when initialising the APIC and IO-APIC components.
apm= [APM] Advanced Power Management
- See header of arch/i386/kernel/apm.c.
+ See header of arch/x86/kernel/apm_32.c.
arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
Format: <io>,<irq>,<nodeID>
See drivers/char/README.epca and
Documentation/digiepca.txt.
+ disable_mtrr_cleanup [X86]
+ enable_mtrr_cleanup [X86]
+ The kernel tries to adjust MTRR layout from continuous
+ to discrete, to make X server driver able to add WB
+ entry later. This parameter enables/disables that.
+
+ mtrr_chunk_size=nn[KMG] [X86]
+ used for mtrr cleanup. It is largest continous chunk
+ that could hold holes aka. UC entries.
+
+ mtrr_gran_size=nn[KMG] [X86]
+ Used for mtrr cleanup. It is granularity of mtrr block.
+ Default is 1.
+ Large value could prevent small alignment from
+ using up MTRRs.
+
+ mtrr_spare_reg_nr=n [X86]
+ Format: <integer>
+ Range: 0,7 : spare reg number
+ Default : 1
+ Used for mtrr cleanup. It is spare mtrr entries number.
+ Set to 2 or more if your graphical card needs more.
+
disable_mtrr_trim [X86, Intel and AMD only]
By default the kernel will trim any uncacheable
memory out of your available memory pool based on
elanfreq= [X86-32]
See comment before function elanfreq_setup() in
- arch/i386/kernel/cpu/cpufreq/elanfreq.c.
+ arch/x86/kernel/cpu/cpufreq/elanfreq.c.
elevator= [IOSCHED]
Format: {"anticipatory" | "cfq" | "deadline" | "noop"}
Format: <reboot_mode>[,<reboot_mode2>[,...]]
See arch/*/kernel/reboot.c or arch/*/kernel/process.c
+ relax_domain_level=
+ [KNL, SMP] Set scheduler's default relax_domain_level.
+ See Documentation/cpusets.txt.
+
reserve= [KNL,BUGS] Force the kernel to ignore some iomem area
reservetop= [X86-32]
select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
select HAVE_ARCH_KGDB if !X86_VOYAGER
- config DEFCONFIG_LIST
+ config ARCH_DEFCONFIG
string
- depends on X86_32
- option defconfig_list
- default "arch/x86/configs/i386_defconfig"
-
- config DEFCONFIG_LIST
- string
- depends on X86_64
- option defconfig_list
- default "arch/x86/configs/x86_64_defconfig"
+ default "arch/x86/configs/i386_defconfig" if X86_32
+ default "arch/x86/configs/x86_64_defconfig" if X86_64
config GENERIC_LOCKBREAK
If you do not specifically know you have a Voyager based machine,
say N here, otherwise the kernel you build will not be bootable.
-config X86_NUMAQ
- bool "NUMAQ (IBM/Sequent)"
- depends on SMP && X86_32
- select NUMA
- help
- This option is used for getting Linux to run on a (IBM/Sequent) NUMA
- multiquad box. This changes the way that processors are bootstrapped,
- and uses Clustered Logical APIC addressing mode instead of Flat Logical.
- You will need a new lynxer.elf file to flash your firmware with - send
- email to <Martin.Bligh@us.ibm.com>.
-
-config X86_SUMMIT
- bool "Summit/EXA (IBM x440)"
- depends on X86_32 && SMP
- help
- This option is needed for IBM systems that use the Summit/EXA chipset.
- In particular, it is needed for the x440.
-
- If you don't have one of these computers, you should say N here.
- If you want to build a NUMA kernel, you must select ACPI.
-
-config X86_BIGSMP
- bool "Support for other sub-arch SMP systems with more than 8 CPUs"
- depends on X86_32 && SMP
- help
- This option is needed for the systems that have more than 8 CPUs
- and if the system is not of any sub-arch type above.
-
- If you don't have such a system, you should say N here.
-
config X86_VISWS
bool "SGI 320/540 (Visual Workstation)"
depends on X86_32
and vice versa. See <file:Documentation/sgi-visws.txt> for details.
config X86_GENERICARCH
- bool "Generic architecture (Summit, bigsmp, ES7000, default)"
+ bool "Generic architecture"
depends on X86_32
help
- This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
- It is intended for a generic binary kernel.
- If you want a NUMA kernel, select ACPI. We need SRAT for NUMA.
+ This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default
+ subarchitectures. It is intended for a generic binary kernel.
+ if you select them all, kernel will probe it one by one. and will
+ fallback to default.
+
+if X86_GENERICARCH
+
+config X86_NUMAQ
+ bool "NUMAQ (IBM/Sequent)"
+ depends on SMP && X86_32
+ select NUMA
+ help
+ This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
+ NUMA multiquad box. This changes the way that processors are
+ bootstrapped, and uses Clustered Logical APIC addressing mode instead
+ of Flat Logical. You will need a new lynxer.elf file to flash your
+ firmware with - send email to <Martin.Bligh@us.ibm.com>.
+
+config X86_SUMMIT
+ bool "Summit/EXA (IBM x440)"
+ depends on X86_32 && SMP
+ help
+ This option is needed for IBM systems that use the Summit/EXA chipset.
+ In particular, it is needed for the x440.
config X86_ES7000
bool "Support for Unisys ES7000 IA32 series"
help
Support for Unisys ES7000 systems. Say 'Y' here if this kernel is
supposed to run on an IA32-based Unisys ES7000 system.
- Only choose this option if you have such a system, otherwise you
- should say N here.
+
+config X86_BIGSMP
+ bool "Support for big SMP systems with more than 8 CPUs"
+ depends on X86_32 && SMP
+ help
+ This option is needed for the systems that have more than 8 CPUs
+ and if the system is not of any sub-arch type above.
+
+endif
config X86_RDC321X
bool "RDC R-321x SoC"
config KVM_CLOCK
bool "KVM paravirtualized clock"
select PARAVIRT
+ select PARAVIRT_CLOCK
depends on !(X86_VISWS || X86_VOYAGER)
help
Turning on this option will allow you to run a paravirtualized clock
over full virtualization. However, when run without a hypervisor
the kernel is theoretically slower and slightly larger.
