diff options
Diffstat (limited to 'arch/x86')
57 files changed, 974 insertions, 1382 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8015641478b..f5cef3fbf9a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -40,6 +40,9 @@ config X86 select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_LZMA config ARCH_DEFCONFIG string @@ -1825,7 +1828,7 @@ config DMAR remapping devices. config DMAR_DEFAULT_ON - def_bool n + def_bool y prompt "Enable DMA Remapping Devices by default" depends on DMAR help diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 1771c804e02..3ca4c194b8e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux vmlinux.bin vmlinux.bin.gz head_$(BITS).o misc.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -47,18 +47,35 @@ ifeq ($(CONFIG_X86_32),y) ifdef CONFIG_RELOCATABLE $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE + $(call if_changed,lzma) else $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma) endif LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T else + $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma) LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T endif -$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE +suffix_$(CONFIG_KERNEL_GZIP) = gz +suffix_$(CONFIG_KERNEL_BZIP2) = bz2 +suffix_$(CONFIG_KERNEL_LZMA) = lzma + +$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index da062216948..e45be73684f 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -116,71 +116,13 @@ /* * gzip declarations */ - -#define OF(args) args #define STATIC static #undef memset #undef memcpy #define memzero(s, n) memset((s), 0, (n)) -typedef unsigned char uch; -typedef unsigned short ush; -typedef unsigned long ulg; - -/* - * Window size must be at least 32k, and a power of two. - * We don't actually have a window just a huge output buffer, - * so we report a 2G window size, as that should always be - * larger than our output buffer: - */ -#define WSIZE 0x80000000 - -/* Input buffer: */ -static unsigned char *inbuf; - -/* Sliding window buffer (and final output buffer): */ -static unsigned char *window; - -/* Valid bytes in inbuf: */ -static unsigned insize; - -/* Index of next byte to be processed in inbuf: */ -static unsigned inptr; - -/* Bytes in output buffer: */ -static unsigned outcnt; - -/* gzip flag byte */ -#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ -#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gz file */ -#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ -#define ORIG_NAM 0x08 /* bit 3 set: original file name present */ -#define COMMENT 0x10 /* bit 4 set: file comment present */ -#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ -#define RESERVED 0xC0 /* bit 6, 7: reserved */ - -#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) - -/* Diagnostic functions */ -#ifdef DEBUG -# define Assert(cond, msg) do { if (!(cond)) error(msg); } while (0) -# define Trace(x) do { fprintf x; } while (0) -# define Tracev(x) do { if (verbose) fprintf x ; } while (0) -# define Tracevv(x) do { if (verbose > 1) fprintf x ; } while (0) -# define Tracec(c, x) do { if (verbose && (c)) fprintf x ; } while (0) -# define Tracecv(c, x) do { if (verbose > 1 && (c)) fprintf x ; } while (0) -#else -# define Assert(cond, msg) -# define Trace(x) -# define Tracev(x) -# define Tracevv(x) -# define Tracec(c, x) -# define Tracecv(c, x) -#endif -static int fill_inbuf(void); -static void flush_window(void); static void error(char *m); /* @@ -189,13 +131,8 @@ static void error(char *m); static struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; -extern unsigned char input_data[]; -extern int input_len; - -static long bytes_out; - static void *memset(void *s, int c, unsigned n); -static void *memcpy(void *dest, const void *src, unsigned n); +void *memcpy(void *dest, const void *src, unsigned n); static void __putstr(int, const char *); #define putstr(__x) __putstr(0, __x) @@ -213,7 +150,17 @@ static char *vidmem; static int vidport; static int lines, cols; -#include "../../../../lib/inflate.c" +#ifdef CONFIG_KERNEL_GZIP +#include "../../../../lib/decompress_inflate.c" +#endif + +#ifdef CONFIG_KERNEL_BZIP2 +#include "../../../../lib/decompress_bunzip2.c" +#endif + +#ifdef CONFIG_KERNEL_LZMA +#include "../../../../lib/decompress_unlzma.c" +#endif static void scroll(void) { @@ -282,7 +229,7 @@ static void *memset(void *s, int c, unsigned n) return s; } -static void *memcpy(void *dest, const void *src, unsigned n) +void *memcpy(void *dest, const void *src, unsigned n) { int i; const char *s = src; @@ -293,38 +240,6 @@ static void *memcpy(void *dest, const void *src, unsigned n) return dest; } -/* =========================================================================== - * Fill the input buffer. This is called only when the buffer is empty - * and at least one byte is really needed. - */ -static int fill_inbuf(void) -{ - error("ran out of input data"); - return 0; -} - -/* =========================================================================== - * Write the output window window[0..outcnt-1] and update crc and bytes_out. - * (Used for the decompressed data only.) - */ -static void flush_window(void) -{ - /* With my window equal to my output buffer - * I only need to compute the crc here. - */ - unsigned long c = crc; /* temporary variable */ - unsigned n; - unsigned char *in, ch; - - in = window; - for (n = 0; n < outcnt; n++) { - ch = *in++; - c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); - } - crc = c; - bytes_out += (unsigned long)outcnt; - outcnt = 0; -} static void error(char *x) { @@ -407,12 +322,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, lines = real_mode->screen_info.orig_video_lines; cols = real_mode->screen_info.orig_video_cols; - window = output; /* Output buffer (Normally at 1M) */ free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - inbuf = input_data; /* Input buffer */ - insize = input_len; - inptr = 0; #ifdef CONFIG_X86_64 if ((unsigned long)output & (__KERNEL_ALIGN - 1)) @@ -430,10 +341,9 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, #endif #endif - makecrc(); if (!quiet) putstr("\nDecompressing Linux... "); - gunzip(); + decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); if (!quiet) putstr("done.\nBooting the kernel.\n"); diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 5c023f6f652..235b81d0f6f 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 @@ -266,7 +266,9 @@ CONFIG_PREEMPT_VOLUNTARY=y 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 4157cc4a2bd..9fe5d212ab4 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 @@ -266,7 +266,9 @@ CONFIG_PREEMPT_VOLUNTARY=y 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/include/asm/apic.h b/arch/x86/include/asm/apic.h index a6208dc7463..4ef949c1972 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -75,7 +75,14 @@ static inline void default_inquire_remote_apic(int apicid) #define setup_secondary_clock setup_secondary_APIC_clock #endif +#ifdef CONFIG_X86_VSMP extern int is_vsmp_box(void); +#else +static inline int is_vsmp_box(void) +{ + return 0; +} +#endif extern void xapic_wait_icr_idle(void); extern u32 safe_xapic_wait_icr_idle(void); extern void xapic_icr_write(u32, u32); @@ -306,7 +313,7 @@ struct apic { void (*send_IPI_self)(int vector); /* wakeup_secondary_cpu */ - int (*wakeup_cpu)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); int trampoline_phys_low; int trampoline_phys_high; @@ -324,8 +331,21 @@ struct apic { u32 (*safe_wait_icr_idle)(void); }; +/* + * Pointer to the local APIC driver in use on this system (there's + * always just one such driver in use - the kernel decides via an + * early probing process which one it picks - and then sticks to it): + */ extern struct apic *apic; +/* + * APIC functionality to boot other CPUs - only used on SMP: + */ +#ifdef CONFIG_SMP +extern atomic_t init_deasserted; +extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); +#endif + static inline u32 apic_read(u32 reg) { return apic->read(reg); @@ -384,9 +404,7 @@ static inline unsigned default_get_apic_id(unsigned long x) #define DEFAULT_TRAMPOLINE_PHYS_LOW 0x467 #define DEFAULT_TRAMPOLINE_PHYS_HIGH 0x469 -#ifdef CONFIG_X86_32 -extern void es7000_update_apic_to_cluster(void); -#else +#ifdef CONFIG_X86_64 extern struct apic apic_flat; extern struct apic apic_physflat; extern struct apic apic_x2apic_cluster; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index dd61616cb73..6526cf08b0e 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -10,17 +10,31 @@ #define EXTENDED_VGA 0xfffe /* 80x50 mode */ #define ASK_VGA 0xfffd /* ask for it at bootup */ +#ifdef __KERNEL__ + /* Physical address where kernel should be loaded. */ #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \ + (CONFIG_PHYSICAL_ALIGN - 1)) \ & ~(CONFIG_PHYSICAL_ALIGN - 1)) +#ifdef CONFIG_KERNEL_BZIP2 +#define BOOT_HEAP_SIZE 0x400000 +#else /* !CONFIG_KERNEL_BZIP2 */ + #ifdef CONFIG_X86_64 #define BOOT_HEAP_SIZE 0x7000 -#define BOOT_STACK_SIZE 0x4000 #else #define BOOT_HEAP_SIZE 0x4000 +#endif + +#endif /* !CONFIG_KERNEL_BZIP2 */ + +#ifdef CONFIG_X86_64 +#define BOOT_STACK_SIZE 0x4000 +#else #define BOOT_STACK_SIZE 0x1000 #endif +#endif /* __KERNEL__ */ + #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 23696d44a0a..dca8f03da5b 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -1,11 +1,155 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1998 Ingo Molnar + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009 + */ + #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +#ifndef __ASSEMBLY__ +#include <linux/kernel.h> +#include <asm/acpi.h> +#include <asm/apicdef.h> +#include <asm/page.h> +#ifdef CONFIG_X86_32 +#include <linux/threads.h> +#include <asm/kmap_types.h> +#else +#include <asm/vsyscall.h> +#ifdef CONFIG_EFI +#include <asm/efi.h> +#endif +#endif + +/* + * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall + * uses fixmaps that relies on FIXADDR_TOP for proper address calculation. + * Because of this, FIXADDR_TOP x86 integration was left as later work. + */ +#ifdef CONFIG_X86_32 +/* used by vmalloc.c, vsyscall.lds.S. + * + * Leave one empty page between vmalloc'ed areas and + * the start of the fixmap. + */ +extern unsigned long __FIXADDR_TOP; +#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) + +#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) +#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) +#else +#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) + +/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ +#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) +#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) +#endif + + +/* + * Here we define all the compile-time 'special' virtual + * addresses. The point is to have a constant address at + * compile time, but to set the physical address only + * in the boot process. + * for x86_32: We allocate these special addresses + * from the end of virtual memory (0xfffff000) backwards. + * Also this lets us do fail-safe vmalloc(), we + * can guarantee that these special addresses and + * vmalloc()-ed addresses never overlap. + * + * These 'compile-time allocated' memory buffers are + * fixed-size 4k pages (or larger if used with an increment + * higher than 1). Use set_fixmap(idx,phys) to associate + * physical memory with fixmap indices. + * + * TLB entries of such buffers will not be flushed across + * task switches. + */ +enum fixed_addresses { #ifdef CONFIG_X86_32 -# include "fixmap_32.h" + FIX_HOLE, + FIX_VDSO, #else -# include "fixmap_64.h" + VSYSCALL_LAST_PAGE, + VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, + VSYSCALL_HPET, #endif + FIX_DBGP_BASE, + FIX_EARLYCON_MEM_BASE, +#ifdef CONFIG_X86_LOCAL_APIC + FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ +#endif +#ifdef CONFIG_X86_IO_APIC + FIX_IO_APIC_BASE_0, + FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, +#endif +#ifdef CONFIG_X86_64 +#ifdef CONFIG_EFI + FIX_EFI_IO_MAP_LAST_PAGE, + FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE + + MAX_EFI_IO_PAGES - 1, +#endif +#endif +#ifdef CONFIG_X86_VISWS_APIC + FIX_CO_CPU, /* Cobalt timer */ + FIX_CO_APIC, /* Cobalt APIC Redirection Table */ + FIX_LI_PCIA, /* Lithium PCI Bridge A */ + FIX_LI_PCIB, /* Lithium PCI Bridge B */ +#endif +#ifdef CONFIG_X86_F00F_BUG + FIX_F00F_IDT, /* Virtual mapping for IDT */ +#endif +#ifdef CONFIG_X86_CYCLONE_TIMER + FIX_CYCLONE_TIMER, /*cyclone timer register*/ +#endif +#ifdef CONFIG_X86_32 + FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ + FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, +#ifdef CONFIG_PCI_MMCONFIG + FIX_PCIE_MCFG, +#endif +#endif +#ifdef CONFIG_PARAVIRT + FIX_PARAVIRT_BOOTMAP, +#endif + __end_of_permanent_fixed_addresses, +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT + FIX_OHCI1394_BASE, +#endif + /* + * 256 temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + * + * We round it up to the next 256 pages boundary so that we + * can have a single pgd entry and a single pte table: + */ +#define NR_FIX_BTMAPS 64 +#define FIX_BTMAPS_SLOTS 4 + FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - + (__end_of_permanent_fixed_addresses & 255), + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, +#ifdef CONFIG_X86_32 + FIX_WP_TEST, +#endif + __end_of_fixed_addresses +}; + + +extern void reserve_top_address(unsigned long reserve); + +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_BOOT_START (FIXADDR_TOP - FIXADDR_BOOT_SIZE) extern int fixmaps_set; @@ -69,4 +213,5 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); return __virt_to_fix(vaddr); } +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h deleted file mode 100644 index 047d9bab2b3..00000000000 --- a/arch/x86/include/asm/fixmap_32.h +++ /dev/null @@ -1,115 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1998 Ingo Molnar - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - */ - -#ifndef _ASM_X86_FIXMAP_32_H -#define _ASM_X86_FIXMAP_32_H - - -/* used by vmalloc.c, vsyscall.lds.S. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap. - */ -extern unsigned long __FIXADDR_TOP; -#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) -#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) - -#ifndef __ASSEMBLY__ -#include <linux/kernel.h> -#include <asm/acpi.h> -#include <asm/apicdef.h> -#include <asm/page.h> -#include <linux/threads.h> -#include <asm/kmap_types.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ -enum fixed_addresses { - FIX_HOLE, - FIX_VDSO, - FIX_DBGP_BASE, - FIX_EARLYCON_MEM_BASE, -#ifdef CONFIG_X86_LOCAL_APIC - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ -#endif -#ifdef CONFIG_X86_IO_APIC - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, -#endif -#ifdef CONFIG_X86_VISWS_APIC - FIX_CO_CPU, /* Cobalt timer */ - FIX_CO_APIC, /* Cobalt APIC Redirection Table */ - FIX_LI_PCIA, /* Lithium PCI Bridge A */ - FIX_LI_PCIB, /* Lithium PCI Bridge B */ -#endif -#ifdef CONFIG_X86_F00F_BUG - FIX_F00F_IDT, /* Virtual mapping for IDT */ -#endif -#ifdef CONFIG_X86_CYCLONE_TIMER - FIX_CYCLONE_TIMER, /*cyclone timer register*/ -#endif - FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ - FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, -#ifdef CONFIG_PCI_MMCONFIG - FIX_PCIE_MCFG, -#endif -#ifdef CONFIG_PARAVIRT - FIX_PARAVIRT_BOOTMAP, -#endif - __end_of_permanent_fixed_addresses, - /* - * 256 temporary boot-time mappings, used by early_ioremap(), - * before ioremap() is functional. - * - * We round it up to the next 256 pages boundary so that we - * can have a single pgd entry and a single pte table: - */ -#define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - - (__end_of_permanent_fixed_addresses & 255), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, - FIX_WP_TEST, -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - FIX_OHCI1394_BASE, -#endif - __end_of_fixed_addresses -}; - -extern void reserve_top_address(unsigned long reserve); - - -#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) - -#define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define __FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) -#define FIXADDR_BOOT_START (FIXADDR_TOP - __FIXADDR_BOOT_SIZE) - -#endif /* !__ASSEMBLY__ */ -#endif /* _ASM_X86_FIXMAP_32_H */ diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h deleted file mode 100644 index 298d9ba3fae..00000000000 --- a/arch/x86/include/asm/fixmap_64.h +++ /dev/null @@ -1,79 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1998 Ingo Molnar - */ - -#ifndef _ASM_X86_FIXMAP_64_H -#define _ASM_X86_FIXMAP_64_H - -#include <linux/kernel.h> -#include <asm/acpi.h> -#include <asm/apicdef.h> -#include <asm/page.h> -#include <asm/vsyscall.h> -#include <asm/efi.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. - * - * These 'compile-time allocated' memory buffers are - * fixed-size 4k pages (or larger if used with an increment - * higher than 1). Use set_fixmap(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -enum fixed_addresses { - VSYSCALL_LAST_PAGE, - VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE - + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, - VSYSCALL_HPET, - FIX_DBGP_BASE, - FIX_EARLYCON_MEM_BASE, - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, - FIX_EFI_IO_MAP_LAST_PAGE, - FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE - + MAX_EFI_IO_PAGES - 1, -#ifdef CONFIG_PARAVIRT - FIX_PARAVIRT_BOOTMAP, -#endif - __end_of_permanent_fixed_addresses, -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - FIX_OHCI1394_BASE, -#endif - /* - * 256 temporary boot-time mappings, used by early_ioremap(), - * before ioremap() is functional. - * - * We round it up to the next 256 pages boundary so that we - * can have a single pgd entry and a single pte table: - */ -#define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - - (__end_of_permanent_fixed_addresses & 255), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, - __end_of_fixed_addresses -}; - -#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ -#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) -#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) - -#endif /* _ASM_X86_FIXMAP_64_H */ diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index c1f06289b14..86af26091d6 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -23,6 +23,9 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> +int +is_io_mapping_possible(resource_size_t 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/numa_32.h b/arch/x86/include/asm/numa_32.h index e9f5db79624..a37229011b5 100644 --- a/arch/x86/include/asm/numa_32.h +++ b/arch/x86/include/asm/numa_32.h @@ -4,8 +4,12 @@ extern int pxm_to_nid(int pxm); extern void numa_remove_cpu(int cpu); -#ifdef CONFIG_NUMA +#ifdef CONFIG_HIGHMEM extern void set_highmem_pages_init(void); +#else +static inline void set_highmem_pages_init(void) +{ +} #endif #endif /* _ASM_X86_NUMA_32_H */ diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 9709fdff661..b0e70056838 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -15,4 +15,7 @@ extern int reserve_memtype(u64 start, u64 end, 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/processor.h b/arch/x86/include/asm/processor.h index c7a98f73821..76139506c3e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -248,7 +248,6 @@ struct x86_hw_tss { #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) #define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) #define INVALID_IO_BITMAP_OFFSET 0x8000 -#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000 struct tss_struct { /* @@ -263,11 +262,6 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; - /* - * Cache the current maximum and the last task that used the bitmap: - */ - unsigned long