diff options
Diffstat (limited to 'include')
242 files changed, 5952 insertions, 1184 deletions
diff --git a/include/asm-alpha/a.out.h b/include/asm-alpha/a.out.h index d97daf42753..e43cf61649a 100644 --- a/include/asm-alpha/a.out.h +++ b/include/asm-alpha/a.out.h @@ -101,6 +101,8 @@ struct exec #define STACK_TOP \ (current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL) +#define STACK_TOP_MAX 0x00120000000UL + #endif #endif /* __A_OUT_GNU_H__ */ diff --git a/include/asm-alpha/fb.h b/include/asm-alpha/fb.h new file mode 100644 index 00000000000..fa9bbb96b2b --- /dev/null +++ b/include/asm-alpha/fb.h @@ -0,0 +1,13 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/device.h> + +/* Caching is off in the I/O space quadrant by design. */ +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-alpha/page.h b/include/asm-alpha/page.h index d2bed3cb33f..bae7f05716d 100644 --- a/include/asm-alpha/page.h +++ b/include/asm-alpha/page.h @@ -17,7 +17,8 @@ extern void clear_page(void *page); #define clear_user_page(page, vaddr, pg) clear_page(page) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vmaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE extern void copy_page(void * _to, void * _from); diff --git a/include/asm-alpha/termios.h b/include/asm-alpha/termios.h index 39e492c3bfa..fa13716a11c 100644 --- a/include/asm-alpha/termios.h +++ b/include/asm-alpha/termios.h @@ -81,7 +81,7 @@ struct termio { #define user_termio_to_kernel_termios(a_termios, u_termio) \ ({ \ - struct termios *k_termios = (a_termios); \ + struct ktermios *k_termios = (a_termios); \ struct termio k_termio; \ int canon, ret; \ \ @@ -113,7 +113,7 @@ struct termio { */ #define kernel_termios_to_user_termio(u_termio, a_termios) \ ({ \ - struct termios *k_termios = (a_termios); \ + struct ktermios *k_termios = (a_termios); \ struct termio k_termio; \ int canon; \ \ diff --git a/include/asm-arm/a.out.h b/include/asm-arm/a.out.h index 3e5fe64c439..d7165e86df2 100644 --- a/include/asm-arm/a.out.h +++ b/include/asm-arm/a.out.h @@ -30,6 +30,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP ((current->personality == PER_LINUX_32BIT) ? \ TASK_SIZE : TASK_SIZE_26) +#define STACK_TOP_MAX TASK_SIZE #endif #ifndef LIBRARY_START_TEXT diff --git a/include/asm-arm/fb.h b/include/asm-arm/fb.h new file mode 100644 index 00000000000..d92e99cd8c8 --- /dev/null +++ b/include/asm-arm/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-arm/pgtable.h b/include/asm-arm/pgtable.h index cb4c2c9d000..d2e8171d1d4 100644 --- a/include/asm-arm/pgtable.h +++ b/include/asm-arm/pgtable.h @@ -83,14 +83,14 @@ * means that a write to a clean page will cause a permission fault, and * the Linux MM layer will mark the page dirty via handle_pte_fault(). * For the hardware to notice the permission change, the TLB entry must - * be flushed, and ptep_establish() does that for us. + * be flushed, and ptep_set_access_flags() does that for us. * * The "accessed" or "young" bit is emulated by a similar method; we only * allow accesses to the page if the "young" bit is set. Accesses to the * page will cause a fault, and handle_pte_fault() will set the young bit * for us as long as the page is marked present in the corresponding Linux - * PTE entry. Again, ptep_establish() will ensure that the TLB is up to - * date. + * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is + * up to date. * * However, when the "young" bit is cleared, we deny access to the page * by clearing the hardware PTE. Currently Linux does not flush the TLB diff --git a/include/asm-arm26/a.out.h b/include/asm-arm26/a.out.h index 9b2702c42c8..7167f54ae3f 100644 --- a/include/asm-arm26/a.out.h +++ b/include/asm-arm26/a.out.h @@ -29,6 +29,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif #ifndef LIBRARY_START_TEXT diff --git a/include/asm-arm26/fb.h b/include/asm-arm26/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-arm26/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-avr32/a.out.h b/include/asm-avr32/a.out.h