+ config PARAVIRT_CLOCK
+ bool
+ default n
+
endif
config MEMTEST_BOOTPARAM
config NUMA
bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
depends on SMP
- depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL)
+ depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || X86_SUMMIT && ACPI) && EXPERIMENTAL)
default n if X86_PC
- default y if (X86_NUMAQ || X86_SUMMIT)
+ default y if (X86_NUMAQ || X86_SUMMIT || X86_GENERICARCH)
help
Enable NUMA (Non Uniform Memory Access) support.
The kernel will try to allocate memory used by a CPU on the
number of nodes. This is only useful for debugging.
config NODES_SHIFT
- int "Max num nodes shift(1-15)"
- range 1 15 if X86_64
+ int "Max num nodes shift(1-9)"
+ range 1 9 if X86_64
default "6" if X86_64
default "4" if X86_NUMAQ
default "3"
See <file:Documentation/mtrr.txt> for more information.
+config MTRR_SANITIZER
+ def_bool y
+ prompt "MTRR cleanup support"
+ depends on MTRR
+ help
+ Convert MTRR layout from continuous to discrete, so some X driver
+ could add WB entries.
+
+ Say N here if you see bootup problems (boot crash, boot hang,
+ spontaneous reboots).
+
+ Could be disabled with disable_mtrr_cleanup. Also mtrr_chunk_size
+ could be used to send largest mtrr entry size for continuous block
+ to hold holes (aka. UC entries)
+
+ If unsure, say Y.
+
+config MTRR_SANITIZER_ENABLE_DEFAULT
+ int "MTRR cleanup enable value (0-1)"
+ range 0 1
+ default "0"
+ depends on MTRR_SANITIZER
+ help
+ Enable mtrr cleanup default value
+
+config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT
+ int "MTRR cleanup spare reg num (0-7)"
+ range 0 7
+ default "1"
+ depends on MTRR_SANITIZER
+ help
+ mtrr cleanup spare entries default, it can be changed via
+ mtrr_spare_reg_nr=
+
config X86_PAT
bool
prompt "x86 PAT support"
config PCI_GODIRECT
bool "Direct"
- config PCI_GOANY
- bool "Any"
-
config PCI_GOOLPC
bool "OLPC"
depends on OLPC
+ config PCI_GOANY
+ bool "Any"
+
endchoice
config PCI_BIOS
depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY)
config PCI_OLPC
- bool
- depends on PCI && PCI_GOOLPC
- default y
+ def_bool y
+ depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY)
config PCI_DOMAINS
def_bool y
source "lib/Kconfig.debug"
config NONPROMISC_DEVMEM
- bool "Disable promiscuous /dev/mem"
+ bool "Filter access to /dev/mem"
help
- The /dev/mem file by default only allows userspace access to PCI
- space and the BIOS code and data regions. This is sufficient for
- dosemu and X and all common users of /dev/mem. With this config
- option, you allow userspace access to all of memory, including
- kernel and userspace memory. Accidental access to this is
- obviously disasterous, but specific access can be used by people
- debugging the kernel.
+ If this option is left off, you allow userspace access to all
+ of memory, including kernel and userspace memory. Accidental
+ access to this is obviously disastrous, but specific access can
+ be used by people debugging the kernel.
+
+ If this option is switched on, the /dev/mem file only allows
+ userspace access to PCI space and the BIOS code and data regions.
+ This is sufficient for dosemu and X and all common users of
+ /dev/mem.
+
+ If in doubt, say Y.
config EARLY_PRINTK
bool "Early printk" if EMBEDDED
config X86_FIND_SMP_CONFIG
def_bool y
- depends on X86_LOCAL_APIC || X86_VOYAGER
+ depends on X86_MPPARSE || X86_VOYAGER || X86_VISWS
depends on X86_32
config X86_MPPARSE
# Makefile for the linux kernel.
#
-extra-y := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds
+extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o setup64.o
-obj-y += bootflag.o e820_$(BITS).o
+obj-y += bootflag.o e820_$(BITS).o e820.o
obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o
obj-$(CONFIG_X86_64) += bugs_64.o
obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
+ obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
static void __cpuinit acpi_register_lapic(int id, u8 enabled)
{
+ unsigned int ver = 0;
+
if (!enabled) {
++disabled_cpus;
return;
}
- generic_processor_info(id, 0);
+ #ifdef CONFIG_X86_32
+ if (boot_cpu_physical_apicid != -1U)
+ ver = apic_version[boot_cpu_physical_apicid];
+ #endif
+
+ generic_processor_info(id, ver);
}
static int __init
#ifdef CONFIG_X86_IO_APIC
-struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS];
-
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
mp_lapic_addr = address;
set_fixmap_nocache(FIX_APIC_BASE, address);
- if (boot_cpu_physical_apicid == -1U)
+ if (boot_cpu_physical_apicid == -1U) {
boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ #ifdef CONFIG_X86_32
+ apic_version[boot_cpu_physical_apicid] =
+ GET_APIC_VERSION(apic_read(APIC_LVR));
+ #endif
+ }
}
static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
+#define MP_ISA_BUS 0
+
+#ifdef CONFIG_X86_ES7000
+extern int es7000_plat;
+#endif
+
+static struct {
+ int apic_id;
+ int gsi_base;
+ int gsi_end;
+ DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
+static int mp_find_ioapic(int gsi)
+{
+ int i = 0;
+
+ /* Find the IOAPIC that manages this GSI. */
+ for (i = 0; i < nr_ioapics; i++) {
+ if ((gsi >= mp_ioapic_routing[i].gsi_base)
+ && (gsi <= mp_ioapic_routing[i].gsi_end))
+ return i;
+ }
+
+ printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi);
+ return -1;
+}
+
+static u8 __init uniq_ioapic_id(u8 id)
+{
+#ifdef CONFIG_X86_32
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+ !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ return io_apic_get_unique_id(nr_ioapics, id);
+ else
+ return id;
+#else
+ int i;
+ DECLARE_BITMAP(used, 256);
+ bitmap_zero(used, 256);
+ for (i = 0; i < nr_ioapics; i++) {
+ struct mp_config_ioapic *ia = &mp_ioapics[i];
+ __set_bit(ia->mp_apicid, used);
+ }
+ if (!test_bit(id, used))
+ return id;
+ return find_first_zero_bit(used, 256);
+#endif
+}
+
+static int bad_ioapic(unsigned long address)
+{
+ if (nr_ioapics >= MAX_IO_APICS) {
+ printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
+ "(found %d)\n", MAX_IO_APICS, nr_ioapics);
+ panic("Recompile kernel with bigger MAX_IO_APICS!\n");
+ }
+ if (!address) {
+ printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
+ " found in table, skipping!\n");
+ return 1;
+ }
+ return 0;
+}
+
+void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
+{
+ int idx = 0;
+
+ if (bad_ioapic(address))
+ return;
+
+ idx = nr_ioapics;
+
+ mp_ioapics[idx].mp_type = MP_IOAPIC;
+ mp_ioapics[idx].mp_flags = MPC_APIC_USABLE;
+ mp_ioapics[idx].mp_apicaddr = address;
+
+ set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+ mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id);
+#ifdef CONFIG_X86_32
+ mp_ioapics[idx].mp_apicver = io_apic_get_version(idx);
+#else
+ mp_ioapics[idx].mp_apicver = 0;
+#endif
+ /*
+ * Build basic GSI lookup table to facilitate gsi->io_apic lookups
+ * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
+ */
+ mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mp_apicid;
+ mp_ioapic_routing[idx].gsi_base = gsi_base;
+ mp_ioapic_routing[idx].gsi_end = gsi_base +
+ io_apic_get_redir_entries(idx);
+
+ printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
+ "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid,
+ mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr,
+ mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
+
+ nr_ioapics++;
+}
+
+void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
+{
+ int ioapic = -1;
+ int pin = -1;
+
+ /*
+ * Convert 'gsi' to 'ioapic.pin'.
