OpenCloudOS-Kernel/arch/x86/kernel/setup.c

1092 lines
26 KiB
C
Raw Normal View History

/*
* Copyright (C) 1995 Linus Torvalds
*
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
*
* Memory region support
* David Parsons <orc@pell.chi.il.us>, July-August 1999
*
* Added E820 sanitization routine (removes overlapping memory regions);
* Brian Moyle <bmoyle@mvista.com>, February 2001
*
* Moved CPU detection code to cpu/${cpu}.c
* Patrick Mochel <mochel@osdl.org>, March 2002
*
* Provisions for empty E820 memory regions (reported by certain BIOSes).
* Alex Achenbach <xela@slit.de>, December 2002.
*
*/
/*
* This file handles the architecture-dependent parts of initialization
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/acpi.h>
#include <linux/sfi.h>
#include <linux/apm_bios.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/console.h>
#include <linux/mca.h>
#include <linux/root_dev.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/edd.h>
Firmware: add iSCSI iBFT Support Add /sysfs/firmware/ibft/[initiator|targetX|ethernetX] directories along with text properties which export the the iSCSI Boot Firmware Table (iBFT) structure. What is iSCSI Boot Firmware Table? It is a mechanism for the iSCSI tools to extract from the machine NICs the iSCSI connection information so that they can automagically mount the iSCSI share/target. Currently the iSCSI information is hard-coded in the initrd. The /sysfs entries are read-only one-name-and-value fields. The usual set of data exposed is: # for a in `find /sys/firmware/ibft/ -type f -print`; do echo -n "$a: "; cat $a; done /sys/firmware/ibft/target0/target-name: iqn.2007.com.intel-sbx44:storage-10gb /sys/firmware/ibft/target0/nic-assoc: 0 /sys/firmware/ibft/target0/chap-type: 0 /sys/firmware/ibft/target0/lun: 00000000 /sys/firmware/ibft/target0/port: 3260 /sys/firmware/ibft/target0/ip-addr: 192.168.79.116 /sys/firmware/ibft/target0/flags: 3 /sys/firmware/ibft/target0/index: 0 /sys/firmware/ibft/ethernet0/mac: 00:11:25:9d:8b:01 /sys/firmware/ibft/ethernet0/vlan: 0 /sys/firmware/ibft/ethernet0/gateway: 192.168.79.254 /sys/firmware/ibft/ethernet0/origin: 0 /sys/firmware/ibft/ethernet0/subnet-mask: 255.255.252.0 /sys/firmware/ibft/ethernet0/ip-addr: 192.168.77.41 /sys/firmware/ibft/ethernet0/flags: 7 /sys/firmware/ibft/ethernet0/index: 0 /sys/firmware/ibft/initiator/initiator-name: iqn.2007-07.com:konrad.initiator /sys/firmware/ibft/initiator/flags: 3 /sys/firmware/ibft/initiator/index: 0 For full details of the IBFT structure please take a look at: ftp://ftp.software.ibm.com/systems/support/system_x_pdf/ibm_iscsi_boot_firmware_table_v1.02.pdf [akpm@linux-foundation.org: fix build] Signed-off-by: Konrad Rzeszutek <konradr@linux.vnet.ibm.com> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Peter Jones <pjones@redhat.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-04-10 10:50:41 +08:00
#include <linux/iscsi_ibft.h>
#include <linux/nodemask.h>
#include <linux/kexec.h>
#include <linux/dmi.h>
#include <linux/pfn.h>
#include <linux/pci.h>
#include <asm/pci-direct.h>
x86: early boot debugging via FireWire (ohci1394_dma=early) This patch adds a new configuration option, which adds support for a new early_param which gets checked in arch/x86/kernel/setup_{32,64}.c:setup_arch() to decide wether OHCI-1394 FireWire controllers should be initialized and enabled for physical DMA access to allow remote debugging of early problems like issues ACPI or other subsystems which are executed very early. If the config option is not enabled, no code is changed, and if the boot paramenter is not given, no new code is executed, and independent of that, all new code is freed after boot, so the config option can be even enabled in standard, non-debug kernels. With specialized tools, it is then possible to get debugging information from machines which have no serial ports (notebooks) such as the printk buffer contents, or any data which can be referenced from global pointers, if it is stored below the 4GB limit and even memory dumps of of the physical RAM region below the 4GB limit can be taken without any cooperation from the CPU of the host, so the machine can be crashed early, it does not matter. In the extreme, even kernel debuggers can be accessed in this way. I wrote a small kgdb module and an accompanying gdb stub for FireWire which allows to gdb to talk to kgdb using remote remory reads and writes over FireWire. An version of the gdb stub fore FireWire is able to read all global data from a system which is running a a normal kernel without any kernel debugger, without any interruption or support of the system's CPU. That way, e.g. the task struct and so on can be read and even manipulated when the physical DMA access is granted. A HOWTO is included in this patch, in Documentation/debugging-via-ohci1394.txt and I've put a copy online at ftp://ftp.suse.de/private/bk/firewire/docs/debugging-via-ohci1394.txt It also has links to all the tools which are available to make use of it another copy of it is online at: ftp://ftp.suse.de/private/bk/firewire/kernel/ohci1394_dma_early-v2.diff Signed-Off-By: Bernhard Kaindl <bk@suse.de> Tested-By: Thomas Renninger <trenn@suse.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:34:11 +08:00
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/delay.h>
#include <linux/kallsyms.h>
