aboutsummaryrefslogtreecommitdiff
path: root/arch/i386
diff options
context:
space:
mode:
Diffstat (limited to 'arch/i386')
-rw-r--r--arch/i386/Kconfig40
-rw-r--r--arch/i386/Makefile7
-rw-r--r--arch/i386/boot/install.sh4
-rw-r--r--arch/i386/kernel/apic.c2
-rw-r--r--arch/i386/kernel/cpu/common.c2
-rw-r--r--arch/i386/kernel/cpu/mtrr/main.c23
-rw-r--r--arch/i386/kernel/cpu/proc.c2
-rw-r--r--arch/i386/kernel/i386_ksyms.c160
-rw-r--r--arch/i386/kernel/i387.c3
-rw-r--r--arch/i386/kernel/io_apic.c13
-rw-r--r--arch/i386/kernel/kprobes.c176
-rw-r--r--arch/i386/kernel/mpparse.c31
-rw-r--r--arch/i386/kernel/nmi.c24
-rw-r--r--arch/i386/kernel/pci-dma.c3
-rw-r--r--arch/i386/kernel/process.c36
-rw-r--r--arch/i386/kernel/ptrace.c2
-rw-r--r--arch/i386/kernel/reboot.c5
-rw-r--r--arch/i386/kernel/setup.c28
-rw-r--r--arch/i386/kernel/signal.c31
-rw-r--r--arch/i386/kernel/smp.c3
-rw-r--r--arch/i386/kernel/smpboot.c14
-rw-r--r--arch/i386/kernel/time.c6
-rw-r--r--arch/i386/kernel/timers/common.c12
-rw-r--r--arch/i386/kernel/timers/timer.c9
-rw-r--r--arch/i386/kernel/timers/timer_hpet.c3
-rw-r--r--arch/i386/kernel/timers/timer_pm.c1
-rw-r--r--arch/i386/kernel/timers/timer_tsc.c8
-rw-r--r--arch/i386/kernel/traps.c21
-rw-r--r--arch/i386/lib/dec_and_lock.c2
-rw-r--r--arch/i386/lib/delay.c6
-rw-r--r--arch/i386/lib/mmx.c5
-rw-r--r--arch/i386/lib/usercopy.c8
-rw-r--r--arch/i386/mach-voyager/voyager_smp.c2
-rw-r--r--arch/i386/mm/Makefile2
-rw-r--r--arch/i386/mm/discontig.c127
-rw-r--r--arch/i386/mm/highmem.c6
-rw-r--r--arch/i386/mm/init.c21
-rw-r--r--arch/i386/mm/ioremap.c5
-rw-r--r--arch/i386/mm/pgtable.c10
-rw-r--r--arch/i386/oprofile/backtrace.c2
-rw-r--r--arch/i386/pci/irq.c22
-rw-r--r--arch/i386/pci/pcbios.c4
-rw-r--r--arch/i386/power/cpu.c14
43 files changed, 585 insertions, 320 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index dfd904f6883..d4ae5f9ceae 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -68,7 +68,6 @@ config X86_VOYAGER
config X86_NUMAQ
bool "NUMAQ (IBM/Sequent)"
- select DISCONTIGMEM
select NUMA
help
This option is used for getting Linux to run on a (IBM/Sequent) NUMA
@@ -783,25 +782,48 @@ comment "NUMA (NUMA-Q) requires SMP, 64GB highmem support"
comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI)
-config DISCONTIGMEM
- bool
- depends on NUMA
- default y
-
config HAVE_ARCH_BOOTMEM_NODE
bool
depends on NUMA
default y
-config HAVE_MEMORY_PRESENT
+config ARCH_HAVE_MEMORY_PRESENT
bool
depends on DISCONTIGMEM
default y
config NEED_NODE_MEMMAP_SIZE
bool
- depends on DISCONTIGMEM
+ depends on DISCONTIGMEM || SPARSEMEM
+ default y
+
+config HAVE_ARCH_ALLOC_REMAP
+ bool
+ depends on NUMA
+ default y
+
+config ARCH_DISCONTIGMEM_ENABLE
+ def_bool y
+ depends on NUMA
+
+config ARCH_DISCONTIGMEM_DEFAULT
+ def_bool y
+ depends on NUMA
+
+config ARCH_SPARSEMEM_ENABLE
+ def_bool y
+ depends on NUMA
+
+config ARCH_SELECT_MEMORY_MODEL
+ def_bool y
+ depends on ARCH_SPARSEMEM_ENABLE
+
+source "mm/Kconfig"
+
+config HAVE_ARCH_EARLY_PFN_TO_NID
+ bool
default y
+ depends on NUMA
config HIGHPTE
bool "Allocate 3rd-level pagetables from highmem"
@@ -939,6 +961,8 @@ config SECCOMP
If unsure, say Y. Only embedded should say N here.
+source kernel/Kconfig.hz
+
endmenu
diff --git a/arch/i386/Makefile b/arch/i386/Makefile
index 1c36ca332a9..bf7c9ba709f 100644
--- a/arch/i386/Makefile
+++ b/arch/i386/Makefile
@@ -17,6 +17,13 @@
# 20050320 Kianusch Sayah Karadji <kianusch@sk-tech.net>
# Added support for GEODE CPU
+HAS_BIARCH := $(call cc-option-yn, -m32)
+ifeq ($(HAS_BIARCH),y)
+AS := $(AS) --32
+LD := $(LD) -m elf_i386
+CC := $(CC) -m32
+endif
+
LDFLAGS := -m elf_i386
OBJCOPYFLAGS := -O binary -R .note -R .comment -S
LDFLAGS_vmlinux :=
diff --git a/arch/i386/boot/install.sh b/arch/i386/boot/install.sh
index 90f2452b3b9..f17b40dfc0f 100644
--- a/arch/i386/boot/install.sh
+++ b/arch/i386/boot/install.sh
@@ -21,8 +21,8 @@
# User may have a custom install script
-if [ -x ~/bin/installkernel ]; then exec ~/bin/installkernel "$@"; fi
-if [ -x /sbin/installkernel ]; then exec /sbin/installkernel "$@"; fi
+if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi
+if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi
# Default install - same as make zlilo
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index d509836b70c..8d993fa7175 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -1133,7 +1133,7 @@ inline void smp_local_timer_interrupt(struct pt_regs * regs)
}
#ifdef CONFIG_SMP
- update_process_times(user_mode(regs));
+ update_process_times(user_mode_vm(regs));
#endif
}
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index d199e525680..b9954248d0a 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -635,7 +635,7 @@ void __init cpu_init (void)
/* Clear all 6 debug registers: */
-#define CD(register) __asm__("movl %0,%%db" #register ::"r"(0) );
+#define CD(register) set_debugreg(0, register)
CD(0); CD(1); CD(2); CD(3); /* no db4 and db5 */; CD(6); CD(7);
diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index e1c2042b9b7..d66b09e0c82 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -375,6 +375,19 @@ int mtrr_add_page(unsigned long base, unsigned long size,
return error;
}
+static int mtrr_check(unsigned long base, unsigned long size)
+{
+ if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
+ printk(KERN_WARNING
+ "mtrr: size and base must be multiples of 4 kiB\n");
+ printk(KERN_DEBUG
+ "mtrr: size: 0x%lx base: 0x%lx\n", size, base);
+ dump_stack();
+ return -1;
+ }
+ return 0;
+}
+
/**
* mtrr_add - Add a memory type region
* @base: Physical base address of region
@@ -415,11 +428,8 @@ int
mtrr_add(unsigned long base, unsigned long size, unsigned int type,
char increment)
{
- if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
- printk(KERN_WARNING "mtrr: size and base must be multiples of 4 kiB\n");
- printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base);
+ if (mtrr_check(base, size))
return -EINVAL;
- }
return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
increment);
}
@@ -511,11 +521,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
int
mtrr_del(int reg, unsigned long base, unsigned long size)
{
- if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
- printk(KERN_INFO "mtrr: size and base must be multiples of 4 kiB\n");
- printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base);
+ if (mtrr_check(base, size))
return -EINVAL;
- }
return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
}
diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c
index 7323c19f354..8bd77d948a8 100644
--- a/arch/i386/kernel/cpu/proc.c
+++ b/arch/i386/kernel/cpu/proc.c
@@ -86,7 +86,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "stepping\t: unknown\n");
if ( cpu_has(c, X86_FEATURE_TSC) ) {
- seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n",
+ seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
cpu_khz / 1000, (cpu_khz % 1000));
}
diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c
index 903190a4b3f..180f070d03c 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -1,97 +1,17 @@
#include <linux/config.h>
#include <linux/module.h>
-#include <linux/smp.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/mca.h>
-#include <linux/sched.h>
-#include <linux/in6.h>
-#include <linux/interrupt.h>
-#include <linux/smp_lock.h>
-#include <linux/pm.h>
-#include <linux/pci.h>
-#include <linux/apm_bios.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/tty.h>
-#include <linux/highmem.h>
-#include <linux/time.h>
-
-#include <asm/semaphore.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/uaccess.h>
#include <asm/checksum.h>
-#include <asm/io.h>
-#include <asm/delay.h>
-#include <asm/irq.h>
-#include <asm/mmx.h>
#include <asm/desc.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <asm/nmi.h>
-#include <asm/ist.h>
-#include <asm/kdebug.h>
-
-extern void dump_thread(struct pt_regs *, struct user *);
-extern spinlock_t rtc_lock;
/* This is definitely a GPL-only symbol */
EXPORT_SYMBOL_GPL(cpu_gdt_table);
-#if defined(CONFIG_APM_MODULE)
-extern void machine_real_restart(unsigned char *, int);
-EXPORT_SYMBOL(machine_real_restart);
-extern void default_idle(void);
-EXPORT_SYMBOL(default_idle);
-#endif
-
-#ifdef CONFIG_SMP
-extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
-extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
-#endif
-
