Merge branch 'x86/core' into perfcounters/core
Conflicts:
arch/x86/kernel/apic/apic.c
arch/x86/kernel/irqinit_32.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8780ffd..2535427 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -285,6 +285,7 @@
---help---
This option is needed for the systems that have more than 8 CPUs
+if X86_32
config X86_EXTENDED_PLATFORM
bool "Support for extended (non-PC) x86 platforms"
default y
@@ -293,12 +294,36 @@
standard PC platforms. (which covers the vast majority of
systems out there.)
- If you enable this option then you'll be able to select a number
- of non-PC x86 platforms.
+ If you enable this option then you'll be able to select support
+ for the following (non-PC) 32 bit x86 platforms:
+ AMD Elan
+ NUMAQ (IBM/Sequent)
+ RDC R-321x SoC
+ SGI 320/540 (Visual Workstation)
+ Summit/EXA (IBM x440)
+ Unisys ES7000 IA32 series
If you have one of these systems, or if you want to build a
generic distribution kernel, say Y here - otherwise say N.
+endif
+if X86_64
+config X86_EXTENDED_PLATFORM
+ bool "Support for extended (non-PC) x86 platforms"
+ default y
+ ---help---
+ If you disable this option then the kernel will only support
+ standard PC platforms. (which covers the vast majority of
+ systems out there.)
+
+ If you enable this option then you'll be able to select support
+ for the following (non-PC) 64 bit x86 platforms:
+ ScaleMP vSMP
+ SGI Ultraviolet
+
+ If you have one of these systems, or if you want to build a
+ generic distribution kernel, say Y here - otherwise say N.
+endif
# This is an alphabetically sorted list of 64 bit extended platforms
# Please maintain the alphabetic order if and when there are additions
@@ -397,19 +422,6 @@
Support for Unisys ES7000 systems. Say 'Y' here if this kernel is
supposed to run on an IA32-based Unisys ES7000 system.
-config X86_VOYAGER
- bool "Voyager (NCR)"
- depends on SMP && !PCI && BROKEN
- depends on X86_32_NON_STANDARD
- ---help---
- Voyager is an MCA-based 32-way capable SMP architecture proprietary
- to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based.
-
- *** WARNING ***
-
- If you do not specifically know you have a Voyager based machine,
- say N here, otherwise the kernel you build will not be bootable.
-
config SCHED_OMIT_FRAME_POINTER
def_bool y
prompt "Single-depth WCHAN output"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ba4781b..fdb45df 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -175,28 +175,8 @@
Add a simple leak tracer to the IOMMU code. This is useful when you
are debugging a buggy device driver that leaks IOMMU mappings.
-config MMIOTRACE
- bool "Memory mapped IO tracing"
- depends on DEBUG_KERNEL && PCI
- select TRACING
- help
- Mmiotrace traces Memory Mapped I/O access and is meant for
- debugging and reverse engineering. It is called from the ioremap
- implementation and works via page faults. Tracing is disabled by
- default and can be enabled at run-time.
-
- See Documentation/tracers/mmiotrace.txt.
- If you are not helping to develop drivers, say N.
-
-config MMIOTRACE_TEST
- tristate "Test module for mmiotrace"
- depends on MMIOTRACE && m
- help
- This is a dumb module for testing mmiotrace. It is very dangerous
- as it will write garbage to IO memory starting at a given address.
- However, it should be safe to use on e.g. unused portion of VRAM.
-
- Say N, unless you absolutely know what you are doing.
+config HAVE_MMIOTRACE_SUPPORT
+ def_bool y
#
# IO delay types:
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index cd48c72..c70eff6 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -32,7 +32,6 @@
setup-y += header.o main.o mca.o memory.o pm.o pmjump.o
setup-y += printf.o string.o tty.o video.o video-mode.o version.o
setup-$(CONFIG_X86_APM_BOOT) += apm.o
-setup-$(CONFIG_X86_VOYAGER) += voyager.o
# The link order of the video-*.o modules can matter. In particular,
# video-vga.o *must* be listed first, followed by video-vesa.o.
diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c
index fba8e9c..7c19ce8 100644
--- a/arch/x86/boot/a20.c
+++ b/arch/x86/boot/a20.c
@@ -126,11 +126,6 @@
int enable_a20(void)
{
-#ifdef CONFIG_X86_VOYAGER
- /* On Voyager, a20_test() is unsafe? */
- enable_a20_kbc();
- return 0;
-#else
int loops = A20_ENABLE_LOOPS;
int kbc_err;
@@ -164,5 +159,4 @@
}
return -1;
-#endif
}
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index cc0ef13..7b2692e 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -302,9 +302,6 @@
/* video-vesa.c */
void vesa_store_edid(void);
-/* voyager.c */
-int query_voyager(void);
-
#endif /* __ASSEMBLY__ */
#endif /* BOOT_BOOT_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 29c5fbf..3a8a866 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -25,14 +25,12 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/boot.h>
#include <asm/asm-offsets.h>
.section ".text.head","ax",@progbits
- .globl startup_32
-
-startup_32:
+ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
@@ -113,6 +111,8 @@
*/
leal relocated(%ebx), %eax
jmp *%eax
+ENDPROC(startup_32)
+
.section ".text"
relocated:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 1d5dff4..ed4a829 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -26,8 +26,8 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/boot.h>
#include <asm/msr.h>
#include <asm/processor-flags.h>
@@ -35,9 +35,7 @@
.section ".text.head"
.code32
- .globl startup_32
-
-startup_32:
+ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
@@ -176,6 +174,7 @@
/* Jump from 32bit compatibility mode into 64bit mode. */
lret
+ENDPROC(startup_32)
no_longmode:
/* This isn't an x86-64 CPU so hang */
@@ -295,7 +294,6 @@
call decompress_kernel
popq %rsi
-
/*
* Jump to the decompressed kernel.
*/
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index ef50c84..11f272c 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -8,6 +8,8 @@
*
* ----------------------------------------------------------------------- */
+#include <linux/linkage.h>
+
/*
* Memory copy routines
*/
@@ -15,9 +17,7 @@
.code16gcc
.text
- .globl memcpy
- .type memcpy, @function
-memcpy:
+GLOBAL(memcpy)
pushw %si
pushw %di
movw %ax, %di
@@ -31,11 +31,9 @@
popw %di
popw %si
ret
- .size memcpy, .-memcpy
+ENDPROC(memcpy)
- .globl memset
- .type memset, @function
-memset:
+GLOBAL(memset)
pushw %di
movw %ax, %di
movzbl %dl, %eax
@@ -48,52 +46,42 @@
rep; stosb
popw %di
ret
- .size memset, .-memset
+ENDPROC(memset)
- .globl copy_from_fs
- .type copy_from_fs, @function
-copy_from_fs:
+GLOBAL(copy_from_fs)
pushw %ds
pushw %fs
popw %ds
call memcpy
popw %ds
ret
- .size copy_from_fs, .-copy_from_fs
+ENDPROC(copy_from_fs)
- .globl copy_to_fs
- .type copy_to_fs, @function
-copy_to_fs:
+GLOBAL(copy_to_fs)
pushw %es
pushw %fs
popw %es
call memcpy
popw %es
ret
- .size copy_to_fs, .-copy_to_fs
+ENDPROC(copy_to_fs)
#if 0 /* Not currently used, but can be enabled as needed */
-
- .globl copy_from_gs
- .type copy_from_gs, @function
-copy_from_gs:
+GLOBAL(copy_from_gs)
pushw %ds
pushw %gs
popw %ds
call memcpy
popw %ds
ret
- .size copy_from_gs, .-copy_from_gs
- .globl copy_to_gs
+ENDPROC(copy_from_gs)
- .type copy_to_gs, @function
-copy_to_gs:
+GLOBAL(copy_to_gs)
pushw %es
pushw %gs
popw %es
call memcpy
popw %es
ret
- .size copy_to_gs, .-copy_to_gs
-
+ENDPROC(copy_to_gs)
#endif
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b993062..7ccff48 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -19,7 +19,7 @@
#include <linux/utsrelease.h>
#include <asm/boot.h>
#include <asm/e820.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/setup.h>
#include "boot.h"
#include "offsets.h"
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 197421d..58f0415 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -149,11 +149,6 @@
/* Query MCA information */
query_mca();
- /* Voyager */
-#ifdef CONFIG_X86_VOYAGER
- query_voyager();
-#endif
-
/* Query Intel SpeedStep (IST) information */
query_ist();
diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S
index 141b6e2..019c17a 100644
--- a/arch/x86/boot/pmjump.S
+++ b/arch/x86/boot/pmjump.S
@@ -15,18 +15,15 @@
#include <asm/boot.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <linux/linkage.h>
.text
-
- .globl protected_mode_jump
- .type protected_mode_jump, @function
-
.code16
/*
* void protected_mode_jump(u32 entrypoint, u32 bootparams);
*/
-protected_mode_jump:
+GLOBAL(protected_mode_jump)
movl %edx, %esi # Pointer to boot_params table
xorl %ebx, %ebx
@@ -47,12 +44,10 @@
.byte 0x66, 0xea # ljmpl opcode
2: .long in_pm32 # offset
.word __BOOT_CS # segment
-
- .size protected_mode_jump, .-protected_mode_jump
+ENDPROC(protected_mode_jump)
.code32
- .type in_pm32, @function
-in_pm32:
+GLOBAL(in_pm32)
# Set up data segments for flat 32-bit mode
movl %ecx, %ds
movl %ecx, %es
@@ -78,5 +73,4 @@
lldt %cx
jmpl *%eax # Jump to the 32-bit entrypoint
-
- .size in_pm32, .-in_pm32
+ENDPROC(in_pm32)
diff --git a/arch/x86/boot/voyager.c b/arch/x86/boot/voyager.c
deleted file mode 100644
index 433909d..0000000
--- a/arch/x86/boot/voyager.c
+++ /dev/null
@@ -1,40 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- * Copyright 2007 rPath, Inc. - All Rights Reserved
- *
- * This file is part of the Linux kernel, and is made available under
- * the terms of the GNU General Public License version 2.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * Get the Voyager config information
- */
-
-#include "boot.h"
-
-int query_voyager(void)
-{
- u8 err;
- u16 es, di;
- /* Abuse the apm_bios_info area for this */
- u8 *data_ptr = (u8 *)&boot_params.apm_bios_info;
-
- data_ptr[0] = 0xff; /* Flag on config not found(?) */
-
- asm("pushw %%es ; "
- "int $0x15 ; "
- "setc %0 ; "
- "movw %%es, %1 ; "
- "popw %%es"
- : "=q" (err), "=r" (es), "=D" (di)
- : "a" (0xffc0));
-
- if (err)
- return -1; /* Not Voyager */
-
- set_fs(es);
- copy_from_fs(data_ptr, di, 7); /* Table is 7 bytes apparently */
- return 0;
-}
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 096dd53..235b81d 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.29-rc4
-# Thu Feb 12 12:57:57 2009
+# Tue Feb 24 15:50:58 2009
#
# CONFIG_64BIT is not set
CONFIG_X86_32=y
@@ -197,7 +197,6 @@
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y
# CONFIG_X86_ELAN is not set
-# CONFIG_X86_VOYAGER is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_VSMP is not set
# CONFIG_X86_RDC321X is not set
@@ -267,7 +266,9 @@
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
-# CONFIG_X86_MCE is not set
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_NONFATAL=y
+CONFIG_X86_MCE_P4THERMAL=y
CONFIG_VM86=y
# CONFIG_TOSHIBA is not set
# CONFIG_I8K is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 2efb5d5..9fe5d21 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.29-rc4
-# Thu Feb 12 12:57:29 2009
+# Tue Feb 24 15:44:16 2009
#
CONFIG_64BIT=y
# CONFIG_X86_32 is not set
@@ -199,7 +199,6 @@
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y
# CONFIG_X86_ELAN is not set
-# CONFIG_X86_VOYAGER is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_VSMP is not set
CONFIG_SCHED_OMIT_FRAME_POINTER=y
@@ -267,7 +266,9 @@
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
-# CONFIG_X86_MCE is not set
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_INTEL=y
+CONFIG_X86_MCE_AMD=y
# CONFIG_I8K is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index dd77ac0..588a7aa 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -33,8 +33,6 @@
#include <asm/sigframe.h>
#include <asm/sys_ia32.h>
-#define DEBUG_SIG 0
-
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
@@ -190,42 +188,47 @@
/*
* Do a signal return; undo the signal stack.
*/
+#define loadsegment_gs(v) load_gs_index(v)
+#define loadsegment_fs(v) loadsegment(fs, v)
+#define loadsegment_ds(v) loadsegment(ds, v)
+#define loadsegment_es(v) loadsegment(es, v)
+
+#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; })
+#define set_user_seg(seg, v) loadsegment_##seg(v)
+
#define COPY(x) { \
get_user_ex(regs->x, &sc->x); \
}
-#define COPY_SEG_CPL3(seg) { \
- unsigned short tmp; \
- get_user_ex(tmp, &sc->seg); \
- regs->seg = tmp | 3; \
-}
+#define GET_SEG(seg) ({ \
+ unsigned short tmp; \
+ get_user_ex(tmp, &sc->seg); \
+ tmp; \
+})
+
+#define COPY_SEG_CPL3(seg) do { \
+ regs->seg = GET_SEG(seg) | 3; \
+} while (0)
#define RELOAD_SEG(seg) { \
- unsigned int cur, pre; \
- get_user_ex(pre, &sc->seg); \
- savesegment(seg, cur); \
+ unsigned int pre = GET_SEG(seg); \
+ unsigned int cur = get_user_seg(seg); \
pre |= 3; \
if (pre != cur) \
- loadsegment(seg, pre); \
+ set_user_seg(seg, pre); \
}
static int ia32_restore_sigcontext(struct pt_regs *regs,
struct sigcontext_ia32 __user *sc,
unsigned int *pax)
{
- unsigned int tmpflags, gs, oldgs, err = 0;
+ unsigned int tmpflags, err = 0;
void __user *buf;
u32 tmp;
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG restore_sigcontext: "
- "sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n",
- sc, sc->err, sc->ip, sc->cs, sc->flags);
-#endif
-
get_user_try {
/*
* Reload fs and gs if they have changed in the signal
@@ -233,12 +236,7 @@
* the handler, but does not clobber them at least in the
* normal case.
*/
- get_user_ex(gs, &sc->gs);
- gs |= 3;
- savesegment(gs, oldgs);
- if (gs != oldgs)
- load_gs_index(gs);
-
+ RELOAD_SEG(gs);
RELOAD_SEG(fs);
RELOAD_SEG(ds);
RELOAD_SEG(es);
@@ -337,17 +335,13 @@
void __user *fpstate,
struct pt_regs *regs, unsigned int mask)
{
- int tmp, err = 0;
+ int err = 0;
put_user_try {
- savesegment(gs, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->gs);
- savesegment(fs, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->fs);
- savesegment(ds, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->ds);
- savesegment(es, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->es);
+ put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs);
+ put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs);
+ put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds);
+ put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es);
put_user_ex(regs->di, &sc->di);
put_user_ex(regs->si, &sc->si);
@@ -488,11 +482,6 @@
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
return 0;
}
@@ -574,10 +563,5 @@
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
return 0;
}
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index dce1bf6..a6208dc 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -146,7 +146,7 @@
return val;
}
-extern int x2apic;
+extern int x2apic, x2apic_phys;
extern void check_x2apic(void);
extern void enable_x2apic(void);
extern void enable_IR_x2apic(void);
diff --git a/arch/x86/include/asm/arch_hooks.h b/arch/x86/include/asm/arch_hooks.h
deleted file mode 100644
index cbd4957..0000000
--- a/arch/x86/include/asm/arch_hooks.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef _ASM_X86_ARCH_HOOKS_H
-#define _ASM_X86_ARCH_HOOKS_H
-
-#include <linux/interrupt.h>
-
-/*
- * linux/include/asm/arch_hooks.h
- *
- * define the architecture specific hooks
- */
-
-/* these aren't arch hooks, they are generic routines
- * that can be used by the hooks */
-extern void init_ISA_irqs(void);
-extern irqreturn_t timer_interrupt(int irq, void *dev_id);
-
-/* these are the defined hooks */
-extern void intr_init_hook(void);
-extern void pre_intr_init_hook(void);
-extern void pre_setup_arch_hook(void);
-extern void trap_init_hook(void);
-extern void pre_time_init_hook(void);
-extern void time_init_hook(void);
-extern void mca_nmi_hook(void);
-
-#endif /* _ASM_X86_ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 58d7091..1a99e6c 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -60,4 +60,8 @@
extern void mask_8259A(void);
extern void unmask_8259A(void);
+#ifdef CONFIG_X86_32
+extern void init_ISA_irqs(void);
+#endif
+
#endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 4f8e820..683d0b4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -124,10 +124,15 @@
/*
* ISA I/O bus memory addresses are 1:1 with the physical address.
+ * However, we truncate the address to unsigned int to avoid undesirable
+ * promitions in legacy drivers.
*/
-#define isa_virt_to_bus (unsigned long)virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
+static inline unsigned int isa_virt_to_bus(volatile void *address)
+{
+ return (unsigned int)virt_to_phys(address);
+}
+#define isa_page_to_bus(page) ((unsigned int)page_to_phys(page))
+#define isa_bus_to_virt phys_to_virt
/*
* However PCI ones are not necessarily 1:1 and therefore these interfaces
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index c1f0628..bd46495 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -23,6 +23,12 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
+int
+reserve_io_memtype_wc(u64 base, unsigned long size, pgprot_t *prot);
+
+void
+free_io_memtype(u64 base, unsigned long size);
+
void *
iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index b07278c..8a285f3 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -128,7 +128,7 @@
#ifndef __ASSEMBLY__
static inline int invalid_vm86_irq(int irq)
{
- return irq < 3 || irq > 15;
+ return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
}
#endif
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index d2e3bf3..886c940 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -9,6 +9,13 @@
#include <linux/types.h>
#include <linux/ioctl.h>
+/* Select x86 specific features in <linux/kvm.h> */
+#define __KVM_HAVE_PIT
+#define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_DEVICE_ASSIGNMENT
+#define __KVM_HAVE_MSI
+#define __KVM_HAVE_USER_NMI
+
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 5d98d0b..9320e2a 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -52,70 +52,14 @@
#endif
+#define GLOBAL(name) \
+ .globl name; \
+ name:
+
#ifdef CONFIG_X86_ALIGNMENT_16
#define __ALIGN .align 16,0x90
#define __ALIGN_STR ".align 16,0x90"
#endif
-/*
- * to check ENTRY_X86/END_X86 and
- * KPROBE_ENTRY_X86/KPROBE_END_X86
- * unbalanced-missed-mixed appearance
- */
-#define __set_entry_x86 .set ENTRY_X86_IN, 0
-#define __unset_entry_x86 .set ENTRY_X86_IN, 1
-#define __set_kprobe_x86 .set KPROBE_X86_IN, 0
-#define __unset_kprobe_x86 .set KPROBE_X86_IN, 1
-
-#define __macro_err_x86 .error "ENTRY_X86/KPROBE_X86 unbalanced,missed,mixed"
-
-#define __check_entry_x86 \
- .ifdef ENTRY_X86_IN; \
- .ifeq ENTRY_X86_IN; \
- __macro_err_x86; \
- .abort; \
- .endif; \
- .endif
-
-#define __check_kprobe_x86 \
- .ifdef KPROBE_X86_IN; \
- .ifeq KPROBE_X86_IN; \
- __macro_err_x86; \
- .abort; \
- .endif; \
- .endif
-
-#define __check_entry_kprobe_x86 \
- __check_entry_x86; \
- __check_kprobe_x86
-
-#define ENTRY_KPROBE_FINAL_X86 __check_entry_kprobe_x86
-
-#define ENTRY_X86(name) \
- __check_entry_kprobe_x86; \
- __set_entry_x86; \
- .globl name; \
- __ALIGN; \
- name:
-
-#define END_X86(name) \
- __unset_entry_x86; \
- __check_entry_kprobe_x86; \
- .size name, .-name
-
-#define KPROBE_ENTRY_X86(name) \
- __check_entry_kprobe_x86; \
- __set_kprobe_x86; \
- .pushsection .kprobes.text, "ax"; \
- .globl name; \
- __ALIGN; \
- name:
-
-#define KPROBE_END_X86(name) \
- __unset_kprobe_x86; \
- __check_entry_kprobe_x86; \
- .size name, .-name; \
- .popsection
-
#endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/mach-voyager/do_timer.h b/arch/x86/include/asm/mach-voyager/do_timer.h
deleted file mode 100644
index 9e5a459..0000000
--- a/arch/x86/include/asm/mach-voyager/do_timer.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* defines for inline arch setup functions */
-#include <linux/clockchips.h>
-
-#include <asm/voyager.h>
-#include <asm/i8253.h>
-
-/**
- * do_timer_interrupt_hook - hook into timer tick
- *
- * Call the pit clock event handler. see asm/i8253.h
- **/
-static inline void do_timer_interrupt_hook(void)
-{
- global_clock_event->event_handler(global_clock_event);
- voyager_timer_interrupt();
-}
-
diff --git a/arch/x86/include/asm/mach-voyager/entry_arch.h b/arch/x86/include/asm/mach-voyager/entry_arch.h
deleted file mode 100644
index ae52624..0000000
--- a/arch/x86/include/asm/mach-voyager/entry_arch.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/entry_arch.h
- *
- * This file builds the VIC and QIC CPI gates
- */
-
-/* initialise the voyager interrupt gates
- *
- * This uses the macros in irq.h to set up assembly jump gates. The
- * calls are then redirected to the same routine with smp_ prefixed */
-BUILD_INTERRUPT(vic_sys_interrupt, VIC_SYS_INT)
-BUILD_INTERRUPT(vic_cmn_interrupt, VIC_CMN_INT)
-BUILD_INTERRUPT(vic_cpi_interrupt, VIC_CPI_LEVEL0);
-
-/* do all the QIC interrupts */
-BUILD_INTERRUPT(qic_timer_interrupt, QIC_TIMER_CPI);
-BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
-BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
-BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
-BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
-BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/arch/x86/include/asm/mach-voyager/setup_arch.h b/arch/x86/include/asm/mach-voyager/setup_arch.h
deleted file mode 100644
index 71729ca..0000000
--- a/arch/x86/include/asm/mach-voyager/setup_arch.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <asm/voyager.h>
-#include <asm/setup.h>
-#define VOYAGER_BIOS_INFO ((struct voyager_bios_info *) \
- (&boot_params.apm_bios_info))
-
-/* Hook to call BIOS initialisation function */
-
-/* for voyager, pass the voyager BIOS/SUS info area to the detection
- * routines */
-
-#define ARCH_SETUP voyager_detect(VOYAGER_BIOS_INFO);
-
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 07f1af4..105fb90 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -32,8 +32,6 @@
get_memcfg_numa_flat();
}
-extern int early_pfn_to_nid(unsigned long pfn);
-
extern void resume_map_numa_kva(pgd_t *pgd);
#else /* !CONFIG_NUMA */
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index a5b3817..a29f48c 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -40,8 +40,6 @@
#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \
NODE_DATA(nid)->node_spanned_pages)
-extern int early_pfn_to_nid(unsigned long pfn);
-
#ifdef CONFIG_NUMA_EMU
#define FAKE_NODE_MIN_SIZE (64 * 1024 * 1024)
#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index b5486aa..f1e4a79 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -33,12 +33,10 @@
/* 44=32+12, the limit we can fit into an unsigned long pfn */
#define __PHYSICAL_MASK_SHIFT 44
#define __VIRTUAL_MASK_SHIFT 32
-#define PAGETABLE_LEVELS 3
#else /* !CONFIG_X86_PAE */
#define __PHYSICAL_MASK_SHIFT 32
#define __VIRTUAL_MASK_SHIFT 32
-#define PAGETABLE_LEVELS 2
#endif /* CONFIG_X86_PAE */
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index bc73af3..d38c91b 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,8 +1,6 @@
#ifndef _ASM_X86_PAGE_64_DEFS_H
#define _ASM_X86_PAGE_64_DEFS_H
-#define PAGETABLE_LEVELS 4
-
#define THREAD_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
#define CURRENT_MASK (~(THREAD_SIZE - 1))
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 2c52ff7..2d625da 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -16,12 +16,6 @@
(ie, 32-bit PAE). */
#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
-#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK)
-
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
-#define PTE_FLAGS_MASK (~PTE_PFN_MASK)
-
#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 9709fdf..b0e7005 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -15,4 +15,7 @@
unsigned long req_type, unsigned long *ret_type);
extern int free_memtype(u64 start, u64 end);
+extern int kernel_map_sync_memtype(u64 base, unsigned long size,
+ unsigned long flag);
+
#endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 09ae67e..daacc23 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -17,6 +17,7 @@
#endif /* !__ASSEMBLY__ */
#define SHARED_KERNEL_PMD 0
+#define PAGETABLE_LEVELS 2
/*
* traditional i386 two-level paging structure:
@@ -25,6 +26,7 @@
#define PGDIR_SHIFT 22
#define PTRS_PER_PGD 1024
+
/*
* the i386 is two-level, so we don't really have any
* PMD directory physically.
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index bcc8962..1bd5876 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -24,6 +24,8 @@
#define SHARED_KERNEL_PMD 1
#endif
+#define PAGETABLE_LEVELS 3
+
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2f59135..fbf42b8 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -18,6 +18,7 @@
#endif /* !__ASSEMBLY__ */
#define SHARED_KERNEL_PMD 0
+#define PAGETABLE_LEVELS 4
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9dafe87..4d258ad 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -173,6 +173,12 @@
#include <linux/types.h>
+/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK)
+
+/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+#define PTE_FLAGS_MASK (~PTE_PFN_MASK)
+
typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
typedef struct { pgdval_t pgd; } pgd_t;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dabab1a..c7a98f7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -403,7 +403,6 @@
#endif
#endif /* X86_64 */
-extern void print_cpu_info(struct cpuinfo_x86 *);
extern unsigned int xstate_size;
extern void free_thread_xstate(struct task_struct *);
extern struct kmem_cache *task_xstate_cachep;
@@ -862,6 +861,7 @@
* User space process size: 3GB (default).
*/
#define TASK_SIZE PAGE_OFFSET
+#define TASK_SIZE_MAX TASK_SIZE
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
@@ -921,7 +921,7 @@
/*
* User space process size. 47bits minus one guard page.