#include <linux/cpufreq.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <linux/uaccess.h>
#include <linux/percpu.h>
#include <linux/crash_dump.h>
#include <linux/tboot.h>
#include <video/edid.h>
#include <asm/mtrr.h>
#include <asm/apic.h>
#include <asm/trampoline.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/efi.h>
#include <asm/timer.h>
#include <asm/i8259.h>
#include <asm/sections.h>
#include <asm/dmi.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/setup_arch.h>
#include <asm/bios_ebda.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/bugs.h>
#include <asm/system.h>
#include <asm/vsyscall.h>
#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/dma.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/paravirt.h>
x86: Hypervisor detection and get tsc_freq from hypervisor Impact: Changes timebase calibration on Vmware. v3->v2 : Abstract the hypervisor detection and feature (tsc_freq) request behind a hypervisor.c file v2->v1 : Add a x86_hyper_vendor field to the cpuinfo_x86 structure. This avoids multiple calls to the hypervisor detection function. This patch adds function to detect if we are running under VMware. The current way to check if we are on VMware is following, # check if "hypervisor present bit" is set, if so read the 0x40000000 cpuid leaf and check for "VMwareVMware" signature. # if the above fails, check the DMI vendors name for "VMware" string if we find one we query the VMware hypervisor port to check if we are under VMware. The DMI + "VMware hypervisor port check" is needed for older VMware products, which don't implement the hypervisor signature cpuid leaf. Also note that since we are checking for the DMI signature the hypervisor port should never be accessed on native hardware. This patch also adds a hypervisor_get_tsc_freq function, instead of calibrating the frequency which can be error prone in virtualized environment, we ask the hypervisor for it. We get the frequency from the hypervisor by accessing the hypervisor port if we are running on VMware. Other hypervisors too can add code to the generic routine to get frequency on their platform. Signed-off-by: Alok N Kataria <akataria@vmware.com> Signed-off-by: Dan Hecht <dhecht@vmware.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2008-10-28 01:41:46 +08:00
#include <asm/hypervisor.h>
#include <asm/olpc_ofw.h>
#include <asm/percpu.h>
#include <asm/topology.h>
#include <asm/apicdef.h>
#include <asm/amd_nb.h>
#ifdef CONFIG_X86_64
#include <asm/numa_64.h>
#endif
#include <asm/mce.h>
#include <asm/alternative.h>
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
* The direct mapping extends to max_pfn_mapped, so that we can directly access
* apertures, ACPI and other tables without having to play with fixmaps.
*/
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
#endif
2009-02-27 09:35:44 +08:00
static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
unsigned long _brk_end = (unsigned long)__brk_base;
#ifdef CONFIG_X86_64
int default_cpu_present_to_apicid(int mps_cpu)
{
return __default_cpu_present_to_apicid(mps_cpu);
}
int default_check_phys_apicid_present(int phys_apicid)
{
return __default_check_phys_apicid_present(phys_apicid);
}
#endif
#ifndef CONFIG_DEBUG_BOOT_PARAMS
struct boot_params __initdata boot_params;
#else
struct boot_params boot_params;
#endif
/*
* Machine setup..
*/
static struct resource data_resource = {
.name = "Kernel data",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
static struct resource code_resource = {
.name = "Kernel code",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
static struct resource bss_resource = {
.name = "Kernel bss",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
#ifdef CONFIG_X86_32
/* cpu data as detected by the assembly code in head.S */
struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
/* common cpu data for all cpus */
struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
EXPORT_SYMBOL(boot_cpu_data);
static void set_mca_bus(int x)
{
#ifdef CONFIG_MCA
MCA_bus = x;
#endif
}
unsigned int def_to_bigsmp;
/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
unsigned int machine_submodel_id;
unsigned int BIOS_revision;
struct apm_info apm_info;
EXPORT_SYMBOL(apm_info);
#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
struct ist_info ist_info;
EXPORT_SYMBOL(ist_info);
#else
struct ist_info ist_info;
#endif
#else
struct cpuinfo_x86 boot_cpu_data __read_mostly = {
.x86_phys_bits = MAX_PHYSMEM_BITS,
};
EXPORT_SYMBOL(boot_cpu_data);
#endif
#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
unsigned long mmu_cr4_features;
#else
unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif
/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
int bootloader_type, bootloader_version;
/*
* Setup options
*/
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);
extern int root_mountflags;
unsigned long saved_video_mode;
#define RAMDISK_IMAGE_START_MASK 0x07FF
#define RAMDISK_PROMPT_FLAG 0x8000
#define RAMDISK_LOAD_FLAG 0x4000
static char __initdata command_line[COMMAND_LINE_SIZE];
#ifdef CONFIG_CMDLINE_BOOL
static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
#endif
#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
struct edd edd;
#ifdef CONFIG_EDD_MODULE
EXPORT_SYMBOL(edd);
#endif
/**
* copy_edd() - Copy the BIOS EDD information
* from boot_params into a safe place.