-#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
-extern struct drive_info_struct drive_info;
-EXPORT_SYMBOL(drive_info);
-#endif
-
-extern unsigned long cpu_khz;
-extern unsigned long get_cmos_time(void);
-
-/* platform dependent support */
-EXPORT_SYMBOL(boot_cpu_data);
-#ifdef CONFIG_DISCONTIGMEM
-EXPORT_SYMBOL(node_data);
-EXPORT_SYMBOL(physnode_map);
-#endif
-#ifdef CONFIG_X86_NUMAQ
-EXPORT_SYMBOL(xquad_portio);
-#endif
-EXPORT_SYMBOL(dump_thread);
-EXPORT_SYMBOL(dump_fpu);
-EXPORT_SYMBOL_GPL(kernel_fpu_begin);
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(ioremap_nocache);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(pm_idle);
-EXPORT_SYMBOL(pm_power_off);
-EXPORT_SYMBOL(get_cmos_time);
-EXPORT_SYMBOL(cpu_khz);
-EXPORT_SYMBOL(apm_info);
-
EXPORT_SYMBOL(__down_failed);
EXPORT_SYMBOL(__down_failed_interruptible);
EXPORT_SYMBOL(__down_failed_trylock);
EXPORT_SYMBOL(__up_wakeup);
/* Networking helper routines. */
EXPORT_SYMBOL(csum_partial_copy_generic);
-/* Delay loops */
-EXPORT_SYMBOL(__ndelay);
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__delay);
-EXPORT_SYMBOL(__const_udelay);
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
@@ -105,87 +25,11 @@ EXPORT_SYMBOL(__put_user_8);
EXPORT_SYMBOL(strpbrk);
EXPORT_SYMBOL(strstr);
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__copy_from_user_ll);
-EXPORT_SYMBOL(__copy_to_user_ll);
-EXPORT_SYMBOL(strnlen_user);
-
-EXPORT_SYMBOL(dma_alloc_coherent);
-EXPORT_SYMBOL(dma_free_coherent);
-
-#ifdef CONFIG_PCI
-EXPORT_SYMBOL(pci_mem_start);
-#endif
-
-#ifdef CONFIG_PCI_BIOS
-EXPORT_SYMBOL(pcibios_set_irq_routing);
-EXPORT_SYMBOL(pcibios_get_irq_routing_table);
-#endif
-
-#ifdef CONFIG_X86_USE_3DNOW
-EXPORT_SYMBOL(_mmx_memcpy);
-EXPORT_SYMBOL(mmx_clear_page);
-EXPORT_SYMBOL(mmx_copy_page);
-#endif
-
-#ifdef CONFIG_X86_HT
-EXPORT_SYMBOL(smp_num_siblings);
-EXPORT_SYMBOL(cpu_sibling_map);
-#endif
-
#ifdef CONFIG_SMP
-EXPORT_SYMBOL(cpu_data);
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(cpu_callout_map);
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
EXPORT_SYMBOL(__write_lock_failed);
EXPORT_SYMBOL(__read_lock_failed);
-
-/* Global SMP stuff */
-EXPORT_SYMBOL(smp_call_function);
-
-/* TLB flushing */
-EXPORT_SYMBOL(flush_tlb_page);
-#endif
-
-#ifdef CONFIG_X86_IO_APIC
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-#endif
-
-#ifdef CONFIG_MCA
-EXPORT_SYMBOL(machine_id);
-#endif
-
-#ifdef CONFIG_VT
-EXPORT_SYMBOL(screen_info);
-#endif
-
-EXPORT_SYMBOL(get_wchan);
-
-EXPORT_SYMBOL(rtc_lock);
-
-EXPORT_SYMBOL_GPL(set_nmi_callback);
-EXPORT_SYMBOL_GPL(unset_nmi_callback);
-
-EXPORT_SYMBOL(register_die_notifier);
-#ifdef CONFIG_HAVE_DEC_LOCK
-EXPORT_SYMBOL(_atomic_dec_and_lock);
-#endif
-
-EXPORT_SYMBOL(__PAGE_KERNEL);
-
-#ifdef CONFIG_HIGHMEM
-EXPORT_SYMBOL(kmap);
-EXPORT_SYMBOL(kunmap);
-EXPORT_SYMBOL(kmap_atomic);
-EXPORT_SYMBOL(kunmap_atomic);
-EXPORT_SYMBOL(kmap_atomic_to_page);
-#endif
-
-#if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
-EXPORT_SYMBOL(ist_info);
#endif
EXPORT_SYMBOL(csum_partial);
diff --git a/arch/i386/kernel/i387.c b/arch/i386/kernel/i387.c
index c55e037f08f..b817168d9c6 100644
--- a/arch/i386/kernel/i387.c
+++ b/arch/i386/kernel/i387.c
@@ -10,6 +10,7 @@
#include <linux/config.h>
#include <linux/sched.h>
+#include <linux/module.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/math_emu.h>
@@ -79,6 +80,7 @@ void kernel_fpu_begin(void)
}
clts();
}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
void restore_fpu( struct task_struct *tsk )
{
@@ -526,6 +528,7 @@ int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu )
return fpvalid;
}
+EXPORT_SYMBOL(dump_fpu);
int dump_task_fpu(struct task_struct *tsk, struct user_i387_struct *fpu)
{
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 7a324e8b86f..08540bc4ba3 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -31,7 +31,7 @@
#include <linux/mc146818rtc.h>
#include <linux/compiler.h>
#include <linux/acpi.h>
-
+#include <linux/module.h>
#include <linux/sysdev.h>
#include <asm/io.h>
#include <asm/smp.h>
@@ -812,6 +812,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
}
return best_guess;
}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
/*
* This function currently is only a helper for the i386 smp boot process where
@@ -1659,6 +1660,12 @@ static void __init setup_ioapic_ids_from_mpc(void)
unsigned long flags;
/*
+ * Don't check I/O APIC IDs for xAPIC systems. They have
+ * no meaning without the serial APIC bus.
+ */
+ if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 < 15))
+ return;
+ /*
* This is broken; anything with a real cpu count has to
* circumvent this idiocy regardless.
*/
@@ -1684,10 +1691,6 @@ static void __init setup_ioapic_ids_from_mpc(void)
mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
}
- /* Don't check I/O APIC IDs for some xAPIC systems. They have
- * no meaning without the serial APIC bus. */
- if (NO_IOAPIC_CHECK)
- continue;
/*
* Sanity check, is the ID really free? Every APIC in a
* system must have a unique ID or we get lots of nice
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 59ff9b45506..3762f6b35ab 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -23,6 +23,9 @@
* Rusty Russell).
* 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
* interface to access function arguments.
+ * 2005-May Hien Nguyen <hien@us.ibm.com>, Jim Keniston
+ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
+ * <prasanna@in.ibm.com> added function-return probes.
*/
#include <linux/config.h>
@@ -30,15 +33,14 @@
#include <linux/ptrace.h>
#include <linux/spinlock.h>
#include <linux/preempt.h>
+#include <asm/cacheflush.h>
#include <asm/kdebug.h>
#include <asm/desc.h>
-/* kprobe_status settings */
-#define KPROBE_HIT_ACTIVE 0x00000001
-#define KPROBE_HIT_SS 0x00000002
-
static struct kprobe *current_kprobe;
static unsigned long kprobe_status, kprobe_old_eflags, kprobe_saved_eflags;
+static struct kprobe *kprobe_prev;
+static unsigned long kprobe_status_prev, kprobe_old_eflags_prev, kprobe_saved_eflags_prev;
static struct pt_regs jprobe_saved_regs;
static long *jprobe_saved_esp;
/* copy of the kernel stack at the probe fire time */
@@ -68,16 +70,50 @@ int arch_prepare_kprobe(struct kprobe *p)
void arch_copy_kprobe(struct kprobe *p)
{
memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ p->opcode = *p->addr;
}
-void arch_remove_kprobe(struct kprobe *p)
+void arch_arm_kprobe(struct kprobe *p)
{
+ *p->addr = BREAKPOINT_INSTRUCTION;
+ flush_icache_range((unsigned long) p->addr,
+ (unsigned long) p->addr + sizeof(kprobe_opcode_t));
}
-static inline void disarm_kprobe(struct kprobe *p, struct pt_regs *regs)
+void arch_disarm_kprobe(struct kprobe *p)
{
*p->addr = p->opcode;
- regs->eip = (unsigned long)p->addr;
+ flush_icache_range((unsigned long) p->addr,
+ (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+}
+
+void arch_remove_kprobe(struct kprobe *p)
+{
+}
+
+static inline void save_previous_kprobe(void)
+{
+ kprobe_prev = current_kprobe;
+ kprobe_status_prev = kprobe_status;
+ kprobe_old_eflags_prev = kprobe_old_eflags;
+ kprobe_saved_eflags_prev = kprobe_saved_eflags;
+}
+
+static inline void restore_previous_kprobe(void)
+{
+ current_kprobe = kprobe_prev;
+ kprobe_status = kprobe_status_prev;
+ kprobe_old_eflags = kprobe_old_eflags_prev;
+ kprobe_saved_eflags = kprobe_saved_eflags_prev;
+}
+
+static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs)
+{
+ current_kprobe = p;
+ kprobe_saved_eflags = kprobe_old_eflags
+ = (regs->eflags & (TF_MASK | IF_MASK));
+ if (is_IF_modifier(p->opcode))
+ kprobe_saved_eflags &= ~IF_MASK;
}
static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
@@ -91,6 +127,50 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
regs->eip = (unsigned long)&p->ainsn.insn;
}
+struct task_struct *arch_get_kprobe_task(void *ptr)
+{
+ return ((struct thread_info *) (((unsigned long) ptr) &
+ (~(THREAD_SIZE -1))))->task;
+}
+
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+ unsigned long *sara = (unsigned long *)&regs->esp;
+ struct kretprobe_instance *ri;
+ static void *orig_ret_addr;
+
+ /*
+ * Save the return address when the return probe hits
+ * the first time, and use it to populate the (krprobe
+ * instance)->ret_addr for subsequent return probes at
+ * the same addrress since stack address would have
+ * the kretprobe_trampoline by then.
