diff options
Diffstat (limited to 'include/asm-x86')
38 files changed, 922 insertions, 693 deletions
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h index 9cbd9a668af..b4a46b7be79 100644 --- a/include/asm-x86/bios_ebda.h +++ b/include/asm-x86/bios_ebda.h @@ -1,6 +1,8 @@ #ifndef _MACH_BIOS_EBDA_H #define _MACH_BIOS_EBDA_H +#include <asm/io.h> + /* * there is a real-mode segmented pointer pointing to the * 4K EBDA area at 0x40E. diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h index 1ae7b270a1e..b81a4d4d333 100644 --- a/include/asm-x86/bitops.h +++ b/include/asm-x86/bitops.h @@ -62,12 +62,9 @@ static inline void set_bit(int nr, volatile void *addr) */ static inline void __set_bit(int nr, volatile void *addr) { - asm volatile("bts %1,%0" - : ADDR - : "Ir" (nr) : "memory"); + asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); } - /** * clear_bit - Clears a bit in memory * @nr: Bit to clear @@ -297,19 +294,145 @@ static inline int variable_test_bit(int nr, volatile const void *addr) static int test_bit(int nr, const volatile unsigned long *addr); #endif -#define test_bit(nr,addr) \ - (__builtin_constant_p(nr) ? \ - constant_test_bit((nr),(addr)) : \ - variable_test_bit((nr),(addr))) +#define test_bit(nr, addr) \ + (__builtin_constant_p((nr)) \ + ? constant_test_bit((nr), (addr)) \ + : variable_test_bit((nr), (addr))) + +/** + * __ffs - find first set bit in word + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +static inline unsigned long __ffs(unsigned long word) +{ + asm("bsf %1,%0" + : "=r" (word) + : "rm" (word)); + return word; +} + +/** + * ffz - find first zero bit in word + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +static inline unsigned long ffz(unsigned long word) +{ + asm("bsf %1,%0" + : "=r" (word) + : "r" (~word)); + return word; +} + +/* + * __fls: find last set bit in word + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +static inline unsigned long __fls(unsigned long word) +{ + asm("bsr %1,%0" + : "=r" (word) + : "rm" (word)); + return word; +} + +#ifdef __KERNEL__ +/** + * ffs - find first set bit in word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs + * routines, therefore differs in spirit from the other bitops. + * + * ffs(value) returns 0 if value is 0 or the position of the first + * set bit if value is nonzero. The first (least significant) bit + * is at position 1. + */ +static inline int ffs(int x) +{ + int r; +#ifdef CONFIG_X86_CMOV + asm("bsfl %1,%0\n\t" + "cmovzl %2,%0" + : "=r" (r) : "rm" (x), "r" (-1)); +#else + asm("bsfl %1,%0\n\t" + "jnz 1f\n\t" + "movl $-1,%0\n" + "1:" : "=r" (r) : "rm" (x)); +#endif + return r + 1; +} + +/** + * fls - find last set bit in word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * ffs, but returns the position of the most significant set bit. + * + * fls(value) returns 0 if value is 0 or the position of the last + * set bit if value is nonzero. The last (most significant) bit is + * at position 32. + */ +static inline int fls(int x) +{ + int r; +#ifdef CONFIG_X86_CMOV + asm("bsrl %1,%0\n\t" + "cmovzl %2,%0" + : "=&r" (r) : "rm" (x), "rm" (-1)); +#else + asm("bsrl %1,%0\n\t" + "jnz 1f\n\t" + "movl $-1,%0\n" + "1:" : "=r" (r) : "rm" (x)); +#endif + return r + 1; +} +#endif /* __KERNEL__ */ #undef BASE_ADDR #undef BIT_ADDR #undef ADDR -#ifdef CONFIG_X86_32 -# include "bitops_32.h" -#else -# include "bitops_64.h" -#endif +static inline void set_bit_string(unsigned long *bitmap, + unsigned long i, int len) +{ + unsigned long end = i + len; + while (i < end) { + __set_bit(i, bitmap); + i++; + } +} + +#ifdef __KERNEL__ + +#include <asm-generic/bitops/sched.h> + +#define ARCH_HAS_FAST_MULTIPLIER 1 + +#include <asm-generic/bitops/hweight.h> + +#endif /* __KERNEL__ */ + +#include <asm-generic/bitops/fls64.h> + +#ifdef __KERNEL__ + +#include <asm-generic/bitops/ext2-non-atomic.h> + +#define ext2_set_bit_atomic(lock, nr, addr) \ + test_and_set_bit((nr), (unsigned long *)(addr)) +#define ext2_clear_bit_atomic(lock, nr, addr) \ + test_and_clear_bit((nr), (unsigned long *)(addr)) + +#include <asm-generic/bitops/minix.h> +#endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ diff --git a/include/asm-x86/bitops_32.h b/include/asm-x86/bitops_32.h deleted file mode 100644 index 2513a81f82a..00000000000 --- a/include/asm-x86/bitops_32.h +++ /dev/null @@ -1,166 +0,0 @@ -#ifndef _I386_BITOPS_H -#define _I386_BITOPS_H - -/* - * Copyright 1992, Linus Torvalds. - */ - -/** - * find_first_zero_bit - find the first zero bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search - * - * Returns the bit number of the first zero bit, not the number of the byte - * containing a bit. - */ -static inline int find_first_zero_bit(const unsigned long *addr, unsigned size) -{ - int d0, d1, d2; - int res; - - if (!size) - return 0; - /* This looks at memory. - * Mark it volatile to tell gcc not to move it around - */ - asm volatile("movl $-1,%%eax\n\t" - "xorl %%edx,%%edx\n\t" - "repe; scasl\n\t" - "je 1f\n\t" - "xorl -4(%%edi),%%eax\n\t" - "subl $4,%%edi\n\t" - "bsfl %%eax,%%edx\n" - "1:\tsubl %%ebx,%%edi\n\t" - "shll $3,%%edi\n\t" - "addl %%edi,%%edx" - : "=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2) - : "1" ((size + 31) >> 5), "2" (addr), - "b" (addr) : "memory"); - return res; -} - -/** - * find_next_zero_bit - find the first zero bit in a memory region - * @addr: The address to base the search on - * @offset: The bit number to start searching at - * @size: The maximum size to search - */ -int find_next_zero_bit(const unsigned long *addr, int size, int offset); - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - __asm__("bsfl %1,%0" - :"=r" (word) - :"rm" (word)); - return word; -} - -/** - * find_first_bit - find the first set bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search - * - * Returns the bit number of the first set bit, not the number of the byte - * containing a bit. - */ -static inline unsigned find_first_bit(const unsigned long *addr, unsigned size) -{ - unsigned x = 0; - - while (x < size) { - unsigned long val = *addr++; - if (val) - return __ffs(val) + x; - x += sizeof(*addr) << 3; - } - return x; -} - -/** - * find_next_bit - find the first set bit in a memory region - * @addr: The address to base the search on - * @offset: The bit number to start searching at - * @size: The maximum size to search - */ -int find_next_bit(const unsigned long *addr, int size, int offset); - -/** - * ffz - find first zero in word. - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -static inline unsigned long ffz(unsigned long word) -{ - __asm__("bsfl %1,%0" - :"=r" (word) - :"r" (~word)); - return word; -} - -#ifdef __KERNEL__ - -#include <asm-generic/bitops/sched.h> - -/** - * ffs - find first bit set - * @x: the word to search - * - * This is defined the same way as - * the libc and compiler builtin ffs routines, therefore - * differs in spirit from the above ffz() (man ffs). - */ -static inline int ffs(int x) -{ - int r; - - __asm__("bsfl %1,%0\n\t" - "jnz 1f\n\t" - "movl $-1,%0\n" - "1:" : "=r" (r) : "rm" (x)); - return r+1; -} - -/** - * fls - find last bit set - * @x: the word to search - * - * This is defined the same way as ffs(). - */ -static inline int fls(int x) -{ - int r; - - __asm__("bsrl %1,%0\n\t" - "jnz 1f\n\t" - "movl $-1,%0\n" - "1:" : "=r" (r) : "rm" (x)); - return r+1; -} - -#include <asm-generic/bitops/hweight.h> - -#endif /* __KERNEL__ */ - -#include <asm-generic/bitops/fls64.h> - -#ifdef __KERNEL__ - -#include <asm-generic/bitops/ext2-non-atomic.h> - -#define ext2_set_bit_atomic(lock, nr, addr) \ - test_and_set_bit((nr), (unsigned long *)(addr)) -#define ext2_clear_bit_atomic(lock, nr, addr) \ - test_and_clear_bit((nr), (unsigned long *)(addr)) - -#include <asm-generic/bitops/minix.h> - -#endif /* __KERNEL__ */ - -#endif /* _I386_BITOPS_H */ diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h deleted file mode 100644 index 365f8207ea5..00000000000 --- a/include/asm-x86/bitops_64.h +++ /dev/null @@ -1,162 +0,0 @@ -#ifndef _X86_64_BITOPS_H -#define _X86_64_BITOPS_H - -/* - * Copyright 1992, Linus Torvalds. - */ - -extern long find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern long find_next_zero_bit(const unsigned long *addr, long size, long offset); -extern long find_first_bit(const unsigned long *addr, unsigned long size); -extern long find_next_bit(const unsigned long *addr, long size, long offset); - -/* return index of first bet set in val or max when no bit is set */ -static inline long __scanbit(unsigned long val, unsigned long max) -{ - asm("bsfq %1,%0 ; cmovz %2,%0" : "=&r" (val) : "r" (val), "r" (max)); - return val; -} - -#define find_next_bit(addr,size,off) \ -((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \ - ((off) + (__scanbit((*(unsigned long *)addr) >> (off),(size)-(off)))) : \ - find_next_bit(addr,size,off))) - -#define find_next_zero_bit(addr,size,off) \ -((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \ - ((off)+(__scanbit(~(((*(unsigned long *)addr)) >> (off)),(size)-(off)))) : \ - find_next_zero_bit(addr,size,off))) - -#define find_first_bit(addr, size) \ - ((__builtin_constant_p((size)) && (size) <= BITS_PER_LONG \ - ? (__scanbit(*(unsigned long *)(addr), (size))) \ - : find_first_bit((addr), (size)))) - -#define find_first_zero_bit(addr, size) \ - ((__builtin_constant_p((size)) && (size) <= BITS_PER_LONG \ - ? (__scanbit(~*(unsigned long *)(addr), (size))) \ - : find_first_zero_bit((addr), (size)))) - -static inline void set_bit_string(unsigned long *bitmap, unsigned long i, - int len) -{ - unsigned long end = i + len; - while (i < end) { - __set_bit(i, bitmap); - i++; - } -} - -/** - * ffz - find first zero in word. - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -static inline unsigned long ffz(unsigned long word) -{ - __asm__("bsfq %1,%0" - :"=r" (word) - :"r" (~word)); - return word; -} - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - __asm__("bsfq %1,%0" - :"=r" (word) - :"rm" (word)); - return word; -} - -/* - * __fls: find last bit set. - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -static inline unsigned long __fls(unsigned long word) -{ - __asm__("bsrq %1,%0" - :"=r" (word) - :"rm" (word)); - return word; -} - -#ifdef __KERNEL__ - -#include <asm-generic/bitops/sched.h> - -/** - * ffs - find first bit set - * @x: the word to search - * - * This is defined the same way as - * the libc and compiler builtin ffs routines, therefore - * differs in spirit from the above ffz (man ffs). - */ -static inline int ffs(int x) -{ - int r; - - __asm__("bsfl %1,%0\n\t" - "cmovzl %2,%0" - : "=r" (r) : "rm" (x), "r" (-1)); - return r+1; -} - -/** - * fls64 - find last bit set in 64 bit word - * @x: the word to search - * - * This is defined the same way as fls. - */ -static inline int fls64(__u64 x) -{ - if (x == 0) - return 0; - return __fls(x) + 1; -} - -/** - * fls - find last bit set - * @x: the word to search - * - * This is defined the same way as ffs. - */ -static inline int fls(int x) -{ - int r; - - __asm__("bsrl %1,%0\n\t" - "cmovzl %2,%0" - : "=&r" (r) : "rm" (x), "rm" (-1)); - return r+1; -} - -#define ARCH_HAS_FAST_MULTIPLIER 1 - -#include <asm-generic/bitops/hweight.h> - -#endif /* __KERNEL__ */ - -#ifdef __KERNEL__ - -#include <asm-generic/bitops/ext2-non-atomic.h> - -#define ext2_set_bit_atomic(lock, nr, addr) \ - test_and_set_bit((nr), (unsigned long *)(addr)) -#define ext2_clear_bit_atomic(lock, nr, addr) \ - test_and_clear_bit((nr), (unsigned long *)(addr)) - -#include <asm-generic/bitops/minix.h> - -#endif /* __KERNEL__ */ - -#endif /* _X86_64_BITOPS_H */ diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h index 51151356840..e8659909e5f 100644 --- a/include/asm-x86/bootparam.h +++ b/include/asm-x86/bootparam.h @@ -9,6 +9,17 @@ #include <asm/ist.h> #include <video/edid.h> +/* setup data types */ +#define SETUP_NONE 0 + +/* extensible setup data list node */ +struct setup_data { + u64 next; + u32 type; + u32 len; + u8 data[0]; +}; + struct setup_header { __u8 setup_sects; __u16 root_flags; @@ -46,6 +57,9 @@ struct setup_header { __u32 cmdline_size; __u32 hardware_subarch; __u64 hardware_subarch_data; + __u32 payload_offset; + __u32 payload_length; + __u64 setup_data; } __attribute__((packed)); struct sys_desc_table { diff --git a/include/asm-x86/e820_64.h b/include/asm-x86/e820_64.h index f478c57eb06..71c4d685d30 100644 --- a/include/asm-x86/e820_64.h +++ b/include/asm-x86/e820_64.h @@ -48,7 +48,8 @@ extern struct e820map e820; extern void update_e820(void); extern void reserve_early(unsigned long start, unsigned long end, char *name); -extern void early_res_to_bootmem(void); +extern void free_early(unsigned long start, unsigned long end); +extern void early_res_to_bootmem(unsigned long start, unsigned long end); #endif/*!