*
*/
static inline void __init copy_edd(void)
{
memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
sizeof(edd.mbr_signature));
memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info));
edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries;
edd.edd_info_nr = boot_params.eddbuf_entries;
}
#else
static inline void __init copy_edd(void)
{
}
#endif
void * __init extend_brk(size_t size, size_t align)
{
size_t mask = align - 1;
void *ret;
BUG_ON(_brk_start == 0);
BUG_ON(align & mask);
_brk_end = (_brk_end + mask) & ~mask;
BUG_ON((char *)(_brk_end + size) > __brk_limit);
ret = (void *)_brk_end;
_brk_end += size;
memset(ret, 0, size);
return ret;
}
#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
static void __init reserve_brk(void)
{
if (_brk_end > _brk_start)
memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
/* Mark brk area as locked down and no longer taking any
new allocations */
_brk_start = 0;
}
#ifdef CONFIG_BLK_DEV_INITRD
#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT)
static void __init relocate_initrd(void)
{
x86: Make sure free_init_pages() frees pages on page boundary When CONFIG_NO_BOOTMEM=y, it could use memory more effiently, or in a more compact fashion. Example: Allocated new RAMDISK: 00ec2000 - 0248ce57 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56 The new RAMDISK's end is not page aligned. Last page could be shared with other users. When free_init_pages are called for initrd or .init, the page could be freed and we could corrupt other data. code segment in free_init_pages(): | for (; addr < end; addr += PAGE_SIZE) { | ClearPageReserved(virt_to_page(addr)); | init_page_count(virt_to_page(addr)); | memset((void *)(addr & ~(PAGE_SIZE-1)), | POISON_FREE_INITMEM, PAGE_SIZE); | free_page(addr); | totalram_pages++; | } last half page could be used as one whole free page. So page align the boundaries. -v2: make the original initramdisk to be aligned, according to Johannes, otherwise we have the chance to lose one page. we still need to keep initrd_end not aligned, otherwise it could confuse decompressor. -v3: change to WARN_ON instead, suggested by Johannes. -v4: use PAGE_ALIGN, suggested by Johannes. We may fix that macro name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN Add comments about assuming ramdisk start is aligned in relocate_initrd(), change to re get ramdisk_image instead of save it to make diff smaller. Add warning for wrong range, suggested by Johannes. -v6: remove one WARN() We need to align beginning in free_init_pages() do not copy more than ramdisk_size, noticed by Johannes Reported-by: Stanislaw Gruszka <sgruszka@redhat.com> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: David Miller <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <1269830604-26214-3-git-send-email-yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-29 10:42:55 +08:00
/* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
x86: Make sure free_init_pages() frees pages on page boundary When CONFIG_NO_BOOTMEM=y, it could use memory more effiently, or in a more compact fashion. Example: Allocated new RAMDISK: 00ec2000 - 0248ce57 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56 The new RAMDISK's end is not page aligned. Last page could be shared with other users. When free_init_pages are called for initrd or .init, the page could be freed and we could corrupt other data. code segment in free_init_pages(): | for (; addr < end; addr += PAGE_SIZE) { | ClearPageReserved(virt_to_page(addr)); | init_page_count(virt_to_page(addr)); | memset((void *)(addr & ~(PAGE_SIZE-1)), | POISON_FREE_INITMEM, PAGE_SIZE); | free_page(addr); | totalram_pages++; | } last half page could be used as one whole free page. So page align the boundaries. -v2: make the original initramdisk to be aligned, according to Johannes, otherwise we have the chance to lose one page. we still need to keep initrd_end not aligned, otherwise it could confuse decompressor. -v3: change to WARN_ON instead, suggested by Johannes. -v4: use PAGE_ALIGN, suggested by Johannes. We may fix that macro name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN Add comments about assuming ramdisk start is aligned in relocate_initrd(), change to re get ramdisk_image instead of save it to make diff smaller. Add warning for wrong range, suggested by Johannes. -v6: remove one WARN() We need to align beginning in free_init_pages() do not copy more than ramdisk_size, noticed by Johannes Reported-by: Stanislaw Gruszka <sgruszka@redhat.com> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: David Miller <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <1269830604-26214-3-git-send-email-yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-29 10:42:55 +08:00
u64 area_size = PAGE_ALIGN(ramdisk_size);
u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
/* We need to move the initrd down into lowmem */
ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
PAGE_SIZE);
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. */
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",
ramdisk_here, ramdisk_here + ramdisk_size);
q = (char *)initrd_start;
/* Copy any lowmem portion of the initrd */
if (ramdisk_image < end_of_lowmem) {
clen = end_of_lowmem - ramdisk_image;
p = (char *)__va(ramdisk_image);
memcpy(q, p, clen);
q += clen;
ramdisk_image += clen;
ramdisk_size -= clen;
}
/* Copy the highmem portion of the initrd */
while (ramdisk_size) {
slop = ramdisk_image & ~PAGE_MASK;
clen = ramdisk_size;
if (clen > MAX_MAP_CHUNK-slop)
clen = MAX_MAP_CHUNK-slop;
mapaddr = ramdisk_image & PAGE_MASK;
p = early_memremap(mapaddr, clen+slop);
memcpy(q, p+slop, clen);
early_iounmap(p, clen+slop);
q += clen;
ramdisk_image += clen;
ramdisk_size -= clen;
}
x86: extend e820 ealy_res support 32bit move early_res related from e820_64.c to e820.c make edba detection to be done in head32.c remove smp_alloc_memory, because we have fixed trampoline address now. Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 10 files changed, 320 insertions(+), 319 deletions(-) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-18 16:18:57 +08:00
/* high pages is not converted by early_res_to_bootmem */
ramdisk_image = boot_params.hdr.ramdisk_image;
ramdisk_size = boot_params.hdr.ramdisk_size;
printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
" %08llx - %08llx\n",
ramdisk_image, ramdisk_image + ramdisk_size - 1,
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
static void __init reserve_initrd(void)
{
