Merge branch 'core-memblock-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-memblock-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (74 commits)
  x86-64: Only set max_pfn_mapped to 512 MiB if we enter via head_64.S
  xen: Cope with unmapped pages when initializing kernel pagetable
  memblock, bootmem: Round pfn properly for memory and reserved regions
  memblock: Annotate memblock functions with __init_memblock
  memblock: Allow memblock_init to be called early
  memblock/arm: Fix memblock_region_is_memory() typo
  x86, memblock: Remove __memblock_x86_find_in_range_size()
  memblock: Fix wraparound in find_region()
  x86-32, memblock: Make add_highpages honor early reserved ranges
  x86, memblock: Fix crashkernel allocation
  arm, memblock: Fix the sparsemem build
  memblock: Fix section mismatch warnings
  powerpc, memblock: Fix memblock API change fallout
  memblock, microblaze: Fix memblock API change fallout
  x86: Remove old bootmem code
  x86, memblock: Use memblock_memory_size()/memblock_free_memory_size() to get correct dma_reserve
  x86: Remove not used early_res code
  x86, memblock: Replace e820_/_early string with memblock_
  x86: Use memblock to replace early_res
  x86, memblock: Use memblock_debug to control debug message print out
  ...

Fix up trivial conflicts in arch/x86/kernel/setup.c and kernel/Makefile

10 files changed, 165 insertions, 102 deletions

diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index 1dc2fa5ce1bd..5810967511d4 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -47,6 +48,7 @@
 #include <asm/bootx.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
+
 #include "mmu_decl.h"
 
 extern int __map_without_ltlbs;
@@ -139,8 +141,19 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
          * coverage with normal-sized pages (or other reasons) do not
          * attempt to allocate outside the allowed range.
          */
-
-        __initial_memory_limit_addr = memstart_addr + mapped;
+        memblock_set_current_limit(mapped);
 
         return mapped;
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* We don't currently support the first MEMBLOCK not mapping 0
+         * physical on those processors
+         */
+        BUG_ON(first_memblock_base != 0);
+
+        /* 40x can only access 16MB at the moment (see head_40x.S) */
+        memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index d8c6efb32bc6..024acab588fd 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -24,6 +24,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
+
 #include <asm/mmu.h>
 #include <asm/system.h>
 #include <asm/page.h>
@@ -213,6 +215,18 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
         return total_lowmem;
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* We don't currently support the first MEMBLOCK not mapping 0
+         * physical on those processors
+         */
+        BUG_ON(first_memblock_base != 0);
+
+        /* 44x has a 256M TLB entry pinned at boot */
+        memblock_set_current_limit(min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+}
+
 #ifdef CONFIG_SMP
 void __cpuinit mmu_init_secondary(int cpu)
 {
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 4b66a1ece6d8..cde270847e7c 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -40,6 +40,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -213,5 +214,14 @@ void __init adjust_total_lowmem(void)
         pr_cont("%lu Mb, residual: %dMb\n", tlbcam_sz(tlbcam_index - 1) >> 20,
                 (unsigned int)((total_lowmem - __max_low_memory) >> 20));
 
-        __initial_memory_limit_addr = memstart_addr + __max_low_memory;
+        memblock_set_current_limit(memstart_addr + __max_low_memory);
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        phys_addr_t limit = first_memblock_base + first_memblock_size;
+
+        /* 64M mapped initially according to head_fsl_booke.S */
+        memblock_set_current_limit(min_t(u64, limit, 0x04000000));
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 09dffe6efa46..83f534d862db 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -588,7 +588,7 @@ static void __init htab_initialize(void)
         unsigned long pteg_count;
         unsigned long prot;
         unsigned long base = 0, size = 0, limit;
-        int i;
+        struct memblock_region *reg;
 
         DBG(" -> htab_initialize()\n");
 
@@ -625,7 +625,7 @@ static void __init htab_initialize(void)
                 if (machine_is(cell))
                         limit = 0x80000000;
                 else
-                        limit = 0;
+                        limit = MEMBLOCK_ALLOC_ANYWHERE;
 
                 table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
 
@@ -649,7 +649,7 @@ static void __init htab_initialize(void)
 #ifdef CONFIG_DEBUG_PAGEALLOC
         linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
         linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-                                                    1, memblock.rmo_size));
+                                                    1, ppc64_rma_size));
         memset(linear_map_hash_slots, 0, linear_map_hash_count);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
@@ -659,9 +659,9 @@ static void __init htab_initialize(void)
          */
 
