated topmost, and - * the device-tree is allocated from the bottom. We try to grow the device-tree - * allocation as we progress. If we can't, then we fail, we don't currently have - * a facility to restart elsewhere, but that shouldn't be necessary neither - * - * Note that calls to reserve_mem have to be done explicitely, memory allocated - * with either alloc_up or alloc_down isn't automatically reserved. - */ - - -/* - * Allocates memory in the RMO upward from the kernel/initrd - * - * When align is 0, this is a special case, it means to allocate in place - * at the current location of alloc_bottom or fail (that is basically - * extending the previous allocation). Used for the device-tree flattening - */ -static unsigned long __init alloc_up(unsigned long size, unsigned long align) -{ - unsigned long offset = reloc_offset(); - unsigned long base = _ALIGN_UP(RELOC(alloc_bottom), align); - unsigned long addr = 0; - - prom_debug("alloc_up(%x, %x)\n", size, align); - if (RELOC(ram_top) == 0) - prom_panic("alloc_up() called with mem not initialized\n"); - - if (align) - base = _ALIGN_UP(RELOC(alloc_bottom), align); - else - base = RELOC(alloc_bottom); - - for(; (base + size) <= RELOC(alloc_top); - base = _ALIGN_UP(base + 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); - addr = (unsigned long)prom_claim(base, size, 0); - if (addr != PROM_ERROR) - break; - addr = 0; - if (align == 0) - break; - } - if (addr == 0) - return 0; - RELOC(alloc_bottom) = addr; - - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", RELOC(alloc_bottom)); - prom_debug(" alloc_top : %x\n", RELOC(alloc_top)); - prom_debug(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); - prom_debug(" rmo_top : %x\n", RELOC(rmo_top)); - prom_debug(" ram_top : %x\n", RELOC(ram_top)); - - return addr; -} - -/* - * Allocates memory downard, either from top of RMO, or if highmem - * is set, from the top of RAM. Note that this one doesn't handle - * failures. In does claim memory if highmem is not set. - */ -static unsigned long __init alloc_down(unsigned long size, unsigned long align, - int highmem) -{ - unsigned long offset = reloc_offset(); - unsigned long base, addr = 0; - - prom_debug("alloc_down(%x, %x, %s)\n", size, align, - highmem ? RELOC("(high)") : RELOC("(low)")); - if (RELOC(ram_top) == 0) - prom_panic("alloc_down() called with mem not initialized\n"); - - if (highmem) { - /* Carve out storage for the TCE table. */ - addr = _ALIGN_DOWN(RELOC(alloc_top_high) - size, align); - if (addr <= RELOC(alloc_bottom)) - return 0; - else { - /* Will we bump into the RMO ? If yes, check out that we - * didn't overlap existing allocations there, if we did, - * we are dead, we must be the first in town ! - */ - if (addr < RELOC(rmo_top)) { - /* Good, we are first */ - if (RELOC(alloc_top) == RELOC(rmo_top)) - RELOC(alloc_top) = RELOC(rmo_top) = addr; - else - return 0; - } - RELOC(alloc_top_high) = addr; - } - goto bail; - } - - base = _ALIGN_DOWN(RELOC(alloc_top) - size, align); - for(; base > RELOC(alloc_bottom); base = _ALIGN_DOWN(base - 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); - addr = (unsigned long)prom_claim(base, size, 0); - if (addr != PROM_ERROR) - break; - addr = 0; - } - if (addr == 0) - return 0; - RELOC(alloc_top) = addr; - - bail: - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", RELOC(alloc_bottom)); - prom_debug(" alloc_top : %x\n", RELOC(alloc_top)); - prom_debug(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); - prom_debug(" rmo_top : %x\n", RELOC(rmo_top)); - prom_debug(" ram_top : %x\n", RELOC(ram_top)); - - return addr; -} - -/* - * Parse a "reg" cell - */ -static unsigned long __init prom_next_cell(int s, cell_t **cellp) -{ - cell_t *p = *cellp; - unsigned long r = 0; - - /* Ignore more than 2 cells */ - while (s > 2) { - p++; - s--; - } - while (s) { - r <<= 32; - r |= *(p++); - s--; - } - - *cellp = p; - return r; -} - -/* - * Very dumb function for adding to the memory reserve list, but - * we don't need anything smarter at this point - * - * XXX Eventually check for collisions. They should NEVER happen - * if problems seem to show up, it would be a good start to track - * them down. - */ -static void reserve_mem(unsigned long base, unsigned long size) -{ - unsigned long offset = reloc_offset(); - unsigned long top = base + size; - unsigned long cnt = RELOC(mem_reserve_cnt); - - if (size == 0) - return; - - /* We need to always keep one empty entry so that we - * have our terminator with "size" set to 0 since we are - * dumb and just copy this entire array to the boot params - */ - base = _ALIGN_DOWN(base, PAGE_SIZE); - top = _ALIGN_UP(top, PAGE_SIZE); - size = top - base; - - if (cnt >= (MEM_RESERVE_MAP_SIZE - 1)) - prom_panic("Memory reserve map exhausted !\n"); - RELOC(mem_reserve_map)[cnt].base = base; - RELOC(mem_reserve_map)[cnt].size = size; - RELOC(mem_reserve_cnt) = cnt + 1; -} - -/* - * Initialize memory allocation mecanism, parse "memory" nodes and - * obtain that way the top of memory and RMO to setup out local allocator - */ -static void __init prom_init_mem(void) -{ - phandle node; - char *path, type[64]; - unsigned int plen; - cell_t *p, *endp; - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - - /* - * We iterate the memory nodes to find - * 1) top of RMO (first node) - * 2) top of memory - */ - prom_debug("root_addr_cells: %x\n", (long)_prom->root_addr_cells); - prom_debug("root_size_cells: %x\n", (long)_prom->root_size_cells); - - prom_debug("scanning memory:\n"); - path = RELOC(prom_scratch); - - for (node = 0; prom_next_node(&node); ) { - type[0] = 0; - prom_getprop(node, "device_type", type, sizeof(type)); - - if (strcmp(type, RELOC("memory"))) - continue; - - plen = prom_getprop(node, "reg", RELOC(regbuf), sizeof(regbuf)); - if (plen > sizeof(regbuf)) { - prom_printf("memory node too large for buffer !\n"); - plen = sizeof(regbuf); - } - p = RELOC(regbuf); - endp = p + (plen / sizeof(cell_t)); - -#ifdef DEBUG_PROM - memset(path, 0, PROM_SCRATCH_SIZE); - call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1); - prom_debug(" node %s :\n", path); -#endif /* DEBUG_PROM */ - - while ((endp - p) >= (_prom->root_addr_cells + _prom->root_size_cells)) { - unsigned long base, size; - - base = prom_next_cell(_prom->root_addr_cells, &p); - size = prom_next_cell(_prom->root_size_cells, &p); - - if (size == 0) - continue; - prom_debug(" %x %x\n", base, size); - if (base == 0) - RELOC(rmo_top) = size; - if ((base + size) > RELOC(ram_top)) - RELOC(ram_top) = base + size; - } - } - - RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(klimit) - offset + 0x4000); - - /* Check if we have an initrd after the kernel, if we do move our bottom - * point to after it - */ - if (RELOC(prom_initrd_start)) { - if (RELOC(prom_initrd_end) > RELOC(alloc_bottom)) - RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end)); - } - - /* - * If prom_memory_limit is set we reduce the upper limits *except* for - * alloc_top_high. This must be the real top of RAM so we can put - * TCE's up there. - */ - - RELOC(alloc_top_high) = RELOC(ram_top); - - if (RELOC(prom_memory_limit)) { - if (RELOC(prom_memory_limit) <= RELOC(alloc_bottom)) { - prom_printf("Ignoring mem=%x <= alloc_bottom.\n", - RELOC(prom_memory_limit)); - RELOC(prom_memory_limit) = 0; - } else if (RELOC(prom_memory_limit) >= RELOC(ram_top)) { - prom_printf("Ignoring mem=%x >= ram_top.\n", - RELOC(prom_memory_limit)); - RELOC(prom_memory_limit) = 0; - } else { - RELOC(ram_top) = RELOC(prom_memory_limit); - RELOC(rmo_top) = min(RELOC(rmo_top), RELOC(prom_memory_limit)); - } - } - - /* - * Setup our top alloc point, that is top of RMO or top of - * segment 0 when running non-LPAR. - */ - if ( RELOC(of_platform) == PLATFORM_PSERIES_LPAR ) - RELOC(alloc_top) = RELOC(rmo_top); - else - /* Some RS64 machines have buggy firmware where claims up at 1GB - * fails. Cap at 768MB as a workaround. Still plenty of room. - */ - RELOC(alloc_top) = RELOC(rmo_top) = min(0x30000000ul, RELOC(ram_top)); - - prom_printf("memory layout at init:\n"); - prom_printf(" memory_limit : %x (16 MB aligned)\n", RELOC(prom_memory_limit)); - prom_printf(" alloc_bottom : %x\n", RELOC(alloc_bottom)); - prom_printf(" alloc_top : %x\n", RELOC(alloc_top)); - prom_printf(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); - prom_printf(" rmo_top : %x\n", RELOC(rmo_top)); - prom_printf(" ram_top : %x\n", RELOC(ram_top)); -} - - -/* - * Allocate room for and instanciate RTAS - */ -static void __init prom_instantiate_rtas(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - phandle rtas_node; - ihandle rtas_inst; - u32 base, entry = 0; - u32 size = 0; - - prom_debug("prom_instantiate_rtas: start...