Pull release into acpica branch

7 files changed, 149 insertions, 102 deletions

diff --git a/arch/ia64/mm/Makefile b/arch/ia64/mm/Makefile
index 7078f67887ec..d78d20f0a0f0 100644
--- a/arch/ia64/mm/Makefile
+++ b/arch/ia64/mm/Makefile
@@ -7,6 +7,5 @@ obj-y := init.o fault.o tlb.o extable.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
 obj-$(CONFIG_NUMA)         += numa.o
 obj-$(CONFIG_DISCONTIGMEM) += discontig.o
-ifndef CONFIG_DISCONTIGMEM
-obj-y += contig.o
-endif
+obj-$(CONFIG_SPARSEMEM)    += discontig.o
+obj-$(CONFIG_FLATMEM)      += contig.o
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 91a055f5731f..acaaec4e4681 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -269,7 +269,7 @@ paging_init (void)
         efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
         if (max_gap < LARGE_GAP) {
                 vmem_map = (struct page *) 0;
-                free_area_init_node(0, &contig_page_data, zones_size, 0,
+                free_area_init_node(0, NODE_DATA(0), zones_size, 0,
                                     zholes_size);
         } else {
                 unsigned long map_size;
@@ -282,7 +282,7 @@ paging_init (void)
                 efi_memmap_walk(create_mem_map_page_table, NULL);
 
                 NODE_DATA(0)->node_mem_map = vmem_map;
-                free_area_init_node(0, &contig_page_data, zones_size,
+                free_area_init_node(0, NODE_DATA(0), zones_size,
                                     0, zholes_size);
 
                 printk("Virtual mem_map starts at 0x%p\n", mem_map);
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index b5c90e548195..0f776b032d31 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -350,14 +350,12 @@ static void __init initialize_pernode_data(void)
  *      for best.
  * @nid: node id
  * @pernodesize: size of this node's pernode data
- * @align: alignment to use for this node's pernode data
  */
-static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize,
-        unsigned long align)
+static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 {
         void *ptr = NULL;
         u8 best = 0xff;
-        int bestnode = -1, node;
+        int bestnode = -1, node, anynode = 0;
 
         for_each_online_node(node) {
                 if (node_isset(node, memory_less_mask))
@@ -366,13 +364,15 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize,
                         best = node_distance(nid, node);
                         bestnode = node;
                 }
+                anynode = node;
         }
 
-        ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat,
-                pernodesize, align, __pa(MAX_DMA_ADDRESS));
+        if (bestnode == -1)
+                bestnode = anynode;
+
+        ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
+                PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 
-        if (!ptr)
-                panic("NO memory for memory less node\n");
         return ptr;
 }
 
@@ -413,14 +413,44 @@ static void __init memory_less_nodes(void)
 
         for_each_node_mask(node, memory_less_mask) {
                 pernodesize = compute_pernodesize(node);
-                pernode = memory_less_node_alloc(node, pernodesize,
-                        (node) ? (node * PERCPU_PAGE_SIZE) : (1024*1024));
+                pernode = memory_less_node_alloc(node, pernodesize);
                 fill_pernode(node, __pa(pernode), pernodesize);
         }
 
         return;
 }
 
+#ifdef CONFIG_SPARSEMEM
+/**
+ * register_sparse_mem - notify SPARSEMEM that this memory range exists.
+ * @start: physical start of range
+ * @end: physical end of range
+ * @arg: unused
+ *
+ * Simply calls SPARSEMEM to register memory section(s).
+ */
+static int __init register_sparse_mem(unsigned long start, unsigned long end,
+        void *arg)
+{
+        int nid;
+
+        start = __pa(start) >> PAGE_SHIFT;
+        end = __pa(end) >> PAGE_SHIFT;
+        nid = early_pfn_to_nid(start);
+        memory_present(nid, start, end);
+
+        return 0;
+}
+
+static void __init arch_sparse_init(void)
+{
+        efi_memmap_walk(register_sparse_mem, NULL);
+        sparse_init();
+}
+#else
+#define arch_sparse_init() do {} while (0)
+#endif
+
 /**
  * find_memory - walk the EFI memory map and setup the bootmem allocator
  *
@@ -524,12 +554,18 @@ void show_mem(void)
         show_free_areas();
         printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
         for_each_pgdat(pgdat) {
-                unsigned long present = pgdat->node_present_pages;
+                unsigned long present;
+                unsigned long flags;
                 int shared = 0, cached = 0, reserved = 0;
+
                 printk("Node ID: %d\n", pgdat->node_id);
+                pgdat_resize_lock(pgdat, &flags);
+                present = pgdat->node_present_pages;
                 for(i = 0; i < pgdat->node_spanned_pages; i++) {
-                        struct page *page = pgdat_page_nr(pgdat, i);
-                        if (!ia64_pfn_valid(pgdat->node_start_pfn+i))
+                        struct page *page;
+                        if (pfn_valid(pgdat->node_start_pfn + i))
+                                page = pfn_to_page(pgdat->node_start_pfn + i);
+                        else
                                 continue;
                         if (PageReserved(page))
                                 reserved++;
@@ -538,6 +574,7 @@ void show_mem(void)
                         else if (page_count(page))
                                 shared += page_count(page)-1;
                 }
+                pgdat_resize_unlock(pgdat, &flags);
                 total_present += present;
                 total_reserved += reserved;
                 total_cached += cached;
@@ -648,12 +685,16 @@ void __init paging_init(void)
 