x86: Make sure free_init_pages() frees pages on page boundary When CONFIG_NO_BOOTMEM=y, it could use memory more effiently, or in a more compact fashion. Example: Allocated new RAMDISK: 00ec2000 - 0248ce57 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56 The new RAMDISK's end is not page aligned. Last page could be shared with other users. When free_init_pages are called for initrd or .init, the page could be freed and we could corrupt other data. code segment in free_init_pages(): | for (; addr < end; addr += PAGE_SIZE) { | ClearPageReserved(virt_to_page(addr)); | init_page_count(virt_to_page(addr)); | memset((void *)(addr & ~(PAGE_SIZE-1)), | POISON_FREE_INITMEM, PAGE_SIZE); | free_page(addr); | totalram_pages++; | } last half page could be used as one whole free page. So page align the boundaries. -v2: make the original initramdisk to be aligned, according to Johannes, otherwise we have the chance to lose one page. we still need to keep initrd_end not aligned, otherwise it could confuse decompressor. -v3: change to WARN_ON instead, suggested by Johannes. -v4: use PAGE_ALIGN, suggested by Johannes. We may fix that macro name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN Add comments about assuming ramdisk start is aligned in relocate_initrd(), change to re get ramdisk_image instead of save it to make diff smaller. Add warning for wrong range, suggested by Johannes. -v6: remove one WARN() We need to align beginning in free_init_pages() do not copy more than ramdisk_size, noticed by Johannes Reported-by: Stanislaw Gruszka <sgruszka@redhat.com> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: David Miller <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <1269830604-26214-3-git-send-email-yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-29 10:42:55 +08:00
/* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
x86: Make sure free_init_pages() frees pages on page boundary When CONFIG_NO_BOOTMEM=y, it could use memory more effiently, or in a more compact fashion. Example: Allocated new RAMDISK: 00ec2000 - 0248ce57 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56 The new RAMDISK's end is not page aligned. Last page could be shared with other users. When free_init_pages are called for initrd or .init, the page could be freed and we could corrupt other data. code segment in free_init_pages(): | for (; addr < end; addr += PAGE_SIZE) { | ClearPageReserved(virt_to_page(addr)); | init_page_count(virt_to_page(addr)); | memset((void *)(addr & ~(PAGE_SIZE-1)), | POISON_FREE_INITMEM, PAGE_SIZE); | free_page(addr); | totalram_pages++; | } last half page could be used as one whole free page. So page align the boundaries. -v2: make the original initramdisk to be aligned, according to Johannes, otherwise we have the chance to lose one page. we still need to keep initrd_end not aligned, otherwise it could confuse decompressor. -v3: change to WARN_ON instead, suggested by Johannes. -v4: use PAGE_ALIGN, suggested by Johannes. We may fix that macro name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN Add comments about assuming ramdisk start is aligned in relocate_initrd(), change to re get ramdisk_image instead of save it to make diff smaller. Add warning for wrong range, suggested by Johannes. -v6: remove one WARN() We need to align beginning in free_init_pages() do not copy more than ramdisk_size, noticed by Johannes Reported-by: Stanislaw Gruszka <sgruszka@redhat.com> Tested-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: David Miller <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <1269830604-26214-3-git-send-email-yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-29 10:42:55 +08:00
u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
return; /* No initrd provided by bootloader */
initrd_start = 0;
if (ramdisk_size >= (end_of_lowmem>>1)) {
memblock_x86_free_range(ramdisk_image, ramdisk_end);
printk(KERN_ERR "initrd too large to handle, "
"disabling initrd\n");
return;
}
printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image,
ramdisk_end);
if (ramdisk_end <= end_of_lowmem) {
/* All in lowmem, easy case */
/*
* don't need to reserve again, already reserved early
* in i386_start_kernel
*/
initrd_start = ramdisk_image + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
return;
}
relocate_initrd();
memblock_x86_free_range(ramdisk_image, ramdisk_end);
}
#else
static void __init reserve_initrd(void)
{
}
#endif /* CONFIG_BLK_DEV_INITRD */
static void __init parse_setup_data(void)
{
struct setup_data *data;
u64 pa_data;
if (boot_params.hdr.version < 0x0209)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, PAGE_SIZE);
switch (data->type) {
case SETUP_E820_EXT:
parse_e820_ext(data, pa_data);
break;
default:
break;
}
pa_data = data->next;
early_iounmap(data, PAGE_SIZE);
}
}
static void __init e820_reserve_setup_data(void)
{
struct setup_data *data;
u64 pa_data;
int found = 0;
if (boot_params.hdr.version < 0x0209)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
e820_update_range(pa_data, sizeof(*data)+data->len,
E820_RAM, E820_RESERVED_KERN);
found = 1;
pa_data = data->next;
early_iounmap(data, sizeof(*data));
}
if (!found)
return;
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
memcpy(&e820_saved, &e820, sizeof(struct e820map));
printk(KERN_INFO "extended physical RAM map:\n");
e820_print_map("reserve setup_data");
}
static void __init memblock_x86_reserve_range_setup_data(void)
{
struct setup_data *data;
u64 pa_data;
char buf[32];
if (boot_params.hdr.version < 0x0209)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
sprintf(buf, "setup data %x", data->type);
memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
pa_data = data->next;
early_iounmap(data, sizeof(*data));
}
}
/*
* --------- Crashkernel reservation ------------------------------
*/
#ifdef CONFIG_KEXEC
static inline unsigned long long get_total_mem(void)
{
unsigned long long total;
total = max_pfn - min_low_pfn;
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;
unsigned long long crash_size, crash_base;
int ret;
total_mem = get_total_mem();
ret = parse_crashkernel(boot_command_line, total_mem,
&crash_size, &crash_base);
if (ret != 0 || crash_size <= 0)
return;
/* 0 means: find the address automatically */
if (crash_base <= 0) {
const unsigned long long alignment = 16<<20; /* 16M */
/*
* 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 = 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;
}
}
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",
(unsigned long)(crash_size >> 20),
(unsigned long)(crash_base >> 20),
(unsigned long)(total_mem >> 20));
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
insert_resource(&iomem_resource, &crashk_res);
}
#else
static void __init reserve_crashkernel(void)
{
}
#endif
static struct resource standard_io_resources[] = {
{ .name = "dma1", .start = 0x00, .end = 0x1f,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "pic1", .start = 0x20, .end = 0x21,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "timer0", .start = 0x40, .end = 0x43,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "timer1", .start = 0x50, .end = 0x53,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "keyboard", .start = 0x60, .end = 0x60,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "keyboard", .start = 0x64, .end = 0x64,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "dma page reg", .start = 0x80, .end = 0x8f,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "pic2", .start = 0xa0, .end = 0xa1,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "dma2", .start = 0xc0, .end = 0xdf,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "fpu", .start = 0xf0, .end = 0xff,
