Merge branch 'for-2.6.27' of git://linux-nfs.org/~bfields/linux

[pandora-kernel.git] / arch / powerpc / mm / hash_utils_64.c

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index a83dfa3..8d3b58e 100644 (file)
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -31,6 +31,7 @@
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/lmb.h>
 
 #include <asm/processor.h>
 #include <asm/pgtable.h>
@@ -41,7 +42,7 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/machdep.h>
-#include <asm/lmb.h>
+#include <asm/prom.h>
 #include <asm/abs_addr.h>
 #include <asm/tlbflush.h>
 #include <asm/io.h>
@@ -93,6 +94,9 @@ unsigned long htab_hash_mask;
 int mmu_linear_psize = MMU_PAGE_4K;
 int mmu_virtual_psize = MMU_PAGE_4K;
 int mmu_vmalloc_psize = MMU_PAGE_4K;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+int mmu_vmemmap_psize = MMU_PAGE_4K;
+#endif
 int mmu_io_psize = MMU_PAGE_4K;
 int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
@@ -116,7 +120,7 @@ static DEFINE_SPINLOCK(linear_map_hash_lock);
 
 /* Pre-POWER4 CPUs (4k pages only)
  */
-struct mmu_psize_def mmu_psize_defaults_old[] = {
+static struct mmu_psize_def mmu_psize_defaults_old[] = {
        [MMU_PAGE_4K] = {
                .shift  = 12,
                .sllp   = 0,
@@ -130,7 +134,7 @@ struct mmu_psize_def mmu_psize_defaults_old[] = {
  *
  * Support for 16Mb large pages
  */
-struct mmu_psize_def mmu_psize_defaults_gp[] = {
+static struct mmu_psize_def mmu_psize_defaults_gp[] = {
        [MMU_PAGE_4K] = {
                .shift  = 12,
                .sllp   = 0,
@@ -191,6 +195,29 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
        return ret < 0 ? ret : 0;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+                     int psize, int ssize)
+{
+       unsigned long vaddr;
+       unsigned int step, shift;
+
+       shift = mmu_psize_defs[psize].shift;
+       step = 1 << shift;
+
+       if (!ppc_md.hpte_removebolted) {
+               printk(KERN_WARNING "Platform doesn't implement "
+                               "hpte_removebolted\n");
+               return -EINVAL;
+       }
+
+       for (vaddr = vstart; vaddr < vend; vaddr += step)
+               ppc_md.hpte_removebolted(vaddr, psize, ssize);
+
+       return 0;
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 static int __init htab_dt_scan_seg_sizes(unsigned long node,
                                         const char *uname, int depth,
                                         void *data)
@@ -363,11 +390,32 @@ static void __init htab_init_page_sizes(void)
        }
 #endif /* CONFIG_PPC_64K_PAGES */
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+       /* We try to use 16M pages for vmemmap if that is supported
+        * and we have at least 1G of RAM at boot
+        */
+       if (mmu_psize_defs[MMU_PAGE_16M].shift &&
+           lmb_phys_mem_size() >= 0x40000000)
+               mmu_vmemmap_psize = MMU_PAGE_16M;
+       else if (mmu_psize_defs[MMU_PAGE_64K].shift)
+               mmu_vmemmap_psize = MMU_PAGE_64K;
+       else
+               mmu_vmemmap_psize = MMU_PAGE_4K;
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
        printk(KERN_DEBUG "Page orders: linear mapping = %d, "
-              "virtual = %d, io = %d\n",
+              "virtual = %d, io = %d"
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+              ", vmemmap = %d"
+#endif
+              "\n",
               mmu_psize_defs[mmu_linear_psize].shift,
               mmu_psize_defs[mmu_virtual_psize].shift,
-              mmu_psize_defs[mmu_io_psize].shift);
+              mmu_psize_defs[mmu_io_psize].shift
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+              ,mmu_psize_defs[mmu_vmemmap_psize].shift
+#endif
+              );
 
 #ifdef CONFIG_HUGETLB_PAGE
        /* Init large page size. Currently, we pick 16M or 1M depending
@@ -434,6 +482,12 @@ void create_section_mapping(unsigned long start, unsigned long end)
                        _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX,
                        mmu_linear_psize, mmu_kernel_ssize));
 }
+
+int remove_section_mapping(unsigned long start, unsigned long end)
+{
+       return htab_remove_mapping(start, end, mmu_linear_psize,
+                       mmu_kernel_ssize);
+}
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static inline void make_bl(unsigned int *insn_addr, void *func)
@@ -479,8 +533,6 @@ void __init htab_initialize(void)
        unsigned long base = 0, size = 0, limit;
        int i;
 
-       extern unsigned long tce_alloc_start, tce_alloc_end;
-
        DBG(" -> htab_initialize()\n");
 
        /* Initialize segment sizes */
@@ -643,6 +695,28 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
        return pp;
 }
 
+#ifdef CONFIG_PPC_MM_SLICES
+unsigned int get_paca_psize(unsigned long addr)
+{
+       unsigned long index, slices;
+
+       if (addr < SLICE_LOW_TOP) {
+               slices = get_paca()->context.low_slices_psize;
+               index = GET_LOW_SLICE_INDEX(addr);
+       } else {
+               slices = get_paca()->context.high_slices_psize;
+               index = GET_HIGH_SLICE_INDEX(addr);
+       }
+       return (slices >> (index * 4)) & 0xF;
+}
+
+#else
+unsigned int get_paca_psize(unsigned long addr)
+{
+       return get_paca()->context.user_psize;
+}
+#endif
+
 /*
  * Demote a segment to using 4k pages.
  * For now this makes the whole process use 4k pages.
@@ -650,13 +724,13 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 #ifdef CONFIG_PPC_64K_PAGES
 void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 {
-       if (mm->context.user_psize == MMU_PAGE_4K)
+       if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
                return;
-       slice_set_user_psize(mm, MMU_PAGE_4K);
+       slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
 #ifdef CONFIG_SPU_BASE
        spu_flush_all_slbs(mm);
 #endif
-       if (get_paca()->context.user_psize != MMU_PAGE_4K) {
+       if (get_paca_psize(addr) != MMU_PAGE_4K) {
                get_paca()->context = mm->context;
                slb_flush_and_rebolt();
        }
@@ -740,11 +814,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
                        DBG_LOW(" user region with no mm !\n");
                        return 1;
                }
-#ifdef CONFIG_PPC_MM_SLICES
                psize = get_slice_psize(mm, ea);
-#else
-               psize = mm->context.user_psize;
-#endif
                ssize = user_segment_size(ea);
                vsid = get_vsid(mm->context.id, ea, ssize);
                break;
@@ -816,7 +886,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
        /* Do actual hashing */
 #ifdef CONFIG_PPC_64K_PAGES
        /* If _PAGE_4K_PFN is set, make sure this is a 4k segment */
-       if (pte_val(*ptep) & _PAGE_4K_PFN) {
+       if ((pte_val(*ptep) & _PAGE_4K_PFN) && psize == MMU_PAGE_64K) {
                demote_segment_4k(mm, ea);
                psize = MMU_PAGE_4K;
        }
@@ -845,7 +915,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
                }
        }
        if (user_region) {
-               if (psize != get_paca()->context.user_psize) {
+               if (psize != get_paca_psize(ea)) {
                        get_paca()->context = mm->context;
                        slb_flush_and_rebolt();
                }