or
memmap=0x10000$0x18690000
- memtest= [KNL,X86_64] Enable memtest
+ memtest= [KNL,X86] Enable memtest
Format: <integer>
range: 0,4 : pattern number
default : 0 <disable>
This usage is only documented in each driver source
file if at all.
+ nf_conntrack.acct=
+ [NETFILTER] Enable connection tracking flow accounting
+ 0 to disable accounting
+ 1 to enable accounting
+ Default value depends on CONFIG_NF_CT_ACCT that is
+ going to be removed in 2.6.29.
+
nfsaddrs= [NFS]
See Documentation/filesystems/nfsroot.txt.
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
+ nox2apic [X86-64,APIC] Do not enable x2APIC mode.
+
+ x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
+ default x2apic cluster mode on platforms
+ supporting x2apic.
+
noltlbs [PPC] Do not use large page/tlb entries for kernel
lowmem mapping on PPC40x.
Note that genuine overcurrent events won't be
reported either.
+ unknown_nmi_panic
+ [X86-32,X86-64]
+ Set unknown_nmi_panic=1 early on boot.
+
usbcore.autosuspend=
[USB] The autosuspend time delay (in seconds) used
for newly-detected USB devices (default 2). This
config MEMTEST
bool "Memtest"
- depends on X86_64
help
This option adds a kernel parameter 'memtest', which allows memtest
to be set.
workaround will setup a 1:1 mapping for the first
16M to make floppy (an ISA device) work.
+config INTR_REMAP
+ bool "Support for Interrupt Remapping (EXPERIMENTAL)"
+ depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+ help
+ Supports Interrupt remapping for IO-APIC and MSI devices.
+ To use x2apic mode in the CPU's which support x2APIC enhancements or
+ to support platforms with CPU's having > 8 bit APIC ID, say Y.
+
source "drivers/pci/pcie/Kconfig"
source "drivers/pci/Kconfig"
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
ifdef CONFIG_FTRACE
- # Do not profile debug utilities
+ # Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_tsc.o = -pg
CFLAGS_REMOVE_rtc.o = -pg
+ CFLAGS_REMOVE_paravirt.o = -pg
endif
#
ifeq ($(CONFIG_X86_64),y)
obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
obj-y += bios_uv.o
+ obj-y += genx2apic_cluster.o
+ obj-y += genx2apic_phys.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
obj-$(CONFIG_AUDIT) += audit_64.o
set_fixmap_nocache(FIX_APIC_BASE, address);
if (boot_cpu_physical_apicid == -1U) {
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
#ifdef CONFIG_X86_32
apic_version[boot_cpu_physical_apicid] =
GET_APIC_VERSION(apic_read(APIC_LVR));
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);
+ pr_debug("Bus #%d is ISA\n", MP_ISA_BUS);
#ifdef CONFIG_X86_ES7000
/*
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);
+ pr_debug(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
acpi_ioapic = 1;
smp_found_config = 1;
+#ifdef CONFIG_X86_32
setup_apic_routing();
+#endif
}
}
if (error == -EINVAL) {
return lapic_get_version() >= 0x14;
}
-void apic_wait_icr_idle(void)
+/*
+ * Paravirt kernels also might be using these below ops. So we still
+ * use generic apic_read()/apic_write(), which might be pointing to different
+ * ops in PARAVIRT case.
+ */
+void xapic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
{
u32 send_status;
int timeout;
return send_status;
}
+void xapic_icr_write(u32 low, u32 id)
+{
+ apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
+ apic_write(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+ u32 icr1, icr2;
+
+ icr2 = apic_read(APIC_ICR2);
+ icr1 = apic_read(APIC_ICR);
+
+ return icr1 | ((u64)icr2 << 32);
+}
+
+static struct apic_ops xapic_ops = {
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .icr_read = xapic_icr_read,
+ .icr_write = xapic_icr_write,
+ .wait_icr_idle = xapic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+EXPORT_SYMBOL_GPL(apic_ops);
+
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
* default configuration (or the MP table is broken).
*/
if (boot_cpu_physical_apicid == -1U)
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
int __init APIC_init_uniprocessor(void)
{
- if (disable_apic)
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
-
if (!smp_found_config && !cpu_has_apic)
return -1;
* might be zero if read from MP tables. Get it from LAPIC.
*/
#ifdef CONFIG_CRASH_DUMP
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
#endif
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
static int __init parse_nolapic(char *arg)
{
disable_apic = 1;
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ setup_clear_cpu_cap(X86_FEATURE_APIC);
return 0;
}
early_param("nolapic", parse_nolapic);
#include <linux/clockchips.h>
#include <linux/acpi_pmtmr.h>
#include <linux/module.h>
+#include <linux/dmar.h>
#include <asm/atomic.h>
#include <asm/smp.h>
#include <asm/proto.h>
#include <asm/timex.h>
#include <asm/apic.h>
+#include <asm/i8259.h>
#include <mach_ipi.h>
#include <mach_apic.h>
static int disable_apic_timer __cpuinitdata;
static int apic_calibrate_pmtmr __initdata;
int disable_apic;
+int disable_x2apic;
+int x2apic;
+
+/* x2apic enabled before OS handover */
+int x2apic_preenabled;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
return lapic_get_version() >= 0x14;
}
-void apic_wait_icr_idle(void)
+void xapic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
{
u32 send_status;
int timeout;
return send_status;
}
+void xapic_icr_write(u32 low, u32 id)
+{
+ apic_write(APIC_ICR2, id << 24);
+ apic_write(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+ u32 icr1, icr2;
+
+ icr2 = apic_read(APIC_ICR2);
+ icr1 = apic_read(APIC_ICR);
+
+ return (icr1 | ((u64)icr2 << 32));
+}
+
+static struct apic_ops xapic_ops = {
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .icr_read = xapic_icr_read,
+ .icr_write = xapic_icr_write,
+ .wait_icr_idle = xapic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+
+EXPORT_SYMBOL_GPL(apic_ops);
+
+static void x2apic_wait_icr_idle(void)
+{
+ /* no need to wait for icr idle in x2apic */
+ return;
+}
+
+static u32 safe_x2apic_wait_icr_idle(void)
+{
+ /* no need to wait for icr idle in x2apic */
+ return 0;
+}
+
+void x2apic_icr_write(u32 low, u32 id)
+{
+ wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+
+u64 x2apic_icr_read(void)
+{
+ unsigned long val;
+
+ rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+ return val;
+}
+
+static struct apic_ops x2apic_ops = {
+ .read = native_apic_msr_read,
+ .write = native_apic_msr_write,
+ .icr_read = x2apic_icr_read,
+ .icr_write = x2apic_icr_write,
+ .wait_icr_idle = x2apic_wait_icr_idle,
+ .safe_wait_icr_idle = safe_x2apic_wait_icr_idle,
+};
+
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
/*
* The ID register is read/write in a real APIC.
*/
- reg0 = read_apic_id();
+ reg0 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
- reg1 = read_apic_id();
+ reg1 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
apic_write(APIC_ID, reg0);
if (reg1 != (reg0 ^ APIC_ID_MASK))
apic_pm_activate();
}
+void check_x2apic(void)
+{
+ int msr, msr2;
+
+ rdmsr(MSR_IA32_APICBASE, msr, msr2);
+
+ if (msr & X2APIC_ENABLE) {
+ printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+ x2apic_preenabled = x2apic = 1;
+ apic_ops = &x2apic_ops;
+ }
+}
+
+void enable_x2apic(void)
+{
+ int msr, msr2;
+
+ rdmsr(MSR_IA32_APICBASE, msr, msr2);
+ if (!(msr & X2APIC_ENABLE)) {
+ printk("Enabling x2apic\n");
+ wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
+ }
+}
+
+void enable_IR_x2apic(void)
+{
+#ifdef CONFIG_INTR_REMAP
+ int ret;
+ unsigned long flags;
+
+ if (!cpu_has_x2apic)
+ return;
+
+ if (!x2apic_preenabled && disable_x2apic) {
+ printk(KERN_INFO
+ "Skipped enabling x2apic and Interrupt-remapping "
+ "because of nox2apic\n");
+ return;
+ }
+
+ if (x2apic_preenabled && disable_x2apic)
+ panic("Bios already enabled x2apic, can't enforce nox2apic");
+
+ if (!x2apic_preenabled && skip_ioapic_setup) {
+ printk(KERN_INFO
+ "Skipped enabling x2apic and Interrupt-remapping "
+ "because of skipping io-apic setup\n");
+ return;
+ }
+
+ ret = dmar_table_init();
+ if (ret) {
+ printk(KERN_INFO
+ "dmar_table_init() failed with %d:\n", ret);
+
+ if (x2apic_preenabled)
+ panic("x2apic enabled by bios. But IR enabling failed");
+ else
+ printk(KERN_INFO
+ "Not enabling x2apic,Intr-remapping\n");
+ return;
+ }
+
+ local_irq_save(flags);
+ mask_8259A();
+ save_mask_IO_APIC_setup();
+
+ ret = enable_intr_remapping(1);
+
+ if (ret && x2apic_preenabled) {
+ local_irq_restore(flags);
+ panic("x2apic enabled by bios. But IR enabling failed");
+ }
+
+ if (ret)
+ goto end;
+
+ if (!x2apic) {
+ x2apic = 1;
+ apic_ops = &x2apic_ops;
+ enable_x2apic();
+ }
+end:
+ if (ret)
+ /*
+ * IR enabling failed
+ */
+ restore_IO_APIC_setup();
+ else
+ reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+
+ unmask_8259A();
+ local_irq_restore(flags);
+
+ if (!ret) {
+ if (!x2apic_preenabled)
+ printk(KERN_INFO
+ "Enabled x2apic and interrupt-remapping\n");
+ else
+ printk(KERN_INFO
+ "Enabled Interrupt-remapping\n");
+ } else
+ printk(KERN_ERR
+ "Failed to enable Interrupt-remapping and x2apic\n");
+#else
+ if (!cpu_has_x2apic)
+ return;
+
+ if (x2apic_preenabled)
+ panic("x2apic enabled prior OS handover,"
+ " enable CONFIG_INTR_REMAP");
+
+ printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+ " and x2apic\n");
+#endif
+
+ return;
+}
+
/*
* Detect and enable local APICs on non-SMP boards.