+ */
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0)
+ return;
+ pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+ /*
+ * TBD: This check is for faulty timer entries, where the override
+ * erroneously sets the trigger to level, resulting in a HUGE
+ * increase of timer interrupts!
+ */
+ if ((bus_irq == 0) && (trigger == 3))
+ trigger = 1;
+
+ mp_irqs[mp_irq_entries].mp_type = MP_INTSRC;
+ mp_irqs[mp_irq_entries].mp_irqtype = mp_INT;
+ mp_irqs[mp_irq_entries].mp_irqflag = (trigger << 2) | polarity;
+ mp_irqs[mp_irq_entries].mp_srcbus = MP_ISA_BUS;
+ mp_irqs[mp_irq_entries].mp_srcbusirq = bus_irq; /* IRQ */
+ mp_irqs[mp_irq_entries].mp_dstapic =
+ mp_ioapics[ioapic].mp_apicid; /* APIC ID */
+ mp_irqs[mp_irq_entries].mp_dstirq = pin; /* INTIN# */
+
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!!\n");
+
+}
+
+void __init mp_config_acpi_legacy_irqs(void)
+{
+ int i = 0;
+ int ioapic = -1;
+
+#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
+ /*
+ * Fabricate the legacy ISA bus (bus #31).
+ */
+ mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
+#endif
+ set_bit(MP_ISA_BUS, mp_bus_not_pci);
+ Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
+
+#ifdef CONFIG_X86_ES7000
+ /*
+ * Older generations of ES7000 have no legacy identity mappings
+ */
+ if (es7000_plat == 1)
+ return;
+#endif
+
+ /*
+ * Locate the IOAPIC that manages the ISA IRQs (0-15).
+ */
+ ioapic = mp_find_ioapic(0);
+ if (ioapic < 0)
+ return;
+
+ /*
+ * Use the default configuration for the IRQs 0-15. Unless
+ * overridden by (MADT) interrupt source override entries.
+ */
+ for (i = 0; i < 16; i++) {
+ int idx;
+
+ mp_irqs[mp_irq_entries].mp_type = MP_INTSRC;
+ mp_irqs[mp_irq_entries].mp_irqflag = 0; /* Conforming */
+ mp_irqs[mp_irq_entries].mp_srcbus = MP_ISA_BUS;
+ mp_irqs[mp_irq_entries].mp_dstapic = mp_ioapics[ioapic].mp_apicid;
+
+ for (idx = 0; idx < mp_irq_entries; idx++) {
+ struct mp_config_intsrc *irq = mp_irqs + idx;
+
+ /* Do we already have a mapping for this ISA IRQ? */
+ if (irq->mp_srcbus == MP_ISA_BUS
+ && irq->mp_srcbusirq == i)
+ break;
+
+ /* Do we already have a mapping for this IOAPIC pin */
+ if ((irq->mp_dstapic ==
+ mp_irqs[mp_irq_entries].mp_dstapic) &&
+ (irq->mp_dstirq == i))
+ break;
+ }
+
+ if (idx != mp_irq_entries) {
+ printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
+ continue; /* IRQ already used */
+ }
+
+ mp_irqs[mp_irq_entries].mp_irqtype = mp_INT;
+ mp_irqs[mp_irq_entries].mp_srcbusirq = i; /* Identity mapped */
+ mp_irqs[mp_irq_entries].mp_dstirq = i;
+
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!!\n");
+ }
+}
+
+int mp_register_gsi(u32 gsi, int triggering, int polarity)
+{
+ int ioapic;
+ int ioapic_pin;
+#ifdef CONFIG_X86_32
+#define MAX_GSI_NUM 4096
+#define IRQ_COMPRESSION_START 64
+
+ static int pci_irq = IRQ_COMPRESSION_START;
+ /*
+ * Mapping between Global System Interrupts, which
+ * represent all possible interrupts, and IRQs
+ * assigned to actual devices.
+ */
+ static int gsi_to_irq[MAX_GSI_NUM];
+#else
+
+ if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
+ return gsi;
+#endif
+
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (acpi_gbl_FADT.sci_interrupt == gsi)
+ return gsi;
+
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0) {
+ printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
+ return gsi;
+ }
+
+ ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+#ifdef CONFIG_X86_32
+ if (ioapic_renumber_irq)
+ gsi = ioapic_renumber_irq(ioapic, gsi);
+#endif
+
+ /*
+ * Avoid pin reprogramming. PRTs typically include entries
+ * with redundant pin->gsi mappings (but unique PCI devices);
+ * we only program the IOAPIC on the first.