.flags = IORESOURCE_BUSY | IORESOURCE_IO }
};
void __init reserve_standard_io_resources(void)
{
int i;
/* request I/O space for devices used on all i[345]86 PCs */
for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
request_resource(&ioport_resource, &standard_io_resources[i]);
}
/*
* 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;
addr = find_ibft_region(&size);
if (size)
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
memblock_x86_reserve_range(addr, addr + size, "* ibft");
}
static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
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, 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.
* take them out.
*/
e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
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);
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
static u64 __init get_max_mapped(void)
{
u64 end = max_pfn_mapped;
end <<= PAGE_SHIFT;
return end;
}
/*
* 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
* for initialization. Note, the efi init code path is determined by the
* global efi_enabled. This allows the same kernel image to be used on existing
* systems (with a traditional BIOS) as well as on EFI systems.
*/
/*
* setup_arch - architecture-specific boot-time initializations
*
* Note: On x86_64, fixmaps are ready for use even before this is called.
*/
void __init setup_arch(char **cmdline_p)
{
x86: Export k8 physical topology To eventually interleave emulated nodes over physical nodes, we need to know the physical topology of the machine without actually registering it. This does the k8 node setup in two parts: detection and registration. NUMA emulation can then used the physical topology detected to setup the address ranges of emulated nodes accordingly. If emulation isn't used, the k8 nodes are registered as normal. Two formals are added to the x86 NUMA setup functions: `acpi' and `k8'. These represent whether ACPI or K8 NUMA has been detected; both cannot be true at the same time. This specifies to the NUMA emulation code whether an underlying physical NUMA topology exists and which interface to use. This patch deals solely with separating the k8 setup path into Northbridge detection and registration steps and leaves the ACPI changes for a subsequent patch. The `acpi' formal is added here, however, to avoid touching all the header files again in the next patch. This approach also ensures emulated nodes will not span physical nodes so the true memory latency is not misrepresented. k8_get_nodes() may now be used to export the k8 physical topology of the machine for NUMA emulation. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andreas Herrmann <andreas.herrmann3@amd.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Ankita Garg <ankita@in.ibm.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <alpine.DEB.1.00.0909251518400.14754@chino.kir.corp.google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-26 06:20:00 +08:00
int acpi = 0;
int amd = 0;
unsigned long flags;
x86: Export k8 physical topology To eventually interleave emulated nodes over physical nodes, we need to know the physical topology of the machine without actually registering it. This does the k8 node setup in two parts: detection and registration. NUMA emulation can then used the physical topology detected to setup the address ranges of emulated nodes accordingly. If emulation isn't used, the k8 nodes are registered as normal. Two formals are added to the x86 NUMA setup functions: `acpi' and `k8'. These represent whether ACPI or K8 NUMA has been detected; both cannot be true at the same time. This specifies to the NUMA emulation code whether an underlying physical NUMA topology exists and which interface to use. This patch deals solely with separating the k8 setup path into Northbridge detection and registration steps and leaves the ACPI changes for a subsequent patch. The `acpi' formal is added here, however, to avoid touching all the header files again in the next patch. This approach also ensures emulated nodes will not span physical nodes so the true memory latency is not misrepresented. k8_get_nodes() may now be used to export the k8 physical topology of the machine for NUMA emulation. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andreas Herrmann <andreas.herrmann3@amd.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Ankita Garg <ankita@in.ibm.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <alpine.DEB.1.00.0909251518400.14754@chino.kir.corp.google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-26 06:20:00 +08:00
#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
/*
* 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();
early_cpu_init();
early_ioremap_init();
setup_olpc_ofw_pgd();
ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
screen_info = boot_params.screen_info;
edid_info = boot_params.edid_info;
#ifdef CONFIG_X86_32
apm_info.bios = boot_params.apm_bios_info;
ist_info = boot_params.ist_info;
if (boot_params.sys_desc_table.length != 0) {
set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2);
machine_id = boot_params.sys_desc_table.table[0];
machine_submodel_id = boot_params.sys_desc_table.table[1];
BIOS_revision = boot_params.sys_desc_table.table[2];
}
#endif
saved_video_mode = boot_params.hdr.vid_mode;
bootloader_type = boot_params.hdr.type_of_loader;
if ((bootloader_type >> 4) == 0xe) {
bootloader_type &= 0xf;
bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
}
bootloader_version = bootloader_type & 0xf;
bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
#endif
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
#ifdef CONFIG_X86_32
"EL32",
#else
"EL64",
#endif
4)) {
efi_enabled = 1;
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 */
e820_reserve_setup_data();
copy_edd();
if (!boot_params.hdr.root_flags)
root_mountflags &= ~MS_RDONLY;
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
2009-02-27 09:35:44 +08:00
init_mm.brk = _brk_end;
code_resource.start = virt_to_phys(_text);
code_resource.end = virt_to_phys(_etext)-1;
data_resource.start = virt_to_phys(_etext);
data_resource.end = virt_to_phys(_edata)-1;
bss_resource.start = virt_to_phys(&__bss_start);
bss_resource.end = virt_to_phys(&__bss_stop)-1;
#ifdef CONFIG_CMDLINE_BOOL
#ifdef CONFIG_CMDLINE_OVERRIDE
strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
#else
if (builtin_cmdline[0]) {
/* append boot loader cmdline to builtin */
strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
}
#endif
#endif
strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
/*
* x86_configure_nx() is called before parse_early_param() to detect
* whether hardware doesn't support NX (so that the early EHCI debug
* console setup can safely call set_fixmap()). It may then be called
* again from within noexec_setup() during parsing early parameters
* to honor the respective command line option.