io_bitmap_max; - struct thread_struct *io_bitmap_owner; /* * .. and then another 0x100 bytes for the emergency kernel stack: diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h index a6ad87b352c..b811d6f5780 100644 --- a/arch/x86/include/asm/seccomp_32.h +++ b/arch/x86/include/asm/seccomp_32.h @@ -1,12 +1,6 @@ #ifndef _ASM_X86_SECCOMP_32_H #define _ASM_X86_SECCOMP_32_H -#include <linux/thread_info.h> - -#ifdef TIF_32BIT -#error "unexpected TIF_32BIT on i386" -#endif - #include <linux/unistd.h> #define __NR_seccomp_read __NR_read diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h index 4171bb794e9..84ec1bd161a 100644 --- a/arch/x86/include/asm/seccomp_64.h +++ b/arch/x86/include/asm/seccomp_64.h @@ -1,14 +1,6 @@ #ifndef _ASM_X86_SECCOMP_64_H #define _ASM_X86_SECCOMP_64_H -#include <linux/thread_info.h> - -#ifdef TIF_32BIT -#error "unexpected TIF_32BIT on x86_64" -#else -#define TIF_32BIT TIF_IA32 -#endif - #include <linux/unistd.h> #include <asm/ia32_unistd.h> diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 66801cb72f6..05c6f6b11fd 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -31,7 +31,6 @@ struct x86_quirks { void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, unsigned short oemsize); int (*setup_ioapic_ids)(void); - int (*update_apic)(void); }; extern void x86_quirk_pre_intr_init(void); @@ -65,7 +64,11 @@ extern void x86_quirk_time_init(void); #include <asm/bootparam.h> /* Interrupt control for vSMPowered x86_64 systems */ +#ifdef CONFIG_X86_VSMP void vsmp_init(void); +#else +static inline void vsmp_init(void) { } +#endif void setup_bios_corruption_check(void); @@ -77,8 +80,6 @@ static inline void visws_early_detect(void) { } static inline int is_visws_box(void) { return 0; } #endif -extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); -extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip); extern struct x86_quirks *x86_quirks; extern unsigned long saved_video_mode; diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index c00bfdbdd45..643c59b4bc6 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -20,6 +20,9 @@ struct task_struct; /* one of the stranger aspects of C forward declarations */ struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next); +struct tss_struct; +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss); #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 987a2c10fe2..8cc687326eb 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -188,30 +188,18 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); -static inline int __copy_from_user_nocache(void *dst, const void __user *src, - unsigned size) +static inline int +__copy_from_user_nocache(void *dst, const void __user *src, unsigned size) { might_sleep(); - /* - * 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(size >= PAGE_SIZE)) - return __copy_user_nocache(dst, src, size, 1); - else - return __copy_from_user(dst, src, size); + return __copy_user_nocache(dst, src, size, 1); } -static inline int __copy_from_user_inatomic_nocache(void *dst, - const void __user *src, - unsigned size) +static inline int +__copy_from_user_inatomic_nocache(void *dst, const void __user *src, + unsigned size) { - if (likely(size >= PAGE_SIZE)) - return __copy_user_nocache(dst, src, size, 0); - else - return __copy_from_user_inatomic(dst, src, size); + return __copy_user_nocache(dst, src, size, 0); } unsigned long diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 8242bf96581..c0a01b5d985 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -12,7 +12,6 @@ extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); extern void uv_cpu_init(void); extern void uv_system_init(void); -extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, @@ -24,8 +23,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) -{ return 1; } static inline const struct cpumask * uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index de5657c039e..95f216bbfaf 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -70,7 +70,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -obj-y += vsmp_64.o +obj-$(CONFIG_X86_VSMP) += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a84ac7b570e..6907b8e85d5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -498,12 +498,12 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) */ 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 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) 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_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 3b002995e14..f933822dba1 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -222,7 +222,6 @@ struct apic apic_flat = { .send_IPI_all = flat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, @@ -373,7 +372,6 @@ struct apic apic_physflat = { .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 0b1093394fd..d806ecaa948 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -16,17 +16,17 @@ #include <asm/apic.h> #include <asm/ipi.h> -static inline unsigned bigsmp_get_apic_id(unsigned long x) +static unsigned bigsmp_get_apic_id(unsigned long x) { return (x >> 24) & 0xFF; } -static inline int bigsmp_apic_id_registered(void) +static int bigsmp_apic_id_registered(void) { return 1; } -static inline const cpumask_t *bigsmp_target_cpus(void) +static const cpumask_t *bigsmp_target_cpus(void) { #ifdef CONFIG_SMP return &cpu_online_map; @@ -35,13 +35,12 @@ static inline const cpumask_t *bigsmp_target_cpus(void) #endif } -static inline unsigned long -bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) { return 0; } -static inline unsigned long bigsmp_check_apicid_present(int bit) +static unsigned long bigsmp_check_apicid_present(int bit) { return 1; } @@ -64,7 +63,7 @@ static inline unsigned long calculate_ldr(int cpu) * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel * document number 292116). So here it goes... */ -static inline void bigsmp_init_apic_ldr(void) +static void bigsmp_init_apic_ldr(void) { unsigned long val; int cpu = smp_processor_id(); @@ -74,19 +73,19 @@ static inline void bigsmp_init_apic_ldr(void) apic_write(APIC_LDR, val); } -static inline void bigsmp_setup_apic_routing(void) +static void bigsmp_setup_apic_routing(void) { printk(KERN_INFO "Enabling APIC mode: Physflat. Using %d I/O APICs\n", nr_ioapics); } -static inline int bigsmp_apicid_to_node(int logical_apicid) +static int bigsmp_apicid_to_node(int logical_apicid) { return apicid_2_node[hard_smp_processor_id()]; } -static inline int bigsmp_cpu_present_to_apicid(int mps_cpu) +static int bigsmp_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids) return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); @@ -94,7 +93,7 @@ static inline int bigsmp_cpu_present_to_apicid(int mps_cpu) return BAD_APICID; } -static inline physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) +static physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) { return physid_mask_of_physid(phys_apicid); } @@ -107,29 +106,24 @@ static inline int bigsmp_cpu_to_logical_apicid(int cpu) return cpu_physical_id(cpu); } -static inline physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) +static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) { /* For clustered we don't have a good way to do this yet - hack */ return physids_promote(0xFFL); } -static inline void bigsmp_setup_portio_remap(void) -{ -} - -static inline int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) +static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) { return 1; } /* As we are using single CPU as destination, pick only one CPU here */ -static inline unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) { return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask)); } -static inline unsigned int -bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, +static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, const struct cpumask *andmask) { int cpu; @@ -148,7 +142,7 @@ bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return BAD_APICID; } -static inline int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) +static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) { return cpuid_apic >> index_msb; } @@ -158,12 +152,12 @@ static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) default_send_IPI_mask_sequence_phys(mask, vector); } -static inline void bigsmp_send_IPI_allbutself(int vector) +static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); } -static inline void bigsmp_send_IPI_all(int vector) +static void bigsmp_send_IPI_all(int vector) { bigsmp_send_IPI_mask(cpu_online_mask, vector); } @@ -256,7 +250,6 @@ struct apic apic_bigsmp = { .send_IPI_all = bigsmp_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 320f2d2e4e5..19588f2770e 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -163,22 +163,17 @@ static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) return 0; } -static int __init es7000_update_apic(void) +static int es7000_apic_is_cluster(void) { - apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; - /* MPENTIUMIII */ if (boot_cpu_data.x86 == 6 && - (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) { - es7000_update_apic_to_cluster(); - apic->wait_for_init_deassert = NULL; - apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; - } + (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) + return 1; return 0; } -static void __init setup_unisys(void) +static void setup_unisys(void) { /* * Determine the generation of the ES7000 currently running. @@ -192,14 +187,12 @@ static void __init setup_unisys(void) else es7000_plat = ES7000_CLASSIC; ioapic_renumber_irq = es7000_rename_gsi; - - x86_quirks->update_apic = es7000_update_apic; } /* * Parse the OEM Table: */ -static int __init parse_unisys_oem(char *oemptr) +static int parse_unisys_oem(char *oemptr) { int i; int success = 0; @@ -261,7 +254,7 @@ static int __init parse_unisys_oem(char *oemptr) } #ifdef