\n"); - - rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas")); - prom_debug("rtas_node: %x\n", rtas_node); - if (!PHANDLE_VALID(rtas_node)) - return; - - prom_getprop(rtas_node, "rtas-size", &size, sizeof(size)); - if (size == 0) - return; - - base = alloc_down(size, PAGE_SIZE, 0); - if (base == 0) { - prom_printf("RTAS allocation failed !\n"); - return; - } - - rtas_inst = call_prom("open", 1, 1, ADDR("/rtas")); - if (!IHANDLE_VALID(rtas_inst)) { - prom_printf("opening rtas package failed"); - return; - } - - prom_printf("instantiating rtas at 0x%x ...", base); - - if (call_prom("call-method", 3, 2, - ADDR("instantiate-rtas"), - rtas_inst, base) != PROM_ERROR) { - entry = (long)_prom->args.rets[1]; - } - if (entry == 0) { - prom_printf(" failed\n"); - return; - } - prom_printf(" done\n"); - - reserve_mem(base, size); - - prom_setprop(rtas_node, "linux,rtas-base", &base, sizeof(base)); - prom_setprop(rtas_node, "linux,rtas-entry", &entry, sizeof(entry)); - - prom_debug("rtas base = 0x%x\n", base); - prom_debug("rtas entry = 0x%x\n", entry); - prom_debug("rtas size = 0x%x\n", (long)size); - - prom_debug("prom_instantiate_rtas: end...\n"); -} - - -/* - * Allocate room for and initialize TCE tables - */ -static void __init prom_initialize_tce_table(void) -{ - phandle node; - ihandle phb_node; - unsigned long offset = reloc_offset(); - char compatible[64], type[64], model[64]; - char *path = RELOC(prom_scratch); - u64 base, align; - u32 minalign, minsize; - u64 tce_entry, *tce_entryp; - u64 local_alloc_top, local_alloc_bottom; - u64 i; - - if (RELOC(ppc64_iommu_off)) - return; - - prom_debug("starting prom_initialize_tce_table\n"); - - /* Cache current top of allocs so we reserve a single block */ - local_alloc_top = RELOC(alloc_top_high); - local_alloc_bottom = local_alloc_top; - - /* Search all nodes looking for PHBs. */ - for (node = 0; prom_next_node(&node); ) { - compatible[0] = 0; - type[0] = 0; - model[0] = 0; - prom_getprop(node, "compatible", - compatible, sizeof(compatible)); - prom_getprop(node, "device_type", type, sizeof(type)); - prom_getprop(node, "model", model, sizeof(model)); - - if ((type[0] == 0) || (strstr(type, RELOC("pci")) == NULL)) - continue; - - /* Keep the old logic in tack to avoid regression. */ - if (compatible[0] != 0) { - if ((strstr(compatible, RELOC("python")) == NULL) && - (strstr(compatible, RELOC("Speedwagon")) == NULL) && - (strstr(compatible, RELOC("Winnipeg")) == NULL)) - continue; - } else if (model[0] != 0) { - if ((strstr(model, RELOC("ython")) == NULL) && - (strstr(model, RELOC("peedwagon")) == NULL) && - (strstr(model, RELOC("innipeg")) == NULL)) - continue; - } - - if (prom_getprop(node, "tce-table-minalign", &minalign, - sizeof(minalign)) == PROM_ERROR) - minalign = 0; - if (prom_getprop(node, "tce-table-minsize", &minsize, - sizeof(minsize)) == PROM_ERROR) - minsize = 4UL << 20; - - /* - * Even though we read what OF wants, we just set the table - * size to 4 MB. This is enough to map 2GB of PCI DMA space. - * By doing this, we avoid the pitfalls of trying to DMA to - * MMIO space and the DMA alias hole. - * - * On POWER4, firmware sets the TCE region by assuming - * each TCE table is 8MB. Using this memory for anything - * else will impact performance, so we always allocate 8MB. - * Anton - */ - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p)) - minsize = 8UL << 20; - else - minsize = 4UL << 20; - - /* Align to the greater of the align or size */ - align = max(minalign, minsize); - base = alloc_down(minsize, align, 1); - if (base == 0) - prom_panic("ERROR, cannot find space for TCE table.\n"); - if (base < local_alloc_bottom) - local_alloc_bottom = base; - - /* Save away the TCE table attributes for later use. */ - prom_setprop(node, "linux,tce-base", &base, sizeof(base)); - prom_setprop(node, "linux,tce-size", &minsize, sizeof(minsize)); - - /* It seems OF doesn't null-terminate the path :-( */ - memset(path, 0, sizeof(path)); - /* Call OF to setup the TCE hardware */ - if (call_prom("package-to-path", 3, 1, node, - path, PROM_SCRATCH_SIZE-1) == PROM_ERROR) { - prom_printf("package-to-path failed\n"); - } - - prom_debug("TCE table: %s\n", path); - prom_debug("\tnode = 0x%x\n", node); - prom_debug("\tbase = 0x%x\n", base); - prom_debug("\tsize = 0x%x\n", minsize); - - /* Initialize the table to have a one-to-one mapping - * over the allocated size. - */ - tce_entryp = (unsigned long *)base; - for (i = 0; i < (minsize >> 3) ;tce_entryp++, i++) { - tce_entry = (i << PAGE_SHIFT); - tce_entry |= 0x3; - *tce_entryp = tce_entry; - } - - prom_printf("opening PHB %s", path); - phb_node = call_prom("open", 1, 1, path); - if (phb_node == 0) - prom_printf("... failed\n"); - else - prom_printf("... done\n"); - - call_prom("call-method", 6, 0, ADDR("set-64-bit-addressing"), - phb_node, -1, minsize, - (u32) base, (u32) (base >> 32)); - call_prom("close", 1, 0, phb_node); - } - - reserve_mem(local_alloc_bottom, local_alloc_top - local_alloc_bottom); - - if (RELOC(prom_memory_limit)) { - /* - * We align the start to a 16MB boundary so we can map the TCE area - * using large pages if possible. The end should be the top of RAM - * so no need to align it. - */ - RELOC(prom_tce_alloc_start) = _ALIGN_DOWN(local_alloc_bottom, 0x1000000); - RELOC(prom_tce_alloc_end) = local_alloc_top; - } - - /* Flag the first invalid entry */ - prom_debug("ending prom_initialize_tce_table\n"); -} - -/* - * With CHRP SMP we need to use the OF to start the other - * processors so we can't wait until smp_boot_cpus (the OF is - * trashed by then) so we have to put the processors into - * a holding pattern controlled by the kernel (not OF) before - * we destroy the OF. - * - * This uses a chunk of low memory, puts some holding pattern - * code there and sends the other processors off to there until - * smp_boot_cpus tells them to do something. The holding pattern - * checks that address until its cpu # is there, when it is that - * cpu jumps to __secondary_start(). smp_boot_cpus() takes care - * of setting those values. - * - * We also use physical address 0x4 here to tell when a cpu - * is in its holding pattern code. - * - * Fixup comment... DRENG / PPPBBB - Peter - * - * -- Cort - */ -static void __init prom_hold_cpus(void) -{ - unsigned long i; - unsigned int reg; - phandle node; - unsigned long offset = reloc_offset(); - char type[64]; - int cpuid = 0; - unsigned int interrupt_server[MAX_CPU_THREADS]; - unsigned int cpu_threads, hw_cpu_num; - int propsize; - extern void __secondary_hold(void); - extern unsigned long __secondary_hold_spinloop; - extern unsigned long __secondary_hold_acknowledge; - unsigned long *spinloop - = (void *)virt_to_abs(&__secondary_hold_spinloop); - unsigned long *acknowledge - = (void *)virt_to_abs(&__secondary_hold_acknowledge); - unsigned long secondary_hold - = virt_to_abs(*PTRRELOC((unsigned long *)__secondary_hold)); - struct prom_t *_prom = PTRRELOC(&prom); - - prom_debug("prom_hold_cpus: start...\n"); - prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); - prom_debug(" 1) *spinloop = 0x%x\n", *spinloop); - prom_debug(" 1) acknowledge = 0x%x\n", - (unsigned long)acknowledge); - prom_debug(" 1) *acknowledge = 0x%x\n", *acknowledge); - prom_debug(" 1) secondary_hold = 0x%x\n", secondary_hold); - - /* Set the common spinloop variable, so all of the secondary cpus - * will block when they are awakened from their OF spinloop. - * This must occur for both SMP and non SMP kernels, since OF will - * be trashed when we move the kernel. - */ - *spinloop = 0; - -#ifdef CONFIG_HMT - for (i=0; i < NR_CPUS; i++) { - RELOC(hmt_thread_data)[i].pir = 0xdeadbeef; - } -#endif - /* look for cpus */ - for (node = 0; prom_next_node(&node); ) { - type[0] = 0; - prom_getprop(node, "device_type", type, sizeof(type)); - if (strcmp(type, RELOC("cpu")) != 0) - continue; - - /* Skip non-configured cpus. */ - if (prom_getprop(node, "status", type, sizeof(type)) > 0) - if (strcmp(type, RELOC("okay")) != 0) - continue; - - reg = -1; - prom_getprop(node, "reg", ®, sizeof(reg)); - - prom_debug("\ncpuid = 0x%x\n", cpuid); - prom_debug("cpu hw idx = 0x%x\n", reg); - - /* Init the acknowledge var which will be reset by - * the secondary cpu when it awakens from its OF - * spinloop. - */ - *acknowledge = (unsigned long)-1; - - propsize = prom_getprop(node, "ibm,ppc-interrupt-server#s", - &interrupt_server, - sizeof(interrupt_server)); - if (propsize < 0) { - /* no property. old hardware has no SMT */ - cpu_threads = 1; - interrupt_server[0] = reg; /* fake it with phys id */ - } else { - /* We have a threaded processor */ - cpu_threads = propsize / sizeof(u32); - if (cpu_threads > MAX_CPU_THREADS) { - prom_printf("SMT: too many threads!