+ */
+ if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
+ printk(KERN_ERR "Invalid reference to IOAPIC pin "
+ "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+ ioapic_pin);
+ return gsi;
+ }
+ if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+ Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
+ mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
+#ifdef CONFIG_X86_32
+ return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
+#else
+ return gsi;
+#endif
+ }
+
+ set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
+#ifdef CONFIG_X86_32
+ /*
+ * For GSI >= 64, use IRQ compression
+ */
+ if ((gsi >= IRQ_COMPRESSION_START)
+ && (triggering == ACPI_LEVEL_SENSITIVE)) {
+ /*
+ * For PCI devices assign IRQs in order, avoiding gaps
+ * due to unused I/O APIC pins.
+ */
+ int irq = gsi;
+ if (gsi < MAX_GSI_NUM) {
+ /*
+ * Retain the VIA chipset work-around (gsi > 15), but
+ * avoid a problem where the 8254 timer (IRQ0) is setup
+ * via an override (so it's not on pin 0 of the ioapic),
+ * and at the same time, the pin 0 interrupt is a PCI
+ * type. The gsi > 15 test could cause these two pins
+ * to be shared as IRQ0, and they are not shareable.
+ * So test for this condition, and if necessary, avoid
+ * the pin collision.
+ */
+ gsi = pci_irq++;
+ /*
+ * Don't assign IRQ used by ACPI SCI
+ */
+ if (gsi == acpi_gbl_FADT.sci_interrupt)
+ gsi = pci_irq++;
+ gsi_to_irq[irq] = gsi;
+ } else {
+ printk(KERN_ERR "GSI %u is too high\n", gsi);
+ return gsi;
+ }
+ }
+#endif
+ io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
+ triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
+ polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+ return gsi;
+}
+
+int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+ u32 gsi, int triggering, int polarity)
+{
+ struct mpc_config_intsrc intsrc;
+ int ioapic;
+
+ /* print the entry should happen on mptable identically */
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqtype = mp_INT;
+ intsrc.mpc_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+ (polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+ intsrc.mpc_srcbus = number;
+ intsrc.mpc_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+ ioapic = mp_find_ioapic(gsi);
+ intsrc.mpc_dstapic = mp_ioapic_routing[ioapic].apic_id;
+ intsrc.mpc_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+ MP_intsrc_info(&intsrc);
+
+ return 0;
+}
+
/*
* Parse IOAPIC related entries in MADT
* returns 0 on success, < 0 on error
*/
int apic_verbosity;
+/* Have we found an MP table */
+int smp_found_config;
+
static struct resource lapic_resource = {
.name = "Local APIC",
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
*/
void clear_local_APIC(void)
{
- int maxlvt = lapic_get_maxlvt();
+ int maxlvt;
u32 v;
/* APIC hasn't been mapped yet */
*/
cpu = 0;
}
+ if (apicid > max_physical_apicid)
+ max_physical_apicid = apicid;
+
/* are we being called early in kernel startup? */
if (x86_cpu_to_apicid_early_ptr) {
u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
* this stage.
*/
- #define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */
+ #define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
xorl %ebx,%ebx /* %ebx is kept at zero */
movl $pa(pg0), %edi
+ movl %edi, pa(init_pg_tables_start)
movl $pa(swapper_pg_pmd), %edx
movl $PTE_ATTR, %eax
10:
jb 10b
1:
movl %edi,pa(init_pg_tables_end)
+ shrl $12, %eax
+ movl %eax, pa(max_pfn_mapped)
/* Do early initialization of the fixmap area */
movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
page_pde_offset = (__PAGE_OFFSET >> 20);
movl $pa(pg0), %edi
+ movl %edi, pa(init_pg_tables_start)
movl $pa(swapper_pg_dir), %edx
movl $PTE_ATTR, %eax
10:
cmpl %ebp,%eax
jb 10b
movl %edi,pa(init_pg_tables_end)
+ shrl $12, %eax
+ movl %eax, pa(max_pfn_mapped)
/* Do early initialization of the fixmap area */
movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
-struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
-struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
+#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
+int mp_bus_id_to_type[MAX_MP_BUSSES];
+#endif
+
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
static int disable_timer_pin_1 __initdata;
/*
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == type &&
- (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mpc_dstirq == pin)
+ if (mp_irqs[i].mp_irqtype == type &&
+ (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mp_dstirq == pin)
return i;
return -1;
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
- return mp_irqs[i].mpc_dstirq;
+ return mp_irqs[i].mp_dstirq;
}
return -1;
}
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
return apic;
}
}
apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, "
"slot:%d, pin:%d.\n", bus, slot, pin);
- if (mp_bus_id_to_pci_bus[bus] == -1) {
+ if (test_bit(bus, mp_bus_not_pci)) {
printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mpc_irqtype &&
+ !mp_irqs[i].mp_irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ if (pin == (mp_irqs[i].mp_srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
* EISA conforming in the MP table, that means its trigger type must
* be read in from the ELCR */
-#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq))
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
/* PCI interrupts are always polarity one level triggered,
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mp_irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
{
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
{
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mpc_dstirq != pin)
+ if (mp_irqs[idx].mp_dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci))
- irq = mp_irqs[idx].mpc_srcbusirq;
+ irq = mp_irqs[idx].mp_srcbusirq;
else {
/*
* PCI IRQs are mapped in order
if (first_notcon) {
apic_printk(APIC_VERBOSE, KERN_DEBUG
" IO-APIC (apicid-pin) %d-%d",
- mp_ioapics[apic].mpc_apicid,
+ mp_ioapics[apic].mp_apicid,
pin);
first_notcon = 0;
} else
apic_printk(APIC_VERBOSE, ", %d-%d",
- mp_ioapics[apic].mpc_apicid, pin);
+ mp_ioapics[apic].mp_apicid, pin);
continue;
}
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
reg_03.raw = io_apic_read(apic, 3);
spin_unlock_irqrestore(&ioapic_lock, flags);
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
* by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999
*/
-#ifndef CONFIG_X86_NUMAQ
static void __init setup_ioapic_ids_from_mpc(void)
{
union IO_APIC_reg_00 reg_00;
unsigned char old_id;
unsigned long flags;
+#ifdef CONFIG_X86_NUMAQ
+ if (found_numaq)
+ return;
+#endif
+
/*
* Don't check I/O APIC IDs for xAPIC systems. They have
* no meaning without the serial APIC bus.