         /* create bolted the linear mapping in the hash table */
-        for (i=0; i < memblock.memory.cnt; i++) {
-                base = (unsigned long)__va(memblock.memory.region[i].base);
-                size = memblock.memory.region[i].size;
+        for_each_memblock(memory, reg) {
+                base = (unsigned long)__va(reg->base);
+                size = reg->size;
 
                 DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
                     base, size, prot);
@@ -696,7 +696,8 @@ static void __init htab_initialize(void)
 #endif /* CONFIG_U3_DART */
                 BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
                                 prot, mmu_linear_psize, mmu_kernel_ssize));
-       }
+        }
+        memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
         /*
          * If we have a memory_limit and we've allocated TCEs then we need to
@@ -1247,3 +1248,23 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
         local_irq_restore(flags);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* We don't currently support the first MEMBLOCK not mapping 0
+         * physical on those processors
+         */
+        BUG_ON(first_memblock_base != 0);
+
+        /* On LPAR systems, the first entry is our RMA region,
+         * non-LPAR 64-bit hash MMU systems don't have a limitation
+         * on real mode access, but using the first entry works well
+         * enough. We also clamp it to 1G to avoid some funky things
+         * such as RTAS bugs etc...
+         */
+        ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+        /* Finally limit subsequent allocations */
+        memblock_set_current_limit(ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 6a6975dc2654..742da43b4ab6 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -92,12 +92,6 @@ int __allow_ioremap_reserved;
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
- * address of the limit of what is accessible with initial MMU setup -
- * 256MB usually, but only 16MB on 601.
- */
-phys_addr_t __initial_memory_limit_addr = (phys_addr_t)0x10000000;
-
-/*
  * Check for command-line options that affect what MMU_init will do.
  */
 void MMU_setup(void)
@@ -126,13 +120,6 @@ void __init MMU_init(void)
         if (ppc_md.progress)
                 ppc_md.progress("MMU:enter", 0x111);
 
-        /* 601 can only access 16MB at the moment */
-        if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-                __initial_memory_limit_addr = 0x01000000;
-        /* 8xx can only access 8MB at the moment */
-        if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
-                __initial_memory_limit_addr = 0x00800000;
-
         /* parse args from command line */
         MMU_setup();
 
@@ -190,20 +177,18 @@ void __init MMU_init(void)
 #ifdef CONFIG_BOOTX_TEXT
         btext_unmap();
 #endif
+
+        /* Shortly after that, the entire linear mapping will be available */
+        memblock_set_current_limit(lowmem_end_addr);
 }
 
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-        void *p;
-
-        if (init_bootmem_done) {
-                p = alloc_bootmem_pages(PAGE_SIZE);
-        } else {
-                p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-                                        __initial_memory_limit_addr));
-        }
-        return p;
+        if (init_bootmem_done)
+                return alloc_bootmem_pages(PAGE_SIZE);
+        else
+                return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
 /* Free up now-unused memory */
@@ -252,3 +237,17 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+
+#ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* We don't currently support the first MEMBLOCK not mapping 0
+         * physical on those processors
+         */
+        BUG_ON(first_memblock_base != 0);
+
+        /* 8xx can only access 8MB at the moment */
+        memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
+#endif /* CONFIG_8xx */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index ace85fa74b29..6374b2196a17 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -330,3 +330,4 @@ int __meminit vmemmap_populate(struct page *start_page,
         return 0;
 }
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1a84a8d00005..a66499650909 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -82,18 +82,11 @@ int page_is_ram(unsigned long pfn)
         return pfn < max_pfn;
 #else
         unsigned long paddr = (pfn << PAGE_SHIFT);
-        int i;
-        for (i=0; i < memblock.memory.cnt; i++) {
-                unsigned long base;
+        struct memblock_region *reg;
 
