x86: move init_memory_mapping() to common mm/init.c

Impact: cleanup

This patch moves the init_memory_mapping() function to common mm/init.c.

Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1236257708-27269-14-git-send-email-penberg@cs.helsinki.fi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 328 insertions, 0 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cc7fe660f33d..3a21b136da24 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -2,10 +2,338 @@
 #include <linux/swap.h>
 
 #include <asm/cacheflush.h>
+#include <asm/e820.h>
 #include <asm/page.h>
 #include <asm/page_types.h>
 #include <asm/sections.h>
 #include <asm/system.h>
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_X86_32
+extern void __init early_ioremap_page_table_range_init(void);
+extern void __init kernel_physical_mapping_init(unsigned long start_pfn,
+                                                unsigned long end_pfn,
+                                                int use_pse);
+#endif
+
+#ifdef CONFIG_X86_64
+extern unsigned long __meminit
+kernel_physical_mapping_init(unsigned long start,
+                             unsigned long end,
+                             unsigned long page_size_mask);
+#endif
+
+unsigned long __initdata table_start;
+unsigned long __meminitdata table_end;
+unsigned long __meminitdata table_top;
+
+int after_bootmem;
+
+int direct_gbpages
+#ifdef CONFIG_DIRECT_GBPAGES
+                                = 1
+#endif
+;
+
+static void __init find_early_table_space(unsigned long end, int use_pse,
+                                          int use_gbpages)
+{
+        unsigned long puds, pmds, ptes, tables, start;
+
+        puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
+        tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+
+        if (use_gbpages) {
+                unsigned long extra;
+
+                extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
+                pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+        } else
+                pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+
+        tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+
+        if (use_pse) {
+                unsigned long extra;
+
+                extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+#ifdef CONFIG_X86_32
+                extra += PMD_SIZE;
+#endif
+                ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        } else
+                ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+        tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
+
+#ifdef CONFIG_X86_32
+        /* for fixmap */
+        tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
+#endif
+
+        /*
+         * RED-PEN putting page tables only on node 0 could
+         * cause a hotspot and fill up ZONE_DMA. The page tables
+         * need roughly 0.5KB per GB.
+         */
+#ifdef CONFIG_X86_32
+        start = 0x7000;
+        table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+                                        tables, PAGE_SIZE);
+#else /* CONFIG_X86_64 */
+        start = 0x8000;
+        table_start = find_e820_area(start, end, tables, PAGE_SIZE);
+#endif
+        if (table_start == -1UL)
+                panic("Cannot find space for the kernel page tables");
+
+        table_start >>= PAGE_SHIFT;
+        table_end = table_start;
+        table_top = table_start + (tables >> PAGE_SHIFT);
+
+        printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
+                end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT);
+}
+
+struct map_range {
+        unsigned long start;
+        unsigned long end;
+        unsigned page_size_mask;
+};
+
+#ifdef CONFIG_X86_32
+#define NR_RANGE_MR 3
+#else /* CONFIG_X86_64 */
+#define NR_RANGE_MR 5
+#endif
+
+static int save_mr(struct map_range *mr, int nr_range,
+                   unsigned long start_pfn, unsigned long end_pfn,
+                   unsigned long page_size_mask)
+{
+        if (start_pfn < end_pfn) {
+                if (nr_range >= NR_RANGE_MR)
+                        panic("run out of range for init_memory_mapping\n");
+                mr[nr_range].start = start_pfn<<PAGE_SHIFT;
+                mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
+                mr[nr_range].page_size_mask = page_size_mask;
+                nr_range++;
+        }
+
+        return nr_range;
+}
+
+#ifdef CONFIG_X86_64
+static void __init init_gbpages(void)
+{
+        if (direct_gbpages && cpu_has_gbpages)
+                printk(KERN_INFO "Using GB pages for direct mapping\n");
+        else
+                direct_gbpages = 0;
+}
+#else
+static inline void init_gbpages(void)
+{
+}
+#endif
+
+/*
+ * Setup the direct mapping of the physical memory at PAGE_OFFSET.
+ * This runs before bootmem is initialized and gets pages directly from
+ * the physical memory. To access them they are temporarily mapped.
+ */
+unsigned long __init_refok init_memory_mapping(unsigned long start,
+                                               unsigned long end)
+{
+        unsigned long page_size_mask = 0;
+        unsigned long start_pfn, end_pfn;
+        unsigned long pos;
+        unsigned long ret;
+
+        struct map_range mr[NR_RANGE_MR];
+        int nr_range, i;
+        int use_pse, use_gbpages;
+
+        printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
+
+        if (!after_bootmem)
+                init_gbpages();
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+        /*
+         * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+         * This will simplify cpa(), which otherwise needs to support splitting
+         * large pages into small in interrupt context, etc.
+         */
+        use_pse = use_gbpages = 0;
+#else
+        use_pse = cpu_has_pse;
+        use_gbpages = direct_gbpages;
+#endif
+
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_PAE
+        set_nx();
+        if (nx_enabled)
+                printk(KERN_INFO "NX (Execute Disable) protection: active\n");