+ */
+ if (((void*) *sara) != kretprobe_trampoline)
+ orig_ret_addr = (void*) *sara;
+
+ if ((ri = get_free_rp_inst(rp)) != NULL) {
+ ri->rp = rp;
+ ri->stack_addr = sara;
+ ri->ret_addr = orig_ret_addr;
+ add_rp_inst(ri);
+ /* Replace the return addr with trampoline addr */
+ *sara = (unsigned long) &kretprobe_trampoline;
+ } else {
+ rp->nmissed++;
+ }
+}
+
+void arch_kprobe_flush_task(struct task_struct *tk)
+{
+ struct kretprobe_instance *ri;
+ while ((ri = get_rp_inst_tsk(tk)) != NULL) {
+ *((unsigned long *)(ri->stack_addr)) =
+ (unsigned long) ri->ret_addr;
+ recycle_rp_inst(ri);
+ }
+}
+
/*
* Interrupts are disabled on entry as trap3 is an interrupt gate and they
* remain disabled thorough out this function.
@@ -127,8 +207,18 @@ static int kprobe_handler(struct pt_regs *regs)
unlock_kprobes();
goto no_kprobe;
}
- disarm_kprobe(p, regs);
- ret = 1;
+ /* We have reentered the kprobe_handler(), since
+ * another probe was hit while within the handler.
+ * We here save the original kprobes variables and
+ * just single step on the instruction of the new probe
+ * without calling any user handlers.
+ */
+ save_previous_kprobe();
+ set_current_kprobe(p, regs);
+ p->nmissed++;
+ prepare_singlestep(p, regs);
+ kprobe_status = KPROBE_REENTER;
+ return 1;
} else {
p = current_kprobe;
if (p->break_handler && p->break_handler(p, regs)) {
@@ -163,11 +253,7 @@ static int kprobe_handler(struct pt_regs *regs)
}
kprobe_status = KPROBE_HIT_ACTIVE;
- current_kprobe = p;
- kprobe_saved_eflags = kprobe_old_eflags
- = (regs->eflags & (TF_MASK | IF_MASK));
- if (is_IF_modifier(p->opcode))
- kprobe_saved_eflags &= ~IF_MASK;
+ set_current_kprobe(p, regs);
if (p->pre_handler && p->pre_handler(p, regs))
/* handler has already set things up, so skip ss setup */
@@ -184,6 +270,55 @@ no_kprobe:
}
/*
+ * For function-return probes, init_kprobes() establishes a probepoint
+ * here. When a retprobed function returns, this probe is hit and
+ * trampoline_probe_handler() runs, calling the kretprobe's handler.
+ */
+ void kretprobe_trampoline_holder(void)
+ {
+ asm volatile ( ".global kretprobe_trampoline\n"
+ "kretprobe_trampoline: \n"
+ "nop\n");
+ }
+
+/*
+ * Called when we hit the probe point at kretprobe_trampoline
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct task_struct *tsk;
+ struct kretprobe_instance *ri;
+ struct hlist_head *head;
+ struct hlist_node *node;
+ unsigned long *sara = ((unsigned long *) &regs->esp) - 1;
+
+ tsk = arch_get_kprobe_task(sara);
+ head = kretprobe_inst_table_head(tsk);
+
+ hlist_for_each_entry(ri, node, head, hlist) {
+ if (ri->stack_addr == sara && ri->rp) {
+ if (ri->rp->handler)
+ ri->rp->handler(ri, regs);
+ }
+ }
+ return 0;
+}
+
+void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
+ unsigned long flags)
+{
+ struct kretprobe_instance *ri;
+ /* RA already popped */
+ unsigned long *sara = ((unsigned long *)&regs->esp) - 1;
+
+ while ((ri = get_rp_inst(sara))) {
+ regs->eip = (unsigned long)ri->ret_addr;
+ recycle_rp_inst(ri);
+ }
+ regs->eflags &= ~TF_MASK;
+}
+
+/*
* Called after single-stepping. p->addr is the address of the
* instruction whose first byte has been replaced by the "int 3"
* instruction. To avoid the SMP problems that can occur when we
@@ -263,13 +398,22 @@ static inline int post_kprobe_handler(struct pt_regs *regs)
if (!kprobe_running())
return 0;
- if (current_kprobe->post_handler)
+ if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
+ kprobe_status = KPROBE_HIT_SSDONE;
current_kprobe->post_handler(current_kprobe, regs, 0);
+ }
- resume_execution(current_kprobe, regs);
+ if (current_kprobe->post_handler != trampoline_post_handler)
+ resume_execution(current_kprobe, regs);
regs->eflags |= kprobe_saved_eflags;
+ /*Restore back the original saved kprobes variables and continue. */
+ if (kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe();
+ goto out;
+ }
unlock_kprobes();
+out:
preempt_enable_no_resched();
/*
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index 1347ab4939e..383a11600d2 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -914,7 +914,10 @@ void __init mp_register_ioapic (
mp_ioapics[idx].mpc_apicaddr = address;
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
- mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 < 15))
+ mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+ else
+ mp_ioapics[idx].mpc_apicid = id;
mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
/*
@@ -1055,11 +1058,20 @@ void __init mp_config_acpi_legacy_irqs (void)
}
}
+#define MAX_GSI_NUM 4096
+
int mp_register_gsi (u32 gsi, int edge_level, int active_high_low)
{
int ioapic = -1;
int ioapic_pin = 0;
int idx, bit = 0;
+ static int pci_irq = 16;
+ /*
+ * Mapping between Global System Interrups, which
+ * represent all possible interrupts, and IRQs
+ * assigned to actual devices.
+ */
+ static int gsi_to_irq[MAX_GSI_NUM];
#ifdef CONFIG_ACPI_BUS
/* Don't set up the ACPI SCI because it's already set up */
@@ -1094,11 +1106,26 @@ int mp_register_gsi (u32 gsi, int edge_level, int active_high_low)
if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
- return gsi;
+ return gsi_to_irq[gsi];
}
mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit);
+ if (edge_level) {
+ /*
+ * For PCI devices assign IRQs in order, avoiding gaps
+ * due to unused I/O APIC pins.