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- old_id = mp_ioapics[apic].mpc_apicid;
+ old_id = mp_ioapics[apic].mp_apicid;
- if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
+ if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
- apic, mp_ioapics[apic].mpc_apicid);
+ apic, mp_ioapics[apic].mp_apicid);
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
reg_00.bits.ID);
- mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
+ mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
}
/*
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(phys_id_present_map,
- mp_ioapics[apic].mpc_apicid)) {
+ mp_ioapics[apic].mp_apicid)) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
- apic, mp_ioapics[apic].mpc_apicid);
+ apic, mp_ioapics[apic].mp_apicid);
for (i = 0; i < get_physical_broadcast(); i++)
if (!physid_isset(i, phys_id_present_map))
break;
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
i);
physid_set(i, phys_id_present_map);
- mp_ioapics[apic].mpc_apicid = i;
+ mp_ioapics[apic].mp_apicid = i;
} else {
physid_mask_t tmp;
- tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
+ tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
apic_printk(APIC_VERBOSE, "Setting %d in the "
"phys_id_present_map\n",
- mp_ioapics[apic].mpc_apicid);
+ mp_ioapics[apic].mp_apicid);
physids_or(phys_id_present_map, phys_id_present_map, tmp);
}
* We need to adjust the IRQ routing table
* if the ID changed.
*/
- if (old_id != mp_ioapics[apic].mpc_apicid)
+ if (old_id != mp_ioapics[apic].mp_apicid)
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_dstapic == old_id)
- mp_irqs[i].mpc_dstapic
- = mp_ioapics[apic].mpc_apicid;
+ if (mp_irqs[i].mp_dstapic == old_id)
+ mp_irqs[i].mp_dstapic
+ = mp_ioapics[apic].mp_apicid;
/*
* Read the right value from the MPC table and
*/
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
- mp_ioapics[apic].mpc_apicid);
+ mp_ioapics[apic].mp_apicid);
- reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
+ reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0, reg_00.raw);
spin_unlock_irqrestore(&ioapic_lock, flags);
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
+ if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
printk("could not set ID!\n");
else
apic_printk(APIC_VERBOSE, " ok.\n");
}
}
-#else
-static void __init setup_ioapic_ids_from_mpc(void) { }
-#endif
int no_timer_check __initdata;
{
int apic1, pin1, apic2, pin2;
int vector;
- unsigned int ver;
unsigned long flags;
local_irq_save(flags);
- ver = apic_read(APIC_LVR);
- ver = GET_APIC_VERSION(ver);
-
/*
* get/set the timer IRQ vector:
*/
* mode for the 8259A whenever interrupts are routed
* through I/O APICs. Also IRQ0 has to be enabled in
* the 8259A which implies the virtual wire has to be
- * disabled in the local APIC. Finally timer interrupts
- * need to be acknowledged manually in the 8259A for
- * timer_interrupt() and for the i82489DX when using
- * the NMI watchdog.
+ * disabled in the local APIC.
*/
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- timer_ack = !cpu_has_tsc;
- timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+ timer_ack = 1;
if (timer_over_8254 > 0)
enable_8259A_irq(0);
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry "
"(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic,
- mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq,
+ mp_ioapics[ioapic].mp_apicid, pin, entry.vector, irq,
edge_level, active_high_low);
ioapic_register_intr(irq, entry.vector, edge_level);
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == mp_INT &&
- mp_irqs[i].mpc_srcbusirq == bus_irq)
+ if (mp_irqs[i].mp_irqtype == mp_INT &&
+ mp_irqs[i].mp_srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
#include <asm/bios_ebda.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
+#include <asm/efi.h>
/* This value is set up by the early boot code to point to the value
immediately after the boot time page tables. It contains a *physical*
address, and must not be in the .bss segment! */
+unsigned long init_pg_tables_start __initdata = ~0UL;
unsigned long init_pg_tables_end __initdata = ~0UL;
/*
}
#endif
-int __initdata user_defined_memmap;
-
-/*
- * "mem=nopentium" disables the 4MB page tables.
- * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
- * to <mem>, overriding the bios size.
- * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from
- * <start> to <start>+<mem>, overriding the bios size.
- *
- * HPA tells me bootloaders need to parse mem=, so no new
- * option should be mem= [also see Documentation/i386/boot.txt]
- */
-static int __init parse_mem(char *arg)
-{
- if (!arg)
- return -EINVAL;
-
- if (strcmp(arg, "nopentium") == 0) {
- setup_clear_cpu_cap(X86_FEATURE_PSE);
- } else {
- /* If the user specifies memory size, we
- * limit the BIOS-provided memory map to
- * that size. exactmap can be used to specify
- * the exact map. mem=number can be used to
- * trim the existing memory map.
- */
- unsigned long long mem_size;
-
- mem_size = memparse(arg, &arg);
- limit_regions(mem_size);
- user_defined_memmap = 1;
- }
- return 0;
-}
-early_param("mem", parse_mem);
-
#ifdef CONFIG_PROC_VMCORE
/* elfcorehdr= specifies the location of elf core header
* stored by the crashed kernel.
return max_low_pfn;
}
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
-/*
- * The BIOS places the EBDA/XBDA at the top of conventional
- * memory, and usually decreases the reported amount of
- * conventional memory (int 0x12) too. This also contains a
- * workaround for Dell systems that neglect to reserve EBDA.
- * The same workaround also avoids a problem with the AMD768MPX
- * chipset: reserve a page before VGA to prevent PCI prefetch
- * into it (errata #56). Usually the page is reserved anyways,
- * unless you have no PS/2 mouse plugged in.