* Original code written by Keir Fraser.
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
/**
*/
void __init init_apic_mappings(void)
{
+ if (x2apic) {
+ boot_cpu_physical_apicid = read_apic_id();
+ return;
+ }
+
/*
* If no local APIC can be found then set up a fake all
* zeroes page to simulate the local APIC and another
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+ boot_cpu_physical_apicid = read_apic_id();
}
/*
return -1;
}
+ enable_IR_x2apic();
+ setup_apic_routing();
+
verify_local_APIC();
connect_bsp_APIC();
cpu_set(cpu, cpu_present_map);
}
+int hard_smp_processor_id(void)
+{
+ return read_apic_id();
+}
+
/*
* Power management
*/
maxlvt = lapic_get_maxlvt();
- apic_pm_state.apic_id = read_apic_id();
+ apic_pm_state.apic_id = apic_read(APIC_ID);
apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
apic_pm_state.apic_ldr = apic_read(APIC_LDR);
apic_pm_state.apic_dfr = apic_read(APIC_DFR);
maxlvt = lapic_get_maxlvt();
local_irq_save(flags);
- rdmsr(MSR_IA32_APICBASE, l, h);
- l &= ~MSR_IA32_APICBASE_BASE;
- l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
- wrmsr(MSR_IA32_APICBASE, l, h);
+ if (!x2apic) {
+ rdmsr(MSR_IA32_APICBASE, l, h);
+ l &= ~MSR_IA32_APICBASE_BASE;
+ l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+ wrmsr(MSR_IA32_APICBASE, l, h);
+ } else
+ enable_x2apic();
+
apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
apic_write(APIC_ID, apic_pm_state.apic_id);
apic_write(APIC_DFR, apic_pm_state.apic_dfr);
return (clusters > 2);
}
+static __init int setup_nox2apic(char *str)
+{
+ disable_x2apic = 1;
+ clear_cpu_cap(&boot_cpu_data, X86_FEATURE_X2APIC);
+ return 0;
+}
+early_param("nox2apic", setup_nox2apic);
+
+
/*
* APIC command line parameters
*/
static __init int setup_disableapic(char *str)
{
disable_apic = 1;
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ setup_clear_cpu_cap(X86_FEATURE_APIC);
return 0;
}
early_param("disableapic", setup_disableapic);
#include <linux/module.h>
#include <linux/kgdb.h>
#include <linux/topology.h>
- #include <linux/string.h>
#include <linux/delay.h>
#include <linux/smp.h>
- #include <linux/module.h>
#include <linux/percpu.h>
- #include <asm/processor.h>
#include <asm/i387.h>
#include <asm/msr.h>
#include <asm/io.h>
+ #include <asm/linkage.h>
#include <asm/mmu_context.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
c->x86_capability[2] = cpuid_edx(0x80860001);
}
- c->extended_cpuid_level = cpuid_eax(0x80000000);
if (c->extended_cpuid_level >= 0x80000007)
c->x86_power = cpuid_edx(0x80000007);
c->x86_phys_bits = eax & 0xff;
}
- /* Assume all 64-bit CPUs support 32-bit syscall */
- set_cpu_cap(c, X86_FEATURE_SYSCALL32);
-
if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
cpu_devs[c->x86_vendor]->c_early_init)
cpu_devs[c->x86_vendor]->c_early_init(c);
validate_pat_support(c);
-
- /* early_param could clear that, but recall get it set again */
- if (disable_apic)
- clear_cpu_cap(c, X86_FEATURE_APIC);
}
/*
}
char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
- DEBUG_STKSZ]
- __attribute__((section(".bss.page_aligned")));
+ DEBUG_STKSZ] __page_aligned_bss;
extern asmlinkage void ignore_sysret(void);
barrier();
check_efer();
+ if (cpu != 0 && x2apic)
+ enable_x2apic();
/*
* set up and load the per-CPU TSS
#include <asm/bios_ebda.h>
#include <asm/e820.h>
#include <asm/trampoline.h>
+ #include <asm/setup.h>
#include <mach_apic.h>
#ifdef CONFIG_X86_32
return sum & 0xFF;
}
- #ifdef CONFIG_X86_NUMAQ
- int found_numaq;
- /*
- * Have to match translation table entries to main table entries by counter
- * hence the mpc_record variable .... can't see a less disgusting way of
- * doing this ....
- */
- struct mpc_config_translation {
- unsigned char mpc_type;
- unsigned char trans_len;
- unsigned char trans_type;
- unsigned char trans_quad;
- unsigned char trans_global;
- unsigned char trans_local;
- unsigned short trans_reserved;
- };
-
-
- static int mpc_record;
- static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY]
- __cpuinitdata;
-
- static inline int generate_logical_apicid(int quad, int phys_apicid)
- {
- return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
- }
-
-
- static inline int mpc_apic_id(struct mpc_config_processor *m,
- struct mpc_config_translation *translation_record)
- {
- int quad = translation_record->trans_quad;
- int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid);
-
- printk(KERN_DEBUG "Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
- m->mpc_apicid,
- (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
- (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
- m->mpc_apicver, quad, logical_apicid);
- return logical_apicid;
- }
-
- int mp_bus_id_to_node[MAX_MP_BUSSES];
-
- int mp_bus_id_to_local[MAX_MP_BUSSES];
-
- static void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
- struct mpc_config_translation *translation)
- {
- int quad = translation->trans_quad;
- int local = translation->trans_local;
-
- mp_bus_id_to_node[m->mpc_busid] = quad;
- mp_bus_id_to_local[m->mpc_busid] = local;
- printk(KERN_INFO "Bus #%d is %s (node %d)\n",
- m->mpc_busid, name, quad);
- }
-
- int quad_local_to_mp_bus_id [NR_CPUS/4][4];
- static void mpc_oem_pci_bus(struct mpc_config_bus *m,
- struct mpc_config_translation *translation)
- {
- int quad = translation->trans_quad;
- int local = translation->trans_local;
-
- quad_local_to_mp_bus_id[quad][local] = m->mpc_busid;
- }
-
- #endif
-
static void __cpuinit MP_processor_info(struct mpc_config_processor *m)
{
int apicid;
disabled_cpus++;
return;
}
- #ifdef CONFIG_X86_NUMAQ
- if (found_numaq)
- apicid = mpc_apic_id(m, translation_table[mpc_record]);
+
+ if (x86_quirks->mpc_apic_id)
+ apicid = x86_quirks->mpc_apic_id(m);
else
apicid = m->mpc_apicid;
- #else
- apicid = m->mpc_apicid;
- #endif
+
if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) {
bootup_cpu = " (Bootup-CPU)";
boot_cpu_physical_apicid = m->mpc_apicid;
memcpy(str, m->mpc_bustype, 6);
str[6] = 0;
- #ifdef CONFIG_X86_NUMAQ
- if (found_numaq)
- mpc_oem_bus_info(m, str, translation_table[mpc_record]);
- #else
- printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str);
- #endif
+ if (x86_quirks->mpc_oem_bus_info)
+ x86_quirks->mpc_oem_bus_info(m, str);
+ else
+ printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str);
#if MAX_MP_BUSSES < 256
if (m->mpc_busid >= MAX_MP_BUSSES) {
mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA;
#endif
} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
- #ifdef CONFIG_X86_NUMAQ
- if (found_numaq)
- mpc_oem_pci_bus(m, translation_table[mpc_record]);
- #endif
+ if (x86_quirks->mpc_oem_pci_bus)
+ x86_quirks->mpc_oem_pci_bus(m);
+
clear_bit(m->mpc_busid, mp_bus_not_pci);
#if defined(CONFIG_EISA) || defined (CONFIG_MCA)
mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI;
m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint);
}
- #ifdef CONFIG_X86_NUMAQ
- static void __init MP_translation_info(struct mpc_config_translation *m)
- {
- printk(KERN_INFO
- "Translation: record %d, type %d, quad %d, global %d, local %d\n",
- mpc_record, m->trans_type, m->trans_quad, m->trans_global,
- m->trans_local);
-
- if (mpc_record >= MAX_MPC_ENTRY)
- printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n");
- else
- translation_table[mpc_record] = m; /* stash this for later */
- if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad))
- node_set_online(m->trans_quad);
- }
-
- /*
- * Read/parse the MPC oem tables
- */
-
- static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable,
- unsigned short oemsize)
- {
- int count = sizeof(*oemtable); /* the header size */
- unsigned char *oemptr = ((unsigned char *)oemtable) + count;
-
- mpc_record = 0;
- printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n",
- oemtable);
- if (memcmp(oemtable->oem_signature, MPC_OEM_SIGNATURE, 4)) {
- printk(KERN_WARNING
- "SMP mpc oemtable: bad signature [%c%c%c%c]!\n",
- oemtable->oem_signature[0], oemtable->oem_signature[1],
- oemtable->oem_signature[2], oemtable->oem_signature[3]);
- return;
- }
- if (mpf_checksum((unsigned char *)oemtable, oemtable->oem_length)) {
- printk(KERN_WARNING "SMP oem mptable: checksum error!\n");
- return;
- }
- while (count < oemtable->oem_length) {
- switch (*oemptr) {
- case MP_TRANSLATION:
- {
- struct mpc_config_translation *m =
- (struct mpc_config_translation *)oemptr;
- MP_translation_info(m);
- oemptr += sizeof(*m);
- count += sizeof(*m);
- ++mpc_record;
- break;
- }
- default:
- {
- printk(KERN_WARNING
- "Unrecognised OEM table entry type! - %d\n",
- (int)*oemptr);
- return;
- }
- }
- }
- }
-
- void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
- char *productid)
- {
- if (strncmp(oem, "IBM NUMA", 8))
- printk("Warning! Not a NUMA-Q system!\n");
- else
- found_numaq = 1;
-
- if (mpc->mpc_oemptr)
- smp_read_mpc_oem((struct mp_config_oemtable *)mpc->mpc_oemptr,
- mpc->mpc_oemsize);
- }
- #endif /* CONFIG_X86_NUMAQ */
-
/*
* Read/parse the MPC
*/
} else
mps_oem_check(mpc, oem, str);
#endif
-
/* save the local APIC address, it might be non-default */
if (!acpi_lapic)
mp_lapic_addr = mpc->mpc_lapic;
if (early)
return 1;
+ if (mpc->mpc_oemptr && x86_quirks->smp_read_mpc_oem) {
+ struct mp_config_oemtable *oem_table = (struct mp_config_oemtable *)(unsigned long)mpc->mpc_oemptr;
+ x86_quirks->smp_read_mpc_oem(oem_table, mpc->mpc_oemsize);
+ }
+
/*
* Now process the configuration blocks.