__ASSEMBLY__*/ diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h index 382eb271a89..5bd206973dc 100644 --- a/include/asm-x86/fixmap.h +++ b/include/asm-x86/fixmap.h @@ -1,5 +1,13 @@ +#ifndef _ASM_FIXMAP_H +#define _ASM_FIXMAP_H + #ifdef CONFIG_X86_32 # include "fixmap_32.h" #else # include "fixmap_64.h" #endif + +#define clear_fixmap(idx) \ + __set_fixmap(idx, 0, __pgprot(0)) + +#endif diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h index eb1665125c4..4b96148e90c 100644 --- a/include/asm-x86/fixmap_32.h +++ b/include/asm-x86/fixmap_32.h @@ -10,8 +10,8 @@ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 */ -#ifndef _ASM_FIXMAP_H -#define _ASM_FIXMAP_H +#ifndef _ASM_FIXMAP_32_H +#define _ASM_FIXMAP_32_H /* used by vmalloc.c, vsyscall.lds.S. @@ -121,9 +121,6 @@ extern void reserve_top_address(unsigned long reserve); #define set_fixmap_nocache(idx, phys) \ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) -#define clear_fixmap(idx) \ - __set_fixmap(idx, 0, __pgprot(0)) - #define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) #define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h index f3d76858c0e..355d26a75a8 100644 --- a/include/asm-x86/fixmap_64.h +++ b/include/asm-x86/fixmap_64.h @@ -8,8 +8,8 @@ * Copyright (C) 1998 Ingo Molnar */ -#ifndef _ASM_FIXMAP_H -#define _ASM_FIXMAP_H +#ifndef _ASM_FIXMAP_64_H +#define _ASM_FIXMAP_64_H #include <linux/kernel.h> #include <asm/apicdef.h> diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h index 9870cc1f2f8..7154dc4de95 100644 --- a/include/asm-x86/geode.h +++ b/include/asm-x86/geode.h @@ -30,7 +30,13 @@ extern int geode_get_dev_base(unsigned int dev); /* MSRS */ -#define GX_GLCP_SYS_RSTPLL 0x4C000014 +#define MSR_GLIU_P2D_RO0 0x10000029 + +#define MSR_LX_GLD_MSR_CONFIG 0x48002001 +#define MSR_LX_MSR_PADSEL 0x48002011 /* NOT 0x48000011; the data + * sheet has the wrong value */ +#define MSR_GLCP_SYS_RSTPLL 0x4C000014 +#define MSR_GLCP_DOTPLL 0x4C000015 #define MSR_LBAR_SMB 0x5140000B #define MSR_LBAR_GPIO 0x5140000C @@ -45,8 +51,14 @@ extern int geode_get_dev_base(unsigned int dev); #define MSR_PIC_ZSEL_LOW 0x51400022 #define MSR_PIC_ZSEL_HIGH 0x51400023 -#define MFGPT_IRQ_MSR 0x51400028 -#define MFGPT_NR_MSR 0x51400029 +#define MSR_MFGPT_IRQ 0x51400028 +#define MSR_MFGPT_NR 0x51400029 +#define MSR_MFGPT_SETUP 0x5140002B + +#define MSR_LX_SPARE_MSR 0x80000011 /* DC-specific */ + +#define MSR_GX_GLD_MSR_CONFIG 0xC0002001 +#define MSR_GX_MSR_PADSEL 0xC0002011 /* Resource Sizes */ @@ -93,6 +105,15 @@ extern int geode_get_dev_base(unsigned int dev); #define PM_AWKD 0x50 #define PM_SSC 0x54 +/* VSA2 magic values */ + +#define VSA_VRC_INDEX 0xAC1C +#define VSA_VRC_DATA 0xAC1E +#define VSA_VR_UNLOCK 0xFC53 /* unlock virtual register */ +#define VSA_VR_SIGNATURE 0x0003 +#define VSA_VR_MEM_SIZE 0x0200 +#define VSA_SIG 0x4132 /* signature is ascii 'VSA2' */ + /* GPIO */ #define GPIO_OUTPUT_VAL 0x00 @@ -164,6 +185,17 @@ static inline int is_geode(void) return (is_geode_gx() || is_geode_lx()); } +/* + * The VSA has virtual registers that we can query for a signature. + */ +static inline int geode_has_vsa2(void) +{ + outw(VSA_VR_UNLOCK, VSA_VRC_INDEX); + outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX); + + return (inw(VSA_VRC_DATA) == VSA_SIG); +} + /* MFGPTs */ #define MFGPT_MAX_TIMERS 8 diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h new file mode 100644 index 00000000000..14171a4924f --- /dev/null +++ b/include/asm-x86/hugetlb.h @@ -0,0 +1,91 @@ +#ifndef _ASM_X86_HUGETLB_H +#define _ASM_X86_HUGETLB_H + +#include <asm/page.h> + + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) { + return 0; +} + +/* + * If the arch doesn't supply something else, assume that hugepage + * size aligned regions are ok without further preparation. + */ +static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +{ + if (len & ~HPAGE_MASK) + return -EINVAL; + if (addr & ~HPAGE_MASK) + return -EINVAL; + return 0; +} + +static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) { +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + set_pte_at(mm, addr, ptep, pte); +} + +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + return ptep_get_and_clear(mm, addr, ptep); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); +} + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline int arch_prepare_hugepage(struct page *page) +{ + return 0; +} + +static inline void arch_release_hugepage(struct page *page) +{ +} + +#endif /* _ASM_X86_HUGETLB_H */ diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h index 7b292d38671..d5b11f60dbd 100644 --- a/include/asm-x86/io.h +++ b/include/asm-x86/io.h @@ -1,3 +1,6 @@ +#ifndef _ASM_X86_IO_H +#define _ASM_X86_IO_H + #define ARCH_HAS_IOREMAP_WC #ifdef CONFIG_X86_32 @@ -5,7 +8,12 @@ #else # include "io_64.h" #endif + +extern void *xlate_dev_mem_ptr(unsigned long phys); +extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr); + extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, unsigned long prot_val); extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size); +#endif /* _ASM_X86_IO_H */ diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h index 509045f5fda..6e73467a4fb 100644 --- a/include/asm-x86/io_32.h +++ b/include/asm-x86/io_32.h @@ -49,12 +49,6 @@ #include <linux/vmalloc.h> /* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* * Convert a virtual cached pointer to an uncached pointer */ #define xlate_dev_kmem_ptr(p) p diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h index c2f5eef47b8..0930bedf9e4 100644 --- a/include/asm-x86/io_64.h +++ b/include/asm-x86/io_64.h @@ -308,12 +308,6 @@ extern int iommu_bio_merge; #define BIO_VMERGE_BOUNDARY iommu_bio_merge /* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* * Convert a virtual cached pointer to an uncached pointer */ #define xlate_dev_kmem_ptr(p) p diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h index 0c9e17c73e0..d593e14f034 100644 --- a/include/asm-x86/io_apic.h +++ b/include/asm-x86/io_apic.h @@ -1,7 +1,7 @@ #ifndef __ASM_IO_APIC_H #define __ASM_IO_APIC_H -#include <asm/types.h> +#include <linux/types.h> #include <asm/mpspec.h> #include <asm/apicdef.h> @@ -110,11 +110,13 @@ extern int nr_ioapic_registers[MAX_IO_APICS]; * MP-BIOS irq configuration table structures: */ +#define MP_MAX_IOAPIC_PIN 127 + struct mp_ioapic_routing { int apic_id; int gsi_base; int gsi_end; - u32 pin_programmed[4]; + DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); }; /* I/O APIC entries */ diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h index 7a71120426a..80eefef2cc7 100644 --- a/include/asm-x86/kvm.h +++ b/include/asm-x86/kvm.h @@ -188,4 +188,45 @@ struct kvm_cpuid2 { struct kvm_cpuid_entry2 entries[0]; }; +/* for KVM_GET_PIT and KVM_SET_PIT */ +struct kvm_pit_channel_state { + __u32 count; /* can be 65536 */ + __u16 latched_count; + __u8 count_latched; + __u8 status_latched; + __u8 status; + __u8 read_state; + __u8 write_state; + __u8 write_latch; + __u8 rw_mode; + __u8 mode; + __u8 bcd; + __u8 gate; + __s64 count_load_time; +}; + +struct kvm_pit_state { + struct kvm_pit_channel_state channels[3]; +}; + +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) + #endif diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h index 68ee390b284..9d963cd6533 100644 --- a/include/asm-x86/kvm_host.h +++ b/include/asm-x86/kvm_host.h @@ -20,6 +20,13 @@ #include <asm/desc.h> +#define KVM_MAX_VCPUS 16 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + +#define KVM_PIO_PAGE_OFFSET 1 + #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ @@ -39,6 +46,13 @@ #define INVALID_PAGE (~(hpa_t)0) #define UNMAPPED_GVA (~(gpa_t)0) +/* shadow tables are PAE even on non-PAE hosts */ +#define KVM_HPAGE_SHIFT 21 +#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT) +#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1)) + +#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE) + #define DE_VECTOR 0 #define UD_VECTOR 6 #define NM_VECTOR 7 @@ -48,6 +62,7 @@ #define SS_VECTOR 12 #define GP_VECTOR 13 #define PF_VECTOR 14 +#define MC_VECTOR 18 #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -58,7 +73,8 @@ #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 -#define KVM_NUM_MMU_PAGES 1024 +#define KVM_MMU_HASH_SHIFT 10 +#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 40 @@ -106,6 +122,12 @@ enum { #define KVM_NR_MEM_OBJS 40 +struct kvm_guest_debug { + int enabled; + unsigned long bp[4]; + int singlestep; +}; + /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -140,6 +162,7 @@ union kvm_mmu_page_role { unsigned pad_for_nice_hex_output:6; unsigned metaphysical:1; unsigned access:3; + unsigned invalid:1; }; }; @@ -204,11 +227,6 @@ struct kvm_vcpu_arch { u64 shadow_efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ -#define VCPU_MP_STATE_RUNNABLE 0 -#define VCPU_MP_STATE_UNINITIALIZED 1 -#define VCPU_MP_STATE_INIT_RECEIVED 2 -#define VCPU_MP_STATE_SIPI_RECEIVED 3 -#define VCPU_MP_STATE_HALTED 4 int mp_state; int sipi_vector; u64 ia32_misc_enable_msr; @@ -226,8 +244,9 @@ struct kvm_vcpu_arch { u64 *last_pte_updated; struct { - gfn_t gfn; /* presumed gfn during guest pte update */ - struct page *page; /* page corresponding to that gfn */ + gfn_t gfn; /* presumed gfn during guest pte update */ + pfn_t pfn; /* pfn corresponding to that gfn */ + int largepage; } update_pte; struct i387_fxsave_struct host_fx_image; @@ -261,6 +280,11 @@ struct kvm_vcpu_arch { /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; + + gpa_t time; + struct kvm_vcpu_time_info hv_clock; + unsigned int time_offset; + struct page *time_page; }; struct kvm_mem_alias { @@ -283,10 +307,13 @@ struct kvm_arch{ struct list_head active_mmu_pages; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; + struct kvm_pit *vpit; int round_robin_prev_vcpu; unsigned int tss_addr; struct page *apic_access_page; + + gpa_t wall_clock; }; struct kvm_vm_stat { @@ -298,6 +325,7 @@ struct kvm_vm_stat { u32 mmu_recycled; u32 mmu_cache_miss; u32 remote_tlb_flush; + u32 lpages; }; struct kvm_vcpu_stat { @@ -320,6 +348,7 @@ struct kvm_vcpu_stat { u32 fpu_reload; u32 insn_emulation; u32 insn_emulation_fail; + u32 hypercalls; }; struct descriptor_table { @@ -355,6 +384,7 @@ struct kvm_x86_ops { u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); + int (*get_cpl)(struct kvm_vcpu *vcpu); void (*set_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); @@ -410,6 +440,15 @@ void kvm_mmu_zap_all(struct kvm *kvm); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); + +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes); +int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, + gpa_t addr, unsigned long *ret); + +extern bool tdp_enabled; + enum emulation_result { EMULATE_DONE, /* no further processing */ EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ @@ -429,6 +468,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, unsigned long *rflags); +void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); @@ -448,12 +488,14 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value); -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0); -unsigned long get_cr8(struct kvm_vcpu *vcpu); -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason); + +void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); +void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); +unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); +void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); @@ -491,6 +533,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code); +void kvm_enable_tdp(void); + int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int complete_pio(struct kvm_vcpu *vcpu); @@ -600,6 +644,7 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) #define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4" #define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4" #define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30" +#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08" #define MSR_IA32_TIME_STAMP_COUNTER 0x010 @@ -610,4 +655,30 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) #define RMODE_TSS_SIZE \ (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) +enum { + TASK_SWITCH_CALL = 0, + TASK_SWITCH_IRET = 1, + TASK_SWITCH_JMP = 2, + TASK_SWITCH_GATE = 3, +}; + +#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 5, d1, d2, d3, d4, d5) +#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 4, d1, d2, d3, d4, 0) +#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 3, d1, d2, d3, 0, 0) +#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 2, d1, d2, 0, 0, 0) +#define KVMTRACE_1D(evt, vcpu, d1, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 1, d1, 0, 0, 0, 0) +#define KVMTRACE_0D(evt, vcpu, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 0, 0, 0, 0, 0, 0) + #endif diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h index c6f3fd8d8c5..50984594207 100644 --- a/include/asm-x86/kvm_para.h +++ b/include/asm-x86/kvm_para.h @@ -10,10 +10,65 @@ * paravirtualization, the appropriate feature bit should be checked. */ #define KVM_CPUID_FEATURES 0x40000001 +#define KVM_FEATURE_CLOCKSOURCE 0 +#define KVM_FEATURE_NOP_IO_DELAY 1 +#define KVM_FEATURE_MMU_OP 2 + +#define MSR_KVM_WALL_CLOCK 0x11 +#define MSR_KVM_SYSTEM_TIME 0x12 + +#define KVM_MAX_MMU_OP_BATCH 32 + +/* Operations for KVM_HC_MMU_OP */ +#define KVM_MMU_OP_WRITE_PTE 1 +#define KVM_MMU_OP_FLUSH_TLB 2 +#define KVM_MMU_OP_RELEASE_PT 3 + +/* Payload for KVM_HC_MMU_OP */ +struct kvm_mmu_op_header { + __u32 op; + __u32 pad; +}; + +struct kvm_mmu_op_write_pte { + struct kvm_mmu_op_header header; + __u64 pte_phys; + __u64 pte_val; +}; + +struct kvm_mmu_op_flush_tlb { + struct kvm_mmu_op_header header; +}; + +struct kvm_mmu_op_release_pt { + struct kvm_mmu_op_header header; + __u64 pt_phys; +}; #ifdef __KERNEL__ #include <asm/processor.h> +/* xen binary-compatible interface. See xen headers for details */ +struct kvm_vcpu_time_info { + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; + uint64_t system_time; + uint32_t tsc_to_system_mul; + int8_t tsc_shift; + int8_t pad[3]; +} __attribute__((__packed__)); /* 32 bytes */ + +struct kvm_wall_clock { + uint32_t wc_version; + uint32_t wc_sec; + uint32_t wc_nsec; +} __attribute__((__packed__)); + + +extern void kvmclock_init(void); + + /* This instruction is vmcall. On non-VT architectures, it will generate a * trap that we will then rewrite to the appropriate instruction. */ diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h index 3ff2c5bff93..56d0e1fa025 100644 --- a/include/asm-x86/mach-default/smpboot_hooks.h +++ b/include/asm-x86/mach-default/smpboot_hooks.h @@ -33,7 +33,7 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile long *) phys_to_virt(0x467)) = 0; } -static inline void smpboot_setup_io_apic(void) +static inline void __init smpboot_setup_io_apic(void) { /* * Here we can be sure that there is an IO-APIC in the system. Let's diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 6724a4bc6b7..b381f4a5a0b 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -47,6 +47,7 @@ #ifndef __ASSEMBLY__ extern int page_is_ram(unsigned long pagenr); +extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_pfn_mapped; diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h index 3d419398499..0f13b945e24 100644 --- a/include/asm-x86/paravirt.h +++ b/include/asm-x86/paravirt.h @@ -220,11 +220,13 @@ struct pv_mmu_ops { unsigned long va); /* Hooks for allocating/releasing pagetable pages */ - void (*alloc_pt)(struct mm_struct *mm, u32 pfn); - void (*alloc_pd)(struct mm_struct *mm, u32 pfn); - void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); - void (*release_pt)(u32 pfn); - void (*release_pd)(u32 pfn); + void (*alloc_pte)(struct mm_struct *mm, u32 pfn); + void (*alloc_pmd)(struct mm_struct *mm, u32 pfn); + void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); + void (*alloc_pud)(struct mm_struct *mm, u32 pfn); + void (*release_pte)(u32 pfn); + void (*release_pmd)(u32 pfn); + void (*release_pud)(u32 pfn); /* Pagetable manipulation functions */ void (*set_pte)(pte_t *ptep, pte_t pteval); @@ -910,28 +912,37 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va); } -static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn) +static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_pt, mm, pfn); + PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn); } -static inline void paravirt_release_pt(unsigned pfn) +static inline void paravirt_release_pte(unsigned pfn) { - PVOP_VCALL1(pv_mmu_ops.release_pt, pfn); + PVOP_VCALL1(pv_mmu_ops.release_pte, pfn); } -static inline void paravirt_alloc_pd(struct mm_struct *mm, unsigned pfn) +static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_pd, mm, pfn); + PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn); } -static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn, - unsigned start, unsigned count) +static inline void paravirt_alloc_pmd_clone(unsigned pfn, unsigned clonepfn, + unsigned start, unsigned count) { - PVOP_VCALL4(pv_mmu_ops.alloc_pd_clone, pfn, clonepfn, start, count); + PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count); } -static inline void paravirt_release_pd(unsigned pfn) +static inline void paravirt_release_pmd(unsigned pfn) { - PVOP_VCALL1(pv_mmu_ops.release_pd, pfn); + PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn); +} + +static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned pfn) +{ + PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn); +} +static inline void paravirt_release_pud(unsigned pfn) +{ + PVOP_VCALL1(pv_mmu_ops.release_pud, pfn); } #ifdef CONFIG_HIGHPTE diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h index 5886eed0588..91e4641f3f3 100644 --- a/include/asm-x86/pgalloc.h +++ b/include/asm-x86/pgalloc.h @@ -1,5 +1,110 @@ -#ifdef CONFIG_X86_32 -# include "pgalloc_32.h" +#ifndef _ASM_X86_PGALLOC_H +#define _ASM_X86_PGALLOC_H + +#include <linux/threads.h> +#include <linux/mm.h> /* for struct page */ +#include <linux/pagemap.h> + +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> #else -# include "pgalloc_64.h" +static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, + unsigned long start, unsigned long count) {} +static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_release_pte(unsigned long pfn) {} +static inline void paravirt_release_pmd(unsigned long pfn) {} +static inline void paravirt_release_pud(unsigned long pfn) {} #endif + +/* + * Allocate and free page tables. + */ +extern pgd_t *pgd_alloc(struct mm_struct *); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); + +extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); +extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); + +/* Should really implement gc for free page table pages. This could be + done with a reference count in struct page. */ + +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); + free_page((unsigned long)pte); +} + +static inline void pte_free(struct mm_struct *mm, struct page *pte) +{ + __free_page(pte); +} + +extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte); + +static inline void pmd_populate_kernel(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); + set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + struct page *pte) +{ + unsigned long pfn = page_to_pfn(pte); + + paravirt_alloc_pte(mm, pfn); + set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); +} + +#define pmd_pgtable(pmd) pmd_page(pmd) + +#if PAGETABLE_LEVELS > 2 +static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); + free_page((unsigned long)pmd); +} + +extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); + +#ifdef CONFIG_X86_PAE +extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); +#else /* !CONFIG_X86_PAE */ +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); +} +#endif /* CONFIG_X86_PAE */ + +#if PAGETABLE_LEVELS > 3 +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +{ + paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); + set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))); +} + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); + free_page((unsigned long)pud); +} + +extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); +#endif /* PAGETABLE_LEVELS > 3 */ +#endif /* PAGETABLE_LEVELS > 2 */ + +#endif /* _ASM_X86_PGALLOC_H */ diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h deleted file mode 100644 index 6bea6e5b5ee..00000000000 --- a/include/asm-x86/pgalloc_32.h +++ /dev/null @@ -1,95 +0,0 @@ -#ifndef _I386_PGALLOC_H -#define _I386_PGALLOC_H - -#include <linux/threads.h> -#include <linux/mm.h> /* for struct page */ -#include <linux/pagemap.h> -#include <asm/tlb.h> -#include <asm-generic/tlb.h> - -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#else -#define paravirt_alloc_pt(mm, pfn) do { } while (0) -#define paravirt_alloc_pd(mm, pfn) do { } while (0) -#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0) -#define paravirt_release_pt(pfn) do { } while (0) -#define paravirt_release_pd(pfn) do { } while (0) -#endif - -static inline void pmd_populate_kernel(struct mm_struct *mm, - pmd_t *pmd, pte_t *pte) -{ - paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT); - set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); -} - -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) -{ - unsigned long pfn = page_to_pfn(pte); - - paravirt_alloc_pt(mm, pfn); - set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); -} -#define pmd_pgtable(pmd) pmd_page(pmd) - -/* - * Allocate and free page tables. - */ -extern pgd_t *pgd_alloc(struct mm_struct *); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); - -extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); -extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - - -extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte); - -#ifdef CONFIG_X86_PAE -/* - * In the PAE case we free the pmds as part of the pgd. - */ -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); -} - -extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); - -static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) -{ - paravirt_alloc_pd(mm, __pa(pmd) >> PAGE_SHIFT); - - /* Note: almost everything apart from _PAGE_PRESENT is - reserved at the pmd (PDPT) level. */ - set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); - - /* - * According to Intel App note "TLBs, Paging-Structure Caches, - * and Their Invalidation", April 2007, document 317080-001, - * section 8.1: in PAE mode we explicitly have to flush the - * TLB via cr3 if the top-level pgd is changed... - */ - if (mm == current->active_mm) - write_cr3(read_cr3()); -} -#endif /* CONFIG_X86_PAE */ - -#endif /* _I386_PGALLOC_H */ diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h deleted file mode 100644 index 8d6722320dc..00000000000 --- a/include/asm-x86/pgalloc_64.h +++ /dev/null @@ -1,133 +0,0 @@ -#ifndef _X86_64_PGALLOC_H -#define _X86_64_PGALLOC_H - -#include <asm/pda.h> -#include <linux/threads.h> -#include <linux/mm.h> - -#define pmd_populate_kernel(mm, pmd, pte) \ - set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte))) -#define pud_populate(mm, pud, pmd) \ - set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))) -#define pgd_populate(mm, pgd, pud) \ - set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))) - -#define pmd_pgtable(pmd) pmd_page(pmd) - -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) -{ - set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT))); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); -} - -static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr) -{ - return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); -} - -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); -} - -static inline void pud_free(struct mm_struct *mm, pud_t *pud) -{ - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); -} - -static inline void pgd_list_add(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - unsigned long flags; - - spin_lock_irqsave(&pgd_lock, flags); - list_add(&page->lru, &pgd_list); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -static inline void pgd_list_del(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - unsigned long flags; - - spin_lock_irqsave(&pgd_lock, flags); - list_del(&page->lru); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -static inline pgd_t *pgd_alloc(struct mm_struct *mm) -{ - unsigned boundary; - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); - if (!pgd) - return NULL; - pgd_list_add(pgd); - /* - * Copy kernel pointers in from init. - * Could keep a freelist or slab cache of those because the kernel - * part never changes. - */ - boundary = pgd_index(__PAGE_OFFSET); - memset(pgd, 0, boundary * sizeof(pgd_t)); - memcpy(pgd + boundary, - init_level4_pgt + boundary, - (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); - return pgd; -} - -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); - pgd_list_del(pgd); - free_page((unsigned long)pgd); -} - -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) -{ - struct page *page; - void *p; - - p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); - if (!p) - return NULL; - page = virt_to_page(p); - pgtable_page_ctor(page); - return page; -} - -/* Should really implement gc for free page table pages. This could be - done with a reference count in struct page. */ - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - -#define __pte_free_tlb(tlb,pte) \ -do { \ - pgtable_page_dtor((pte)); \ - tlb_remove_page((tlb), (pte)); \ -} while (0) - -#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) -#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) - -#endif /* _X86_64_PGALLOC_H */ diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index f1d9f4a03f6..801b31f7145 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H -#define USER_PTRS_PER_PGD ((TASK_SIZE-1)/PGDIR_SIZE+1) #define FIRST_USER_ADDRESS 0 #define _PAGE_BIT_PRESENT 0 /* is present */ @@ -196,6 +195,11 @@ static inline int pte_exec(pte_t pte) return !(pte_val(pte) & _PAGE_NX); } +static inline int pte_special(pte_t pte) +{ + return 0; +} + static inline int pmd_large(pmd_t pte) { return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) == @@ -257,6 +261,11 @@ static inline pte_t pte_clrglobal(pte_t pte) return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL); } +static inline pte_t pte_mkspecial(pte_t pte) +{ + return pte; +} + extern pteval_t __supported_pte_mask; static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) @@ -289,6 +298,15 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) +#ifndef __ASSEMBLY__ +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); +#endif + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT */ @@ -330,6 +348,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) # include "pgtable_64.h" #endif +#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) +#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) + #ifndef __ASSEMBLY__ enum { @@ -389,37 +410,17 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, * bit at the same time. */ #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -#define