+ */
+ int irq = gsi;
+ if (gsi < MAX_GSI_NUM) {
+ gsi = pci_irq++;
+ gsi_to_irq[irq] = gsi;
+ } else {
+ printk(KERN_ERR "GSI %u is too high\n", gsi);
+ return gsi;
+ }
+ }
+
io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1,
active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1);
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 2c0ee9c2d02..da6c46d667c 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -28,8 +28,7 @@
#include <linux/sysctl.h>
#include <asm/smp.h>
-#include <asm/mtrr.h>
-#include <asm/mpspec.h>
+#include <asm/div64.h>
#include <asm/nmi.h>
#include "mach_traps.h"
@@ -324,6 +323,16 @@ static void clear_msr_range(unsigned int base, unsigned int n)
wrmsr(base+i, 0, 0);
}
+static inline void write_watchdog_counter(const char *descr)
+{
+ u64 count = (u64)cpu_khz * 1000;
+
+ do_div(count, nmi_hz);
+ if(descr)
+ Dprintk("setting %s to -0x%08Lx\n", descr, count);
+ wrmsrl(nmi_perfctr_msr, 0 - count);
+}
+
static void setup_k7_watchdog(void)
{
unsigned int evntsel;
@@ -339,8 +348,7 @@ static void setup_k7_watchdog(void)
| K7_NMI_EVENT;
wrmsr(MSR_K7_EVNTSEL0, evntsel, 0);
- Dprintk("setting K7_PERFCTR0 to %08lx\n", -(cpu_khz/nmi_hz*1000));
- wrmsr(MSR_K7_PERFCTR0, -(cpu_khz/nmi_hz*1000), -1);
+ write_watchdog_counter("K7_PERFCTR0");
apic_write(APIC_LVTPC, APIC_DM_NMI);
evntsel |= K7_EVNTSEL_ENABLE;
wrmsr(MSR_K7_EVNTSEL0, evntsel, 0);
@@ -361,8 +369,7 @@ static void setup_p6_watchdog(void)
| P6_NMI_EVENT;
wrmsr(MSR_P6_EVNTSEL0, evntsel, 0);
- Dprintk("setting P6_PERFCTR0 to %08lx\n", -(cpu_khz/nmi_hz*1000));
- wrmsr(MSR_P6_PERFCTR0, -(cpu_khz/nmi_hz*1000), 0);
+ write_watchdog_counter("P6_PERFCTR0");
apic_write(APIC_LVTPC, APIC_DM_NMI);
evntsel |= P6_EVNTSEL0_ENABLE;
wrmsr(MSR_P6_EVNTSEL0, evntsel, 0);
@@ -402,8 +409,7 @@ static int setup_p4_watchdog(void)
wrmsr(MSR_P4_CRU_ESCR0, P4_NMI_CRU_ESCR0, 0);
wrmsr(MSR_P4_IQ_CCCR0, P4_NMI_IQ_CCCR0 & ~P4_CCCR_ENABLE, 0);
- Dprintk("setting P4_IQ_COUNTER0 to 0x%08lx\n", -(cpu_khz/nmi_hz*1000));
- wrmsr(MSR_P4_IQ_COUNTER0, -(cpu_khz/nmi_hz*1000), -1);
+ write_watchdog_counter("P4_IQ_COUNTER0");
apic_write(APIC_LVTPC, APIC_DM_NMI);
wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
return 1;
@@ -518,7 +524,7 @@ void nmi_watchdog_tick (struct pt_regs * regs)
* other P6 variant */
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
- wrmsr(nmi_perfctr_msr, -(cpu_khz/nmi_hz*1000), -1);
+ write_watchdog_counter(NULL);
}
}
diff --git a/arch/i386/kernel/pci-dma.c b/arch/i386/kernel/pci-dma.c
index 4de2e03c7b4..1e51427cc9e 100644
--- a/arch/i386/kernel/pci-dma.c
+++ b/arch/i386/kernel/pci-dma.c
@@ -11,6 +11,7 @@
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/pci.h>
+#include <linux/module.h>
#include <asm/io.h>
struct dma_coherent_mem {
@@ -54,6 +55,7 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
}
return ret;
}
+EXPORT_SYMBOL(dma_alloc_coherent);
void dma_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_handle)
@@ -68,6 +70,7 @@ void dma_free_coherent(struct device *dev, size_t size,
} else
free_pages((unsigned long)vaddr, order);
}
+EXPORT_SYMBOL(dma_free_coherent);
int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
dma_addr_t device_addr, size_t size, int flags)
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 96e3ea6b17c..aea2ce1145d 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -37,6 +37,7 @@
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/random.h>
+#include <linux/kprobes.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -73,6 +74,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
* Powermanagement idle function, if any..
*/
void (*pm_idle)(void);
+EXPORT_SYMBOL(pm_idle);
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
void disable_hlt(void)
@@ -105,6 +107,9 @@ void default_idle(void)
cpu_relax();
}
}
+#ifdef CONFIG_APM_MODULE
+EXPORT_SYMBOL(default_idle);
+#endif
/*
* On SMP it's slightly faster (but much more power-consuming!)
@@ -262,7 +267,7 @@ void show_regs(struct pt_regs * regs)
printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id());
print_symbol("EIP is at %s\n", regs->eip);
- if (regs->xcs & 3)
+ if (user_mode(regs))
printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
printk(" EFLAGS: %08lx %s (%s)\n",
regs->eflags, print_tainted(), system_utsname.release);
@@ -325,6 +330,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
/* Ok, create the new process.. */
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
}
+EXPORT_SYMBOL(kernel_thread);
/*
* Free current thread data structures etc..
@@ -334,6 +340,13 @@ void exit_thread(void)
struct task_struct *tsk = current;
struct thread_struct *t = &tsk->thread;
+ /*
+ * Remove function-return probe instances associated with this task
+ * and put them back on the free list. Do not insert an exit probe for
+ * this function, it will be disabled by kprobe_flush_task if you do.
+ */
+ kprobe_flush_task(tsk);
+
/* The process may have allocated an io port bitmap... nuke it. */
if (unlikely(NULL != t->io_bitmap_ptr)) {
int cpu = get_cpu();
@@ -357,6 +370,13 @@ void flush_thread(void)
{
struct task_struct *tsk = current;
+ /*
+ * Remove function-return probe instances associated with this task
+ * and put them back on the free list. Do not insert an exit probe for
+ * this function, it will be disabled by kprobe_flush_task if you do.
+ */
+ kprobe_flush_task(tsk);
+
memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
/*
@@ -508,6 +528,7 @@ void dump_thread(struct pt_regs * regs, struct user * dump)
dump->u_fpvalid = dump_fpu (regs, &dump->i387);
}
+EXPORT_SYMBOL(dump_thread);
/*
* Capture the user space registers if the task is not running (in user space)
@@ -627,13 +648,13 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
* Now maybe reload the debug registers
*/
if (unlikely(next->debugreg[7])) {
- loaddebug(next, 0);
- loaddebug(next, 1);
- loaddebug(next, 2);
- loaddebug(next, 3);
+ set_debugreg(current->thread.debugreg[0], 0);
+ set_debugreg(current->thread.debugreg[1], 1);
+ set_debugreg(current->thread.debugreg[2], 2);
+ set_debugreg(current->thread.debugreg[3], 3);
/* no 4 and 5 */
- loaddebug(next, 6);
- loaddebug(next, 7);
+ set_debugreg(current->thread.debugreg[6], 6);
+ set_debugreg(current->thread.debugreg[7], 7);
}
if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr))
@@ -731,6 +752,7 @@ unsigned long get_wchan(struct task_struct *p)
} while (count++ < 16);
return 0;
}
+EXPORT_SYMBOL(get_wchan);
/*
* sys_alloc_thread_area: get a yet unused TLS descriptor index.
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index e34f651fa13..0da59b42843 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -668,7 +668,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
info.si_code = TRAP_BRKPT;
/* User-mode eip? */
- info.si_addr = user_mode(regs) ? (void __user *) regs->eip : NULL;
+ info.si_addr = user_mode_vm(regs) ? (void __user *) regs->eip : NULL;
/* Send us the fakey SIGTRAP */
force_sig_info(SIGTRAP, &info, tsk);
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 6dc27eb70ee..db912209a8d 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -2,6 +2,7 @@
* linux/arch/i386/kernel/reboot.c
*/
+#include <linux/config.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/delay.h>
@@ -19,6 +20,7 @@
* Power off function, if any
*/
void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
static int reboot_mode;
static int reboot_thru_bios;
@@ -295,6 +297,9 @@ void machine_real_restart(unsigned char *code, int length)
:
: "i" ((void *) (0x1000 - sizeof (real_mode_switch) - 100)));
}
+#ifdef CONFIG_APM_MODULE
+EXPORT_SYMBOL(machine_real_restart);
+#endif
void machine_restart(char * __unused)
{
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 2bfbddebdbf..30406fd0b64 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -23,8 +23,10 @@
* This file handles the architecture-dependent parts of initialization
*/
+#include <linux/config.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/mmzone.h>
#include <linux/tty.h>
#include <linux/ioport.h>
#include <linux/acpi.h>
@@ -73,6 +75,7 @@ EXPORT_SYMBOL(efi_enabled);
struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
/* common cpu data for all cpus */
struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
+EXPORT_SYMBOL(boot_cpu_data);
unsigned long mmu_cr4_features;
@@ -90,12 +93,18 @@ extern acpi_interrupt_flags acpi_sci_flags;
/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
+#ifdef CONFIG_MCA
+EXPORT_SYMBOL(machine_id);
+#endif
unsigned int machine_submodel_id;
unsigned int BIOS_revision;
unsigned int mca_pentium_flag;
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0x10000000;
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pci_mem_start);
+#endif
/* Boot loader ID as an integer, for the benefit of proc_dointvec */
int bootloader_type;
@@ -107,14 +116,26 @@ static unsigned int highmem_pages = -1;
* Setup options
*/
struct drive_info_struct { char dummy[32]; } drive_info;
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || \
+ defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+EXPORT_SYMBOL(drive_info);
+#endif
struct screen_info screen_info;
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
struct apm_info apm_info;
+EXPORT_SYMBOL(apm_info);
struct sys_desc_table_struct {
unsigned short length;
unsigned char table[0];
};
struct edid_info edid_info;
struct ist_info ist_info;
+#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
+ defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
+EXPORT_SYMBOL(ist_info);
+#endif
struct e820map e820;
extern void early_cpu_init(void);
@@ -1022,7 +1043,7 @@ static void __init reserve_ebda_region(void)
reserve_bootmem(addr, PAGE_SIZE);
}
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init setup_bootmem_allocator(void);
static unsigned long __init setup_memory(void)
{
@@ -1072,9 +1093,9 @@ void __init zone_sizes_init(void)
free_area_init(zones_size);
}
#else
-extern unsigned long setup_memory(void);
+extern unsigned long __init setup_memory(void);
extern void zone_sizes_init(void);
-#endif /* !CONFIG_DISCONTIGMEM */
+#endif /* !CONFIG_NEED_MULTIPLE_NODES */
void __init setup_bootmem_allocator(void)
{
@@ -1475,6 +1496,7 @@ void __init setup_arch(char **cmdline_p)
#endif
paging_init();
remapped_pgdat_init();
+ sparse_init();
zone_sizes_init();
/*
diff --git a/arch/i386/kernel/signal.c b/arch/i386/kernel/signal.c
index ea46d028af0..b9b8f4e20fa 100644
--- a/arch/i386/kernel/signal.c
+++ b/arch/i386/kernel/signal.c
@@ -346,8 +346,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
extern void __user __kernel_sigreturn;
extern void __user __kernel_rt_sigreturn;
-static void setup_frame(int sig, struct k_sigaction *ka,
- sigset_t *set, struct pt_regs * regs)
+static int setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs)
{
void __user *restorer;
struct sigframe __user *frame;
@@ -429,13 +429,14 @@ static void setup_frame(int sig, struct k_sigaction *ka,
current->comm, current->pid, frame, regs->eip, frame->pretcode);
#endif
- return;
+ return 1;
give_sigsegv:
force_sigsegv(sig, current);
+ return 0;
}
-static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs * regs)
{
void __user *restorer;
@@ -522,20 +523,23 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
current->comm, current->pid, frame, regs->eip, frame->pretcode);
#endif
- return;
+ return 1;
give_sigsegv:
force_sigsegv(sig, current);
+ return 0;
}
/*
* OK, we're invoking a handler
*/
-static void
+static int
handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
sigset_t *oldset, struct pt_regs * regs)
{
+ int ret;
+
/* Are we from a system call? */
if (regs->orig_eax >= 0) {
/* If so, check system call restarting.. */
@@ -569,17 +573,19 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
/* Set up the stack frame */
if (ka->sa.sa_flags & SA_SIGINFO)
- setup_rt_frame(sig, ka, info, oldset, regs);
+ ret = setup_rt_frame(sig, ka, info, oldset, regs);
else
- setup_frame(sig, ka, oldset, regs);
+ ret = setup_frame(sig, ka, oldset, regs);
- if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ if (ret && !(ka->sa.sa_flags & SA_NODEFER)) {
spin_lock_irq(&current->sighand->siglock);
sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
sigaddset(&current->blocked,sig);
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
}
+
+ return ret;
}
/*
@@ -599,7 +605,7 @@ int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset)
* kernel mode. Just return without doing anything
* if so.
*/
- if ((regs->xcs & 3) != 3)
+ if (!user_mode(regs))
return 1;
if (current->flags & PF_FREEZE) {
@@ -618,12 +624,11 @@ int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset)
* inside the kernel.
*/
if (unlikely(current->thread.debugreg[7])) {
- loaddebug(&current->thread, 7);
+ set_debugreg(current->thread.debugreg[7], 7);
}
/* Whee! Actually deliver the signal. */
- handle_signal(signr, &info, &ka, oldset, regs);
- return 1;
+ return handle_signal(signr, &info, &ka, oldset, regs);
}
no_signal:
diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
index 6223c33ac91..68be7d0c723 100644
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -19,6 +19,7 @@
#include <linux/mc146818rtc.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
#include <asm/mtrr.h>
#include <asm/tlbflush.h>
@@ -452,6 +453,7 @@ void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
preempt_enable();
}
+EXPORT_SYMBOL(flush_tlb_page);
static void do_flush_tlb_all(void* info)
{
@@ -547,6 +549,7 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
return 0;
}
+EXPORT_SYMBOL(smp_call_function);
static void stop_this_cpu (void * dummy)
{
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index bc1bb6919e6..c20d96d5c15 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -60,6 +60,9 @@ static int __initdata smp_b_stepping;
/* Number of siblings per CPU package */
int smp_num_siblings = 1;
+#ifdef CONFIG_X86_HT
+EXPORT_SYMBOL(smp_num_siblings);
+#endif
int phys_proc_id[NR_CPUS]; /* Package ID of each logical CPU */
EXPORT_SYMBOL(phys_proc_id);
int cpu_core_id[NR_CPUS]; /* Core ID of each logical CPU */
@@ -67,13 +70,16 @@ EXPORT_SYMBOL(cpu_core_id);
/* bitmap of online cpus */
cpumask_t cpu_online_map;
+EXPORT_SYMBOL(cpu_online_map);
cpumask_t cpu_callin_map;
cpumask_t cpu_callout_map;
+EXPORT_SYMBOL(cpu_callout_map);
static cpumask_t smp_commenced_mask;
/* Per CPU bogomips and other parameters */
struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
+EXPORT_SYMBOL(cpu_data);
u8 x86_cpu_to_apicid[NR_CPUS] =
{ [0 ... NR_CPUS-1] = 0xff };
@@ -199,7 +205,7 @@ static void __init synchronize_tsc_bp (void)
unsigned long long t0;
unsigned long long sum, avg;
long long delta;
- unsigned long one_usec;
+ unsigned int one_usec;
int buggy = 0;
printk(KERN_INFO "checking TSC synchronization across %u CPUs: ", num_booting_cpus());
@@ -885,8 +891,14 @@ static void smp_tune_scheduling (void)
static int boot_cpu_logical_apicid;
/* Where the IO area was mapped on multiquad, always 0 otherwise */
void *xquad_portio;
+#ifdef CONFIG_X86_NUMAQ
+EXPORT_SYMBOL(xquad_portio);
+#endif
cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned;
+#ifdef CONFIG_X86_HT
+EXPORT_SYMBOL(cpu_sibling_map);
+#endif
cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
EXPORT_SYMBOL(cpu_core_map);
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index a0dcb7c87c3..e68d9fdb075 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -77,11 +77,13 @@ u64 jiffies_64 = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
-unsigned long cpu_khz; /* Detected as we calibrate the TSC */
+unsigned int cpu_khz; /* Detected as we calibrate the TSC */
+EXPORT_SYMBOL(cpu_khz);
extern unsigned long wall_jiffies;
DEFINE_SPINLOCK(rtc_lock);
+EXPORT_SYMBOL(rtc_lock);
DEFINE_SPINLOCK(i8253_lock);
EXPORT_SYMBOL(i8253_lock);
@@ -324,6 +326,8 @@ unsigned long get_cmos_time(void)
return retval;
}
+EXPORT_SYMBOL(get_cmos_time);
+
static void sync_cmos_clock(unsigned long dummy);
static struct timer_list sync_cmos_timer =
diff --git a/arch/i386/kernel/timers/common.c b/arch/i386/kernel/timers/common.c
index 8e201219f52..37353bd3180 100644
--- a/arch/i386/kernel/timers/common.c
+++ b/arch/i386/kernel/timers/common.c
@@ -139,6 +139,15 @@ bad_calibration:
}
#endif
+
+unsigned long read_timer_tsc(void)
+{
+ unsigned long retval;
+ rdtscl(retval);
+ return retval;
+}
+
+
/* calculate cpu_khz */
void init_cpu_khz(void)