*/
- #ifdef CONFIG_X86_NUMAQ
- mpc_record = 0;
- #endif
+ if (x86_quirks->mpc_record)
+ *x86_quirks->mpc_record = 0;
+
while (count < mpc->mpc_length) {
switch (*mpt) {
case MP_PROCESSOR:
count = mpc->mpc_length;
break;
}
- #ifdef CONFIG_X86_NUMAQ
- ++mpc_record;
- #endif
+ if (x86_quirks->mpc_record)
+ (*x86_quirks->mpc_record)++;
}
#ifdef CONFIG_X86_GENERICARCH
generic_bigsmp_probe();
#endif
+#ifdef CONFIG_X86_32
setup_apic_routing();
+#endif
if (!num_processors)
printk(KERN_ERR "MPTABLE: no processors registered!\n");
return num_processors;
static struct intel_mp_floating *mpf_found;
- /*
- * Machine specific quirk for finding the SMP config before other setup
- * activities destroy the table:
- */
- int (*mach_get_smp_config_quirk)(unsigned int early);
-
/*
* Scan the memory blocks for an SMP configuration block.
*/
{
struct intel_mp_floating *mpf = mpf_found;
- if (mach_get_smp_config_quirk) {
- if (mach_get_smp_config_quirk(early))
+ if (x86_quirks->mach_get_smp_config) {
+ if (x86_quirks->mach_get_smp_config(early))
return;
}
if (acpi_lapic && early)
return 0;
}
- int (*mach_find_smp_config_quirk)(unsigned int reserve);
-
static void __init __find_smp_config(unsigned int reserve)
{
unsigned int address;
- if (mach_find_smp_config_quirk) {
- if (mach_find_smp_config_quirk(reserve))
+ if (x86_quirks->mach_find_smp_config) {
+ if (x86_quirks->mach_find_smp_config(reserve))
return;
}
/*
#include <asm/desc.h>
#include <asm/setup.h>
#include <asm/arch_hooks.h>
+ #include <asm/pgtable.h>
#include <asm/time.h>
#include <asm/pgalloc.h>
#include <asm/irq.h>
.pv_irq_ops = pv_irq_ops,
.pv_apic_ops = pv_apic_ops,
.pv_mmu_ops = pv_mmu_ops,
+ .pv_lock_ops = pv_lock_ops,
};
return *((void **)&tmpl + type);
}
return __get_cpu_var(paravirt_lazy_mode);
}
+ void __init paravirt_use_bytelocks(void)
+ {
+ #ifdef CONFIG_SMP
+ pv_lock_ops.spin_is_locked = __byte_spin_is_locked;
+ pv_lock_ops.spin_is_contended = __byte_spin_is_contended;
+ pv_lock_ops.spin_lock = __byte_spin_lock;
+ pv_lock_ops.spin_trylock = __byte_spin_trylock;
+ pv_lock_ops.spin_unlock = __byte_spin_unlock;
+ #endif
+ }
+
struct pv_info pv_info = {
.name = "bare hardware",
.paravirt_enabled = 0,
struct pv_apic_ops pv_apic_ops = {
#ifdef CONFIG_X86_LOCAL_APIC
- .apic_write = native_apic_write,
- .apic_read = native_apic_read,
.setup_boot_clock = setup_boot_APIC_clock,
.setup_secondary_clock = setup_secondary_APIC_clock,
.startup_ipi_hook = paravirt_nop,
#ifndef CONFIG_X86_64
.pagetable_setup_start = native_pagetable_setup_start,
.pagetable_setup_done = native_pagetable_setup_done,
+ #else
+ .pagetable_setup_start = paravirt_nop,
+ .pagetable_setup_done = paravirt_nop,
#endif
.read_cr2 = native_read_cr2,
.set_fixmap = native_set_fixmap,
};
+ struct pv_lock_ops pv_lock_ops = {
+ #ifdef CONFIG_SMP
+ .spin_is_locked = __ticket_spin_is_locked,
+ .spin_is_contended = __ticket_spin_is_contended,
+
+ .spin_lock = __ticket_spin_lock,
+ .spin_trylock = __ticket_spin_trylock,
+ .spin_unlock = __ticket_spin_unlock,
+ #endif
+ };
+ EXPORT_SYMBOL_GPL(pv_lock_ops);
+
EXPORT_SYMBOL_GPL(pv_time_ops);
EXPORT_SYMBOL (pv_cpu_ops);
EXPORT_SYMBOL (pv_mmu_ops);
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/delay.h>
- #include <linux/highmem.h>
#include <linux/kallsyms.h>
- #include <linux/edd.h>
- #include <linux/iscsi_ibft.h>
- #include <linux/kexec.h>
#include <linux/cpufreq.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <asm/smp.h>
#include <asm/desc.h>
#include <asm/dma.h>
- #include <asm/gart.h>
+ #include <asm/iommu.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/paravirt.h>
#include <asm/percpu.h>
- #include <asm/sections.h>
#include <asm/topology.h>
#include <asm/apicdef.h>
#ifdef CONFIG_X86_64
early_param("elfcorehdr", setup_elfcorehdr);
#endif
+ static struct x86_quirks default_x86_quirks __initdata;
+
+ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
+
/*
* 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
num_physpages = max_pfn;
check_efer();
+ if (cpu_has_x2apic)
+ check_x2apic();
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
vmi_init();
#endif
+ paravirt_pagetable_setup_start(swapper_pg_dir);
paging_init();
+ paravirt_pagetable_setup_done(swapper_pg_dir);
+ paravirt_post_allocator_init();
#ifdef CONFIG_X86_64
map_vsyscall();
init_cpu_to_node();
#endif
- #ifdef CONFIG_X86_NUMAQ
- /*
- * need to check online nodes num, call it
- * here before time_init/tsc_init
- */
- numaq_tsc_disable();
- #endif
-
init_apic_mappings();
ioapic_init_mappings();
static atomic_t init_deasserted;
-static int boot_cpu_logical_apicid;
/* representing cpus for which sibling maps can be computed */
static cpumask_t cpu_sibling_setup_map;
#endif
#ifdef CONFIG_X86_32
+static int boot_cpu_logical_apicid;
+
u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = BAD_APICID };
/*
* (This works even if the APIC is not enabled.)
*/
- phys_id = GET_APIC_ID(read_apic_id());
+ phys_id = read_apic_id();
cpuid = smp_processor_id();
if (cpu_isset(cpuid, cpu_callin_map)) {
panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
phys_id, cpuid);
}
- Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
+ pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
/*
* STARTUP IPIs are fragile beasts as they might sometimes
* boards)
*/
- Dprintk("CALLIN, before setup_local_APIC().\n");
+ pr_debug("CALLIN, before setup_local_APIC().\n");
smp_callin_clear_local_apic();
setup_local_APIC();
end_local_APIC_setup();
local_irq_enable();
calibrate_delay();
local_irq_disable();
- Dprintk("Stack at about %p\n", &cpuid);
+ pr_debug("Stack at about %p\n", &cpuid);
/*
* Save our processor parameters
/*
* Allow the user to impress friends.
