Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 152 insertions, 175 deletions

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c3a4fbb2b996..afaf38447ef5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/apm_bios.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/mca.h>
@@ -83,7 +84,6 @@
 #include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
-#include <asm/vmi.h>
 #include <asm/setup_arch.h>
 #include <asm/bios_ebda.h>
 #include <asm/cacheflush.h>
@@ -107,11 +107,13 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
 #include <asm/mce.h>
+#include <asm/alternative.h>
+#include <asm/prom.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -125,7 +127,6 @@ unsigned long max_pfn_mapped;
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
 
-unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
 unsigned long _brk_end = (unsigned long)__brk_base;
@@ -297,12 +298,15 @@ static void __init init_gbpages(void)
 static inline void init_gbpages(void)
 {
 }
+static void __init cleanup_highmap(void)
+{
+}
 #endif
 
 static void __init reserve_brk(void)
 {
         if (_brk_end > _brk_start)
-                reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+                memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
 
         /* Mark brk area as locked down and no longer taking any
            new allocations */
@@ -324,17 +328,16 @@ static void __init relocate_initrd(void)
         char *p, *q;
 
         /* We need to move the initrd down into lowmem */
-        ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
+        ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
                                          PAGE_SIZE);
 
-        if (ramdisk_here == -1ULL)
+        if (ramdisk_here == MEMBLOCK_ERROR)
                 panic("Cannot find place for new RAMDISK of size %lld\n",
                          ramdisk_size);
 
         /* Note: this includes all the lowmem currently occupied by
            the initrd, we rely on that fact to keep the data intact. */
-        reserve_early(ramdisk_here, ramdisk_here + area_size,
-                         "NEW RAMDISK");
+        memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK");
         initrd_start = ramdisk_here + PAGE_OFFSET;
         initrd_end   = initrd_start + ramdisk_size;
         printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
@@ -390,7 +393,7 @@ static void __init reserve_initrd(void)
         initrd_start = 0;
 
         if (ramdisk_size >= (end_of_lowmem>>1)) {
-                free_early(ramdisk_image, ramdisk_end);
+                memblock_x86_free_range(ramdisk_image, ramdisk_end);
                 printk(KERN_ERR "initrd too large to handle, "
                        "disabling initrd\n");
                 return;
@@ -413,7 +416,7 @@ static void __init reserve_initrd(void)
 
         relocate_initrd();
 
-        free_early(ramdisk_image, ramdisk_end);
+        memblock_x86_free_range(ramdisk_image, ramdisk_end);
 }
 #else
 static void __init reserve_initrd(void)
@@ -430,16 +433,30 @@ static void __init parse_setup_data(void)
                 return;
         pa_data = boot_params.hdr.setup_data;
         while (pa_data) {
-                data = early_memremap(pa_data, PAGE_SIZE);
+                u32 data_len, map_len;
+
+                map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
+                              (u64)sizeof(struct setup_data));
+                data = early_memremap(pa_data, map_len);
+                data_len = data->len + sizeof(struct setup_data);
+                if (data_len > map_len) {
+                        early_iounmap(data, map_len);
+                        data = early_memremap(pa_data, data_len);
+                        map_len = data_len;
+                }
+
                 switch (data->type) {
                 case SETUP_E820_EXT:
-                        parse_e820_ext(data, pa_data);
+                        parse_e820_ext(data);
+                        break;
+                case SETUP_DTB:
+                        add_dtb(pa_data);
                         break;
                 default:
                         break;
                 }
                 pa_data = data->next;
-                early_iounmap(data, PAGE_SIZE);
+                early_iounmap(data, map_len);
         }
 }
 
@@ -469,7 +486,7 @@ static void __init e820_reserve_setup_data(void)
         e820_print_map("reserve setup_data");
 }
 