*/
x86_configure_nx();
parse_early_param();
x86_report_nx();
/* after early param, so could get panic from serial */
memblock_x86_reserve_range_setup_data();
if (acpi_mps_check()) {
#ifdef CONFIG_X86_LOCAL_APIC
disable_apic = 1;
#endif
setup_clear_cpu_cap(X86_FEATURE_APIC);
}
#ifdef CONFIG_PCI
if (pci_early_dump_regs)
early_dump_pci_devices();
#endif
finish_e820_parsing();
if (efi_enabled)
efi_init();
dmi_scan_machine();
x86: Hypervisor detection and get tsc_freq from hypervisor Impact: Changes timebase calibration on Vmware. v3->v2 : Abstract the hypervisor detection and feature (tsc_freq) request behind a hypervisor.c file v2->v1 : Add a x86_hyper_vendor field to the cpuinfo_x86 structure. This avoids multiple calls to the hypervisor detection function. This patch adds function to detect if we are running under VMware. The current way to check if we are on VMware is following, # check if "hypervisor present bit" is set, if so read the 0x40000000 cpuid leaf and check for "VMwareVMware" signature. # if the above fails, check the DMI vendors name for "VMware" string if we find one we query the VMware hypervisor port to check if we are under VMware. The DMI + "VMware hypervisor port check" is needed for older VMware products, which don't implement the hypervisor signature cpuid leaf. Also note that since we are checking for the DMI signature the hypervisor port should never be accessed on native hardware. This patch also adds a hypervisor_get_tsc_freq function, instead of calibrating the frequency which can be error prone in virtualized environment, we ask the hypervisor for it. We get the frequency from the hypervisor by accessing the hypervisor port if we are running on VMware. Other hypervisors too can add code to the generic routine to get frequency on their platform. Signed-off-by: Alok N Kataria <akataria@vmware.com> Signed-off-by: Dan Hecht <dhecht@vmware.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2008-10-28 01:41:46 +08:00
/*
* VMware detection requires dmi to be available, so this
* needs to be done after dmi_scan_machine, for the BP.
*/
init_hypervisor_platform();
x86: Hypervisor detection and get tsc_freq from hypervisor Impact: Changes timebase calibration on Vmware. v3->v2 : Abstract the hypervisor detection and feature (tsc_freq) request behind a hypervisor.c file v2->v1 : Add a x86_hyper_vendor field to the cpuinfo_x86 structure. This avoids multiple calls to the hypervisor detection function. This patch adds function to detect if we are running under VMware. The current way to check if we are on VMware is following, # check if "hypervisor present bit" is set, if so read the 0x40000000 cpuid leaf and check for "VMwareVMware" signature. # if the above fails, check the DMI vendors name for "VMware" string if we find one we query the VMware hypervisor port to check if we are under VMware. The DMI + "VMware hypervisor port check" is needed for older VMware products, which don't implement the hypervisor signature cpuid leaf. Also note that since we are checking for the DMI signature the hypervisor port should never be accessed on native hardware. This patch also adds a hypervisor_get_tsc_freq function, instead of calibrating the frequency which can be error prone in virtualized environment, we ask the hypervisor for it. We get the frequency from the hypervisor by accessing the hypervisor port if we are running on VMware. Other hypervisors too can add code to the generic routine to get frequency on their platform. Signed-off-by: Alok N Kataria <akataria@vmware.com> Signed-off-by: Dan Hecht <dhecht@vmware.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2008-10-28 01:41:46 +08:00
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
insert_resource(&iomem_resource, &code_resource);
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
E820_RESERVED);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
printk(KERN_INFO "fixed physical RAM map:\n");
e820_print_map("bad_ppro");
}
#else
early_gart_iommu_check();
#endif
/*
* partially used pages are not usable - thus
* we are rounding upwards:
*/
max_pfn = e820_end_of_ram_pfn();
/* update e820 for memory not covered by WB MTRRs */
mtrr_bp_init();
if (mtrr_trim_uncached_memory(max_pfn))
max_pfn = e820_end_of_ram_pfn();
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
find_low_pfn_range();
#else
num_physpages = max_pfn;
check_x2apic();
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
max_low_pfn = e820_end_of_low_ram_pfn();
else
max_low_pfn = max_pfn;
high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
#endif
/*
* Find and reserve possible boot-time SMP configuration:
*/
find_smp_config();
reserve_ibft_region();
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
/*
* Need to conclude brk, before memblock_x86_fill()
* it could use memblock_find_in_range, could overlap with
* brk area.