*/
- Dprintk("Before bogomips.\n");
+ pr_debug("Before bogomips.\n");
for_each_possible_cpu(cpu)
if (cpu_isset(cpu, cpu_callout_map))
bogosum += cpu_data(cpu).loops_per_jiffy;
bogosum/(500000/HZ),
(bogosum/(5000/HZ))%100);
- Dprintk("Before bogocount - setting activated=1.\n");
+ pr_debug("Before bogocount - setting activated=1.\n");
}
static inline void __inquire_remote_apic(int apicid)
printk(KERN_CONT
"a previous APIC delivery may have failed\n");
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
- apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);
+ apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
timeout = 0;
do {
int maxlvt;
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+ apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
- Dprintk("Waiting for send to finish...\n");
+ pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
/*
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
- Dprintk("NMI sent.\n");
+ pr_debug("NMI sent.\n");
if (send_status)
printk(KERN_ERR "APIC never delivered???\n");
apic_read(APIC_ESR);
}
- Dprintk("Asserting INIT.\n");
+ pr_debug("Asserting INIT.\n");
/*
* Turn INIT on target chip
*/
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/*
* Send IPI
*/
- apic_write(APIC_ICR,
- APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+ phys_apicid);
- Dprintk("Waiting for send to finish...\n");
+ pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
mdelay(10);
- Dprintk("Deasserting INIT.\n");
+ pr_debug("Deasserting INIT.\n");
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Send IPI */
- apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
- Dprintk("Waiting for send to finish...\n");
+ pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
mb();
/*
* Run STARTUP IPI loop.
*/
- Dprintk("#startup loops: %d.\n", num_starts);
+ pr_debug("#startup loops: %d.\n", num_starts);
for (j = 1; j <= num_starts; j++) {
- Dprintk("Sending STARTUP #%d.\n", j);
+ pr_debug("Sending STARTUP #%d.\n", j);
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- Dprintk("After apic_write.\n");
+ pr_debug("After apic_write.\n");
/*
* STARTUP IPI
*/
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write(APIC_ICR, APIC_DM_STARTUP | (start_eip >> 12));
+ apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+ phys_apicid);
/*
* Give the other CPU some time to accept the IPI.
*/
udelay(300);
- Dprintk("Startup point 1.\n");
+ pr_debug("Startup point 1.\n");
- Dprintk("Waiting for send to finish...\n");
+ pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
/*
if (send_status || accept_status)
break;
}
- Dprintk("After Startup.\n");
+ pr_debug("After Startup.\n");
if (send_status)
printk(KERN_ERR "APIC never delivered???\n");
*
* Must be called after the _cpu_pda pointer table is initialized.
*/
- static int __cpuinit get_local_pda(int cpu)
+ int __cpuinit get_local_pda(int cpu)
{
struct x8664_pda *oldpda, *newpda;
unsigned long size = sizeof(struct x8664_pda);
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
- Dprintk("Setting warm reset code and vector.\n");
+ pr_debug("Setting warm reset code and vector.\n");
store_NMI_vector(&nmi_high, &nmi_low);
/*
* allow APs to start initializing.
*/
- Dprintk("Before Callout %d.\n", cpu);
+ pr_debug("Before Callout %d.\n", cpu);
cpu_set(cpu, cpu_callout_map);
- Dprintk("After Callout %d.\n", cpu);
+ pr_debug("After Callout %d.\n", cpu);
/*
* Wait 5s total for a response
if (cpu_isset(cpu, cpu_callin_map)) {
/* number CPUs logically, starting from 1 (BSP is 0) */
- Dprintk("OK.\n");
+ pr_debug("OK.\n");
printk(KERN_INFO "CPU%d: ", cpu);
print_cpu_info(&cpu_data(cpu));
- Dprintk("CPU has booted.\n");
+ pr_debug("CPU has booted.\n");
} else {
boot_error = 1;
if (*((volatile unsigned char *)trampoline_base)
WARN_ON(irqs_disabled());
- Dprintk("++++++++++++++++++++=_---CPU UP %u\n", cpu);
+ pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu);
if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid ||
!physid_isset(apicid, phys_cpu_present_map)) {
* Already booted CPU?
*/
if (cpu_isset(cpu, cpu_callin_map)) {
- Dprintk("do_boot_cpu %d Already started\n", cpu);
+ pr_debug("do_boot_cpu %d Already started\n", cpu);
return -ENOSYS;
}
err = do_boot_cpu(apicid, cpu);
#endif
if (err) {
- Dprintk("do_boot_cpu failed %d\n", err);
+ pr_debug("do_boot_cpu failed %d\n", err);
return -EIO;
}
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* Final full version of the data */
+#ifdef CONFIG_X86_32
boot_cpu_logical_apicid = logical_smp_processor_id();
+#endif
current_thread_info()->cpu = 0; /* needed? */
set_cpu_sibling_map(0);
+#ifdef CONFIG_X86_64
+ enable_IR_x2apic();
+ setup_apic_routing();
+#endif
+
if (smp_sanity_check(max_cpus) < 0) {
printk(KERN_INFO "SMP disabled\n");
disable_smp();
}
preempt_disable();
- if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+ if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
- GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+ read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
preempt_enable();
void __init native_smp_cpus_done(unsigned int max_cpus)
{
- Dprintk("Boot done.\n");
+ pr_debug("Boot done.\n");
impress_friends();
smp_checks();
cpu_clear(cpu, cpu_callout_map);
cpu_clear(cpu, cpu_callin_map);
/* was set by cpu_init() */
- clear_bit(cpu, (unsigned long *)&cpu_initialized);
+ cpu_clear(cpu, cpu_initialized);
numa_remove_cpu(cpu);
}
{
extern unsigned int maxcpus;
- maxcpus = simple_strtoul(arg, NULL, 0);
+ if (arg)
+ maxcpus = simple_strtoul(arg, NULL, 0);
return 0;
}
early_param("maxcpus", parse_maxcpus);
#include <xen/interface/sched.h>
#include <xen/features.h>
#include <xen/page.h>
+ #include <xen/hvc-console.h>
#include <asm/paravirt.h>
+#include <asm/apic.h>
#include <asm/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
+ #include <asm/msr-index.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
- #include <asm/pgalloc.h>
#include "xen-ops.h"
#include "mmu.h"
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+ /*
+ * Identity map, in addition to plain kernel map. This needs to be
+ * large enough to allocate page table pages to allocate the rest.
+ * Each page can map 2MB.
+ */
+ static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
+
+ #ifdef CONFIG_X86_64
+ /* l3 pud for userspace vsyscall mapping */
+ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+ #endif /* CONFIG_X86_64 */
+
/*
* Note about cr3 (pagetable base) values:
*
static void __init xen_banner(void)
{
+ unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
+ struct xen_extraversion extra;
+ HYPERVISOR_xen_version(XENVER_extraversion, &extra);
+
printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
pv_info.name);
- printk(KERN_INFO "Hypervisor signature: %s%s\n",
- xen_start_info->magic,
+ printk(KERN_INFO "Xen version: %d.%d%s%s\n",
+ version >> 16, version & 0xffff, extra.extraversion,
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
- xen_mc_batch();
-
- load_TLS_descriptor(t, cpu, 0);
- load_TLS_descriptor(t, cpu, 1);
- load_TLS_descriptor(t, cpu, 2);
-
- xen_mc_issue(PARAVIRT_LAZY_CPU);
-
/*
* XXX sleazy hack: If we're being called in a lazy-cpu zone,
* it means we're in a context switch, and %gs has just been
* Either way, it has been saved, and the new value will get
* loaded properly. This will go away as soon as Xen has been
* modified to not save/restore %gs for normal hypercalls.
+ *
+ * On x86_64, this hack is not used for %gs, because gs points
+ * to KERNEL_GS_BASE (and uses it for PDA references), so we
+ * must not zero %gs on x86_64
+ *
+ * For x86_64, we need to zero %fs, otherwise we may get an
+ * exception between the new %fs descriptor being loaded and
+ * %fs being effectively cleared at __switch_to().