index 50bf6e31a14..9f398ab28ed 100644 --- a/include/asm-avr32/a.out.h +++ b/include/asm-avr32/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-avr32/arch-at32ap/board.h b/include/asm-avr32/arch-at32ap/board.h index 97448043884..0215965dc58 100644 --- a/include/asm-avr32/arch-at32ap/board.h +++ b/include/asm-avr32/arch-at32ap/board.h @@ -36,4 +36,18 @@ struct platform_device * at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data, unsigned long fbmem_start, unsigned long fbmem_len); +/* depending on what's hooked up, not all SSC pins will be used */ +#define ATMEL_SSC_TK 0x01 +#define ATMEL_SSC_TF 0x02 +#define ATMEL_SSC_TD 0x04 +#define ATMEL_SSC_TX (ATMEL_SSC_TK | ATMEL_SSC_TF | ATMEL_SSC_TD) + +#define ATMEL_SSC_RK 0x10 +#define ATMEL_SSC_RF 0x20 +#define ATMEL_SSC_RD 0x40 +#define ATMEL_SSC_RX (ATMEL_SSC_RK | ATMEL_SSC_RF | ATMEL_SSC_RD) + +struct platform_device * +at32_add_device_ssc(unsigned int id, unsigned int flags); + #endif /* __ASM_ARCH_BOARD_H */ diff --git a/include/asm-avr32/arch-at32ap/sm.h b/include/asm-avr32/arch-at32ap/sm.h deleted file mode 100644 index 265a9ead20b..00000000000 --- a/include/asm-avr32/arch-at32ap/sm.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * AT32 System Manager interface. - * - * Copyright (C) 2006 Atmel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef __ASM_AVR32_AT32_SM_H__ -#define __ASM_AVR32_AT32_SM_H__ - -struct irq_chip; -struct platform_device; - -struct at32_sm { - spinlock_t lock; - void __iomem *regs; - struct irq_chip *eim_chip; - unsigned int eim_first_irq; - struct platform_device *pdev; -}; - -extern struct platform_device at32_sm_device; -extern struct at32_sm system_manager; - -#endif /* __ASM_AVR32_AT32_SM_H__ */ diff --git a/include/asm-avr32/atomic.h b/include/asm-avr32/atomic.h index b9c2548a52f..7ef3862a73d 100644 --- a/include/asm-avr32/atomic.h +++ b/include/asm-avr32/atomic.h @@ -101,7 +101,7 @@ static inline int atomic_sub_unless(atomic_t *v, int a, int u) " mov %1, 1\n" "1:" : "=&r"(tmp), "=&r"(result), "=o"(v->counter) - : "m"(v->counter), "rKs21"(a), "rKs21"(u) + : "m"(v->counter), "rKs21"(a), "rKs21"(u), "1"(result) : "cc", "memory"); return result; @@ -137,7 +137,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) " mov %1, 1\n" "1:" : "=&r"(tmp), "=&r"(result), "=o"(v->counter) - : "m"(v->counter), "r"(a), "ir"(u) + : "m"(v->counter), "r"(a), "ir"(u), "1"(result) : "cc", "memory"); } diff --git a/include/asm-avr32/fb.h b/include/asm-avr32/fb.h new file mode 100644 index 00000000000..41baf84ad40 --- /dev/null +++ b/include/asm-avr32/fb.h @@ -0,0 +1,21 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = __pgprot((pgprot_val(vma->vm_page_prot) + & ~_PAGE_CACHABLE) + | (_PAGE_BUFFER | _PAGE_DIRTY)); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-avr32/unaligned.h b/include/asm-avr32/unaligned.h index 3042723fcbf..36f5fd43054 100644 --- a/include/asm-avr32/unaligned.h +++ b/include/asm-avr32/unaligned.h @@ -7,19 +7,10 @@ * words, but halfwords must be halfword-aligned, and doublewords must * be word-aligned. * - * TODO: Make all this CPU-specific and optimize. + * However, swapped word loads must be word-aligned so we can't + * optimize word loads in general. */ -#include <linux/string.h> - -/* Use memmove here, so gcc does not insert a __builtin_memcpy. */ - -#define get_unaligned(ptr) \ - ({ __typeof__(*(ptr)) __tmp; memmove(&__tmp, (ptr), sizeof(*(ptr))); __tmp; }) - -#define put_unaligned(val, ptr) \ - ({ __typeof__(*(ptr)) __tmp = (val); \ - memmove((ptr), &__tmp, sizeof(*(ptr))); \ - (void)0; }) +#include <asm-generic/unaligned.h> #endif /* __ASM_AVR32_UNALIGNED_H */ diff --git a/include/asm-blackfin/fb.h b/include/asm-blackfin/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-blackfin/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-cris/a.out.h b/include/asm-cris/a.out.h index 770734ce54a..919b34a084f 100644 --- a/include/asm-cris/a.out.h +++ b/include/asm-cris/a.out.h @@ -8,6 +8,7 @@ /* grabbed from the