*/
reserve_brk();
memblock.current_limit = get_max_mapped();
memblock_x86_fill();
/* 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);
reserve_trampoline_memory();
#ifdef CONFIG_ACPI_SLEEP
/*
* Reserve low memory region for sleep support.
* even before init_memory_mapping
*/
acpi_reserve_wakeup_memory();
#endif
init_gbpages();
/* max_pfn_mapped is updated here */
max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
max_pfn_mapped = max_low_pfn_mapped;
#ifdef CONFIG_X86_64
if (max_pfn > max_low_pfn) {
max_pfn_mapped = init_memory_mapping(1UL<<32,
max_pfn<<PAGE_SHIFT);
/* can we preseve max_low_pfn ?*/
max_low_pfn = max_pfn;
}
#endif
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
memblock.current_limit = get_max_mapped();
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
*/
#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
if (init_ohci1394_dma_early)
init_ohci1394_dma_on_all_controllers();
#endif
reserve_initrd();
reserve_crashkernel();
vsmp_init();
io_delay_init();
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
acpi_boot_table_init();
early_acpi_boot_init();
#ifdef CONFIG_ACPI_NUMA
/*
* Parse SRAT to discover nodes.
*/
acpi = acpi_numa_init();
#endif
#ifdef CONFIG_AMD_NUMA
if (!acpi)
amd = !amd_numa_init(0, max_pfn);
x86: Export k8 physical topology To eventually interleave emulated nodes over physical nodes, we need to know the physical topology of the machine without actually registering it. This does the k8 node setup in two parts: detection and registration. NUMA emulation can then used the physical topology detected to setup the address ranges of emulated nodes accordingly. If emulation isn't used, the k8 nodes are registered as normal. Two formals are added to the x86 NUMA setup functions: `acpi' and `k8'. These represent whether ACPI or K8 NUMA has been detected; both cannot be true at the same time. This specifies to the NUMA emulation code whether an underlying physical NUMA topology exists and which interface to use. This patch deals solely with separating the k8 setup path into Northbridge detection and registration steps and leaves the ACPI changes for a subsequent patch. The `acpi' formal is added here, however, to avoid touching all the header files again in the next patch. This approach also ensures emulated nodes will not span physical nodes so the true memory latency is not misrepresented. k8_get_nodes() may now be used to export the k8 physical topology of the machine for NUMA emulation. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andreas Herrmann <andreas.herrmann3@amd.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Ankita Garg <ankita@in.ibm.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <alpine.DEB.1.00.0909251518400.14754@chino.kir.corp.google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-26 06:20:00 +08:00
#endif
initmem_init(0, max_pfn, acpi, amd);
memblock_find_dma_reserve();
dma32_reserve_bootmem();
#ifdef CONFIG_KVM_CLOCK
kvmclock_init();
#endif
x86_init.paging.pagetable_setup_start(swapper_pg_dir);
paging_init();
x86_init.paging.pagetable_setup_done(swapper_pg_dir);
x86: early boot debugging via FireWire (ohci1394_dma=early) This patch adds a new configuration option, which adds support for a new early_param which gets checked in arch/x86/kernel/setup_{32,64}.c:setup_arch() to decide wether OHCI-1394 FireWire controllers should be initialized and enabled for physical DMA access to allow remote debugging of early problems like issues ACPI or other subsystems which are executed very early. If the config option is not enabled, no code is changed, and if the boot paramenter is not given, no new code is executed, and independent of that, all new code is freed after boot, so the config option can be even enabled in standard, non-debug kernels. With specialized tools, it is then possible to get debugging information from machines which have no serial ports (notebooks) such as the printk buffer contents, or any data which can be referenced from global pointers, if it is stored below the 4GB limit and even memory dumps of of the physical RAM region below the 4GB limit can be taken without any cooperation from the CPU of the host, so the machine can be crashed early, it does not matter. In the extreme, even kernel debuggers can be accessed in this way. I wrote a small kgdb module and an accompanying gdb stub for FireWire which allows to gdb to talk to kgdb using remote remory reads and writes over FireWire. An version of the gdb stub fore FireWire is able to read all global data from a system which is running a a normal kernel without any kernel debugger, without any interruption or support of the system's CPU. That way, e.g. the task struct and so on can be read and even manipulated when the physical DMA access is granted. A HOWTO is included in this patch, in Documentation/debugging-via-ohci1394.txt and I've put a copy online at ftp://ftp.suse.de/private/bk/firewire/docs/debugging-via-ohci1394.txt It also has links to all the tools which are available to make use of it another copy of it is online at: ftp://ftp.suse.de/private/bk/firewire/kernel/ohci1394_dma_early-v2.diff Signed-Off-By: Bernhard Kaindl <bk@suse.de> Tested-By: Thomas Renninger <trenn@suse.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:34:11 +08:00
#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