-static void __init reserve_early_setup_data(void)
+static void __init memblock_x86_reserve_range_setup_data(void)
 {
         struct setup_data *data;
         u64 pa_data;
@@ -481,7 +498,7 @@ static void __init reserve_early_setup_data(void)
         while (pa_data) {
                 data = early_memremap(pa_data, sizeof(*data));
                 sprintf(buf, "setup data %x", data->type);
-                reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+                memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
                 pa_data = data->next;
                 early_iounmap(data, sizeof(*data));
         }
@@ -502,6 +519,18 @@ static inline unsigned long long get_total_mem(void)
         return total << PAGE_SHIFT;
 }
 
+/*
+ * Keep the crash kernel below this limit.  On 32 bits earlier kernels
+ * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
+ * limit once kexec-tools are fixed.
+ */
+#ifdef CONFIG_X86_32
+# define CRASH_KERNEL_ADDR_MAX  (512 << 20)
+#else
+# define CRASH_KERNEL_ADDR_MAX  (896 << 20)
+#endif
+
 static void __init reserve_crashkernel(void)
 {
         unsigned long long total_mem;
@@ -519,23 +548,27 @@ static void __init reserve_crashkernel(void)
         if (crash_base <= 0) {
                 const unsigned long long alignment = 16<<20;    /* 16M */
 
-                crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
-                                 alignment);
-                if (crash_base == -1ULL) {
+                /*
+                 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
+                 */
+                crash_base = memblock_find_in_range(alignment,
+                               CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+
+                if (crash_base == MEMBLOCK_ERROR) {
                         pr_info("crashkernel reservation failed - No suitable area found.\n");
                         return;
                 }
         } else {
                 unsigned long long start;
 
-                start = find_e820_area(crash_base, ULONG_MAX, crash_size,
-                                 1<<20);
+                start = memblock_find_in_range(crash_base,
+                                 crash_base + crash_size, crash_size, 1<<20);
                 if (start != crash_base) {
                         pr_info("crashkernel reservation failed - memory is in use.\n");
                         return;
                 }
         }
-        reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
+        memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
         printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
                         "for crashkernel (System RAM: %ldMB)\n",
@@ -586,28 +619,6 @@ void __init reserve_standard_io_resources(void)
 
 }
 
-/*
- * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
- * is_kdump_kernel() to determine if we are booting after a panic. Hence
- * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
- */
-
-#ifdef CONFIG_CRASH_DUMP
-/* elfcorehdr= specifies the location of elf core header
- * stored by the crashed kernel. This option will be passed
- * by kexec loader to the capture kernel.
- */
-static int __init setup_elfcorehdr(char *arg)
-{
-        char *end;
-        if (!arg)
-                return -EINVAL;
-        elfcorehdr_addr = memparse(arg, &end);
-        return end > arg ? 0 : -EINVAL;
-}
-early_param("elfcorehdr", setup_elfcorehdr);
-#endif
-
 static __init void reserve_ibft_region(void)
 {
         unsigned long addr, size = 0;
@@ -615,82 +626,10 @@ static __init void reserve_ibft_region(void)
         addr = find_ibft_region(&size);
 
         if (size)
-                reserve_early_overlap_ok(addr, addr + size, "ibft");
+                memblock_x86_reserve_range(addr, addr + size, "* ibft");
 }
 