*/
-#define TASK_SIZE64 ((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
@@ -930,12 +930,12 @@
0xc0000000 : 0xFFFFe000)
#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \
- IA32_PAGE_OFFSET : TASK_SIZE64)
+ IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \
- IA32_PAGE_OFFSET : TASK_SIZE64)
+ IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define STACK_TOP TASK_SIZE
-#define STACK_TOP_MAX TASK_SIZE64
+#define STACK_TOP_MAX TASK_SIZE_MAX
#define INIT_THREAD { \
.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 8029369..66801cb 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -13,6 +13,7 @@
struct mpc_cpu;
struct mpc_bus;
struct mpc_oemtable;
+
struct x86_quirks {
int (*arch_pre_time_init)(void);
int (*arch_time_init)(void);
@@ -33,6 +34,14 @@
int (*update_apic)(void);
};
+extern void x86_quirk_pre_intr_init(void);
+extern void x86_quirk_intr_init(void);
+
+extern void x86_quirk_trap_init(void);
+
+extern void x86_quirk_pre_time_init(void);
+extern void x86_quirk_time_init(void);
+
#endif /* __ASSEMBLY__ */
#ifdef __i386__
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 258ef73..7043408 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -82,7 +82,7 @@
/* kernel/signal_64.c */
asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
struct pt_regs *);
-asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+long sys_rt_sigreturn(struct pt_regs *);
/* kernel/sys_x86_64.c */
asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 2bb6a83..a81195e 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -3,6 +3,7 @@
#include <linux/init.h>
#include <linux/pm.h>
#include <linux/percpu.h>
+#include <linux/interrupt.h>
#define TICK_SIZE (tick_nsec / 1000)
@@ -12,6 +13,7 @@
#ifdef CONFIG_X86_32
extern int timer_ack;
extern int recalibrate_cpu_khz(void);
+extern irqreturn_t timer_interrupt(int irq, void *dev_id);
#endif /* CONFIG_X86_32 */
extern int no_timer_check;
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 5e06259..a0ba613 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -157,7 +157,7 @@
}
static __always_inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n)
+ const void __user *from, unsigned long n, unsigned long total)
{
might_fault();
if (__builtin_constant_p(n)) {
@@ -180,7 +180,7 @@
static __always_inline unsigned long
__copy_from_user_inatomic_nocache(void *to, const void __user *from,
- unsigned long n)
+ unsigned long n, unsigned long total)
{
return __copy_from_user_ll_nocache_nozero(to, from, n);
}
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 84210c4..dcaa0404 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -189,17 +189,28 @@
unsigned size, int zerorest);
static inline int __copy_from_user_nocache(void *dst, const void __user *src,
- unsigned size)
+ unsigned size, unsigned long total)
{
might_sleep();
- return __copy_user_nocache(dst, src, size, 1);
+ /*
+ * In practice this limit means that large file write()s
+ * which get chunked to 4K copies get handled via
+ * non-temporal stores here. Smaller writes get handled
+ * via regular __copy_from_user():
+ */
+ if (likely(total >= PAGE_SIZE))
+ return __copy_user_nocache(dst, src, size, 1);
+ else
+ return __copy_from_user(dst, src, size);
}
static inline int __copy_from_user_inatomic_nocache(void *dst,
- const void __user *src,
- unsigned size)
+ const void __user *src, unsigned size, unsigned total)
{
- return __copy_user_nocache(dst, src, size, 0);
+ if (likely(total >= PAGE_SIZE))
+ return __copy_user_nocache(dst, src, size, 0);
+ else
+ return __copy_from_user_inatomic(dst, src, size);
}
unsigned long
diff --git a/arch/x86/include/asm/vic.h b/arch/x86/include/asm/vic.h
deleted file mode 100644
index 53100f3..0000000
--- a/arch/x86/include/asm/vic.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager Interrupt Controller */
-
-/* The eight CPI vectors. To activate a CPI, you write a bit mask
- * corresponding to the processor set to be interrupted into the
- * relevant register. That set of CPUs will then be interrupted with
- * the CPI */
-static const int VIC_CPI_Registers[] =
- {0xFC00, 0xFC01, 0xFC08, 0xFC09,
- 0xFC10, 0xFC11, 0xFC18, 0xFC19 };
-
-#define VIC_PROC_WHO_AM_I 0xfc29
-# define QUAD_IDENTIFIER 0xC0
-# define EIGHT_SLOT_IDENTIFIER 0xE0
-#define QIC_EXTENDED_PROCESSOR_SELECT 0xFC72
-#define VIC_CPI_BASE_REGISTER 0xFC41
-#define VIC_PROCESSOR_ID 0xFC21
-# define VIC_CPU_MASQUERADE_ENABLE 0x8
-
-#define VIC_CLAIM_REGISTER_0 0xFC38
-#define VIC_CLAIM_REGISTER_1 0xFC39
-#define VIC_REDIRECT_REGISTER_0 0xFC60
-#define VIC_REDIRECT_REGISTER_1 0xFC61
-#define VIC_PRIORITY_REGISTER 0xFC20
-
-#define VIC_PRIMARY_MC_BASE 0xFC48
-#define VIC_SECONDARY_MC_BASE 0xFC49
-
-#define QIC_PROCESSOR_ID 0xFC71
-# define QIC_CPUID_ENABLE 0x08
-
-#define QIC_VIC_CPI_BASE_REGISTER 0xFC79
-#define QIC_CPI_BASE_REGISTER 0xFC7A
-
-#define QIC_MASK_REGISTER0 0xFC80
-/* NOTE: these are masked high, enabled low */
-# define QIC_PERF_TIMER 0x01
-# define QIC_LPE 0x02
-# define QIC_SYS_INT 0x04
-# define QIC_CMN_INT 0x08
-/* at the moment, just enable CMN_INT, disable SYS_INT */
-# define QIC_DEFAULT_MASK0 (~(QIC_CMN_INT /* | VIC_SYS_INT */))
-#define QIC_MASK_REGISTER1 0xFC81
-# define QIC_BOOT_CPI_MASK 0xFE
-/* Enable CPI's 1-6 inclusive */
-# define QIC_CPI_ENABLE 0x81
-
-#define QIC_INTERRUPT_CLEAR0 0xFC8A
-#define QIC_INTERRUPT_CLEAR1 0xFC8B
-
-/* this is where we place the CPI vectors */
-#define VIC_DEFAULT_CPI_BASE 0xC0
-/* this is where we place the QIC CPI vectors */
-#define QIC_DEFAULT_CPI_BASE 0xD0
-
-#define VIC_BOOT_INTERRUPT_MASK 0xfe
-
-extern void smp_vic_timer_interrupt(void);
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
deleted file mode 100644
index c1635d4..0000000
--- a/arch/x86/include/asm/voyager.h
+++ /dev/null
@@ -1,571 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager system */
-
-#undef VOYAGER_DEBUG
-#undef VOYAGER_CAT_DEBUG
-
-#ifdef VOYAGER_DEBUG
-#define VDEBUG(x) printk x
-#else
-#define VDEBUG(x)
-#endif
-
-/* There are three levels of voyager machine: 3,4 and 5. The rule is
- * if it's less than 3435 it's a Level 3 except for a 3360 which is
- * a level 4. A 3435 or above is a Level 5 */
-#define VOYAGER_LEVEL5_AND_ABOVE 0x3435
-#define VOYAGER_LEVEL4 0x3360
-
-/* The L4 DINO ASIC */
-#define VOYAGER_DINO 0x43
-
-/* voyager ports in standard I/O space */
-#define VOYAGER_MC_SETUP 0x96
-
-
-#define VOYAGER_CAT_CONFIG_PORT 0x97
-# define VOYAGER_CAT_DESELECT 0xff
-#define VOYAGER_SSPB_RELOCATION_PORT 0x98
-
-/* Valid CAT controller commands */
-/* start instruction register cycle */
-#define VOYAGER_CAT_IRCYC 0x01
-/* start data register cycle */
-#define VOYAGER_CAT_DRCYC 0x02
-/* move to execute state */
-#define VOYAGER_CAT_RUN 0x0F
-/* end operation */
-#define VOYAGER_CAT_END 0x80
-/* hold in idle state */
-#define VOYAGER_CAT_HOLD 0x90
-/* single step an "intest" vector */
-#define VOYAGER_CAT_STEP 0xE0
-/* return cat controller to CLEMSON mode */
-#define VOYAGER_CAT_CLEMSON 0xFF
-
-/* the default cat command header */
-#define VOYAGER_CAT_HEADER 0x7F
-
-/* the range of possible CAT module ids in the system */
-#define VOYAGER_MIN_MODULE 0x10
-#define VOYAGER_MAX_MODULE 0x1f
-
-/* The voyager registers per asic */
-#define VOYAGER_ASIC_ID_REG 0x00
-#define VOYAGER_ASIC_TYPE_REG 0x01
-/* the sub address registers can be made auto incrementing on reads */
-#define VOYAGER_AUTO_INC_REG 0x02
-# define VOYAGER_AUTO_INC 0x04
-# define VOYAGER_NO_AUTO_INC 0xfb
-#define VOYAGER_SUBADDRDATA 0x03
-#define VOYAGER_SCANPATH 0x05
-# define VOYAGER_CONNECT_ASIC 0x01
-# define VOYAGER_DISCONNECT_ASIC 0xfe
-#define VOYAGER_SUBADDRLO 0x06
-#define VOYAGER_SUBADDRHI 0x07
-#define VOYAGER_SUBMODSELECT 0x08
-#define VOYAGER_SUBMODPRESENT 0x09
-
-#define VOYAGER_SUBADDR_LO 0xff
-#define VOYAGER_SUBADDR_HI 0xffff
-
-/* the maximum size of a scan path -- used to form instructions */
-#define VOYAGER_MAX_SCAN_PATH 0x100
-/* the biggest possible register size (in bytes) */
-#define VOYAGER_MAX_REG_SIZE 4
-
-/* Total number of possible modules (including submodules) */
-#define VOYAGER_MAX_MODULES 16
-/* Largest number of asics per module */
-#define VOYAGER_MAX_ASICS_PER_MODULE 7
-
-/* the CAT asic of each module is always the first one */
-#define VOYAGER_CAT_ID 0
-#define VOYAGER_PSI 0x1a
-
-/* voyager instruction operations and registers */
-#define VOYAGER_READ_CONFIG 0x1
-#define VOYAGER_WRITE_CONFIG 0x2
-#define VOYAGER_BYPASS 0xff
-
-typedef struct voyager_asic {
- __u8 asic_addr; /* ASIC address; Level 4 */
- __u8 asic_type; /* ASIC type */
- __u8 asic_id; /* ASIC id */
- __u8 jtag_id[4]; /* JTAG id */
- __u8 asic_location; /* Location within scan path; start w/ 0 */
- __u8 bit_location; /* Location within bit stream; start w/ 0 */
- __u8 ireg_length; /* Instruction register length */
- __u16 subaddr; /* Amount of sub address space */
- struct voyager_asic *next; /* Next asic in linked list */
-} voyager_asic_t;
-
-typedef struct voyager_module {
- __u8 module_addr; /* Module address */
- __u8 scan_path_connected; /* Scan path connected */
- __u16 ee_size; /* Size of the EEPROM */
- __u16 num_asics; /* Number of Asics */
- __u16 inst_bits; /* Instruction bits in the scan path */
- __u16 largest_reg; /* Largest register in the scan path */
- __u16 smallest_reg; /* Smallest register in the scan path */
- voyager_asic_t *asic; /* First ASIC in scan path (CAT_I) */
- struct voyager_module *submodule; /* Submodule pointer */
- struct voyager_module *next; /* Next module in linked list */
-} voyager_module_t;
-
-typedef struct voyager_eeprom_hdr {
- __u8 module_id[4];
- __u8 version_id;
- __u8 config_id;
- __u16 boundry_id; /* boundary scan id */
- __u16 ee_size; /* size of EEPROM */
- __u8 assembly[11]; /* assembly # */
- __u8 assembly_rev; /* assembly rev */
- __u8 tracer[4]; /* tracer number */
- __u16 assembly_cksum; /* asm checksum */
- __u16 power_consump; /* pwr requirements */
- __u16 num_asics; /* number of asics */
- __u16 bist_time; /* min. bist time */
- __u16 err_log_offset; /* error log offset */
- __u16 scan_path_offset;/* scan path offset */
- __u16 cct_offset;
- __u16 log_length; /* length of err log */
- __u16 xsum_end; /* offset to end of
- checksum */
- __u8 reserved[4];
- __u8 sflag; /* starting sentinal */
- __u8 part_number[13]; /* prom part number */
- __u8 version[10]; /* version number */
- __u8 signature[8];
- __u16 eeprom_chksum;
- __u32 data_stamp_offset;
- __u8 eflag ; /* ending sentinal */
-} __attribute__((packed)) voyager_eprom_hdr_t;
-
-
-
-#define VOYAGER_EPROM_SIZE_OFFSET \
- ((__u16)(&(((voyager_eprom_hdr_t *)0)->ee_size)))
-#define VOYAGER_XSUM_END_OFFSET 0x2a
-
-/* the following three definitions are for internal table layouts
- * in the module EPROMs. We really only care about the IDs and
- * offsets */
-typedef struct voyager_sp_table {
- __u8 asic_id;
- __u8 bypass_flag;
- __u16 asic_data_offset;
- __u16 config_data_offset;
-} __attribute__((packed)) voyager_sp_table_t;
-
-typedef struct voyager_jtag_table {
- __u8 icode[4];
- __u8 runbist[4];
- __u8 intest[4];
- __u8 samp_preld[4];
- __u8 ireg_len;
-} __attribute__((packed)) voyager_jtt_t;
-
-typedef struct voyager_asic_data_table {
- __u8 jtag_id[4];
- __u16 length_bsr;
- __u16 length_bist_reg;
- __u32 bist_clk;
- __u16 subaddr_bits;
- __u16 seed_bits;
- __u16 sig_bits;
- __u16 jtag_offset;
-} __attribute__((packed)) voyager_at_t;
-
-/* Voyager Interrupt Controller (VIC) registers */
-
-/* Base to add to Cross Processor Interrupts (CPIs) when triggering
- * the CPU IRQ line */
-/* register defines for the WCBICs (one per processor) */
-#define VOYAGER_WCBIC0 0x41 /* bus A node P1 processor 0 */
-#define VOYAGER_WCBIC1 0x49 /* bus A node P1 processor 1 */
-#define VOYAGER_WCBIC2 0x51 /* bus A node P2 processor 0 */
-#define VOYAGER_WCBIC3 0x59 /* bus A node P2 processor 1 */
-#define VOYAGER_WCBIC4 0x61 /* bus B node P1 processor 0 */
-#define VOYAGER_WCBIC5 0x69 /* bus B node P1 processor 1 */
-#define VOYAGER_WCBIC6 0x71 /* bus B node P2 processor 0 */
-#define VOYAGER_WCBIC7 0x79 /* bus B node P2 processor 1 */
-
-
-/* top of memory registers */
-#define VOYAGER_WCBIC_TOM_L 0x4
-#define VOYAGER_WCBIC_TOM_H 0x5
-
-/* register defines for Voyager Memory Contol (VMC)
- * these are present on L4 machines only */
-#define VOYAGER_VMC1 0x81
-#define VOYAGER_VMC2 0x91
-#define VOYAGER_VMC3 0xa1
-#define VOYAGER_VMC4 0xb1
-
-/* VMC Ports */
-#define VOYAGER_VMC_MEMORY_SETUP 0x9
-# define VMC_Interleaving 0x01
-# define VMC_4Way 0x02
-# define VMC_EvenCacheLines 0x04
-# define VMC_HighLine 0x08
-# define VMC_Start0_Enable 0x20
-# define VMC_Start1_Enable 0x40
-# define VMC_Vremap 0x80
-#define VOYAGER_VMC_BANK_DENSITY 0xa
-# define VMC_BANK_EMPTY 0
-# define VMC_BANK_4MB 1
-# define VMC_BANK_16MB 2
-# define VMC_BANK_64MB 3
-# define VMC_BANK0_MASK 0x03
-# define VMC_BANK1_MASK 0x0C
-# define VMC_BANK2_MASK 0x30
-# define VMC_BANK3_MASK 0xC0
-
-/* Magellan Memory Controller (MMC) defines - present on L5 */
-#define VOYAGER_MMC_ASIC_ID 1
-/* the two memory modules corresponding to memory cards in the system */
-#define VOYAGER_MMC_MEMORY0_MODULE 0x14
-#define VOYAGER_MMC_MEMORY1_MODULE 0x15
-/* the Magellan Memory Address (MMA) defines */
-#define VOYAGER_MMA_ASIC_ID 2
-
-/* Submodule number for the Quad Baseboard */
-#define VOYAGER_QUAD_BASEBOARD 1
-
-/* ASIC defines for the Quad Baseboard */
-#define VOYAGER_QUAD_QDATA0 1
-#define VOYAGER_QUAD_QDATA1 2
-#define VOYAGER_QUAD_QABC 3
-
-/* Useful areas in extended CMOS */
-#define VOYAGER_PROCESSOR_PRESENT_MASK 0x88a
-#define VOYAGER_MEMORY_CLICKMAP 0xa23
-#define VOYAGER_DUMP_LOCATION 0xb1a
-
-/* SUS In Control bit - used to tell SUS that we don't need to be
- * babysat anymore */
-#define VOYAGER_SUS_IN_CONTROL_PORT 0x3ff
-# define VOYAGER_IN_CONTROL_FLAG 0x80
-
-/* Voyager PSI defines */
-#define VOYAGER_PSI_STATUS_REG 0x08
-# define PSI_DC_FAIL 0x01
-# define PSI_MON 0x02
-# define PSI_FAULT 0x04
-# define PSI_ALARM 0x08
-# define PSI_CURRENT 0x10
-# define PSI_DVM 0x20
-# define PSI_PSCFAULT 0x40
-# define PSI_STAT_CHG 0x80
-
-#define VOYAGER_PSI_SUPPLY_REG 0x8000
- /* read */
-# define PSI_FAIL_DC 0x01
-# define PSI_FAIL_AC 0x02
-# define PSI_MON_INT 0x04
-# define PSI_SWITCH_OFF 0x08
-# define PSI_HX_OFF 0x10
-# define PSI_SECURITY 0x20
-# define PSI_CMOS_BATT_LOW 0x40
-# define PSI_CMOS_BATT_FAIL 0x80
- /* write */
-# define PSI_CLR_SWITCH_OFF 0x13
-# define PSI_CLR_HX_OFF 0x14
-# define PSI_CLR_CMOS_BATT_FAIL 0x17
-
-#define VOYAGER_PSI_MASK 0x8001
-# define PSI_MASK_MASK 0x10
-
-#define VOYAGER_PSI_AC_FAIL_REG 0x8004
-#define AC_FAIL_STAT_CHANGE 0x80
-
-#define VOYAGER_PSI_GENERAL_REG 0x8007
- /* read */
-# define PSI_SWITCH_ON 0x01
-# define PSI_SWITCH_ENABLED 0x02
-# define PSI_ALARM_ENABLED 0x08
-# define PSI_SECURE_ENABLED 0x10
-# define PSI_COLD_RESET 0x20
-# define PSI_COLD_START 0x80
- /* write */
-# define PSI_POWER_DOWN 0x10
-# define PSI_SWITCH_DISABLE 0x01
-# define PSI_SWITCH_ENABLE 0x11
-# define PSI_CLEAR 0x12
-# define PSI_ALARM_DISABLE 0x03
-# define PSI_ALARM_ENABLE 0x13
-# define PSI_CLEAR_COLD_RESET 0x05
-# define PSI_SET_COLD_RESET 0x15
-# define PSI_CLEAR_COLD_START 0x07
-# define PSI_SET_COLD_START 0x17
-
-
-
-struct voyager_bios_info {
- __u8 len;
- __u8 major;
- __u8 minor;
- __u8 debug;
- __u8 num_classes;
- __u8 class_1;
- __u8 class_2;
-};
-
-/* The following structures and definitions are for the Kernel/SUS
- * interface these are needed to find out how SUS initialised any Quad
- * boards in the system */
-
-#define NUMBER_OF_MC_BUSSES 2
-#define SLOTS_PER_MC_BUS 8
-#define MAX_CPUS 16 /* 16 way CPU system */
-#define MAX_PROCESSOR_BOARDS 4 /* 4 processor slot system */
-#define MAX_CACHE_LEVELS 4 /* # of cache levels supported */
-#define MAX_SHARED_CPUS 4 /* # of CPUs that can share a LARC */
-#define NUMBER_OF_POS_REGS 8
-
-typedef struct {
- __u8 MC_Slot;
- __u8 POS_Values[NUMBER_OF_POS_REGS];
-} __attribute__((packed)) MC_SlotInformation_t;
-
-struct QuadDescription {
- __u8 Type; /* for type 0 (DYADIC or MONADIC) all fields
- * will be zero except for slot */
- __u8 StructureVersion;
- __u32 CPI_BaseAddress;
- __u32 LARC_BankSize;
- __u32 LocalMemoryStateBits;
- __u8 Slot; /* Processor slots 1 - 4 */
-} __attribute__((packed));
-
-struct ProcBoardInfo {
- __u8 Type;
- __u8 StructureVersion;
- __u8 NumberOfBoards;
- struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
-} __attribute__((packed));
-
-struct CacheDescription {
- __u8 Level;
- __u32 TotalSize;
- __u16 LineSize;
- __u8 Associativity;
- __u8 CacheType;
- __u8 WriteType;
- __u8 Number_CPUs_SharedBy;
- __u8 Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
-
-} __attribute__((packed));
-
-struct CPU_Description {
- __u8 CPU_HardwareId;
- char *FRU_String;
- __u8 NumberOfCacheLevels;
- struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
-} __attribute__((packed));
-
-struct CPU_Info {
- __u8 Type;
- __u8 StructureVersion;
- __u8 NumberOf_CPUs;
- struct CPU_Description CPU_Data[MAX_CPUS];
-} __attribute__((packed));
-
-
-/*
- * This structure will be used by SUS and the OS.
- * The assumption about this structure is that no blank space is
- * packed in it by our friend the compiler.
- */
-typedef struct {
- __u8 Mailbox_SUS; /* Written to by SUS to give
- commands/response to the OS */
- __u8 Mailbox_OS; /* Written to by the OS to give
- commands/response to SUS */
- __u8 SUS_MailboxVersion; /* Tells the OS which iteration of the
- interface SUS supports */
- __u8 OS_MailboxVersion; /* Tells SUS which iteration of the
- interface the OS supports */
- __u32 OS_Flags; /* Flags set by the OS as info for
- SUS */
- __u32 SUS_Flags; /* Flags set by SUS as info
- for the OS */
- __u32 WatchDogPeriod; /* Watchdog period (in seconds) which
- the DP uses to see if the OS
- is dead */
- __u32 WatchDogCount; /* Updated by the OS on every tic. */
- __u32 MemoryFor_SUS_ErrorLog; /* Flat 32 bit address which tells SUS
- where to stuff the SUS error log
- on a dump */
- MC_SlotInformation_t MC_SlotInfo[NUMBER_OF_MC_BUSSES*SLOTS_PER_MC_BUS];
- /* Storage for MCA POS data */
- /* All new SECOND_PASS_INTERFACE fields added from this point */
- struct ProcBoardInfo *BoardData;
- struct CPU_Info *CPU_Data;
- /* All new fields must be added from this point */
-} Voyager_KernelSUS_Mbox_t;
-
-/* structure for finding the right memory address to send a QIC CPI to */
-struct voyager_qic_cpi {
- /* Each cache line (32 bytes) can trigger a cpi. The cpi
- * read/write may occur anywhere in the cache line---pick the
- * middle to be safe */
- struct {
- __u32 pad1[3];
- __u32 cpi;
- __u32 pad2[4];
- } qic_cpi[8];
-};
-
-struct voyager_status {
- __u32 power_fail:1;
- __u32 switch_off:1;
- __u32 request_from_kernel:1;
-};
-
-struct voyager_psi_regs {
- __u8 cat_id;
- __u8 cat_dev;
- __u8 cat_control;
- __u8 subaddr;
- __u8 dummy4;
- __u8 checkbit;
- __u8 subaddr_low;
- __u8 subaddr_high;
- __u8 intstatus;
- __u8 stat1;
- __u8 stat3;
- __u8 fault;
- __u8 tms;
- __u8 gen;
- __u8 sysconf;
- __u8 dummy15;
-};
-
-struct voyager_psi_subregs {
- __u8 supply;
- __u8 mask;
- __u8 present;
- __u8 DCfail;
- __u8 ACfail;
- __u8 fail;
- __u8 UPSfail;
- __u8 genstatus;
-};
-
-struct voyager_psi {
- struct voyager_psi_regs regs;
- struct voyager_psi_subregs subregs;
-};
-
-struct voyager_SUS {
-#define VOYAGER_DUMP_BUTTON_NMI 0x1
-#define VOYAGER_SUS_VALID 0x2
-#define VOYAGER_SYSINT_COMPLETE 0x3
- __u8 SUS_mbox;
-#define VOYAGER_NO_COMMAND 0x0
-#define VOYAGER_IGNORE_DUMP 0x1
-#define VOYAGER_DO_DUMP 0x2
-#define VOYAGER_SYSINT_HANDSHAKE 0x3
-#define VOYAGER_DO_MEM_DUMP 0x4
-#define VOYAGER_SYSINT_WAS_RECOVERED 0x5
- __u8 kernel_mbox;
-#define VOYAGER_MAILBOX_VERSION 0x10
- __u8 SUS_version;
- __u8 kernel_version;
-#define VOYAGER_OS_HAS_SYSINT 0x1
-#define VOYAGER_OS_IN_PROGRESS 0x2
-#define VOYAGER_UPDATING_WDPERIOD 0x4
- __u32 kernel_flags;
-#define VOYAGER_SUS_BOOTING 0x1
-#define VOYAGER_SUS_IN_PROGRESS 0x2
- __u32 SUS_flags;
- __u32 watchdog_period;
- __u32 watchdog_count;
- __u32 SUS_errorlog;
- /* lots of system configuration stuff under here */
-};
-
-/* Variables exported by voyager_smp */
-extern __u32 voyager_extended_vic_processors;
-extern __u32 voyager_allowed_boot_processors;
-extern __u32 voyager_quad_processors;
-extern struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS];
-extern struct voyager_SUS *voyager_SUS;
-
-/* variables exported always */
-extern struct task_struct *voyager_thread;
-extern int voyager_level;
-extern struct voyager_status voyager_status;
-
-/* functions exported by the voyager and voyager_smp modules */
-extern int voyager_cat_readb(__u8 module, __u8 asic, int reg);
-extern void voyager_cat_init(void);
-extern void voyager_detect(struct voyager_bios_info *);
-extern void voyager_trap_init(void);
-extern void voyager_setup_irqs(void);
-extern int voyager_memory_detect(int region, __u32 *addr, __u32 *length);
-extern void voyager_smp_intr_init(void);
-extern __u8 voyager_extended_cmos_read(__u16 cmos_address);
-extern void voyager_smp_dump(void);
-extern void voyager_timer_interrupt(void);
-extern void smp_local_timer_interrupt(void);
-extern void voyager_power_off(void);
-extern void smp_voyager_power_off(void *dummy);
-extern void voyager_restart(void);
-extern void voyager_cat_power_off(void);
-extern void voyager_cat_do_common_interrupt(void);
-extern void voyager_handle_nmi(void);
-extern void voyager_smp_intr_init(void);
-/* Commands for the following are */
-#define VOYAGER_PSI_READ 0
-#define VOYAGER_PSI_WRITE 1
-#define VOYAGER_PSI_SUBREAD 2
-#define VOYAGER_PSI_SUBWRITE 3
-extern void voyager_cat_psi(__u8, __u16, __u8 *);
-
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0 0
-#define VIC_CPI_LEVEL1 1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI 2
-#define VIC_INVALIDATE_CPI 3
-#define VIC_RESCHEDULE_CPI 4
-#define VIC_ENABLE_IRQ_CPI 5
-#define VIC_CALL_FUNCTION_CPI 6
-#define VIC_CALL_FUNCTION_SINGLE_CPI 7
-
-/* Now the QIC CPIs: Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET 1
-#define QIC_TIMER_CPI (VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_SINGLE_CPI (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI VIC_CALL_FUNCTION_SINGLE_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT 8
-#define VIC_CMN_INT 15
-
-/* This is the boot CPI for alternate processors. It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI (VIC_CPI_LEVEL0 + 8)
-
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index 3355973..580b4e2 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -3,8 +3,8 @@
*/
#include <asm/segment.h>
#include <asm/msr-index.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
#include <asm/processor-flags.h>
.code16
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index a12e6a9..8ded418 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,7 +1,7 @@
.section .text.page_aligned
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
# Copyright 2003, 2008 Pavel Machek <pavel@suse.cz>, distribute under GPLv2
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index bcc2934..8ea5164 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -1,8 +1,8 @@
.text
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/msr.h>
#include <asm/asm-offsets.h>
@@ -13,7 +13,6 @@
* Hooray, we are in Long 64-bit mode (but still running in low memory)
*/
ENTRY(wakeup_long64)
-wakeup_long64:
movq saved_magic, %rax
movq $0x123456789abcdef0, %rdx
cmpq %rdx, %rax
@@ -34,16 +33,12 @@
movq saved_rip, %rax
jmp *%rax
+ENDPROC(wakeup_long64)
bogus_64_magic:
jmp bogus_64_magic
- .align 2
- .p2align 4,,15
-.globl do_suspend_lowlevel
- .type do_suspend_lowlevel,@function
-do_suspend_lowlevel:
-.LFB5:
+ENTRY(do_suspend_lowlevel)
subq $8, %rsp
xorl %eax, %eax
call save_processor_state
@@ -67,7 +62,7 @@
pushfq
popq pt_regs_flags(%rax)
- movq $.L97, saved_rip(%rip)
+ movq $resume_point, saved_rip(%rip)
movq %rsp, saved_rsp
movq %rbp, saved_rbp
@@ -78,14 +73,12 @@
addq $8, %rsp
movl $3, %edi
xorl %eax, %eax
- jmp acpi_enter_sleep_state
-.L97:
- .p2align 4,,7
-.L99:
- .align 4
- movl $24, %eax
- movw %ax, %ds
+ call acpi_enter_sleep_state
+ /* in case something went wrong, restore the machine status and go on */
+ jmp resume_point
+ .align 4
+resume_point:
/* We don't restore %rax, it must be 0 anyway */
movq $saved_context, %rax
movq saved_context_cr4(%rax), %rbx
@@ -117,12 +110,9 @@
xorl %eax, %eax
addq $8, %rsp
jmp restore_processor_state
-.LFE5:
-.Lfe5:
- .size do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel
-
+ENDPROC(do_suspend_lowlevel)
+
.data
-ALIGN
ENTRY(saved_rbp) .quad 0
ENTRY(saved_rsi) .quad 0
ENTRY(saved_rdi) .quad 0
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a84ac7b..6907b8e 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -498,12 +498,12 @@
*/
void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
{
- unsigned long flags;
char *vaddr;
int nr_pages = 2;
struct page *pages[2];
int i;
+ might_sleep();
if (!core_kernel_text((unsigned long)addr)) {
pages[0] = vmalloc_to_page(addr);
pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -517,9 +517,9 @@
nr_pages = 1;
vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
BUG_ON(!vaddr);
- local_irq_save(flags);
+ local_irq_disable();
memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
- local_irq_restore(flags);
+ local_irq_enable();
vunmap(vaddr);
sync_core();
/* Could also do a CLFLUSH here to speed up CPU recovery; but
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d1bf032..4732768 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -35,7 +35,6 @@
#include <linux/mm.h>
#include <asm/perf_counter.h>
-#include <asm/arch_hooks.h>
#include <asm/pgalloc.h>
#include <asm/atomic.h>
#include <asm/mpspec.h>
@@ -840,7 +839,7 @@
}
/* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
if (maxlvt >= 5) {
v = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
@@ -1269,14 +1268,7 @@
#ifdef CONFIG_X86_X2APIC
void check_x2apic(void)
{
- int msr, msr2;
-
- if (!cpu_has_x2apic)
- return;
-
- rdmsr(MSR_IA32_APICBASE, msr, msr2);
-
- if (msr & X2APIC_ENABLE) {
+ if (x2apic_enabled()) {
pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
x2apic_preenabled = x2apic = 1;
}
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index c9ec907..3a730fa 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -35,7 +35,6 @@
#include <linux/init.h>
#include <linux/interrupt.h>
#include <asm/acpi.h>
-#include <asm/arch_hooks.h>
#include <asm/e820.h>
#include <asm/setup.h>
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 70935dd..e7c1636 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,9 +50,16 @@
void __init default_setup_apic_routing(void)
{
#ifdef CONFIG_X86_X2APIC
- if (apic == &apic_x2apic_phys || apic == &apic_x2apic_cluster) {
- if (!intr_remapping_enabled)
- apic = &apic_flat;
+ if (x2apic && (apic != &apic_x2apic_phys &&
+#ifdef CONFIG_X86_UV
+ apic != &apic_x2apic_uv_x &&
+#endif
+ apic != &apic_x2apic_cluster)) {
+ if (x2apic_phys)
+ apic = &apic_x2apic_phys;
+ else
+ apic = &apic_x2apic_cluster;
+ printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
}
#endif
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index cfe7b09..32838b5 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -48,7 +48,7 @@
#include <linux/gfp.h>
#include <linux/smp.h>
-static inline unsigned summit_get_apic_id(unsigned long x)
+static unsigned summit_get_apic_id(unsigned long x)
{
return (x >> 24) & 0xFF;
}
@@ -58,7 +58,7 @@
default_send_IPI_mask_sequence_logical(mask, vector);
}
-static inline void summit_send_IPI_allbutself(int vector)
+static void summit_send_IPI_allbutself(int vector)
{
cpumask_t mask = cpu_online_map;
cpu_clear(smp_processor_id(), mask);
@@ -67,7 +67,7 @@
summit_send_IPI_mask(&mask, vector);
}
-static inline void summit_send_IPI_all(int vector)
+static void summit_send_IPI_all(int vector)
{
summit_send_IPI_mask(&cpu_online_map, vector);
}
@@ -82,8 +82,8 @@
#define setup_summit() {}
#endif
-static inline int
-summit_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
+static int summit_mps_oem_check(struct mpc_table *mpc, char *oem,
+ char *productid)
{
if (!strncmp(oem, "IBM ENSW", 8) &&
(!strncmp(productid, "VIGIL SMP", 9)
@@ -98,7 +98,7 @@
}
/* Hook from generic ACPI tables.c */
-static inline int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
if (!strncmp(oem_id, "IBM", 3) &&
(!strncmp(oem_table_id, "SERVIGIL", 8)
@@ -186,7 +186,7 @@
#define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
-static inline const cpumask_t *summit_target_cpus(void)
+static const cpumask_t *summit_target_cpus(void)
{
/* CPU_MASK_ALL (0xff) has undefined behaviour with
* dest_LowestPrio mode logical clustered apic interrupt routing
@@ -195,19 +195,18 @@
return &cpumask_of_cpu(0);
}
-static inline unsigned long
-summit_check_apicid_used(physid_mask_t bitmap, int apicid)
+static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid)
{
return 0;
}
/* we don't use the phys_cpu_present_map to indicate apicid presence */
-static inline unsigned long summit_check_apicid_present(int bit)
+static unsigned long summit_check_apicid_present(int bit)
{
return 1;
}
-static inline void summit_init_apic_ldr(void)
+static void summit_init_apic_ldr(void)
{
unsigned long val, id;
int count = 0;
@@ -234,18 +233,18 @@
apic_write(APIC_LDR, val);
}
-static inline int summit_apic_id_registered(void)
+static int summit_apic_id_registered(void)
{
return 1;
}
-static inline void summit_setup_apic_routing(void)
+static void summit_setup_apic_routing(void)
{
printk("Enabling APIC mode: Summit. Using %d I/O APICs\n",
nr_ioapics);
}
-static inline int summit_apicid_to_node(int logical_apicid)
+static int summit_apicid_to_node(int logical_apicid)
{
#ifdef CONFIG_SMP
return apicid_2_node[hard_smp_processor_id()];
@@ -266,7 +265,7 @@
#endif
}
-static inline int summit_cpu_present_to_apicid(int mps_cpu)
+static int summit_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids)
return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
@@ -274,28 +273,23 @@
return BAD_APICID;
}
-static inline physid_mask_t
-summit_ioapic_phys_id_map(physid_mask_t phys_id_map)
+static physid_mask_t summit_ioapic_phys_id_map(physid_mask_t phys_id_map)
{
/* For clustered we don't have a good way to do this yet - hack */
return physids_promote(0x0F);
}
-static inline physid_mask_t summit_apicid_to_cpu_present(int apicid)
+static physid_mask_t summit_apicid_to_cpu_present(int apicid)
{
return physid_mask_of_physid(0);
}
-static inline void summit_setup_portio_remap(void)
-{
-}
-
-static inline int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
{
return 1;
}
-static inline unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
{
int cpus_found = 0;
int num_bits_set;
@@ -303,12 +297,10 @@
int cpu;
num_bits_set = cpus_weight(*cpumask);
- /* Return id to all */
if (num_bits_set >= nr_cpu_ids)
- return 0xFF;
+ return BAD_APICID;
/*
- * The cpus in the mask must all be on the apic cluster. If are not
- * on the same apicid cluster return default value of target_cpus():
+ * The cpus in the mask must all be on the apic cluster.
*/
cpu = first_cpu(*cpumask);
apicid = summit_cpu_to_logical_apicid(cpu);
@@ -318,9 +310,9 @@
int new_apicid = summit_cpu_to_logical_apicid(cpu);
if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
- printk ("%s: Not a valid mask!\n", __func__);
+ printk("%s: Not a valid mask!\n", __func__);
- return 0xFF;
+ return BAD_APICID;
}
apicid = apicid | new_apicid;
cpus_found++;
@@ -330,8 +322,7 @@
return apicid;
}
-static inline unsigned int
-summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
+static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
const struct cpumask *andmask)
{
int apicid = summit_cpu_to_logical_apicid(0);
@@ -356,7 +347,7 @@
*
* See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
*/
-static inline int summit_phys_pkg_id(int cpuid_apic, int index_msb)
+static int summit_phys_pkg_id(int cpuid_apic, int index_msb)
{
return hard_smp_processor_id() >> index_msb;
}
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 4e39d9a..354b9c4 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -14,10 +14,7 @@
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
- if (cpu_has_x2apic)
- return 1;
-
- return 0;
+ return x2apic_enabled();
}
/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index d2d52eb..5bcb174 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -10,7 +10,7 @@
#include <asm/apic.h>
#include <asm/ipi.h>
-static int x2apic_phys;
+int x2apic_phys;
static int set_x2apic_phys_mode(char *arg)
{
@@ -21,10 +21,10 @@
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
- if (cpu_has_x2apic && x2apic_phys)
- return 1;
-
- return 0;
+ if (x2apic_phys)
+ return x2apic_enabled();
+ else
+ return 0;
}
/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 37ba5f8..10033fe 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1192,6 +1192,7 @@
device_suspend(PMSG_SUSPEND);
local_irq_disable();
device_power_down(PMSG_SUSPEND);
+ sysdev_suspend(PMSG_SUSPEND);
local_irq_enable();
@@ -1208,6 +1209,7 @@
if (err != APM_SUCCESS)
apm_error("suspend", err);
err = (err == APM_SUCCESS) ? 0 : -EIO;
+ sysdev_resume();
device_power_up(PMSG_RESUME);
local_irq_enable();
device_resume(PMSG_RESUME);
@@ -1228,6 +1230,7 @@
local_irq_disable();
device_power_down(PMSG_SUSPEND);
+ sysdev_suspend(PMSG_SUSPEND);
local_irq_enable();
err = set_system_power_state(APM_STATE_STANDBY);
@@ -1235,6 +1238,7 @@
apm_error("standby", err);
local_irq_disable();
+ sysdev_resume();
device_power_up(PMSG_RESUME);
local_irq_enable();
}
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
index c2f930d..41ab3f0 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
@@ -204,12 +204,12 @@
}
/* Enable Enhanced PowerSaver */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & 1 << 16)) {
- val |= 1 << 16;
+ if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
+ val |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
wrmsrl(MSR_IA32_MISC_ENABLE, val);
/* Can be locked at 0 */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & 1 << 16)) {
+ if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
printk(KERN_INFO "eps: Can't enable Enhanced PowerSaver\n");
return -ENODEV;
}
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index fb039cd..6428aa1 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1157,8 +1157,7 @@
data->cpu = pol->cpu;
data->currpstate = HW_PSTATE_INVALID;
- rc = powernow_k8_cpu_init_acpi(data);
- if (rc) {
+ if (powernow_k8_cpu_init_acpi(data)) {
/*
* Use the PSB BIOS structure. This is only availabe on
* an UP version, and is deprecated by AMD.