*/
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+ #ifdef CONFIG_X86_32
loadsegment(gs, 0);
+ #else
+ loadsegment(fs, 0);
+ #endif
+ }
+
+ xen_mc_batch();
+
+ load_TLS_descriptor(t, cpu, 0);
+ load_TLS_descriptor(t, cpu, 1);
+ load_TLS_descriptor(t, cpu, 2);
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+ }
+
+ #ifdef CONFIG_X86_64
+ static void xen_load_gs_index(unsigned int idx)
+ {
+ if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
+ BUG();
}
+ #endif
static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
const void *ptr)
preempt_enable();
}
- static int cvt_gate_to_trap(int vector, u32 low, u32 high,
+ static int cvt_gate_to_trap(int vector, const gate_desc *val,
struct trap_info *info)
{
- u8 type, dpl;
-
- type = (high >> 8) & 0x1f;
- dpl = (high >> 13) & 3;
-
- if (type != 0xf && type != 0xe)
+ if (val->type != 0xf && val->type != 0xe)
return 0;
info->vector = vector;
- info->address = (high & 0xffff0000) | (low & 0x0000ffff);
- info->cs = low >> 16;
- info->flags = dpl;
+ info->address = gate_offset(*val);
+ info->cs = gate_segment(*val);
+ info->flags = val->dpl;
/* interrupt gates clear IF */
- if (type == 0xe)
+ if (val->type == 0xe)
info->flags |= 4;
return 1;
if (p >= start && (p + 8) <= end) {
struct trap_info info[2];
- u32 *desc = (u32 *)g;
info[1].address = 0;
- if (cvt_gate_to_trap(entrynum, desc[0], desc[1], &info[0]))
+ if (cvt_gate_to_trap(entrynum, g, &info[0]))
if (HYPERVISOR_set_trap_table(info))
BUG();
}
{
unsigned in, out, count;
- count = (desc->size+1) / 8;
+ count = (desc->size+1) / sizeof(gate_desc);
BUG_ON(count > 256);
for (in = out = 0; in < count; in++) {
- const u32 *entry = (u32 *)(desc->address + in * 8);
+ gate_desc *entry = (gate_desc*)(desc->address) + in;
- if (cvt_gate_to_trap(in, entry[0], entry[1], &traps[out]))
+ if (cvt_gate_to_trap(in, entry, &traps[out]))
out++;
}
traps[out].address = 0;
}
#ifdef CONFIG_X86_LOCAL_APIC
-static u32 xen_apic_read(unsigned long reg)
+static u32 xen_apic_read(u32 reg)
{
return 0;
}
-static void xen_apic_write(unsigned long reg, u32 val)
+static void xen_apic_write(u32 reg, u32 val)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
+
+static u64 xen_apic_icr_read(void)
+{
+ return 0;
+}
+
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+ /* Warn to see if there's any stray references */
+ WARN_ON(1);
+}
+
+static void xen_apic_wait_icr_idle(void)
+{
+ return;
+}
+
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+ return 0;
+}
+
+static struct apic_ops xen_basic_apic_ops = {
+ .read = xen_apic_read,
+ .write = xen_apic_write,
+ .icr_read = xen_apic_icr_read,
+ .icr_write = xen_apic_icr_write,
+ .wait_icr_idle = xen_apic_wait_icr_idle,
+ .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
+};
+
#endif
static void xen_flush_tlb(void)
x86_write_percpu(xen_current_cr3, (unsigned long)v);
}
- static void xen_write_cr3(unsigned long cr3)
+ static void __xen_write_cr3(bool kernel, unsigned long cr3)
{
struct mmuext_op *op;
struct multicall_space mcs;
- unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
+ unsigned long mfn;
- BUG_ON(preemptible());
+ if (cr3)
+ mfn = pfn_to_mfn(PFN_DOWN(cr3));
+ else
+ mfn = 0;
- mcs = xen_mc_entry(sizeof(*op)); /* disables interrupts */
+ WARN_ON(mfn == 0 && kernel);
- /* Update while interrupts are disabled, so its atomic with
- respect to ipis */
- x86_write_percpu(xen_cr3, cr3);
+ mcs = __xen_mc_entry(sizeof(*op));
op = mcs.args;
- op->cmd = MMUEXT_NEW_BASEPTR;
+ op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
op->arg1.mfn = mfn;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- /* Update xen_update_cr3 once the batch has actually
- been submitted. */
- xen_mc_callback(set_current_cr3, (void *)cr3);
+ if (kernel) {
+ x86_write_percpu(xen_cr3, cr3);
+
+ /* Update xen_current_cr3 once the batch has actually
+ been submitted. */
+ xen_mc_callback(set_current_cr3, (void *)cr3);
+ }
+ }
+
+ static void xen_write_cr3(unsigned long cr3)
+ {
+ BUG_ON(preemptible());
+
+ xen_mc_batch(); /* disables interrupts */
+
+ /* Update while interrupts are disabled, so its atomic with
+ respect to ipis */
+ x86_write_percpu(xen_cr3, cr3);
+
+ __xen_write_cr3(true, cr3);
+
+ #ifdef CONFIG_X86_64
+ {
+ pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+ if (user_pgd)
+ __xen_write_cr3(false, __pa(user_pgd));
+ else
+ __xen_write_cr3(false, 0);
+ }
+ #endif
xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
+ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
+ {
+ int ret;
+
+ ret = 0;
+
+ switch(msr) {
+ #ifdef CONFIG_X86_64
+ unsigned which;
+ u64 base;
+
+ case MSR_FS_BASE: which = SEGBASE_FS; goto set;
+ case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set;
+ case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set;
+
+ set:
+ base = ((u64)high << 32) | low;
+ if (HYPERVISOR_set_segment_base(which, base) != 0)
+ ret = -EFAULT;
+ break;
+ #endif
+ default:
+ ret = native_write_msr_safe(msr, low, high);
+ }
+
+ return ret;
+ }
+
/* Early in boot, while setting up the initial pagetable, assume
everything is pinned. */
static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn)
xen_alloc_ptpage(mm, pfn, PT_PMD);
}
+ static int xen_pgd_alloc(struct mm_struct *mm)
+ {
+ pgd_t *pgd = mm->pgd;
+ int ret = 0;
+
+ BUG_ON(PagePinned(virt_to_page(pgd)));
+
+ #ifdef CONFIG_X86_64
+ {
+ struct page *page = virt_to_page(pgd);
+ pgd_t *user_pgd;
+
+ BUG_ON(page->private != 0);
+
+ ret = -ENOMEM;
+
+ user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ page->private = (unsigned long)user_pgd;
+
+ if (user_pgd != NULL) {
+ user_pgd[pgd_index(VSYSCALL_START)] =
+ __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+ ret = 0;
+ }
+
+ BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+ }
+ #endif
+
+ return ret;
+ }
+
+ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+ {
+ #ifdef CONFIG_X86_64
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+ if (user_pgd)
+ free_page((unsigned long)user_pgd);
+ #endif
+ }
+
/* This should never happen until we're OK to use struct page */
static void xen_release_ptpage(u32 pfn, unsigned level)
{
xen_release_ptpage(pfn, PT_PMD);
}
+ #if PAGETABLE_LEVELS == 4
+ static void xen_alloc_pud(struct mm_struct *mm, u32 pfn)
+ {
+ xen_alloc_ptpage(mm, pfn, PT_PUD);
+ }
+
+ static void xen_release_pud(u32 pfn)
+ {
+ xen_release_ptpage(pfn, PT_PUD);
+ }
+ #endif
+
#ifdef CONFIG_HIGHPTE
static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
{
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. This
- * is a stand-in while we copy the pmd pages.
- */
- memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
-
- /*
- * 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);
-
- make_lowmem_page_readonly(pmd);
-
- 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 */
- make_lowmem_page_readonly(empty_zero_page);
- make_lowmem_page_readonly(base);
- /*
- * Switch to new pagetable. This is done before
- * pagetable_init has done anything so that the new pages
- * added to the table can be prepared properly for Xen.
- */
- xen_write_cr3(__pa(base));
-
- /* Unpin initial Xen pagetable */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
- PFN_DOWN(__pa(xen_start_info->pt_base)));
}
void xen_setup_shared_info(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
- /*
- * Create a mapping for the shared info page.
- * Should be set_fixmap(), but shared_info is a machine
- * address with no corresponding pseudo-phys address.
- */
- set_pte_mfn(addr,
- PFN_DOWN(xen_start_info->shared_info),
- PAGE_KERNEL);
-
- HYPERVISOR_shared_info = (struct shared_info *)addr;
+ set_fixmap(FIX_PARAVIRT_BOOTMAP,
+ xen_start_info->shared_info);
+
+ HYPERVISOR_shared_info =
+ (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
} else
HYPERVISOR_shared_info =
(struct shared_info *)__va(xen_start_info->shared_info);
static __init void xen_pagetable_setup_done(pgd_t *base)
{
- /* This will work as long as patching hasn't happened yet
- (which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
- pv_mmu_ops.set_pte = xen_set_pte;
-
xen_setup_shared_info();
-
- /* Actually pin the pagetable down, but we can't set PG_pinned
- yet because the page structures don't exist yet. */
- pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
}
static __init void xen_post_allocator_init(void)
{
+ pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
+ #if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.set_pgd = xen_set_pgd;
+ #endif
+
+ /* This will work as long as patching hasn't happened yet
+ (which it hasn't) */
+ pv_mmu_ops.alloc_pte = xen_alloc_pte;
+ pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
+ pv_mmu_ops.release_pte = xen_release_pte;
+ pv_mmu_ops.release_pmd = xen_release_pmd;
+ #if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.alloc_pud = xen_alloc_pud;