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
-{
-        printk(KERN_NOTICE
-                "%s detected: BIOS may corrupt low RAM, working around it.\n",
-                d->ident);
-
-        e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-        sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-
-        return 0;
-}
-#endif
-
-/* List of systems that have known low memory corruption BIOS problems */
-static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix/MSC BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
-                },
-        },
-        /*
-         * AMI BIOS with low memory corruption was found on Intel DG45ID and
-         * DG45FC boards.
-         * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
-         * match only DMI_BOARD_NAME and see if there is more bad products
-         * with this vendor.
-         */
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
-                },
-        },
-        /*
-         * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
-         * match on the product name.
-         */
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
-                },
-        },
-#endif
-        {}
-};
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
 static void __init trim_bios_range(void)
 {
@@ -698,8 +637,14 @@ static void __init trim_bios_range(void)
          * A special case is the first 4Kb of memory;
          * This is a BIOS owned area, not kernel ram, but generally
          * not listed as such in the E820 table.
+         *
+         * This typically reserves additional memory (64KiB by default)
+         * since some BIOSes are known to corrupt low memory.  See the
+         * Kconfig help text for X86_RESERVE_LOW.
          */
-        e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+        e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
+                          E820_RAM, E820_RESERVED);
+
         /*
          * special case: Some BIOSen report the PC BIOS
          * area (640->1Mb) as ram even though it is not.
@@ -709,6 +654,28 @@ static void __init trim_bios_range(void)
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+static int __init parse_reservelow(char *p)
+{
+        unsigned long long size;
+
+        if (!p)
+                return -EINVAL;
+
+        size = memparse(p, &p);
+
+        if (size < 4096)
+                size = 4096;
+
+        if (size > 640*1024)
+                size = 640*1024;
+
+        reserve_low = size;
+
+        return 0;
+}
+
+early_param("reservelow", parse_reservelow);
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -724,20 +691,28 @@ static void __init trim_bios_range(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-        int acpi = 0;
-        int k8 = 0;
-
 #ifdef CONFIG_X86_32
         memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
         visws_early_detect();
+
+        /*
+         * copy kernel address range established so far and switch
+         * to the proper swapper page table
+         */
+        clone_pgd_range(swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+                        initial_page_table + KERNEL_PGD_BOUNDARY,
+                        KERNEL_PGD_PTRS);
+
+        load_cr3(swapper_pg_dir);
+        __flush_tlb_all();
 #else
         printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
-        /* VMI may relocate the fixmap; do this before touching ioremap area */
-        vmi_init();
-
-        /* OFW also may relocate the fixmap */
+        /*
+         * If we have OLPC OFW, we might end up relocating the fixmap due to
+         * reserve_top(), so do this before touching the ioremap area.
+         */
         olpc_ofw_detect();
 
         early_trap_init();
@@ -782,12 +757,13 @@ void __init setup_arch(char **cmdline_p)
 #endif
          4)) {
                 efi_enabled = 1;
-                efi_reserve_early();
+                efi_memblock_x86_reserve_range();
         }
 #endif
 
         x86_init.oem.arch_setup();
 
+        iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
         setup_memory_map();
         parse_setup_data();
         /* update the e820_saved too */
@@ -838,11 +814,8 @@ void __init setup_arch(char **cmdline_p)
 
         x86_report_nx();
 
-        /* Must be before kernel pagetables are setup */
-        vmi_activate();
-
         /* after early param, so could get panic from serial */
-        reserve_early_setup_data();
+        memblock_x86_reserve_range_setup_data();
 
         if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -863,8 +836,6 @@ void __init setup_arch(char **cmdline_p)
 
         dmi_scan_machine();
 
-        dmi_check_system(bad_bios_dmi_table);
-
         /*
          * VMware detection requires dmi to be available, so this
          * needs to be done after dmi_scan_machine, for the BP.
@@ -897,8 +868,6 @@ void __init setup_arch(char **cmdline_p)
          */
         max_pfn = e820_end_of_ram_pfn();
 
-        /* preallocate 4k for mptable mpc */
-        early_reserve_e820_mpc_new();
         /* update e820 for memory not covered by WB MTRRs */
         mtrr_bp_init();
         if (mtrr_trim_uncached_memory(max_pfn))
@@ -920,18 +889,8 @@ void __init setup_arch(char **cmdline_p)
                 max_low_pfn = max_pfn;
 
         high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
-        max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-        setup_bios_corruption_check();
-#endif
-
-        printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
-                        max_pfn_mapped<<PAGE_SHIFT);
-
-        reserve_brk();
-
         /*
          * Find and reserve possible boot-time SMP configuration:
          */
@@ -939,15 +898,37 @@ void __init setup_arch(char **cmdline_p)
 
         reserve_ibft_region();
 