@@ -1176,17 +1175,20 @@
"ACPI maintainers and complain to your BIOS "
"vendor.\n");
#endif
- goto err_out;
+ kfree(data);
+ return -ENODEV;
}
if (pol->cpu != 0) {
printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
"CPU other than CPU0. Complain to your BIOS "
"vendor.\n");
- goto err_out;
+ kfree(data);
+ return -ENODEV;
}
rc = find_psb_table(data);
if (rc) {
- goto err_out;
+ kfree(data);
+ return -ENODEV;
}
/* Take a crude guess here.
* That guess was in microseconds, so multiply with 1000 */
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index f089982..c9f1fdc 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -390,14 +390,14 @@
enable it if not. */
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- if (!(l & (1<<16))) {
- l |= (1<<16);
+ if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
+ l |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
dprintk("trying to enable Enhanced SpeedStep (%x)\n", l);
wrmsr(MSR_IA32_MISC_ENABLE, l, h);
/* check to see if it stuck */
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- if (!(l & (1<<16))) {
+ if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
printk(KERN_INFO PFX
"couldn't enable Enhanced SpeedStep\n");
return -ENODEV;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7aeef1d..25c559b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -146,10 +146,10 @@
*/
if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
- if ((lo & (1<<9)) == 0) {
+ if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
- lo |= (1<<9); /* Disable hw prefetching */
+ lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
}
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 1c83803..fe79985 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -295,11 +295,11 @@
* If we know that the error was in user space, send a
* SIGBUS. Otherwise, panic if tolerance is low.
*
- * do_exit() takes an awful lot of locks and has a slight
+ * force_sig() takes an awful lot of locks and has a slight
* risk of deadlocking.
*/
if (user_space) {
- do_exit(SIGBUS);
+ force_sig(SIGBUS, current);
} else if (panic_on_oops || tolerant < 2) {
mce_panic("Uncorrected machine check",
&panicm, mcestart);
@@ -490,7 +490,7 @@
}
-static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
+static void mce_cpu_features(struct cpuinfo_x86 *c)
{
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
@@ -734,6 +734,7 @@
static int mce_resume(struct sys_device *dev)
{
mce_init(NULL);
+ mce_cpu_features(¤t_cpu_data);
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 4772e91..9817506 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -121,7 +121,7 @@
}
/* cpu init entry point, called from mce.c with preempt off */
-void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
+void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
unsigned int bank, block;
unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 5e8c79e..aa5e287 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -31,7 +31,7 @@
irq_exit();
}
-static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
+static void intel_init_thermal(struct cpuinfo_x86 *c)
{
u32 l, h;
int tm2 = 0;
@@ -49,13 +49,13 @@
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
h = apic_read(APIC_LVTTHMR);
- if ((l & (1 << 3)) && (h & APIC_DM_SMI)) {
+ if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG
"CPU%d: Thermal monitoring handled by SMI\n", cpu);
return;
}
- if (cpu_has(c, X86_FEATURE_TM2) && (l & (1 << 13)))
+ if (cpu_has(c, X86_FEATURE_TM2) && (l & MSR_IA32_MISC_ENABLE_TM2))
tm2 = 1;
if (h & APIC_VECTOR_MASK) {
@@ -73,7 +73,7 @@
wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03, h);
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- wrmsr(MSR_IA32_MISC_ENABLE, l | (1 << 3), h);
+ wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
l = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
@@ -85,7 +85,7 @@
return;
}
-void __cpuinit mce_intel_feature_init(struct cpuinfo_x86 *c)
+void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
}
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index 9b60fce..f53bdcb 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -85,7 +85,7 @@
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
h = apic_read(APIC_LVTTHMR);
- if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
+ if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n",
cpu);
return; /* -EBUSY */
@@ -111,7 +111,7 @@
vendor_thermal_interrupt = intel_thermal_interrupt;
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+ wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
l = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index e858268..508bec1 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -858,6 +858,9 @@
*/
void __init reserve_early(u64 start, u64 end, char *name)
{
+ if (start >= end)
+ return;
+
drop_overlaps_that_are_ok(start, end);
__reserve_early(start, end, name, 0);
}
diff --git a/arch/x86/kernel/efi_stub_32.S b/arch/x86/kernel/efi_stub_32.S
index ef00bb7..fbe66e6 100644
--- a/arch/x86/kernel/efi_stub_32.S
+++ b/arch/x86/kernel/efi_stub_32.S
@@ -6,7 +6,7 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
/*
* efi_call_phys(void *, ...) is a function with variable parameters.
@@ -113,6 +113,7 @@
movl (%edx), %ecx
pushl %ecx
ret
+ENDPROC(efi_call_phys)
.previous
.data
diff --git a/arch/x86/kernel/efi_stub_64.S b/arch/x86/kernel/efi_stub_64.S
index 99b47d4..4c07cca 100644
--- a/arch/x86/kernel/efi_stub_64.S
+++ b/arch/x86/kernel/efi_stub_64.S
@@ -41,6 +41,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call0)
ENTRY(efi_call1)
SAVE_XMM
@@ -50,6 +51,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call1)
ENTRY(efi_call2)
SAVE_XMM
@@ -59,6 +61,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call2)
ENTRY(efi_call3)
SAVE_XMM
@@ -69,6 +72,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call3)
ENTRY(efi_call4)
SAVE_XMM
@@ -80,6 +84,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call4)
ENTRY(efi_call5)
SAVE_XMM
@@ -92,6 +97,7 @@
addq $48, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call5)
ENTRY(efi_call6)
SAVE_XMM
@@ -107,3 +113,4 @@
addq $48, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call6)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e992068..899e893 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -47,7 +47,7 @@
#include <asm/errno.h>
#include <asm/segment.h>
#include <asm/smp.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/desc.h>
#include <asm/percpu.h>
#include <asm/dwarf2.h>
@@ -1359,7 +1359,7 @@
CFI_ADJUST_CFA_OFFSET 4
pushl %esp
CFI_ADJUST_CFA_OFFSET 4
- addw $4, (%esp)
+ addl $4, (%esp)
/* copy the iret frame of 12 bytes */
.rept 3
pushl 16(%esp)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 860afce..24c7031 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -48,7 +48,7 @@
#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/hw_irq.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
@@ -77,20 +77,17 @@
movq 8(%rbp), %rsi
subq $MCOUNT_INSN_SIZE, %rdi
-.globl ftrace_call
-ftrace_call:
+GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
+GLOBAL(ftrace_graph_call)
jmp ftrace_stub
#endif
-.globl ftrace_stub
-ftrace_stub:
+GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
@@ -110,8 +107,7 @@
jnz ftrace_graph_caller
#endif
-.globl ftrace_stub
-ftrace_stub:
+GLOBAL(ftrace_stub)
retq
trace:
@@ -148,9 +144,7 @@
retq
END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
+GLOBAL(return_to_handler)
subq $80, %rsp
movq %rax, (%rsp)
@@ -188,6 +182,7 @@
ENTRY(native_usergs_sysret64)
swapgs
sysretq
+ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
@@ -633,16 +628,14 @@
* Syscall return path ending with IRET.
* Has correct top of stack, but partial stack frame.
*/
- .globl int_ret_from_sys_call
- .globl int_with_check
-int_ret_from_sys_call:
+GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $3,CS-ARGOFFSET(%rsp)
je retint_restore_args
movl $_TIF_ALLWORK_MASK,%edi
/* edi: mask to check */
-int_with_check:
+GLOBAL(int_with_check)
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
movl TI_flags(%rcx),%edx
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 2a0aad7..c32ca19 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -11,8 +11,8 @@
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
#include <asm/desc.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 2e648e3..54b29bb 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -329,8 +329,6 @@
#endif /* CONFIG_EARLY_PRINTK */
.previous
-.balign PAGE_SIZE
-
#define NEXT_PAGE(name) \
.balign PAGE_SIZE; \
ENTRY(name)
@@ -419,7 +417,7 @@
.section .bss, "aw", @nobits
.align L1_CACHE_BYTES
ENTRY(idt_table)
- .skip 256 * 16
+ .skip IDT_ENTRIES * 16
.section .bss.page_aligned, "aw", @nobits
.align PAGE_SIZE
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 11d5093..df89102 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -22,7 +22,6 @@
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/apic.h>
-#include <asm/arch_hooks.h>
#include <asm/i8259.h>
/*
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 520e6c1..f3e11cb2 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -18,7 +18,7 @@
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/apic.h>
-#include <asm/arch_hooks.h>
+#include <asm/setup.h>
#include <asm/i8259.h>
#include <asm/traps.h>
@@ -181,8 +181,8 @@
{
int i;
- /* all the set up before the call gates are initialised */
- pre_intr_init_hook();
+ /* Execute any quirks before the call gates are initialised: */
+ x86_quirk_pre_intr_init();
apic_intr_init();
@@ -201,10 +201,11 @@
if (!acpi_ioapic)
setup_irq(2, &irq2);
- /* setup after call gates are initialised (usually add in
- * the architecture specific gates)
+ /*
+ * Call quirks after call gates are initialised (usually add in
+ * the architecture specific gates):
*/
- intr_init_hook();
+ x86_quirk_intr_init();
/*
* External FPU? Set up irq13 if so, for
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 652fce6d..137f2e8 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -19,7 +19,6 @@
#include <linux/clocksource.h>
#include <linux/kvm_para.h>
#include <asm/pvclock.h>
-#include <asm/arch_hooks.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <linux/percpu.h>
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 37f4200..f5fc8c7 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -121,7 +121,7 @@
static void machine_kexec_prepare_page_tables(struct kimage *image)
{
void *control_page;
- pmd_t *pmd = 0;
+ pmd_t *pmd = NULL;
control_page = page_address(image->control_code_page);
#ifdef CONFIG_X86_PAE
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 2dc1837..845d80c 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -51,7 +51,6 @@
#include <linux/ioport.h>
#include <asm/uaccess.h>
#include <linux/init.h>
-#include <asm/arch_hooks.h>
static unsigned char which_scsi;
@@ -474,6 +473,4 @@
* adapter was responsible for the error.
*/
bus_for_each_dev(&mca_bus_type, NULL, NULL, mca_handle_nmi_callback);
-
- mca_nmi_hook();
-} /* mca_handle_nmi */
+}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 7f4d258..37cb1bd 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -710,13 +710,22 @@
* of physical memory; so that simply reserving
* PAGE_SIZE from mpf->physptr yields BUG()
* in reserve_bootmem.
+ * also need to make sure physptr is below than
+ * max_low_pfn
+ * we don't need reserve the area above max_low_pfn
*/
unsigned long end = max_low_pfn * PAGE_SIZE;
- if (mpf->physptr + size > end)
- size = end - mpf->physptr;
-#endif
+
+ if (mpf->physptr < end) {
+ if (mpf->physptr + size > end)
+ size = end - mpf->physptr;
+ reserve_bootmem_generic(mpf->physptr, size,
+ BOOTMEM_DEFAULT);
+ }
+#else
reserve_bootmem_generic(mpf->physptr, size,
BOOTMEM_DEFAULT);
+#endif
}
return 1;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 6dc4dca..63dd358 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -28,7 +28,6 @@
#include <asm/paravirt.h>
#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>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index fec79ad..646da41 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -111,9 +111,6 @@
check_pgt_cache();
rmb();
- if (rcu_pending(cpu))
- rcu_check_callbacks(cpu, 0);
-
if (cpu_is_offline(cpu))
play_dead();
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index d2f7cd5..fb2159a 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -268,7 +268,7 @@
if (test_tsk_thread_flag(task, TIF_IA32))
return IA32_PAGE_OFFSET - 3;
#endif
- return TASK_SIZE64 - 7;
+ return TASK_SIZE_MAX - 7;
}
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index a160f31..2064d0a 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -7,7 +7,7 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/kexec.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index b0bbdd4..d32cfb2 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -7,10 +7,10 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/kexec.h>
#include <asm/processor-flags.h>
-#include <asm/pgtable.h>
+#include <asm/pgtable_types.h>
/*
* Must be relocatable PIC code callable as a C function
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ebef800..5b85759 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -74,8 +74,9 @@
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
-#include <asm/arch_hooks.h>
#include <asm/efi.h>
+#include <asm/timer.h>
+#include <asm/i8259.h>
#include <asm/sections.h>
#include <asm/dmi.h>
#include <asm/io_apic.h>
@@ -668,7 +669,6 @@
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
- pre_setup_arch_hook();
#else
printk(KERN_INFO "Command line: %s\n", boot_command_line);
#endif
@@ -988,7 +988,7 @@
#ifdef CONFIG_X86_32
/**
- * pre_intr_init_hook - initialisation prior to setting up interrupt vectors
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
*
* Description:
* Perform any necessary interrupt initialisation prior to setting up
@@ -996,7 +996,7 @@
* interrupts should be initialised here if the machine emulates a PC
* in any way.
**/
-void __init pre_intr_init_hook(void)
+void __init x86_quirk_pre_intr_init(void)
{
if (x86_quirks->arch_pre_intr_init) {
if (x86_quirks->arch_pre_intr_init())
@@ -1006,7 +1006,7 @@
}
/**
- * intr_init_hook - post gate setup interrupt initialisation
+ * x86_quirk_intr_init - post gate setup interrupt initialisation
*
* Description:
* Fill in any interrupts that may have been left out by the general
@@ -1014,7 +1014,7 @@
* than the devices on the I/O bus (like APIC interrupts in intel MP
* systems) are started here.
**/
-void __init intr_init_hook(void)
+void __init x86_quirk_intr_init(void)
{
if (x86_quirks->arch_intr_init) {
if (x86_quirks->arch_intr_init())
@@ -1023,25 +1023,13 @@
}
/**
- * pre_setup_arch_hook - hook called prior to any setup_arch() execution
- *
- * Description:
- * generally used to activate any machine specific identification
- * routines that may be needed before setup_arch() runs. On Voyager
- * this is used to get the board revision and type.
- **/
-void __init pre_setup_arch_hook(void)
-{
-}
-
-/**
- * trap_init_hook - initialise system specific traps
+ * x86_quirk_trap_init - initialise system specific traps
*
* Description:
* Called as the final act of trap_init(). Used in VISWS to initialise
* the various board specific APIC traps.
**/
-void __init trap_init_hook(void)
+void __init x86_quirk_trap_init(void)
{
if (x86_quirks->arch_trap_init) {
if (x86_quirks->arch_trap_init())
@@ -1051,29 +1039,29 @@
static struct irqaction irq0 = {
.handler = timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+ .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
.mask = CPU_MASK_NONE,
.name = "timer"
};
/**
- * pre_time_init_hook - do any specific initialisations before.
+ * x86_quirk_pre_time_init - do any specific initialisations before.
*
**/
-void __init pre_time_init_hook(void)
+void __init x86_quirk_pre_time_init(void)
{
if (x86_quirks->arch_pre_time_init)
x86_quirks->arch_pre_time_init();
}
/**
- * time_init_hook - do any specific initialisations for the system timer.
+ * x86_quirk_time_init - do any specific initialisations for the system timer.
*
* Description:
* Must plug the system timer interrupt source at HZ into the IRQ listed
* in irq_vectors.h:TIMER_IRQ
**/
-void __init time_init_hook(void)
+void __init x86_quirk_time_init(void)
{
if (x86_quirks->arch_time_init) {
/*
@@ -1088,25 +1076,4 @@
irq0.mask = cpumask_of_cpu(0);
setup_irq(0, &irq0);
}
-
-#ifdef CONFIG_MCA
-/**
- * mca_nmi_hook - hook into MCA specific NMI chain
- *
- * Description:
- * The MCA (Microchannel Architecture) has an NMI chain for NMI sources
- * along the MCA bus. Use this to hook into that chain if you will need
- * it.
- **/
-void mca_nmi_hook(void)
-{
- /*
- * If I recall correctly, there's a whole bunch of other things that
- * we can do to check for NMI problems, but that's all I know about
- * at the moment.
- */
- pr_warning("NMI generated from unknown source!\n");
-}
-#endif /* CONFIG_MCA */
-
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index 764c74e..5c5d87f 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -33,7 +33,7 @@
#include <linux/time.h>
#include <linux/mca.h>
-#include <asm/arch_hooks.h>
+#include <asm/setup.h>
#include <asm/hpet.h>
#include <asm/time.h>
#include <asm/timer.h>
@@ -118,7 +118,7 @@
{
if (!hpet_enable())
setup_pit_timer();
- time_init_hook();
+ x86_quirk_time_init();
}
/*
@@ -131,7 +131,7 @@
*/
void __init time_init(void)
{
- pre_time_init_hook();
+ x86_quirk_pre_time_init();
tsc_init();
late_time_init = choose_time_init();
}
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index e6e695a..241ec39 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -115,7 +115,7 @@
static struct irqaction irq0 = {
.handler = timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
+ .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
.mask = CPU_MASK_NONE,
.name = "timer"
};
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
index d8ccc3c..66d874e 100644
--- a/arch/x86/kernel/trampoline_32.S
+++ b/arch/x86/kernel/trampoline_32.S
@@ -29,7 +29,7 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
/* We can free up trampoline after bootup if cpu hotplug is not supported. */
#ifndef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 95a012a..cddfb8d 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -25,8 +25,8 @@
*/
#include <linux/linkage.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/msr.h>
#include <asm/segment.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c85a86c..1dba866 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -61,7 +61,7 @@
#include <asm/proto.h>
#else
#include <asm/processor-flags.h>
-#include <asm/arch_hooks.h>
+#include <asm/setup.h>
#include <asm/traps.h>
#include "cpu/mcheck/mce.h"
@@ -942,7 +942,7 @@
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_BADSTK;
- info.si_addr = 0;
+ info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception",
regs, error_code, 32, SIGILL) == NOTIFY_STOP)
return;
@@ -1023,6 +1023,6 @@
cpu_init();
#ifdef CONFIG_X86_32
- trap_init_hook();
+ x86_quirk_trap_init();
#endif
}
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 34199d3..191a876 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -24,7 +24,6 @@
#include <asm/visws/cobalt.h>
#include <asm/visws/piix4.h>
-#include <asm/arch_hooks.h>
#include <asm/io_apic.h>
#include <asm/fixmap.h>
#include <asm/reboot.h>
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index a4791ef..33a788d 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -28,7 +28,6 @@
#include <asm/vmi.h>
#include <asm/vmi_time.h>
-#include <asm/arch_hooks.h>
#include <asm/apicdef.h>
#include <asm/apic.h>
#include <asm/timer.h>
@@ -202,7 +201,7 @@
static struct irqaction vmi_clock_action = {
.name = "vmi-timer",
.handler = vmi_timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_NOBALANCING,
+ .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
.mask = CPU_MASK_ALL,
};
@@ -283,10 +282,12 @@
#endif
/** vmi clocksource */
+static struct clocksource clocksource_vmi;
static cycle_t read_real_cycles(void)
{
- return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+ cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+ return max(ret, clocksource_vmi.cycle_last);
}
static struct clocksource clocksource_vmi = {
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 3eba7f7..0d86096 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -12,7 +12,7 @@
#include <asm-generic/vmlinux.lds.h>
#include <asm/thread_info.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/cache.h>
#include <asm/boot.h>
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 087a7f2..fbfced6 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -6,7 +6,7 @@
#include <asm-generic/vmlinux.lds.h>
#include <asm/asm-offsets.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#undef i386 /* in case the preprocessor is a 32bit one */
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index e665d1c..72bd275 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -207,7 +207,7 @@
hrtimer_add_expires_ns(&pt->timer, pt->period);
pt->scheduled = hrtimer_get_expires_ns(&pt->timer);
if (pt->period)
- ps->channels[0].count_load_time = hrtimer_get_expires(&pt->timer);
+ ps->channels[0].count_load_time = ktime_get();
return (pt->period == 0 ? 0 : 1);
}
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index c019b8e..cf17ed5 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -87,13 +87,6 @@
}
EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
- kvm_apic_timer_intr_post(vcpu, vec);
- /* TODO: PIT, RTC etc. */
-}
-EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
-
void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
__kvm_migrate_apic_timer(vcpu);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2bf32a0..82579ee 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -89,7 +89,6 @@
void kvm_pic_reset(struct kvm_kpic_state *s);
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afac68c..f0b67f2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -35,6 +35,12 @@
#include "kvm_cache_regs.h"
#include "irq.h"
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
#define PRId64 "d"
#define PRIx64 "llx"
#define PRIu64 "u"
@@ -511,52 +517,22 @@
static u32 apic_get_tmcct(struct kvm_lapic *apic)
{
- u64 counter_passed;
- ktime_t passed, now;
+ ktime_t remaining;
+ s64 ns;
u32 tmcct;
ASSERT(apic != NULL);
- now = apic->timer.dev.base->get_time();
- tmcct = apic_get_reg(apic, APIC_TMICT);
-
/* if initial count is 0, current count should also be 0 */
- if (tmcct == 0)
+ if (apic_get_reg(apic, APIC_TMICT) == 0)
return 0;
- if (unlikely(ktime_to_ns(now) <=
- ktime_to_ns(apic->timer.last_update))) {
- /* Wrap around */
- passed = ktime_add(( {
- (ktime_t) {
- .tv64 = KTIME_MAX -
- (apic->timer.last_update).tv64}; }
- ), now);
- apic_debug("time elapsed\n");
- } else
- passed = ktime_sub(now, apic->timer.last_update);
+ remaining = hrtimer_expires_remaining(&apic->timer.dev);
+ if (ktime_to_ns(remaining) < 0)
+ remaining = ktime_set(0, 0);
- counter_passed = div64_u64(ktime_to_ns(passed),
- (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
-
- if (counter_passed > tmcct) {
- if (unlikely(!apic_lvtt_period(apic))) {
- /* one-shot timers stick at 0 until reset */
- tmcct = 0;
- } else {
- /*
- * periodic timers reset to APIC_TMICT when they
- * hit 0. The while loop simulates this happening N
- * times. (counter_passed %= tmcct) would also work,
- * but might be slower or not work on 32-bit??
- */
- while (counter_passed > tmcct)
- counter_passed -= tmcct;
- tmcct -= counter_passed;
- }
- } else {
- tmcct -= counter_passed;
- }
+ ns = mod_64(ktime_to_ns(remaining), apic->timer.period);
+ tmcct = div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
return tmcct;
}
@@ -653,8 +629,6 @@
{
ktime_t now = apic->timer.dev.base->get_time();
- apic->timer.last_update = now;
-
apic->timer.period = apic_get_reg(apic, APIC_TMICT) *
APIC_BUS_CYCLE_NS * apic->timer.divide_count;
atomic_set(&apic->timer.pending, 0);
@@ -1110,16 +1084,6 @@
}
}
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
-
- if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec)
- apic->timer.last_update = ktime_add_ns(
- apic->timer.last_update,
- apic->timer.period);
-}
-
int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
{
int vector = kvm_apic_has_interrupt(vcpu);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 8185888..45ab6ee 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -12,7 +12,6 @@
atomic_t pending;
s64 period; /* unit: ns */
u32 divide_count;
- ktime_t last_update;
struct hrtimer dev;
} timer;
struct kvm_vcpu *vcpu;
@@ -42,7 +41,6 @@
void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 83f11c7..2d4477c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1698,8 +1698,13 @@
if (largepage)
spte |= PT_PAGE_SIZE_MASK;
if (mt_mask) {
- mt_mask = get_memory_type(vcpu, gfn) <<
- kvm_x86_ops->get_mt_mask_shift();
+ if (!kvm_is_mmio_pfn(pfn)) {
+ mt_mask = get_memory_type(vcpu, gfn) <<
+ kvm_x86_ops->get_mt_mask_shift();
+ mt_mask |= VMX_EPT_IGMT_BIT;
+ } else
+ mt_mask = MTRR_TYPE_UNCACHABLE <<
+ kvm_x86_ops->get_mt_mask_shift();
spte |= mt_mask;
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1452851..a9e769e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1600,7 +1600,6 @@
/* Okay, we can deliver the interrupt: grab it and update PIC state. */
intr_vector = kvm_cpu_get_interrupt(vcpu);
svm_inject_irq(svm, intr_vector);
- kvm_timer_intr_post(vcpu, intr_vector);
out:
update_cr8_intercept(vcpu);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6259d74..7611af5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -903,6 +903,7 @@
data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
default:
+ vmx_load_host_state(to_vmx(vcpu));
msr = find_msr_entry(to_vmx(vcpu), msr_index);
if (msr) {
data = msr->data;
@@ -3285,7 +3286,6 @@
}
if (vcpu->arch.interrupt.pending) {
vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
- kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr);
if (kvm_cpu_has_interrupt(vcpu))
enable_irq_window(vcpu);
}
@@ -3687,8 +3687,7 @@
if (vm_need_ept()) {
bypass_guest_pf = 0;
kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
- VMX_EPT_WRITABLE_MASK |
- VMX_EPT_IGMT_BIT);
+ VMX_EPT_WRITABLE_MASK);
kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
VMX_EPT_EXECUTABLE_MASK,
VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cc17546..758b7a1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -967,7 +967,6 @@
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
- case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
case KVM_CAP_MP_STATE:
@@ -992,6 +991,9 @@
case KVM_CAP_IOMMU:
r = iommu_found();
break;
+ case KVM_CAP_CLOCKSOURCE:
+ r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC);
+ break;
default:
r = 0;
break;
@@ -4127,9 +4129,13 @@
}
-void kvm_arch_destroy_vm(struct kvm *kvm)
+void kvm_arch_sync_events(struct kvm *kvm)
{
kvm_free_all_assigned_devices(kvm);
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
kvm_iommu_unmap_guest(kvm);
kvm_free_pit(kvm);
kfree(kvm->arch.vpic);
diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig
index c70e12b..8dab8f7 100644
--- a/arch/x86/lguest/Kconfig
+++ b/arch/x86/lguest/Kconfig
@@ -3,7 +3,6 @@
select PARAVIRT
depends on X86_32
depends on !X86_PAE
- depends on !X86_VOYAGER
select VIRTIO
select VIRTIO_RING
select VIRTIO_CONSOLE
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index ad37400..51f1504 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,7 +28,7 @@
#include <linux/linkage.h>
#include <asm/dwarf2.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
diff --git a/arch/x86/mach-voyager/Makefile b/arch/x86/mach-voyager/Makefile
deleted file mode 100644
index 15c250b..0000000
--- a/arch/x86/mach-voyager/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-EXTRA_CFLAGS := -Iarch/x86/kernel
-obj-y := setup.o voyager_basic.o voyager_thread.o
-
-obj-$(CONFIG_SMP) += voyager_smp.o voyager_cat.o
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
deleted file mode 100644
index 66b7eb5..0000000
--- a/arch/x86/mach-voyager/setup.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * Machine specific setup for generic
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <asm/arch_hooks.h>
-#include <asm/voyager.h>
-#include <asm/e820.h>
-#include <asm/io.h>
-#include <asm/setup.h>
-#include <asm/cpu.h>
-
-void __init pre_intr_init_hook(void)
-{
- init_ISA_irqs();
-}
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
- .handler = no_action,
- .mask = CPU_MASK_NONE,
- .name = "cascade",
-};
-
-void __init intr_init_hook(void)
-{
-#ifdef CONFIG_SMP
- voyager_smp_intr_init();
-#endif
-
- setup_irq(2, &irq2);
-}
-
-static void voyager_disable_tsc(void)
-{
- /* Voyagers run their CPUs from independent clocks, so disable
- * the TSC code because we can't sync them */
- setup_clear_cpu_cap(X86_FEATURE_TSC);
-}
-
-void __init pre_setup_arch_hook(void)
-{
- voyager_disable_tsc();
-}
-
-void __init pre_time_init_hook(void)
-{
- voyager_disable_tsc();
-}
-
-void __init trap_init_hook(void)
-{
-}
-
-static struct irqaction irq0 = {
- .handler = timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
- .mask = CPU_MASK_NONE,
- .name = "timer"
-};
-
-void __init time_init_hook(void)
-{
- irq0.mask = cpumask_of_cpu(safe_smp_processor_id());
- setup_irq(0, &irq0);
-}
-
-/* Hook for machine specific memory setup. */
-
-char *__init machine_specific_memory_setup(void)
-{
- char *who;
- int new_nr;
-
- who = "NOT VOYAGER";
-
- if (voyager_level == 5) {
- __u32 addr, length;
- int i;
-
- who = "Voyager-SUS";
-
- e820.nr_map = 0;
- for (i = 0; voyager_memory_detect(i, &addr, &length); i++) {
- e820_add_region(addr, length, E820_RAM);
- }
- return who;
- } else if (voyager_level == 4) {
- __u32 tom;
- __u16 catbase = inb(VOYAGER_SSPB_RELOCATION_PORT) << 8;
- /* select the DINO config space */
- outb(VOYAGER_DINO, VOYAGER_CAT_CONFIG_PORT);
- /* Read DINO top of memory register */
- tom = ((inb(catbase + 0x4) & 0xf0) << 16)
- + ((inb(catbase + 0x5) & 0x7f) << 24);
-
- if (inb(catbase) != VOYAGER_DINO) {
- printk(KERN_ERR
- "Voyager: Failed to get DINO for L4, setting tom to EXT_MEM_K\n");
- tom = (boot_params.screen_info.ext_mem_k) << 10;
- }
- who = "Voyager-TOM";
- e820_add_region(0, 0x9f000, E820_RAM);
- /* map from 1M to top of memory */
- e820_add_region(1 * 1024 * 1024, tom - 1 * 1024 * 1024,
- E820_RAM);
- /* FIXME: Should check the ASICs to see if I need to
- * take out the 8M window. Just do it at the moment
- * */
- e820_add_region(8 * 1024 * 1024, 8 * 1024 * 1024,
- E820_RESERVED);
- return who;
- }
-
- return default_machine_specific_memory_setup();
-}
diff --git a/arch/x86/mach-voyager/voyager_basic.c b/arch/x86/mach-voyager/voyager_basic.c
deleted file mode 100644
index 46d6f80..0000000
--- a/arch/x86/mach-voyager/voyager_basic.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * This file contains all the voyager specific routines for getting
- * initialisation of the architecture to function. For additional
- * features see:
- *
- * voyager_cat.c - Voyager CAT bus interface
- * voyager_smp.c - Voyager SMP hal (emulates linux smp.c)
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/sysrq.h>
-#include <linux/smp.h>
-#include <linux/nodemask.h>
-#include <asm/io.h>
-#include <asm/voyager.h>
-#include <asm/vic.h>
-#include <linux/pm.h>
-#include <asm/tlbflush.h>
-#include <asm/arch_hooks.h>
-#include <asm/i8253.h>
-
-/*
- * Power off function, if any
- */
-void (*pm_power_off) (void);
-EXPORT_SYMBOL(pm_power_off);
-
-int voyager_level = 0;
-
-struct voyager_SUS *voyager_SUS = NULL;
-
-#ifdef CONFIG_SMP
-static void voyager_dump(int dummy1, struct tty_struct *dummy3)
-{
- /* get here via a sysrq */
- voyager_smp_dump();
-}
-
-static struct sysrq_key_op sysrq_voyager_dump_op = {
- .handler = voyager_dump,
- .help_msg = "Voyager",
- .action_msg = "Dump Voyager Status",
-};
-#endif
-
-void voyager_detect(struct voyager_bios_info *bios)
-{
- if (bios->len != 0xff) {
- int class = (bios->class_1 << 8)
- | (bios->class_2 & 0xff);
-
- printk("Voyager System detected.\n"
- " Class %x, Revision %d.%d\n",
- class, bios->major, bios->minor);
- if (class == VOYAGER_LEVEL4)
- voyager_level = 4;
- else if (class < VOYAGER_LEVEL5_AND_ABOVE)
- voyager_level = 3;
- else
- voyager_level = 5;
- printk(" Architecture Level %d\n", voyager_level);
- if (voyager_level < 4)
- printk
- ("\n**WARNING**: Voyager HAL only supports Levels 4 and 5 Architectures at the moment\n\n");
- /* install the power off handler */
- pm_power_off = voyager_power_off;
-#ifdef CONFIG_SMP
- register_sysrq_key('v', &sysrq_voyager_dump_op);
-#endif
- } else {
- printk("\n\n**WARNING**: No Voyager Subsystem Found\n");
- }
-}
-
-void voyager_system_interrupt(int cpl, void *dev_id)
-{
- printk("Voyager: detected system interrupt\n");
-}
-
-/* Routine to read information from the extended CMOS area */
-__u8 voyager_extended_cmos_read(__u16 addr)
-{
- outb(addr & 0xff, 0x74);
- outb((addr >> 8) & 0xff, 0x75);
- return inb(0x76);
-}
-
-/* internal definitions for the SUS Click Map of memory */
-
-#define CLICK_ENTRIES 16
-#define CLICK_SIZE 4096 /* click to byte conversion for Length */
-
-typedef struct ClickMap {
- struct Entry {
- __u32 Address;
- __u32 Length;
- } Entry[CLICK_ENTRIES];
-} ClickMap_t;
-
-/* This routine is pretty much an awful hack to read the bios clickmap by
- * mapping it into page 0. There are usually three regions in the map:
- * Base Memory
- * Extended Memory
- * zero length marker for end of map
- *
- * Returns are 0 for failure and 1 for success on extracting region.