- */
-static void __init reserve_ebda_region(void)
-{
- unsigned int lowmem, ebda_addr;
-
- /* To determine the position of the EBDA and the */
- /* end of conventional memory, we need to look at */
- /* the BIOS data area. In a paravirtual environment */
- /* that area is absent. We'll just have to assume */
- /* that the paravirt case can handle memory setup */
- /* correctly, without our help. */
- if (paravirt_enabled())
- return;
-
- /* end of low (conventional) memory */
- lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
- lowmem <<= 10;
-
- /* start of EBDA area */
- ebda_addr = get_bios_ebda();
-
- /* Fixup: bios puts an EBDA in the top 64K segment */
- /* of conventional memory, but does not adjust lowmem. */
- if ((lowmem - ebda_addr) <= 0x10000)
- lowmem = ebda_addr;
-
- /* Fixup: bios does not report an EBDA at all. */
- /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
- if ((ebda_addr == 0) && (lowmem >= 0x9f000))
- lowmem = 0x9f000;
-
- /* Paranoia: should never happen, but... */
- if ((lowmem == 0) || (lowmem >= 0x100000))
- lowmem = 0x9f000;
-
- /* reserve all memory between lowmem and the 1MB mark */
- reserve_bootmem(lowmem, 0x100000 - lowmem, BOOTMEM_DEFAULT);
-}
-
#ifndef CONFIG_NEED_MULTIPLE_NODES
static void __init setup_bootmem_allocator(void);
static unsigned long __init setup_memory(void)
if (max_pfn > max_low_pfn) {
highstart_pfn = max_low_pfn;
}
+ memory_present(0, 0, highend_pfn);
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
pages_to_mb(highend_pfn - highstart_pfn));
num_physpages = highend_pfn;
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
+ memory_present(0, 0, max_low_pfn);
num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
max_zone_pfns[ZONE_DMA] =
virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+ remove_all_active_ranges();
#ifdef CONFIG_HIGHMEM
max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
- add_active_range(0, 0, highend_pfn);
+ e820_register_active_regions(0, 0, highend_pfn);
#else
- add_active_range(0, 0, max_low_pfn);
+ e820_register_active_regions(0, 0, max_low_pfn);
#endif
free_area_init_nodes(max_zone_pfns);
(unsigned long)(crash_size >> 20),
(unsigned long)(crash_base >> 20),
(unsigned long)(total_mem >> 20));
+
+ if (reserve_bootmem(crash_base, crash_size,
+ BOOTMEM_EXCLUSIVE) < 0) {
+ printk(KERN_INFO "crashkernel reservation "
+ "failed - memory is in use\n");
+ return;
+ }
+
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
- reserve_bootmem(crash_base, crash_size,
- BOOTMEM_DEFAULT);
} else
printk(KERN_INFO "crashkernel reservation failed - "
"you have to specify a base address\n");
static void __init reserve_initrd(void)
{
- unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
- unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
- unsigned long ramdisk_end = ramdisk_image + ramdisk_size;
- unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT;
- unsigned long ramdisk_here;
-
- initrd_start = 0;
+ u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+ u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 ramdisk_end = ramdisk_image + ramdisk_size;
+ u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;
+ u64 ramdisk_here;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
return; /* No initrd provided by bootloader */
- if (ramdisk_end < ramdisk_image) {
- printk(KERN_ERR "initrd wraps around end of memory, "
- "disabling initrd\n");
- return;
- }
+ initrd_start = 0;
+
if (ramdisk_size >= end_of_lowmem/2) {
+ free_early(ramdisk_image, ramdisk_end);
printk(KERN_ERR "initrd too large to handle, "
"disabling initrd\n");
return;
}
+
+ printk(KERN_INFO "old RAMDISK: %08llx - %08llx\n", ramdisk_image,
+ ramdisk_end);
+
+
if (ramdisk_end <= end_of_lowmem) {
/* All in lowmem, easy case */
- reserve_bootmem(ramdisk_image, ramdisk_size, BOOTMEM_DEFAULT);
+ /*
+ * 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;
}
/* We need to move the initrd down into lowmem */
- ramdisk_here = (end_of_lowmem - ramdisk_size) & PAGE_MASK;
+ ramdisk_here = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+ end_of_lowmem, ramdisk_size,
+ PAGE_SIZE);
+
+ if (ramdisk_here == -1ULL)
+ 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_bootmem(ramdisk_here, ramdisk_size, BOOTMEM_DEFAULT);
+ reserve_early(ramdisk_here, ramdisk_here + ramdisk_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);
do_relocate_initrd = true;
}
static void __init relocate_initrd(void)
{
- unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
- unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
- unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT;
- unsigned long ramdisk_here;
+ u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+ u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;
+ u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
p = (char *)__va(ramdisk_image);
memcpy(q, p, clen);
q += clen;
+ /* need to free these low pages...*/
+ printk(KERN_INFO "Freeing old partial RAMDISK %08llx-%08llx\n",
+ ramdisk_image, ramdisk_image + clen - 1);
+ free_bootmem(ramdisk_image, clen);
ramdisk_image += clen;
ramdisk_size -= clen;
}
ramdisk_image += clen;
ramdisk_size -= clen;
}
+ /* 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 "Copied RAMDISK from %016llx - %016llx to %08llx - %08llx\n",
+ ramdisk_image, ramdisk_image + ramdisk_size - 1,
+ ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
#endif /* CONFIG_BLK_DEV_INITRD */
void __init setup_bootmem_allocator(void)
{
- unsigned long bootmap_size;
+ int i;
+ unsigned long bootmap_size, bootmap;
/*
* Initialize the boot-time allocator (with low memory only):
*/
- bootmap_size = init_bootmem(min_low_pfn, max_low_pfn);
-
- register_bootmem_low_pages(max_low_pfn);
-
- /*
- * Reserve the bootmem bitmap itself as well. We do this in two
- * steps (first step was init_bootmem()) because this catches
- * the (very unlikely) case of us accidentally initializing the
- * bootmem allocator with an invalid RAM area.
- */
- reserve_bootmem(__pa_symbol(_text), (PFN_PHYS(min_low_pfn) +
- bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text),
- BOOTMEM_DEFAULT);
-
- /*
- * reserve physical page 0 - it's a special BIOS page on many boxes,
- * enabling clean reboots, SMP operation, laptop functions.
- */
- reserve_bootmem(0, PAGE_SIZE, BOOTMEM_DEFAULT);
-
- /* reserve EBDA region */
- reserve_ebda_region();
-
-#ifdef CONFIG_SMP
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- reserve_bootmem(PAGE_SIZE, PAGE_SIZE, BOOTMEM_DEFAULT);
+ bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
+ bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+ max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+ PAGE_SIZE);
+ if (bootmap == -1L)
+ panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+ reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#ifdef CONFIG_BLK_DEV_INITRD
+ reserve_initrd();
#endif
+ bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, max_low_pfn);
+ printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
+ max_pfn_mapped<<PAGE_SHIFT);
+ printk(KERN_INFO " low ram: %08lx - %08lx\n",
+ min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT);
+ printk(KERN_INFO " bootmap %08lx - %08lx\n",
+ bootmap, bootmap + bootmap_size);
+ for_each_online_node(i)
+ free_bootmem_with_active_regions(i, max_low_pfn);
+ early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+
#ifdef CONFIG_ACPI_SLEEP
/*
* Reserve low memory region for sleep support.