-        reserve_trampoline_memory();
+        /*
+         * Need to conclude brk, before memblock_x86_fill()
+         *  it could use memblock_find_in_range, could overlap with
+         *  brk area.
+         */
+        reserve_brk();
+
+        cleanup_highmap();
+
+        memblock.current_limit = get_max_mapped();
+        memblock_x86_fill();
 
-#ifdef CONFIG_ACPI_SLEEP
         /*
-         * Reserve low memory region for sleep support.
-         * even before init_memory_mapping
+         * The EFI specification says that boot service code won't be called
+         * after ExitBootServices(). This is, in fact, a lie.
          */
-        acpi_reserve_wakeup_memory();
+        if (efi_enabled)
+                efi_reserve_boot_services();
+
+        /* preallocate 4k for mptable mpc */
+        early_reserve_e820_mpc_new();
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+        setup_bios_corruption_check();
 #endif
+
+        printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+                        max_pfn_mapped<<PAGE_SHIFT);
+
+        setup_trampolines();
+
         init_gbpages();
 
         /* max_pfn_mapped is updated here */
@@ -962,6 +943,7 @@ void __init setup_arch(char **cmdline_p)
                 max_low_pfn = max_pfn;
         }
 #endif
+        memblock.current_limit = get_max_mapped();
 
         /*
          * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -971,6 +953,8 @@ void __init setup_arch(char **cmdline_p)
         if (init_ohci1394_dma_early)
                 init_ohci1394_dma_on_all_controllers();
 #endif
+        /* Allocate bigger log buffer */
+        setup_log_buf(1);
 
         reserve_initrd();
 
@@ -987,24 +971,8 @@ void __init setup_arch(char **cmdline_p)
 
         early_acpi_boot_init();
 
-#ifdef CONFIG_ACPI_NUMA
-        /*
-         * Parse SRAT to discover nodes.
-         */
-        acpi = acpi_numa_init();
-#endif
-
-#ifdef CONFIG_K8_NUMA
-        if (!acpi)
-                k8 = !k8_numa_init(0, max_pfn);
-#endif
-
-        initmem_init(0, max_pfn, acpi, k8);
-#ifndef CONFIG_NO_BOOTMEM
-        early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-#endif
-
-        dma32_reserve_bootmem();
+        initmem_init();
+        memblock_find_dma_reserve();
 
 #ifdef CONFIG_KVM_CLOCK
         kvmclock_init();
@@ -1014,7 +982,17 @@ void __init setup_arch(char **cmdline_p)
         paging_init();
         x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
-        setup_trampoline_page_table();
+        if (boot_cpu_data.cpuid_level >= 0) {
+                /* A CPU has %cr4 if and only if it has CPUID */
+                mmu_cr4_features = read_cr4();
+        }
+
+#ifdef CONFIG_X86_32
+        /* sync back kernel address range */
+        clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+                        swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+                        KERNEL_PGD_PTRS);
+#endif
 
         tboot_probe();
 
@@ -1030,8 +1008,8 @@ void __init setup_arch(char **cmdline_p)
          * Read APIC and some other early information from ACPI tables.
          */
         acpi_boot_init();
-
         sfi_init();
+        x86_dtb_init();
 
         /*
          * get boot-time SMP configuration:
@@ -1041,15 +1019,10 @@ void __init setup_arch(char **cmdline_p)
 
         prefill_possible_map();
 
-#ifdef CONFIG_X86_64
         init_cpu_to_node();
-#endif
 
         init_apic_mappings();
-        ioapic_init_mappings();
-
-        /* need to wait for io_apic is mapped */
-        probe_nr_irqs_gsi();
+        ioapic_and_gsi_init();
 
         kvm_guest_init();
 
@@ -1070,7 +1043,11 @@ void __init setup_arch(char **cmdline_p)
 #endif
         x86_init.oem.banner();
 
+        x86_init.timers.wallclock_init();
+
         mcheck_init();
+
+        arch_init_ideal_nops();
 }
 
 #ifdef CONFIG_X86_32