- */
-int __init voyager_memory_detect(int region, __u32 * start, __u32 * length)
-{
- int i;
- int retval = 0;
- __u8 cmos[4];
- ClickMap_t *map;
- unsigned long map_addr;
- unsigned long old;
-
- if (region >= CLICK_ENTRIES) {
- printk("Voyager: Illegal ClickMap region %d\n", region);
- return 0;
- }
-
- for (i = 0; i < sizeof(cmos); i++)
- cmos[i] =
- voyager_extended_cmos_read(VOYAGER_MEMORY_CLICKMAP + i);
-
- map_addr = *(unsigned long *)cmos;
-
- /* steal page 0 for this */
- old = pg0[0];
- pg0[0] = ((map_addr & PAGE_MASK) | _PAGE_RW | _PAGE_PRESENT);
- local_flush_tlb();
- /* now clear everything out but page 0 */
- map = (ClickMap_t *) (map_addr & (~PAGE_MASK));
-
- /* zero length is the end of the clickmap */
- if (map->Entry[region].Length != 0) {
- *length = map->Entry[region].Length * CLICK_SIZE;
- *start = map->Entry[region].Address;
- retval = 1;
- }
-
- /* replace the mapping */
- pg0[0] = old;
- local_flush_tlb();
- return retval;
-}
-
-/* voyager specific handling code for timer interrupts. Used to hand
- * off the timer tick to the SMP code, since the VIC doesn't have an
- * internal timer (The QIC does, but that's another story). */
-void voyager_timer_interrupt(void)
-{
- if ((jiffies & 0x3ff) == 0) {
-
- /* There seems to be something flaky in either
- * hardware or software that is resetting the timer 0
- * count to something much higher than it should be
- * This seems to occur in the boot sequence, just
- * before root is mounted. Therefore, every 10
- * seconds or so, we sanity check the timer zero count
- * and kick it back to where it should be.
- *
- * FIXME: This is the most awful hack yet seen. I
- * should work out exactly what is interfering with
- * the timer count settings early in the boot sequence
- * and swiftly introduce it to something sharp and
- * pointy. */
- __u16 val;
-
- spin_lock(&i8253_lock);
-
- outb_p(0x00, 0x43);
- val = inb_p(0x40);
- val |= inb(0x40) << 8;
- spin_unlock(&i8253_lock);
-
- if (val > LATCH) {
- printk
- ("\nVOYAGER: countdown timer value too high (%d), resetting\n\n",
- val);
- spin_lock(&i8253_lock);
- outb(0x34, 0x43);
- outb_p(LATCH & 0xff, 0x40); /* LSB */
- outb(LATCH >> 8, 0x40); /* MSB */
- spin_unlock(&i8253_lock);
- }
- }
-#ifdef CONFIG_SMP
- smp_vic_timer_interrupt();
-#endif
-}
-
-void voyager_power_off(void)
-{
- printk("VOYAGER Power Off\n");
-
- if (voyager_level == 5) {
- voyager_cat_power_off();
- } else if (voyager_level == 4) {
- /* This doesn't apparently work on most L4 machines,
- * but the specs say to do this to get automatic power
- * off. Unfortunately, if it doesn't power off the
- * machine, it ends up doing a cold restart, which
- * isn't really intended, so comment out the code */
-#if 0
- int port;
-
- /* enable the voyager Configuration Space */
- outb((inb(VOYAGER_MC_SETUP) & 0xf0) | 0x8, VOYAGER_MC_SETUP);
- /* the port for the power off flag is an offset from the
- floating base */
- port = (inb(VOYAGER_SSPB_RELOCATION_PORT) << 8) + 0x21;
- /* set the power off flag */
- outb(inb(port) | 0x1, port);
-#endif
- }
- /* and wait for it to happen */
- local_irq_disable();
- for (;;)
- halt();
-}
-
-/* copied from process.c */
-static inline void kb_wait(void)
-{
- int i;
-
- for (i = 0; i < 0x10000; i++)
- if ((inb_p(0x64) & 0x02) == 0)
- break;
-}
-
-void machine_shutdown(void)
-{
- /* Architecture specific shutdown needed before a kexec */
-}
-
-void machine_restart(char *cmd)
-{
- printk("Voyager Warm Restart\n");
- kb_wait();
-
- if (voyager_level == 5) {
- /* write magic values to the RTC to inform system that
- * shutdown is beginning */
- outb(0x8f, 0x70);
- outb(0x5, 0x71);
-
- udelay(50);
- outb(0xfe, 0x64); /* pull reset low */
- } else if (voyager_level == 4) {
- __u16 catbase = inb(VOYAGER_SSPB_RELOCATION_PORT) << 8;
- __u8 basebd = inb(VOYAGER_MC_SETUP);
-
- outb(basebd | 0x08, VOYAGER_MC_SETUP);
- outb(0x02, catbase + 0x21);
- }
- local_irq_disable();
- for (;;)
- halt();
-}
-
-void machine_emergency_restart(void)
-{
- /*for now, just hook this to a warm restart */
- machine_restart(NULL);
-}
-
-void mca_nmi_hook(void)
-{
- __u8 dumpval __maybe_unused = inb(0xf823);
- __u8 swnmi __maybe_unused = inb(0xf813);
-
- /* FIXME: assume dump switch pressed */
- /* check to see if the dump switch was pressed */
- VDEBUG(("VOYAGER: dumpval = 0x%x, swnmi = 0x%x\n", dumpval, swnmi));
- /* clear swnmi */
- outb(0xff, 0xf813);
- /* tell SUS to ignore dump */
- if (voyager_level == 5 && voyager_SUS != NULL) {
- if (voyager_SUS->SUS_mbox == VOYAGER_DUMP_BUTTON_NMI) {
- voyager_SUS->kernel_mbox = VOYAGER_NO_COMMAND;
- voyager_SUS->kernel_flags |= VOYAGER_OS_IN_PROGRESS;
- udelay(1000);
- voyager_SUS->kernel_mbox = VOYAGER_IGNORE_DUMP;
- voyager_SUS->kernel_flags &= ~VOYAGER_OS_IN_PROGRESS;
- }
- }
- printk(KERN_ERR
- "VOYAGER: Dump switch pressed, printing CPU%d tracebacks\n",
- smp_processor_id());
- show_stack(NULL, NULL);
- show_state();
-}
-
-void machine_halt(void)
-{
- /* treat a halt like a power off */
- machine_power_off();
-}
-
-void machine_power_off(void)
-{
- if (pm_power_off)
- pm_power_off();
-}
diff --git a/arch/x86/mach-voyager/voyager_cat.c b/arch/x86/mach-voyager/voyager_cat.c
deleted file mode 100644
index 2ad598c..0000000
--- a/arch/x86/mach-voyager/voyager_cat.c
+++ /dev/null
@@ -1,1197 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * This file contains all the logic for manipulating the CAT bus
- * in a level 5 machine.
- *
- * The CAT bus is a serial configuration and test bus. Its primary
- * uses are to probe the initial configuration of the system and to
- * diagnose error conditions when a system interrupt occurs. The low
- * level interface is fairly primitive, so most of this file consists
- * of bit shift manipulations to send and receive packets on the
- * serial bus */
-
-#include <linux/types.h>
-#include <linux/completion.h>
-#include <linux/sched.h>
-#include <asm/voyager.h>
-#include <asm/vic.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <asm/io.h>
-
-#ifdef VOYAGER_CAT_DEBUG
-#define CDEBUG(x) printk x
-#else
-#define CDEBUG(x)
-#endif
-
-/* the CAT command port */
-#define CAT_CMD (sspb + 0xe)
-/* the CAT data port */
-#define CAT_DATA (sspb + 0xd)
-
-/* the internal cat functions */
-static void cat_pack(__u8 * msg, __u16 start_bit, __u8 * data, __u16 num_bits);
-static void cat_unpack(__u8 * msg, __u16 start_bit, __u8 * data,
- __u16 num_bits);
-static void cat_build_header(__u8 * header, const __u16 len,
- const __u16 smallest_reg_bits,
- const __u16 longest_reg_bits);
-static int cat_sendinst(voyager_module_t * modp, voyager_asic_t * asicp,
- __u8 reg, __u8 op);
-static int cat_getdata(voyager_module_t * modp, voyager_asic_t * asicp,
- __u8 reg, __u8 * value);
-static int cat_shiftout(__u8 * data, __u16 data_bytes, __u16 header_bytes,
- __u8 pad_bits);
-static int cat_write(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg,
- __u8 value);
-static int cat_read(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg,
- __u8 * value);
-static int cat_subread(voyager_module_t * modp, voyager_asic_t * asicp,
- __u16 offset, __u16 len, void *buf);
-static int cat_senddata(voyager_module_t * modp, voyager_asic_t * asicp,
- __u8 reg, __u8 value);
-static int cat_disconnect(voyager_module_t * modp, voyager_asic_t * asicp);
-static int cat_connect(voyager_module_t * modp, voyager_asic_t * asicp);
-
-static inline const char *cat_module_name(int module_id)
-{
- switch (module_id) {
- case 0x10:
- return "Processor Slot 0";
- case 0x11:
- return "Processor Slot 1";
- case 0x12:
- return "Processor Slot 2";
- case 0x13:
- return "Processor Slot 4";
- case 0x14:
- return "Memory Slot 0";
- case 0x15:
- return "Memory Slot 1";
- case 0x18:
- return "Primary Microchannel";
- case 0x19:
- return "Secondary Microchannel";
- case 0x1a:
- return "Power Supply Interface";
- case 0x1c:
- return "Processor Slot 5";
- case 0x1d:
- return "Processor Slot 6";
- case 0x1e:
- return "Processor Slot 7";
- case 0x1f:
- return "Processor Slot 8";
- default:
- return "Unknown Module";
- }
-}
-
-static int sspb = 0; /* stores the super port location */
-int voyager_8slot = 0; /* set to true if a 51xx monster */
-
-voyager_module_t *voyager_cat_list;
-
-/* the I/O port assignments for the VIC and QIC */
-static struct resource vic_res = {
- .name = "Voyager Interrupt Controller",
- .start = 0xFC00,
- .end = 0xFC6F
-};
-static struct resource qic_res = {
- .name = "Quad Interrupt Controller",
- .start = 0xFC70,
- .end = 0xFCFF
-};
-
-/* This function is used to pack a data bit stream inside a message.
- * It writes num_bits of the data buffer in msg starting at start_bit.
- * Note: This function assumes that any unused bit in the data stream
- * is set to zero so that the ors will work correctly */
-static void
-cat_pack(__u8 * msg, const __u16 start_bit, __u8 * data, const __u16 num_bits)
-{
- /* compute initial shift needed */
- const __u16 offset = start_bit % BITS_PER_BYTE;
- __u16 len = num_bits / BITS_PER_BYTE;
- __u16 byte = start_bit / BITS_PER_BYTE;
- __u16 residue = (num_bits % BITS_PER_BYTE) + offset;
- int i;
-
- /* adjust if we have more than a byte of residue */
- if (residue >= BITS_PER_BYTE) {
- residue -= BITS_PER_BYTE;
- len++;
- }
-
- /* clear out the bits. We assume here that if len==0 then
- * residue >= offset. This is always true for the catbus
- * operations */
- msg[byte] &= 0xff << (BITS_PER_BYTE - offset);
- msg[byte++] |= data[0] >> offset;
- if (len == 0)
- return;
- for (i = 1; i < len; i++)
- msg[byte++] = (data[i - 1] << (BITS_PER_BYTE - offset))
- | (data[i] >> offset);
- if (residue != 0) {
- __u8 mask = 0xff >> residue;
- __u8 last_byte = data[i - 1] << (BITS_PER_BYTE - offset)
- | (data[i] >> offset);
-
- last_byte &= ~mask;
- msg[byte] &= mask;
- msg[byte] |= last_byte;
- }
- return;
-}
-
-/* unpack the data again (same arguments as cat_pack()). data buffer
- * must be zero populated.
- *
- * Function: given a message string move to start_bit and copy num_bits into
- * data (starting at bit 0 in data).
- */
-static void
-cat_unpack(__u8 * msg, const __u16 start_bit, __u8 * data, const __u16 num_bits)
-{
- /* compute initial shift needed */
- const __u16 offset = start_bit % BITS_PER_BYTE;
- __u16 len = num_bits / BITS_PER_BYTE;
- const __u8 last_bits = num_bits % BITS_PER_BYTE;
- __u16 byte = start_bit / BITS_PER_BYTE;
- int i;
-
- if (last_bits != 0)
- len++;
-
- /* special case: want < 8 bits from msg and we can get it from
- * a single byte of the msg */
- if (len == 0 && BITS_PER_BYTE - offset >= num_bits) {
- data[0] = msg[byte] << offset;
- data[0] &= 0xff >> (BITS_PER_BYTE - num_bits);
- return;
- }
- for (i = 0; i < len; i++) {
- /* this annoying if has to be done just in case a read of
- * msg one beyond the array causes a panic */
- if (offset != 0) {
- data[i] = msg[byte++] << offset;
- data[i] |= msg[byte] >> (BITS_PER_BYTE - offset);
- } else {
- data[i] = msg[byte++];
- }
- }
- /* do we need to truncate the final byte */
- if (last_bits != 0) {
- data[i - 1] &= 0xff << (BITS_PER_BYTE - last_bits);
- }
- return;
-}
-
-static void
-cat_build_header(__u8 * header, const __u16 len, const __u16 smallest_reg_bits,
- const __u16 longest_reg_bits)
-{
- int i;
- __u16 start_bit = (smallest_reg_bits - 1) % BITS_PER_BYTE;
- __u8 *last_byte = &header[len - 1];
-
- if (start_bit == 0)
- start_bit = 1; /* must have at least one bit in the hdr */
-
- for (i = 0; i < len; i++)
- header[i] = 0;
-
- for (i = start_bit; i > 0; i--)
- *last_byte = ((*last_byte) << 1) + 1;
-
-}
-
-static int
-cat_sendinst(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg, __u8 op)
-{
- __u8 parity, inst, inst_buf[4] = { 0 };
- __u8 iseq[VOYAGER_MAX_SCAN_PATH], hseq[VOYAGER_MAX_REG_SIZE];
- __u16 ibytes, hbytes, padbits;
- int i;
-
- /*
- * Parity is the parity of the register number + 1 (READ_REGISTER
- * and WRITE_REGISTER always add '1' to the number of bits == 1)
- */
- parity = (__u8) (1 + (reg & 0x01) +
- ((__u8) (reg & 0x02) >> 1) +
- ((__u8) (reg & 0x04) >> 2) +
- ((__u8) (reg & 0x08) >> 3)) % 2;
-
- inst = ((parity << 7) | (reg << 2) | op);
-
- outb(VOYAGER_CAT_IRCYC, CAT_CMD);
- if (!modp->scan_path_connected) {
- if (asicp->asic_id != VOYAGER_CAT_ID) {
- printk
- ("**WARNING***: cat_sendinst has disconnected scan path not to CAT asic\n");
- return 1;
- }
- outb(VOYAGER_CAT_HEADER, CAT_DATA);
- outb(inst, CAT_DATA);
- if (inb(CAT_DATA) != VOYAGER_CAT_HEADER) {
- CDEBUG(("VOYAGER CAT: cat_sendinst failed to get CAT_HEADER\n"));
- return 1;
- }
- return 0;
- }
- ibytes = modp->inst_bits / BITS_PER_BYTE;
- if ((padbits = modp->inst_bits % BITS_PER_BYTE) != 0) {
- padbits = BITS_PER_BYTE - padbits;
- ibytes++;
- }
- hbytes = modp->largest_reg / BITS_PER_BYTE;
- if (modp->largest_reg % BITS_PER_BYTE)
- hbytes++;
- CDEBUG(("cat_sendinst: ibytes=%d, hbytes=%d\n", ibytes, hbytes));
- /* initialise the instruction sequence to 0xff */
- for (i = 0; i < ibytes + hbytes; i++)
- iseq[i] = 0xff;
- cat_build_header(hseq, hbytes, modp->smallest_reg, modp->largest_reg);
- cat_pack(iseq, modp->inst_bits, hseq, hbytes * BITS_PER_BYTE);
- inst_buf[0] = inst;
- inst_buf[1] = 0xFF >> (modp->largest_reg % BITS_PER_BYTE);
- cat_pack(iseq, asicp->bit_location, inst_buf, asicp->ireg_length);
-#ifdef VOYAGER_CAT_DEBUG
- printk("ins = 0x%x, iseq: ", inst);
- for (i = 0; i < ibytes + hbytes; i++)
- printk("0x%x ", iseq[i]);
- printk("\n");
-#endif
- if (cat_shiftout(iseq, ibytes, hbytes, padbits)) {
- CDEBUG(("VOYAGER CAT: cat_sendinst: cat_shiftout failed\n"));
- return 1;
- }
- CDEBUG(("CAT SHIFTOUT DONE\n"));
- return 0;
-}
-
-static int
-cat_getdata(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg,
- __u8 * value)
-{
- if (!modp->scan_path_connected) {
- if (asicp->asic_id != VOYAGER_CAT_ID) {
- CDEBUG(("VOYAGER CAT: ERROR: cat_getdata to CAT asic with scan path connected\n"));
- return 1;
- }
- if (reg > VOYAGER_SUBADDRHI)
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- outb(VOYAGER_CAT_DRCYC, CAT_CMD);
- outb(VOYAGER_CAT_HEADER, CAT_DATA);
- *value = inb(CAT_DATA);
- outb(0xAA, CAT_DATA);
- if (inb(CAT_DATA) != VOYAGER_CAT_HEADER) {
- CDEBUG(("cat_getdata: failed to get VOYAGER_CAT_HEADER\n"));
- return 1;
- }
- return 0;
- } else {
- __u16 sbits = modp->num_asics - 1 + asicp->ireg_length;
- __u16 sbytes = sbits / BITS_PER_BYTE;
- __u16 tbytes;
- __u8 string[VOYAGER_MAX_SCAN_PATH],
- trailer[VOYAGER_MAX_REG_SIZE];
- __u8 padbits;
- int i;
-
- outb(VOYAGER_CAT_DRCYC, CAT_CMD);
-
- if ((padbits = sbits % BITS_PER_BYTE) != 0) {
- padbits = BITS_PER_BYTE - padbits;
- sbytes++;
- }
- tbytes = asicp->ireg_length / BITS_PER_BYTE;
- if (asicp->ireg_length % BITS_PER_BYTE)
- tbytes++;
- CDEBUG(("cat_getdata: tbytes = %d, sbytes = %d, padbits = %d\n",
- tbytes, sbytes, padbits));
- cat_build_header(trailer, tbytes, 1, asicp->ireg_length);
-
- for (i = tbytes - 1; i >= 0; i--) {
- outb(trailer[i], CAT_DATA);
- string[sbytes + i] = inb(CAT_DATA);
- }
-
- for (i = sbytes - 1; i >= 0; i--) {
- outb(0xaa, CAT_DATA);
- string[i] = inb(CAT_DATA);
- }
- *value = 0;
- cat_unpack(string,
- padbits + (tbytes * BITS_PER_BYTE) +
- asicp->asic_location, value, asicp->ireg_length);
-#ifdef VOYAGER_CAT_DEBUG
- printk("value=0x%x, string: ", *value);
- for (i = 0; i < tbytes + sbytes; i++)
- printk("0x%x ", string[i]);
- printk("\n");
-#endif
-
- /* sanity check the rest of the return */
- for (i = 0; i < tbytes; i++) {
- __u8 input = 0;
-
- cat_unpack(string, padbits + (i * BITS_PER_BYTE),
- &input, BITS_PER_BYTE);
- if (trailer[i] != input) {
- CDEBUG(("cat_getdata: failed to sanity check rest of ret(%d) 0x%x != 0x%x\n", i, input, trailer[i]));
- return 1;
- }
- }
- CDEBUG(("cat_getdata DONE\n"));
- return 0;
- }
-}
-
-static int
-cat_shiftout(__u8 * data, __u16 data_bytes, __u16 header_bytes, __u8 pad_bits)
-{
- int i;
-
- for (i = data_bytes + header_bytes - 1; i >= header_bytes; i--)
- outb(data[i], CAT_DATA);
-
- for (i = header_bytes - 1; i >= 0; i--) {
- __u8 header = 0;
- __u8 input;
-
- outb(data[i], CAT_DATA);
- input = inb(CAT_DATA);
- CDEBUG(("cat_shiftout: returned 0x%x\n", input));
- cat_unpack(data, ((data_bytes + i) * BITS_PER_BYTE) - pad_bits,
- &header, BITS_PER_BYTE);
- if (input != header) {
- CDEBUG(("VOYAGER CAT: cat_shiftout failed to return header 0x%x != 0x%x\n", input, header));
- return 1;
- }
- }
- return 0;
-}
-
-static int
-cat_senddata(voyager_module_t * modp, voyager_asic_t * asicp,
- __u8 reg, __u8 value)
-{
- outb(VOYAGER_CAT_DRCYC, CAT_CMD);
- if (!modp->scan_path_connected) {
- if (asicp->asic_id != VOYAGER_CAT_ID) {
- CDEBUG(("VOYAGER CAT: ERROR: scan path disconnected when asic != CAT\n"));
- return 1;
- }
- outb(VOYAGER_CAT_HEADER, CAT_DATA);
- outb(value, CAT_DATA);
- if (inb(CAT_DATA) != VOYAGER_CAT_HEADER) {
- CDEBUG(("cat_senddata: failed to get correct header response to sent data\n"));
- return 1;
- }
- if (reg > VOYAGER_SUBADDRHI) {
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- outb(VOYAGER_CAT_END, CAT_CMD);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- }
-
- return 0;
- } else {
- __u16 hbytes = asicp->ireg_length / BITS_PER_BYTE;
- __u16 dbytes =
- (modp->num_asics - 1 + asicp->ireg_length) / BITS_PER_BYTE;
- __u8 padbits, dseq[VOYAGER_MAX_SCAN_PATH],
- hseq[VOYAGER_MAX_REG_SIZE];
- int i;
-
- if ((padbits = (modp->num_asics - 1
- + asicp->ireg_length) % BITS_PER_BYTE) != 0) {
- padbits = BITS_PER_BYTE - padbits;
- dbytes++;
- }
- if (asicp->ireg_length % BITS_PER_BYTE)
- hbytes++;
-
- cat_build_header(hseq, hbytes, 1, asicp->ireg_length);
-
- for (i = 0; i < dbytes + hbytes; i++)
- dseq[i] = 0xff;
- CDEBUG(("cat_senddata: dbytes=%d, hbytes=%d, padbits=%d\n",
- dbytes, hbytes, padbits));
- cat_pack(dseq, modp->num_asics - 1 + asicp->ireg_length,
- hseq, hbytes * BITS_PER_BYTE);
- cat_pack(dseq, asicp->asic_location, &value,
- asicp->ireg_length);
-#ifdef VOYAGER_CAT_DEBUG
- printk("dseq ");
- for (i = 0; i < hbytes + dbytes; i++) {
- printk("0x%x ", dseq[i]);
- }
- printk("\n");
-#endif
- return cat_shiftout(dseq, dbytes, hbytes, padbits);
- }
-}
-
-static int
-cat_write(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg, __u8 value)
-{
- if (cat_sendinst(modp, asicp, reg, VOYAGER_WRITE_CONFIG))
- return 1;
- return cat_senddata(modp, asicp, reg, value);
-}
-
-static int
-cat_read(voyager_module_t * modp, voyager_asic_t * asicp, __u8 reg,
- __u8 * value)
-{
- if (cat_sendinst(modp, asicp, reg, VOYAGER_READ_CONFIG))
- return 1;
- return cat_getdata(modp, asicp, reg, value);
-}
-
-static int
-cat_subaddrsetup(voyager_module_t * modp, voyager_asic_t * asicp, __u16 offset,
- __u16 len)
-{
- __u8 val;
-
- if (len > 1) {
- /* set auto increment */
- __u8 newval;
-
- if (cat_read(modp, asicp, VOYAGER_AUTO_INC_REG, &val)) {
- CDEBUG(("cat_subaddrsetup: read of VOYAGER_AUTO_INC_REG failed\n"));
- return 1;
- }
- CDEBUG(("cat_subaddrsetup: VOYAGER_AUTO_INC_REG = 0x%x\n",
- val));
- newval = val | VOYAGER_AUTO_INC;
- if (newval != val) {
- if (cat_write(modp, asicp, VOYAGER_AUTO_INC_REG, val)) {
- CDEBUG(("cat_subaddrsetup: write to VOYAGER_AUTO_INC_REG failed\n"));
- return 1;
- }
- }
- }
- if (cat_write(modp, asicp, VOYAGER_SUBADDRLO, (__u8) (offset & 0xff))) {
- CDEBUG(("cat_subaddrsetup: write to SUBADDRLO failed\n"));
- return 1;
- }
- if (asicp->subaddr > VOYAGER_SUBADDR_LO) {
- if (cat_write
- (modp, asicp, VOYAGER_SUBADDRHI, (__u8) (offset >> 8))) {
- CDEBUG(("cat_subaddrsetup: write to SUBADDRHI failed\n"));
- return 1;
- }
- cat_read(modp, asicp, VOYAGER_SUBADDRHI, &val);
- CDEBUG(("cat_subaddrsetup: offset = %d, hi = %d\n", offset,
- val));
- }
- cat_read(modp, asicp, VOYAGER_SUBADDRLO, &val);
- CDEBUG(("cat_subaddrsetup: offset = %d, lo = %d\n", offset, val));
- return 0;
-}
-
-static int
-cat_subwrite(voyager_module_t * modp, voyager_asic_t * asicp, __u16 offset,
- __u16 len, void *buf)
-{
- int i, retval;
-
- /* FIXME: need special actions for VOYAGER_CAT_ID here */
- if (asicp->asic_id == VOYAGER_CAT_ID) {
- CDEBUG(("cat_subwrite: ATTEMPT TO WRITE TO CAT ASIC\n"));
- /* FIXME -- This is supposed to be handled better
- * There is a problem writing to the cat asic in the
- * PSI. The 30us delay seems to work, though */
- udelay(30);
- }
-
- if ((retval = cat_subaddrsetup(modp, asicp, offset, len)) != 0) {
- printk("cat_subwrite: cat_subaddrsetup FAILED\n");
- return retval;
- }
-
- if (cat_sendinst
- (modp, asicp, VOYAGER_SUBADDRDATA, VOYAGER_WRITE_CONFIG)) {
- printk("cat_subwrite: cat_sendinst FAILED\n");
- return 1;
- }
- for (i = 0; i < len; i++) {
- if (cat_senddata(modp, asicp, 0xFF, ((__u8 *) buf)[i])) {
- printk
- ("cat_subwrite: cat_sendata element at %d FAILED\n",
- i);
- return 1;
- }
- }
- return 0;
-}
-static int
-cat_subread(voyager_module_t * modp, voyager_asic_t * asicp, __u16 offset,
- __u16 len, void *buf)
-{
- int i, retval;
-
- if ((retval = cat_subaddrsetup(modp, asicp, offset, len)) != 0) {
- CDEBUG(("cat_subread: cat_subaddrsetup FAILED\n"));
- return retval;
- }
-
- if (cat_sendinst(modp, asicp, VOYAGER_SUBADDRDATA, VOYAGER_READ_CONFIG)) {
- CDEBUG(("cat_subread: cat_sendinst failed\n"));
- return 1;
- }
- for (i = 0; i < len; i++) {
- if (cat_getdata(modp, asicp, 0xFF, &((__u8 *) buf)[i])) {
- CDEBUG(("cat_subread: cat_getdata element %d failed\n",
- i));
- return 1;
- }
- }
- return 0;
-}
-
-/* buffer for storing EPROM data read in during initialisation */
-static __initdata __u8 eprom_buf[0xFFFF];
-static voyager_module_t *voyager_initial_module;
-
-/* Initialise the cat bus components. We assume this is called by the
- * boot cpu *after* all memory initialisation has been done (so we can
- * use kmalloc) but before smp initialisation, so we can probe the SMP
- * configuration and pick up necessary information. */
-void __init voyager_cat_init(void)
-{
- voyager_module_t **modpp = &voyager_initial_module;
- voyager_asic_t **asicpp;
- voyager_asic_t *qabc_asic = NULL;
- int i, j;
- unsigned long qic_addr = 0;
- __u8 qabc_data[0x20];
- __u8 num_submodules, val;
- voyager_eprom_hdr_t *eprom_hdr = (voyager_eprom_hdr_t *) & eprom_buf[0];
-
- __u8 cmos[4];
- unsigned long addr;
-
- /* initiallise the SUS mailbox */
- for (i = 0; i < sizeof(cmos); i++)
- cmos[i] = voyager_extended_cmos_read(VOYAGER_DUMP_LOCATION + i);
- addr = *(unsigned long *)cmos;
- if ((addr & 0xff000000) != 0xff000000) {
- printk(KERN_ERR
- "Voyager failed to get SUS mailbox (addr = 0x%lx\n",
- addr);
- } else {
- static struct resource res;
-
- res.name = "voyager SUS";
- res.start = addr;
- res.end = addr + 0x3ff;
-
- request_resource(&iomem_resource, &res);
- voyager_SUS = (struct voyager_SUS *)
- ioremap(addr, 0x400);
- printk(KERN_NOTICE "Voyager SUS mailbox version 0x%x\n",
- voyager_SUS->SUS_version);
- voyager_SUS->kernel_version = VOYAGER_MAILBOX_VERSION;
- voyager_SUS->kernel_flags = VOYAGER_OS_HAS_SYSINT;
- }
-
- /* clear the processor counts */
- voyager_extended_vic_processors = 0;
- voyager_quad_processors = 0;
-
- printk("VOYAGER: beginning CAT bus probe\n");
- /* set up the SuperSet Port Block which tells us where the
- * CAT communication port is */
- sspb = inb(VOYAGER_SSPB_RELOCATION_PORT) * 0x100;
- VDEBUG(("VOYAGER DEBUG: sspb = 0x%x\n", sspb));
-
- /* now find out if were 8 slot or normal */
- if ((inb(VIC_PROC_WHO_AM_I) & EIGHT_SLOT_IDENTIFIER)
- == EIGHT_SLOT_IDENTIFIER) {
- voyager_8slot = 1;
- printk(KERN_NOTICE
- "Voyager: Eight slot 51xx configuration detected\n");
- }
-
- for (i = VOYAGER_MIN_MODULE; i <= VOYAGER_MAX_MODULE; i++) {
- __u8 input;
- int asic;
- __u16 eprom_size;
- __u16 sp_offset;
-
- outb(VOYAGER_CAT_DESELECT, VOYAGER_CAT_CONFIG_PORT);
- outb(i, VOYAGER_CAT_CONFIG_PORT);
-
- /* check the presence of the module */
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- outb(VOYAGER_CAT_IRCYC, CAT_CMD);
- outb(VOYAGER_CAT_HEADER, CAT_DATA);
- /* stream series of alternating 1's and 0's to stimulate
- * response */
- outb(0xAA, CAT_DATA);
- input = inb(CAT_DATA);
- outb(VOYAGER_CAT_END, CAT_CMD);
- if (input != VOYAGER_CAT_HEADER) {
- continue;
- }
- CDEBUG(("VOYAGER DEBUG: found module id 0x%x, %s\n", i,
- cat_module_name(i)));
- *modpp = kmalloc(sizeof(voyager_module_t), GFP_KERNEL); /*&voyager_module_storage[cat_count++]; */
- if (*modpp == NULL) {
- printk("**WARNING** kmalloc failure in cat_init\n");
- continue;
- }
- memset(*modpp, 0, sizeof(voyager_module_t));
- /* need temporary asic for cat_subread. It will be
- * filled in correctly later */
- (*modpp)->asic = kmalloc(sizeof(voyager_asic_t), GFP_KERNEL); /*&voyager_asic_storage[asic_count]; */
- if ((*modpp)->asic == NULL) {
- printk("**WARNING** kmalloc failure in cat_init\n");
- continue;
- }
- memset((*modpp)->asic, 0, sizeof(voyager_asic_t));
- (*modpp)->asic->asic_id = VOYAGER_CAT_ID;
- (*modpp)->asic->subaddr = VOYAGER_SUBADDR_HI;
- (*modpp)->module_addr = i;
- (*modpp)->scan_path_connected = 0;
- if (i == VOYAGER_PSI) {
- /* Exception leg for modules with no EEPROM */
- printk("Module \"%s\"\n", cat_module_name(i));
- continue;
- }
-
- CDEBUG(("cat_init: Reading eeprom for module 0x%x at offset %d\n", i, VOYAGER_XSUM_END_OFFSET));
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_disconnect(*modpp, (*modpp)->asic);
- if (cat_subread(*modpp, (*modpp)->asic,
- VOYAGER_XSUM_END_OFFSET, sizeof(eprom_size),
- &eprom_size)) {
- printk
- ("**WARNING**: Voyager couldn't read EPROM size for module 0x%x\n",
- i);
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- if (eprom_size > sizeof(eprom_buf)) {
- printk
- ("**WARNING**: Voyager insufficient size to read EPROM data, module 0x%x. Need %d\n",
- i, eprom_size);
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- CDEBUG(("cat_init: module 0x%x, eeprom_size %d\n", i,
- eprom_size));
- if (cat_subread
- (*modpp, (*modpp)->asic, 0, eprom_size, eprom_buf)) {
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- printk("Module \"%s\", version 0x%x, tracer 0x%x, asics %d\n",
- cat_module_name(i), eprom_hdr->version_id,
- *((__u32 *) eprom_hdr->tracer), eprom_hdr->num_asics);
- (*modpp)->ee_size = eprom_hdr->ee_size;
- (*modpp)->num_asics = eprom_hdr->num_asics;
- asicpp = &((*modpp)->asic);
- sp_offset = eprom_hdr->scan_path_offset;
- /* All we really care about are the Quad cards. We
- * identify them because they are in a processor slot
- * and have only four asics */
- if ((i < 0x10 || (i >= 0x14 && i < 0x1c) || i > 0x1f)) {
- modpp = &((*modpp)->next);
- continue;
- }
- /* Now we know it's in a processor slot, does it have
- * a quad baseboard submodule */
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_read(*modpp, (*modpp)->asic, VOYAGER_SUBMODPRESENT,
- &num_submodules);
- /* lowest two bits, active low */
- num_submodules = ~(0xfc | num_submodules);
- CDEBUG(("VOYAGER CAT: %d submodules present\n",
- num_submodules));
- if (num_submodules == 0) {
- /* fill in the dyadic extended processors */
- __u8 cpu = i & 0x07;
-
- printk("Module \"%s\": Dyadic Processor Card\n",
- cat_module_name(i));
- voyager_extended_vic_processors |= (1 << cpu);
- cpu += 4;
- voyager_extended_vic_processors |= (1 << cpu);
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
-
- /* now we want to read the asics on the first submodule,
- * which should be the quad base board */
-
- cat_read(*modpp, (*modpp)->asic, VOYAGER_SUBMODSELECT, &val);
- CDEBUG(("cat_init: SUBMODSELECT value = 0x%x\n", val));
- val = (val & 0x7c) | VOYAGER_QUAD_BASEBOARD;
- cat_write(*modpp, (*modpp)->asic, VOYAGER_SUBMODSELECT, val);
-
- outb(VOYAGER_CAT_END, CAT_CMD);
-
- CDEBUG(("cat_init: Reading eeprom for module 0x%x at offset %d\n", i, VOYAGER_XSUM_END_OFFSET));
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_disconnect(*modpp, (*modpp)->asic);
- if (cat_subread(*modpp, (*modpp)->asic,
- VOYAGER_XSUM_END_OFFSET, sizeof(eprom_size),
- &eprom_size)) {
- printk
- ("**WARNING**: Voyager couldn't read EPROM size for module 0x%x\n",
- i);
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- if (eprom_size > sizeof(eprom_buf)) {
- printk
- ("**WARNING**: Voyager insufficient size to read EPROM data, module 0x%x. Need %d\n",
- i, eprom_size);
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- CDEBUG(("cat_init: module 0x%x, eeprom_size %d\n", i,
- eprom_size));
- if (cat_subread
- (*modpp, (*modpp)->asic, 0, eprom_size, eprom_buf)) {
- outb(VOYAGER_CAT_END, CAT_CMD);
- continue;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- /* Now do everything for the QBB submodule 1 */
- (*modpp)->ee_size = eprom_hdr->ee_size;
- (*modpp)->num_asics = eprom_hdr->num_asics;
- asicpp = &((*modpp)->asic);
- sp_offset = eprom_hdr->scan_path_offset;
- /* get rid of the dummy CAT asic and read the real one */
- kfree((*modpp)->asic);
- for (asic = 0; asic < (*modpp)->num_asics; asic++) {
- int j;
- voyager_asic_t *asicp = *asicpp = kzalloc(sizeof(voyager_asic_t), GFP_KERNEL); /*&voyager_asic_storage[asic_count++]; */
- voyager_sp_table_t *sp_table;
- voyager_at_t *asic_table;
- voyager_jtt_t *jtag_table;
-
- if (asicp == NULL) {
- printk
- ("**WARNING** kmalloc failure in cat_init\n");
- continue;
- }
- asicpp = &(asicp->next);
- asicp->asic_location = asic;
- sp_table =
- (voyager_sp_table_t *) (eprom_buf + sp_offset);
- asicp->asic_id = sp_table->asic_id;
- asic_table =
- (voyager_at_t *) (eprom_buf +
- sp_table->asic_data_offset);
- for (j = 0; j < 4; j++)
- asicp->jtag_id[j] = asic_table->jtag_id[j];
- jtag_table =
- (voyager_jtt_t *) (eprom_buf +
- asic_table->jtag_offset);
- asicp->ireg_length = jtag_table->ireg_len;
- asicp->bit_location = (*modpp)->inst_bits;
- (*modpp)->inst_bits += asicp->ireg_length;
- if (asicp->ireg_length > (*modpp)->largest_reg)
- (*modpp)->largest_reg = asicp->ireg_length;
- if (asicp->ireg_length < (*modpp)->smallest_reg ||
- (*modpp)->smallest_reg == 0)
- (*modpp)->smallest_reg = asicp->ireg_length;
- CDEBUG(("asic 0x%x, ireg_length=%d, bit_location=%d\n",
- asicp->asic_id, asicp->ireg_length,
- asicp->bit_location));
- if (asicp->asic_id == VOYAGER_QUAD_QABC) {
- CDEBUG(("VOYAGER CAT: QABC ASIC found\n"));
- qabc_asic = asicp;
- }
- sp_offset += sizeof(voyager_sp_table_t);
- }
- CDEBUG(("Module inst_bits = %d, largest_reg = %d, smallest_reg=%d\n", (*modpp)->inst_bits, (*modpp)->largest_reg, (*modpp)->smallest_reg));
- /* OK, now we have the QUAD ASICs set up, use them.