         max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
+        arch_sparse_init();
+
         efi_memmap_walk(filter_rsvd_memory, count_node_pages);
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
         vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page));
         vmem_map = (struct page *) vmalloc_end;
         efi_memmap_walk(create_mem_map_page_table, NULL);
         printk("Virtual mem_map starts at 0x%p\n", vmem_map);
+#endif
 
         for_each_online_node(node) {
                 memset(zones_size, 0, sizeof(zones_size));
@@ -690,7 +731,9 @@ void __init paging_init(void)
 
                 pfn_offset = mem_data[node].min_pfn;
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
                 NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
+#endif
                 free_area_init_node(node, NODE_DATA(node), zones_size,
                                     pfn_offset, zholes_size);
         }
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 3c32af910d60..af7eb087dca7 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -20,32 +20,6 @@
 extern void die (char *, struct pt_regs *, long);
 
 /*
- * This routine is analogous to expand_stack() but instead grows the
- * register backing store (which grows towards higher addresses).
- * Since the register backing store is access sequentially, we
- * disallow growing the RBS by more than a page at a time.  Note that
- * the VM_GROWSUP flag can be set on any VM area but that's fine
- * because the total process size is still limited by RLIMIT_STACK and
- * RLIMIT_AS.
- */
-static inline long
-expand_backing_store (struct vm_area_struct *vma, unsigned long address)
-{
-        unsigned long grow;
-
-        grow = PAGE_SIZE >> PAGE_SHIFT;
-        if (address - vma->vm_start > current->signal->rlim[RLIMIT_STACK].rlim_cur
-            || (((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) > current->signal->rlim[RLIMIT_AS].rlim_cur))
-                return -ENOMEM;
-        vma->vm_end += PAGE_SIZE;
-        vma->vm_mm->total_vm += grow;
-        if (vma->vm_flags & VM_LOCKED)
-                vma->vm_mm->locked_vm += grow;
-        __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, grow);
-        return 0;
-}
-
-/*
  * Return TRUE if ADDRESS points at a page in the kernel's mapped segment
  * (inside region 5, on ia64) and that page is present.
  */
@@ -185,7 +159,13 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
                 if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
                     || REGION_OFFSET(address) >= RGN_MAP_LIMIT)
                         goto bad_area;
-                if (expand_backing_store(vma, address))
+                /*
+                 * Since the register backing store is accessed sequentially,
+                 * we disallow growing it by more than a page at a time.
+                 */
+                if (address > vma->vm_end + PAGE_SIZE - sizeof(long))
+                        goto bad_area;
+                if (expand_upwards(vma, address))
                         goto bad_area;
         }
         goto good_area;
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 1281c609ee98..e3215ba64ffd 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -158,7 +158,7 @@ ia64_init_addr_space (void)
                 vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
                 vma->vm_end = vma->vm_start + PAGE_SIZE;
                 vma->vm_page_prot = protection_map[VM_DATA_DEFAULT_FLAGS & 0x7];
-                vma->vm_flags = VM_DATA_DEFAULT_FLAGS | VM_GROWSUP;
+                vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
                 down_write(&current->mm->mmap_sem);
                 if (insert_vm_struct(current->mm, vma)) {
                         up_write(&current->mm->mmap_sem);
@@ -275,26 +275,21 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
 