+ pv_mmu_ops.release_pud = xen_release_pud;
+ #endif
+ #ifdef CONFIG_X86_64
+ SetPagePinned(virt_to_page(level3_user_vsyscall));
+ #endif
xen_mark_init_mm_pinned();
}
/* xen_vcpu_setup managed to place the vcpu_info within the
percpu area for all cpus, so make use of it */
+ #ifdef CONFIG_X86_32
if (have_vcpu_info_placement) {
printk(KERN_INFO "Xen: using vcpu_info placement\n");
pv_irq_ops.irq_enable = xen_irq_enable_direct;
pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
}
+ #endif
}
static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
goto patch_site
switch (type) {
+ #ifdef CONFIG_X86_32
SITE(pv_irq_ops, irq_enable);
SITE(pv_irq_ops, irq_disable);
SITE(pv_irq_ops, save_fl);
SITE(pv_irq_ops, restore_fl);
+ #endif /* CONFIG_X86_32 */
#undef SITE
patch_site:
#ifdef CONFIG_X86_F00F_BUG
case FIX_F00F_IDT:
#endif
+ #ifdef CONFIG_X86_32
case FIX_WP_TEST:
case FIX_VDSO:
+ # ifdef CONFIG_HIGHMEM
+ case FIX_KMAP_BEGIN ... FIX_KMAP_END:
+ # endif
+ #else
+ case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+ #endif
#ifdef CONFIG_X86_LOCAL_APIC
case FIX_APIC_BASE: /* maps dummy local APIC */
#endif
}
__native_set_fixmap(idx, pte);
+
+ #ifdef CONFIG_X86_64
+ /* Replicate changes to map the vsyscall page into the user
+ pagetable vsyscall mapping. */
+ if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+ unsigned long vaddr = __fix_to_virt(idx);
+ set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
+ }
+ #endif
}
static const struct pv_info xen_info __initdata = {
.wbinvd = native_wbinvd,
.read_msr = native_read_msr_safe,
- .write_msr = native_write_msr_safe,
+ .write_msr = xen_write_msr_safe,
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
.iret = xen_iret,
.irq_enable_sysexit = xen_sysexit,
+ #ifdef CONFIG_X86_64
+ .usergs_sysret32 = xen_sysret32,
+ .usergs_sysret64 = xen_sysret64,
+ #endif
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.load_gdt = xen_load_gdt,
.load_idt = xen_load_idt,
.load_tls = xen_load_tls,
+ #ifdef CONFIG_X86_64
+ .load_gs_index = xen_load_gs_index,
+ #endif
.store_gdt = native_store_gdt,
.store_idt = native_store_idt,
.set_iopl_mask = xen_set_iopl_mask,
.io_delay = xen_io_delay,
+ /* Xen takes care of %gs when switching to usermode for us */
+ .swapgs = paravirt_nop,
+
.lazy_mode = {
.enter = paravirt_enter_lazy_cpu,
.leave = xen_leave_lazy,
},
};
+ static void __init __xen_init_IRQ(void)
+ {
+ #ifdef CONFIG_X86_64
+ int i;
+
+ /* Create identity vector->irq map */
+ for(i = 0; i < NR_VECTORS; i++) {
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(vector_irq, cpu)[i] = i;
+ }
+ #endif /* CONFIG_X86_64 */
+
+ xen_init_IRQ();
+ }
+
static const struct pv_irq_ops xen_irq_ops __initdata = {
- .init_IRQ = xen_init_IRQ,
+ .init_IRQ = __xen_init_IRQ,
.save_fl = xen_save_fl,
.restore_fl = xen_restore_fl,
.irq_disable = xen_irq_disable,
.safe_halt = xen_safe_halt,
.halt = xen_halt,
#ifdef CONFIG_X86_64
- .adjust_exception_frame = paravirt_nop,
+ .adjust_exception_frame = xen_adjust_exception_frame,
#endif
};
static const struct pv_apic_ops xen_apic_ops __initdata = {
#ifdef CONFIG_X86_LOCAL_APIC
- .apic_write = xen_apic_write,
- .apic_read = xen_apic_read,
.setup_boot_clock = paravirt_nop,
.setup_secondary_clock = paravirt_nop,
.startup_ipi_hook = paravirt_nop,
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
- .pgd_alloc = __paravirt_pgd_alloc,
- .pgd_free = paravirt_nop,
+ .pgd_alloc = xen_pgd_alloc,
+ .pgd_free = xen_pgd_free,
.alloc_pte = xen_alloc_pte_init,
.release_pte = xen_release_pte_init,
.kmap_atomic_pte = xen_kmap_atomic_pte,
#endif
- .set_pte = NULL, /* see xen_pagetable_setup_* */
+ #ifdef CONFIG_X86_64
+ .set_pte = xen_set_pte,
+ #else
+ .set_pte = xen_set_pte_init,
+ #endif
.set_pte_at = xen_set_pte_at,
.set_pmd = xen_set_pmd_hyper,
.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_hyper,
.pte_clear = xen_pte_clear,
.pmd_clear = xen_pmd_clear,
+ #endif /* CONFIG_X86_PAE */
+ .set_pud = xen_set_pud_hyper,
.make_pmd = xen_make_pmd,
.pmd_val = xen_pmd_val,
+ #if PAGETABLE_LEVELS == 4
+ .pud_val = xen_pud_val,
+ .make_pud = xen_make_pud,
+ .set_pgd = xen_set_pgd_hyper,
+
+ .alloc_pud = xen_alloc_pte_init,
+ .release_pud = xen_release_pte_init,
+ #endif /* PAGETABLE_LEVELS == 4 */
+
.activate_mm = xen_activate_mm,
.dup_mmap = xen_dup_mmap,
.exit_mmap = xen_exit_mmap,
.set_fixmap = xen_set_fixmap,
};
- #ifdef CONFIG_SMP
- static const struct smp_ops xen_smp_ops __initdata = {
- .smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
- .smp_prepare_cpus = xen_smp_prepare_cpus,
- .cpu_up = xen_cpu_up,
- .smp_cpus_done = xen_smp_cpus_done,
-
- .smp_send_stop = xen_smp_send_stop,
- .smp_send_reschedule = xen_smp_send_reschedule,
-
- .send_call_func_ipi = xen_smp_send_call_function_ipi,
- .send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
- };
- #endif /* CONFIG_SMP */
-
static void xen_reboot(int reason)
{
struct sched_shutdown r = { .reason = reason };
static void __init xen_reserve_top(void)
{
+ #ifdef CONFIG_X86_32
unsigned long top = HYPERVISOR_VIRT_START;
struct xen_platform_parameters pp;
top = pp.virt_start;
reserve_top_address(-top + 2 * PAGE_SIZE);
+ #endif /* CONFIG_X86_32 */
+ }
+
+ /*
+ * Like __va(), but returns address in the kernel mapping (which is
+ * all we have until the physical memory mapping has been set up.
+ */
+ static void *__ka(phys_addr_t paddr)
+ {
+ #ifdef CONFIG_X86_64
+ return (void *)(paddr + __START_KERNEL_map);
+ #else
+ return __va(paddr);
+ #endif
}
+ /* Convert a machine address to physical address */
+ static unsigned long m2p(phys_addr_t maddr)
+ {
+ phys_addr_t paddr;
+
+ maddr &= PTE_MASK;
+ paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
+
+ return paddr;
+ }
+
+ /* Convert a machine address to kernel virtual */
+ static void *m2v(phys_addr_t maddr)
+ {
+ return __ka(m2p(maddr));
+ }
+
+ #ifdef CONFIG_X86_64
+ static void walk(pgd_t *pgd, unsigned long addr)
+ {
+ unsigned l4idx = pgd_index(addr);
+ unsigned l3idx = pud_index(addr);
+ unsigned l2idx = pmd_index(addr);
+ unsigned l1idx = pte_index(addr);
+ pgd_t l4;
+ pud_t l3;
+ pmd_t l2;
+ pte_t l1;
+
+ xen_raw_printk("walk %p, %lx -> %d %d %d %d\n",
+ pgd, addr, l4idx, l3idx, l2idx, l1idx);
+
+ l4 = pgd[l4idx];
+ xen_raw_printk(" l4: %016lx\n", l4.pgd);
+ xen_raw_printk(" %016lx\n", pgd_val(l4));
+
+ l3 = ((pud_t *)(m2v(l4.pgd)))[l3idx];
+ xen_raw_printk(" l3: %016lx\n", l3.pud);
+ xen_raw_printk(" %016lx\n", pud_val(l3));
+
+ l2 = ((pmd_t *)(m2v(l3.pud)))[l2idx];
+ xen_raw_printk(" l2: %016lx\n", l2.pmd);
+ xen_raw_printk(" %016lx\n", pmd_val(l2));
+
+ l1 = ((pte_t *)(m2v(l2.pmd)))[l1idx];
+ xen_raw_printk(" l1: %016lx\n", l1.pte);
+ xen_raw_printk(" %016lx\n", pte_val(l1));
+ }
+ #endif
+
+ static void set_page_prot(void *addr, pgprot_t prot)
+ {
+ unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+ pte_t pte = pfn_pte(pfn, prot);
+
+ xen_raw_printk("addr=%p pfn=%lx mfn=%lx prot=%016llx pte=%016llx\n",
+ addr, pfn, get_phys_to_machine(pfn),
+ pgprot_val(prot), pte.pte);
+
+ if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+ BUG();
+ }
+
+ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+ {
+ unsigned pmdidx, pteidx;
+ unsigned ident_pte;
+ unsigned long pfn;
+
+ ident_pte = 0;
+ pfn = 0;
+ for(pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+ pte_t *pte_page;
+
+ /* Reuse or allocate a page of ptes */
+ if (pmd_present(pmd[pmdidx]))
+ pte_page = m2v(pmd[pmdidx].pmd);
+ else {
+ /* Check for free pte pages */
+ if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
+ break;
+
+ pte_page = &level1_ident_pgt[ident_pte];
+ ident_pte += PTRS_PER_PTE;
+
+ pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
+ }
+
+ /* Install mappings */
+ for(pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+ pte_t pte;
+
+ if (pfn > max_pfn_mapped)
+ max_pfn_mapped = pfn;
+
+ if (!pte_none(pte_page[pteidx]))
+ continue;
+
+ pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
+ pte_page[pteidx] = pte;
+ }
+ }
+
+ for(pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+ set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
+
+ set_page_prot(pmd, PAGE_KERNEL_RO);
+ }
+
+ #ifdef CONFIG_X86_64
+ static void convert_pfn_mfn(void *v)
+ {
+ pte_t *pte = v;
+ int i;
+
+ /* All levels are converted the same way, so just treat them
+ as ptes. */
+ for(i = 0; i < PTRS_PER_PTE; i++)
+ pte[i] = xen_make_pte(pte[i].pte);
+ }
+
+ /*
+ * Set up the inital kernel pagetable.
+ *
+ * We can construct this by grafting the Xen provided pagetable into
+ * head_64.S's preconstructed pagetables. We copy the Xen L2's into
+ * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This
+ * means that only the kernel has a physical mapping to start with -
+ * but that's enough to get __va working. We need to fill in the rest
+ * of the physical mapping once some sort of allocator has been set
+ * up.