- * we need to:
- *
- * 1. Find the Memory area for the Quad CPIs.
- * 2. Find the Extended VIC processor
- * 3. Configure a second extended VIC processor (This
- * cannot be done for the 51xx.
- * */
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_connect(*modpp, (*modpp)->asic);
- CDEBUG(("CAT CONNECTED!!\n"));
- cat_subread(*modpp, qabc_asic, 0, sizeof(qabc_data), qabc_data);
- qic_addr = qabc_data[5] << 8;
- qic_addr = (qic_addr | qabc_data[6]) << 8;
- qic_addr = (qic_addr | qabc_data[7]) << 8;
- printk
- ("Module \"%s\": Quad Processor Card; CPI 0x%lx, SET=0x%x\n",
- cat_module_name(i), qic_addr, qabc_data[8]);
-#if 0 /* plumbing fails---FIXME */
- if ((qabc_data[8] & 0xf0) == 0) {
- /* FIXME: 32 way 8 CPU slot monster cannot be
- * plumbed this way---need to check for it */
-
- printk("Plumbing second Extended Quad Processor\n");
- /* second VIC line hardwired to Quad CPU 1 */
- qabc_data[8] |= 0x20;
- cat_subwrite(*modpp, qabc_asic, 8, 1, &qabc_data[8]);
-#ifdef VOYAGER_CAT_DEBUG
- /* verify plumbing */
- cat_subread(*modpp, qabc_asic, 8, 1, &qabc_data[8]);
- if ((qabc_data[8] & 0xf0) == 0) {
- CDEBUG(("PLUMBING FAILED: 0x%x\n",
- qabc_data[8]));
- }
-#endif
- }
-#endif
-
- {
- struct resource *res =
- kzalloc(sizeof(struct resource), GFP_KERNEL);
- res->name = kmalloc(128, GFP_KERNEL);
- sprintf((char *)res->name, "Voyager %s Quad CPI",
- cat_module_name(i));
- res->start = qic_addr;
- res->end = qic_addr + 0x3ff;
- request_resource(&iomem_resource, res);
- }
-
- qic_addr = (unsigned long)ioremap_cache(qic_addr, 0x400);
-
- for (j = 0; j < 4; j++) {
- __u8 cpu;
-
- if (voyager_8slot) {
- /* 8 slot has a different mapping,
- * each slot has only one vic line, so
- * 1 cpu in each slot must be < 8 */
- cpu = (i & 0x07) + j * 8;
- } else {
- cpu = (i & 0x03) + j * 4;
- }
- if ((qabc_data[8] & (1 << j))) {
- voyager_extended_vic_processors |= (1 << cpu);
- }
- if (qabc_data[8] & (1 << (j + 4))) {
- /* Second SET register plumbed: Quad
- * card has two VIC connected CPUs.
- * Secondary cannot be booted as a VIC
- * CPU */
- voyager_extended_vic_processors |= (1 << cpu);
- voyager_allowed_boot_processors &=
- (~(1 << cpu));
- }
-
- voyager_quad_processors |= (1 << cpu);
- voyager_quad_cpi_addr[cpu] = (struct voyager_qic_cpi *)
- (qic_addr + (j << 8));
- CDEBUG(("CPU%d: CPI address 0x%lx\n", cpu,
- (unsigned long)voyager_quad_cpi_addr[cpu]));
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
-
- *asicpp = NULL;
- modpp = &((*modpp)->next);
- }
- *modpp = NULL;
- printk
- ("CAT Bus Initialisation finished: extended procs 0x%x, quad procs 0x%x, allowed vic boot = 0x%x\n",
- voyager_extended_vic_processors, voyager_quad_processors,
- voyager_allowed_boot_processors);
- request_resource(&ioport_resource, &vic_res);
- if (voyager_quad_processors)
- request_resource(&ioport_resource, &qic_res);
- /* set up the front power switch */
-}
-
-int voyager_cat_readb(__u8 module, __u8 asic, int reg)
-{
- return 0;
-}
-
-static int cat_disconnect(voyager_module_t * modp, voyager_asic_t * asicp)
-{
- __u8 val;
- int err = 0;
-
- if (!modp->scan_path_connected)
- return 0;
- if (asicp->asic_id != VOYAGER_CAT_ID) {
- CDEBUG(("cat_disconnect: ASIC is not CAT\n"));
- return 1;
- }
- err = cat_read(modp, asicp, VOYAGER_SCANPATH, &val);
- if (err) {
- CDEBUG(("cat_disconnect: failed to read SCANPATH\n"));
- return err;
- }
- val &= VOYAGER_DISCONNECT_ASIC;
- err = cat_write(modp, asicp, VOYAGER_SCANPATH, val);
- if (err) {
- CDEBUG(("cat_disconnect: failed to write SCANPATH\n"));
- return err;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- modp->scan_path_connected = 0;
-
- return 0;
-}
-
-static int cat_connect(voyager_module_t * modp, voyager_asic_t * asicp)
-{
- __u8 val;
- int err = 0;
-
- if (modp->scan_path_connected)
- return 0;
- if (asicp->asic_id != VOYAGER_CAT_ID) {
- CDEBUG(("cat_connect: ASIC is not CAT\n"));
- return 1;
- }
-
- err = cat_read(modp, asicp, VOYAGER_SCANPATH, &val);
- if (err) {
- CDEBUG(("cat_connect: failed to read SCANPATH\n"));
- return err;
- }
- val |= VOYAGER_CONNECT_ASIC;
- err = cat_write(modp, asicp, VOYAGER_SCANPATH, val);
- if (err) {
- CDEBUG(("cat_connect: failed to write SCANPATH\n"));
- return err;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- modp->scan_path_connected = 1;
-
- return 0;
-}
-
-void voyager_cat_power_off(void)
-{
- /* Power the machine off by writing to the PSI over the CAT
- * bus */
- __u8 data;
- voyager_module_t psi = { 0 };
- voyager_asic_t psi_asic = { 0 };
-
- psi.asic = &psi_asic;
- psi.asic->asic_id = VOYAGER_CAT_ID;
- psi.asic->subaddr = VOYAGER_SUBADDR_HI;
- psi.module_addr = VOYAGER_PSI;
- psi.scan_path_connected = 0;
-
- outb(VOYAGER_CAT_END, CAT_CMD);
- /* Connect the PSI to the CAT Bus */
- outb(VOYAGER_CAT_DESELECT, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_PSI, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_disconnect(&psi, &psi_asic);
- /* Read the status */
- cat_subread(&psi, &psi_asic, VOYAGER_PSI_GENERAL_REG, 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
- CDEBUG(("PSI STATUS 0x%x\n", data));
- /* These two writes are power off prep and perform */
- data = PSI_CLEAR;
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_subwrite(&psi, &psi_asic, VOYAGER_PSI_GENERAL_REG, 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
- data = PSI_POWER_DOWN;
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_subwrite(&psi, &psi_asic, VOYAGER_PSI_GENERAL_REG, 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
-}
-
-struct voyager_status voyager_status = { 0 };
-
-void voyager_cat_psi(__u8 cmd, __u16 reg, __u8 * data)
-{
- voyager_module_t psi = { 0 };
- voyager_asic_t psi_asic = { 0 };
-
- psi.asic = &psi_asic;
- psi.asic->asic_id = VOYAGER_CAT_ID;
- psi.asic->subaddr = VOYAGER_SUBADDR_HI;
- psi.module_addr = VOYAGER_PSI;
- psi.scan_path_connected = 0;
-
- outb(VOYAGER_CAT_END, CAT_CMD);
- /* Connect the PSI to the CAT Bus */
- outb(VOYAGER_CAT_DESELECT, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_PSI, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_disconnect(&psi, &psi_asic);
- switch (cmd) {
- case VOYAGER_PSI_READ:
- cat_read(&psi, &psi_asic, reg, data);
- break;
- case VOYAGER_PSI_WRITE:
- cat_write(&psi, &psi_asic, reg, *data);
- break;
- case VOYAGER_PSI_SUBREAD:
- cat_subread(&psi, &psi_asic, reg, 1, data);
- break;
- case VOYAGER_PSI_SUBWRITE:
- cat_subwrite(&psi, &psi_asic, reg, 1, data);
- break;
- default:
- printk(KERN_ERR "Voyager PSI, unrecognised command %d\n", cmd);
- break;
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
-}
-
-void voyager_cat_do_common_interrupt(void)
-{
- /* This is caused either by a memory parity error or something
- * in the PSI */
- __u8 data;
- voyager_module_t psi = { 0 };
- voyager_asic_t psi_asic = { 0 };
- struct voyager_psi psi_reg;
- int i;
- re_read:
- psi.asic = &psi_asic;
- psi.asic->asic_id = VOYAGER_CAT_ID;
- psi.asic->subaddr = VOYAGER_SUBADDR_HI;
- psi.module_addr = VOYAGER_PSI;
- psi.scan_path_connected = 0;
-
- outb(VOYAGER_CAT_END, CAT_CMD);
- /* Connect the PSI to the CAT Bus */
- outb(VOYAGER_CAT_DESELECT, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_PSI, VOYAGER_CAT_CONFIG_PORT);
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_disconnect(&psi, &psi_asic);
- /* Read the status. NOTE: Need to read *all* the PSI regs here
- * otherwise the cmn int will be reasserted */
- for (i = 0; i < sizeof(psi_reg.regs); i++) {
- cat_read(&psi, &psi_asic, i, &((__u8 *) & psi_reg.regs)[i]);
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
- if ((psi_reg.regs.checkbit & 0x02) == 0) {
- psi_reg.regs.checkbit |= 0x02;
- cat_write(&psi, &psi_asic, 5, psi_reg.regs.checkbit);
- printk("VOYAGER RE-READ PSI\n");
- goto re_read;
- }
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- for (i = 0; i < sizeof(psi_reg.subregs); i++) {
- /* This looks strange, but the PSI doesn't do auto increment
- * correctly */
- cat_subread(&psi, &psi_asic, VOYAGER_PSI_SUPPLY_REG + i,
- 1, &((__u8 *) & psi_reg.subregs)[i]);
- }
- outb(VOYAGER_CAT_END, CAT_CMD);
-#ifdef VOYAGER_CAT_DEBUG
- printk("VOYAGER PSI: ");
- for (i = 0; i < sizeof(psi_reg.regs); i++)
- printk("%02x ", ((__u8 *) & psi_reg.regs)[i]);
- printk("\n ");
- for (i = 0; i < sizeof(psi_reg.subregs); i++)
- printk("%02x ", ((__u8 *) & psi_reg.subregs)[i]);
- printk("\n");
-#endif
- if (psi_reg.regs.intstatus & PSI_MON) {
- /* switch off or power fail */
-
- if (psi_reg.subregs.supply & PSI_SWITCH_OFF) {
- if (voyager_status.switch_off) {
- printk(KERN_ERR
- "Voyager front panel switch turned off again---Immediate power off!\n");
- voyager_cat_power_off();
- /* not reached */
- } else {
- printk(KERN_ERR
- "Voyager front panel switch turned off\n");
- voyager_status.switch_off = 1;
- voyager_status.request_from_kernel = 1;
- wake_up_process(voyager_thread);
- }
- /* Tell the hardware we're taking care of the
- * shutdown, otherwise it will power the box off
- * within 3 seconds of the switch being pressed and,
- * which is much more important to us, continue to
- * assert the common interrupt */
- data = PSI_CLR_SWITCH_OFF;
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_subwrite(&psi, &psi_asic, VOYAGER_PSI_SUPPLY_REG,
- 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
- } else {
-
- VDEBUG(("Voyager ac fail reg 0x%x\n",
- psi_reg.subregs.ACfail));
- if ((psi_reg.subregs.ACfail & AC_FAIL_STAT_CHANGE) == 0) {
- /* No further update */
- return;
- }
-#if 0
- /* Don't bother trying to find out who failed.
- * FIXME: This probably makes the code incorrect on
- * anything other than a 345x */
- for (i = 0; i < 5; i++) {
- if (psi_reg.subregs.ACfail & (1 << i)) {
- break;
- }
- }
- printk(KERN_NOTICE "AC FAIL IN SUPPLY %d\n", i);
-#endif
- /* DON'T do this: it shuts down the AC PSI
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- data = PSI_MASK_MASK | i;
- cat_subwrite(&psi, &psi_asic, VOYAGER_PSI_MASK,
- 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
- */
- printk(KERN_ERR "Voyager AC power failure\n");
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- data = PSI_COLD_START;
- cat_subwrite(&psi, &psi_asic, VOYAGER_PSI_GENERAL_REG,
- 1, &data);
- outb(VOYAGER_CAT_END, CAT_CMD);
- voyager_status.power_fail = 1;
- voyager_status.request_from_kernel = 1;
- wake_up_process(voyager_thread);
- }
-
- } else if (psi_reg.regs.intstatus & PSI_FAULT) {
- /* Major fault! */
- printk(KERN_ERR
- "Voyager PSI Detected major fault, immediate power off!\n");
- voyager_cat_power_off();
- /* not reached */
- } else if (psi_reg.regs.intstatus & (PSI_DC_FAIL | PSI_ALARM
- | PSI_CURRENT | PSI_DVM
- | PSI_PSCFAULT | PSI_STAT_CHG)) {
- /* other psi fault */
-
- printk(KERN_WARNING "Voyager PSI status 0x%x\n", data);
- /* clear the PSI fault */
- outb(VOYAGER_CAT_RUN, CAT_CMD);
- cat_write(&psi, &psi_asic, VOYAGER_PSI_STATUS_REG, 0);
- outb(VOYAGER_CAT_END, CAT_CMD);
- }
-}
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
deleted file mode 100644
index 98e3c2b..0000000
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ /dev/null
@@ -1,1805 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * This file provides all the same external entries as smp.c but uses
- * the voyager hal to provide the functionality
- */
-#include <linux/cpu.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/kernel_stat.h>
-#include <linux/delay.h>
-#include <linux/mc146818rtc.h>
-#include <linux/cache.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/bootmem.h>
-#include <linux/completion.h>
-#include <asm/desc.h>
-#include <asm/voyager.h>
-#include <asm/vic.h>
-#include <asm/mtrr.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/arch_hooks.h>
-#include <asm/trampoline.h>
-
-/* TLB state -- visible externally, indexed physically */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { &init_mm, 0 };
-
-/* CPU IRQ affinity -- set to all ones initially */
-static unsigned long cpu_irq_affinity[NR_CPUS] __cacheline_aligned =
- {[0 ... NR_CPUS-1] = ~0UL };
-
-/* per CPU data structure (for /proc/cpuinfo et al), visible externally
- * indexed physically */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
-EXPORT_PER_CPU_SYMBOL(cpu_info);
-
-/* physical ID of the CPU used to boot the system */
-unsigned char boot_cpu_id;
-
-/* The memory line addresses for the Quad CPIs */
-struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS] __cacheline_aligned;
-
-/* The masks for the Extended VIC processors, filled in by cat_init */
-__u32 voyager_extended_vic_processors = 0;
-
-/* Masks for the extended Quad processors which cannot be VIC booted */
-__u32 voyager_allowed_boot_processors = 0;
-
-/* The mask for the Quad Processors (both extended and non-extended) */
-__u32 voyager_quad_processors = 0;
-
-/* Total count of live CPUs, used in process.c to display
- * the CPU information and in irq.c for the per CPU irq
- * activity count. Finally exported by i386_ksyms.c */
-static int voyager_extended_cpus = 1;
-
-/* Used for the invalidate map that's also checked in the spinlock */
-static volatile unsigned long smp_invalidate_needed;
-
-/* Bitmask of CPUs present in the system - exported by i386_syms.c, used
- * by scheduler but indexed physically */
-cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
-
-/* The internal functions */
-static void send_CPI(__u32 cpuset, __u8 cpi);
-static void ack_CPI(__u8 cpi);
-static int ack_QIC_CPI(__u8 cpi);
-static void ack_special_QIC_CPI(__u8 cpi);
-static void ack_VIC_CPI(__u8 cpi);
-static void send_CPI_allbutself(__u8 cpi);
-static void mask_vic_irq(unsigned int irq);
-static void unmask_vic_irq(unsigned int irq);
-static unsigned int startup_vic_irq(unsigned int irq);
-static void enable_local_vic_irq(unsigned int irq);
-static void disable_local_vic_irq(unsigned int irq);
-static void before_handle_vic_irq(unsigned int irq);
-static void after_handle_vic_irq(unsigned int irq);
-static void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask);
-static void ack_vic_irq(unsigned int irq);
-static void vic_enable_cpi(void);
-static void do_boot_cpu(__u8 cpuid);
-static void do_quad_bootstrap(void);
-static void initialize_secondary(void);
-
-int hard_smp_processor_id(void);
-int safe_smp_processor_id(void);
-
-/* Inline functions */
-static inline void send_one_QIC_CPI(__u8 cpu, __u8 cpi)
-{
- voyager_quad_cpi_addr[cpu]->qic_cpi[cpi].cpi =
- (smp_processor_id() << 16) + cpi;
-}
-
-static inline void send_QIC_CPI(__u32 cpuset, __u8 cpi)
-{
- int cpu;
-
- for_each_online_cpu(cpu) {
- if (cpuset & (1 << cpu)) {
-#ifdef VOYAGER_DEBUG
- if (!cpu_online(cpu))
- VDEBUG(("CPU%d sending cpi %d to CPU%d not in "
- "cpu_online_map\n",
- hard_smp_processor_id(), cpi, cpu));
-#endif
- send_one_QIC_CPI(cpu, cpi - QIC_CPI_OFFSET);
- }
- }
-}
-
-static inline void wrapper_smp_local_timer_interrupt(void)
-{
- irq_enter();
- smp_local_timer_interrupt();
- irq_exit();
-}
-
-static inline void send_one_CPI(__u8 cpu, __u8 cpi)
-{
- if (voyager_quad_processors & (1 << cpu))
- send_one_QIC_CPI(cpu, cpi - QIC_CPI_OFFSET);
- else
- send_CPI(1 << cpu, cpi);
-}
-
-static inline void send_CPI_allbutself(__u8 cpi)
-{
- __u8 cpu = smp_processor_id();
- __u32 mask = cpus_addr(cpu_online_map)[0] & ~(1 << cpu);
- send_CPI(mask, cpi);
-}
-
-static inline int is_cpu_quad(void)
-{
- __u8 cpumask = inb(VIC_PROC_WHO_AM_I);
- return ((cpumask & QUAD_IDENTIFIER) == QUAD_IDENTIFIER);
-}
-
-static inline int is_cpu_extended(void)
-{
- __u8 cpu = hard_smp_processor_id();
-
- return (voyager_extended_vic_processors & (1 << cpu));
-}
-
-static inline int is_cpu_vic_boot(void)
-{
- __u8 cpu = hard_smp_processor_id();
-
- return (voyager_extended_vic_processors
- & voyager_allowed_boot_processors & (1 << cpu));
-}
-
-static inline void ack_CPI(__u8 cpi)
-{
- switch (cpi) {
- case VIC_CPU_BOOT_CPI:
- if (is_cpu_quad() && !is_cpu_vic_boot())
- ack_QIC_CPI(cpi);
- else
- ack_VIC_CPI(cpi);
- break;
- case VIC_SYS_INT:
- case VIC_CMN_INT:
- /* These are slightly strange. Even on the Quad card,
- * They are vectored as VIC CPIs */
- if (is_cpu_quad())
- ack_special_QIC_CPI(cpi);
- else
- ack_VIC_CPI(cpi);
- break;
- default:
- printk("VOYAGER ERROR: CPI%d is in common CPI code\n", cpi);
- break;
- }
-}
-
-/* local variables */
-
-/* The VIC IRQ descriptors -- these look almost identical to the
- * 8259 IRQs except that masks and things must be kept per processor
- */
-static struct irq_chip vic_chip = {
- .name = "VIC",
- .startup = startup_vic_irq,
- .mask = mask_vic_irq,
- .unmask = unmask_vic_irq,
- .set_affinity = set_vic_irq_affinity,
-};
-
-/* used to count up as CPUs are brought on line (starts at 0) */
-static int cpucount = 0;
-
-/* The per cpu profile stuff - used in smp_local_timer_interrupt */
-static DEFINE_PER_CPU(int, prof_multiplier) = 1;
-static DEFINE_PER_CPU(int, prof_old_multiplier) = 1;
-static DEFINE_PER_CPU(int, prof_counter) = 1;
-
-/* the map used to check if a CPU has booted */
-static __u32 cpu_booted_map;
-
-/* the synchronize flag used to hold all secondary CPUs spinning in
- * a tight loop until the boot sequence is ready for them */
-static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
-
-/* This is for the new dynamic CPU boot code */
-
-/* The per processor IRQ masks (these are usually kept in sync) */
-static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
-
-/* the list of IRQs to be enabled by the VIC_ENABLE_IRQ_CPI */
-static __u16 vic_irq_enable_mask[NR_CPUS] __cacheline_aligned = { 0 };
-
-/* Lock for enable/disable of VIC interrupts */
-static __cacheline_aligned DEFINE_SPINLOCK(vic_irq_lock);
-
-/* The boot processor is correctly set up in PC mode when it
- * comes up, but the secondaries need their master/slave 8259
- * pairs initializing correctly */
-
-/* Interrupt counters (per cpu) and total - used to try to
- * even up the interrupt handling routines */
-static long vic_intr_total = 0;
-static long vic_intr_count[NR_CPUS] __cacheline_aligned = { 0 };
-static unsigned long vic_tick[NR_CPUS] __cacheline_aligned = { 0 };
-
-/* Since we can only use CPI0, we fake all the other CPIs */
-static unsigned long vic_cpi_mailbox[NR_CPUS] __cacheline_aligned;
-
-/* debugging routine to read the isr of the cpu's pic */
-static inline __u16 vic_read_isr(void)
-{
- __u16 isr;
-
- outb(0x0b, 0xa0);
- isr = inb(0xa0) << 8;
- outb(0x0b, 0x20);
- isr |= inb(0x20);
-
- return isr;
-}
-
-static __init void qic_setup(void)
-{
- if (!is_cpu_quad()) {
- /* not a quad, no setup */
- return;
- }
- outb(QIC_DEFAULT_MASK0, QIC_MASK_REGISTER0);
- outb(QIC_CPI_ENABLE, QIC_MASK_REGISTER1);
-
- if (is_cpu_extended()) {
- /* the QIC duplicate of the VIC base register */
- outb(VIC_DEFAULT_CPI_BASE, QIC_VIC_CPI_BASE_REGISTER);
- outb(QIC_DEFAULT_CPI_BASE, QIC_CPI_BASE_REGISTER);
-
- /* FIXME: should set up the QIC timer and memory parity
- * error vectors here */
- }
-}
-
-static __init void vic_setup_pic(void)
-{
- outb(1, VIC_REDIRECT_REGISTER_1);
- /* clear the claim registers for dynamic routing */
- outb(0, VIC_CLAIM_REGISTER_0);
- outb(0, VIC_CLAIM_REGISTER_1);
-
- outb(0, VIC_PRIORITY_REGISTER);
- /* Set the Primary and Secondary Microchannel vector
- * bases to be the same as the ordinary interrupts
- *
- * FIXME: This would be more efficient using separate
- * vectors. */
- outb(FIRST_EXTERNAL_VECTOR, VIC_PRIMARY_MC_BASE);
- outb(FIRST_EXTERNAL_VECTOR, VIC_SECONDARY_MC_BASE);
- /* Now initiallise the master PIC belonging to this CPU by
- * sending the four ICWs */
-
- /* ICW1: level triggered, ICW4 needed */
- outb(0x19, 0x20);
-
- /* ICW2: vector base */
- outb(FIRST_EXTERNAL_VECTOR, 0x21);
-
- /* ICW3: slave at line 2 */
- outb(0x04, 0x21);
-
- /* ICW4: 8086 mode */
- outb(0x01, 0x21);
-
- /* now the same for the slave PIC */
-
- /* ICW1: level trigger, ICW4 needed */
- outb(0x19, 0xA0);
-
- /* ICW2: slave vector base */
- outb(FIRST_EXTERNAL_VECTOR + 8, 0xA1);
-
- /* ICW3: slave ID */
- outb(0x02, 0xA1);
-
- /* ICW4: 8086 mode */
- outb(0x01, 0xA1);
-}
-
-static void do_quad_bootstrap(void)
-{
- if (is_cpu_quad() && is_cpu_vic_boot()) {
- int i;
- unsigned long flags;
- __u8 cpuid = hard_smp_processor_id();
-
- local_irq_save(flags);
-
- for (i = 0; i < 4; i++) {
- /* FIXME: this would be >>3 &0x7 on the 32 way */
- if (((cpuid >> 2) & 0x03) == i)
- /* don't lower our own mask! */
- continue;
-
- /* masquerade as local Quad CPU */
- outb(QIC_CPUID_ENABLE | i, QIC_PROCESSOR_ID);
- /* enable the startup CPI */
- outb(QIC_BOOT_CPI_MASK, QIC_MASK_REGISTER1);
- /* restore cpu id */
- outb(0, QIC_PROCESSOR_ID);
- }
- local_irq_restore(flags);
- }
-}
-
-void prefill_possible_map(void)
-{
- /* This is empty on voyager because we need a much
- * earlier detection which is done in find_smp_config */
-}
-
-/* Set up all the basic stuff: read the SMP config and make all the
- * SMP information reflect only the boot cpu. All others will be
- * brought on-line later. */
-void __init find_smp_config(void)
-{
- int i;
-
- boot_cpu_id = hard_smp_processor_id();
-
- printk("VOYAGER SMP: Boot cpu is %d\n", boot_cpu_id);
-
- /* initialize the CPU structures (moved from smp_boot_cpus) */
- for (i = 0; i < nr_cpu_ids; i++)
- cpu_irq_affinity[i] = ~0;
- cpu_online_map = cpumask_of_cpu(boot_cpu_id);
-
- /* The boot CPU must be extended */
- voyager_extended_vic_processors = 1 << boot_cpu_id;
- /* initially, all of the first 8 CPUs can boot */
- voyager_allowed_boot_processors = 0xff;
- /* set up everything for just this CPU, we can alter
- * this as we start the other CPUs later */
- /* now get the CPU disposition from the extended CMOS */
- cpus_addr(phys_cpu_present_map)[0] =
- voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK);
- cpus_addr(phys_cpu_present_map)[0] |=
- voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8;
- cpus_addr(phys_cpu_present_map)[0] |=
- voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
- 2) << 16;
- cpus_addr(phys_cpu_present_map)[0] |=
- voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
- 3) << 24;
- init_cpu_possible(&phys_cpu_present_map);
- printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n",
- cpus_addr(phys_cpu_present_map)[0]);
- /* Here we set up the VIC to enable SMP */
- /* enable the CPIs by writing the base vector to their register */
- outb(VIC_DEFAULT_CPI_BASE, VIC_CPI_BASE_REGISTER);
- outb(1, VIC_REDIRECT_REGISTER_1);
- /* set the claim registers for static routing --- Boot CPU gets
- * all interrupts untill all other CPUs started */
- outb(0xff, VIC_CLAIM_REGISTER_0);
- outb(0xff, VIC_CLAIM_REGISTER_1);
- /* Set the Primary and Secondary Microchannel vector
- * bases to be the same as the ordinary interrupts
- *
- * FIXME: This would be more efficient using separate
- * vectors. */
- outb(FIRST_EXTERNAL_VECTOR, VIC_PRIMARY_MC_BASE);
- outb(FIRST_EXTERNAL_VECTOR, VIC_SECONDARY_MC_BASE);
-
- /* Finally tell the firmware that we're driving */
- outb(inb(VOYAGER_SUS_IN_CONTROL_PORT) | VOYAGER_IN_CONTROL_FLAG,
- VOYAGER_SUS_IN_CONTROL_PORT);
-
- current_thread_info()->cpu = boot_cpu_id;
- percpu_write(cpu_number, boot_cpu_id);
-}
-
-/*
- * The bootstrap kernel entry code has set these up. Save them
- * for a given CPU, id is physical */
-void __init smp_store_cpu_info(int id)
-{
- struct cpuinfo_x86 *c = &cpu_data(id);
-
- *c = boot_cpu_data;
- c->cpu_index = id;
-
- identify_secondary_cpu(c);
-}
-
-/* Routine initially called when a non-boot CPU is brought online */
-static void __init start_secondary(void *unused)
-{
- __u8 cpuid = hard_smp_processor_id();
-
- cpu_init();
-
- /* OK, we're in the routine */
- ack_CPI(VIC_CPU_BOOT_CPI);
-
- /* setup the 8259 master slave pair belonging to this CPU ---
- * we won't actually receive any until the boot CPU
- * relinquishes it's static routing mask */
- vic_setup_pic();
-
- qic_setup();
-
- if (is_cpu_quad() && !is_cpu_vic_boot()) {
- /* clear the boot CPI */
- __u8 dummy;
-
- dummy =
- voyager_quad_cpi_addr[cpuid]->qic_cpi[VIC_CPU_BOOT_CPI].cpi;
- printk("read dummy %d\n", dummy);
- }
-
- /* lower the mask to receive CPIs */
- vic_enable_cpi();
-
- VDEBUG(("VOYAGER SMP: CPU%d, stack at about %p\n", cpuid, &cpuid));
-
- notify_cpu_starting(cpuid);
-
- /* enable interrupts */
- local_irq_enable();
-
- /* get our bogomips */
- calibrate_delay();
-
- /* save our processor parameters */
- smp_store_cpu_info(cpuid);
-
- /* if we're a quad, we may need to bootstrap other CPUs */
- do_quad_bootstrap();
-
- /* FIXME: this is rather a poor hack to prevent the CPU
- * activating softirqs while it's supposed to be waiting for
- * permission to proceed. Without this, the new per CPU stuff
- * in the softirqs will fail */
- local_irq_disable();
- cpu_set(cpuid, cpu_callin_map);
-
- /* signal that we're done */
- cpu_booted_map = 1;
-
- while (!cpu_isset(cpuid, smp_commenced_mask))
- rep_nop();
- local_irq_enable();
-
- local_flush_tlb();
-
- cpu_set(cpuid, cpu_online_map);
- wmb();
- cpu_idle();
-}
-
-/* Routine to kick start the given CPU and wait for it to report ready
- * (or timeout in startup). When this routine returns, the requested
- * CPU is either fully running and configured or known to be dead.