\n" - "SMT: found %x, max is %x\n", - cpu_threads, MAX_CPU_THREADS); - cpu_threads = 1; /* ToDo: panic? */ - } - } - - hw_cpu_num = interrupt_server[0]; - if (hw_cpu_num != _prom->cpu) { - /* Primary Thread of non-boot cpu */ - prom_printf("%x : starting cpu hw idx %x... ", cpuid, reg); - call_prom("start-cpu", 3, 0, node, - secondary_hold, reg); - - for ( i = 0 ; (i < 100000000) && - (*acknowledge == ((unsigned long)-1)); i++ ) - mb(); - - if (*acknowledge == reg) { - prom_printf("done\n"); - /* We have to get every CPU out of OF, - * even if we never start it. */ - if (cpuid >= NR_CPUS) - goto next; - } else { - prom_printf("failed: %x\n", *acknowledge); - } - } -#ifdef CONFIG_SMP - else - prom_printf("%x : boot cpu %x\n", cpuid, reg); -#endif -next: -#ifdef CONFIG_SMP - /* Init paca for secondary threads. They start later. */ - for (i=1; i < cpu_threads; i++) { - cpuid++; - if (cpuid >= NR_CPUS) - continue; - } -#endif /* CONFIG_SMP */ - cpuid++; - } -#ifdef CONFIG_HMT - /* Only enable HMT on processors that provide support. */ - if (__is_processor(PV_PULSAR) || - __is_processor(PV_ICESTAR) || - __is_processor(PV_SSTAR)) { - prom_printf(" starting secondary threads\n"); - - for (i = 0; i < NR_CPUS; i += 2) { - if (!cpu_online(i)) - continue; - - if (i == 0) { - unsigned long pir = mfspr(SPRN_PIR); - if (__is_processor(PV_PULSAR)) { - RELOC(hmt_thread_data)[i].pir = - pir & 0x1f; - } else { - RELOC(hmt_thread_data)[i].pir = - pir & 0x3ff; - } - } - } - } else { - prom_printf("Processor is not HMT capable\n"); - } -#endif - - if (cpuid > NR_CPUS) - prom_printf("WARNING: maximum CPUs (" __stringify(NR_CPUS) - ") exceeded: ignoring extras\n"); - - prom_debug("prom_hold_cpus: end...\n"); -} - - -static void __init prom_init_client_services(unsigned long pp) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - - /* Get a handle to the prom entry point before anything else */ - _prom->entry = pp; - - /* Init default value for phys size */ - _prom->root_size_cells = 1; - _prom->root_addr_cells = 2; - - /* get a handle for the stdout device */ - _prom->chosen = call_prom("finddevice", 1, 1, ADDR("/chosen")); - if (!PHANDLE_VALID(_prom->chosen)) - prom_panic("cannot find chosen"); /* msg won't be printed :( */ - - /* get device tree root */ - _prom->root = call_prom("finddevice", 1, 1, ADDR("/")); - if (!PHANDLE_VALID(_prom->root)) - prom_panic("cannot find device tree root"); /* msg won't be printed :( */ -} - -static void __init prom_init_stdout(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - char *path = RELOC(of_stdout_device); - char type[16]; - u32 val; - - if (prom_getprop(_prom->chosen, "stdout", &val, sizeof(val)) <= 0) - prom_panic("cannot find stdout"); - - _prom->stdout = val; - - /* Get the full OF pathname of the stdout device */ - memset(path, 0, 256); - call_prom("instance-to-path", 3, 1, _prom->stdout, path, 255); - val = call_prom("instance-to-package", 1, 1, _prom->stdout); - prom_setprop(_prom->chosen, "linux,stdout-package", &val, sizeof(val)); - prom_printf("OF stdout device is: %s\n", RELOC(of_stdout_device)); - prom_setprop(_prom->chosen, "linux,stdout-path", - RELOC(of_stdout_device), strlen(RELOC(of_stdout_device))+1); - - /* If it's a display, note it */ - memset(type, 0, sizeof(type)); - prom_getprop(val, "device_type", type, sizeof(type)); - if (strcmp(type, RELOC("display")) == 0) { - _prom->disp_node = val; - prom_setprop(val, "linux,boot-display", NULL, 0); - } -} - -static void __init prom_close_stdin(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - ihandle val; - - if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) - call_prom("close", 1, 0, val); -} - -static int __init prom_find_machine_type(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - char compat[256]; - int len, i = 0; - phandle rtas; - - len = prom_getprop(_prom->root, "compatible", - compat, sizeof(compat)-1); - if (len > 0) { - compat[len] = 0; - while (i < len) { - char *p = &compat[i]; - int sl = strlen(p); - if (sl == 0) - break; - if (strstr(p, RELOC("Power Macintosh")) || - strstr(p, RELOC("MacRISC4"))) - return PLATFORM_POWERMAC; - if (strstr(p, RELOC("Momentum,Maple"))) - return PLATFORM_MAPLE; - i += sl + 1; - } - } - /* Default to pSeries. We need to know if we are running LPAR */ - rtas = call_prom("finddevice", 1, 1, ADDR("/rtas")); - if (PHANDLE_VALID(rtas)) { - int x = prom_getproplen(rtas, "ibm,hypertas-functions"); - if (x != PROM_ERROR) { - prom_printf("Hypertas detected, assuming LPAR !\n"); - return PLATFORM_PSERIES_LPAR; - } - } - return PLATFORM_PSERIES; -} - -static int __init prom_set_color(ihandle ih, int i, int r, int g, int b) -{ - unsigned long offset = reloc_offset(); - - return call_prom("call-method", 6, 1, ADDR("color!"), ih, i, b, g, r); -} - -/* - * If we have a display that we don't know how to drive, - * we will want to try to execute OF's open method for it - * later. However, OF will probably fall over if we do that - * we've taken over the MMU. - * So we check whether we will need to open the display, - * and if so, open it now. - */ -static void __init prom_check_displays(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - char type[16], *path; - phandle node; - ihandle ih; - int i; - - static unsigned char default_colors[] = { - 0x00, 0x00, 0x00, - 0x00, 0x00, 0xaa, - 0x00, 0xaa, 0x00, - 0x00, 0xaa, 0xaa, - 0xaa, 0x00, 0x00, - 0xaa, 0x00, 0xaa, - 0xaa, 0xaa, 0x00, - 0xaa, 0xaa, 0xaa, - 0x55, 0x55, 0x55, - 0x55, 0x55, 0xff, - 0x55, 0xff, 0x55, - 0x55, 0xff, 0xff, - 0xff, 0x55, 0x55, - 0xff, 0x55, 0xff, - 0xff, 0xff, 0x55, - 0xff, 0xff, 0xff - }; - const unsigned char *clut; - - prom_printf("Looking for displays\n"); - for (node = 0; prom_next_node(&node); ) { - memset(type, 0, sizeof(type)); - prom_getprop(node, "device_type", type, sizeof(type)); - if (strcmp(type, RELOC("display")) != 0) - continue; - - /* It seems OF doesn't null-terminate the path :-( */ - path = RELOC(prom_scratch); - memset(path, 0, PROM_SCRATCH_SIZE); - - /* - * leave some room at the end of the path for appending extra - * arguments - */ - if (call_prom("package-to-path", 3, 1, node, path, - PROM_SCRATCH_SIZE-10) == PROM_ERROR) - continue; - prom_printf("found display : %s, opening ... ", path); - - ih = call_prom("open", 1, 1, path); - if (ih == 0) { - prom_printf("failed\n"); - continue; - } - - /* Success */ - prom_printf("done\n"); - prom_setprop(node, "linux,opened", NULL, 0); - - /* - * stdout wasn't a display node, pick the first we can find - * for btext - */ - if (_prom->disp_node == 0) - _prom->disp_node = node; - - /* Setup a useable color table when the appropriate - * method is available. Should update this to set-colors */ - clut = RELOC(default_colors); - for (i = 0; i < 32; i++, clut += 3) - if (prom_set_color(ih, i, clut[0], clut[1], - clut[2]) != 0) - break; - -#ifdef CONFIG_LOGO_LINUX_CLUT224 - clut = PTRRELOC(RELOC(logo_linux_clut224.clut)); - for (i = 0; i < RELOC(logo_linux_clut224.clutsize); i++, clut += 3) - if (prom_set_color(ih, i + 32, clut[0], clut[1], - clut[2]) != 0) - break; -#endif /* CONFIG_LOGO_LINUX_CLUT224 */ - } -} - - -/* Return (relocated) pointer to this much memory: moves initrd if reqd. */ -static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end, - unsigned long needed, unsigned long align) -{ - unsigned long offset = reloc_offset(); - void *ret; - - *mem_start = _ALIGN(*mem_start, align); - while ((*mem_start + needed) > *mem_end) { - unsigned long room, chunk; - - prom_debug("Chunk exhausted, claiming more at %x...