+ */
+ static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+ {
+ pud_t *l3;
+ pmd_t *l2;
+
+ /* Zap identity mapping */
+ init_level4_pgt[0] = __pgd(0);
+
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ convert_pfn_mfn(init_level4_pgt);
+ convert_pfn_mfn(level3_ident_pgt);
+ convert_pfn_mfn(level3_kernel_pgt);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
+
+ memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+ memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
+ memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ /* Set up identity map */
+ xen_map_identity_early(level2_ident_pgt, max_pfn);
+
+ /* Make pagetable pieces RO */
+ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ /* Switch over */
+ pgd = init_level4_pgt;
+
+ /*
+ * At this stage there can be no user pgd, and no page
+ * structure to attach it to, so make sure we just set kernel
+ * pgd.
+ */
+ xen_mc_batch();
+ __xen_write_cr3(true, __pa(pgd));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+
+ reserve_early(__pa(xen_start_info->pt_base),
+ __pa(xen_start_info->pt_base +
+ xen_start_info->nr_pt_frames * PAGE_SIZE),
+ "XEN PAGETABLES");
+
+ return pgd;
+ }
+ #else /* !CONFIG_X86_64 */
+ static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
+
+ static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+ {
+ pmd_t *kernel_pmd;
+
+ init_pg_tables_start = __pa(pgd);
+ init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
+ max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
+
+ kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+ memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ xen_map_identity_early(level2_kernel_pgt, max_pfn);
+
+ memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
+ __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+ set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
+
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ xen_write_cr3(__pa(swapper_pg_dir));
+
+ pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+
+ return swapper_pg_dir;
+ }
+ #endif /* CONFIG_X86_64 */
+
/* First C function to be called on Xen boot */
asmlinkage void __init xen_start_kernel(void)
{
pv_apic_ops = xen_apic_ops;
pv_mmu_ops = xen_mmu_ops;
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * set up the basic apic ops.
+ */
+ apic_ops = &xen_basic_apic_ops;
+#endif
+
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
machine_ops = xen_machine_ops;
- #ifdef CONFIG_SMP
- smp_ops = xen_smp_ops;
+ #ifdef CONFIG_X86_64
+ /* Disable until direct per-cpu data access. */
+ have_vcpu_info_placement = 0;
+ x86_64_init_pda();
#endif
+ xen_smp_init();
+
/* Get mfn list */
if (!xen_feature(XENFEAT_auto_translated_physmap))
xen_build_dynamic_phys_to_machine();
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;
- max_pfn_mapped = (init_pg_tables_end + 512*1024) >> PAGE_SHIFT;
-
- init_mm.pgd = pgd; /* use the Xen pagetables to start */
-
- /* keep using Xen gdt for now; no urgent need to change it */
-
- x86_write_percpu(xen_cr3, __pa(pgd));
- x86_write_percpu(xen_current_cr3, __pa(pgd));
+ /* Prevent unwanted bits from being set in PTEs. */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
+ if (!is_initial_xendomain())
+ __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
+ xen_raw_console_write("mapping kernel into physical memory\n");
+ pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+
+ init_mm.pgd = pgd;
+
+ /* keep using Xen gdt for now; no urgent need to change it */
+
pv_info.kernel_rpl = 1;
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();
+ #ifdef CONFIG_X86_32
/* set up basic CPUID stuff */
cpu_detect(&new_cpu_data);
new_cpu_data.hard_math = 1;
new_cpu_data.x86_capability[0] = cpuid_edx(1);
+ #endif
/* Poke various useful things into boot_params */
boot_params.hdr.type_of_loader = (9 << 4) | 0;
boot_params.hdr.ramdisk_image = xen_start_info->mod_start
? __pa(xen_start_info->mod_start) : 0;
boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
+ boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
if (!is_initial_xendomain()) {
add_preferred_console("xenboot", 0, NULL);
add_preferred_console("hvc", 0, NULL);
}
+ xen_raw_console_write("about to get started...\n");
+
+ #if 0
+ xen_raw_printk("&boot_params=%p __pa(&boot_params)=%lx __va(__pa(&boot_params))=%lx\n",
+ &boot_params, __pa_symbol(&boot_params),
+ __va(__pa_symbol(&boot_params)));
+
+ walk(pgd, &boot_params);
+ walk(pgd, __va(__pa(&boot_params)));
+ #endif
+
/* Start the world */
+ #ifdef CONFIG_X86_32
i386_start_kernel();
+ #else
+ x86_64_start_reservations((char *)__pa_symbol(&boot_params));
+ #endif
}
#include "intel-iommu.h"
#include <asm/proto.h> /* force_iommu in this header in x86-64*/
#include <asm/cacheflush.h>
- #include <asm/gart.h>
+ #include <asm/iommu.h>
#include "pci.h"
#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
-#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) /* 10sec */
-
#define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1)
DEFINE_TIMER(unmap_timer, flush_unmaps_timeout, 0, 0);
-static struct intel_iommu *g_iommus;
-
#define HIGH_WATER_MARK 250
struct deferred_flush_tables {
int next;
static void domain_remove_dev_info(struct dmar_domain *domain);
-static int dmar_disabled;
+int dmar_disabled;
static int __initdata dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;
kmem_cache_free(iommu_iova_cache, iova);
}
-static inline void __iommu_flush_cache(
- struct intel_iommu *iommu, void *addr, int size)
-{
- if (!ecap_coherent(iommu->ecap))
- clflush_cache_range(addr, size);
-}
-
/* Gets context entry for a given bus and devfn */
static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
u8 bus, u8 devfn)
return 0;
}
-#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \
-{\
- cycles_t start_time = get_cycles();\
- while (1) {\
- sts = op (iommu->reg + offset);\
- if (cond)\
- break;\
- if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\
- panic("DMAR hardware is malfunctioning\n");\
- cpu_relax();\
- }\
-}
-
static void iommu_set_root_entry(struct intel_iommu *iommu)
{
void *addr;
return -ENOMEM;
}
+ spin_lock_init(&iommu->lock);
+
/*
* if Caching mode is set, then invalid translations are tagged
* with domainid 0. Hence we need to pre-allocate it.
set_bit(0, iommu->domain_ids);
return 0;
}
-static struct intel_iommu *alloc_iommu(struct intel_iommu *iommu,
- struct dmar_drhd_unit *drhd)
-{
- int ret;
- int map_size;
- u32 ver;
-
- iommu->reg = ioremap(drhd->reg_base_addr, PAGE_SIZE_4K);
- if (!iommu->reg) {
- printk(KERN_ERR "IOMMU: can't map the region\n");
- goto error;
- }
- iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
- iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
-
- /* the registers might be more than one page */
- map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
- cap_max_fault_reg_offset(iommu->cap));
- map_size = PAGE_ALIGN_4K(map_size);
- if (map_size > PAGE_SIZE_4K) {
- iounmap(iommu->reg);
- iommu->reg = ioremap(drhd->reg_base_addr, map_size);
- if (!iommu->reg) {
- printk(KERN_ERR "IOMMU: can't map the region\n");
- goto error;
- }
- }
-
- ver = readl(iommu->reg + DMAR_VER_REG);
- pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
- drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
- iommu->cap, iommu->ecap);
- ret = iommu_init_domains(iommu);
- if (ret)
- goto error_unmap;
- spin_lock_init(&iommu->lock);
- spin_lock_init(&iommu->register_lock);
- drhd->iommu = iommu;
- return iommu;
-error_unmap:
- iounmap(iommu->reg);
-error:
- kfree(iommu);
- return NULL;
-}
static void domain_exit(struct dmar_domain *domain);
-static void free_iommu(struct intel_iommu *iommu)
+
+void free_dmar_iommu(struct intel_iommu *iommu)
{
struct dmar_domain *domain;
int i;
- if (!iommu)
- return;
-
i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap));
for (; i < cap_ndoms(iommu->cap); ) {
domain = iommu->domains[i];
/* free context mapping */
free_context_table(iommu);
-
- if (iommu->reg)
- iounmap(iommu->reg);
- kfree(iommu);
}
static struct dmar_domain * iommu_alloc_domain(struct intel_iommu *iommu)
return NULL;
}
-static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
- struct pci_dev *dev)
-{
- int index;
-
- while (dev) {
- for (index = 0; index < cnt; index++)
- if (dev == devices[index])
- return 1;
-
- /* Check our parent */
- dev = dev->bus->self;
- }
-
- return 0;
-}
-
-static struct dmar_drhd_unit *
-dmar_find_matched_drhd_unit(struct pci_dev *dev)
-{
- struct dmar_drhd_unit *drhd = NULL;
-
- list_for_each_entry(drhd, &dmar_drhd_units, list) {
- if (drhd->include_all || dmar_pci_device_match(drhd->devices,
- drhd->devices_cnt, dev))
- return drhd;
- }
-
- return NULL;
-}
-
/* domain is initialized */
static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
{
* endfor
*/
for_each_drhd_unit(drhd) {
- if (drhd->ignored)
- continue;
g_num_of_iommus++;
/*
* lock not needed as this is only incremented in the single
*/
}
- g_iommus = kzalloc(g_num_of_iommus * sizeof(*iommu), GFP_KERNEL);
- if (!g_iommus) {
- ret = -ENOMEM;
- goto error;
- }
-
deferred_flush = kzalloc(g_num_of_iommus *
sizeof(struct deferred_flush_tables), GFP_KERNEL);
if (!deferred_flush) {
goto error;
}
- i = 0;
for_each_drhd_unit(drhd) {
if (drhd->ignored)
continue;
- iommu = alloc_iommu(&g_iommus[i], drhd);
- i++;
- if (!iommu) {
- ret = -ENOMEM;
+
+ iommu = drhd->iommu;
+
+ ret = iommu_init_domains(iommu);
+ if (ret)
goto error;
- }
/*
* TBD:
iommu = drhd->iommu;
free_iommu(iommu);
}
- kfree(g_iommus);
return ret;
}
/* just flush them all */
for (i = 0; i < g_num_of_iommus; i++) {
if (deferred_flush[i].next) {
- iommu_flush_iotlb_global(&g_iommus[i], 0);
+ struct intel_iommu *iommu =
+ deferred_flush[i].domain[0]->iommu;
+
+ iommu_flush_iotlb_global(iommu, 0);
for (j = 0; j < deferred_flush[i].next; j++) {
__free_iova(&deferred_flush[i].domain[j]->iovad,
deferred_flush[i].iova[j]);
if (list_size == HIGH_WATER_MARK)
flush_unmaps();
- iommu_id = dom->iommu - g_iommus;
+ iommu_id = dom->iommu->seq_id;
+
next = deferred_flush[iommu_id].next;
deferred_flush[iommu_id].domain[next] = dom;
deferred_flush[iommu_id].iova[next] = iova;
}
-void __init detect_intel_iommu(void)
-{
- if (swiotlb || no_iommu || iommu_detected || dmar_disabled)
- return;
- if (early_dmar_detect()) {
- iommu_detected = 1;
- }
-}
-
static void __init init_no_remapping_devices(void)
{
struct dmar_drhd_unit *drhd;
{
int ret = 0;
- if (no_iommu || swiotlb || dmar_disabled)
- return -ENODEV;
-
if (dmar_table_init())
return -ENODEV;
+ if (dmar_dev_scope_init())
+ return -ENODEV;
+
+ /*
+ * Check the need for DMA-remapping initialization now.