- *
- * We call this routine sequentially 1 CPU at a time, so no need for
- * locking */
-
-static void __init do_boot_cpu(__u8 cpu)
-{
- struct task_struct *idle;
- int timeout;
- unsigned long flags;
- int quad_boot = (1 << cpu) & voyager_quad_processors
- & ~(voyager_extended_vic_processors
- & voyager_allowed_boot_processors);
-
- /* This is the format of the CPI IDT gate (in real mode) which
- * we're hijacking to boot the CPU */
- union IDTFormat {
- struct seg {
- __u16 Offset;
- __u16 Segment;
- } idt;
- __u32 val;
- } hijack_source;
-
- __u32 *hijack_vector;
- __u32 start_phys_address = setup_trampoline();
-
- /* There's a clever trick to this: The linux trampoline is
- * compiled to begin at absolute location zero, so make the
- * address zero but have the data segment selector compensate
- * for the actual address */
- hijack_source.idt.Offset = start_phys_address & 0x000F;
- hijack_source.idt.Segment = (start_phys_address >> 4) & 0xFFFF;
-
- cpucount++;
- alternatives_smp_switch(1);
-
- idle = fork_idle(cpu);
- if (IS_ERR(idle))
- panic("failed fork for CPU%d", cpu);
- idle->thread.ip = (unsigned long)start_secondary;
- /* init_tasks (in sched.c) is indexed logically */
- stack_start.sp = (void *)idle->thread.sp;
-
- per_cpu(current_task, cpu) = idle;
- early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
- irq_ctx_init(cpu);
-
- /* Note: Don't modify initial ss override */
- VDEBUG(("VOYAGER SMP: Booting CPU%d at 0x%lx[%x:%x], stack %p\n", cpu,
- (unsigned long)hijack_source.val, hijack_source.idt.Segment,
- hijack_source.idt.Offset, stack_start.sp));
-
- /* init lowmem identity mapping */
- clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
- flush_tlb_all();
-
- if (quad_boot) {
- printk("CPU %d: non extended Quad boot\n", cpu);
- hijack_vector =
- (__u32 *)
- phys_to_virt((VIC_CPU_BOOT_CPI + QIC_DEFAULT_CPI_BASE) * 4);
- *hijack_vector = hijack_source.val;
- } else {
- printk("CPU%d: extended VIC boot\n", cpu);
- hijack_vector =
- (__u32 *)
- phys_to_virt((VIC_CPU_BOOT_CPI + VIC_DEFAULT_CPI_BASE) * 4);
- *hijack_vector = hijack_source.val;
- /* VIC errata, may also receive interrupt at this address */
- hijack_vector =
- (__u32 *)
- phys_to_virt((VIC_CPU_BOOT_ERRATA_CPI +
- VIC_DEFAULT_CPI_BASE) * 4);
- *hijack_vector = hijack_source.val;
- }
- /* All non-boot CPUs start with interrupts fully masked. Need
- * to lower the mask of the CPI we're about to send. We do
- * this in the VIC by masquerading as the processor we're
- * about to boot and lowering its interrupt mask */
- local_irq_save(flags);
- if (quad_boot) {
- send_one_QIC_CPI(cpu, VIC_CPU_BOOT_CPI);
- } else {
- outb(VIC_CPU_MASQUERADE_ENABLE | cpu, VIC_PROCESSOR_ID);
- /* here we're altering registers belonging to `cpu' */
-
- outb(VIC_BOOT_INTERRUPT_MASK, 0x21);
- /* now go back to our original identity */
- outb(boot_cpu_id, VIC_PROCESSOR_ID);
-
- /* and boot the CPU */
-
- send_CPI((1 << cpu), VIC_CPU_BOOT_CPI);
- }
- cpu_booted_map = 0;
- local_irq_restore(flags);
-
- /* now wait for it to become ready (or timeout) */
- for (timeout = 0; timeout < 50000; timeout++) {
- if (cpu_booted_map)
- break;
- udelay(100);
- }
- /* reset the page table */
- zap_low_mappings();
-
- if (cpu_booted_map) {
- VDEBUG(("CPU%d: Booted successfully, back in CPU %d\n",
- cpu, smp_processor_id()));
-
- printk("CPU%d: ", cpu);
- print_cpu_info(&cpu_data(cpu));
- wmb();
- cpu_set(cpu, cpu_callout_map);
- cpu_set(cpu, cpu_present_map);
- } else {
- printk("CPU%d FAILED TO BOOT: ", cpu);
- if (*
- ((volatile unsigned char *)phys_to_virt(start_phys_address))
- == 0xA5)
- printk("Stuck.\n");
- else
- printk("Not responding.\n");
-
- cpucount--;
- }
-}
-
-void __init smp_boot_cpus(void)
-{
- int i;
-
- /* CAT BUS initialisation must be done after the memory */
- /* FIXME: The L4 has a catbus too, it just needs to be
- * accessed in a totally different way */
- if (voyager_level == 5) {
- voyager_cat_init();
-
- /* now that the cat has probed the Voyager System Bus, sanity
- * check the cpu map */
- if (((voyager_quad_processors | voyager_extended_vic_processors)
- & cpus_addr(phys_cpu_present_map)[0]) !=
- cpus_addr(phys_cpu_present_map)[0]) {
- /* should panic */
- printk("\n\n***WARNING*** "
- "Sanity check of CPU present map FAILED\n");
- }
- } else if (voyager_level == 4)
- voyager_extended_vic_processors =
- cpus_addr(phys_cpu_present_map)[0];
-
- /* this sets up the idle task to run on the current cpu */
- voyager_extended_cpus = 1;
- /* Remove the global_irq_holder setting, it triggers a BUG() on
- * schedule at the moment */
- //global_irq_holder = boot_cpu_id;
-
- /* FIXME: Need to do something about this but currently only works
- * on CPUs with a tsc which none of mine have.
- smp_tune_scheduling();
- */
- smp_store_cpu_info(boot_cpu_id);
- /* setup the jump vector */
- initial_code = (unsigned long)initialize_secondary;
- printk("CPU%d: ", boot_cpu_id);
- print_cpu_info(&cpu_data(boot_cpu_id));
-
- if (is_cpu_quad()) {
- /* booting on a Quad CPU */
- printk("VOYAGER SMP: Boot CPU is Quad\n");
- qic_setup();
- do_quad_bootstrap();
- }
-
- /* enable our own CPIs */
- vic_enable_cpi();
-
- cpu_set(boot_cpu_id, cpu_online_map);
- cpu_set(boot_cpu_id, cpu_callout_map);
-
- /* loop over all the extended VIC CPUs and boot them. The
- * Quad CPUs must be bootstrapped by their extended VIC cpu */
- for (i = 0; i < nr_cpu_ids; i++) {
- if (i == boot_cpu_id || !cpu_isset(i, phys_cpu_present_map))
- continue;
- do_boot_cpu(i);
- /* This udelay seems to be needed for the Quad boots
- * don't remove unless you know what you're doing */
- udelay(1000);
- }
- /* we could compute the total bogomips here, but why bother?,
- * Code added from smpboot.c */
- {
- unsigned long bogosum = 0;
-
- for_each_online_cpu(i)
- bogosum += cpu_data(i).loops_per_jiffy;
- printk(KERN_INFO "Total of %d processors activated "
- "(%lu.%02lu BogoMIPS).\n",
- cpucount + 1, bogosum / (500000 / HZ),
- (bogosum / (5000 / HZ)) % 100);
- }
- voyager_extended_cpus = hweight32(voyager_extended_vic_processors);
- printk("VOYAGER: Extended (interrupt handling CPUs): "
- "%d, non-extended: %d\n", voyager_extended_cpus,
- num_booting_cpus() - voyager_extended_cpus);
- /* that's it, switch to symmetric mode */
- outb(0, VIC_PRIORITY_REGISTER);
- outb(0, VIC_CLAIM_REGISTER_0);
- outb(0, VIC_CLAIM_REGISTER_1);
-
- VDEBUG(("VOYAGER SMP: Booted with %d CPUs\n", num_booting_cpus()));
-}
-
-/* Reload the secondary CPUs task structure (this function does not
- * return ) */
-static void __init initialize_secondary(void)
-{
-#if 0
- // AC kernels only
- set_current(hard_get_current());
-#endif
-
- /*
- * We don't actually need to load the full TSS,
- * basically just the stack pointer and the eip.
- */
-
- asm volatile ("movl %0,%%esp\n\t"
- "jmp *%1"::"r" (current->thread.sp),
- "r"(current->thread.ip));
-}
-
-/* handle a Voyager SYS_INT -- If we don't, the base board will
- * panic the system.
- *
- * System interrupts occur because some problem was detected on the
- * various busses. To find out what you have to probe all the
- * hardware via the CAT bus. FIXME: At the moment we do nothing. */
-void smp_vic_sys_interrupt(struct pt_regs *regs)
-{
- ack_CPI(VIC_SYS_INT);
- printk("Voyager SYSTEM INTERRUPT\n");
-}
-
-/* Handle a voyager CMN_INT; These interrupts occur either because of
- * a system status change or because a single bit memory error
- * occurred. FIXME: At the moment, ignore all this. */
-void smp_vic_cmn_interrupt(struct pt_regs *regs)
-{
- static __u8 in_cmn_int = 0;
- static DEFINE_SPINLOCK(cmn_int_lock);
-
- /* common ints are broadcast, so make sure we only do this once */
- _raw_spin_lock(&cmn_int_lock);
- if (in_cmn_int)
- goto unlock_end;
-
- in_cmn_int++;
- _raw_spin_unlock(&cmn_int_lock);
-
- VDEBUG(("Voyager COMMON INTERRUPT\n"));
-
- if (voyager_level == 5)
- voyager_cat_do_common_interrupt();
-
- _raw_spin_lock(&cmn_int_lock);
- in_cmn_int = 0;
- unlock_end:
- _raw_spin_unlock(&cmn_int_lock);
- ack_CPI(VIC_CMN_INT);
-}
-
-/*
- * Reschedule call back. Nothing to do, all the work is done
- * automatically when we return from the interrupt. */
-static void smp_reschedule_interrupt(void)
-{
- /* do nothing */
-}
-
-static struct mm_struct *flush_mm;
-static unsigned long flush_va;
-static DEFINE_SPINLOCK(tlbstate_lock);
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- *
- * We need to reload %cr3 since the page tables may be going
- * away from under us..
- */
-static inline void voyager_leave_mm(unsigned long cpu)
-{
- if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
- BUG();
- cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask);
- load_cr3(swapper_pg_dir);
-}
-
-/*
- * Invalidate call-back
- */
-static void smp_invalidate_interrupt(void)
-{
- __u8 cpu = smp_processor_id();
-
- if (!test_bit(cpu, &smp_invalidate_needed))
- return;
- /* This will flood messages. Don't uncomment unless you see
- * Problems with cross cpu invalidation
- VDEBUG(("VOYAGER SMP: CPU%d received INVALIDATE_CPI\n",
- smp_processor_id()));
- */
-
- if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) {
- if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) {
- if (flush_va == TLB_FLUSH_ALL)
- local_flush_tlb();
- else
- __flush_tlb_one(flush_va);
- } else
- voyager_leave_mm(cpu);
- }
- smp_mb__before_clear_bit();
- clear_bit(cpu, &smp_invalidate_needed);
- smp_mb__after_clear_bit();
-}
-
-/* All the new flush operations for 2.4 */
-
-/* This routine is called with a physical cpu mask */
-static void
-voyager_flush_tlb_others(unsigned long cpumask, struct mm_struct *mm,
- unsigned long va)
-{
- int stuck = 50000;
-
- if (!cpumask)
- BUG();
- if ((cpumask & cpus_addr(cpu_online_map)[0]) != cpumask)
- BUG();
- if (cpumask & (1 << smp_processor_id()))
- BUG();
- if (!mm)
- BUG();
-
- spin_lock(&tlbstate_lock);
-
- flush_mm = mm;
- flush_va = va;
- atomic_set_mask(cpumask, &smp_invalidate_needed);
- /*
- * We have to send the CPI only to
- * CPUs affected.
- */
- send_CPI(cpumask, VIC_INVALIDATE_CPI);
-
- while (smp_invalidate_needed) {
- mb();
- if (--stuck == 0) {
- printk("***WARNING*** Stuck doing invalidate CPI "
- "(CPU%d)\n", smp_processor_id());
- break;
- }
- }
-
- /* Uncomment only to debug invalidation problems
- VDEBUG(("VOYAGER SMP: Completed invalidate CPI (CPU%d)\n", cpu));
- */
-
- flush_mm = NULL;
- flush_va = 0;
- spin_unlock(&tlbstate_lock);
-}
-
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
- unsigned long cpu_mask;
-
- preempt_disable();
-
- cpu_mask = cpus_addr(mm->cpu_vm_mask)[0] & ~(1 << smp_processor_id());
- local_flush_tlb();
- if (cpu_mask)
- voyager_flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
- preempt_enable();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- unsigned long cpu_mask;
-
- preempt_disable();
-
- cpu_mask = cpus_addr(mm->cpu_vm_mask)[0] & ~(1 << smp_processor_id());
-
- if (current->active_mm == mm) {
- if (current->mm)
- local_flush_tlb();
- else
- voyager_leave_mm(smp_processor_id());
- }
- if (cpu_mask)
- voyager_flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
- preempt_enable();
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
-{
- struct mm_struct *mm = vma->vm_mm;
- unsigned long cpu_mask;
-
- preempt_disable();
-
- cpu_mask = cpus_addr(mm->cpu_vm_mask)[0] & ~(1 << smp_processor_id());
- if (current->active_mm == mm) {
- if (current->mm)
- __flush_tlb_one(va);
- else
- voyager_leave_mm(smp_processor_id());
- }
-
- if (cpu_mask)
- voyager_flush_tlb_others(cpu_mask, mm, va);
-
- preempt_enable();
-}
-
-EXPORT_SYMBOL(flush_tlb_page);
-
-/* enable the requested IRQs */
-static void smp_enable_irq_interrupt(void)
-{
- __u8 irq;
- __u8 cpu = get_cpu();
-
- VDEBUG(("VOYAGER SMP: CPU%d enabling irq mask 0x%x\n", cpu,
- vic_irq_enable_mask[cpu]));
-
- spin_lock(&vic_irq_lock);
- for (irq = 0; irq < 16; irq++) {
- if (vic_irq_enable_mask[cpu] & (1 << irq))
- enable_local_vic_irq(irq);
- }
- vic_irq_enable_mask[cpu] = 0;
- spin_unlock(&vic_irq_lock);
-
- put_cpu_no_resched();
-}
-
-/*
- * CPU halt call-back
- */
-static void smp_stop_cpu_function(void *dummy)
-{
- VDEBUG(("VOYAGER SMP: CPU%d is STOPPING\n", smp_processor_id()));
- cpu_clear(smp_processor_id(), cpu_online_map);
- local_irq_disable();
- for (;;)
- halt();
-}
-
-/* execute a thread on a new CPU. The function to be called must be
- * previously set up. This is used to schedule a function for
- * execution on all CPUs - set up the function then broadcast a
- * function_interrupt CPI to come here on each CPU */
-static void smp_call_function_interrupt(void)
-{
- irq_enter();
- generic_smp_call_function_interrupt();
- __get_cpu_var(irq_stat).irq_call_count++;
- irq_exit();
-}
-
-static void smp_call_function_single_interrupt(void)
-{
- irq_enter();
- generic_smp_call_function_single_interrupt();
- __get_cpu_var(irq_stat).irq_call_count++;
- irq_exit();
-}
-
-/* Sorry about the name. In an APIC based system, the APICs
- * themselves are programmed to send a timer interrupt. This is used
- * by linux to reschedule the processor. Voyager doesn't have this,
- * so we use the system clock to interrupt one processor, which in
- * turn, broadcasts a timer CPI to all the others --- we receive that
- * CPI here. We don't use this actually for counting so losing
- * ticks doesn't matter
- *
- * FIXME: For those CPUs which actually have a local APIC, we could
- * try to use it to trigger this interrupt instead of having to
- * broadcast the timer tick. Unfortunately, all my pentium DYADs have
- * no local APIC, so I can't do this
- *
- * This function is currently a placeholder and is unused in the code */
-void smp_apic_timer_interrupt(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
- wrapper_smp_local_timer_interrupt();
- set_irq_regs(old_regs);
-}
-
-/* All of the QUAD interrupt GATES */
-void smp_qic_timer_interrupt(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
- ack_QIC_CPI(QIC_TIMER_CPI);
- wrapper_smp_local_timer_interrupt();
- set_irq_regs(old_regs);
-}
-
-void smp_qic_invalidate_interrupt(struct pt_regs *regs)
-{
- ack_QIC_CPI(QIC_INVALIDATE_CPI);
- smp_invalidate_interrupt();
-}
-
-void smp_qic_reschedule_interrupt(struct pt_regs *regs)
-{
- ack_QIC_CPI(QIC_RESCHEDULE_CPI);
- smp_reschedule_interrupt();
-}
-
-void smp_qic_enable_irq_interrupt(struct pt_regs *regs)
-{
- ack_QIC_CPI(QIC_ENABLE_IRQ_CPI);
- smp_enable_irq_interrupt();
-}
-
-void smp_qic_call_function_interrupt(struct pt_regs *regs)
-{
- ack_QIC_CPI(QIC_CALL_FUNCTION_CPI);
- smp_call_function_interrupt();
-}
-
-void smp_qic_call_function_single_interrupt(struct pt_regs *regs)
-{
- ack_QIC_CPI(QIC_CALL_FUNCTION_SINGLE_CPI);
- smp_call_function_single_interrupt();
-}
-
-void smp_vic_cpi_interrupt(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
- __u8 cpu = smp_processor_id();
-
- if (is_cpu_quad())
- ack_QIC_CPI(VIC_CPI_LEVEL0);
- else
- ack_VIC_CPI(VIC_CPI_LEVEL0);
-
- if (test_and_clear_bit(VIC_TIMER_CPI, &vic_cpi_mailbox[cpu]))
- wrapper_smp_local_timer_interrupt();
- if (test_and_clear_bit(VIC_INVALIDATE_CPI, &vic_cpi_mailbox[cpu]))
- smp_invalidate_interrupt();
- if (test_and_clear_bit(VIC_RESCHEDULE_CPI, &vic_cpi_mailbox[cpu]))
- smp_reschedule_interrupt();
- if (test_and_clear_bit(VIC_ENABLE_IRQ_CPI, &vic_cpi_mailbox[cpu]))
- smp_enable_irq_interrupt();
- if (test_and_clear_bit(VIC_CALL_FUNCTION_CPI, &vic_cpi_mailbox[cpu]))
- smp_call_function_interrupt();
- if (test_and_clear_bit(VIC_CALL_FUNCTION_SINGLE_CPI, &vic_cpi_mailbox[cpu]))
- smp_call_function_single_interrupt();
- set_irq_regs(old_regs);
-}
-
-static void do_flush_tlb_all(void *info)
-{
- unsigned long cpu = smp_processor_id();
-
- __flush_tlb_all();
- if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY)
- voyager_leave_mm(cpu);
-}
-
-/* flush the TLB of every active CPU in the system */
-void flush_tlb_all(void)
-{
- on_each_cpu(do_flush_tlb_all, 0, 1);
-}
-
-/* send a reschedule CPI to one CPU by physical CPU number*/
-static void voyager_smp_send_reschedule(int cpu)
-{
- send_one_CPI(cpu, VIC_RESCHEDULE_CPI);
-}
-
-int hard_smp_processor_id(void)
-{
- __u8 i;
- __u8 cpumask = inb(VIC_PROC_WHO_AM_I);
- if ((cpumask & QUAD_IDENTIFIER) == QUAD_IDENTIFIER)
- return cpumask & 0x1F;
-
- for (i = 0; i < 8; i++) {
- if (cpumask & (1 << i))
- return i;
- }
- printk("** WARNING ** Illegal cpuid returned by VIC: %d", cpumask);
- return 0;
-}
-
-int safe_smp_processor_id(void)
-{
- return hard_smp_processor_id();
-}
-
-/* broadcast a halt to all other CPUs */
-static void voyager_smp_send_stop(void)
-{
- smp_call_function(smp_stop_cpu_function, NULL, 1);
-}
-
-/* this function is triggered in time.c when a clock tick fires
- * we need to re-broadcast the tick to all CPUs */
-void smp_vic_timer_interrupt(void)
-{
- send_CPI_allbutself(VIC_TIMER_CPI);
- smp_local_timer_interrupt();
-}
-
-/* local (per CPU) timer interrupt. It does both profiling and
- * process statistics/rescheduling.
- *
- * We do profiling in every local tick, statistics/rescheduling
- * happen only every 'profiling multiplier' ticks. The default
- * multiplier is 1 and it can be changed by writing the new multiplier
- * value into /proc/profile.
- */
-void smp_local_timer_interrupt(void)
-{
- int cpu = smp_processor_id();
- long weight;
-
- profile_tick(CPU_PROFILING);
- if (--per_cpu(prof_counter, cpu) <= 0) {
- /*
- * The multiplier may have changed since the last time we got
- * to this point as a result of the user writing to
- * /proc/profile. In this case we need to adjust the APIC
- * timer accordingly.
- *
- * Interrupts are already masked off at this point.
- */
- per_cpu(prof_counter, cpu) = per_cpu(prof_multiplier, cpu);
- if (per_cpu(prof_counter, cpu) !=
- per_cpu(prof_old_multiplier, cpu)) {
- /* FIXME: need to update the vic timer tick here */
- per_cpu(prof_old_multiplier, cpu) =
- per_cpu(prof_counter, cpu);
- }
-
- update_process_times(user_mode_vm(get_irq_regs()));
- }
-
- if (((1 << cpu) & voyager_extended_vic_processors) == 0)
- /* only extended VIC processors participate in
- * interrupt distribution */
- return;
-
- /*
- * We take the 'long' return path, and there every subsystem
- * grabs the appropriate locks (kernel lock/ irq lock).
- *
- * we might want to decouple profiling from the 'long path',
- * and do the profiling totally in assembly.
- *
- * Currently this isn't too much of an issue (performance wise),
- * we can take more than 100K local irqs per second on a 100 MHz P5.
- */
-
- if ((++vic_tick[cpu] & 0x7) != 0)
- return;
- /* get here every 16 ticks (about every 1/6 of a second) */
-
- /* Change our priority to give someone else a chance at getting
- * the IRQ. The algorithm goes like this:
- *
- * In the VIC, the dynamically routed interrupt is always
- * handled by the lowest priority eligible (i.e. receiving
- * interrupts) CPU. If >1 eligible CPUs are equal lowest, the
- * lowest processor number gets it.
- *
- * The priority of a CPU is controlled by a special per-CPU
- * VIC priority register which is 3 bits wide 0 being lowest
- * and 7 highest priority..
- *
- * Therefore we subtract the average number of interrupts from
- * the number we've fielded. If this number is negative, we
- * lower the activity count and if it is positive, we raise
- * it.
- *
- * I'm afraid this still leads to odd looking interrupt counts:
- * the totals are all roughly equal, but the individual ones
- * look rather skewed.
- *
- * FIXME: This algorithm is total crap when mixed with SMP
- * affinity code since we now try to even up the interrupt
- * counts when an affinity binding is keeping them on a
- * particular CPU*/
- weight = (vic_intr_count[cpu] * voyager_extended_cpus
- - vic_intr_total) >> 4;
- weight += 4;
- if (weight > 7)
- weight = 7;
- if (weight < 0)
- weight = 0;
-
- outb((__u8) weight, VIC_PRIORITY_REGISTER);
-
-#ifdef VOYAGER_DEBUG
- if ((vic_tick[cpu] & 0xFFF) == 0) {
- /* print this message roughly every 25 secs */
- printk("VOYAGER SMP: vic_tick[%d] = %lu, weight = %ld\n",
- cpu, vic_tick[cpu], weight);
- }
-#endif
-}
-
-/* setup the profiling timer */
-int setup_profiling_timer(unsigned int multiplier)
-{
- int i;
-
- if ((!multiplier))
- return -EINVAL;
-
- /*
- * Set the new multiplier for each CPU. CPUs don't start using the
- * new values until the next timer interrupt in which they do process
- * accounting.
- */
- for (i = 0; i < nr_cpu_ids; ++i)
- per_cpu(prof_multiplier, i) = multiplier;
-
- return 0;
-}
-
-/* This is a bit of a mess, but forced on us by the genirq changes
- * there's no genirq handler that really does what voyager wants
- * so hack it up with the simple IRQ handler */
-static void handle_vic_irq(unsigned int irq, struct irq_desc *desc)
-{
- before_handle_vic_irq(irq);
- handle_simple_irq(irq, desc);
- after_handle_vic_irq(irq);
-}
-
-/* The CPIs are handled in the per cpu 8259s, so they must be
- * enabled to be received: FIX: enabling the CPIs in the early
- * boot sequence interferes with bug checking; enable them later
- * on in smp_init */
-#define VIC_SET_GATE(cpi, vector) \
- set_intr_gate((cpi) + VIC_DEFAULT_CPI_BASE, (vector))
-#define QIC_SET_GATE(cpi, vector) \
- set_intr_gate((cpi) + QIC_DEFAULT_CPI_BASE, (vector))
-
-void __init voyager_smp_intr_init(void)
-{
- int i;
-
- /* initialize the per cpu irq mask to all disabled */
- for (i = 0; i < nr_cpu_ids; i++)
- vic_irq_mask[i] = 0xFFFF;
-
- VIC_SET_GATE(VIC_CPI_LEVEL0, vic_cpi_interrupt);
-
- VIC_SET_GATE(VIC_SYS_INT, vic_sys_interrupt);
- VIC_SET_GATE(VIC_CMN_INT, vic_cmn_interrupt);
-
- QIC_SET_GATE(QIC_TIMER_CPI, qic_timer_interrupt);
- QIC_SET_GATE(QIC_INVALIDATE_CPI, qic_invalidate_interrupt);
- QIC_SET_GATE(QIC_RESCHEDULE_CPI, qic_reschedule_interrupt);
- QIC_SET_GATE(QIC_ENABLE_IRQ_CPI, qic_enable_irq_interrupt);
- QIC_SET_GATE(QIC_CALL_FUNCTION_CPI, qic_call_function_interrupt);
-
- /* now put the VIC descriptor into the first 48 IRQs
- *
- * This is for later: first 16 correspond to PC IRQs; next 16
- * are Primary MC IRQs and final 16 are Secondary MC IRQs */
- for (i = 0; i < 48; i++)
- set_irq_chip_and_handler(i, &vic_chip, handle_vic_irq);
-}
-
-/* send a CPI at level cpi to a set of cpus in cpuset (set 1 bit per
- * processor to receive CPI */
-static void send_CPI(__u32 cpuset, __u8 cpi)
-{
- int cpu;
- __u32 quad_cpuset = (cpuset & voyager_quad_processors);
-
- if (cpi < VIC_START_FAKE_CPI) {
- /* fake CPI are only used for booting, so send to the
- * extended quads as well---Quads must be VIC booted */
- outb((__u8) (cpuset), VIC_CPI_Registers[cpi]);
- return;
- }
- if (quad_cpuset)
- send_QIC_CPI(quad_cpuset, cpi);
- cpuset &= ~quad_cpuset;
- cpuset &= 0xff; /* only first 8 CPUs vaild for VIC CPI */
- if (cpuset == 0)
- return;
- for_each_online_cpu(cpu) {
- if (cpuset & (1 << cpu))
- set_bit(cpi, &vic_cpi_mailbox[cpu]);
- }
- if (cpuset)
- outb((__u8) cpuset, VIC_CPI_Registers[VIC_CPI_LEVEL0]);
-}
-
-/* Acknowledge receipt of CPI in the QIC, clear in QIC hardware and
- * set the cache line to shared by reading it.
- *
- * DON'T make this inline otherwise the cache line read will be
- * optimised away
- * */
-static int ack_QIC_CPI(__u8 cpi)
-{
- __u8 cpu = hard_smp_processor_id();
-
- cpi &= 7;
-
- outb(1 << cpi, QIC_INTERRUPT_CLEAR1);
- return voyager_quad_cpi_addr[cpu]->qic_cpi[cpi].cpi;
-}
-
-static void ack_special_QIC_CPI(__u8 cpi)
-{
- switch (cpi) {
- case VIC_CMN_INT:
- outb(QIC_CMN_INT, QIC_INTERRUPT_CLEAR0);
- break;
- case VIC_SYS_INT:
- outb(QIC_SYS_INT, QIC_INTERRUPT_CLEAR0);
- break;
- }
- /* also clear at the VIC, just in case (nop for non-extended proc) */
- ack_VIC_CPI(cpi);
-}
-
-/* Acknowledge receipt of CPI in the VIC (essentially an EOI) */
-static void ack_VIC_CPI(__u8 cpi)
-{
-#ifdef VOYAGER_DEBUG
- unsigned long flags;
- __u16 isr;
- __u8 cpu = smp_processor_id();
-
- local_irq_save(flags);
- isr = vic_read_isr();
- if ((isr & (1 << (cpi & 7))) == 0) {
- printk("VOYAGER SMP: CPU%d lost CPI%d\n", cpu, cpi);
- }
-#endif
- /* send specific EOI; the two system interrupts have
- * bit 4 set for a separate vector but behave as the
- * corresponding 3 bit intr */
- outb_p(0x60 | (cpi & 7), 0x20);
-
-#ifdef VOYAGER_DEBUG
- if ((vic_read_isr() & (1 << (cpi & 7))) != 0) {
- printk("VOYAGER SMP: CPU%d still asserting CPI%d\n", cpu, cpi);
- }
- local_irq_restore(flags);
-#endif
-}
-
-/* cribbed with thanks from irq.c */
-#define __byte(x,y) (((unsigned char *)&(y))[x])
-#define cached_21(cpu) (__byte(0,vic_irq_mask[cpu]))
-#define cached_A1(cpu) (__byte(1,vic_irq_mask[cpu]))
-
-static unsigned int startup_vic_irq(unsigned int irq)
-{
- unmask_vic_irq(irq);
-
- return 0;
-}
-
-/* The enable and disable routines. This is where we run into
- * conflicting architectural philosophy. Fundamentally, the voyager
- * architecture does not expect to have to disable interrupts globally
- * (the IRQ controllers belong to each CPU). The processor masquerade
- * which is used to start the system shouldn't be used in a running OS
- * since it will cause great confusion if two separate CPUs drive to
- * the same IRQ controller (I know, I've tried it).