-                base = memblock.memory.region[i].base;
-
-                if ((paddr >= base) &&
-                        (paddr < (base + memblock.memory.region[i].size))) {
+        for_each_memblock(memory, reg)
+                if (paddr >= reg->base && paddr < (reg->base + reg->size))
                         return 1;
-                }
-        }
-
         return 0;
 #endif
 }
@@ -149,23 +142,19 @@ int
 walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
                 void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
-        struct memblock_property res;
-        unsigned long pfn, len;
-        u64 end;
+        struct memblock_region *reg;
+        unsigned long end_pfn = start_pfn + nr_pages;
+        unsigned long tstart, tend;
         int ret = -1;
 
-        res.base = (u64) start_pfn << PAGE_SHIFT;
-        res.size = (u64) nr_pages << PAGE_SHIFT;
-
-        end = res.base + res.size - 1;
-        while ((res.base < end) && (memblock_find(&res) >= 0)) {
-                pfn = (unsigned long)(res.base >> PAGE_SHIFT);
-                len = (unsigned long)(res.size >> PAGE_SHIFT);
-                ret = (*func)(pfn, len, arg);
+        for_each_memblock(memory, reg) {
+                tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
+                tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+                if (tstart >= tend)
+                        continue;
+                ret = (*func)(tstart, tend - tstart, arg);
                 if (ret)
                         break;
-                res.base += (res.size + 1);
-                res.size = (end - res.base + 1);
         }
         return ret;
 }
@@ -179,9 +168,9 @@ EXPORT_SYMBOL_GPL(walk_system_ram_range);
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init do_init_bootmem(void)
 {
-        unsigned long i;
         unsigned long start, bootmap_pages;
         unsigned long total_pages;
+        struct memblock_region *reg;
         int boot_mapsize;
 
         max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -204,10 +193,10 @@ void __init do_init_bootmem(void)
         boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
 
         /* Add active regions with valid PFNs */
-        for (i = 0; i < memblock.memory.cnt; i++) {
+        for_each_memblock(memory, reg) {
                 unsigned long start_pfn, end_pfn;
-                start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-                end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+                start_pfn = memblock_region_memory_base_pfn(reg);
+                end_pfn = memblock_region_memory_end_pfn(reg);
                 add_active_range(0, start_pfn, end_pfn);
         }
 
@@ -218,29 +207,21 @@ void __init do_init_bootmem(void)
         free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
 
         /* reserve the sections we're already using */
-        for (i = 0; i < memblock.reserved.cnt; i++) {
-                unsigned long addr = memblock.reserved.region[i].base +
-                                     memblock_size_bytes(&memblock.reserved, i) - 1;
-                if (addr < lowmem_end_addr)
-                        reserve_bootmem(memblock.reserved.region[i].base,
-                                        memblock_size_bytes(&memblock.reserved, i),
-                                        BOOTMEM_DEFAULT);
-                else if (memblock.reserved.region[i].base < lowmem_end_addr) {
-                        unsigned long adjusted_size = lowmem_end_addr -
-                                      memblock.reserved.region[i].base;
-                        reserve_bootmem(memblock.reserved.region[i].base,
-                                        adjusted_size, BOOTMEM_DEFAULT);
+        for_each_memblock(reserved, reg) {
+                unsigned long top = reg->base + reg->size - 1;
+                if (top < lowmem_end_addr)
+                        reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+                else if (reg->base < lowmem_end_addr) {
+                        unsigned long trunc_size = lowmem_end_addr - reg->base;
+                        reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
                 }
         }
 #else
         free_bootmem_with_active_regions(0, max_pfn);
 
         /* reserve the sections we're already using */
-        for (i = 0; i < memblock.reserved.cnt; i++)
-                reserve_bootmem(memblock.reserved.region[i].base,
-                                memblock_size_bytes(&memblock.reserved, i),
-                                BOOTMEM_DEFAULT);
-
+        for_each_memblock(reserved, reg)
+                reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 #endif
         /* XXX need to clip this if using highmem? */
         sparse_memory_present_with_active_regions(0);
@@ -251,22 +232,15 @@ void __init do_init_bootmem(void)
 /* mark pages that don't exist as nosave */
 static int __init mark_nonram_nosave(void)
 {
-        unsigned long memblock_next_region_start_pfn,
-                      memblock_region_max_pfn;
-        int i;
-
-        for (i = 0; i < memblock.memory.cnt - 1; i++) {
-                memblock_region_max_pfn =
-                        (memblock.memory.region[i].base >> PAGE_SHIFT) +
-                        (memblock.memory.region[i].size >> PAGE_SHIFT);
-                memblock_next_region_start_pfn =
-                        memblock.memory.region[i+1].base >> PAGE_SHIFT;
-
-                if (memblock_region_max_pfn < memblock_next_region_start_pfn)
-                        register_nosave_region(memblock_region_max_pfn,
-                                               memblock_next_region_start_pfn);
+        struct memblock_region *reg, *prev = NULL;
+
+        for_each_memblock(memory, reg) {
+                if (prev &&
+                    memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg))
+                        register_nosave_region(memblock_region_memory_end_pfn(prev),
+                                               memblock_region_memory_base_pfn(reg));
+                prev = reg;
         }
-
         return 0;
 }
 