         pgd = pgd_offset_k(address);            /* note: this is NOT pgd_offset()! */
 
-        spin_lock(&init_mm.page_table_lock);
         {
                 pud = pud_alloc(&init_mm, pgd, address);
                 if (!pud)
                         goto out;
-
                 pmd = pmd_alloc(&init_mm, pud, address);
                 if (!pmd)
                         goto out;
-                pte = pte_alloc_map(&init_mm, pmd, address);
+                pte = pte_alloc_kernel(pmd, address);
                 if (!pte)
                         goto out;
-                if (!pte_none(*pte)) {
-                        pte_unmap(pte);
+                if (!pte_none(*pte))
                         goto out;
-                }
                 set_pte(pte, mk_pte(page, pgprot));
-                pte_unmap(pte);
         }
-  out:  spin_unlock(&init_mm.page_table_lock);
+  out:
         /* no need for flush_tlb */
         return page;
 }
@@ -593,7 +588,7 @@ mem_init (void)
         platform_dma_init();
 #endif
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
         if (!mem_map)
                 BUG();
         max_mapnr = max_low_pfn;
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index 77118bbf3d8b..4e5c8b36ad93 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -47,3 +47,27 @@ paddr_to_nid(unsigned long paddr)
 
         return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0);
 }
+
+#if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
+/*
+ * Because of holes evaluate on section limits.
+ * If the section of memory exists, then return the node where the section
+ * resides.  Otherwise return node 0 as the default.  This is used by
+ * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
+ * the section resides.
+ */
+int early_pfn_to_nid(unsigned long pfn)
+{
+        int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
+
+        for (i = 0; i < num_node_memblks; i++) {
+                ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
+                esec = (node_memblk[i].start_paddr + node_memblk[i].size +
+                        ((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
+                if (section >= ssec && section < esec)
+                        return node_memblk[i].nid;
+        }
+
+        return 0;
+}
+#endif
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 464557e4ed82..41105d454423 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -8,6 +8,8 @@
  *              Modified RID allocation for SMP
  *          Goutham Rao <goutham.rao@intel.com>
  *              IPI based ptc implementation and A-step IPI implementation.
+ * Rohit Seth <rohit.seth@intel.com>
+ * Ken Chen <kenneth.w.chen@intel.com>
  */
 #include <linux/config.h>
 #include <linux/module.h>
@@ -16,80 +18,83 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/bootmem.h>
 
 #include <asm/delay.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/pal.h>
 #include <asm/tlbflush.h>
+#include <asm/dma.h>
 
 static struct {
         unsigned long mask;     /* mask of supported purge page-sizes */
-        unsigned long max_bits; /* log2() of largest supported purge page-size */
+        unsigned long max_bits; /* log2 of largest supported purge page-size */
 } purge;
 
 struct ia64_ctx ia64_ctx = {
         .lock =         SPIN_LOCK_UNLOCKED,
         .next =         1,
-        .limit =        (1 << 15) - 1,          /* start out with the safe (architected) limit */
         .max_ctx =      ~0U
 };
 
 DEFINE_PER_CPU(u8, ia64_need_tlb_flush);
 
 /*
+ * Initializes the ia64_ctx.bitmap array based on max_ctx+1.
+ * Called after cpu_init() has setup ia64_ctx.max_ctx based on
+ * maximum RID that is supported by boot CPU.
+ */
+void __init
+mmu_context_init (void)
+{
+        ia64_ctx.bitmap = alloc_bootmem((ia64_ctx.max_ctx+1)>>3);
+        ia64_ctx.flushmap = alloc_bootmem((ia64_ctx.max_ctx+1)>>3);
+}
+
+/*
  * Acquire the ia64_ctx.lock before calling this function!
  */
 void
 wrap_mmu_context (struct mm_struct *mm)
 {
-        unsigned long tsk_context, max_ctx = ia64_ctx.max_ctx;
-        struct task_struct *tsk;
-        int i;
+        int i, cpu;
+        unsigned long flush_bit;
 
-        if (ia64_ctx.next > max_ctx)
-                ia64_ctx.next = 300;    /* skip daemons */
-        ia64_ctx.limit = max_ctx + 1;
+        for (i=0; i <= ia64_ctx.max_ctx / BITS_PER_LONG; i++) {
+                flush_bit = xchg(&ia64_ctx.flushmap[i], 0);
+                ia64_ctx.bitmap[i] ^= flush_bit;
+        }
+ 
+        /* use offset at 300 to skip daemons */
+        ia64_ctx.next = find_next_zero_bit(ia64_ctx.bitmap,
+                                ia64_ctx.max_ctx, 300);
+        ia64_ctx.limit = find_next_bit(ia64_ctx.bitmap,
+                                ia64_ctx.max_ctx, ia64_ctx.next);
 