ptep_set_access_flags(vma, address, ptep, entry, dirty) \ -({ \ - int __changed = !pte_same(*(ptep), entry); \ - if (__changed && dirty) { \ - *ptep = entry; \ - pte_update_defer((vma)->vm_mm, (address), (ptep)); \ - flush_tlb_page(vma, address); \ - } \ - __changed; \ -}) +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define ptep_test_and_clear_young(vma, addr, ptep) ({ \ - int __ret = 0; \ - if (pte_young(*(ptep))) \ - __ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, \ - &(ptep)->pte); \ - if (__ret) \ - pte_update((vma)->vm_mm, addr, ptep); \ - __ret; \ -}) +extern int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -#define ptep_clear_flush_young(vma, address, ptep) \ -({ \ - int __young; \ - __young = ptep_test_and_clear_young((vma), (address), (ptep)); \ - if (__young) \ - flush_tlb_page(vma, address); \ - __young; \ -}) +extern int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, @@ -456,6 +457,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep); } +/* + * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); + * + * dst - pointer to pgd range anwhere on a pgd page + * src - "" + * count - the number of pgds to copy. + * + * dst and src can be on the same page, but the range must not overlap, + * and must not cross a page boundary. + */ +static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) +{ + memcpy(dst, src, count * sizeof(pgd_t)); +} + + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h index c4a64367445..577ab79c4c2 100644 --- a/include/asm-x86/pgtable_32.h +++ b/include/asm-x86/pgtable_32.h @@ -48,9 +48,6 @@ void paging_init(void); #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) -#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT) -#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS) - /* Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the * physical memory until the kernel virtual memory starts. That means that @@ -109,21 +106,6 @@ extern int pmd_bad(pmd_t pmd); #endif /* - * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); - * - * dst - pointer to pgd range anwhere on a pgd page - * src - "" - * count - the number of pgds to copy. - * - * dst and src can be on the same page, but the range must not overlap, - * and must not cross a page boundary. - */ -static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) -{ - memcpy(dst, src, count * sizeof(pgd_t)); -} - -/* * Macro to mark a page protection value as "uncacheable". * On processors which do not support it, this is a no-op. */ @@ -216,16 +198,16 @@ do { \ */ #define update_mmu_cache(vma, address, pte) do { } while (0) -void native_pagetable_setup_start(pgd_t *base); -void native_pagetable_setup_done(pgd_t *base); +extern void native_pagetable_setup_start(pgd_t *base); +extern void native_pagetable_setup_done(pgd_t *base); #ifndef CONFIG_PARAVIRT -static inline void paravirt_pagetable_setup_start(pgd_t *base) +static inline void __init paravirt_pagetable_setup_start(pgd_t *base) { native_pagetable_setup_start(base); } -static inline void paravirt_pagetable_setup_done(pgd_t *base) +static inline void __init paravirt_pagetable_setup_done(pgd_t *base) { native_pagetable_setup_done(base); } diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h index 9fd87d0b647..a3bbf8766c1 100644 --- a/include/asm-x86/pgtable_64.h +++ b/include/asm-x86/pgtable_64.h @@ -24,7 +24,7 @@ extern void paging_init(void); #endif /* !__ASSEMBLY__ */ -#define SHARED_KERNEL_PMD 1 +#define SHARED_KERNEL_PMD 0 /* * PGDIR_SHIFT determines what a top-level page table entry can map diff --git a/include/asm-x86/posix_types.h b/include/asm-x86/posix_types.h index fe312a5ba20..bb7133dc155 100644 --- a/include/asm-x86/posix_types.h +++ b/include/asm-x86/posix_types.h @@ -1,5 +1,11 @@ #ifdef __KERNEL__ -# if defined(CONFIG_X86_32) || defined(__i386__) +# ifdef CONFIG_X86_32 +# include "posix_types_32.h" +# else +# include "posix_types_64.h" +# endif +#else +# ifdef __i386__ # include "posix_types_32.h" # else # include "posix_types_64.h" diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h index e6bf92ddeb2..2e7974ec77e 100644 --- a/include/asm-x86/processor.h +++ b/include/asm-x86/processor.h @@ -118,7 +118,6 @@ struct cpuinfo_x86 { #define X86_VENDOR_CYRIX 1 #define X86_VENDOR_AMD 2 #define X86_VENDOR_UMC 3 -#define X86_VENDOR_NEXGEN 4 #define X86_VENDOR_CENTAUR 5 #define X86_VENDOR_TRANSMETA 7 #define X86_VENDOR_NSC 8 @@ -723,6 +722,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { + trace_hardirqs_on(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h index 24ec061566c..9f922b0b95d 100644 --- a/include/asm-x86/ptrace.h +++ b/include/asm-x86/ptrace.h @@ -231,6 +231,8 @@ extern int do_get_thread_area(struct task_struct *p, int idx, extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); +#define __ARCH_WANT_COMPAT_SYS_PTRACE + #endif /* __KERNEL__ */ #endif /* !__ASSEMBLY__ */ diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h index 6b5233b4f84..e63741f1939 100644 --- a/include/asm-x86/reboot.h +++ b/include/asm-x86/reboot.h @@ -15,5 +15,7 @@ struct machine_ops { extern struct machine_ops machine_ops; void machine_real_restart(unsigned char *code, int length); +void native_machine_crash_shutdown(struct pt_regs *regs); +void native_machine_shutdown(void); #endif /* _ASM_REBOOT_H */ diff --git a/include/asm-x86/rio.h b/include/asm-x86/rio.h index 3451c576e6a..c9448bd8968 100644 --- a/include/asm-x86/rio.h +++ b/include/asm-x86/rio.h @@ -60,15 +60,4 @@ enum { ALT_CALGARY = 5, /* Second Planar Calgary */ }; -/* - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E. - */ -static inline unsigned long get_bios_ebda(void) -{ - unsigned long address = *(unsigned short *)phys_to_virt(0x40EUL); - address <<= 4; - return address; -} - #endif /* __ASM_RIO_H */ diff --git a/include/asm-x86/unistd.h b/include/asm-x86/unistd.h index effc7ad8e12..2a58ed3e51d 100644 --- a/include/asm-x86/unistd.h +++ b/include/asm-x86/unistd.h @@ -1,5 +1,11 @@ #ifdef __KERNEL__ -# if defined(CONFIG_X86_32) || defined(__i386__) +# ifdef CONFIG_X86_32 +# include "unistd_32.h" +# else +# include "unistd_64.h" +# endif +#else +# ifdef __i386__ # include "unistd_32.h" # else # include "unistd_64.h" diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h new file mode 100644 index 00000000000..596312a7bfc --- /dev/null +++ b/include/asm-x86/xen/events.h @@ -0,0 +1,22 @@ +#ifndef __XEN_EVENTS_H +#define __XEN_EVENTS_H + +enum ipi_vector { + XEN_RESCHEDULE_VECTOR, + XEN_CALL_FUNCTION_VECTOR, + + XEN_NR_IPIS, +}; + +static inline int xen_irqs_disabled(struct pt_regs *regs) +{ + return raw_irqs_disabled_flags(regs->flags); +} + +static