intel stuff */ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP struct exec diff --git a/include/asm-cris/fb.h b/include/asm-cris/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-cris/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-cris/page.h b/include/asm-cris/page.h index 9f13c32552b..0648e3153f8 100644 --- a/include/asm-cris/page.h +++ b/include/asm-cris/page.h @@ -20,7 +20,8 @@ #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-frv/fb.h b/include/asm-frv/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-frv/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-frv/mem-layout.h b/include/asm-frv/mem-layout.h index a025dd4514e..aaf2a773d9d 100644 --- a/include/asm-frv/mem-layout.h +++ b/include/asm-frv/mem-layout.h @@ -60,6 +60,7 @@ */ #define BRK_BASE __UL(2 * 1024 * 1024 + PAGE_SIZE) #define STACK_TOP __UL(2 * 1024 * 1024) +#define STACK_TOP_MAX STACK_TOP /* userspace process size */ #ifdef CONFIG_MMU diff --git a/include/asm-frv/pgtable.h b/include/asm-frv/pgtable.h index adde6998525..147e995bec2 100644 --- a/include/asm-frv/pgtable.h +++ b/include/asm-frv/pgtable.h @@ -388,13 +388,6 @@ static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte |= _PAGE_DIRTY; return pt static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte |= _PAGE_ACCESSED; return pte; } static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte &= ~_PAGE_WP; return pte; } -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - int i = test_and_clear_bit(_PAGE_BIT_DIRTY, ptep); - asm volatile("dcf %M0" :: "U"(*ptep)); - return i; -} - static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { int i = test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep); @@ -504,7 +497,6 @@ static inline int pte_file(pte_t pte) remap_pfn_range(vma, vaddr, pfn, size, prot) #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 7f30cce5285..344e3091af2 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -28,7 +28,7 @@ struct bug_entry { #endif #ifndef HAVE_ARCH_BUG_ON -#define BUG_ON(condition) do { if (unlikely((condition)!=0)) BUG(); } while(0) +#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while(0) #endif #ifndef HAVE_ARCH_WARN_ON diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index d984a904143..d85172e9ed4 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -14,6 +14,11 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; #define DEFINE_PER_CPU(type, name) \ __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp + /* var is in discarded region: offset to particular copy we want */ #define per_cpu(var, cpu) (*({ \ extern int simple_identifier_##var(void); \ @@ -34,6 +39,9 @@ do { \ #define DEFINE_PER_CPU(type, name) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) + #define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var)) #define __get_cpu_var(var) per_cpu__##var #define __raw_get_cpu_var(var) per_cpu__##var diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 7d7bcf990e9..f605e8d0eed 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -3,25 +3,6 @@ #ifndef __ASSEMBLY__ -#ifndef __HAVE_ARCH_PTEP_ESTABLISH -/* - * Establish a new mapping: - * - flush the old one - * - update the page tables - * - inform the TLB about the new one - * - * We hold the mm semaphore for reading, and the pte lock. - * - * Note: the old pte is known to not be writable, so we don't need to - * worry about dirty bits etc getting lost. - */ -#define ptep_establish(__vma, __address, __ptep, __entry) \ -do { \ - set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \ - flush_tlb_page(__vma, __address); \ -} while (0) -#endif - #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Largely same as above, but only sets the access flags (dirty, @@ -68,31 +49,6 @@ do { \ }) #endif -#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define ptep_test_and_clear_dirty(__vma, __address, __ptep) \ -({ \ - pte_t __pte = *__ptep; \ - int r = 1; \ - if (!pte_dirty(__pte)) \ - r = 0; \ - else \ - set_pte_at((__vma)->vm_mm, (__address), (__ptep), \ - pte_mkclean(__pte)); \ - r; \ -}) -#endif - -#ifndef __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH -#define ptep_clear_flush_dirty(__vma, __address, __ptep) \ -({ \ - int __dirty; \ - __dirty = ptep_test_and_clear_dirty(__vma, __address, __ptep); \ - if (__dirty) \ - flush_tlb_page(__vma, __address); \ - __dirty; \ -}) -#endif - #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR #define ptep_get_and_clear(__mm, __address, __ptep) \ ({ \ diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 09ec447fe2a..16a466e5068 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -18,7 +18,8 @@ #define get_unaligned(ptr) \ __get_unaligned((ptr), sizeof(*(ptr))) #define put_unaligned(x,ptr) \ - __put_unaligned((__u64)(x), (ptr), sizeof(*(ptr))) + ((void)sizeof(*(ptr)=(x)),\ + __put_unaligned((__force __u64)(x), (ptr), sizeof(*(ptr)))) /* * This function doesn't actually exist. The idea is that when @@ -95,21 +96,21 @@ static inline void __ustw(__u16 val, __u16 *addr) default: \ bad_unaligned_access_length(); \ }; \ - (__typeof__(*(ptr)))val; \ + (__force __typeof__(*(ptr)))val; \ }) #define __put_unaligned(val, ptr, size) \ -do { \ +({ \ void *__gu_p = ptr; \ switch (size) { \ case 1: \ - *(__u8 *)__gu_p = val; \ + *(__u8 *)__gu_p = (__force __u8)val; \ break; \ case 2: \ - __ustw(val, __gu_p); \ + __ustw((__force __u16)val, __gu_p); \ break; \ case 4: \ - __ustl(val, __gu_p); \ + __ustl((__force __u32)val, __gu_p); \ break; \ case 8: \ __ustq(val, __gu_p); \ @@ -117,6 +118,7 @@ do { \ default: \ bad_unaligned_access_length(); \ }; \ -} while(0) + (void)0; \ +}) #endif /* _ASM_GENERIC_UNALIGNED_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 84155eb67f1..0240e0506a0 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -224,7 +224,11 @@ } #define NOTES \ - .notes : { *(.note.*) } :note + .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ + VMLINUX_SYMBOL(__start_notes) = .; \ + *(.note.*) \ + VMLINUX_SYMBOL(__stop_notes) = .; \ + } #define INITCALLS \ *(.initcall0.init) \ @@ -245,3 +249,11 @@ *(.initcall7.init) \ *(.initcall7s.init) +#define PERCPU(align) \ + . = ALIGN(align); \ + __per_cpu_start = .; \ + .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \ + *(.data.percpu) \ + *(.data.percpu.shared_aligned) \ + } \ + __per_cpu_end = .; diff --git a/include/asm-h8300/a.out.h b/include/asm-h8300/a.out.h index 3c70939f9f0..aa5d2277823 100644 --- a/include/asm-h8300/a.out.h +++ b/include/asm-h8300/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-h8300/fb.h b/include/asm-h8300/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-h8300/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-h8300/page.h b/include/asm-h8300/page.h index 3b4f2903f91..c8cc81a3aca 100644 --- a/include/asm-h8300/page.h +++ b/include/asm-h8300/page.h @@ -22,7 +22,8 @@ #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-i386/a.out.h b/include/asm-i386/a.out.h index ab17bb8e546..851a60f8258 100644 --- a/include/asm-i386/a.out.h +++ b/include/asm-i386/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-i386/fb.h b/include/asm-i386/fb.h new file mode 100644 index 00000000000..d1c6297d4a6 --- /dev/null +++ b/include/asm-i386/fb.h @@ -0,0 +1,17 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +extern int fb_is_primary_device(struct fb_info *info); + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + if (boot_cpu_data.x86 > 3) + pgprot_val(vma->vm_page_prot) |= _PAGE_PCD; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-i386/irq.h b/include/asm-i386/irq.h index 9e15ce0006e..36f310632c4 100644 --- a/include/asm-i386/irq.h +++ b/include/asm-i386/irq.h @@ -41,6 +41,7 @@ extern int irqbalance_disable(char *str); extern void fixup_irqs(cpumask_t map); #endif +unsigned int do_IRQ(struct pt_regs *regs); void init_IRQ(void); void __init native_init_IRQ(void); diff --git a/include/asm-i386/kprobes.h b/include/asm-i386/kprobes.h index 8774d06689d..06f7303c30c 100644 --- a/include/asm-i386/kprobes.h +++ b/include/asm-i386/kprobes.h @@ -42,7 +42,6 @@ typedef u8 kprobe_opcode_t; ? (MAX_STACK_SIZE) \ : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)pentry #define ARCH_SUPPORTS_KRETPROBES #define ARCH_INACTIVE_KPROBE_COUNT 0 #define flush_insn_slot(p) do { } while (0) diff --git a/include/asm-i386/mach-default/irq_vectors_limits.h b/include/asm-i386/mach-default/irq_vectors_limits.h index 7f161e760be..a90c7a60109 100644 --- a/include/asm-i386/mach-default/irq_vectors_limits.h +++ b/include/asm-i386/mach-default/irq_vectors_limits.h @@ -1,7 +1,7 @@ #ifndef _ASM_IRQ_VECTORS_LIMITS_H #define _ASM_IRQ_VECTORS_LIMITS_H -#ifdef CONFIG_X86_IO_APIC +#if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) #define NR_IRQS 224 # if (224 >= 32 * NR_CPUS) # define NR_IRQ_VECTORS NR_IRQS diff --git a/include/asm-i386/mmu_context.h b/include/asm-i386/mmu_context.h index 8198d1cca1f..7eb0b0b1fb3 100644 --- a/include/asm-i386/mmu_context.h +++ b/include/asm-i386/mmu_context.h @@ -32,6 +32,8 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) #endif } +void leave_mm(unsigned long cpu); + static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h index 818ac8bf01e..99cf5d3692a 100644 --- a/include/asm-i386/page.h +++ b/include/asm-i386/page.h @@ -34,7 +34,8 @@ #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h index 7f846a7d6bc..7df88be2dd9 100644 --- a/include/asm-i386/paravirt.h +++ b/include/asm-i386/paravirt.h @@ -52,6 +52,8 @@ struct paravirt_ops /* Basic arch-specific setup */ void (*arch_setup)(void); char *(*memory_setup)(void); + void (*post_allocator_init)(void); + void (*init_IRQ)(void); void (*time_init)(void); @@ -116,7 +118,7 @@ struct paravirt_ops u64 (*read_tsc)(void); u64 (*read_pmc)(void); - u64 (*get_scheduled_cycles)(void); + unsigned long long (*sched_clock)(void); unsigned long (*get_cpu_khz)(void); /* Segment descriptor handling */ @@ -173,7 +175,7 @@ struct paravirt_ops unsigned long va); /* Hooks for allocating/releasing pagetable pages */ - void (*alloc_pt)(u32 pfn); + void (*alloc_pt)(struct mm_struct *mm, u32 pfn); void (*alloc_pd)(u32 pfn); void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); void (*release_pt)(u32 pfn); @@ -260,6 +262,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len) unsigned paravirt_patch_insns(void *site, unsigned len, const char *start, const char *end); +int paravirt_disable_iospace(void); /* * This generates an indirect call based on the operation type number. @@ -563,7 +566,10 @@ static inline u64 paravirt_read_tsc(void) #define rdtscll(val) (val = paravirt_read_tsc()) -#define get_scheduled_cycles(val) (val = paravirt_ops.get_scheduled_cycles()) +static inline unsigned long long paravirt_sched_clock(void) +{ + return PVOP_CALL0(unsigned long long, sched_clock); +} #define calculate_cpu_khz() (paravirt_ops.get_cpu_khz()) #define write_tsc(val1,val2) wrmsr(0x10, val1, val2) @@ -669,6 +675,12 @@ static inline void setup_secondary_clock(void) } #endif +static inline void paravirt_post_allocator_init(void) +{ + if (paravirt_ops.post_allocator_init) + (*paravirt_ops.post_allocator_init)(); +} + static inline void paravirt_pagetable_setup_start(pgd_t *base) { if (paravirt_ops.pagetable_setup_start) @@ -725,9 +737,9 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va); } -static inline void paravirt_alloc_pt(unsigned pfn) +static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn) { - PVOP_VCALL1(alloc_pt, pfn); + PVOP_VCALL2(alloc_pt, mm, pfn); } static inline void paravirt_release_pt(unsigned pfn) { diff --git a/include/asm-i386/percpu.h b/include/asm-i386/percpu.h index f54830b5d5a..a7ebd436f3c 100644 --- a/include/asm-i386/percpu.h +++ b/include/asm-i386/percpu.h @@ -54,6 +54,11 @@ extern unsigned long __per_cpu_offset[]; #define DEFINE_PER_CPU(type, name) \ __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp + /* We can use this directly for local CPU (faster). */ DECLARE_PER_CPU(unsigned long, this_cpu_off); diff --git a/include/asm-i386/pgalloc.h