@@ -327,7 +301,7 @@ void __init mem_init(void)
                 swiotlb_init(1);
 #endif
 
-        num_physpages = memblock.memory.size >> PAGE_SHIFT;
+        num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT;
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 002878ccf90b..74505b245374 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -802,16 +802,17 @@ static void __init setup_nonnuma(void)
         unsigned long top_of_ram = memblock_end_of_DRAM();
         unsigned long total_ram = memblock_phys_mem_size();
         unsigned long start_pfn, end_pfn;
-        unsigned int i, nid = 0;
+        unsigned int nid = 0;
+        struct memblock_region *reg;
 
         printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
                top_of_ram, total_ram);
         printk(KERN_DEBUG "Memory hole size: %ldMB\n",
                (top_of_ram - total_ram) >> 20);
 
-        for (i = 0; i < memblock.memory.cnt; ++i) {
-                start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-                end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+        for_each_memblock(memory, reg) {
+                start_pfn = memblock_region_memory_base_pfn(reg);
+                end_pfn = memblock_region_memory_end_pfn(reg);
 
                 fake_numa_create_new_node(end_pfn, &nid);
                 add_active_range(nid, start_pfn, end_pfn);
@@ -947,11 +948,11 @@ static struct notifier_block __cpuinitdata ppc64_numa_nb = {
 static void mark_reserved_regions_for_nid(int nid)
 {
         struct pglist_data *node = NODE_DATA(nid);
-        int i;
+        struct memblock_region *reg;
 
-        for (i = 0; i < memblock.reserved.cnt; i++) {
-                unsigned long physbase = memblock.reserved.region[i].base;
-                unsigned long size = memblock.reserved.region[i].size;
+        for_each_memblock(reserved, reg) {
+                unsigned long physbase = reg->base;
+                unsigned long size = reg->size;
                 unsigned long start_pfn = physbase >> PAGE_SHIFT;
                 unsigned long end_pfn = PFN_UP(physbase + size);
                 struct node_active_region node_ar;
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f8a01829d64f..11571e118831 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -223,8 +223,7 @@ void __init MMU_init_hw(void)
          * Find some memory for the hash table.
          */
         if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-        Hash = __va(memblock_alloc_base(Hash_size, Hash_size,
-                                   __initial_memory_limit_addr));
+        Hash = __va(memblock_alloc(Hash_size, Hash_size));
         cacheable_memzero(Hash, Hash_size);
         _SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
@@ -272,3 +271,18 @@ void __init MMU_init_hw(void)
 
         if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* We don't currently support the first MEMBLOCK not mapping 0
+         * physical on those processors
+         */
+        BUG_ON(first_memblock_base != 0);
+
+        /* 601 can only access 16MB at the moment */
+        if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+                memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+        else /* Anything else has 256M mapped */
+                memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index fe391e942521..6a0f20c25469 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -509,6 +509,8 @@ static void __early_init_mmu(int boot_cpu)
          * the MMU configuration
          */
         mb();
+
+        memblock_set_current_limit(linear_map_top);
 }
 
 void __init early_init_mmu(void)
@@ -521,4 +523,18 @@ void __cpuinit early_init_mmu_secondary(void)
         __early_init_mmu(0);
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+                                phys_addr_t first_memblock_size)
+{
+        /* On Embedded 64-bit, we adjust the RMA size to match
+         * the bolted TLB entry. We know for now that only 1G
+         * entries are supported though that may eventually
+         * change. We crop it to the size of the first MEMBLOCK to
+         * avoid going over total available memory just in case...
+         */
+        ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+        /* Finally limit subsequent allocations */
+        memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+}
 #endif /* CONFIG_PPC64 */