{
@@ -154,7 +163,8 @@ void init_cpu_khz(void)
:"=a" (cpu_khz), "=d" (edx)
:"r" (tsc_quotient),
"0" (eax), "1" (edx));
- printk("Detected %lu.%03lu MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000);
+ printk("Detected %u.%03u MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
}
}
}
diff --git a/arch/i386/kernel/timers/timer.c b/arch/i386/kernel/timers/timer.c
index a3d6a288088..7e39ed8e33f 100644
--- a/arch/i386/kernel/timers/timer.c
+++ b/arch/i386/kernel/timers/timer.c
@@ -64,3 +64,12 @@ struct timer_opts* __init select_timer(void)
panic("select_timer: Cannot find a suitable timer\n");
return NULL;
}
+
+int read_current_timer(unsigned long *timer_val)
+{
+ if (cur_timer->read_timer) {
+ *timer_val = cur_timer->read_timer();
+ return 0;
+ }
+ return -1;
+}
diff --git a/arch/i386/kernel/timers/timer_hpet.c b/arch/i386/kernel/timers/timer_hpet.c
index f778f471a09..d766e0963ac 100644
--- a/arch/i386/kernel/timers/timer_hpet.c
+++ b/arch/i386/kernel/timers/timer_hpet.c
@@ -158,7 +158,7 @@ static int __init init_hpet(char* override)
{ unsigned long eax=0, edx=1000;
ASM_DIV64_REG(cpu_khz, edx, tsc_quotient,
eax, edx);
- printk("Detected %lu.%03lu MHz processor.\n",
+ printk("Detected %u.%03u MHz processor.\n",
cpu_khz / 1000, cpu_khz % 1000);
}
set_cyc2ns_scale(cpu_khz/1000);
@@ -186,6 +186,7 @@ static struct timer_opts timer_hpet = {
.get_offset = get_offset_hpet,
.monotonic_clock = monotonic_clock_hpet,
.delay = delay_hpet,
+ .read_timer = read_timer_tsc,
};
struct init_timer_opts __initdata timer_hpet_init = {
diff --git a/arch/i386/kernel/timers/timer_pm.c b/arch/i386/kernel/timers/timer_pm.c
index d77f22030fe..4ef20e66349 100644
--- a/arch/i386/kernel/timers/timer_pm.c
+++ b/arch/i386/kernel/timers/timer_pm.c
@@ -246,6 +246,7 @@ static struct timer_opts timer_pmtmr = {
.get_offset = get_offset_pmtmr,
.monotonic_clock = monotonic_clock_pmtmr,
.delay = delay_pmtmr,
+ .read_timer = read_timer_tsc,
};
struct init_timer_opts __initdata timer_pmtmr_init = {
diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c
index 180444d8782..54c36b18202 100644
--- a/arch/i386/kernel/timers/timer_tsc.c
+++ b/arch/i386/kernel/timers/timer_tsc.c
@@ -256,7 +256,7 @@ static unsigned long loops_per_jiffy_ref = 0;
#ifndef CONFIG_SMP
static unsigned long fast_gettimeoffset_ref = 0;
-static unsigned long cpu_khz_ref = 0;
+static unsigned int cpu_khz_ref = 0;
#endif
static int
@@ -323,7 +323,7 @@ static inline void cpufreq_delayed_get(void) { return; }
int recalibrate_cpu_khz(void)
{
#ifndef CONFIG_SMP
- unsigned long cpu_khz_old = cpu_khz;
+ unsigned int cpu_khz_old = cpu_khz;
if (cpu_has_tsc) {
init_cpu_khz();
@@ -534,7 +534,8 @@ static int __init init_tsc(char* override)
:"=a" (cpu_khz), "=d" (edx)
:"r" (tsc_quotient),
"0" (eax), "1" (edx));
- printk("Detected %lu.%03lu MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000);
+ printk("Detected %u.%03u MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
}
set_cyc2ns_scale(cpu_khz/1000);
return 0;
@@ -572,6 +573,7 @@ static struct timer_opts timer_tsc = {
.get_offset = get_offset_tsc,
.monotonic_clock = monotonic_clock_tsc,
.delay = delay_tsc,
+ .read_timer = read_timer_tsc,
};
struct init_timer_opts __initdata timer_tsc_init = {
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 83c579e82a8..e4d4e2162c7 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -104,6 +104,7 @@ int register_die_notifier(struct notifier_block *nb)
spin_unlock_irqrestore(&die_notifier_lock, flags);
return err;
}
+EXPORT_SYMBOL(register_die_notifier);
static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
{
@@ -209,7 +210,7 @@ void show_registers(struct pt_regs *regs)
esp = (unsigned long) (&regs->esp);
ss = __KERNEL_DS;
- if (regs->xcs & 3) {
+ if (user_mode(regs)) {
in_kernel = 0;
esp = regs->esp;
ss = regs->xss & 0xffff;
@@ -265,7 +266,7 @@ static void handle_BUG(struct pt_regs *regs)
char c;
unsigned long eip;
- if (regs->xcs & 3)
+ if (user_mode(regs))
goto no_bug; /* Not in kernel */
eip = regs->eip;
@@ -353,7 +354,7 @@ void die(const char * str, struct pt_regs * regs, long err)
static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
{
- if (!(regs->eflags & VM_MASK) && !(3 & regs->xcs))
+ if (!user_mode_vm(regs))
die(str, regs, err);
}
@@ -366,7 +367,7 @@ static void do_trap(int trapnr, int signr, char *str, int vm86,
goto trap_signal;
}
- if (!(regs->xcs & 3))
+ if (!user_mode(regs))
goto kernel_trap;
trap_signal: {
@@ -488,7 +489,7 @@ fastcall void do_general_protection(struct pt_regs * regs, long error_code)
if (regs->eflags & VM_MASK)
goto gp_in_vm86;
- if (!(regs->xcs & 3))
+ if (!user_mode(regs))
goto gp_in_kernel;
current->thread.error_code = error_code;
@@ -636,11 +637,13 @@ void set_nmi_callback(nmi_callback_t callback)
{
nmi_callback = callback;
}
+EXPORT_SYMBOL_GPL(set_nmi_callback);
void unset_nmi_callback(void)
{
nmi_callback = dummy_nmi_callback;
}
+EXPORT_SYMBOL_GPL(unset_nmi_callback);
#ifdef CONFIG_KPROBES
fastcall void do_int3(struct pt_regs *regs, long error_code)
@@ -682,7 +685,7 @@ fastcall void do_debug(struct pt_regs * regs, long error_code)
unsigned int condition;
struct task_struct *tsk = current;
- __asm__ __volatile__("movl %%db6,%0" : "=r" (condition));
+ get_debugreg(condition, 6);
if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
SIGTRAP) == NOTIFY_STOP)
@@ -713,7 +716,7 @@ fastcall void do_debug(struct pt_regs * regs, long error_code)
* check for kernel mode by just checking the CPL
* of CS.
*/
- if ((regs->xcs & 3) == 0)
+ if (!user_mode(regs))
goto clear_TF_reenable;
}
@@ -724,9 +727,7 @@ fastcall void do_debug(struct pt_regs * regs, long error_code)
* the signal is delivered.
*/
clear_dr7:
- __asm__("movl %0,%%db7"
- : /* no output */
- : "r" (0));
+ set_debugreg(0, 7);
return;
debug_vm86:
diff --git a/arch/i386/lib/dec_and_lock.c b/arch/i386/lib/dec_and_lock.c
index ab43394dc77..8b81b2524fa 100644
--- a/arch/i386/lib/dec_and_lock.c
+++ b/arch/i386/lib/dec_and_lock.c
@@ -8,6 +8,7 @@
*/
#include <linux/spinlock.h>
+#include <linux/module.h>
#include <asm/atomic.h>
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
@@ -38,3 +39,4 @@ slow_path:
spin_unlock(lock);
return 0;
}
+EXPORT_SYMBOL(_atomic_dec_and_lock);
diff --git a/arch/i386/lib/delay.c b/arch/i386/lib/delay.c
index eb0cdfe9280..c49a6acbee5 100644
--- a/arch/i386/lib/delay.c
+++ b/arch/i386/lib/delay.c
@@ -13,6 +13,7 @@
#include <linux/config.h>
#include <linux/sched.h>
#include <linux/delay.h>
+#include <linux/module.h>
#include <asm/processor.h>
#include <asm/delay.h>
#include <asm/timer.h>
@@ -47,3 +48,8 @@ void __ndelay(unsigned long nsecs)
{
__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
}
+
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/i386/lib/mmx.c b/arch/i386/lib/mmx.c
index 01f8b1a2cc8..2afda94dffd 100644
--- a/arch/i386/lib/mmx.c
+++ b/arch/i386/lib/mmx.c
@@ -3,6 +3,7 @@
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
+#include <linux/module.h>
#include <asm/i387.h>
@@ -397,3 +398,7 @@ void mmx_copy_page(void *to, void *from)
else
fast_copy_page(to, from);
}
+
+EXPORT_SYMBOL(_mmx_memcpy);
+EXPORT_SYMBOL(mmx_clear_page);
+EXPORT_SYMBOL(mmx_copy_page);
diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c
index 51aa2bbb026..4cf981d70f4 100644
--- a/arch/i386/lib/usercopy.c
+++ b/arch/i386/lib/usercopy.c
@@ -84,6 +84,7 @@ __strncpy_from_user(char *dst, const char __user *src, long count)
__do_strncpy_from_user(dst, src, count, res);
return res;
}
+EXPORT_SYMBOL(__strncpy_from_user);
/**
* strncpy_from_user: - Copy a NUL terminated string from userspace.
@@ -111,7 +112,7 @@ strncpy_from_user(char *dst, const char __user *src, long count)
__do_strncpy_from_user(dst, src, count, res);
return res;
}
-
+EXPORT_SYMBOL(strncpy_from_user);
/*
* Zero Userspace
@@ -157,6 +158,7 @@ clear_user(void __user *to, unsigned long n)
__do_clear_user(to, n);
return n;
}
+EXPORT_SYMBOL(clear_user);
/**
* __clear_user: - Zero a block of memory in user space, with less checking.
@@ -175,6 +177,7 @@ __clear_user(void __user *to, unsigned long n)
__do_clear_user(to, n);
return n;
}
+EXPORT_SYMBOL(__clear_user);
/**
* strlen_user: - Get the size of a string in user space.