+#endif
+
+        /* Enable PSE if available */
+        if (cpu_has_pse)
+                set_in_cr4(X86_CR4_PSE);
+
+        /* Enable PGE if available */
+        if (cpu_has_pge) {
+                set_in_cr4(X86_CR4_PGE);
+                __supported_pte_mask |= _PAGE_GLOBAL;
+        }
+#endif
+
+        if (use_gbpages)
+                page_size_mask |= 1 << PG_LEVEL_1G;
+        if (use_pse)
+                page_size_mask |= 1 << PG_LEVEL_2M;
+
+        memset(mr, 0, sizeof(mr));
+        nr_range = 0;
+
+        /* head if not big page alignment ? */
+        start_pfn = start >> PAGE_SHIFT;
+        pos = start_pfn << PAGE_SHIFT;
+#ifdef CONFIG_X86_32
+        /*
+         * Don't use a large page for the first 2/4MB of memory
+         * because there are often fixed size MTRRs in there
+         * and overlapping MTRRs into large pages can cause
+         * slowdowns.
+         */
+        if (pos == 0)
+                end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
+        else
+                end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+                                 << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+        end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
+                        << (PMD_SHIFT - PAGE_SHIFT);
+#endif
+        if (end_pfn > (end >> PAGE_SHIFT))
+                end_pfn = end >> PAGE_SHIFT;
+        if (start_pfn < end_pfn) {
+                nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+                pos = end_pfn << PAGE_SHIFT;
+        }
+
+        /* big page (2M) range */
+        start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+                         << (PMD_SHIFT - PAGE_SHIFT);
+#ifdef CONFIG_X86_32
+        end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+        end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+                         << (PUD_SHIFT - PAGE_SHIFT);
+        if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+                end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+#endif
+
+        if (start_pfn < end_pfn) {
+                nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                                page_size_mask & (1<<PG_LEVEL_2M));
+                pos = end_pfn << PAGE_SHIFT;
+        }
+
+#ifdef CONFIG_X86_64
+        /* big page (1G) range */
+        start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+                         << (PUD_SHIFT - PAGE_SHIFT);
+        end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+        if (start_pfn < end_pfn) {
+                nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                                page_size_mask &
+                                 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+                pos = end_pfn << PAGE_SHIFT;
+        }
+
+        /* tail is not big page (1G) alignment */
+        start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+                         << (PMD_SHIFT - PAGE_SHIFT);
+        end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+        if (start_pfn < end_pfn) {
+                nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                                page_size_mask & (1<<PG_LEVEL_2M));
+                pos = end_pfn << PAGE_SHIFT;
+        }
+#endif
+
+        /* tail is not big page (2M) alignment */
+        start_pfn = pos>>PAGE_SHIFT;
+        end_pfn = end>>PAGE_SHIFT;
+        nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+
+        /* try to merge same page size and continuous */
+        for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
+                unsigned long old_start;
+                if (mr[i].end != mr[i+1].start ||
+                    mr[i].page_size_mask != mr[i+1].page_size_mask)
+                        continue;
+                /* move it */
+                old_start = mr[i].start;
+                memmove(&mr[i], &mr[i+1],
+                        (nr_range - 1 - i) * sizeof(struct map_range));
+                mr[i--].start = old_start;
+                nr_range--;
+        }
+
+        for (i = 0; i < nr_range; i++)
+                printk(KERN_DEBUG " %010lx - %010lx page %s\n",
+                                mr[i].start, mr[i].end,
+                        (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
+                         (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
+
+        /*
+         * Find space for the kernel direct mapping tables.
+         *
+         * Later we should allocate these tables in the local node of the
+         * memory mapped. Unfortunately this is done currently before the
+         * nodes are discovered.
+         */
+        if (!after_bootmem)
+                find_early_table_space(end, use_pse, use_gbpages);
+
+#ifdef CONFIG_X86_32
+        for (i = 0; i < nr_range; i++)
+                kernel_physical_mapping_init(
+                                mr[i].start >> PAGE_SHIFT,
+                                mr[i].end >> PAGE_SHIFT,
+                                mr[i].page_size_mask == (1<<PG_LEVEL_2M));
+        ret = end;
+#else /* CONFIG_X86_64 */
+        for (i = 0; i < nr_range; i++)
+                ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
+                                                   mr[i].page_size_mask);
+#endif
+
+#ifdef CONFIG_X86_32
+        early_ioremap_page_table_range_init();
+
+        load_cr3(swapper_pg_dir);
+#endif
+
+#ifdef CONFIG_X86_64
+        if (!after_bootmem)
+                mmu_cr4_features = read_cr4();
+#endif
+        __flush_tlb_all();
+
+        if (!after_bootmem && table_end > table_start)
+                reserve_early(table_start << PAGE_SHIFT,
+                                 table_end << PAGE_SHIFT, "PGTABLE");
+
+        if (!after_bootmem)
+                early_memtest(start, end);
+
+        return ret >> PAGE_SHIFT;
+}
+
 
 /*
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address