\n", - RELOC(alloc_bottom)); - room = RELOC(alloc_top) - RELOC(alloc_bottom); - if (room > DEVTREE_CHUNK_SIZE) - room = DEVTREE_CHUNK_SIZE; - if (room < PAGE_SIZE) - prom_panic("No memory for flatten_device_tree (no room)"); - chunk = alloc_up(room, 0); - if (chunk == 0) - prom_panic("No memory for flatten_device_tree (claim failed)"); - *mem_end = RELOC(alloc_top); - } - - ret = (void *)*mem_start; - *mem_start += needed; - - return ret; -} - -#define dt_push_token(token, mem_start, mem_end) \ - do { *((u32 *)make_room(mem_start, mem_end, 4, 4)) = token; } while(0) - -static unsigned long __init dt_find_string(char *str) -{ - unsigned long offset = reloc_offset(); - char *s, *os; - - s = os = (char *)RELOC(dt_string_start); - s += 4; - while (s < (char *)RELOC(dt_string_end)) { - if (strcmp(s, str) == 0) - return s - os; - s += strlen(s) + 1; - } - return 0; -} - -/* - * The Open Firmware 1275 specification states properties must be 31 bytes or - * less, however not all firmwares obey this. Make it 64 bytes to be safe. - */ -#define MAX_PROPERTY_NAME 64 - -static void __init scan_dt_build_strings(phandle node, - unsigned long *mem_start, - unsigned long *mem_end) -{ - unsigned long offset = reloc_offset(); - char *prev_name, *namep, *sstart; - unsigned long soff; - phandle child; - - sstart = (char *)RELOC(dt_string_start); - - /* get and store all property names */ - prev_name = RELOC(""); - for (;;) { - /* 64 is max len of name including nul. */ - namep = make_room(mem_start, mem_end, MAX_PROPERTY_NAME, 1); - if (call_prom("nextprop", 3, 1, node, prev_name, namep) != 1) { - /* No more nodes: unwind alloc */ - *mem_start = (unsigned long)namep; - break; - } - - /* skip "name" */ - if (strcmp(namep, RELOC("name")) == 0) { - *mem_start = (unsigned long)namep; - prev_name = RELOC("name"); - continue; - } - /* get/create string entry */ - soff = dt_find_string(namep); - if (soff != 0) { - *mem_start = (unsigned long)namep; - namep = sstart + soff; - } else { - /* Trim off some if we can */ - *mem_start = (unsigned long)namep + strlen(namep) + 1; - RELOC(dt_string_end) = *mem_start; - } - prev_name = namep; - } - - /* do all our children */ - child = call_prom("child", 1, 1, node); - while (child != 0) { - scan_dt_build_strings(child, mem_start, mem_end); - child = call_prom("peer", 1, 1, child); - } -} - -static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, - unsigned long *mem_end) -{ - phandle child; - char *namep, *prev_name, *sstart, *p, *ep, *lp, *path; - unsigned long soff; - unsigned char *valp; - unsigned long offset = reloc_offset(); - static char pname[MAX_PROPERTY_NAME]; - int l; - - dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end); - - /* get the node's full name */ - namep = (char *)*mem_start; - l = call_prom("package-to-path", 3, 1, node, - namep, *mem_end - *mem_start); - if (l >= 0) { - /* Didn't fit? Get more room. */ - if ((l+1) > (*mem_end - *mem_start)) { - namep = make_room(mem_start, mem_end, l+1, 1); - call_prom("package-to-path", 3, 1, node, namep, l); - } - namep[l] = '\0'; - - /* Fixup an Apple bug where they have bogus \0 chars in the - * middle of the path in some properties - */ - for (p = namep, ep = namep + l; p < ep; p++) - if (*p == '\0') { - memmove(p, p+1, ep - p); - ep--; l--; p--; - } - - /* now try to extract the unit name in that mess */ - for (p = namep, lp = NULL; *p; p++) - if (*p == '/') - lp = p + 1; - if (lp != NULL) - memmove(namep, lp, strlen(lp) + 1); - *mem_start = _ALIGN(((unsigned long) namep) + - strlen(namep) + 1, 4); - } - - /* get it again for debugging */ - path = RELOC(prom_scratch); - memset(path, 0, PROM_SCRATCH_SIZE); - call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1); - - /* get and store all properties */ - prev_name = RELOC(""); - sstart = (char *)RELOC(dt_string_start); - for (;;) { - if (call_prom("nextprop", 3, 1, node, prev_name, - RELOC(pname)) != 1) - break; - - /* skip "name" */ - if (strcmp(RELOC(pname), RELOC("name")) == 0) { - prev_name = RELOC("name"); - continue; - } - - /* find string offset */ - soff = dt_find_string(RELOC(pname)); - if (soff == 0) { - prom_printf("WARNING: Can't find string index for" - " <%s>, node %s\n", RELOC(pname), path); - break; - } - prev_name = sstart + soff; - - /* get length */ - l = call_prom("getproplen", 2, 1, node, RELOC(pname)); - - /* sanity checks */ - if (l == PROM_ERROR) - continue; - if (l > MAX_PROPERTY_LENGTH) { - prom_printf("WARNING: ignoring large property "); - /* It seems OF doesn't null-terminate the path :-( */ - prom_printf("[%s] ", path); - prom_printf("%s length 0x%x\n", RELOC(pname), l); - continue; - } - - /* push property head */ - dt_push_token(OF_DT_PROP, mem_start, mem_end); - dt_push_token(l, mem_start, mem_end); - dt_push_token(soff, mem_start, mem_end); - - /* push property content */ - valp = make_room(mem_start, mem_end, l, 4); - call_prom("getprop", 4, 1, node, RELOC(pname), valp, l); - *mem_start = _ALIGN(*mem_start, 4); - } - - /* Add a "linux,phandle" property. */ - soff = dt_find_string(RELOC("linux,phandle")); - if (soff == 0) - prom_printf("WARNING: Can't find string index for" - " node %s\n", path); - else { - dt_push_token(OF_DT_PROP, mem_start, mem_end); - dt_push_token(4, mem_start, mem_end); - dt_push_token(soff, mem_start, mem_end); - valp = make_room(mem_start, mem_end, 4, 4); - *(u32 *)valp = node; - } - - /* do all our children */ - child = call_prom("child", 1, 1, node); - while (child != 0) { - scan_dt_build_struct(child, mem_start, mem_end); - child = call_prom("peer", 1, 1, child); - } - - dt_push_token(OF_DT_END_NODE, mem_start, mem_end); -} - -static void __init flatten_device_tree(void) -{ - phandle root; - unsigned long offset = reloc_offset(); - unsigned long mem_start, mem_end, room; - struct boot_param_header *hdr; - struct prom_t *_prom = PTRRELOC(&prom); - char *namep; - u64 *rsvmap; - - /* - * Check how much room we have between alloc top & bottom (+/- a - * few pages), crop to 4Mb, as this is our "chuck" size - */ - room = RELOC(alloc_top) - RELOC(alloc_bottom) - 0x4000; - if (room > DEVTREE_CHUNK_SIZE) - room = DEVTREE_CHUNK_SIZE; - prom_debug("starting device tree allocs at %x\n", RELOC(alloc_bottom)); - - /* Now try to claim that */ - mem_start = (unsigned long)alloc_up(room, PAGE_SIZE); - if (mem_start == 0) - prom_panic("Can't allocate initial device-tree chunk\n"); - mem_end = RELOC(alloc_top); - - /* Get root of tree */ - root = call_prom("peer", 1, 1, (phandle)0); - if (root == (phandle)0) - prom_panic ("couldn't get device tree root\n"); - - /* Build header and make room for mem rsv map */ - mem_start = _ALIGN(mem_start, 4); - hdr = make_room(&mem_start, &mem_end, - sizeof(struct boot_param_header), 4); - RELOC(dt_header_start) = (unsigned long)hdr; - rsvmap = make_room(&mem_start, &mem_end, sizeof(mem_reserve_map), 8); - - /* Start of strings */ - mem_start = PAGE_ALIGN(mem_start); - RELOC(dt_string_start) = mem_start; - mem_start += 4; /* hole */ - - /* Add "linux,phandle" in there, we'll need it */ - namep = make_room(&mem_start, &mem_end, 16, 1); - strcpy(namep, RELOC("linux,phandle")); - mem_start = (unsigned long)namep + strlen(namep) + 1; - - /* Build string array */ - prom_printf("Building dt strings...\n"); - scan_dt_build_strings(root, &mem_start, &mem_end); - RELOC(dt_string_end) = mem_start; - - /* Build structure */ - mem_start = PAGE_ALIGN(mem_start); - RELOC(dt_struct_start) = mem_start; - prom_printf("Building dt structure...\n"); - scan_dt_build_struct(root, &mem_start, &mem_end); - dt_push_token(OF_DT_END, &mem_start, &mem_end); - RELOC(dt_struct_end) = PAGE_ALIGN(mem_start); - - /* Finish header */ - hdr->boot_cpuid_phys = _prom->cpu; - hdr->magic = OF_DT_HEADER; - hdr->totalsize = RELOC(dt_struct_end) - RELOC(dt_header_start); - hdr->off_dt_struct = RELOC(dt_struct_start) - RELOC(dt_header_start); - hdr->off_dt_strings = RELOC(dt_string_start) - RELOC(dt_header_start); - hdr->dt_strings_size = RELOC(dt_string_end) - RELOC(dt_string_start); - hdr->off_mem_rsvmap = ((unsigned long)rsvmap) - RELOC(dt_header_start); - hdr->version = OF_DT_VERSION; - /* Version 16 is not backward compatible */ - hdr->last_comp_version = 0x10; - - /* Reserve the whole thing and copy the reserve map in, we - * also bump mem_reserve_cnt to cause further reservations to - * fail since it's too late. - */ - reserve_mem(RELOC(dt_header_start), hdr->totalsize); - memcpy(rsvmap, RELOC(mem_reserve_map), sizeof(mem_reserve_map)); - -#ifdef DEBUG_PROM - { - int i; - prom_printf("reserved memory map:\n"); - for (i = 0; i < RELOC(mem_reserve_cnt); i++) - prom_printf(" %x - %x\n", RELOC(mem_reserve_map)[i].base, - RELOC(mem_reserve_map)[i].size); - } -#endif - RELOC(mem_reserve_cnt) = MEM_RESERVE_MAP_SIZE; - - prom_printf("Device tree strings 0x%x -> 0x%x\n", - RELOC(dt_string_start), RELOC(dt_string_end)); - prom_printf("Device tree struct 0x%x -> 0x%x\n", - RELOC(dt_struct_start), RELOC(dt_struct_end)); - -} - - -static void __init fixup_device_tree(void) -{ - unsigned long offset = reloc_offset(); - phandle u3, i2c, mpic; - u32 u3_rev; - u32 interrupts[2]; - u32 parent; - - /* Some G5s have a missing interrupt definition, fix it up here */ - u3 = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000")); - if (!PHANDLE_VALID(u3)) - return; - i2c = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/i2c@f8001000")); - if (!PHANDLE_VALID(i2c)) - return; - mpic = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/mpic@f8040000")); - if (!PHANDLE_VALID(mpic)) - return; - - /* check if proper rev of u3 */ - if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev)) - == PROM_ERROR) - return; - if (u3_rev < 0x35 || u3_rev > 0x39) - return; - /* does it need fixup ? */ - if (prom_getproplen(i2c, "interrupts") > 0) - return; - - prom_printf("fixing up bogus interrupts for u3 i2c...