@@ -218,6 +221,7 @@ long strnlen_user(const char __user *s, long n)
:"cc");
return res & mask;
}
+EXPORT_SYMBOL(strnlen_user);
#ifdef CONFIG_X86_INTEL_USERCOPY
static unsigned long
@@ -570,6 +574,7 @@ survive:
n = __copy_user_intel(to, from, n);
return n;
}
+EXPORT_SYMBOL(__copy_to_user_ll);
unsigned long
__copy_from_user_ll(void *to, const void __user *from, unsigned long n)
@@ -581,6 +586,7 @@ __copy_from_user_ll(void *to, const void __user *from, unsigned long n)
n = __copy_user_zeroing_intel(to, from, n);
return n;
}
+EXPORT_SYMBOL(__copy_from_user_ll);
/**
* copy_to_user: - Copy a block of data into user space.
diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c
index a6e0ddd65bd..8c8527593da 100644
--- a/arch/i386/mach-voyager/voyager_smp.c
+++ b/arch/i386/mach-voyager/voyager_smp.c
@@ -1288,7 +1288,7 @@ smp_local_timer_interrupt(struct pt_regs * regs)
per_cpu(prof_counter, cpu);
}
- update_process_times(user_mode(regs));
+ update_process_times(user_mode_vm(regs));
}
if( ((1<<cpu) & voyager_extended_vic_processors) == 0)
diff --git a/arch/i386/mm/Makefile b/arch/i386/mm/Makefile
index fc327250684..80908b5aa60 100644
--- a/arch/i386/mm/Makefile
+++ b/arch/i386/mm/Makefile
@@ -4,7 +4,7 @@
obj-y := init.o pgtable.o fault.o ioremap.o extable.o pageattr.o mmap.o
-obj-$(CONFIG_DISCONTIGMEM) += discontig.o
+obj-$(CONFIG_NUMA) += discontig.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_HIGHMEM) += highmem.o
obj-$(CONFIG_BOOT_IOREMAP) += boot_ioremap.o
diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c
index 1726b4096b1..f429c871e84 100644
--- a/arch/i386/mm/discontig.c
+++ b/arch/i386/mm/discontig.c
@@ -29,12 +29,14 @@
#include <linux/highmem.h>
#include <linux/initrd.h>
#include <linux/nodemask.h>
+#include <linux/module.h>
#include <asm/e820.h>
#include <asm/setup.h>
#include <asm/mmzone.h>
#include <bios_ebda.h>
struct pglist_data *node_data[MAX_NUMNODES];
+EXPORT_SYMBOL(node_data);
bootmem_data_t node0_bdata;
/*
@@ -42,12 +44,16 @@ bootmem_data_t node0_bdata;
* populated the following initialisation.
*
* 1) node_online_map - the map of all nodes configured (online) in the system
- * 2) physnode_map - the mapping between a pfn and owning node
- * 3) node_start_pfn - the starting page frame number for a node
+ * 2) node_start_pfn - the starting page frame number for a node
* 3) node_end_pfn - the ending page fram number for a node
*/
+unsigned long node_start_pfn[MAX_NUMNODES];
+unsigned long node_end_pfn[MAX_NUMNODES];
+
+#ifdef CONFIG_DISCONTIGMEM
/*
+ * 4) physnode_map - the mapping between a pfn and owning node
* physnode_map keeps track of the physical memory layout of a generic
* numa node on a 256Mb break (each element of the array will
* represent 256Mb of memory and will be marked by the node id. so,
@@ -59,6 +65,7 @@ bootmem_data_t node0_bdata;
* physnode_map[8- ] = -1;
*/
s8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+EXPORT_SYMBOL(physnode_map);
void memory_present(int nid, unsigned long start, unsigned long end)
{
@@ -85,9 +92,7 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
return (nr_pages + 1) * sizeof(struct page);
}
-
-unsigned long node_start_pfn[MAX_NUMNODES];
-unsigned long node_end_pfn[MAX_NUMNODES];
+#endif
extern unsigned long find_max_low_pfn(void);
extern void find_max_pfn(void);
@@ -108,6 +113,9 @@ unsigned long node_remap_offset[MAX_NUMNODES];
void *node_remap_start_vaddr[MAX_NUMNODES];
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
+void *node_remap_end_vaddr[MAX_NUMNODES];
+void *node_remap_alloc_vaddr[MAX_NUMNODES];
+
/*
* FLAT - support for basic PC memory model with discontig enabled, essentially
* a single node with all available processors in it with a flat
@@ -146,6 +154,21 @@ static void __init find_max_pfn_node(int nid)
BUG();
}
+/* Find the owning node for a pfn. */
+int early_pfn_to_nid(unsigned long pfn)
+{
+ int nid;
+
+ for_each_node(nid) {
+ if (node_end_pfn[nid] == 0)
+ break;
+ if (node_start_pfn[nid] <= pfn && node_end_pfn[nid] >= pfn)
+ return nid;
+ }
+
+ return 0;
+}
+
/*
* Allocate memory for the pg_data_t for this node via a crude pre-bootmem
* method. For node zero take this from the bottom of memory, for
@@ -163,6 +186,21 @@ static void __init allocate_pgdat(int nid)
}
}
+void *alloc_remap(int nid, unsigned long size)
+{
+ void *allocation = node_remap_alloc_vaddr[nid];
+
+ size = ALIGN(size, L1_CACHE_BYTES);
+
+ if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
+ return 0;
+
+ node_remap_alloc_vaddr[nid] += size;
+ memset(allocation, 0, size);
+
+ return allocation;
+}
+
void __init remap_numa_kva(void)
{
void *vaddr;
@@ -170,8 +208,6 @@ void __init remap_numa_kva(void)
int node;
for_each_online_node(node) {
- if (node == 0)
- continue;
for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
set_pmd_pfn((ulong) vaddr,
@@ -185,13 +221,9 @@ static unsigned long calculate_numa_remap_pages(void)
{
int nid;
unsigned long size, reserve_pages = 0;
+ unsigned long pfn;
for_each_online_node(nid) {
- if (nid == 0)
- continue;
- if (!node_remap_size[nid])
- continue;
-
/*
* The acpi/srat node info can show hot-add memroy zones
* where memory could be added but not currently present.
@@ -208,11 +240,24 @@ static unsigned long calculate_numa_remap_pages(void)
size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES;
/* now the roundup is correct, convert to PAGE_SIZE pages */
size = size * PTRS_PER_PTE;
+
+ /*
+ * Validate the region we are allocating only contains valid
+ * pages.
+ */
+ for (pfn = node_end_pfn[nid] - size;
+ pfn < node_end_pfn[nid]; pfn++)
+ if (!page_is_ram(pfn))
+ break;
+
+ if (pfn != node_end_pfn[nid])
+ size = 0;
+
printk("Reserving %ld pages of KVA for lmem_map of node %d\n",
size, nid);
node_remap_size[nid] = size;
- reserve_pages += size;
node_remap_offset[nid] = reserve_pages;
+ reserve_pages += size;
printk("Shrinking node %d from %ld pages to %ld pages\n",
nid, node_end_pfn[nid], node_end_pfn[nid] - size);
node_end_pfn[nid] -= size;
@@ -265,12 +310,18 @@ unsigned long __init setup_memory(void)
(ulong) pfn_to_kaddr(max_low_pfn));
for_each_online_node(nid) {
node_remap_start_vaddr[nid] = pfn_to_kaddr(
- (highstart_pfn + reserve_pages) - node_remap_offset[nid]);
+ highstart_pfn + node_remap_offset[nid]);
+ /* Init the node remap allocator */
+ node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +
+ (node_remap_size[nid] * PAGE_SIZE);
+ node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] +
+ ALIGN(sizeof(pg_data_t), PAGE_SIZE);
+
allocate_pgdat(nid);
printk ("node %d will remap to vaddr %08lx - %08lx\n", nid,
(ulong) node_remap_start_vaddr[nid],
- (ulong) pfn_to_kaddr(highstart_pfn + reserve_pages
- - node_remap_offset[nid] + node_remap_size[nid]));
+ (ulong) pfn_to_kaddr(highstart_pfn
+ + node_remap_offset[nid] + node_remap_size[nid]));
}
printk("High memory starts at vaddr %08lx\n",
(ulong) pfn_to_kaddr(highstart_pfn));
@@ -333,23 +384,9 @@ void __init zone_sizes_init(void)
}
zholes_size = get_zholes_size(nid);
- /*
- * We let the lmem_map for node 0 be allocated from the
- * normal bootmem allocator, but other nodes come from the
- * remapped KVA area - mbligh
- */
- if (!nid)
- free_area_init_node(nid, NODE_DATA(nid),
- zones_size, start, zholes_size);
- else {
- unsigned long lmem_map;
- lmem_map = (unsigned long)node_remap_start_vaddr[nid];
- lmem_map += sizeof(pg_data_t) + PAGE_SIZE - 1;
- lmem_map &= PAGE_MASK;
- NODE_DATA(nid)->node_mem_map = (struct page *)lmem_map;
- free_area_init_node(nid, NODE_DATA(nid), zones_size,
- start, zholes_size);
- }
+
+ free_area_init_node(nid, NODE_DATA(nid), zones_size, start,
+ zholes_size);
}
return;
}
@@ -358,24 +395,26 @@ void __init set_highmem_pages_init(int bad_ppro)
{
#ifdef CONFIG_HIGHMEM
struct zone *zone;
+ struct page *page;
for_each_zone(zone) {
- unsigned long node_pfn, node_high_size, zone_start_pfn;
- struct page * zone_mem_map;
-
+ unsigned long node_pfn, zone_start_pfn, zone_end_pfn;
+
if (!is_highmem(zone))
continue;
- printk("Initializing %s for node %d\n", zone->name,