CONFIG_ACPI -static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) +static int find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; struct es7000_oem_table *table; @@ -292,7 +285,7 @@ static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) return 0; } -static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) +static void unmap_unisys_acpi_oem_table(unsigned long oem_addr) { if (!oem_addr) return; @@ -310,8 +303,10 @@ static int es7000_check_dsdt(void) return 0; } +static int es7000_acpi_ret; + /* Hook from generic ACPI tables.c */ -static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { unsigned long oem_addr = 0; int check_dsdt; @@ -332,10 +327,26 @@ static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) */ unmap_unisys_acpi_oem_table(oem_addr); } - return ret; + + es7000_acpi_ret = ret; + + return ret && !es7000_apic_is_cluster(); } + +static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id) +{ + int ret = es7000_acpi_ret; + + return ret && es7000_apic_is_cluster(); +} + #else /* !CONFIG_ACPI: */ -static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return 0; +} + +static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id) { return 0; } @@ -349,8 +360,7 @@ static void es7000_spin(int n) rep_nop(); } -static int __init -es7000_mip_write(struct mip_reg *mip_reg) +static int es7000_mip_write(struct mip_reg *mip_reg) { int status = 0; int spin; @@ -383,7 +393,7 @@ es7000_mip_write(struct mip_reg *mip_reg) return status; } -static void __init es7000_enable_apic_mode(void) +static void es7000_enable_apic_mode(void) { struct mip_reg es7000_mip_reg; int mip_status; @@ -416,11 +426,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) static void es7000_wait_for_init_deassert(atomic_t *deassert) { -#ifndef CONFIG_ES7000_CLUSTERED_APIC while (!atomic_read(deassert)) cpu_relax(); -#endif - return; } static unsigned int es7000_get_apic_id(unsigned long x) @@ -565,72 +572,24 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int -es7000_cpu_mask_to_apicid_cluster(const struct cpumask *cpumask) -{ - int cpus_found = 0; - int num_bits_set; - int apicid; - int cpu; - - num_bits_set = cpumask_weight(cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return 0xFF; - /* - * 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(): - */ - cpu = cpumask_first(cpumask); - apicid = es7000_cpu_to_logical_apicid(cpu); - - while (cpus_found < num_bits_set) { - if (cpumask_test_cpu(cpu, cpumask)) { - int new_apicid = es7000_cpu_to_logical_apicid(cpu); - - if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - WARN(1, "Not a valid mask!"); - - return 0xFF; - } - apicid = new_apicid; - cpus_found++; - } - cpu++; - } - return apicid; -} - static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask) { - int cpus_found = 0; - int num_bits_set; - int apicid; - int cpu; + unsigned int round = 0; + int cpu, uninitialized_var(apicid); - num_bits_set = cpus_weight(*cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return es7000_cpu_to_logical_apicid(0); /* - * 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 = es7000_cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - int new_apicid = es7000_cpu_to_logical_apicid(cpu); + for_each_cpu(cpu, cpumask) { + int new_apicid = es7000_cpu_to_logical_apicid(cpu); - if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - printk("%s: Not a valid mask!\n", __func__); + if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { + WARN(1, "Not a valid mask!"); - return es7000_cpu_to_logical_apicid(0); - } - apicid = new_apicid; - cpus_found++; + return BAD_APICID; } - cpu++; + apicid = new_apicid; + round++; } return apicid; } @@ -659,37 +618,103 @@ static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -void __init es7000_update_apic_to_cluster(void) -{ - apic->target_cpus = target_cpus_cluster; - apic->irq_delivery_mode = dest_LowestPrio; - /* logical delivery broadcast to all procs: */ - apic->irq_dest_mode = 1; - - apic->init_apic_ldr = es7000_init_apic_ldr_cluster; - - apic->cpu_mask_to_apicid = es7000_cpu_mask_to_apicid_cluster; -} - static int probe_es7000(void) { /* probed later in mptable/ACPI hooks */ return 0; } -static __init int -es7000_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +static int es7000_mps_ret; +static int es7000_mps_oem_check(struct mpc_table *mpc, char *oem, + char *productid) { + int ret = 0; + if (mpc->oemptr) { struct mpc_oemtable *oem_table = (struct mpc_oemtable *)mpc->oemptr; if (!strncmp(oem, "UNISYS", 6)) - return parse_unisys_oem((char *)oem_table); + ret = parse_unisys_oem((char *)oem_table); } - return 0; + + es7000_mps_ret = ret; + + return ret && !es7000_apic_is_cluster(); } +static int es7000_mps_oem_check_cluster(struct mpc_table *mpc, char *oem, + char *productid) +{ + int ret = es7000_mps_ret; + + return ret && es7000_apic_is_cluster(); +} + +struct apic apic_es7000_cluster = { + + .name = "es7000", + .probe = probe_es7000, + .acpi_madt_oem_check = es7000_acpi_madt_oem_check_cluster, + .apic_id_registered = es7000_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* logical delivery broadcast to all procs: */ + .irq_dest_mode = 1, + + .target_cpus = target_cpus_cluster, + .disable_esr = 1, + .dest_logical = 0, + .check_apicid_used = es7000_check_apicid_used, + .check_apicid_present = es7000_check_apicid_present, + + .vector_allocation_domain = es7000_vector_allocation_domain, + .init_apic_ldr = es7000_init_apic_ldr_cluster, + + .ioapic_phys_id_map = es7000_ioapic_phys_id_map, + .setup_apic_routing = es7000_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = es7000_apicid_to_node, + .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, + .cpu_present_to_apicid = es7000_cpu_present_to_apicid, + .apicid_to_cpu_present = es7000_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = es7000_check_phys_apicid_present, + .enable_apic_mode = es7000_enable_apic_mode, + .phys_pkg_id = es7000_phys_pkg_id, + .mps_oem_check = es7000_mps_oem_check_cluster, + + .get_apic_id = es7000_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0xFF << 24, + + .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, + + .send_IPI_mask = es7000_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = es7000_send_IPI_allbutself, + .send_IPI_all = es7000_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_secondary_cpu = wakeup_secondary_cpu_via_mip, + + .trampoline_phys_low = 0x467, + .trampoline_phys_high = 0x469, + + .wait_for_init_deassert = NULL, + + /* Nothing to do for most platforms, since cleared by the INIT cycle: */ + .smp_callin_clear_local_apic = NULL, + .inquire_remote_apic = default_inquire_remote_apic, + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = native_apic_wait_icr_idle, + .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, +}; struct apic apic_es7000 = { @@ -737,8 +762,6 @@ struct apic apic_es7000 = { .send_IPI_all = es7000_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, - .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index d9d6d61eed8..ba2fc646553 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -69,7 +69,7 @@ struct mpc_trans { /* x86_quirks member */ static int mpc_record; -static __cpuinitdata struct mpc_trans *translation_table[MAX_MPC_ENTRY]; +static struct mpc_trans *translation_table[MAX_MPC_ENTRY]; int mp_bus_id_to_node[MAX_MP_BUSSES]; int mp_bus_id_to_local[MAX_MP_BUSSES]; @@ -256,13 +256,6 @@ static int __init numaq_setup_ioapic_ids(void) return 1; } -static int __init numaq_update_apic(void) -{ - apic->wakeup_cpu = wakeup_secondary_cpu_via_nmi; - - return 0; -} - static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, @@ -278,7 +271,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .mpc_oem_pci_bus = mpc_oem_pci_bus, .smp_read_mpc_oem = smp_read_mpc_oem, .setup_ioapic_ids = numaq_setup_ioapic_ids, - .update_apic = numaq_update_apic, }; static __init void early_check_numaq(void) @@ -546,7 +538,7 @@ struct apic apic_numaq = { .send_IPI_all = numaq_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, + .wakeup_secondary_cpu = wakeup_secondary_cpu_via_nmi, .trampoline_phys_low = NUMAQ_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 3a730fa574b..141c99a1c26 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -138,7 +138,6 @@ struct apic apic_default = { .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, @@ -159,6 +158,7 @@ extern struct apic apic_numaq; extern struct apic apic_summit; extern struct apic apic_bigsmp; extern struct apic apic_es7000; +extern struct apic apic_es7000_cluster; extern struct apic apic_default; struct apic *apic = &apic_default; @@ -176,6 +176,7 @@ static struct apic *apic_probe[] __initdata = { #endif #ifdef CONFIG_X86_ES7000 &apic_es7000, + &apic_es7000_cluster, #endif &apic_default, /* must be last */ NULL, @@ -197,9 +198,6 @@ static int __init parse_apic(char *arg) } } - if (x86_quirks->update_apic) - x86_quirks->update_apic(); - /* Parsed again by __setup for debug/verbose */ return 0; } @@ -218,8 +216,6 @@ void __init generic_bigsmp_probe(void) if (!cmdline_apic && apic == &apic_default) { if (apic_bigsmp.probe()) { apic = &apic_bigsmp; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Overriding APIC driver with %s\n", apic->name); } @@ -240,9 +236,6 @@ void __init generic_apic_probe(void) /* Not visible without early console */ if (!apic_probe[i]) panic("Didn't find an APIC driver"); - - if (x86_quirks->update_apic) - x86_quirks->update_apic(); } printk(KERN_INFO "Using APIC driver %s\n", apic->name); } @@ -262,8 +255,6 @@ generic_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) if (!cmdline_apic) { apic = apic_probe[i]; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Switched to APIC driver `%s'.\n", apic->name); } @@ -284,8 +275,6 @@ int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (!cmdline_apic) { apic = apic_probe[i]; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Switched to APIC driver `%s'.