\n"); - - /* interrupt on this revision of u3 is number 0 and level */ - interrupts[0] = 0; - interrupts[1] = 1; - prom_setprop(i2c, "interrupts", &interrupts, sizeof(interrupts)); - parent = (u32)mpic; - prom_setprop(i2c, "interrupt-parent", &parent, sizeof(parent)); -} - - -static void __init prom_find_boot_cpu(void) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - u32 getprop_rval; - ihandle prom_cpu; - phandle cpu_pkg; - - if (prom_getprop(_prom->chosen, "cpu", &prom_cpu, sizeof(prom_cpu)) <= 0) - prom_panic("cannot find boot cpu"); - - cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); - - prom_getprop(cpu_pkg, "reg", &getprop_rval, sizeof(getprop_rval)); - _prom->cpu = getprop_rval; - - prom_debug("Booting CPU hw index = 0x%x\n", _prom->cpu); -} - -static void __init prom_check_initrd(unsigned long r3, unsigned long r4) -{ -#ifdef CONFIG_BLK_DEV_INITRD - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - - if ( r3 && r4 && r4 != 0xdeadbeef) { - u64 val; - - RELOC(prom_initrd_start) = (r3 >= KERNELBASE) ? __pa(r3) : r3; - RELOC(prom_initrd_end) = RELOC(prom_initrd_start) + r4; - - val = (u64)RELOC(prom_initrd_start); - prom_setprop(_prom->chosen, "linux,initrd-start", &val, sizeof(val)); - val = (u64)RELOC(prom_initrd_end); - prom_setprop(_prom->chosen, "linux,initrd-end", &val, sizeof(val)); - - reserve_mem(RELOC(prom_initrd_start), - RELOC(prom_initrd_end) - RELOC(prom_initrd_start)); - - prom_debug("initrd_start=0x%x\n", RELOC(prom_initrd_start)); - prom_debug("initrd_end=0x%x\n", RELOC(prom_initrd_end)); - } -#endif /* CONFIG_BLK_DEV_INITRD */ -} - -/* - * We enter here early on, when the Open Firmware prom is still - * handling exceptions and the MMU hash table for us. - */ - -unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long pp, - unsigned long r6, unsigned long r7) -{ - unsigned long offset = reloc_offset(); - struct prom_t *_prom = PTRRELOC(&prom); - unsigned long phys = KERNELBASE - offset; - u32 getprop_rval; - - /* - * First zero the BSS - */ - memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start); - - /* - * Init interface to Open Firmware, get some node references, - * like /chosen - */ - prom_init_client_services(pp); - - /* - * Init prom stdout device - */ - prom_init_stdout(); - prom_debug("klimit=0x%x\n", RELOC(klimit)); - prom_debug("offset=0x%x\n", offset); - - /* - * Check for an initrd - */ - prom_check_initrd(r3, r4); - - /* - * Get default machine type. At this point, we do not differenciate - * between pSeries SMP and pSeries LPAR - */ - RELOC(of_platform) = prom_find_machine_type(); - getprop_rval = RELOC(of_platform); - prom_setprop(_prom->chosen, "linux,platform", - &getprop_rval, sizeof(getprop_rval)); - - /* - * On pSeries, inform the firmware about our capabilities - */ - if (RELOC(of_platform) == PLATFORM_PSERIES || - RELOC(of_platform) == PLATFORM_PSERIES_LPAR) - prom_send_capabilities(); - - /* - * On pSeries and Cell, copy the CPU hold code - */ - if (RELOC(of_platform) & (PLATFORM_PSERIES | PLATFORM_CELL)) - copy_and_flush(0, KERNELBASE - offset, 0x100, 0); - - /* - * Get memory cells format - */ - getprop_rval = 1; - prom_getprop(_prom->root, "#size-cells", - &getprop_rval, sizeof(getprop_rval)); - _prom->root_size_cells = getprop_rval; - getprop_rval = 2; - prom_getprop(_prom->root, "#address-cells", - &getprop_rval, sizeof(getprop_rval)); - _prom->root_addr_cells = getprop_rval; - - /* - * Do early parsing of command line - */ - early_cmdline_parse(); - - /* - * Initialize memory management within prom_init - */ - prom_init_mem(); - - /* - * Determine which cpu is actually running right _now_ - */ - prom_find_boot_cpu(); - - /* - * Initialize display devices - */ - prom_check_displays(); - - /* - * Initialize IOMMU (TCE tables) on pSeries. Do that before anything else - * that uses the allocator, we need to make sure we get the top of memory - * available for us here... - */ - if (RELOC(of_platform) == PLATFORM_PSERIES) - prom_initialize_tce_table(); - - /* - * On non-powermacs, try to instantiate RTAS and puts all CPUs - * in spin-loops. PowerMacs don't have a working RTAS and use - * a different way to spin CPUs - */ - if (RELOC(of_platform) != PLATFORM_POWERMAC) { - prom_instantiate_rtas(); - prom_hold_cpus(); - } - - /* - * Fill in some infos for use by the kernel later on - */ - if (RELOC(ppc64_iommu_off)) - prom_setprop(_prom->chosen, "linux,iommu-off", NULL, 0); - - if (RELOC(iommu_force_on)) - prom_setprop(_prom->chosen, "linux,iommu-force-on", NULL, 0); - - if (RELOC(prom_memory_limit)) - prom_setprop(_prom->chosen, "linux,memory-limit", - PTRRELOC(&prom_memory_limit), sizeof(RELOC(prom_memory_limit))); - - if (RELOC(prom_tce_alloc_start)) { - prom_setprop(_prom->chosen, "linux,tce-alloc-start", - PTRRELOC(&prom_tce_alloc_start), sizeof(RELOC(prom_tce_alloc_start))); - prom_setprop(_prom->chosen, "linux,tce-alloc-end", - PTRRELOC(&prom_tce_alloc_end), sizeof(RELOC(prom_tce_alloc_end))); - } - - /* - * Fixup any known bugs in the device-tree - */ - fixup_device_tree(); - - /* - * Now finally create the flattened device-tree - */ - prom_printf("copying OF device tree ...\n"); - flatten_device_tree(); - - /* in case stdin is USB and still active on IBM machines... */ - prom_close_stdin(); - - /* - * Call OF "quiesce" method to shut down pending DMA's from - * devices etc... - */ - prom_printf("Calling quiesce ...\n"); - call_prom("quiesce", 0, 0); - - /* - * And finally, call the kernel passing it the flattened device - * tree and NULL as r5, thus triggering the new entry point which - * is common to us and kexec - */ - prom_printf("returning from prom_init\n"); - prom_debug("->dt_header_start=0x%x\n", RELOC(dt_header_start)); - prom_debug("->phys=0x%x\n", phys); - - __start(RELOC(dt_header_start), phys, 0); - - return 0; -} - diff --git a/arch/ppc64/kernel/semaphore.c b/arch/ppc64/kernel/semaphore.c deleted file mode 100644 index a1c1db573e9c..000000000000 --- a/arch/ppc64/kernel/semaphore.c +++ /dev/null @@ -1,136 +0,0 @@ -/* - * - * - * PowerPC-specific semaphore code. - * - * Copyright (C) 1999 Cort Dougan - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * April 2001 - Reworked by Paul Mackerras - * to eliminate the SMP races in the old version between the updates - * of `count' and `waking'. Now we use negative `count' values to - * indicate that some process(es) are waiting for the semaphore. - */ - -#include -#include -#include - -#include -#include -#include - -/* - * Atomically update sem->count. - * This does the equivalent of the following: - * - * old_count = sem->count; - * tmp = MAX(old_count, 0) + incr; - * sem->count = tmp; - * return old_count; - */ -static inline int __sem_update_count(struct semaphore *sem, int incr) -{ - int old_count, tmp; - - __asm__ __volatile__("\n" -"1: lwarx %0,0,%3\n" -" srawi %1,%0,31\n" -" andc %1,%0,%1\n" -" add %1,%1,%4\n" -" stwcx. %1,0,%3\n" -" bne 1b" - : "=&r" (old_count), "=&r" (tmp), "=m" (sem->count) - : "r" (&sem->count), "r" (incr), "m" (sem->count) - : "cc"); - - return old_count; -} - -void __up(struct semaphore *sem) -{ - /* - * Note that we incremented count in up() before we came here, - * but that was ineffective since the result was <= 0, and - * any negative value of count is equivalent to 0. - * This ends up setting count to 1, unless count is now > 0 - * (i.e. because some other cpu has called up() in the meantime), - * in which case we just increment count. - */ - __sem_update_count(sem, 1); - wake_up(&sem->wait); -} -EXPORT_SYMBOL(__up); - -/* - * Note that when we come in to __down or __down_interruptible, - * we have already decremented count, but that decrement was - * ineffective since the result was < 0, and any negative value - * of count is equivalent to 0. - * Thus it is only when we decrement count from some value > 0 - * that we have actually got the semaphore. - */ -void __sched __down(struct semaphore *sem) -{ - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - - __set_task_state(tsk, TASK_UNINTERRUPTIBLE); - add_wait_queue_exclusive(&sem->wait, &wait); - - /* - * Try to get the semaphore. If the count is > 0, then we've - * got the semaphore; we decrement count and exit the loop. - * If the count is 0 or negative, we set