*/
find_smp_config();
#endif
-#ifdef CONFIG_BLK_DEV_INITRD
- reserve_initrd();
-#endif
- numa_kva_reserve();
reserve_crashkernel();
reserve_ibft_region();
static void set_mca_bus(int x) { }
#endif
-/* Overridden in paravirt.c if CONFIG_PARAVIRT */
-char * __init __attribute__((weak)) memory_setup(void)
-{
- return machine_specific_memory_setup();
-}
-
#ifdef CONFIG_NUMA
/*
* In the golden day, when everything among i386 and x86_64 will be
pre_setup_arch_hook();
early_cpu_init();
early_ioremap_init();
+ reserve_setup_data();
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
- "EL32", 4))
+ "EL32", 4)) {
efi_enabled = 1;
+ efi_reserve_early();
+ }
#endif
ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
#endif
ARCH_SETUP
- printk(KERN_INFO "BIOS-provided physical RAM map:\n");
- print_memory_map(memory_setup());
+ setup_memory_map();
copy_edd();
bss_resource.start = virt_to_phys(&__bss_start);
bss_resource.end = virt_to_phys(&__bss_stop)-1;
+ parse_setup_data();
+
parse_early_param();
- if (user_defined_memmap) {
- printk(KERN_INFO "user-defined physical RAM map:\n");
- print_memory_map("user");
- }
+ finish_e820_parsing();
strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
if (efi_enabled)
efi_init();
+ e820_register_active_regions(0, 0, -1UL);
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+ max_pfn = e820_end_of_ram();
+
+ /* preallocate 4k for mptable mpc */
+ early_reserve_e820_mpc_new();
/* update e820 for memory not covered by WB MTRRs */
- propagate_e820_map();
mtrr_bp_init();
- if (mtrr_trim_uncached_memory(max_pfn))
- propagate_e820_map();
+ if (mtrr_trim_uncached_memory(max_pfn)) {
+ remove_all_active_ranges();
+ e820_register_active_regions(0, 0, -1UL);
+ max_pfn = e820_end_of_ram();
+ }
max_low_pfn = setup_memory();
* not to exceed the 8Mb limit.
*/
-#ifdef CONFIG_SMP
- smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
-#endif
paging_init();
/*
#ifdef CONFIG_ACPI
acpi_boot_init();
-
+#endif
+#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
+ if (smp_found_config)
+ get_smp_config();
+#endif
#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC)
if (def_to_bigsmp)
printk(KERN_WARNING "More than 8 CPUs detected and "
"CONFIG_X86_PC cannot handle it.\nUse "
"CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
#endif
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
- if (smp_found_config)
- get_smp_config();
-#endif
- e820_register_memory();
- e820_mark_nosave_regions();
+ e820_setup_gap();
+ e820_mark_nosave_regions(max_low_pfn);
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
return c->llc_shared_map;
}
-#ifdef CONFIG_X86_32
-/*
- * We are called very early to get the low memory for the
- * SMP bootup trampoline page.
- */
-void __init smp_alloc_memory(void)
-{
- trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
- /*
- * Has to be in very low memory so we can execute
- * real-mode AP code.
- */
- if (__pa(trampoline_base) >= 0x9F000)
- BUG();
-}
-#endif
-
static void impress_friends(void)
{
int cpu;
#endif
cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
- cpu_clear(cpu, cpu_possible_map);
cpu_clear(cpu, cpu_present_map);
per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
}
*/
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
+ preempt_disable();
nmi_watchdog_default();
smp_cpu_index_default();
current_cpu_data = boot_cpu_data;
if (smp_sanity_check(max_cpus) < 0) {
printk(KERN_INFO "SMP disabled\n");
disable_smp();
- return;
+ goto out;
}
preempt_disable();
printk(KERN_INFO "CPU%d: ", 0);
print_cpu_info(&cpu_data(0));
setup_boot_clock();
+ out:
+ preempt_enable();
}
/*
* Early setup to make printk work.
int vector = FIRST_EXTERNAL_VECTOR + i;
if (vector != SYSCALL_VECTOR) {
set_intr_gate(vector, interrupt[i]);
- set_irq_chip_and_handler(i, &lguest_irq_controller,
- handle_level_irq);
+ set_irq_chip_and_handler_name(i, &lguest_irq_controller,
+ handle_level_irq,
+ "level");
}
}
/* This call is required to set up for 4k stacks, where we have
* clobbered. The Launcher places our initial pagetables somewhere at
* the top of our physical memory, so we don't need extra space: set
* init_pg_tables_end to the end of the kernel. */
+ init_pg_tables_start = __pa(pg0);
init_pg_tables_end = __pa(pg0);
/* Load the %fs segment register (the per-cpu segment register) with
pm_power_off = lguest_power_off;
machine_ops.restart = lguest_restart;
- /* Now we're set up, call start_kernel() in init/main.c and we proceed
+ /* Now we're set up, call i386_start_kernel() in head32.c and we proceed
* to boot as normal. It never returns. */
- start_kernel();
+ i386_start_kernel();
}
/*
* This marks the end of stage II of our journey, The Guest.
static __init void xen_pagetable_setup_start(pgd_t *base)
{
pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+ int i;
/* special set_pte for pagetable initialization */
pv_mmu_ops.set_pte = xen_set_pte_init;
init_mm.pgd = base;
/*
- * copy top-level of Xen-supplied pagetable into place. For
- * !PAE we can use this as-is, but for PAE it is a stand-in
- * while we copy the pmd pages.
+ * copy top-level of Xen-supplied pagetable into place. This
+ * is a stand-in while we copy the pmd pages.
*/
memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
- if (PTRS_PER_PMD > 1) {
- int i;
- /*
- * For PAE, need to allocate new pmds, rather than
- * share Xen's, since Xen doesn't like pmd's being
- * shared between address spaces.
- */
- for (i = 0; i < PTRS_PER_PGD; i++) {
- if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
- pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+ /*
+ * For PAE, need to allocate new pmds, rather than
+ * share Xen's, since Xen doesn't like pmd's being
+ * shared between address spaces.