- *
- * The solution is a variant on the NCR lazy SPL design:
- *
- * 1) To disable an interrupt, do nothing (other than set the
- * IRQ_DISABLED flag). This dares the interrupt actually to arrive.
- *
- * 2) If the interrupt dares to come in, raise the local mask against
- * it (this will result in all the CPU masks being raised
- * eventually).
- *
- * 3) To enable the interrupt, lower the mask on the local CPU and
- * broadcast an Interrupt enable CPI which causes all other CPUs to
- * adjust their masks accordingly. */
-
-static void unmask_vic_irq(unsigned int irq)
-{
- /* linux doesn't to processor-irq affinity, so enable on
- * all CPUs we know about */
- int cpu = smp_processor_id(), real_cpu;
- __u16 mask = (1 << irq);
- __u32 processorList = 0;
- unsigned long flags;
-
- VDEBUG(("VOYAGER: unmask_vic_irq(%d) CPU%d affinity 0x%lx\n",
- irq, cpu, cpu_irq_affinity[cpu]));
- spin_lock_irqsave(&vic_irq_lock, flags);
- for_each_online_cpu(real_cpu) {
- if (!(voyager_extended_vic_processors & (1 << real_cpu)))
- continue;
- if (!(cpu_irq_affinity[real_cpu] & mask)) {
- /* irq has no affinity for this CPU, ignore */
- continue;
- }
- if (real_cpu == cpu) {
- enable_local_vic_irq(irq);
- } else if (vic_irq_mask[real_cpu] & mask) {
- vic_irq_enable_mask[real_cpu] |= mask;
- processorList |= (1 << real_cpu);
- }
- }
- spin_unlock_irqrestore(&vic_irq_lock, flags);
- if (processorList)
- send_CPI(processorList, VIC_ENABLE_IRQ_CPI);
-}
-
-static void mask_vic_irq(unsigned int irq)
-{
- /* lazy disable, do nothing */
-}
-
-static void enable_local_vic_irq(unsigned int irq)
-{
- __u8 cpu = smp_processor_id();
- __u16 mask = ~(1 << irq);
- __u16 old_mask = vic_irq_mask[cpu];
-
- vic_irq_mask[cpu] &= mask;
- if (vic_irq_mask[cpu] == old_mask)
- return;
-
- VDEBUG(("VOYAGER DEBUG: Enabling irq %d in hardware on CPU %d\n",
- irq, cpu));
-
- if (irq & 8) {
- outb_p(cached_A1(cpu), 0xA1);
- (void)inb_p(0xA1);
- } else {
- outb_p(cached_21(cpu), 0x21);
- (void)inb_p(0x21);
- }
-}
-
-static void disable_local_vic_irq(unsigned int irq)
-{
- __u8 cpu = smp_processor_id();
- __u16 mask = (1 << irq);
- __u16 old_mask = vic_irq_mask[cpu];
-
- if (irq == 7)
- return;
-
- vic_irq_mask[cpu] |= mask;
- if (old_mask == vic_irq_mask[cpu])
- return;
-
- VDEBUG(("VOYAGER DEBUG: Disabling irq %d in hardware on CPU %d\n",
- irq, cpu));
-
- if (irq & 8) {
- outb_p(cached_A1(cpu), 0xA1);
- (void)inb_p(0xA1);
- } else {
- outb_p(cached_21(cpu), 0x21);
- (void)inb_p(0x21);
- }
-}
-
-/* The VIC is level triggered, so the ack can only be issued after the
- * interrupt completes. However, we do Voyager lazy interrupt
- * handling here: It is an extremely expensive operation to mask an
- * interrupt in the vic, so we merely set a flag (IRQ_DISABLED). If
- * this interrupt actually comes in, then we mask and ack here to push
- * the interrupt off to another CPU */
-static void before_handle_vic_irq(unsigned int irq)
-{
- irq_desc_t *desc = irq_to_desc(irq);
- __u8 cpu = smp_processor_id();
-
- _raw_spin_lock(&vic_irq_lock);
- vic_intr_total++;
- vic_intr_count[cpu]++;
-
- if (!(cpu_irq_affinity[cpu] & (1 << irq))) {
- /* The irq is not in our affinity mask, push it off
- * onto another CPU */
- VDEBUG(("VOYAGER DEBUG: affinity triggered disable of irq %d "
- "on cpu %d\n", irq, cpu));
- disable_local_vic_irq(irq);
- /* set IRQ_INPROGRESS to prevent the handler in irq.c from
- * actually calling the interrupt routine */
- desc->status |= IRQ_REPLAY | IRQ_INPROGRESS;
- } else if (desc->status & IRQ_DISABLED) {
- /* Damn, the interrupt actually arrived, do the lazy
- * disable thing. The interrupt routine in irq.c will
- * not handle a IRQ_DISABLED interrupt, so nothing more
- * need be done here */
- VDEBUG(("VOYAGER DEBUG: lazy disable of irq %d on CPU %d\n",
- irq, cpu));
- disable_local_vic_irq(irq);
- desc->status |= IRQ_REPLAY;
- } else {
- desc->status &= ~IRQ_REPLAY;
- }
-
- _raw_spin_unlock(&vic_irq_lock);
-}
-
-/* Finish the VIC interrupt: basically mask */
-static void after_handle_vic_irq(unsigned int irq)
-{
- irq_desc_t *desc = irq_to_desc(irq);
-
- _raw_spin_lock(&vic_irq_lock);
- {
- unsigned int status = desc->status & ~IRQ_INPROGRESS;
-#ifdef VOYAGER_DEBUG
- __u16 isr;
-#endif
-
- desc->status = status;
- if ((status & IRQ_DISABLED))
- disable_local_vic_irq(irq);
-#ifdef VOYAGER_DEBUG
- /* DEBUG: before we ack, check what's in progress */
- isr = vic_read_isr();
- if ((isr & (1 << irq) && !(status & IRQ_REPLAY)) == 0) {
- int i;
- __u8 cpu = smp_processor_id();
- __u8 real_cpu;
- int mask; /* Um... initialize me??? --RR */
-
- printk("VOYAGER SMP: CPU%d lost interrupt %d\n",
- cpu, irq);
- for_each_possible_cpu(real_cpu, mask) {
-
- outb(VIC_CPU_MASQUERADE_ENABLE | real_cpu,
- VIC_PROCESSOR_ID);
- isr = vic_read_isr();
- if (isr & (1 << irq)) {
- printk
- ("VOYAGER SMP: CPU%d ack irq %d\n",
- real_cpu, irq);
- ack_vic_irq(irq);
- }
- outb(cpu, VIC_PROCESSOR_ID);
- }
- }
-#endif /* VOYAGER_DEBUG */
- /* as soon as we ack, the interrupt is eligible for
- * receipt by another CPU so everything must be in
- * order here */
- ack_vic_irq(irq);
- if (status & IRQ_REPLAY) {
- /* replay is set if we disable the interrupt
- * in the before_handle_vic_irq() routine, so
- * clear the in progress bit here to allow the
- * next CPU to handle this correctly */
- desc->status &= ~(IRQ_REPLAY | IRQ_INPROGRESS);
- }
-#ifdef VOYAGER_DEBUG
- isr = vic_read_isr();
- if ((isr & (1 << irq)) != 0)
- printk("VOYAGER SMP: after_handle_vic_irq() after "
- "ack irq=%d, isr=0x%x\n", irq, isr);
-#endif /* VOYAGER_DEBUG */
- }
- _raw_spin_unlock(&vic_irq_lock);
-
- /* All code after this point is out of the main path - the IRQ
- * may be intercepted by another CPU if reasserted */
-}
-
-/* Linux processor - interrupt affinity manipulations.
- *
- * For each processor, we maintain a 32 bit irq affinity mask.
- * Initially it is set to all 1's so every processor accepts every
- * interrupt. In this call, we change the processor's affinity mask:
- *
- * Change from enable to disable:
- *
- * If the interrupt ever comes in to the processor, we will disable it
- * and ack it to push it off to another CPU, so just accept the mask here.
- *
- * Change from disable to enable:
- *
- * change the mask and then do an interrupt enable CPI to re-enable on
- * the selected processors */
-
-void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask)
-{
- /* Only extended processors handle interrupts */
- unsigned long real_mask;
- unsigned long irq_mask = 1 << irq;
- int cpu;
-
- real_mask = cpus_addr(*mask)[0] & voyager_extended_vic_processors;
-
- if (cpus_addr(*mask)[0] == 0)
- /* can't have no CPUs to accept the interrupt -- extremely
- * bad things will happen */
- return;
-
- if (irq == 0)
- /* can't change the affinity of the timer IRQ. This
- * is due to the constraint in the voyager
- * architecture that the CPI also comes in on and IRQ
- * line and we have chosen IRQ0 for this. If you
- * raise the mask on this interrupt, the processor
- * will no-longer be able to accept VIC CPIs */
- return;
-
- if (irq >= 32)
- /* You can only have 32 interrupts in a voyager system
- * (and 32 only if you have a secondary microchannel
- * bus) */
- return;
-
- for_each_online_cpu(cpu) {
- unsigned long cpu_mask = 1 << cpu;
-
- if (cpu_mask & real_mask) {
- /* enable the interrupt for this cpu */
- cpu_irq_affinity[cpu] |= irq_mask;
- } else {
- /* disable the interrupt for this cpu */
- cpu_irq_affinity[cpu] &= ~irq_mask;
- }
- }
- /* this is magic, we now have the correct affinity maps, so
- * enable the interrupt. This will send an enable CPI to
- * those CPUs who need to enable it in their local masks,
- * causing them to correct for the new affinity . If the
- * interrupt is currently globally disabled, it will simply be
- * disabled again as it comes in (voyager lazy disable). If
- * the affinity map is tightened to disable the interrupt on a
- * cpu, it will be pushed off when it comes in */
- unmask_vic_irq(irq);
-}
-
-static void ack_vic_irq(unsigned int irq)
-{
- if (irq & 8) {
- outb(0x62, 0x20); /* Specific EOI to cascade */
- outb(0x60 | (irq & 7), 0xA0);
- } else {
- outb(0x60 | (irq & 7), 0x20);
- }
-}
-
-/* enable the CPIs. In the VIC, the CPIs are delivered by the 8259
- * but are not vectored by it. This means that the 8259 mask must be
- * lowered to receive them */
-static __init void vic_enable_cpi(void)
-{
- __u8 cpu = smp_processor_id();
-
- /* just take a copy of the current mask (nop for boot cpu) */
- vic_irq_mask[cpu] = vic_irq_mask[boot_cpu_id];
-
- enable_local_vic_irq(VIC_CPI_LEVEL0);
- enable_local_vic_irq(VIC_CPI_LEVEL1);
- /* for sys int and cmn int */
- enable_local_vic_irq(7);
-
- if (is_cpu_quad()) {
- outb(QIC_DEFAULT_MASK0, QIC_MASK_REGISTER0);
- outb(QIC_CPI_ENABLE, QIC_MASK_REGISTER1);
- VDEBUG(("VOYAGER SMP: QIC ENABLE CPI: CPU%d: MASK 0x%x\n",
- cpu, QIC_CPI_ENABLE));
- }
-
- VDEBUG(("VOYAGER SMP: ENABLE CPI: CPU%d: MASK 0x%x\n",
- cpu, vic_irq_mask[cpu]));
-}
-
-void voyager_smp_dump()
-{
- int old_cpu = smp_processor_id(), cpu;
-
- /* dump the interrupt masks of each processor */
- for_each_online_cpu(cpu) {
- __u16 imr, isr, irr;
- unsigned long flags;
-
- local_irq_save(flags);
- outb(VIC_CPU_MASQUERADE_ENABLE | cpu, VIC_PROCESSOR_ID);
- imr = (inb(0xa1) << 8) | inb(0x21);
- outb(0x0a, 0xa0);
- irr = inb(0xa0) << 8;
- outb(0x0a, 0x20);
- irr |= inb(0x20);
- outb(0x0b, 0xa0);
- isr = inb(0xa0) << 8;
- outb(0x0b, 0x20);
- isr |= inb(0x20);
- outb(old_cpu, VIC_PROCESSOR_ID);
- local_irq_restore(flags);
- printk("\tCPU%d: mask=0x%x, IMR=0x%x, IRR=0x%x, ISR=0x%x\n",
- cpu, vic_irq_mask[cpu], imr, irr, isr);
-#if 0
- /* These lines are put in to try to unstick an un ack'd irq */
- if (isr != 0) {
- int irq;
- for (irq = 0; irq < 16; irq++) {
- if (isr & (1 << irq)) {
- printk("\tCPU%d: ack irq %d\n",
- cpu, irq);
- local_irq_save(flags);
- outb(VIC_CPU_MASQUERADE_ENABLE | cpu,
- VIC_PROCESSOR_ID);
- ack_vic_irq(irq);
- outb(old_cpu, VIC_PROCESSOR_ID);
- local_irq_restore(flags);
- }
- }
- }
-#endif
- }
-}
-
-void smp_voyager_power_off(void *dummy)
-{
- if (smp_processor_id() == boot_cpu_id)
- voyager_power_off();
- else
- smp_stop_cpu_function(NULL);
-}
-
-static void __init voyager_smp_prepare_cpus(unsigned int max_cpus)
-{
- /* FIXME: ignore max_cpus for now */
- smp_boot_cpus();
-}
-
-static void __cpuinit voyager_smp_prepare_boot_cpu(void)
-{
- int cpu = smp_processor_id();
- switch_to_new_gdt(cpu);
-
- cpu_set(cpu, cpu_online_map);
- cpu_set(cpu, cpu_callout_map);
- cpu_set(cpu, cpu_possible_map);
- cpu_set(cpu, cpu_present_map);
-
-}
-
-static int __cpuinit voyager_cpu_up(unsigned int cpu)
-{
- /* This only works at boot for x86. See "rewrite" above. */
- if (cpu_isset(cpu, smp_commenced_mask))
- return -ENOSYS;
-
- /* In case one didn't come up */
- if (!cpu_isset(cpu, cpu_callin_map))
- return -EIO;
- /* Unleash the CPU! */
- cpu_set(cpu, smp_commenced_mask);
- while (!cpu_online(cpu))
- mb();
- return 0;
-}
-
-static void __init voyager_smp_cpus_done(unsigned int max_cpus)
-{
- zap_low_mappings();
-}
-
-void __init smp_setup_processor_id(void)
-{
- current_thread_info()->cpu = hard_smp_processor_id();
-}
-
-static void voyager_send_call_func(const struct cpumask *callmask)
-{
- __u32 mask = cpus_addr(*callmask)[0] & ~(1 << smp_processor_id());
- send_CPI(mask, VIC_CALL_FUNCTION_CPI);
-}
-
-static void voyager_send_call_func_single(int cpu)
-{
- send_CPI(1 << cpu, VIC_CALL_FUNCTION_SINGLE_CPI);
-}
-
-struct smp_ops smp_ops = {
- .smp_prepare_boot_cpu = voyager_smp_prepare_boot_cpu,
- .smp_prepare_cpus = voyager_smp_prepare_cpus,
- .cpu_up = voyager_cpu_up,
- .smp_cpus_done = voyager_smp_cpus_done,
-
- .smp_send_stop = voyager_smp_send_stop,
- .smp_send_reschedule = voyager_smp_send_reschedule,
-
- .send_call_func_ipi = voyager_send_call_func,
- .send_call_func_single_ipi = voyager_send_call_func_single,
-};
diff --git a/arch/x86/mach-voyager/voyager_thread.c b/arch/x86/mach-voyager/voyager_thread.c
deleted file mode 100644
index 15464a2..0000000
--- a/arch/x86/mach-voyager/voyager_thread.c
+++ /dev/null
@@ -1,128 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * This module provides the machine status monitor thread for the
- * voyager architecture. This allows us to monitor the machine
- * environment (temp, voltage, fan function) and the front panel and
- * internal UPS. If a fault is detected, this thread takes corrective
- * action (usually just informing init)
- * */
-
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/kernel_stat.h>
-#include <linux/delay.h>
-#include <linux/mc146818rtc.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/kmod.h>
-#include <linux/completion.h>
-#include <linux/sched.h>
-#include <linux/kthread.h>
-#include <asm/desc.h>
-#include <asm/voyager.h>
-#include <asm/vic.h>
-#include <asm/mtrr.h>
-#include <asm/msr.h>
-
-struct task_struct *voyager_thread;
-static __u8 set_timeout;
-
-static int execute(const char *string)
-{
- int ret;
-
- char *envp[] = {
- "HOME=/",
- "TERM=linux",
- "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
- NULL,
- };
- char *argv[] = {
- "/bin/bash",
- "-c",
- (char *)string,
- NULL,
- };
-
- if ((ret =
- call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC)) != 0) {
- printk(KERN_ERR "Voyager failed to run \"%s\": %i\n", string,
- ret);
- }
- return ret;
-}
-
-static void check_from_kernel(void)
-{
- if (voyager_status.switch_off) {
-
- /* FIXME: This should be configurable via proc */
- execute("umask 600; echo 0 > /etc/initrunlvl; kill -HUP 1");
- } else if (voyager_status.power_fail) {
- VDEBUG(("Voyager daemon detected AC power failure\n"));
-
- /* FIXME: This should be configureable via proc */
- execute("umask 600; echo F > /etc/powerstatus; kill -PWR 1");
- set_timeout = 1;
- }
-}
-
-static void check_continuing_condition(void)
-{
- if (voyager_status.power_fail) {
- __u8 data;
- voyager_cat_psi(VOYAGER_PSI_SUBREAD,
- VOYAGER_PSI_AC_FAIL_REG, &data);
- if ((data & 0x1f) == 0) {
- /* all power restored */
- printk(KERN_NOTICE
- "VOYAGER AC power restored, cancelling shutdown\n");
- /* FIXME: should be user configureable */
- execute
- ("umask 600; echo O > /etc/powerstatus; kill -PWR 1");
- set_timeout = 0;
- }
- }
-}
-
-static int thread(void *unused)
-{
- printk(KERN_NOTICE "Voyager starting monitor thread\n");
-
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(set_timeout ? HZ : MAX_SCHEDULE_TIMEOUT);
-
- VDEBUG(("Voyager Daemon awoken\n"));
- if (voyager_status.request_from_kernel == 0) {
- /* probably awoken from timeout */
- check_continuing_condition();
- } else {
- check_from_kernel();
- voyager_status.request_from_kernel = 0;
- }
- }
-}
-
-static int __init voyager_thread_start(void)
-{
- voyager_thread = kthread_run(thread, NULL, "kvoyagerd");
- if (IS_ERR(voyager_thread)) {
- printk(KERN_ERR
- "Voyager: Failed to create system monitor thread.\n");
- return PTR_ERR(voyager_thread);
- }
- return 0;
-}
-
-static void __exit voyager_thread_stop(void)
-{
- kthread_stop(voyager_thread);
-}
-
-module_init(voyager_thread_start);
-module_exit(voyager_thread_stop);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2964417..a03b727 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1,74 +1,79 @@
/*
* Copyright (C) 1995 Linus Torvalds
- * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mmiotrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/tty.h>
-#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/mmiotrace.h>
+#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
-#include <linux/bootmem.h> /* for max_low_pfn */
-#include <linux/vmalloc.h>
-#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/vt_kern.h>
+#include <linux/signal.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/module.h>
#include <linux/kdebug.h>
+#include <linux/errno.h>
#include <linux/magic.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/mman.h>
+#include <linux/tty.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
-#include <asm/system.h>
-#include <asm/desc.h>
-#include <asm/segment.h>
-#include <asm/pgalloc.h>
-#include <asm/smp.h>
-#include <asm/tlbflush.h>
-#include <asm/proto.h>
#include <asm-generic/sections.h>
+
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/segment.h>
+#include <asm/system.h>
+#include <asm/proto.h>
#include <asm/traps.h>
+#include <asm/desc.h>
/*
- * Page fault error code bits
- * bit 0 == 0 means no page found, 1 means protection fault
- * bit 1 == 0 means read, 1 means write
- * bit 2 == 0 means kernel, 1 means user-mode
- * bit 3 == 1 means use of reserved bit detected
- * bit 4 == 1 means fault was an instruction fetch
+ * Page fault error code bits:
+ *
+ * bit 0 == 0: no page found 1: protection fault
+ * bit 1 == 0: read access 1: write access
+ * bit 2 == 0: kernel-mode access 1: user-mode access
+ * bit 3 == 1: use of reserved bit detected
+ * bit 4 == 1: fault was an instruction fetch
*/
-#define PF_PROT (1<<0)
-#define PF_WRITE (1<<1)
-#define PF_USER (1<<2)
-#define PF_RSVD (1<<3)
-#define PF_INSTR (1<<4)
+enum x86_pf_error_code {
+ PF_PROT = 1 << 0,
+ PF_WRITE = 1 << 1,
+ PF_USER = 1 << 2,
+ PF_RSVD = 1 << 3,
+ PF_INSTR = 1 << 4,
+};
+
+/*
+ * Returns 0 if mmiotrace is disabled, or if the fault is not
+ * handled by mmiotrace:
+ */
static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
{
-#ifdef CONFIG_MMIOTRACE
if (unlikely(is_kmmio_active()))
if (kmmio_handler(regs, addr) == 1)
return -1;
-#endif
return 0;
}
static inline int notify_page_fault(struct pt_regs *regs)
{
-#ifdef CONFIG_KPROBES
int ret = 0;
/* kprobe_running() needs smp_processor_id() */
- if (!user_mode_vm(regs)) {
+ if (kprobes_built_in() && !user_mode_vm(regs)) {
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 14))
ret = 1;
@@ -76,29 +81,76 @@
}
return ret;
-#else
- return 0;
-#endif
}
/*
- * X86_32
- * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * Prefetch quirks:
*
- * X86_64
- * Sometimes the CPU reports invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * 32-bit mode:
*
- * Opcode checker based on code by Richard Brunner
+ * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ *
+ * 64-bit mode:
+ *
+ * Sometimes the CPU reports invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ *
+ * Opcode checker based on code by Richard Brunner.
*/
-static int is_prefetch(struct pt_regs *regs, unsigned long error_code,
- unsigned long addr)
+static inline int
+check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
+ unsigned char opcode, int *prefetch)
{
- unsigned char *instr;
- int scan_more = 1;
- int prefetch = 0;
+ unsigned char instr_hi = opcode & 0xf0;
+ unsigned char instr_lo = opcode & 0x0f;
+
+ switch (instr_hi) {
+ case 0x20:
+ case 0x30:
+ /*
+ * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
+ * In X86_64 long mode, the CPU will signal invalid
+ * opcode if some of these prefixes are present so
+ * X86_64 will never get here anyway
+ */
+ return ((instr_lo & 7) == 0x6);
+#ifdef CONFIG_X86_64
+ case 0x40:
+ /*
+ * In AMD64 long mode 0x40..0x4F are valid REX prefixes
+ * Need to figure out under what instruction mode the
+ * instruction was issued. Could check the LDT for lm,
+ * but for now it's good enough to assume that long
+ * mode only uses well known segments or kernel.
+ */
+ return (!user_mode(regs)) || (regs->cs == __USER_CS);
+#endif
+ case 0x60:
+ /* 0x64 thru 0x67 are valid prefixes in all modes. */
+ return (instr_lo & 0xC) == 0x4;
+ case 0xF0:
+ /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
+ return !instr_lo || (instr_lo>>1) == 1;
+ case 0x00:
+ /* Prefetch instruction is 0x0F0D or 0x0F18 */
+ if (probe_kernel_address(instr, opcode))
+ return 0;
+
+ *prefetch = (instr_lo == 0xF) &&
+ (opcode == 0x0D || opcode == 0x18);
+ return 0;
+ default:
+ return 0;
+ }
+}
+
+static int
+is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
+{
unsigned char *max_instr;
+ unsigned char *instr;
+ int prefetch = 0;
/*
* If it was a exec (instruction fetch) fault on NX page, then
@@ -107,164 +159,42 @@
if (error_code & PF_INSTR)
return 0;
- instr = (unsigned char *)convert_ip_to_linear(current, regs);
+ instr = (void *)convert_ip_to_linear(current, regs);
max_instr = instr + 15;
if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
return 0;
- while (scan_more && instr < max_instr) {
+ while (instr < max_instr) {
unsigned char opcode;
- unsigned char instr_hi;
- unsigned char instr_lo;
if (probe_kernel_address(instr, opcode))
break;
- instr_hi = opcode & 0xf0;
- instr_lo = opcode & 0x0f;
instr++;
- switch (instr_hi) {
- case 0x20:
- case 0x30:
- /*
- * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
- * In X86_64 long mode, the CPU will signal invalid
- * opcode if some of these prefixes are present so
- * X86_64 will never get here anyway
- */
- scan_more = ((instr_lo & 7) == 0x6);
+ if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
break;
-#ifdef CONFIG_X86_64
- case 0x40:
- /*
- * In AMD64 long mode 0x40..0x4F are valid REX prefixes
- * Need to figure out under what instruction mode the
- * instruction was issued. Could check the LDT for lm,
- * but for now it's good enough to assume that long
- * mode only uses well known segments or kernel.
- */
- scan_more = (!user_mode(regs)) || (regs->cs == __USER_CS);
- break;
-#endif
- case 0x60:
- /* 0x64 thru 0x67 are valid prefixes in all modes. */
- scan_more = (instr_lo & 0xC) == 0x4;
- break;
- case 0xF0:
- /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
- scan_more = !instr_lo || (instr_lo>>1) == 1;
- break;
- case 0x00:
- /* Prefetch instruction is 0x0F0D or 0x0F18 */
- scan_more = 0;
-
- if (probe_kernel_address(instr, opcode))
- break;
- prefetch = (instr_lo == 0xF) &&
- (opcode == 0x0D || opcode == 0x18);
- break;
- default:
- scan_more = 0;
- break;
- }
}
return prefetch;
}
-static void force_sig_info_fault(int si_signo, int si_code,
- unsigned long address, struct task_struct *tsk)
+static void
+force_sig_info_fault(int si_signo, int si_code, unsigned long address,
+ struct task_struct *tsk)
{
siginfo_t info;
- info.si_signo = si_signo;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)address;
+ info.si_signo = si_signo;
+ info.si_errno = 0;
+ info.si_code = si_code;
+ info.si_addr = (void __user *)address;
+
force_sig_info(si_signo, &info, tsk);
}
-#ifdef CONFIG_X86_64
-static int bad_address(void *p)
-{
- unsigned long dummy;
- return probe_kernel_address((unsigned long *)p, dummy);
-}
-#endif
-
-static void dump_pagetable(unsigned long address)
-{
-#ifdef CONFIG_X86_32
- __typeof__(pte_val(__pte(0))) page;
-
- page = read_cr3();
- page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
-#ifdef CONFIG_X86_PAE
- printk("*pdpt = %016Lx ", page);
- if ((page >> PAGE_SHIFT) < max_low_pfn
- && page & _PAGE_PRESENT) {
- page &= PAGE_MASK;
- page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
- & (PTRS_PER_PMD - 1)];
- printk(KERN_CONT "*pde = %016Lx ", page);
- page &= ~_PAGE_NX;
- }
-#else
- printk("*pde = %08lx ", page);
-#endif
-
- /*
- * We must not directly access the pte in the highpte
- * case if the page table is located in highmem.
- * And let's rather not kmap-atomic the pte, just in case
- * it's allocated already.
- */
- if ((page >> PAGE_SHIFT) < max_low_pfn
- && (page & _PAGE_PRESENT)
- && !(page & _PAGE_PSE)) {
- page &= PAGE_MASK;
- page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
- & (PTRS_PER_PTE - 1)];
- printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
- }
-
- printk("\n");
-#else /* CONFIG_X86_64 */
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- pgd = (pgd_t *)read_cr3();
-
- pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
- pgd += pgd_index(address);
- if (bad_address(pgd)) goto bad;
- printk("PGD %lx ", pgd_val(*pgd));
- if (!pgd_present(*pgd)) goto ret;
-
- pud = pud_offset(pgd, address);
- if (bad_address(pud)) goto bad;
- printk("PUD %lx ", pud_val(*pud));
- if (!pud_present(*pud) || pud_large(*pud))
- goto ret;
-
- pmd = pmd_offset(pud, address);
- if (bad_address(pmd)) goto bad;
- printk("PMD %lx ", pmd_val(*pmd));
- if (!pmd_present(*pmd) || pmd_large(*pmd)) goto ret;
-
- pte = pte_offset_kernel(pmd, address);
- if (bad_address(pte)) goto bad;
- printk("PTE %lx", pte_val(*pte));
-ret:
- printk("\n");
- return;
-bad:
- printk("BAD\n");
-#endif
-}
+DEFINE_SPINLOCK(pgd_lock);
+LIST_HEAD(pgd_list);
#ifdef CONFIG_X86_32
static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
@@ -285,7 +215,6 @@
* and redundant with the set_pmd() on non-PAE. As would
* set_pud.
*/
-
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
@@ -295,46 +224,334 @@
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
return NULL;
+
if (!pmd_present(*pmd)) {
set_pmd(pmd, *pmd_k);
arch_flush_lazy_mmu_mode();
- } else
+ } else {
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+ }
+
return pmd_k;
}
+
+void vmalloc_sync_all(void)
+{
+ unsigned long address;
+
+ if (SHARED_KERNEL_PMD)
+ return;
+
+ for (address = VMALLOC_START & PMD_MASK;
+ address >= TASK_SIZE && address < FIXADDR_TOP;
+ address += PMD_SIZE) {
+
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (!vmalloc_sync_one(page_address(page), address))
+ break;
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
+ * 32-bit:
+ *
+ * Handle a fault on the vmalloc or module mapping area
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+ unsigned long pgd_paddr;
+ pmd_t *pmd_k;
+ pte_t *pte_k;
+
+ /* Make sure we are in vmalloc area: */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "current" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ pgd_paddr = read_cr3();
+ pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+ if (!pmd_k)
+ return -1;
+
+ pte_k = pte_offset_kernel(pmd_k, address);
+ if (!pte_present(*pte_k))
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Did it hit the DOS screen memory VA from vm86 mode?
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+ struct task_struct *tsk)
+{
+ unsigned long bit;
+
+ if (!v8086_mode(regs))
+ return;
+
+ bit = (address - 0xA0000) >> PAGE_SHIFT;
+ if (bit < 32)
+ tsk->thread.screen_bitmap |= 1 << bit;
+}
+
+static void dump_pagetable(unsigned long address)
+{
+ __typeof__(pte_val(__pte(0))) page;
+
+ page = read_cr3();
+ page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
+
+#ifdef CONFIG_X86_PAE
+ printk("*pdpt = %016Lx ", page);
+ if ((page >> PAGE_SHIFT) < max_low_pfn
+ && page & _PAGE_PRESENT) {
+ page &= PAGE_MASK;
+ page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
+ & (PTRS_PER_PMD - 1)];
+ printk(KERN_CONT "*pde = %016Lx ", page);
+ page &= ~_PAGE_NX;
+ }
+#else
+ printk("*pde = %08lx ", page);
#endif
-#ifdef CONFIG_X86_64
+ /*
+ * We must not directly access the pte in the highpte
+ * case if the page table is located in highmem.
+ * And let's rather not kmap-atomic the pte, just in case
+ * it's allocated already:
+ */
+ if ((page >> PAGE_SHIFT) < max_low_pfn
+ && (page & _PAGE_PRESENT)
+ && !(page & _PAGE_PSE)) {
+
+ page &= PAGE_MASK;
+ page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
+ & (PTRS_PER_PTE - 1)];
+ printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
+ }
+
+ printk("\n");
+}
+
+#else /* CONFIG_X86_64: */
+
+void vmalloc_sync_all(void)
+{
+ unsigned long address;
+
+ for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
+ address += PGDIR_SIZE) {
+
+ const pgd_t *pgd_ref = pgd_offset_k(address);
+ unsigned long flags;
+ struct page *page;
+
+ if (pgd_none(*pgd_ref))
+ continue;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd;
+ pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
+ * 64-bit:
+ *
+ * Handle a fault on the vmalloc area
+ *
+ * This assumes no large pages in there.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+ pgd_t *pgd, *pgd_ref;
+ pud_t *pud, *pud_ref;
+ pmd_t *pmd, *pmd_ref;
+ pte_t *pte, *pte_ref;
+
+ /* Make sure we are in vmalloc area: */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
+ /*
+ * Copy kernel mappings over when needed. This can also
+ * happen within a race in page table update. In the later
+ * case just flush:
+ */
+ pgd = pgd_offset(current->active_mm, address);
+ pgd_ref = pgd_offset_k(address);
+ if (pgd_none(*pgd_ref))
+ return -1;
+
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+
+ /*
+ * Below here mismatches are bugs because these lower tables
+ * are shared:
+ */
+
+ pud = pud_offset(pgd, address);
+ pud_ref = pud_offset(pgd_ref, address);
+ if (pud_none(*pud_ref))
+ return -1;
+
+ if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+ BUG();
+
+ pmd = pmd_offset(pud, address);
+ pmd_ref = pmd_offset(pud_ref, address);
+ if (pmd_none(*pmd_ref))
+ return -1;
+
+ if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+ BUG();
+
+ pte_ref = pte_offset_kernel(pmd_ref, address);
+ if (!pte_present(*pte_ref))
+ return -1;
+
+ pte = pte_offset_kernel(pmd, address);
+
+ /*
+ * Don't use pte_page here, because the mappings can point
+ * outside mem_map, and the NUMA hash lookup cannot handle
+ * that:
+ */
+ if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
+ BUG();
+
+ return 0;
+}
+
static const char errata93_warning[] =
KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n"
KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n"
KERN_ERR "******* Please consider a BIOS update.\n"
KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n";
-#endif
-/* Workaround for K8 erratum #93 & buggy BIOS.