         /*
-         * Scan all the task's mm->context and set proper safe range
+         * can't call flush_tlb_all() here because of race condition
+         * with O(1) scheduler [EF]
          */
-
-        read_lock(&tasklist_lock);
-  repeat:
-        for_each_process(tsk) {
-                if (!tsk->mm)
-                        continue;
-                tsk_context = tsk->mm->context;
-                if (tsk_context == ia64_ctx.next) {
-                        if (++ia64_ctx.next >= ia64_ctx.limit) {
-                                /* empty range: reset the range limit and start over */
-                                if (ia64_ctx.next > max_ctx)
-                                        ia64_ctx.next = 300;
-                                ia64_ctx.limit = max_ctx + 1;
-                                goto repeat;
-                        }
-                }
-                if ((tsk_context > ia64_ctx.next) && (tsk_context < ia64_ctx.limit))
-                        ia64_ctx.limit = tsk_context;
-        }
-        read_unlock(&tasklist_lock);
-        /* can't call flush_tlb_all() here because of race condition with O(1) scheduler [EF] */
-        {
-                int cpu = get_cpu(); /* prevent preemption/migration */
-                for (i = 0; i < NR_CPUS; ++i)
-                        if (cpu_online(i) && (i != cpu))
-                                per_cpu(ia64_need_tlb_flush, i) = 1;
-                put_cpu();
-        }
+        cpu = get_cpu(); /* prevent preemption/migration */
+        for_each_online_cpu(i)
+                if (i != cpu)
+                        per_cpu(ia64_need_tlb_flush, i) = 1;
+        put_cpu();
         local_flush_tlb_all();
 }
 
 void
-ia64_global_tlb_purge (unsigned long start, unsigned long end, unsigned long nbits)
+ia64_global_tlb_purge (struct mm_struct *mm, unsigned long start,
+                       unsigned long end, unsigned long nbits)
 {
         static DEFINE_SPINLOCK(ptcg_lock);
 
+        if (mm != current->active_mm) {
+                flush_tlb_all();
+                return;
+        }
+
         /* HW requires global serialization of ptc.ga.  */
         spin_lock(&ptcg_lock);
         {
@@ -129,36 +134,37 @@ local_flush_tlb_all (void)
 }
 
 void
-flush_tlb_range (struct vm_area_struct *vma, unsigned long start, unsigned long end)
+flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
+                 unsigned long end)
 {
         struct mm_struct *mm = vma->vm_mm;
         unsigned long size = end - start;
         unsigned long nbits;
 
+#ifndef CONFIG_SMP
         if (mm != current->active_mm) {
-                /* this does happen, but perhaps it's not worth optimizing for? */
-#ifdef CONFIG_SMP
-                flush_tlb_all();
-#else
                 mm->context = 0;
-#endif
                 return;
         }
+#endif
 
         nbits = ia64_fls(size + 0xfff);
-        while (unlikely (((1UL << nbits) & purge.mask) == 0) && (nbits < purge.max_bits))
+        while (unlikely (((1UL << nbits) & purge.mask) == 0) &&
+                        (nbits < purge.max_bits))
                 ++nbits;
         if (nbits > purge.max_bits)
                 nbits = purge.max_bits;
         start &= ~((1UL << nbits) - 1);
 
 # ifdef CONFIG_SMP
-        platform_global_tlb_purge(start, end, nbits);
+        platform_global_tlb_purge(mm, start, end, nbits);
 # else
+        preempt_disable();
         do {
                 ia64_ptcl(start, (nbits<<2));
                 start += (1UL << nbits);
         } while (start < end);
+        preempt_enable();
 # endif
 
         ia64_srlz_i();                  /* srlz.i implies srlz.d */
@@ -186,5 +192,5 @@ ia64_tlb_init (void)
         local_cpu_data->ptce_stride[0] = ptce_info.stride[0];
         local_cpu_data->ptce_stride[1] = ptce_info.stride[1];
 
-        local_flush_tlb_all();          /* nuke left overs from bootstrapping... */
+        local_flush_tlb_all();  /* nuke left overs from bootstrapping... */
 }