\n", apic->name); } diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index e7c163661c7..8d7748efe6a 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -68,9 +68,6 @@ void __init default_setup_apic_routing(void) apic = &apic_physflat; printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); } - - if (x86_quirks->update_apic) - x86_quirks->update_apic(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index cfe7b09015d..aac52fa873f 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 @@ static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector) 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 @@ static inline void summit_send_IPI_allbutself(int vector) 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); } @@ -77,13 +77,13 @@ static inline void summit_send_IPI_all(int vector) extern int use_cyclone; #ifdef CONFIG_X86_SUMMIT_NUMA -extern void setup_summit(void); +static void setup_summit(void); #else -#define setup_summit() {} +static inline void setup_summit(void) {} #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 @@ summit_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) } /* 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 @@ static inline int is_WPEG(struct rio_detail *rio){ #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 @@ static inline const cpumask_t *summit_target_cpus(void) 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 @@ static inline void summit_init_apic_ldr(void) 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 @@ static inline int summit_cpu_to_logical_apicid(int cpu) #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); @@ -274,64 +273,44 @@ static inline int summit_cpu_present_to_apicid(int mps_cpu) 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; - int apicid; - int cpu; - - num_bits_set = cpus_weight(*cpumask); - /* Return id to all */ - if (num_bits_set >= nr_cpu_ids) - return 0xFF; + unsigned int round = 0; + int cpu, apicid = 0; + /* - * 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); + for_each_cpu(cpu, cpumask) { + int new_apicid = summit_cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - 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__); - - return 0xFF; - } - apicid = apicid | new_apicid; - cpus_found++; + if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { + printk("%s: Not a valid mask!\n", __func__); + return BAD_APICID; } - cpu++; + apicid |= new_apicid; + round++; } 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 +335,7 @@ summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, * * 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; } @@ -381,15 +360,15 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) } #ifdef CONFIG_X86_SUMMIT_NUMA -static struct rio_table_hdr *rio_table_hdr __initdata; -static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata; -static struct rio_detail *rio_devs[MAX_NUMNODES*4] __initdata; +static struct rio_table_hdr *rio_table_hdr; +static struct scal_detail *scal_devs[MAX_NUMNODES]; +static struct rio_detail *rio_devs[MAX_NUMNODES*4]; #ifndef CONFIG_X86_NUMAQ -static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata; +static int mp_bus_id_to_node[MAX_MP_BUSSES]; #endif -static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) +static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) { int twister = 0, node = 0; int i, bus, num_buses; @@ -451,7 +430,7 @@ static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) return bus; } -static int __init build_detail_arrays(void) +static int build_detail_arrays(void) { unsigned long ptr; int i, scal_detail_size, rio_detail_size; @@ -485,7 +464,7 @@ static int __init build_detail_arrays(void) return 1; } -void __init setup_summit(void) +void setup_summit(void) { unsigned long ptr; unsigned short offset; @@ -583,7 +562,6 @@ struct apic apic_summit = { .send_IPI_all = summit_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 354b9c45601..8fb87b6dd63 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -224,7 +224,6 @@ struct apic apic_x2apic_cluster = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 5bcb174409b..23625b9f98b 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -213,7 +213,6 @@ struct apic apic_x2apic_phys = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 20b4ad07c3a..1bd6da1f8fa 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -7,28 +7,28 @@ * * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved. */ - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/hardirq.h> +#include <linux/proc_fs.h> +#include <linux/threads.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/string.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/sched.h> -#include <linux/module.h> -#include <linux/hardirq.h> #include <linux/timer.h> -#include <linux/proc_fs.h> -#include <asm/current.h> -#include <asm/smp.h> -#include <asm/apic.h> -#include <asm/ipi.h> -#include <asm/pgtable.h> -#include <asm/uv/uv.h> +#include <linux/cpu.h> +#include <linux/init.h> + #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> +#include <asm/current.h> +#include <asm/pgtable.h> #include <asm/uv/bios.h> +#include <asm/uv/uv.h> +#include <asm/apic.h> +#include <asm/ipi.h> +#include <asm/smp.h> DEFINE_PER_CPU(int, x2apic_extra_bits); @@ -91,24 +91,28 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask) cpumask_set_cpu(cpu, retmask); } -int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) +static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { +#ifdef CONFIG_SMP unsigned long val; int pnode; pnode = uv_apicid_to_pnode(phys_apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | + ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); mdelay(10); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | + ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_STARTUP; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); + + atomic_set(&init_deasserted, 1); +#endif return 0; } @@ -285,7 +289,7 @@ struct apic apic_x2apic_uv_x = { .send_IPI_all = uv_send_IPI_all, .send_IPI_self = uv_send_IPI_self, - .wakeup_cpu = NULL, + .wakeup_secondary_cpu = uv_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, @@ -365,7 +369,7 @@ static __init void map_high(char *id, unsigned long base, int shift, paddr = base << shift; bytes = (1UL << shift) * (max_pnode + 1); printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, - paddr + bytes); + paddr + bytes); if (map_type == map_uc) init_extra_mapping_uc(paddr, bytes); else @@ -528,7 +532,7 @@ late_initcall(uv_init_heartbeat); /* * Called on each cpu to initialize the per_cpu UV data area. - * ZZZ hotplug not supported yet + * FIXME: hotplug not supported yet */ void __cpuinit uv_cpu_init(void) { diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 01b1244ef1c..d67e0e48bc2 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -7,11 +7,10 @@ /* * Get CPU information for use by the procfs. */ -#ifdef CONFIG_X86_32 static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, unsigned int cpu) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", @@ -24,6 +23,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, #endif } +#ifdef CONFIG_X86_32 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { /* @@ -50,22 +50,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) c->wp_works_ok ? "yes" : "no"); } #else -static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, - unsigned int cpu) -{ -#ifdef CONFIG_SMP - if (c->x86_max_cores * smp_num_siblings > 1) { - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); - seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - seq_printf(m, "apicid\t\t: %d\n", c->apicid); - seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); - } -#endif -} - static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { seq_printf(m, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e85826829cf..508bec1cee2 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -858,6 +858,9 @@ void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) */ 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/ioport.c b/arch/x86/kernel/ioport.c index e41980a373a..99c4d308f16 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -85,19 +85,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) t->io_bitmap_max = bytes; -#ifdef CONFIG_X86_32 - /* - * Sets the lazy trigger so that the next I/O operation will - * reload the correct bitmap. - * Reset the owner so that a process switch will not set - * tss->io_bitmap_base to IO_BITMAP_OFFSET. - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY; - tss->io_bitmap_owner = NULL; -#else /* Update the TSS: */ memcpy(tss->io_bitmap, t->io_bitmap_ptr, bytes_updated); -#endif put_cpu(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 87b69d4fac1..6afa5232dbb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,8 +1,8 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <asm/idle.h> #include <linux/smp.h> +#include <linux/prctl.