inline void xen_do_IRQ(int irq, struct pt_regs *regs) +{ + regs->orig_ax = ~irq; + do_IRQ(regs); +} + +#endif /* __XEN_EVENTS_H */ diff --git a/include/asm-x86/xen/grant_table.h b/include/asm-x86/xen/grant_table.h new file mode 100644 index 00000000000..2444d4593a3 --- /dev/null +++ b/include/asm-x86/xen/grant_table.h @@ -0,0 +1,7 @@ +#ifndef __XEN_GRANT_TABLE_H +#define __XEN_GRANT_TABLE_H + +#define xen_alloc_vm_area(size) alloc_vm_area(size) +#define xen_free_vm_area(area) free_vm_area(area) + +#endif /* __XEN_GRANT_TABLE_H */ diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h index bc0ee7d961c..c2ccd997ed3 100644 --- a/include/asm-x86/xen/hypercall.h +++ b/include/asm-x86/xen/hypercall.h @@ -164,6 +164,12 @@ HYPERVISOR_set_callbacks(unsigned long event_selector, } static inline int +HYPERVISOR_callback_op(int cmd, void *arg) +{ + return _hypercall2(int, callback_op, cmd, arg); +} + +static inline int HYPERVISOR_fpu_taskswitch(int set) { return _hypercall1(int, fpu_taskswitch, set); diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h index 165c3968e13..6227000a1e8 100644 --- a/include/asm-x86/xen/interface.h +++ b/include/asm-x86/xen/interface.h @@ -22,6 +22,30 @@ #define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) #define GUEST_HANDLE(name) __guest_handle_ ## name +#ifdef __XEN__ +#if defined(__i386__) +#define set_xen_guest_handle(hnd, val) \ + do { \ + if (sizeof(hnd) == 8) \ + *(uint64_t *)&(hnd) = 0; \ + (hnd).p = val; \ + } while (0) +#elif defined(__x86_64__) +#define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0) +#endif +#else +#if defined(__i386__) +#define set_xen_guest_handle(hnd, val) \ + do { \ + if (sizeof(hnd) == 8) \ + *(uint64_t *)&(hnd) = 0; \ + (hnd) = val; \ + } while (0) +#elif defined(__x86_64__) +#define set_xen_guest_handle(hnd, val) do { (hnd) = val; } while (0) +#endif +#endif + #ifndef __ASSEMBLY__ /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); @@ -171,6 +195,10 @@ struct arch_vcpu_info { unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */ }; +struct xen_callback { + unsigned long cs; + unsigned long eip; +}; #endif /* !__ASSEMBLY__ */ /* diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h new file mode 100644 index 00000000000..01799305f02 --- /dev/null +++ b/include/asm-x86/xen/page.h @@ -0,0 +1,168 @@ +#ifndef __XEN_PAGE_H +#define __XEN_PAGE_H + +#include <linux/pfn.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> + +#include <xen/features.h> + +/* Xen machine address */ +typedef struct xmaddr { + phys_addr_t maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + phys_addr_t paddr; +} xpaddr_t; + +#define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) +#define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) + +/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ +#define INVALID_P2M_ENTRY (~0UL) +#define FOREIGN_FRAME_BIT (1UL<<31) +#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) + +extern unsigned long *phys_to_machine_mapping; + +static inline unsigned long pfn_to_mfn(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return pfn; + + return phys_to_machine_mapping[(unsigned int)(pfn)] & + ~FOREIGN_FRAME_BIT; +} + +static inline int phys_to_machine_mapping_valid(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 1; + + return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY); +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + +#if 0 + if (unlikely((mfn >> machine_to_phys_order) != 0)) + return max_mapnr; +#endif + + pfn = 0; + /* + * The array access can fail (e.g., device space beyond end of RAM). + * In such cases it doesn't matter what we return (we return garbage), + * but we must handle the fault without crashing! + */ + __get_user(pfn, &machine_to_phys_mapping[mfn]); + + return pfn; +} + +static inline xmaddr_t phys_to_machine(xpaddr_t phys) +{ + unsigned offset = phys.paddr & ~PAGE_MASK; + return XMADDR(PFN_PHYS((u64)pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset); +} + +static inline xpaddr_t machine_to_phys(xmaddr_t machine) +{ + unsigned offset = machine.maddr & ~PAGE_MASK; + return XPADDR(PFN_PHYS((u64)mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset); +} + +/* + * We detect special mappings in one of two ways: + * 1. If the MFN is an I/O page then Xen will set the m2p entry + * to be outside our maximum possible pseudophys range. + * 2. If the MFN belongs to a different domain then we will certainly + * not have MFN in our p2m table. Conversely, if the page is ours, + * then we'll have p2m(m2p(MFN))==MFN. + * If we detect a special mapping then it doesn't have a 'struct page'. + * We force !pfn_valid() by returning an out-of-range pointer. + * + * NB. These checks require that, for any MFN that is not in our reservation, + * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if + * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. + * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. + * + * NB2. When deliberately mapping foreign pages into the p2m table, you *must* + * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we + * require. In all the cases we care about, the FOREIGN_FRAME bit is + * masked (e.g., pfn_to_mfn()) so behaviour there is correct. + */ +static inline unsigned long mfn_to_local_pfn(unsigned long mfn) +{ + extern unsigned long max_mapnr; + unsigned long pfn = mfn_to_pfn(mfn); + if ((pfn < max_mapnr) + && !xen_feature(XENFEAT_auto_translated_physmap) + && (phys_to_machine_mapping[pfn] != mfn)) + return max_mapnr; /* force !pfn_valid() */ + return pfn; +} + +static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + phys_to_machine_mapping[pfn] = mfn; +} + +/* VIRT <-> MACHINE conversion */ +#define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) +#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) + +static inline unsigned long pte_mfn(pte_t pte) +{ + return (pte.pte & ~_PAGE_NX) >> PAGE_SHIFT; +} + +static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) | + (pgprot_val(pgprot) & __supported_pte_mask); + + return pte; +} + +static inline pteval_t pte_val_ma(pte_t pte) +{ + return pte.pte; +} + +static inline pte_t __pte_ma(pteval_t x) +{ + return (pte_t) { .pte = x }; +} + +#ifdef CONFIG_X86_PAE +#define pmd_val_ma(v) ((v).pmd) +#define pud_val_ma(v) ((v).pgd.pgd) +#define __pmd_ma(x) ((pmd_t) { (x) } ) +#else /* !X86_PAE */ +#define pmd_val_ma(v) ((v).pud.pgd.pgd) +#endif /* CONFIG_X86_PAE */ + +#define pgd_val_ma(x) ((x).pgd) + + +xmaddr_t arbitrary_virt_to_machine(unsigned long address); +void make_lowmem_page_readonly(void *vaddr); +void make_lowmem_page_readwrite(void *vaddr); + +#endif /* __XEN_PAGE_H */ |