- BIOS SMM functions are required to use a specific workaround
- to avoid corruption of the 64bit RIP register on C stepping K8.
- A lot of BIOS that didn't get tested properly miss this.
- The OS sees this as a page fault with the upper 32bits of RIP cleared.
- Try to work around it here.
- Note we only handle faults in kernel here.
- Does nothing for X86_32
+/*
+ * No vm86 mode in 64-bit mode:
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+ struct task_struct *tsk)
+{
+}
+
+static int bad_address(void *p)
+{
+ unsigned long dummy;
+
+ return probe_kernel_address((unsigned long *)p, dummy);
+}
+
+static void dump_pagetable(unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = (pgd_t *)read_cr3();
+
+ pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
+
+ pgd += pgd_index(address);
+ if (bad_address(pgd))
+ goto bad;
+
+ printk("PGD %lx ", pgd_val(*pgd));
+
+ if (!pgd_present(*pgd))
+ goto out;
+
+ pud = pud_offset(pgd, address);
+ if (bad_address(pud))
+ goto bad;
+
+ printk("PUD %lx ", pud_val(*pud));
+ if (!pud_present(*pud) || pud_large(*pud))
+ goto out;
+
+ pmd = pmd_offset(pud, address);
+ if (bad_address(pmd))
+ goto bad;
+
+ printk("PMD %lx ", pmd_val(*pmd));
+ if (!pmd_present(*pmd) || pmd_large(*pmd))
+ goto out;
+
+ pte = pte_offset_kernel(pmd, address);
+ if (bad_address(pte))
+ goto bad;
+
+ printk("PTE %lx", pte_val(*pte));
+out:
+ printk("\n");
+ return;
+bad:
+ printk("BAD\n");
+}
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Workaround for K8 erratum #93 & buggy BIOS.
+ *
+ * BIOS SMM functions are required to use a specific workaround
+ * to avoid corruption of the 64bit RIP register on C stepping K8.
+ *
+ * A lot of BIOS that didn't get tested properly miss this.
+ *
+ * The OS sees this as a page fault with the upper 32bits of RIP cleared.
+ * Try to work around it here.
+ *
+ * Note we only handle faults in kernel here.
+ * Does nothing on 32-bit.
*/
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- static int warned;
+ static int once;
+
if (address != regs->ip)
return 0;
+
if ((address >> 32) != 0)
return 0;
+
address |= 0xffffffffUL << 32;
if ((address >= (u64)_stext && address <= (u64)_etext) ||
(address >= MODULES_VADDR && address <= MODULES_END)) {
- if (!warned) {
+ if (!once) {
printk(errata93_warning);
- warned = 1;
+ once = 1;
}
regs->ip = address;
return 1;
@@ -344,16 +561,17 @@
}
/*
- * Work around K8 erratum #100 K8 in compat mode occasionally jumps to illegal
- * addresses >4GB. We catch this in the page fault handler because these
- * addresses are not reachable. Just detect this case and return. Any code
+ * Work around K8 erratum #100 K8 in compat mode occasionally jumps
+ * to illegal addresses >4GB.
+ *
+ * We catch this in the page fault handler because these addresses
+ * are not reachable. Just detect this case and return. Any code
* segment in LDT is compatibility mode.
*/
static int is_errata100(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
- (address >> 32))
+ if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
return 1;
#endif
return 0;
@@ -363,8 +581,9 @@
{
#ifdef CONFIG_X86_F00F_BUG
unsigned long nr;
+
/*
- * Pentium F0 0F C7 C8 bug workaround.
+ * Pentium F0 0F C7 C8 bug workaround:
*/
if (boot_cpu_data.f00f_bug) {
nr = (address - idt_descr.address) >> 3;
@@ -378,80 +597,87 @@
return 0;
}
-static void show_fault_oops(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
+static const char nx_warning[] = KERN_CRIT
+"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
+
+static void
+show_fault_oops(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
-#ifdef CONFIG_X86_32
if (!oops_may_print())
return;
-#endif
-#ifdef CONFIG_X86_PAE
if (error_code & PF_INSTR) {
unsigned int level;
+
pte_t *pte = lookup_address(address, &level);
if (pte && pte_present(*pte) && !pte_exec(*pte))
- printk(KERN_CRIT "kernel tried to execute "
- "NX-protected page - exploit attempt? "
- "(uid: %d)\n", current_uid());
+ printk(nx_warning, current_uid());
}
-#endif
printk(KERN_ALERT "BUG: unable to handle kernel ");
if (address < PAGE_SIZE)
printk(KERN_CONT "NULL pointer dereference");
else
printk(KERN_CONT "paging request");
+
printk(KERN_CONT " at %p\n", (void *) address);
printk(KERN_ALERT "IP:");
printk_address(regs->ip, 1);
+
dump_pagetable(address);
}
-#ifdef CONFIG_X86_64
-static noinline void pgtable_bad(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+pgtable_bad(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
- unsigned long flags = oops_begin();
- int sig = SIGKILL;
- struct task_struct *tsk = current;
+ struct task_struct *tsk;
+ unsigned long flags;
+ int sig;
+
+ flags = oops_begin();
+ tsk = current;
+ sig = SIGKILL;
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
tsk->comm, address);
dump_pagetable(address);
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
+
if (__die("Bad pagetable", regs, error_code))
sig = 0;
+
oops_end(flags, regs, sig);
}
-#endif
-static noinline void no_context(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+no_context(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
struct task_struct *tsk = current;
unsigned long *stackend;
-
-#ifdef CONFIG_X86_64
unsigned long flags;
int sig;
-#endif
- /* Are we prepared to handle this kernel fault? */
+ /* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
/*
- * X86_32
- * Valid to do another page fault here, because if this fault
- * had been triggered by is_prefetch fixup_exception would have
- * handled it.
+ * 32-bit:
*
- * X86_64
- * Hall of shame of CPU/BIOS bugs.
+ * Valid to do another page fault here, because if this fault
+ * had been triggered by is_prefetch fixup_exception would have
+ * handled it.
+ *
+ * 64-bit:
+ *
+ * Hall of shame of CPU/BIOS bugs.
*/
if (is_prefetch(regs, error_code, address))
return;
@@ -461,54 +687,70 @@
/*
* Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
+ * terminate things with extreme prejudice:
*/
-#ifdef CONFIG_X86_32
- bust_spinlocks(1);
-#else
flags = oops_begin();
-#endif
show_fault_oops(regs, error_code, address);
- stackend = end_of_stack(tsk);
+ stackend = end_of_stack(tsk);
if (*stackend != STACK_END_MAGIC)
printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
-#ifdef CONFIG_X86_32
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
-#else
sig = SIGKILL;
if (__die("Oops", regs, error_code))
sig = 0;
+
/* Executive summary in case the body of the oops scrolled away */
printk(KERN_EMERG "CR2: %016lx\n", address);
+
oops_end(flags, regs, sig);
-#endif
}
-static void __bad_area_nosemaphore(struct pt_regs *regs,
- unsigned long error_code, unsigned long address,
- int si_code)
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, struct task_struct *tsk)
+{
+ if (!unhandled_signal(tsk, SIGSEGV))
+ return;
+
+ if (!printk_ratelimit())
+ return;
+
+ printk(KERN_CONT "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+ tsk->comm, task_pid_nr(tsk), address,
+ (void *)regs->ip, (void *)regs->sp, error_code);
+
+ print_vma_addr(KERN_CONT " in ", regs->ip);
+
+ printk(KERN_CONT "\n");
+}
+
+static void
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, int si_code)
{
struct task_struct *tsk = current;
/* User mode accesses just cause a SIGSEGV */
if (error_code & PF_USER) {
/*
- * It's possible to have interrupts off here.
+ * It's possible to have interrupts off here:
*/
local_irq_enable();
/*
* Valid to do another page fault here because this one came
- * from user space.
+ * from user space:
*/
if (is_prefetch(regs, error_code, address))
return;
@@ -516,22 +758,16 @@
if (is_errata100(regs, address))
return;
- if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
- printk_ratelimit()) {
- printk(
- "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
- task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address,
- (void *) regs->ip, (void *) regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
- printk("\n");
- }
+ if (unlikely(show_unhandled_signals))
+ show_signal_msg(regs, error_code, address, tsk);
- tsk->thread.cr2 = address;
- /* Kernel addresses are always protection faults */
- tsk->thread.error_code = error_code | (address >= TASK_SIZE);
- tsk->thread.trap_no = 14;
+ /* Kernel addresses are always protection faults: */
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+
force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+
return;
}
@@ -541,15 +777,16 @@
no_context(regs, error_code, address);
}
-static noinline void bad_area_nosemaphore(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
}
-static void __bad_area(struct pt_regs *regs,
- unsigned long error_code, unsigned long address,
- int si_code)
+static void
+__bad_area(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, int si_code)
{
struct mm_struct *mm = current->mm;
@@ -562,67 +799,75 @@
__bad_area_nosemaphore(regs, error_code, address, si_code);
}
-static noinline void bad_area(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
__bad_area(regs, error_code, address, SEGV_MAPERR);
}
-static noinline void bad_area_access_error(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
__bad_area(regs, error_code, address, SEGV_ACCERR);
}
/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void out_of_memory(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static void
+out_of_memory(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
/*
* We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed).
+ * (which will retry the fault, or kill us if we got oom-killed):
*/
up_read(¤t->mm->mmap_sem);
+
pagefault_out_of_memory();
}
-static void do_sigbus(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static void
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
up_read(&mm->mmap_sem);
- /* Kernel mode? Handle exceptions or die */
+ /* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER))
no_context(regs, error_code, address);
-#ifdef CONFIG_X86_32
- /* User space => ok to do another page fault */
+
+ /* User-space => ok to do another page fault: */
if (is_prefetch(regs, error_code, address))
return;
-#endif
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+
force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}
-static noinline void mm_fault_error(struct pt_regs *regs,
- unsigned long error_code, unsigned long address, unsigned int fault)
+static noinline void
+mm_fault_error(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, unsigned int fault)
{
- if (fault & VM_FAULT_OOM)
+ if (fault & VM_FAULT_OOM) {
out_of_memory(regs, error_code, address);
- else if (fault & VM_FAULT_SIGBUS)
- do_sigbus(regs, error_code, address);
- else
- BUG();
+ } else {
+ if (fault & VM_FAULT_SIGBUS)
+ do_sigbus(regs, error_code, address);
+ else
+ BUG();
+ }
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & PF_WRITE) && !pte_write(*pte))
return 0;
+
if ((error_code & PF_INSTR) && !pte_exec(*pte))
return 0;
@@ -630,21 +875,25 @@
}
/*
- * Handle a spurious fault caused by a stale TLB entry. This allows
- * us to lazily refresh the TLB when increasing the permissions of a
- * kernel page (RO -> RW or NX -> X). Doing it eagerly is very
- * expensive since that implies doing a full cross-processor TLB
- * flush, even if no stale TLB entries exist on other processors.
+ * Handle a spurious fault caused by a stale TLB entry.
+ *
+ * This allows us to lazily refresh the TLB when increasing the
+ * permissions of a kernel page (RO -> RW or NX -> X). Doing it
+ * eagerly is very expensive since that implies doing a full
+ * cross-processor TLB flush, even if no stale TLB entries exist
+ * on other processors.
+ *
* There are no security implications to leaving a stale TLB when
* increasing the permissions on a page.
*/
-static noinline int spurious_fault(unsigned long error_code,
- unsigned long address)
+static noinline int
+spurious_fault(unsigned long error_code, unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
+ int ret;
/* Reserved-bit violation or user access to kernel space? */
if (error_code & (PF_USER | PF_RSVD))
@@ -672,123 +921,46 @@
if (!pte_present(*pte))
return 0;
- return spurious_fault_check(error_code, pte);
-}
-
-/*
- * X86_32
- * Handle a fault on the vmalloc or module mapping area
- *
- * X86_64
- * Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
- */
-static noinline int vmalloc_fault(unsigned long address)
-{
-#ifdef CONFIG_X86_32
- unsigned long pgd_paddr;
- pmd_t *pmd_k;
- pte_t *pte_k;
-
- /* Make sure we are in vmalloc area */
- if (!(address >= VMALLOC_START && address < VMALLOC_END))
- return -1;
+ ret = spurious_fault_check(error_code, pte);
+ if (!ret)
+ return 0;
/*
- * Synchronize this task's top level page-table
- * with the 'reference' page table.
- *
- * Do _not_ use "current" here. We might be inside
- * an interrupt in the middle of a task switch..
+ * Make sure we have permissions in PMD.
+ * If not, then there's a bug in the page tables:
*/
- pgd_paddr = read_cr3();
- pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
- if (!pmd_k)
- return -1;
- pte_k = pte_offset_kernel(pmd_k, address);
- if (!pte_present(*pte_k))
- return -1;
- return 0;
-#else
- pgd_t *pgd, *pgd_ref;
- pud_t *pud, *pud_ref;
- pmd_t *pmd, *pmd_ref;
- pte_t *pte, *pte_ref;
+ ret = spurious_fault_check(error_code, (pte_t *) pmd);
+ WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
- /* Make sure we are in vmalloc area */
- if (!(address >= VMALLOC_START && address < VMALLOC_END))
- return -1;
-
- /* Copy kernel mappings over when needed. This can also
- happen within a race in page table update. In the later
- case just flush. */
-
- pgd = pgd_offset(current->active_mm, address);
- pgd_ref = pgd_offset_k(address);
- if (pgd_none(*pgd_ref))
- return -1;
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-
- /* Below here mismatches are bugs because these lower tables
- are shared */
-
- pud = pud_offset(pgd, address);
- pud_ref = pud_offset(pgd_ref, address);
- if (pud_none(*pud_ref))
- return -1;
- if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
- BUG();
- pmd = pmd_offset(pud, address);
- pmd_ref = pmd_offset(pud_ref, address);
- if (pmd_none(*pmd_ref))
- return -1;
- if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
- BUG();
- pte_ref = pte_offset_kernel(pmd_ref, address);
- if (!pte_present(*pte_ref))
- return -1;
- pte = pte_offset_kernel(pmd, address);
- /* Don't use pte_page here, because the mappings can point
- outside mem_map, and the NUMA hash lookup cannot handle
- that. */
- if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
- BUG();
- return 0;
-#endif
+ return ret;
}
int show_unhandled_signals = 1;
-static inline int access_error(unsigned long error_code, int write,
- struct vm_area_struct *vma)
+static inline int
+access_error(unsigned long error_code, int write, struct vm_area_struct *vma)
{
if (write) {
- /* write, present and write, not present */
+ /* write, present and write, not present: */
if (unlikely(!(vma->vm_flags & VM_WRITE)))
return 1;
- } else if (unlikely(error_code & PF_PROT)) {
- /* read, present */
- return 1;
- } else {
- /* read, not present */
- if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
- return 1;
+ return 0;
}
+ /* read, present: */
+ if (unlikely(error_code & PF_PROT))
+ return 1;
+
+ /* read, not present: */
+ if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+ return 1;
+
return 0;
}
static int fault_in_kernel_space(unsigned long address)
{
-#ifdef CONFIG_X86_32
- return address >= TASK_SIZE;
-#else /* !CONFIG_X86_32 */
- return address >= TASK_SIZE64;
-#endif /* CONFIG_X86_32 */
+ return address >= TASK_SIZE_MAX;
}
/*
@@ -796,23 +968,22 @@
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
-#ifdef CONFIG_X86_64
-asmlinkage
-#endif
-void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
- unsigned long address;
- struct task_struct *tsk;
- struct mm_struct *mm;
struct vm_area_struct *vma;
+ struct task_struct *tsk;
+ unsigned long address;
+ struct mm_struct *mm;
int write;
int fault;
tsk = current;
mm = tsk->mm;
+
prefetchw(&mm->mmap_sem);
- /* get the address */
+ /* Get the faulting address: */
address = read_cr2();
if (unlikely(kmmio_fault(regs, address)))
@@ -836,22 +1007,23 @@
vmalloc_fault(address) >= 0)
return;
- /* Can handle a stale RO->RW TLB */
+ /* Can handle a stale RO->RW TLB: */
if (spurious_fault(error_code, address))
return;
- /* kprobes don't want to hook the spurious faults. */
+ /* kprobes don't want to hook the spurious faults: */
if (notify_page_fault(regs))
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
- * fault we could otherwise deadlock.
+ * fault we could otherwise deadlock:
*/
bad_area_nosemaphore(regs, error_code, address);
+
return;
}
- /* kprobes don't want to hook the spurious faults. */
+ /* kprobes don't want to hook the spurious faults: */
if (unlikely(notify_page_fault(regs)))
return;
/*
@@ -859,22 +1031,22 @@
* vmalloc fault has been handled.
*
* User-mode registers count as a user access even for any
- * potential system fault or CPU buglet.
+ * potential system fault or CPU buglet:
*/
if (user_mode_vm(regs)) {
local_irq_enable();
error_code |= PF_USER;
- } else if (regs->flags & X86_EFLAGS_IF)
- local_irq_enable();
+ } else {
+ if (regs->flags & X86_EFLAGS_IF)
+ local_irq_enable();
+ }
-#ifdef CONFIG_X86_64
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
-#endif
/*
- * If we're in an interrupt, have no user context or are running in an
- * atomic region then we must not take the fault.
+ * If we're in an interrupt, have no user context or are running
+ * in an atomic region then we must not take the fault:
*/
if (unlikely(in_atomic() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
@@ -883,19 +1055,19 @@
/*
* When running in the kernel we expect faults to occur only to
- * addresses in user space. All other faults represent errors in the
- * kernel and should generate an OOPS. Unfortunately, in the case of an
- * erroneous fault occurring in a code path which already holds mmap_sem
- * we will deadlock attempting to validate the fault against the
- * address space. Luckily the kernel only validly references user
- * space from well defined areas of code, which are listed in the
- * exceptions table.
+ * addresses in user space. All other faults represent errors in
+ * the kernel and should generate an OOPS. Unfortunately, in the
+ * case of an erroneous fault occurring in a code path which already
+ * holds mmap_sem we will deadlock attempting to validate the fault
+ * against the address space. Luckily the kernel only validly
+ * references user space from well defined areas of code, which are
+ * listed in the exceptions table.
*
* As the vast majority of faults will be valid we will only perform
- * the source reference check when there is a possibility of a deadlock.
- * Attempt to lock the address space, if we cannot we then validate the
- * source. If this is invalid we can skip the address space check,
- * thus avoiding the deadlock.
+ * the source reference check when there is a possibility of a
+ * deadlock. Attempt to lock the address space, if we cannot we then
+ * validate the source. If this is invalid we can skip the address
+ * space check, thus avoiding the deadlock:
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if ((error_code & PF_USER) == 0 &&
@@ -906,8 +1078,9 @@
down_read(&mm->mmap_sem);
} else {
/*
- * The above down_read_trylock() might have succeeded in which
- * case we'll have missed the might_sleep() from down_read().
+ * The above down_read_trylock() might have succeeded in
+ * which case we'll have missed the might_sleep() from
+ * down_read():
*/
might_sleep();
}
@@ -927,7 +1100,7 @@
/*
* Accessing the stack below %sp is always a bug.
* The large cushion allows instructions like enter
- * and pusha to work. ("enter $65535,$31" pushes
+ * and pusha to work. ("enter $65535, $31" pushes
* 32 pointers and then decrements %sp by 65535.)
*/
if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
@@ -946,6 +1119,7 @@
*/
good_area:
write = error_code & PF_WRITE;
+
if (unlikely(access_error(error_code, write, vma))) {
bad_area_access_error(regs, error_code, address);
return;
@@ -954,75 +1128,21 @@
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
- * the fault.
+ * the fault:
*/
fault = handle_mm_fault(mm, vma, address, write);
+
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, fault);
return;
}
+
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
-#ifdef CONFIG_X86_32
- /*
- * Did it hit the DOS screen memory VA from vm86 mode?
- */
- if (v8086_mode(regs)) {
- unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
- if (bit < 32)
- tsk->thread.screen_bitmap |= 1 << bit;
- }
-#endif
+ check_v8086_mode(regs, address, tsk);
+
up_read(&mm->mmap_sem);
}
-
-DEFINE_SPINLOCK(pgd_lock);
-LIST_HEAD(pgd_list);
-
-void vmalloc_sync_all(void)
-{
- unsigned long address;
-
-#ifdef CONFIG_X86_32
- if (SHARED_KERNEL_PMD)
- return;
-
- for (address = VMALLOC_START & PMD_MASK;
- address >= TASK_SIZE && address < FIXADDR_TOP;
- address += PMD_SIZE) {
- unsigned long flags;
- struct page *page;
-
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- if (!vmalloc_sync_one(page_address(page),
- address))
- break;
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
-#else /* CONFIG_X86_64 */
- for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
- address += PGDIR_SIZE) {
- const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
-#endif
-}
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index ca53224..d5e2842 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -20,6 +20,64 @@
#include <asm/pat.h>
#include <linux/module.h>
+#ifdef CONFIG_X86_PAE
+static int
+is_io_mapping_possible(resource_size_t base, unsigned long size)
+{
+ return 1;
+}
+#else
+static int
+is_io_mapping_possible(resource_size_t base, unsigned long size)
+{
+ /* There is no way to map greater than 1 << 32 address without PAE */
+ if (base + size > 0x100000000ULL)
+ return 0;
+
+ return 1;
+}
+#endif
+
+int
+reserve_io_memtype_wc(u64 base, unsigned long size, pgprot_t *prot)
+{
+ unsigned long ret_flag;
+
+ if (!is_io_mapping_possible(base, size))
+ goto out_err;
+
+ if (!pat_enabled) {
+ *prot = pgprot_noncached(PAGE_KERNEL);
+ return 0;
+ }
+
+ if (reserve_memtype(base, base + size, _PAGE_CACHE_WC, &ret_flag))
+ goto out_err;
+
+ if (ret_flag == _PAGE_CACHE_WB)
+ goto out_free;
+
+ if (kernel_map_sync_memtype(base, size, ret_flag))
+ goto out_free;
+
+ *prot = __pgprot(__PAGE_KERNEL | ret_flag);
+ return 0;
+
+out_free:
+ free_memtype(base, base + size);
+out_err:
+ return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(reserve_io_memtype_wc);
+
+void
+free_io_memtype(u64 base, unsigned long size)
+{
+ if (pat_enabled)
+ free_memtype(base, base + size);
+}
+EXPORT_SYMBOL_GPL(free_io_memtype);
+
/* Map 'pfn' using fixed map 'type' and protections 'prot'
*/
void *
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 9cab18b..0bcd788 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -9,44 +9,44 @@
#include <asm/e820.h>
-static void __init memtest(unsigned long start_phys, unsigned long size,
- unsigned pattern)
+static u64 patterns[] __initdata = {
+ 0,
+ 0xffffffffffffffffULL,
+ 0x5555555555555555ULL,
+ 0xaaaaaaaaaaaaaaaaULL,
+ 0x1111111111111111ULL,
+ 0x2222222222222222ULL,
+ 0x4444444444444444ULL,
+ 0x8888888888888888ULL,
+ 0x3333333333333333ULL,
+ 0x6666666666666666ULL,
+ 0x9999999999999999ULL,
+ 0xccccccccccccccccULL,
+ 0x7777777777777777ULL,
+ 0xbbbbbbbbbbbbbbbbULL,
+ 0xddddddddddddddddULL,
+ 0xeeeeeeeeeeeeeeeeULL,
+ 0x7a6c7258554e494cULL, /* yeah ;-) */
+};
+
+static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
{
- unsigned long i;
- unsigned long *start;
- unsigned long start_bad;
- unsigned long last_bad;
- unsigned long val;
- unsigned long start_phys_aligned;
- unsigned long count;
- unsigned long incr;
+ printk(KERN_INFO " %016llx bad mem addr %010llx - %010llx reserved\n",
+ (unsigned long long) pattern,
+ (unsigned long long) start_bad,
+ (unsigned long long) end_bad);
+ reserve_early(start_bad, end_bad, "BAD RAM");
+}
- switch (pattern) {
- case 0:
- val = 0UL;
- break;
- case 1:
- val = -1UL;
- break;
- case 2:
-#ifdef CONFIG_X86_64
- val = 0x5555555555555555UL;
-#else
- val = 0x55555555UL;
-#endif
- break;
- case 3:
-#ifdef CONFIG_X86_64
- val = 0xaaaaaaaaaaaaaaaaUL;
-#else
- val = 0xaaaaaaaaUL;
-#endif
- break;
- default:
- return;
- }
+static void __init memtest(u64 pattern, u64 start_phys, u64 size)
+{
+ u64 i, count;
+ u64 *start;
+ u64 start_bad, last_bad;
+ u64 start_phys_aligned;
+ size_t incr;
- incr = sizeof(unsigned long);
+ incr = sizeof(pattern);
start_phys_aligned = ALIGN(start_phys, incr);
count = (size - (start_phys_aligned - start_phys))/incr;
start = __va(start_phys_aligned);
@@ -54,25 +54,42 @@
last_bad = 0;
for (i = 0; i < count; i++)
- start[i] = val;
+ start[i] = pattern;
for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
- if (*start != val) {
- if (start_phys_aligned == last_bad + incr) {
- last_bad += incr;
- } else {
- if (start_bad) {
- printk(KERN_CONT "\n %016lx bad mem addr %010lx - %010lx reserved",
- val, start_bad, last_bad + incr);
- reserve_early(start_bad, last_bad + incr, "BAD RAM");
- }
- start_bad = last_bad = start_phys_aligned;
- }
+ if (*start == pattern)
+ continue;
+ if (start_phys_aligned == last_bad + incr) {
+ last_bad += incr;
+ continue;
}
+ if (start_bad)
+ reserve_bad_mem(pattern, start_bad, last_bad + incr);
+ start_bad = last_bad = start_phys_aligned;
}
- if (start_bad) {
- printk(KERN_CONT "\n %016lx bad mem addr %010lx - %010lx reserved",
- val, start_bad, last_bad + incr);
- reserve_early(start_bad, last_bad + incr, "BAD RAM");
+ if (start_bad)
+ reserve_bad_mem(pattern, start_bad, last_bad + incr);
+}
+
+static void __init do_one_pass(u64 pattern, u64 start, u64 end)
+{
+ u64 size = 0;
+
+ while (start < end) {
+ start = find_e820_area_size(start, &size, 1);
+
+ /* done ? */
+ if (start >= end)
+ break;
+ if (start + size > end)
+ size = end - start;
+
+ printk(KERN_INFO " %010llx - %010llx pattern %016llx\n",
+ (unsigned long long) start,
+ (unsigned long long) start + size,
+ (unsigned long long) cpu_to_be64(pattern));
+ memtest(pattern, start, size);
+
+ start += size;
}
}
@@ -90,33 +107,22 @@
void __init early_memtest(unsigned long start, unsigned long end)
{
- u64 t_start, t_size;
- unsigned pattern;
+ unsigned int i;
+ unsigned int idx = 0;
if (!memtest_pattern)
return;
- printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
- for (pattern = 0; pattern < memtest_pattern; pattern++) {
- t_start = start;
- t_size = 0;
- while (t_start < end) {
- t_start = find_e820_area_size(t_start, &t_size, 1);
-
- /* done ? */
- if (t_start >= end)
- break;
- if (t_start + t_size > end)
- t_size = end - t_start;
-
- printk(KERN_CONT "\n %010llx - %010llx pattern %d",
- (unsigned long long)t_start,
- (unsigned long long)t_start + t_size, pattern);
-
- memtest(t_start, t_size, pattern);
-
- t_start += t_size;
- }
+ printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern);
+ for (i = 0; i < memtest_pattern; i++) {
+ idx = i % ARRAY_SIZE(patterns);
+ do_one_pass(patterns[idx], start, end);
}
- printk(KERN_CONT "\n");
+
+ if (idx > 0) {
+ printk(KERN_INFO "early_memtest: wipe out "
+ "test pattern from memory\n");
+ /* additional test with pattern 0 will do this */
+ do_one_pass(0, start, end);
+ }
}
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index d1f7439..3957cd6 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -194,7 +194,7 @@
size = ALIGN(size, L1_CACHE_BYTES);
if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
- return 0;
+ return NULL;
node_remap_alloc_vaddr[nid] += size;
memset(allocation, 0, size);
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index deb1c1a..64c9cf0 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -166,7 +166,7 @@
return shift;
}
-int early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn)
{
return phys_to_nid(pfn << PAGE_SHIFT);
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8ca0d85..8253bc9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -482,6 +482,13 @@
pbase = (pte_t *)page_address(base);
paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
+ /*
+ * If we ever want to utilize the PAT bit, we need to
+ * update this function to make sure it's converted from
+ * bit 12 to bit 7 when we cross from the 2MB level to
+ * the 4K level:
+ */
+ WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
#ifdef CONFIG_X86_64
if (level == PG_LEVEL_1G) {
@@ -508,18 +515,13 @@
#endif
/*
- * Install the new, split up pagetable. Important details here:
+ * Install the new, split up pagetable.
*
- * On Intel the NX bit of all levels must be cleared to make a
- * page executable. See section 4.13.2 of Intel 64 and IA-32
- * Architectures Software Developer's Manual).
- *
- * Mark the entry present. The current mapping might be
- * set to not present, which we preserved above.
+ * We use the standard kernel pagetable protections for the new
+ * pagetable protections, the actual ptes set above control the
+ * primary protection behavior:
*/
- ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
- pgprot_val(ref_prot) |= _PAGE_PRESENT;
- __set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
+ __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
base = NULL;
out_unlock:
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 05f9aef..fdfedb6 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -634,6 +634,33 @@
}
/*
+ * Change the memory type for the physial address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
+{
+ unsigned long id_sz;
+
+ if (!pat_enabled || base >= __pa(high_memory))
+ return 0;
+
+ id_sz = (__pa(high_memory) < base + size) ?
+ __pa(high_memory) - base :
+ size;
+
+ if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
+ printk(KERN_INFO
+ "%s:%d ioremap_change_attr failed %s "
+ "for %Lx-%Lx\n",
+ current->comm, current->pid,
+ cattr_name(flags),
+ base, (unsigned long long)(base + size));
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
* Internal interface to reserve a range of physical memory with prot.
* Reserved non RAM regions only and after successful reserve_memtype,
* this func also keeps identity mapping (if any) in sync with this new prot.
@@ -642,7 +669,7 @@
int strict_prot)
{
int is_ram = 0;
- int id_sz, ret;
+ int ret;
unsigned long flags;
unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
@@ -679,23 +706,8 @@
flags);
}
- /* Need to keep identity mapping in sync */
- if (paddr >= __pa(high_memory))
- return 0;
-
- id_sz = (__pa(high_memory) < paddr + size) ?
- __pa(high_memory) - paddr :
- size;
-
- if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+ if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
free_memtype(paddr, paddr + size);
- printk(KERN_ERR
- "%s:%d reserve_pfn_range ioremap_change_attr failed %s "
- "for %Lx-%Lx\n",
- current->comm, current->pid,
- cattr_name(flags),
- (unsigned long long)paddr,
- (unsigned long long)(paddr + size));
return -EINVAL;
}
return 0;
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index d1e9b53..b641388 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -8,7 +8,7 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0004159..9356547 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -18,7 +18,7 @@
.text
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 9c98cc6..7133cdf 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -85,8 +85,8 @@
unsigned long addr, end;
unsigned offset;
end = (start + PMD_SIZE - 1) & PMD_MASK;
- if (end >= TASK_SIZE64)
- end = TASK_SIZE64;
+ if (end >= TASK_SIZE_MAX)
+ end = TASK_SIZE_MAX;
end -= len;
/* This loses some more bits than a modulo, but is cheaper */
offset = get_random_int() & (PTRS_PER_PTE - 1);
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 87b9ab1..b83e119 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -6,7 +6,7 @@
bool "Xen guest support"
select PARAVIRT
select PARAVIRT_CLOCK
- depends on X86_64 || (X86_32 && X86_PAE && !(X86_VISWS || X86_VOYAGER))
+ depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS)
depends on X86_CMPXCHG && X86_TSC
help
This is the Linux Xen port. Enabling this will allow the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 86497d5..c52f403 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -940,6 +940,9 @@
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
+ local_irq_disable();
+ early_boot_irqs_off();
+
xen_raw_console_write("mapping kernel into physical memory\n");
pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 63d49a5..1a5ff24 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -8,7 +8,7 @@
#include <asm/boot.h>
#include <asm/asm.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <xen/interface/elfnote.h>
#include <asm/xen/interface.h>