x86-32: Separate 1:1 pagetables from swapper_pg_dir This patch fixes machine crashes which occur when heavily exercising the CPU hotplug codepaths on a 32-bit kernel. These crashes are caused by AMD Erratum 383 and result in a fatal machine check exception. Here's the scenario: 1. On 32-bit, the swapper_pg_dir page table is used as the initial page table for booting a secondary CPU. 2. To make this work, swapper_pg_dir needs a direct mapping of physical memory in it (the low mappings). By adding those low, large page (2M) mappings (PAE kernel), we create the necessary conditions for Erratum 383 to occur. 3. Other CPUs which do not participate in the off- and onlining game may use swapper_pg_dir while the low mappings are present (when leave_mm is called). For all steps below, the CPU referred to is a CPU that is using swapper_pg_dir, and not the CPU which is being onlined. 4. The presence of the low mappings in swapper_pg_dir can result in TLB entries for addresses below __PAGE_OFFSET to be established speculatively. These TLB entries are marked global and large. 5. When the CPU with such TLB entry switches to another page table, this TLB entry remains because it is global. 6. The process then generates an access to an address covered by the above TLB entry but there is a permission mismatch - the TLB entry covers a large global page not accessible to userspace. 7. Due to this permission mismatch a new 4kb, user TLB entry gets established. Further, Erratum 383 provides for a small window of time where both TLB entries are present. This results in an uncorrectable machine check exception signalling a TLB multimatch which panics the machine. There are two ways to fix this issue: 1. Always do a global TLB flush when a new cr3 is loaded and the old page table was swapper_pg_dir. I consider this a hack hard to understand and with performance implications 2. Do not use swapper_pg_dir to boot secondary CPUs like 64-bit does. This patch implements solution 2. It introduces a trampoline_pg_dir which has the same layout as swapper_pg_dir with low_mappings. This page table is used as the initial page table of the booting CPU. Later in the bringup process, it switches to swapper_pg_dir and does a global TLB flush. This fixes the crashes in our test cases. -v2: switch to swapper_pg_dir right after entering start_secondary() so that we are able to access percpu data which might not be mapped in the trampoline page table. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> LKML-Reference: <20100816123833.GB28147@aftab> Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-16 20:38:33 +08:00
x86, intel_txt: Intel TXT boot support This patch adds kernel configuration and boot support for Intel Trusted Execution Technology (Intel TXT). Intel's technology for safer computing, Intel Trusted Execution Technology (Intel TXT), defines platform-level enhancements that provide the building blocks for creating trusted platforms. Intel TXT was formerly known by the code name LaGrande Technology (LT). Intel TXT in Brief: o Provides dynamic root of trust for measurement (DRTM) o Data protection in case of improper shutdown o Measurement and verification of launched environment Intel TXT is part of the vPro(TM) brand and is also available some non-vPro systems. It is currently available on desktop systems based on the Q35, X38, Q45, and Q43 Express chipsets (e.g. Dell Optiplex 755, HP dc7800, etc.) and mobile systems based on the GM45, PM45, and GS45 Express chipsets. For more information, see http://www.intel.com/technology/security/. This site also has a link to the Intel TXT MLE Developers Manual, which has been updated for the new released platforms. A much more complete description of how these patches support TXT, how to configure a system for it, etc. is in the Documentation/intel_txt.txt file in this patch. This patch provides the TXT support routines for complete functionality, documentation for TXT support and for the changes to the boot_params structure, and boot detection of a TXT launch. Attempts to shutdown (reboot, Sx) the system will result in platform resets; subsequent patches will support these shutdown modes properly. Documentation/intel_txt.txt | 210 +++++++++++++++++++++ Documentation/x86/zero-page.txt | 1 arch/x86/include/asm/bootparam.h | 3 arch/x86/include/asm/fixmap.h | 3 arch/x86/include/asm/tboot.h | 197 ++++++++++++++++++++ arch/x86/kernel/Makefile | 1 arch/x86/kernel/setup.c | 4 arch/x86/kernel/tboot.c | 379 +++++++++++++++++++++++++++++++++++++++ security/Kconfig | 30 +++ 9 files changed, 827 insertions(+), 1 deletion(-) Signed-off-by: Joseph Cihula <joseph.cihula@intel.com> Signed-off-by: Shane Wang <shane.wang@intel.com> Signed-off-by: Gang Wei <gang.wei@intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-07-01 10:30:59 +08:00
tboot_probe();
#ifdef CONFIG_X86_64
map_vsyscall();
#endif
generic_apic_probe();
early_quirks();
/*
* Read APIC and some other early information from ACPI tables.
*/
acpi_boot_init();
sfi_init();
/*
* get boot-time SMP configuration:
*/
if (smp_found_config)
get_smp_config();
prefill_possible_map();
#ifdef CONFIG_X86_64
init_cpu_to_node();
#endif
init_apic_mappings();
ioapic_and_gsi_init();
kvm_guest_init();
e820_reserve_resources();
e820_mark_nosave_regions(max_low_pfn);
x86_init.resources.reserve_resources();
e820_setup_gap();
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
#endif
x86_init.oem.banner();
mcheck_init();
local_irq_save(flags);
arch_init_ideal_nop5();
local_irq_restore(flags);
}
#ifdef CONFIG_X86_32
static struct resource video_ram_resource = {
.name = "Video RAM area",
.start = 0xa0000,
.end = 0xbffff,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
void __init i386_reserve_resources(void)
{
request_resource(&iomem_resource, &video_ram_resource);
reserve_standard_io_resources();
}
#endif /* CONFIG_X86_32 */