it to -1, indicating - * that we are asleep, and then sleep. - */ - while (__sem_update_count(sem, -1) <= 0) { - schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - } - remove_wait_queue(&sem->wait, &wait); - __set_task_state(tsk, TASK_RUNNING); - - /* - * If there are any more sleepers, wake one of them up so - * that it can either get the semaphore, or set count to -1 - * indicating that there are still processes sleeping. - */ - wake_up(&sem->wait); -} -EXPORT_SYMBOL(__down); - -int __sched __down_interruptible(struct semaphore * sem) -{ - int retval = 0; - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - - __set_task_state(tsk, TASK_INTERRUPTIBLE); - add_wait_queue_exclusive(&sem->wait, &wait); - - while (__sem_update_count(sem, -1) <= 0) { - if (signal_pending(current)) { - /* - * A signal is pending - give up trying. - * Set sem->count to 0 if it is negative, - * since we are no longer sleeping. - */ - __sem_update_count(sem, 0); - retval = -EINTR; - break; - } - schedule(); - set_task_state(tsk, TASK_INTERRUPTIBLE); - } - remove_wait_queue(&sem->wait, &wait); - __set_task_state(tsk, TASK_RUNNING); - - wake_up(&sem->wait); - return retval; -} -EXPORT_SYMBOL(__down_interruptible); diff --git a/arch/ppc64/kernel/vdso.c b/arch/ppc64/kernel/vdso.c deleted file mode 100644 index 1bbacac44988..000000000000 --- a/arch/ppc64/kernel/vdso.c +++ /dev/null @@ -1,625 +0,0 @@ -/* - * linux/arch/ppc64/kernel/vdso.c - * - * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp. - * - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#undef DEBUG - -#ifdef DEBUG -#define DBG(fmt...) printk(fmt) -#else -#define DBG(fmt...) -#endif - - -/* - * The vDSOs themselves are here - */ -extern char vdso64_start, vdso64_end; -extern char vdso32_start, vdso32_end; - -static void *vdso64_kbase = &vdso64_start; -static void *vdso32_kbase = &vdso32_start; - -unsigned int vdso64_pages; -unsigned int vdso32_pages; - -/* Signal trampolines user addresses */ - -unsigned long vdso64_rt_sigtramp; -unsigned long vdso32_sigtramp; -unsigned long vdso32_rt_sigtramp; - -/* Format of the patch table */ -struct vdso_patch_def -{ - u32 pvr_mask, pvr_value; - const char *gen_name; - const char *fix_name; -}; - -/* Table of functions to patch based on the CPU type/revision - * - * TODO: Improve by adding whole lists for each entry - */ -static struct vdso_patch_def vdso_patches[] = { - { - 0xffff0000, 0x003a0000, /* POWER5 */ - "__kernel_sync_dicache", "__kernel_sync_dicache_p5" - }, - { - 0xffff0000, 0x003b0000, /* POWER5 */ - "__kernel_sync_dicache", "__kernel_sync_dicache_p5" - }, -}; - -/* - * Some infos carried around for each of them during parsing at - * boot time. - */ -struct lib32_elfinfo -{ - Elf32_Ehdr *hdr; /* ptr to ELF */ - Elf32_Sym *dynsym; /* ptr to .dynsym section */ - unsigned long dynsymsize; /* size of .dynsym section */ - char *dynstr; /* ptr to .dynstr section */ - unsigned long text; /* offset of .text section in .so */ -}; - -struct lib64_elfinfo -{ - Elf64_Ehdr *hdr; - Elf64_Sym *dynsym; - unsigned long dynsymsize; - char *dynstr; - unsigned long text; -}; - - -#ifdef __DEBUG -static void dump_one_vdso_page(struct page *pg, struct page *upg) -{ - printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT), - page_count(pg), - pg->flags); - if (upg/* && pg != upg*/) { - printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg) << PAGE_SHIFT), - page_count(upg), - upg->flags); - } - printk("\n"); -} - -static void dump_vdso_pages(struct vm_area_struct * vma) -{ - int i; - - if (!vma || test_thread_flag(TIF_32BIT)) { - printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase); - for (i=0; ivm_mm) ? - follow_page(vma->vm_mm, vma->vm_start + i*PAGE_SIZE, 0) - : NULL; - dump_one_vdso_page(pg, upg); - } - } - if (!vma || !test_thread_flag(TIF_32BIT)) { - printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase); - for (i=0; ivm_mm) ? - follow_page(vma->vm_mm, vma->vm_start + i*PAGE_SIZE, 0) - : NULL; - dump_one_vdso_page(pg, upg); - } - } -} -#endif /* DEBUG */ - -/* - * Keep a dummy vma_close for now, it will prevent VMA merging. - */ -static void vdso_vma_close(struct vm_area_struct * vma) -{ -} - -/* - * Our nopage() function, maps in the actual vDSO kernel pages, they will - * be mapped read-only by do_no_page(), and eventually COW'ed, either - * right away for an initial write access, or by do_wp_page(). - */ -static struct page * vdso_vma_nopage(struct vm_area_struct * vma, - unsigned long address, int *type) -{ - unsigned long offset = address - vma->vm_start; - struct page *pg; - void *vbase = test_thread_flag(TIF_32BIT) ? vdso32_kbase : vdso64_kbase; - - DBG("vdso_vma_nopage(current: %s, address: %016lx, off: %lx)\n", - current->comm, address, offset); - - if (address < vma->vm_start || address > vma->vm_end) - return NOPAGE_SIGBUS; - - /* - * Last page is systemcfg. - */ - if ((vma->vm_end - address) <= PAGE_SIZE) - pg = virt_to_page(_systemcfg); - else - pg = virt_to_page(vbase + offset); - - get_page(pg); - DBG(" ->page count: %d\n", page_count(pg)); - - return pg; -} - -static struct vm_operations_struct vdso_vmops = { - .close = vdso_vma_close, - .nopage = vdso_vma_nopage, -}; - -/* - * This is called from binfmt_elf, we create the special vma for the - * vDSO and insert it into the mm struct tree - */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - unsigned long vdso_pages; - unsigned long vdso_base; - - if (test_thread_flag(TIF_32BIT)) { - vdso_pages = vdso32_pages; - vdso_base = VDSO32_MBASE; - } else { - vdso_pages = vdso64_pages; - vdso_base = VDSO64_MBASE; - } - - current->thread.vdso_base = 0; - - /* vDSO has a problem and was disabled, just don't "enable" it for the - * process - */ - if (vdso_pages == 0) - return 0; - - vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); - if (vma == NULL) - return -ENOMEM; - - memset(vma, 0, sizeof(*vma)); - - /* - * pick a base address for the vDSO in process space. We try to put it - * at vdso_base which is the "natural" base for it, but we might fail - * and end up putting it elsewhere. - */ - vdso_base = get_unmapped_area(NULL, vdso_base, - vdso_pages << PAGE_SHIFT, 0, 0); - if (vdso_base & ~PAGE_MASK) { - kmem_cache_free(vm_area_cachep, vma); - return (int)vdso_base; - } - - current->thread.vdso_base = vdso_base; - - vma->vm_mm = mm; - vma->vm_start = current->thread.vdso_base; - - /* - * the VMA size is one page more than the vDSO since systemcfg - * is mapped in the last one - */ - vma->vm_end = vma->vm_start + ((vdso_pages + 1) << PAGE_SHIFT); - - /* - * our vma flags don't have VM_WRITE so by default, the process isn't allowed - * to write those pages. - * gdb can break that with ptrace interface, and thus trigger COW on those - * pages but it's then your responsibility to never do that on the "data" page - * of the vDSO or you'll stop getting kernel updates and your nice userland - * gettimeofday will be totally dead. It's fine to use that for setting - * breakpoints in the vDSO code pages though - */ - vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_RESERVED; - vma->vm_flags |= mm->def_flags; - vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; - vma->vm_ops = &vdso_vmops; - - down_write(&mm->mmap_sem); - if (insert_vm_struct(mm, vma)) { - up_write(&mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); - return -ENOMEM; - } - mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; - up_write(&mm->mmap_sem); - - return 0; -} - -static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname, - unsigned long *size) -{ - Elf32_Shdr *sechdrs; - unsigned int i; - char *secnames; - - /* Grab section headers and strings so we can tell who is who */ - sechdrs = (void *)ehdr + ehdr->e_shoff; - secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; - - /* Find the section they want */ - for (i = 1; i < ehdr->e_shnum; i++) { - if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { - if (size) - *size = sechdrs[i].sh_size; - return (void *)ehdr + sechdrs[i].sh_offset; - } - } - *size = 0; - return NULL; -} - -static void * __init find_section64(Elf64_Ehdr *ehdr, const char *secname, - unsigned long *size) -{ - Elf64_Shdr *sechdrs; - unsigned int i; - char *secnames; - - /* Grab section headers and strings so we can tell who is who */ - sechdrs = (void *)ehdr + ehdr->e_shoff; - secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; - - /* Find the section they want */ - for (i = 1; i < ehdr->e_shnum; i++) { - if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { - if (size) - *size = sechdrs[i].sh_size; - return (void *)ehdr + sechdrs[i].sh_offset; - } - } - if (size) - *size = 0; - return NULL; -} - -static Elf32_Sym * __init find_symbol32(struct lib32_elfinfo *lib, const char *symname) -{ - unsigned int i; - char name[32], *c; - - for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) { - if (lib->dynsym[i].st_name == 0) - continue; - strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, 32); - c = strchr(name, '@'); - if (c) - *c = 0; - if (strcmp(symname, name) == 0) - return &lib->dynsym[i]; - } - return NULL; -} - -static Elf64_Sym * __init find_symbol64(struct lib64_elfinfo *lib, const char *symname) -{ - unsigned int i; - char name[32], *c; - - for (i = 0; i < (lib->dynsymsize / sizeof(Elf64_Sym)); i++) { - if (lib->dynsym[i].st_name == 0) - continue; - strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, 32); - c = strchr(name, '@'); - if (c) - *c = 0; - if (strcmp(symname, name) == 0) - return &lib->dynsym[i]; - } - return NULL; -} - -/* Note that we assume the section is .text and the symbol is relative to - * the library base - */ -static unsigned long __init find_function32(struct lib32_elfinfo *lib, const char *symname) -{ - Elf32_Sym *sym = find_symbol32(lib, symname); - - if (sym == NULL) { - printk(KERN_WARNING "vDSO32: function %s not found !