+ */
+ for (i = 0; i < PTRS_PER_PGD; i++) {
+ if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
+ pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
- memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
- PAGE_SIZE);
+ memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
+ PAGE_SIZE);
- make_lowmem_page_readonly(pmd);
+ make_lowmem_page_readonly(pmd);
- set_pgd(&base[i], __pgd(1 + __pa(pmd)));
- } else
- pgd_clear(&base[i]);
- }
+ set_pgd(&base[i], __pgd(1 + __pa(pmd)));
+ } else
+ pgd_clear(&base[i]);
}
/* make sure zero_page is mapped RO so we can use it in pagetables */
/* Actually pin the pagetable down, but we can't set PG_pinned
yet because the page structures don't exist yet. */
- {
- unsigned level;
-
- #ifdef CONFIG_X86_PAE
- level = MMUEXT_PIN_L3_TABLE;
- #else
- level = MMUEXT_PIN_L2_TABLE;
- #endif
-
- pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
- }
+ pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
}
/* This is called once we have the cpu_possible_map */
.make_pte = xen_make_pte,
.make_pgd = xen_make_pgd,
- #ifdef CONFIG_X86_PAE
.set_pte_atomic = xen_set_pte_atomic,
.set_pte_present = xen_set_pte_at,
.set_pud = xen_set_pud,
.make_pmd = xen_make_pmd,
.pmd_val = xen_pmd_val,
- #endif /* PAE */
.activate_mm = xen_activate_mm,
.dup_mmap = xen_dup_mmap,
pgd = (pgd_t *)xen_start_info->pt_base;
+ init_pg_tables_start = __pa(pgd);
init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
init_mm.pgd = pgd; /* use the Xen pagetables to start */
if (xen_feature(XENFEAT_supervisor_mode_kernel))
pv_info.kernel_rpl = 0;
+ /* Prevent unwanted bits from being set in PTEs. */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
+ if (!is_initial_xendomain())
+ __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
/* set the limit of our address space */
xen_reserve_top();
add_preferred_console("hvc", 0, NULL);
/* Start the world */
- start_kernel();
+ i386_start_kernel();
}
* (see walk_page_range for more details)
*/
struct mm_walk {
- int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *);
- int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *);
- int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *);
- int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *);
- int (*pte_hole)(unsigned long, unsigned long, void *);
+ int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *);
+ int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *);
+ int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
+ int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
+ int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
+ struct mm_struct *mm;
+ void *private;
};
- int walk_page_range(const struct mm_struct *, unsigned long addr,
- unsigned long end, const struct mm_walk *walk,
- void *private);
+ int walk_page_range(unsigned long addr, unsigned long end,
+ struct mm_walk *walk);
void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
extern void free_area_init_nodes(unsigned long *max_zone_pfn);
extern void add_active_range(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
-extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
- unsigned long new_end_pfn);
+extern void shrink_active_range(unsigned int nid, unsigned long new_end_pfn);
extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
extern void remove_all_active_ranges(void);
printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
KERN_EMERG "Backtrace:\n");
dump_stack();
- page->flags &= ~(1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_reclaim |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_buddy );
+ page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD;
set_page_count(page, 0);
reset_page_mapcount(page);
page->mapping = NULL;
(page->mapping != NULL) |
(page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
- (page->flags & (
- 1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
bad_page(page);
if (PageDirty(page))
__ClearPageDirty(page);
(page->mapping != NULL) |
(page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
- (page->flags & (
- 1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
bad_page(page);
/*
(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
&preferred_zone);
+ if (!preferred_zone)
+ return NULL;
+
classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
static void build_zonelist_cache(pg_data_t *pgdat)
{
pgdat->node_zonelists[0].zlcache_ptr = NULL;
- pgdat->node_zonelists[1].zlcache_ptr = NULL;
}
#endif /* CONFIG_NUMA */
alloc_size = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
- if (system_state == SYSTEM_BOOTING) {
+ if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
alloc_bootmem_node(pgdat, alloc_size);
} else {
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
- memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT;
+ memmap_pages =
+ PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
if (realsize >= memmap_pages) {
realsize -= memmap_pages;
printk(KERN_DEBUG
calculate_node_totalpages(pgdat, zones_size, zholes_size);
alloc_node_mem_map(pgdat);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
+ nid, (unsigned long)pgdat,
+ (unsigned long)pgdat->node_mem_map);
+#endif
free_area_init_core(pgdat, zones_size, zholes_size);
}
/**
* shrink_active_range - Shrink an existing registered range of PFNs
* @nid: The node id the range is on that should be shrunk
- * @old_end_pfn: The old end PFN of the range
* @new_end_pfn: The new PFN of the range
*
* i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept at the end physical page range that has already been
- * registered with add_active_range(). This function allows an arch to shrink
- * an existing registered range.
+ * The map is kept near the end physical page range that has already been
+ * registered. This function allows an arch to shrink an existing registered
+ * range.
*/
-void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
- unsigned long new_end_pfn)
+void __init shrink_active_range(unsigned int nid, unsigned long new_end_pfn)
{
- int i;
+ int i, j;
+ int removed = 0;
/* Find the old active region end and shrink */
- for_each_active_range_index_in_nid(i, nid)
- if (early_node_map[i].end_pfn == old_end_pfn) {
+ for_each_active_range_index_in_nid(i, nid) {
+ if (early_node_map[i].start_pfn >= new_end_pfn) {
+ /* clear it */
+ early_node_map[i].end_pfn = 0;
+ removed = 1;
+ continue;
+ }
+ if (early_node_map[i].end_pfn > new_end_pfn) {
early_node_map[i].end_pfn = new_end_pfn;
- break;
+ continue;
}
+ }
+
+ if (!removed)
+ return;
+
+ /* remove the blank ones */
+ for (i = nr_nodemap_entries - 1; i > 0; i--) {
+ if (early_node_map[i].nid != nid)
+ continue;
+ if (early_node_map[i].end_pfn)
+ continue;
+ /* we found it, get rid of it */
+ for (j = i; j < nr_nodemap_entries - 1; j++)
+ memcpy(&early_node_map[j], &early_node_map[j+1],
+ sizeof(early_node_map[j]));
+ j = nr_nodemap_entries - 1;
+ memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
+ nr_nodemap_entries--;
+ }
}
/**