- zone->zone_pgdat->node_id);
-
- node_high_size = zone->spanned_pages;
- zone_mem_map = zone->zone_mem_map;
zone_start_pfn = zone->zone_start_pfn;
+ zone_end_pfn = zone_start_pfn + zone->spanned_pages;
+
+ printk("Initializing %s for node %d (%08lx:%08lx)\n",
+ zone->name, zone->zone_pgdat->node_id,
+ zone_start_pfn, zone_end_pfn);
- for (node_pfn = 0; node_pfn < node_high_size; node_pfn++) {
- one_highpage_init((struct page *)(zone_mem_map + node_pfn),
- zone_start_pfn + node_pfn, bad_ppro);
+ for (node_pfn = zone_start_pfn; node_pfn < zone_end_pfn; node_pfn++) {
+ if (!pfn_valid(node_pfn))
+ continue;
+ page = pfn_to_page(node_pfn);
+ one_highpage_init(page, node_pfn, bad_ppro);
}
}
totalram_pages += totalhigh_pages;
diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c
index fc4c4cad4e9..4b7aaf99d7e 100644
--- a/arch/i386/mm/highmem.c
+++ b/arch/i386/mm/highmem.c
@@ -1,4 +1,5 @@
#include <linux/highmem.h>
+#include <linux/module.h>
void *kmap(struct page *page)
{
@@ -87,3 +88,8 @@ struct page *kmap_atomic_to_page(void *ptr)
return pte_page(*pte);
}
+EXPORT_SYMBOL(kmap);
+EXPORT_SYMBOL(kunmap);
+EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_to_page);
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 8766c771bb4..3672e2ef51a 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -191,7 +191,7 @@ static inline int page_kills_ppro(unsigned long pagenr)
extern int is_available_memory(efi_memory_desc_t *);
-static inline int page_is_ram(unsigned long pagenr)
+int page_is_ram(unsigned long pagenr)
{
int i;
unsigned long addr, end;
@@ -276,7 +276,9 @@ void __init one_highpage_init(struct page *page, int pfn, int bad_ppro)
SetPageReserved(page);
}
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
+extern void set_highmem_pages_init(int);
+#else
static void __init set_highmem_pages_init(int bad_ppro)
{
int pfn;
@@ -284,9 +286,7 @@ static void __init set_highmem_pages_init(int bad_ppro)
one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
totalram_pages += totalhigh_pages;
}
-#else
-extern void set_highmem_pages_init(int);
-#endif /* !CONFIG_DISCONTIGMEM */
+#endif /* CONFIG_FLATMEM */
#else
#define kmap_init() do { } while (0)
@@ -295,12 +295,13 @@ extern void set_highmem_pages_init(int);
#endif /* CONFIG_HIGHMEM */
unsigned long long __PAGE_KERNEL = _PAGE_KERNEL;
+EXPORT_SYMBOL(__PAGE_KERNEL);
unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;
-#ifndef CONFIG_DISCONTIGMEM
-#define remap_numa_kva() do {} while (0)
-#else
+#ifdef CONFIG_NUMA
extern void __init remap_numa_kva(void);
+#else
+#define remap_numa_kva() do {} while (0)
#endif
static void __init pagetable_init (void)
@@ -525,7 +526,7 @@ static void __init set_max_mapnr_init(void)
#else
num_physpages = max_low_pfn;
#endif
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
max_mapnr = num_physpages;
#endif
}
@@ -539,7 +540,7 @@ void __init mem_init(void)
int tmp;
int bad_ppro;
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
if (!mem_map)
BUG();
#endif
diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c
index ab542792b27..d393eefc705 100644
--- a/arch/i386/mm/ioremap.c
+++ b/arch/i386/mm/ioremap.c
@@ -11,6 +11,7 @@
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <asm/io.h>
#include <asm/fixmap.h>
#include <asm/cacheflush.h>
@@ -165,7 +166,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
}
return (void __iomem *) (offset + (char __iomem *)addr);
}
-
+EXPORT_SYMBOL(__ioremap);
/**
* ioremap_nocache - map bus memory into CPU space
@@ -222,6 +223,7 @@ void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
return p;
}
+EXPORT_SYMBOL(ioremap_nocache);
void iounmap(volatile void __iomem *addr)
{
@@ -255,6 +257,7 @@ out_unlock:
write_unlock(&vmlist_lock);
kfree(p);
}
+EXPORT_SYMBOL(iounmap);
void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
{
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index dd81479ff88..270c59f099a 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -30,13 +30,14 @@ void show_mem(void)
struct page *page;
pg_data_t *pgdat;
unsigned long i;
+ struct page_state ps;
printk("Mem-info:\n");
show_free_areas();
printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
for_each_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
- page = pgdat->node_mem_map + i;
+ page = pgdat_page_nr(pgdat, i);
total++;
if (PageHighMem(page))
highmem++;
@@ -53,6 +54,13 @@ void show_mem(void)
printk("%d reserved pages\n",reserved);
printk("%d pages shared\n",shared);
printk("%d pages swap cached\n",cached);
+
+ get_page_state(&ps);
+ printk("%lu pages dirty\n", ps.nr_dirty);
+ printk("%lu pages writeback\n", ps.nr_writeback);
+ printk("%lu pages mapped\n", ps.nr_mapped);
+ printk("%lu pages slab\n", ps.nr_slab);
+ printk("%lu pages pagetables\n", ps.nr_page_table_pages);
}
/*
diff --git a/arch/i386/oprofile/backtrace.c b/arch/i386/oprofile/backtrace.c
index 52d72e074f7..65dfd2edb67 100644
--- a/arch/i386/oprofile/backtrace.c
+++ b/arch/i386/oprofile/backtrace.c
@@ -91,7 +91,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
head = (struct frame_head *)regs->ebp;
#endif
- if (!user_mode(regs)) {
+ if (!user_mode_vm(regs)) {
while (depth-- && valid_kernel_stack(head, regs))
head = dump_backtrace(head);
return;
diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c
index da21b1d07c1..83458f81e66 100644
--- a/arch/i386/pci/irq.c
+++ b/arch/i386/pci/irq.c
@@ -227,6 +227,24 @@ static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i
}
/*
+ * The VIA pirq rules are nibble-based, like ALI,
+ * but without the ugly irq number munging.
+ * However, for 82C586, nibble map is different .
+ */
+static int pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static unsigned int pirqmap[4] = { 3, 2, 5, 1 };
+ return read_config_nybble(router, 0x55, pirqmap[pirq-1]);
+}
+
+static int pirq_via586_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ static unsigned int pirqmap[4] = { 3, 2, 5, 1 };
+ write_config_nybble(router, 0x55, pirqmap[pirq-1], irq);
+ return 1;
+}
+
+/*
* ITE 8330G pirq rules are nibble-based
* FIXME: pirqmap may be { 1, 0, 3, 2 },
* 2+3 are both mapped to irq 9 on my system
@@ -512,6 +530,10 @@ static __init int via_router_probe(struct irq_router *r, struct pci_dev *router,
switch(device)
{
case PCI_DEVICE_ID_VIA_82C586_0:
+ r->name = "VIA";
+ r->get = pirq_via586_get;
+ r->set = pirq_via586_set;
+ return 1;
case PCI_DEVICE_ID_VIA_82C596:
case PCI_DEVICE_ID_VIA_82C686:
case PCI_DEVICE_ID_VIA_8231:
diff --git a/arch/i386/pci/pcbios.c b/arch/i386/pci/pcbios.c
index 141421b673b..b9d65f0bc2d 100644
--- a/arch/i386/pci/pcbios.c
+++ b/arch/i386/pci/pcbios.c
@@ -4,6 +4,7 @@
#include <linux/pci.h>
#include <linux/init.h>
+#include <linux/module.h>
#include "pci.h"
#include "pci-functions.h"
@@ -456,7 +457,7 @@ struct irq_routing_table * __devinit pcibios_get_irq_routing_table(void)
free_page(page);
return rt;
}
-
+EXPORT_SYMBOL(pcibios_get_irq_routing_table);
int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
{
@@ -473,6 +474,7 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
"S" (&pci_indirect));
return !(ret & 0xff00);
}
+EXPORT_SYMBOL(pcibios_set_irq_routing);
static int __init pci_pcbios_init(void)
{
diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c
index cf337c673d9..6f521cf19a1 100644
--- a/arch/i386/power/cpu.c
+++ b/arch/i386/power/cpu.c
@@ -94,13 +94,13 @@ static void fix_processor_context(void)
* Now maybe reload the debug registers
*/
if (current->thread.debugreg[7]){
- loaddebug(&current->thread, 0);
- loaddebug(&current->thread, 1);
- loaddebug(&current->thread, 2);
- loaddebug(&current->thread, 3);
- /* no 4 and 5 */
- loaddebug(&current->thread, 6);
- loaddebug(&current->thread, 7);
+ set_debugreg(current->thread.debugreg[0], 0);
+ set_debugreg(current->thread.debugreg[1], 1);
+ set_debugreg(current->thread.debugreg[2], 2);
+ set_debugreg(current->thread.debugreg[3], 3);
+ /* no 4 and 5 */
+ set_debugreg(current->thread.debugreg[6], 6);
+ set_debugreg(current->thread.debugreg[7], 7);
}
}