\n", symname); - return 0; - } - return sym->st_value - VDSO32_LBASE; -} - -/* Note that we assume the section is .text and the symbol is relative to - * the library base - */ -static unsigned long __init find_function64(struct lib64_elfinfo *lib, const char *symname) -{ - Elf64_Sym *sym = find_symbol64(lib, symname); - - if (sym == NULL) { - printk(KERN_WARNING "vDSO64: function %s not found !\n", symname); - return 0; - } -#ifdef VDS64_HAS_DESCRIPTORS - return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) - VDSO64_LBASE; -#else - return sym->st_value - VDSO64_LBASE; -#endif -} - - -static __init int vdso_do_find_sections(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64) -{ - void *sect; - - /* - * Locate symbol tables & text section - */ - - v32->dynsym = find_section32(v32->hdr, ".dynsym", &v32->dynsymsize); - v32->dynstr = find_section32(v32->hdr, ".dynstr", NULL); - if (v32->dynsym == NULL || v32->dynstr == NULL) { - printk(KERN_ERR "vDSO32: a required symbol section was not found\n"); - return -1; - } - sect = find_section32(v32->hdr, ".text", NULL); - if (sect == NULL) { - printk(KERN_ERR "vDSO32: the .text section was not found\n"); - return -1; - } - v32->text = sect - vdso32_kbase; - - v64->dynsym = find_section64(v64->hdr, ".dynsym", &v64->dynsymsize); - v64->dynstr = find_section64(v64->hdr, ".dynstr", NULL); - if (v64->dynsym == NULL || v64->dynstr == NULL) { - printk(KERN_ERR "vDSO64: a required symbol section was not found\n"); - return -1; - } - sect = find_section64(v64->hdr, ".text", NULL); - if (sect == NULL) { - printk(KERN_ERR "vDSO64: the .text section was not found\n"); - return -1; - } - v64->text = sect - vdso64_kbase; - - return 0; -} - -static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64) -{ - /* - * Find signal trampolines - */ - - vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64"); - vdso32_sigtramp = find_function32(v32, "__kernel_sigtramp32"); - vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32"); -} - -static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64) -{ - Elf32_Sym *sym32; - Elf64_Sym *sym64; - - sym32 = find_symbol32(v32, "__kernel_datapage_offset"); - if (sym32 == NULL) { - printk(KERN_ERR "vDSO32: Can't find symbol __kernel_datapage_offset !\n"); - return -1; - } - *((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) = - (vdso32_pages << PAGE_SHIFT) - (sym32->st_value - VDSO32_LBASE); - - sym64 = find_symbol64(v64, "__kernel_datapage_offset"); - if (sym64 == NULL) { - printk(KERN_ERR "vDSO64: Can't find symbol __kernel_datapage_offset !\n"); - return -1; - } - *((int *)(vdso64_kbase + sym64->st_value - VDSO64_LBASE)) = - (vdso64_pages << PAGE_SHIFT) - (sym64->st_value - VDSO64_LBASE); - - return 0; -} - -static int vdso_do_func_patch32(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64, - const char *orig, const char *fix) -{ - Elf32_Sym *sym32_gen, *sym32_fix; - - sym32_gen = find_symbol32(v32, orig); - if (sym32_gen == NULL) { - printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", orig); - return -1; - } - sym32_fix = find_symbol32(v32, fix); - if (sym32_fix == NULL) { - printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", fix); - return -1; - } - sym32_gen->st_value = sym32_fix->st_value; - sym32_gen->st_size = sym32_fix->st_size; - sym32_gen->st_info = sym32_fix->st_info; - sym32_gen->st_other = sym32_fix->st_other; - sym32_gen->st_shndx = sym32_fix->st_shndx; - - return 0; -} - -static int vdso_do_func_patch64(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64, - const char *orig, const char *fix) -{ - Elf64_Sym *sym64_gen, *sym64_fix; - - sym64_gen = find_symbol64(v64, orig); - if (sym64_gen == NULL) { - printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", orig); - return -1; - } - sym64_fix = find_symbol64(v64, fix); - if (sym64_fix == NULL) { - printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", fix); - return -1; - } - sym64_gen->st_value = sym64_fix->st_value; - sym64_gen->st_size = sym64_fix->st_size; - sym64_gen->st_info = sym64_fix->st_info; - sym64_gen->st_other = sym64_fix->st_other; - sym64_gen->st_shndx = sym64_fix->st_shndx; - - return 0; -} - -static __init int vdso_fixup_alt_funcs(struct lib32_elfinfo *v32, - struct lib64_elfinfo *v64) -{ - u32 pvr; - int i; - - pvr = mfspr(SPRN_PVR); - for (i = 0; i < ARRAY_SIZE(vdso_patches); i++) { - struct vdso_patch_def *patch = &vdso_patches[i]; - int match = (pvr & patch->pvr_mask) == patch->pvr_value; - - DBG("patch %d (mask: %x, pvr: %x) : %s\n", - i, patch->pvr_mask, patch->pvr_value, match ? "match" : "skip"); - - if (!match) - continue; - - DBG("replacing %s with %s...\n", patch->gen_name, patch->fix_name); - - /* - * Patch the 32 bits and 64 bits symbols. Note that we do not patch - * the "." symbol on 64 bits. It would be easy to do, but doesn't - * seem to be necessary, patching the OPD symbol is enough. - */ - vdso_do_func_patch32(v32, v64, patch->gen_name, patch->fix_name); - vdso_do_func_patch64(v32, v64, patch->gen_name, patch->fix_name); - } - - return 0; -} - - -static __init int vdso_setup(void) -{ - struct lib32_elfinfo v32; - struct lib64_elfinfo v64; - - v32.hdr = vdso32_kbase; - v64.hdr = vdso64_kbase; - - if (vdso_do_find_sections(&v32, &v64)) - return -1; - - if (vdso_fixup_datapage(&v32, &v64)) - return -1; - - if (vdso_fixup_alt_funcs(&v32, &v64)) - return -1; - - vdso_setup_trampolines(&v32, &v64); - - return 0; -} - -void __init vdso_init(void) -{ - int i; - - vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT; - vdso32_pages = (&vdso32_end - &vdso32_start) >> PAGE_SHIFT; - - DBG("vdso64_kbase: %p, 0x%x pages, vdso32_kbase: %p, 0x%x pages\n", - vdso64_kbase, vdso64_pages, vdso32_kbase, vdso32_pages); - - /* - * Initialize the vDSO images in memory, that is do necessary - * fixups of vDSO symbols, locate trampolines, etc... - */ - if (vdso_setup()) { - printk(KERN_ERR "vDSO setup failure, not enabled !\n"); - /* XXX should free pages here ? */ - vdso64_pages = vdso32_pages = 0; - return; - } - - /* Make sure pages are in the correct state */ - for (i = 0; i < vdso64_pages; i++) { - struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); - get_page(pg); - } - for (i = 0; i < vdso32_pages; i++) { - struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); - get_page(pg); - } - - get_page(virt_to_page(_systemcfg)); -} - -int in_gate_area_no_task(unsigned long addr) -{ - return 0; -} - -int in_gate_area(struct task_struct *task, unsigned long addr) -{ - return 0; -} - -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) -{ - return NULL; -} - diff --git a/arch/ppc64/kernel/vmlinux.lds.S b/arch/ppc64/kernel/vmlinux.lds.S deleted file mode 100644 index 022f220e772f..000000000000 --- a/arch/ppc64/kernel/vmlinux.lds.S +++ /dev/null @@ -1,151 +0,0 @@ -#include -#include - -OUTPUT_ARCH(powerpc:common64) -jiffies = jiffies_64; -SECTIONS -{ - /* Sections to be discarded. */ - /DISCARD/ : { - *(.exitcall.exit) - } - - - /* Read-only sections, merged into text segment: */ - .text : { - *(.text .text.