+ * Above initialization will also be used by Interrupt-remapping.
+ */
+ if (no_iommu || swiotlb || dmar_disabled)
+ return -ENODEV;
+
iommu_init_mempool();
dmar_init_reserved_ranges();
#include <asm/apicdef.h>
#include <asm/processor.h>
#include <asm/system.h>
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
- #define Dprintk printk
-
/*
* Debugging macros
*/
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
-#define apic_write native_apic_write
-#define apic_read native_apic_read
#define setup_boot_clock setup_boot_APIC_clock
#define setup_secondary_clock setup_secondary_APIC_clock
#endif
extern int is_vsmp_box(void);
-static inline void native_apic_write(unsigned long reg, u32 v)
+static inline void native_apic_mem_write(u32 reg, u32 v)
{
volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
ASM_OUTPUT2("0" (v), "m" (*addr)));
}
-static inline u32 native_apic_read(unsigned long reg)
+static inline u32 native_apic_mem_read(u32 reg)
{
return *((volatile u32 *)(APIC_BASE + reg));
}
-extern void apic_wait_icr_idle(void);
-extern u32 safe_apic_wait_icr_idle(void);
+static inline void native_apic_msr_write(u32 reg, u32 v)
+{
+ if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
+ reg == APIC_LVR)
+ return;
+
+ wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
+}
+
+static inline u32 native_apic_msr_read(u32 reg)
+{
+ u32 low, high;
+
+ if (reg == APIC_DFR)
+ return -1;
+
+ rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
+ return low;
+}
+
+#ifndef CONFIG_X86_32
+extern int x2apic, x2apic_preenabled;
+extern void check_x2apic(void);
+extern void enable_x2apic(void);
+extern void enable_IR_x2apic(void);
+extern void x2apic_icr_write(u32 low, u32 id);
+#endif
+
+struct apic_ops {
+ u32 (*read)(u32 reg);
+ void (*write)(u32 reg, u32 v);
+ u64 (*icr_read)(void);
+ void (*icr_write)(u32 low, u32 high);
+ void (*wait_icr_idle)(void);
+ u32 (*safe_wait_icr_idle)(void);
+};
+
+extern struct apic_ops *apic_ops;
+
+#define apic_read (apic_ops->read)
+#define apic_write (apic_ops->write)
+#define apic_icr_read (apic_ops->icr_read)
+#define apic_icr_write (apic_ops->icr_write)
+#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
+#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+
extern int get_physical_broadcast(void);
+#ifdef CONFIG_X86_64
+static inline void ack_x2APIC_irq(void)
+{
+ /* Docs say use 0 for future compatibility */
+ native_apic_msr_write(APIC_EOI, 0);
+}
+#endif
+
+
static inline void ack_APIC_irq(void)
{
/*
*/
/* Docs say use 0 for future compatibility */
+#ifdef CONFIG_X86_32
apic_write(APIC_EOI, 0);
+#else
+ native_apic_mem_write(APIC_EOI, 0);
+#endif
}
extern int lapic_get_maxlvt(void);
struct pv_apic_ops {
#ifdef CONFIG_X86_LOCAL_APIC
- /*
- * Direct APIC operations, principally for VMI. Ideally
- * these shouldn't be in this interface.
- */
- void (*apic_write)(unsigned long reg, u32 v);
- u32 (*apic_read)(unsigned long reg);
void (*setup_boot_clock)(void);
void (*setup_secondary_clock)(void);
unsigned long phys, pgprot_t flags);
};
+ struct raw_spinlock;
+ struct pv_lock_ops {
+ int (*spin_is_locked)(struct raw_spinlock *lock);
+ int (*spin_is_contended)(struct raw_spinlock *lock);
+ void (*spin_lock)(struct raw_spinlock *lock);
+ int (*spin_trylock)(struct raw_spinlock *lock);
+ void (*spin_unlock)(struct raw_spinlock *lock);
+ };
+
/* This contains all the paravirt structures: we get a convenient
* number for each function using the offset which we use to indicate
* what to patch. */
struct pv_irq_ops pv_irq_ops;
struct pv_apic_ops pv_apic_ops;
struct pv_mmu_ops pv_mmu_ops;
+ struct pv_lock_ops pv_lock_ops;
};
extern struct pv_info pv_info;
extern struct pv_irq_ops pv_irq_ops;
extern struct pv_apic_ops pv_apic_ops;
extern struct pv_mmu_ops pv_mmu_ops;
+ extern struct pv_lock_ops pv_lock_ops;
#define PARAVIRT_PATCH(x) \
(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
}
#ifdef CONFIG_X86_LOCAL_APIC
-/*
- * Basic functions accessing APICs.
- */
-static inline void apic_write(unsigned long reg, u32 v)
-{
- PVOP_VCALL2(pv_apic_ops.apic_write, reg, v);
-}
-
-static inline u32 apic_read(unsigned long reg)
-{
- return PVOP_CALL1(unsigned long, pv_apic_ops.apic_read, reg);
-}
-
static inline void setup_boot_clock(void)
{
PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
void _paravirt_nop(void);
#define paravirt_nop ((void *)_paravirt_nop)
+ void paravirt_use_bytelocks(void);
+
+ #ifdef CONFIG_SMP
+
+ static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+ {
+ return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+ }
+
+ static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+ {
+ return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
+ }
+
+ static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+ {
+ PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
+ }
+
+ static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
+ {
+ return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
+ }
+
+ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+ {
+ PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+ }
+
+ #endif
+
/* These all sit in the .parainstructions section to tell us what to patch. */
struct paravirt_patch_site {
u8 *instr; /* original instructions */
* caller saved registers but the argument parameter */
#define PV_SAVE_REGS "pushq %%rdi;"
#define PV_RESTORE_REGS "popq %%rdi;"
- #define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx"
- #define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx"
+ #define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
+ #define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
#define PV_FLAGS_ARG "D"
#endif
return f;
}
+
/* Make sure as little as possible of this mess escapes. */
#undef PARAVIRT_CALL
#undef __PVOP_CALL
#ifdef CONFIG_X86_64
- #define PV_SAVE_REGS pushq %rax; pushq %rdi; pushq %rcx; pushq %rdx
- #define PV_RESTORE_REGS popq %rdx; popq %rcx; popq %rdi; popq %rax
+ #define PV_SAVE_REGS \
+ push %rax; \
+ push %rcx; \
+ push %rdx; \
+ push %rsi; \
+ push %rdi; \
+ push %r8; \
+ push %r9; \
+ push %r10; \
+ push %r11
+ #define PV_RESTORE_REGS \
+ pop %r11; \
+ pop %r10; \
+ pop %r9; \
+ pop %r8; \
+ pop %rdi; \
+ pop %rsi; \
+ pop %rdx; \
+ pop %rcx; \
+ pop %rax
#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8)
#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
extern void (*mtrr_hook)(void);
extern void zap_low_mappings(void);
+ extern int __cpuinit get_local_pda(int cpu);
+
extern int smp_num_siblings;
extern unsigned int num_processors;
extern cpumask_t cpu_initialized;
#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef CONFIG_X86_64
static inline int logical_smp_processor_id(void)
{
/* we don't want to mark this access volatile - bad code generation */
return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
}
-#ifndef CONFIG_X86_64
+#include <mach_apicdef.h>
static inline unsigned int read_apic_id(void)
{
- return *(u32 *)(APIC_BASE + APIC_ID);
+ unsigned int reg;
+
+ reg = *(u32 *)(APIC_BASE + APIC_ID);
+
+ return GET_APIC_ID(reg);
}
-#else
-extern unsigned int read_apic_id(void);
#endif
-# ifdef APIC_DEFINITION
+# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
extern int hard_smp_processor_id(void);
# else
-# include <mach_apicdef.h>
+#include <mach_apicdef.h>
static inline int hard_smp_processor_id(void)
{
/* we don't want to mark this access volatile - bad code generation */
- return GET_APIC_ID(read_apic_id());
+ return read_apic_id();
}
# endif /* APIC_DEFINITION */