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/module.h> @@ -11,6 +11,9 @@ #include <linux/ftrace.h> #include <asm/system.h> #include <asm/apic.h> +#include <asm/idle.h> +#include <asm/uaccess.h> +#include <asm/i387.h> unsigned long idle_halt; EXPORT_SYMBOL(idle_halt); @@ -56,6 +59,192 @@ void arch_task_cache_init(void) } /* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ + struct task_struct *me = current; + struct thread_struct *t = &me->thread; + + if (me->thread.io_bitmap_ptr) { + struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + + kfree(t->io_bitmap_ptr); + t->io_bitmap_ptr = NULL; + clear_thread_flag(TIF_IO_BITMAP); + /* + * Careful, clear this in the TSS too: + */ + memset(tss->io_bitmap, 0xff, t->io_bitmap_max); + t->io_bitmap_max = 0; + put_cpu(); + } + + ds_exit_thread(current); +} + +void flush_thread(void) +{ + struct task_struct *tsk = current; + +#ifdef CONFIG_X86_64 + if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) { + clear_tsk_thread_flag(tsk, TIF_ABI_PENDING); + if (test_tsk_thread_flag(tsk, TIF_IA32)) { + clear_tsk_thread_flag(tsk, TIF_IA32); + } else { + set_tsk_thread_flag(tsk, TIF_IA32); + current_thread_info()->status |= TS_COMPAT; + } + } +#endif + + clear_tsk_thread_flag(tsk, TIF_DEBUG); + + tsk->thread.debugreg0 = 0; + tsk->thread.debugreg1 = 0; + tsk->thread.debugreg2 = 0; + tsk->thread.debugreg3 = 0; + tsk->thread.debugreg6 = 0; + tsk->thread.debugreg7 = 0; + memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); + /* + * Forget coprocessor state.. + */ + tsk->fpu_counter = 0; + clear_fpu(tsk); + clear_used_math(); +} + +static void hard_disable_TSC(void) +{ + write_cr4(read_cr4() | X86_CR4_TSD); +} + +void disable_TSC(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_disable_TSC(); + preempt_enable(); +} + +static void hard_enable_TSC(void) +{ + write_cr4(read_cr4() & ~X86_CR4_TSD); +} + +static void enable_TSC(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_enable_TSC(); + preempt_enable(); +} + +int get_tsc_mode(unsigned long adr) +{ + unsigned int val; + + if (test_thread_flag(TIF_NOTSC)) + val = PR_TSC_SIGSEGV; + else + val = PR_TSC_ENABLE; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_tsc_mode(unsigned int val) +{ + if (val == PR_TSC_SIGSEGV) + disable_TSC(); + else if (val == PR_TSC_ENABLE) + enable_TSC(); + else + return -EINVAL; + + return 0; +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + + prev = &prev_p->thread; + next = &next_p->thread; + + if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || + test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) + ds_switch_to(prev_p, next_p); + else if (next->debugctlmsr != prev->debugctlmsr) + update_debugctlmsr(next->debugctlmsr); + + if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { + set_debugreg(next->debugreg0, 0); + set_debugreg(next->debugreg1, 1); + set_debugreg(next->debugreg2, 2); + set_debugreg(next->debugreg3, 3); + /* no 4 and 5 */ + set_debugreg(next->debugreg6, 6); + set_debugreg(next->debugreg7, 7); + } + + if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ + test_tsk_thread_flag(next_p, TIF_NOTSC)) { + /* prev and next are different */ + if (test_tsk_thread_flag(next_p, TIF_NOTSC)) + hard_disable_TSC(); + else + hard_enable_TSC(); + } + + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + /* + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: + */ + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + /* + * Clear any possible leftover bits: + */ + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + } +} + +int sys_fork(struct pt_regs *regs) +{ + return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +int sys_vfork(struct pt_regs *regs) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, + NULL, NULL); +} + + +/* * Idle related variables and functions */ unsigned long boot_option_idle_override = 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 646da41a620..14014d766ca 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -230,55 +230,6 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) } EXPORT_SYMBOL(kernel_thread); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - /* The process may have allocated an io port bitmap... nuke it. */ - if (unlikely(test_thread_flag(TIF_IO_BITMAP))) { - struct task_struct *tsk = current; - struct thread_struct *t = &tsk->thread; - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, tss->io_bitmap_max); - t->io_bitmap_max = 0; - tss->io_bitmap_owner = NULL; - tss->io_bitmap_max = 0; - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; - put_cpu(); - } - - ds_exit_thread(current); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - clear_tsk_thread_flag(tsk, TIF_DEBUG); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -366,127 +317,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); -} - -void disable_TSC(void) -{ - preempt_disable(); - if (!test_and_set_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_disable_TSC(); - preempt_enable(); -} - -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - -static void enable_TSC(void) -{ - preempt_disable(); - if (test_and_clear_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_enable_TSC(); - preempt_enable(); -} - -int get_tsc_mode(unsigned long adr) -{ - unsigned int val; - - if (test_thread_flag(TIF_NOTSC)) - val = PR_TSC_SIGSEGV; - else - val = PR_TSC_ENABLE; - - return put_user(val, (unsigned int __user *)adr); -} - -int set_tsc_mode(unsigned int val) -{ - if (val == PR_TSC_SIGSEGV) - disable_TSC(); - else if (val == PR_TSC_ENABLE) - enable_TSC(); - else - return -EINVAL; - - return 0; -} - -static noinline void -__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; - - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); - - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg0, 0); - set_debugreg(next->debugreg1, 1); - set_debugreg(next->debugreg2, 2); - set_debugreg(next->debugreg3, 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg6, 6); - set_debugreg(next->debugreg7, 7); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Disable the bitmap via an invalid offset. We still cache - * the previous bitmap owner and the IO bitmap contents: - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; - return; - } - - if (likely(next == tss->io_bitmap_owner)) { - /* - * Previous owner of the bitmap (hence the bitmap content) - * matches the next task, we dont have to do anything but - * to set a valid offset in the TSS: - */ - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - return; - } - /* - * Lazy TSS's I/O bitmap copy. We set an invalid offset here - * and we let the task to get a GPF in case an I/O instruction - * is performed. The handler of the GPF will verify that the - * faulting task has a valid I/O bitmap and, it true, does the - * real copy and restart the instruction. This will save us - * redundant copies when the currently switched task does not - * perform any I/O during its timeslice. - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY; -} /* * switch_to(x,yn) should switch tasks from x to y. @@ -600,11 +430,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - int sys_clone(struct pt_regs *regs) { unsigned long clone_flags; @@ -621,21 +446,6 @@ int sys_clone(struct pt_regs *regs) } /* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - -/* * sys_execve() executes a new program. */ int sys_execve(struct pt_regs *regs) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 836ef6575f0..abb7e6a7f0c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -237,61 +237,6 @@ void show_regs(struct pt_regs *regs) show_trace(NULL, regs, (void *)(regs + 1), regs->bp); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - struct task_struct *me = current; - struct thread_struct *t = &me->thread; - - if (me->thread.io_bitmap_ptr) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - } - - ds_exit_thread(current); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) { - clear_tsk_thread_flag(tsk, TIF_ABI_PENDING); - if (test_tsk_thread_flag(tsk, TIF_IA32)) { - clear_tsk_thread_flag(tsk, TIF_IA32); - } else { - set_tsk_thread_flag(tsk, TIF_IA32); - current_thread_info()->status |= TS_COMPAT; - } - } - clear_tsk_thread_flag(tsk, TIF_DEBUG); - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { @@ -425,118 +370,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); -} - -void disable_TSC(void) -{ - preempt_disable(); - if (!test_and_set_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_disable_TSC(); - preempt_enable(); -} - -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - -static void enable_TSC(void) -{ - preempt_disable(); - if (test_and_clear_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_enable_TSC(); - preempt_enable(); -} - -int get_tsc_mode(unsigned long adr) -{ - unsigned int val; - - if (test_thread_flag(TIF_NOTSC)) - val = PR_TSC_SIGSEGV; - else - val = PR_TSC_ENABLE; - - return put_user(val, (unsigned int __user *)adr); -} - -int set_tsc_mode(unsigned int val) -{ - if (val == PR_TSC_SIGSEGV) - disable_TSC(); - else if (val == PR_TSC_ENABLE) - enable_TSC(); - else - return -EINVAL; - - return 0; -} - -/* - * This special macro can be used to load a debugging register - */ -#define loaddebug(thread, r) set_debugreg(thread->debugreg ## r, r) - -static inline void __switch_to_xtra(struct task_struct *prev_p, - struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread, - next = &next_p->thread; - - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); - - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } -} - /* * switch_to(x,y) should switch tasks from x to y. * @@ -694,11 +527,6 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -asmlinkage long sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) @@ -708,22 +536,6 @@ sys_clone(unsigned long clone_flags, unsigned long newsp, return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); } -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -asmlinkage long sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, - NULL, NULL); -} - unsigned long get_wchan(struct task_struct *p) { unsigned long stack; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index fb2159a5c81..3d9672e59c1 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1383,7 +1383,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, #ifdef CONFIG_X86_32 # define IS_IA32 1 #elif defined CONFIG_IA32_EMULATION -# define IS_IA32 test_thread_flag(TIF_IA32) +# define IS_IA32 is_compat_task() #else # define IS_IA32 0 #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5b85759e797..4c54bc0d8ff 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -600,19 +600,7 @@ static int __init setup_elfcorehdr(char *arg) early_param("elfcorehdr", setup_elfcorehdr); #endif -static int __init