*) - SCHED_TEXT - LOCK_TEXT - KPROBES_TEXT - *(.fixup) - . = ALIGN(PAGE_SIZE); - _etext = .; - } - - __ex_table : { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } - - __bug_table : { - __start___bug_table = .; - *(__bug_table) - __stop___bug_table = .; - } - - __ftr_fixup : { - __start___ftr_fixup = .; - *(__ftr_fixup) - __stop___ftr_fixup = .; - } - - RODATA - - - /* will be freed after init */ - . = ALIGN(PAGE_SIZE); - __init_begin = .; - - .init.text : { - _sinittext = .; - *(.init.text) - _einittext = .; - } - - .init.data : { - *(.init.data) - } - - . = ALIGN(16); - .init.setup : { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - - .initcall.init : { - __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) - __initcall_end = .; - } - - .con_initcall.init : { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } - - SECURITY_INIT - - . = ALIGN(PAGE_SIZE); - .init.ramfs : { - __initramfs_start = .; - *(.init.ramfs) - __initramfs_end = .; - } - - .data.percpu : { - __per_cpu_start = .; - *(.data.percpu) - __per_cpu_end = .; - } - - . = ALIGN(PAGE_SIZE); - . = ALIGN(16384); - __init_end = .; - /* freed after init ends here */ - - - /* Read/write sections */ - . = ALIGN(PAGE_SIZE); - . = ALIGN(16384); - _sdata = .; - /* The initial task and kernel stack */ - .data.init_task : { - *(.data.init_task) - } - - . = ALIGN(PAGE_SIZE); - .data.page_aligned : { - *(.data.page_aligned) - } - - .data.cacheline_aligned : { - *(.data.cacheline_aligned) - } - - .data : { - *(.data .data.rel* .toc1) - *(.branch_lt) - } - - .opd : { - *(.opd) - } - - .got : { - __toc_start = .; - *(.got) - *(.toc) - . = ALIGN(PAGE_SIZE); - _edata = .; - } - - - . = ALIGN(PAGE_SIZE); - .bss : { - __bss_start = .; - *(.bss) - __bss_stop = .; - } - - . = ALIGN(PAGE_SIZE); - _end = . ; -} diff --git a/arch/ppc64/xmon/privinst.h b/arch/ppc64/xmon/privinst.h deleted file mode 100644 index 02eb40dac0b3..000000000000 --- a/arch/ppc64/xmon/privinst.h +++ /dev/null @@ -1,64 +0,0 @@ -/* - * Copyright (C) 1996 Paul Mackerras. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#define GETREG(reg) \ - static inline unsigned long get_ ## reg (void) \ - { unsigned long ret; asm volatile ("mf" #reg " %0" : "=r" (ret) :); return ret; } - -#define SETREG(reg) \ - static inline void set_ ## reg (unsigned long val) \ - { asm volatile ("mt" #reg " %0" : : "r" (val)); } - -GETREG(msr) -SETREG(msrd) -GETREG(cr) - -#define GSETSPR(n, name) \ - static inline long get_ ## name (void) \ - { long ret; asm volatile ("mfspr %0," #n : "=r" (ret) : ); return ret; } \ - static inline void set_ ## name (long val) \ - { asm volatile ("mtspr " #n ",%0" : : "r" (val)); } - -GSETSPR(0, mq) -GSETSPR(1, xer) -GSETSPR(4, rtcu) -GSETSPR(5, rtcl) -GSETSPR(8, lr) -GSETSPR(9, ctr) -GSETSPR(18, dsisr) -GSETSPR(19, dar) -GSETSPR(22, dec) -GSETSPR(25, sdr1) -GSETSPR(26, srr0) -GSETSPR(27, srr1) -GSETSPR(272, sprg0) -GSETSPR(273, sprg1) -GSETSPR(274, sprg2) -GSETSPR(275, sprg3) -GSETSPR(282, ear) -GSETSPR(287, pvr) -GSETSPR(1008, hid0) -GSETSPR(1009, hid1) -GSETSPR(1010, iabr) -GSETSPR(1023, pir) - -static inline void store_inst(void *p) -{ - asm volatile ("dcbst 0,%0; sync; icbi 0,%0; isync" : : "r" (p)); -} - -static inline void cflush(void *p) -{ - asm volatile ("dcbf 0,%0; icbi 0,%0" : : "r" (p)); -} - -static inline void cinval(void *p) -{ - asm volatile ("dcbi 0,%0; icbi 0,%0" : : "r" (p)); -} diff --git a/include/asm-ppc64/page.h b/include/asm-ppc64/page.h deleted file mode 100644 index 3efc3288f7e9..000000000000 --- a/include/asm-ppc64/page.h +++ /dev/null @@ -1,328 +0,0 @@ -#ifndef _PPC64_PAGE_H -#define _PPC64_PAGE_H - -/* - * Copyright (C) 2001 PPC64 Team, IBM Corp - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include - -/* - * We support either 4k or 64k software page size. When using 64k pages - * however, wether we are really supporting 64k pages in HW or not is - * irrelevant to those definitions. We always define HW_PAGE_SHIFT to 12 - * as use of 64k pages remains a linux kernel specific, every notion of - * page number shared with the firmware, TCEs, iommu, etc... still assumes - * a page size of 4096. - */ -#ifdef CONFIG_PPC_64K_PAGES -#define PAGE_SHIFT 16 -#else -#define PAGE_SHIFT 12 -#endif - -#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) - -/* HW_PAGE_SHIFT is always 4k pages */ -#define HW_PAGE_SHIFT 12 -#define HW_PAGE_SIZE (ASM_CONST(1) << HW_PAGE_SHIFT) -#define HW_PAGE_MASK (~(HW_PAGE_SIZE-1)) - -/* PAGE_FACTOR is the number of bits factor between PAGE_SHIFT and - * HW_PAGE_SHIFT, that is 4k pages - */ -#define PAGE_FACTOR (PAGE_SHIFT - HW_PAGE_SHIFT) - -/* Segment size */ -#define SID_SHIFT 28 -#define SID_MASK 0xfffffffffUL -#define ESID_MASK 0xfffffffff0000000UL -#define GET_ESID(x) (((x) >> SID_SHIFT) & SID_MASK) - -/* Large pages size */ - -#ifndef __ASSEMBLY__ -extern unsigned int HPAGE_SHIFT; -#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) -#define HPAGE_MASK (~(HPAGE_SIZE - 1)) -#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) -#endif /* __ASSEMBLY__ */ - -#ifdef CONFIG_HUGETLB_PAGE - - -#define HTLB_AREA_SHIFT 40 -#define HTLB_AREA_SIZE (1UL << HTLB_AREA_SHIFT) -#define GET_HTLB_AREA(x) ((x) >> HTLB_AREA_SHIFT) - -#define LOW_ESID_MASK(addr, len) (((1U << (GET_ESID(addr+len-1)+1)) \ - - (1U << GET_ESID(addr))) & 0xffff) -#define HTLB_AREA_MASK(addr, len) (((1U << (GET_HTLB_AREA(addr+len-1)+1)) \ - - (1U << GET_HTLB_AREA(addr))) & 0xffff) - -#define ARCH_HAS_HUGEPAGE_ONLY_RANGE -#define ARCH_HAS_PREPARE_HUGEPAGE_RANGE -#define ARCH_HAS_SETCLEAR_HUGE_PTE - -#define touches_hugepage_low_range(mm, addr, len) \ - (LOW_ESID_MASK((addr), (len)) & (mm)->context.low_htlb_areas) -#define touches_hugepage_high_range(mm, addr, len) \ - (HTLB_AREA_MASK((addr), (len)) & (mm)->context.high_htlb_areas) - -#define __within_hugepage_low_range(addr, len, segmask) \ - ((LOW_ESID_MASK((addr), (len)) | (segmask)) == (segmask)) -#define within_hugepage_low_range(addr, len) \ - __within_hugepage_low_range((addr), (len), \ - current->mm->context.low_htlb_areas) -#define __within_hugepage_high_range(addr, len, zonemask) \ - ((HTLB_AREA_MASK((addr), (len)) | (zonemask)) == (zonemask)) -#define within_hugepage_high_range(addr, len) \ - __within_hugepage_high_range((addr), (len), \ - current->mm->context.high_htlb_areas) - -#define is_hugepage_only_range(mm, addr, len) \ - (touches_hugepage_high_range((mm), (addr), (len)) || \ - touches_hugepage_low_range((mm), (addr), (len))) -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA - -#define in_hugepage_area(context, addr) \ - (cpu_has_feature(CPU_FTR_16M_PAGE) && \ - ( ((1 << GET_HTLB_AREA(addr)) & (context).high_htlb_areas) || \ - ( ((addr) < 0x100000000L) && \ - ((1 << GET_ESID(addr)) & (context).low_htlb_areas) ) ) ) - -#else /* !CONFIG_HUGETLB_PAGE */ - -#define in_hugepage_area(mm, addr) 0 - -#endif /* !CONFIG_HUGETLB_PAGE */ - -/* align addr on a size boundary - adjust address up/down if needed */ -#define _ALIGN_UP(addr,size) (((addr)+((size)-1))&(~((size)-1))) -#define _ALIGN_DOWN(addr,size) ((addr)&(~((size)-1))) - -/* align addr on a size boundary - adjust address up if needed */ -#define _ALIGN(addr,size) _ALIGN_UP(addr,size) - -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE) - -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ -#include - -#undef STRICT_MM_TYPECHECKS - -#define REGION_SIZE 4UL -#define REGION_SHIFT 60UL -#define REGION_MASK (((1UL<> REGION_SHIFT) -#define KERNEL_REGION_ID (KERNELBASE >> REGION_SHIFT) -#define USER_REGION_ID (0UL) -#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) - -#define __va(x) ((void *)((unsigned long)(x) + KERNELBASE)) - -#ifdef CONFIG_FLATMEM -#define pfn_to_page(pfn) (mem_map + (pfn)) -#define page_to_pfn(page) ((unsigned long)((page) - mem_map)) -#define pfn_valid(pfn) ((pfn) < max_mapnr) -#endif - -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) - -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) - -/* - * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI, - * and needs to be executable. This means the whole heap ends - * up being executable. - */ -#define VM_DATA_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_DATA_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_DATA_DEFAULT_FLAGS \ - (test_thread_flag(TIF_32BIT) ? \ - VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64) - -/* - * This is the default if a program doesn't have a PT_GNU_STACK - * program header entry. The PPC64 ELF ABI has a non executable stack - * stack by default, so in the absense of a PT_GNU_STACK program header - * we turn execute permission off. - */ -#define VM_STACK_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_STACK_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_STACK_DEFAULT_FLAGS \ - (test_thread_flag(TIF_32BIT) ? \ - VM_STACK_DEFAULT_FLAGS32 : VM_STACK_DEFAULT_FLAGS64) - -#endif /* __KERNEL__ */ - -#include - -#endif /* _PPC64_PAGE_H */