default_update_apic(void) -{ -#ifdef CONFIG_SMP - if (!apic->wakeup_cpu) - apic->wakeup_cpu = wakeup_secondary_cpu_via_init; -#endif - - return 0; -} - -static struct x86_quirks default_x86_quirks __initdata = { - .update_apic = default_update_apic, -}; +static struct x86_quirks default_x86_quirks __initdata; struct x86_quirks *x86_quirks __initdata = &default_x86_quirks; @@ -875,9 +863,7 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); -#ifdef CONFIG_X86_64 vsmp_init(); -#endif io_delay_init(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 7cdcd16885e..d2cc6428c58 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -187,40 +187,35 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, /* * Set up a signal frame. */ -#ifdef CONFIG_X86_32 -static const struct { - u16 poplmovl; - u32 val; - u16 int80; -} __attribute__((packed)) retcode = { - 0xb858, /* popl %eax; movl $..., %eax */ - __NR_sigreturn, - 0x80cd, /* int $0x80 */ -}; - -static const struct { - u8 movl; - u32 val; - u16 int80; - u8 pad; -} __attribute__((packed)) rt_retcode = { - 0xb8, /* movl $..., %eax */ - __NR_rt_sigreturn, - 0x80cd, /* int $0x80 */ - 0 -}; /* * Determine which stack to use.. */ +static unsigned long align_sigframe(unsigned long sp) +{ +#ifdef CONFIG_X86_32 + /* + * Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. + */ + sp = ((sp + 4) & -16ul) - 4; +#else /* !CONFIG_X86_32 */ + sp = round_down(sp, 16) - 8; +#endif + return sp; +} + static inline void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, - void **fpstate) + void __user **fpstate) { - unsigned long sp; - /* Default to using normal stack */ - sp = regs->sp; + unsigned long sp = regs->sp; + +#ifdef CONFIG_X86_64 + /* redzone */ + sp -= 128; +#endif /* CONFIG_X86_64 */ /* * If we are on the alternate signal stack and would overflow it, don't. @@ -234,30 +229,52 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; } else { +#ifdef CONFIG_X86_32 /* This is the legacy signal stack switching. */ if ((regs->ss & 0xffff) != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) sp = (unsigned long) ka->sa.sa_restorer; +#endif /* CONFIG_X86_32 */ } if (used_math()) { - sp = sp - sig_xstate_size; - *fpstate = (struct _fpstate *) sp; + sp -= sig_xstate_size; +#ifdef CONFIG_X86_64 + sp = round_down(sp, 64); +#endif /* CONFIG_X86_64 */ + *fpstate = (void __user *)sp; + if (save_i387_xstate(*fpstate) < 0) return (void __user *)-1L; } - sp -= frame_size; - /* - * Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. - */ - sp = ((sp + 4) & -16ul) - 4; - - return (void __user *) sp; + return (void __user *)align_sigframe(sp - frame_size); } +#ifdef CONFIG_X86_32 +static const struct { + u16 poplmovl; + u32 val; + u16 int80; +} __attribute__((packed)) retcode = { + 0xb858, /* popl %eax; movl $..., %eax */ + __NR_sigreturn, + 0x80cd, /* int $0x80 */ +}; + +static const struct { + u8 movl; + u32 val; + u16 int80; + u8 pad; +} __attribute__((packed)) rt_retcode = { + 0xb8, /* movl $..., %eax */ + __NR_rt_sigreturn, + 0x80cd, /* int $0x80 */ + 0 +}; + static int __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs *regs) @@ -388,24 +405,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; } #else /* !CONFIG_X86_32 */ -/* - * Determine which stack to use.. - */ -static void __user * -get_stack(struct k_sigaction *ka, unsigned long sp, unsigned long size) -{ - /* Default to using normal stack - redzone*/ - sp -= 128; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) - sp = current->sas_ss_sp + current->sas_ss_size; - } - - return (void __user *)round_down(sp - size, 64); -} - static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { @@ -414,15 +413,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, int err = 0; struct task_struct *me = current; - if (used_math()) { - fp = get_stack(ka, regs->sp, sig_xstate_size); - frame = (void __user *)round_down( - (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8; - - if (save_i387_xstate(fp) < 0) - return -EFAULT; - } else - frame = get_stack(ka, regs->sp, sizeof(struct rt_sigframe)) - 8; + frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9ce666387f3..249334f5080 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -112,7 +112,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); -static atomic_t init_deasserted; +atomic_t init_deasserted; /* Set if we find a B stepping CPU */ @@ -614,12 +614,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) unsigned long send_status, accept_status = 0; int maxlvt, num_starts, j; - if (get_uv_system_type() == UV_NON_UNIQUE_APIC) { - send_status = uv_wakeup_secondary(phys_apicid, start_eip); - atomic_set(&init_deasserted, 1); - return send_status; - } - maxlvt = lapic_get_maxlvt(); /* @@ -748,7 +742,8 @@ static void __cpuinit do_fork_idle(struct work_struct *work) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. - * Returns zero if CPU booted OK, else error code from ->wakeup_cpu. + * Returns zero if CPU booted OK, else error code from + * ->wakeup_secondary_cpu. */ static int __cpuinit do_boot_cpu(int apicid, int cpu) { @@ -835,9 +830,13 @@ do_rest: } /* - * Starting actual IPI sequence... + * Kick the secondary CPU. Use the method in the APIC driver + * if it's defined - or use an INIT boot APIC message otherwise: */ - boot_error = apic->wakeup_cpu(apicid, start_ip); + if (apic->wakeup_secondary_cpu) + boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); + else + boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); if (!boot_error) { /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c05430ac1b4..a1d288327ff 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -118,47 +118,6 @@ die_if_kernel(const char *str, struct pt_regs *regs, long err) if (!user_mode_vm(regs)) die(str, regs, err); } - -/* - * Perform the lazy TSS's I/O bitmap copy. If the TSS has an - * invalid offset set (the LAZY one) and the faulting thread has - * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS, - * we set the offset field correctly and return 1. - */ -static int lazy_iobitmap_copy(void) -{ - struct thread_struct *thread; - struct tss_struct *tss; - int cpu; - - cpu = get_cpu(); - tss = &per_cpu(init_tss, cpu); - thread = ¤t->thread; - - if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY && - thread->io_bitmap_ptr) { - memcpy(tss->io_bitmap, thread->io_bitmap_ptr, - thread->io_bitmap_max); - /* - * If the previously set map was extending to higher ports - * than the current one, pad extra space with 0xff (no access). - */ - if (thread->io_bitmap_max < tss->io_bitmap_max) { - memset((char *) tss->io_bitmap + - thread->io_bitmap_max, 0xff, - tss->io_bitmap_max - thread->io_bitmap_max); - } - tss->io_bitmap_max = thread->io_bitmap_max; - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - tss->io_bitmap_owner = thread; - put_cpu(); - - return 1; - } - put_cpu(); - - return 0; -} #endif static void __kprobes @@ -309,11 +268,6 @@ do_general_protection(struct pt_regs *regs, long error_code) conditional_sti(regs); #ifdef CONFIG_X86_32 - if (lazy_iobitmap_copy()) { - /* restart the faulting instruction */ - return; - } - if (regs->flags & X86_VM_MASK) goto gp_in_vm86; #endif diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index c609205df59..74de562812c 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -22,7 +22,7 @@ #include <asm/paravirt.h> #include <asm/setup.h> -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' @@ -114,7 +114,6 @@ static void __init set_vsmp_pv_ops(void) } #endif -#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -139,15 +138,6 @@ int is_vsmp_box(void) return 0; } } -#else -static void __init detect_vsmp_box(void) -{ -} -int is_vsmp_box(void) -{ - return 0; -} -#endif void __init vsmp_init(void) { diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 2b938a38491..08537747cb5 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,4 +1,4 @@ -obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ +obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o gup.o obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index bcc079c282d..00f127c80b0 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -1,5 +1,6 @@ #include <linux/highmem.h> #include <linux/module.h> +#include <linux/swap.h> /* for totalram_pages */ void *kmap(struct page *page) { @@ -156,3 +157,36 @@ EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); EXPORT_SYMBOL(kunmap_atomic); + +#ifdef CONFIG_NUMA +void __init set_highmem_pages_init(void) +{ + struct zone *zone; + int nid; + + for_each_zone(zone) { + unsigned long zone_start_pfn, zone_end_pfn; + + if (!is_highmem(zone)) + continue; + + zone_start_pfn = zone->zone_start_pfn; + zone_end_pfn = zone_start_pfn + zone->spanned_pages; + + nid = zone_to_nid(zone); + printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", + zone->name, nid, zone_start_pfn, zone_end_pfn); + + add_highpages_with_active_regions(nid, zone_start_pfn, + zone_end_pfn); + } + totalram_pages += totalhigh_pages; +} +#else +void __init set_highmem_pages_init(void) +{ + add_highpages_with_active_regions(0, highstart_pfn, highend_pfn); + + totalram_pages += totalhigh_pages; +} +#endif /* CONFIG_NUMA */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c new file mode 100644 index 00000000000..ce6a722587d --- /dev/null +++ b/arch/x86/mm/init.c @@ -0,0 +1,49 @@ +#include <linux/swap.h> +#include <asm/cacheflush.h> +#include <asm/page.h> +#include <asm/sections.h> +#include <asm/system.h> + +void free_init_pages(char *what, unsigned long begin, unsigned long end) +{ + unsigned long addr = begin; + + if (addr >= end) + return; + + /* + * If debugging page accesses then do not free this memory but + * mark them not present - any buggy init-section access will + * create a kernel page fault: + */ +#ifdef CONFIG_DEBUG_PAGEALLOC + printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", + begin, PAGE_ALIGN(end)); + set_memory_np(begin, (end - begin) >> PAGE_SHIFT); +#else + /* + * We just marked the kernel text read only above, now that + * we are going to free part of that, we need to make that + * writeable first. + */ + set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); + + printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); + + for (; addr < end; addr += PAGE_SIZE) { + ClearPageReserved(virt_to_page(addr)); + init_page_count(virt_to_page(addr)); + memset((void *)(addr & ~(PAGE_SIZE-1)), + POISON_FREE_INITMEM, PAGE_SIZE); + free_page(addr); + totalram_pages++; + } +#endif +} + +void free_initmem(void) +{ + free_init_pages("unused kernel memory", + (unsigned long)(&__init_begin), + (unsigned long)(&__init_end)); +} diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ef0bb941cdf..47df0e1bbeb 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -50,8 +50,6 @@ #include <asm/setup.h> #include <asm/cacheflush.h> -unsigned int __VMALLOC_RESERVE = 128 << 20; - unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; @@ -486,22 +484,10 @@ void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, work_with_active_regions(nid, add_highpages_work_fn, &data); } -#ifndef CONFIG_NUMA -static void __init set_highmem_pages_init(void) -{ - add_highpages_with_active_regions(0, highstart_pfn, highend_pfn); - - totalram_pages += totalhigh_pages; -} -#endif /* !CONFIG_NUMA */ - #else static inline void permanent_kmaps_init(pgd_t *pgd_base) { } -static inline void set_highmem_pages_init(void) -{ -} #endif /* CONFIG_HIGHMEM */ void __init native_pagetable_setup_start(pgd_t *base) @@ -864,10 +850,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse) unsigned long puds, pmds, ptes, tables, start; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = PAGE_ALIGN(puds * sizeof(pud_t)); + tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += PAGE_ALIGN(pmds * sizeof(pmd_t)); + tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); if (use_pse) { unsigned long extra; @@ -878,10 +864,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse) } else ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - tables += PAGE_ALIGN(ptes * sizeof(pte_t)); + tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); /* for fixmap */ - tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t)); + tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); /* * RED-PEN putting page tables only on node 0 could @@ -1231,45 +1217,6 @@ void mark_rodata_ro(void) } #endif -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * If debugging page accesses then do not free this memory but - * mark them not present - any buggy init-section access will - * create a kernel page fault: - */ - printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); - set_memory_np(begin, (end - begin) >> PAGE_SHIFT); -#else - unsigned long addr; - - /* - * We just marked the kernel text read only above, now that - * we are going to free part of that, we need to make that - * writeable first. - */ - set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); -#endif -} - -void free_initmem(void) -{ - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); -} - #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7d4e76da336..11981fc8570 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -748,6 +748,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, pos = start_pfn << PAGE_SHIFT; end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (end_pfn > (end >> PAGE_SHIFT)) + end_pfn = end >> PAGE_SHIFT; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); pos = end_pfn << PAGE_SHIFT; @@ -979,43 +981,6 @@ void __init mem_init(void) initsize >> 10); } -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr = begin; - - if (addr >= end) - return; - - /* - * If debugging page accesses then do not free this memory but - * mark them not present - any buggy init-section access will - * create a kernel page fault: - */ -#ifdef CONFIG_DEBUG_PAGEALLOC - printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); - set_memory_np(begin, (end - begin) >> PAGE_SHIFT); -#else - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); - - for (; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)(addr & ~(PAGE_SIZE-1)), - POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } -#endif -} - -void free_initmem(void) -{ - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); -} - #ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index ca53224fc56..04102d42ff4 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -20,6 +20,17 @@ #include <asm/pat.h> #include <linux/module.h> +int is_io_mapping_possible(resource_size_t base, unsigned long size) +{ +#ifndef CONFIG_X86_PAE + /* There is no way to map greater than 1 << 32 address without PAE */ + if (base + size > 0x100000000ULL) + return 0; +#endif + return 1; +} +EXPORT_SYMBOL_GPL(is_io_mapping_possible); + /* 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 9cab18b0b85..0bcd7883d03 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; - - 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; - } + 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"); +} - incr = sizeof(unsigned long); +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(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 @@ static void __init memtest(unsigned long start_phys, unsigned long size, 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 @@ early_param("memtest", parse_memtest); 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); + 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); + } - t_start += t_size; - } + 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); } - printk(KERN_CONT "\n"); } diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 3957cd6d645..451fe95a035 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -423,32 +423,6 @@ void __init initmem_init(unsigned long start_pfn, setup_bootmem_allocator(); } -void __init set_highmem_pages_init(void) -{ -#ifdef CONFIG_HIGHMEM - struct zone *zone; - int nid; - - for_each_zone(zone) { - unsigned long zone_start_pfn, zone_end_pfn; - - if (!is_highmem(zone)) - continue; - - zone_start_pfn = zone->zone_start_pfn; - zone_end_pfn = zone_start_pfn + zone->spanned_pages; - - nid = zone_to_nid(zone); - printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", - zone->name, nid, zone_start_pfn, zone_end_pfn); - - add_highpages_with_active_regions(nid, zone_start_pfn, - zone_end_pfn); - } - totalram_pages += totalhigh_pages; -#endif -} - #ifdef CONFIG_MEMORY_HOTPLUG static int paddr_to_nid(u64 addr) { diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 05f9aef6818..2ed37158012 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -11,6 +11,7 @@ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/fs.h> @@ -634,6 +635,33 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) } /* + * 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 +670,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, 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 +707,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, 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; @@ -877,6 +890,7 @@ pgprot_t pgprot_writecombine(pgprot_t prot) else return pgprot_noncached(prot); } +EXPORT_SYMBOL_GPL(pgprot_writecombine); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 86f2ffc43c3..5b7c7c8464f 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -313,6 +313,24 @@ int ptep_clear_flush_young(struct vm_area_struct *vma, return young; } +/** + * reserve_top_address - reserves a hole in the top of kernel address space + * @reserve - size of hole to reserve + * + * Can be used to relocate the fixmap area and poke a hole in the top + * of kernel address space to make room for a hypervisor. + */ +void __init reserve_top_address(unsigned long reserve) +{ +#ifdef CONFIG_X86_32 + BUG_ON(fixmaps_set > 0); + printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", + (int)-reserve); + __FIXADDR_TOP = -reserve - PAGE_SIZE; + __VMALLOC_RESERVE += reserve; +#endif +} + int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 0951db9ee51..f2e477c91c1 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -20,6 +20,8 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> +unsigned int __VMALLOC_RESERVE = 128 << 20; + /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. @@ -97,22 +99,6 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); -/** - * reserve_top_address - reserves a hole in the top of kernel address space - * @reserve - size of hole to reserve - * - * Can be used to relocate the fixmap area and poke a hole in the top - * of kernel address space to make room for a hypervisor. - */ -void __init reserve_top_address(unsigned long reserve) -{ - BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; - __VMALLOC_RESERVE += reserve; -} - /* * vmalloc=size forces the vmalloc area to be exactly 'size' * bytes. This can be used to increase (or decrease) the diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index e9f80c744cf..10131fbdaad 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -78,8 +78,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) if (cpu_has_arch_perfmon) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); - if (counter_width < eax.split.bit_width) - counter_width = eax.split.bit_width; + + /* + * For Core2 (family 6, model 15), don't reset the + * counter width: + */ + if (!(eax.split.version_id == 0 && + current_cpu_data.x86 == 6 && + current_cpu_data.x86_model == 15)) { + + if (counter_width < eax.split.bit_width) + counter_width = eax.split.bit_width; + } } /* clear all counters */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 352ea683065..82cd39a6cbd 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -942,6 +942,9 @@ asmlinkage void __init xen_start_kernel(void) 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); |