b/include/asm-i386/pgalloc.h index d07b7afc269..f2fc33ceb9f 100644 --- a/include/asm-i386/pgalloc.h +++ b/include/asm-i386/pgalloc.h @@ -7,7 +7,7 @@ #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else -#define paravirt_alloc_pt(pfn) do { } while (0) +#define paravirt_alloc_pt(mm, pfn) do { } while (0) #define paravirt_alloc_pd(pfn) do { } while (0) #define paravirt_alloc_pd(pfn) do { } while (0) #define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0) @@ -17,13 +17,13 @@ #define pmd_populate_kernel(mm, pmd, pte) \ do { \ - paravirt_alloc_pt(__pa(pte) >> PAGE_SHIFT); \ + paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT); \ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \ } while (0) #define pmd_populate(mm, pmd, pte) \ do { \ - paravirt_alloc_pt(page_to_pfn(pte)); \ + paravirt_alloc_pt(mm, page_to_pfn(pte)); \ set_pmd(pmd, __pmd(_PAGE_TABLE + \ ((unsigned long long)page_to_pfn(pte) << \ (unsigned long long) PAGE_SHIFT))); \ diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h index 01734e05e63..c7fefa6b12f 100644 --- a/include/asm-i386/pgtable.h +++ b/include/asm-i386/pgtable.h @@ -289,17 +289,6 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) __changed; \ }) -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define ptep_test_and_clear_dirty(vma, addr, ptep) ({ \ - int __ret = 0; \ - if (pte_dirty(*(ptep))) \ - __ret = test_and_clear_bit(_PAGE_BIT_DIRTY, \ - &(ptep)->pte_low); \ - if (__ret) \ - pte_update((vma)->vm_mm, addr, ptep); \ - __ret; \ -}) - #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young(vma, addr, ptep) ({ \ int __ret = 0; \ @@ -311,27 +300,6 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) __ret; \ }) -/* - * Rules for using ptep_establish: the pte MUST be a user pte, and - * must be a present->present transition. - */ -#define __HAVE_ARCH_PTEP_ESTABLISH -#define ptep_establish(vma, address, ptep, pteval) \ -do { \ - set_pte_present((vma)->vm_mm, address, ptep, pteval); \ - flush_tlb_page(vma, address); \ -} while (0) - -#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH -#define ptep_clear_flush_dirty(vma, address, ptep) \ -({ \ - int __dirty; \ - __dirty = ptep_test_and_clear_dirty((vma), (address), (ptep)); \ - if (__dirty) \ - flush_tlb_page(vma, address); \ - __dirty; \ -}) - #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young(vma, address, ptep) \ ({ \ diff --git a/include/asm-i386/setup.h b/include/asm-i386/setup.h index 0d5bff9dc4a..7862fe858a9 100644 --- a/include/asm-i386/setup.h +++ b/include/asm-i386/setup.h @@ -81,6 +81,10 @@ void __init add_memory_region(unsigned long long start, extern unsigned long init_pg_tables_end; +#ifndef CONFIG_PARAVIRT +#define paravirt_post_allocator_init() do {} while (0) +#endif + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h index 0c713278706..1f73bde165b 100644 --- a/include/asm-i386/smp.h +++ b/include/asm-i386/smp.h @@ -43,9 +43,12 @@ extern u8 x86_cpu_to_apicid[]; #define cpu_physical_id(cpu) x86_cpu_to_apicid[cpu] +extern void set_cpu_sibling_map(int cpu); + #ifdef CONFIG_HOTPLUG_CPU extern void cpu_exit_clear(void); extern void cpu_uninit(void); +extern void remove_siblinginfo(int cpu); #endif struct smp_ops @@ -129,6 +132,8 @@ extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern unsigned int num_processors; +void __cpuinit smp_store_cpu_info(int id); + #endif /* !__ASSEMBLY__ */ #else /* CONFIG_SMP */ diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h index 153770e25fa..51a713e33a9 100644 --- a/include/asm-i386/timer.h +++ b/include/asm-i386/timer.h @@ -15,8 +15,38 @@ extern int no_sync_cmos_clock; extern int recalibrate_cpu_khz(void); #ifndef CONFIG_PARAVIRT -#define get_scheduled_cycles(val) rdtscll(val) #define calculate_cpu_khz() native_calculate_cpu_khz() #endif +/* Accellerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better percision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ +extern unsigned long cyc2ns_scale __read_mostly; + +#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ + +static inline unsigned long long cycles_2_ns(unsigned long long cyc) +{ + return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR; +} + + #endif diff --git a/include/asm-i386/tsc.h b/include/asm-i386/tsc.h index 62c091ffccc..a4d806610b7 100644 --- a/include/asm-i386/tsc.h +++ b/include/asm-i386/tsc.h @@ -63,6 +63,7 @@ extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern void init_tsc_clocksource(void); +int check_tsc_unstable(void); /* * Boot-time check whether the TSCs are synchronized across diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h index e84ace1ec8b..9b15545eb9b 100644 --- a/include/asm-i386/unistd.h +++ b/include/asm-i386/unistd.h @@ -329,10 +329,11 @@ #define __NR_signalfd 321 #define __NR_timerfd 322 #define __NR_eventfd 323 +#define __NR_fallocate 324 #ifdef __KERNEL__ -#define NR_syscalls 324 +#define NR_syscalls 325 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/include/asm-i386/vmi_time.h b/include/asm-i386/vmi_time.h index 213930b995c..47818813032 100644 --- a/include/asm-i386/vmi_time.h +++ b/include/asm-i386/vmi_time.h @@ -49,7 +49,7 @@ extern struct vmi_timer_ops { extern void __init vmi_time_init(void); extern unsigned long vmi_get_wallclock(void); extern int vmi_set_wallclock(unsigned long now); -extern unsigned long long vmi_get_sched_cycles(void); +extern unsigned long long vmi_sched_clock(void); extern unsigned long vmi_cpu_khz(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/include/asm-i386/xen/hypercall.h b/include/asm-i386/xen/hypercall.h new file mode 100644 index 00000000000..bc0ee7d961c --- /dev/null +++ b/include/asm-i386/xen/hypercall.h @@ -0,0 +1,413 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERCALL_H__ +#define __HYPERCALL_H__ + +#include <linux/errno.h> +#include <linux/string.h> + +#include <xen/interface/xen.h> +#include <xen/interface/sched.h> +#include <xen/interface/physdev.h> + +extern struct { char _entry[32]; } hypercall_page[]; + +#define _hypercall0(type, name) \ +({ \ + long __res; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res) \ + : [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall1(type, name, a1) \ +({ \ + long __res, __ign1; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1) \ + : "1" ((long)(a1)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall2(type, name, a1, a2) \ +({ \ + long __res, __ign1, __ign2; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall3(type, name, a1, a2, a3) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall4(type, name, a1, a2, a3, a4) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4, __ign5; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4), "=D" (__ign5) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)), \ + "5" ((long)(a5)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +static inline int +HYPERVISOR_set_trap_table(struct trap_info *table) +{ + return _hypercall1(int, set_trap_table, table); +} + +static inline int +HYPERVISOR_mmu_update(struct mmu_update *req, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmu_update, req, count, success_count, domid); +} + +static inline int +HYPERVISOR_mmuext_op(struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmuext_op, op, count, success_count, domid); +} + +static inline int +HYPERVISOR_set_gdt(unsigned long *frame_list, int entries) +{ + return _hypercall2(int, set_gdt, frame_list, entries); +} + +static inline int +HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp) +{ + return _hypercall2(int, stack_switch, ss, esp); +} + +static inline int +HYPERVISOR_set_callbacks(unsigned long event_selector, + unsigned long event_address, + unsigned long failsafe_selector, + unsigned long failsafe_address) +{ + return _hypercall4(int, set_callbacks, + event_selector, event_address, + failsafe_selector, failsafe_address); +} + +static inline int +HYPERVISOR_fpu_taskswitch(int set) +{ + return _hypercall1(int, fpu_taskswitch, set); +} + +static inline int +HYPERVISOR_sched_op(int cmd, unsigned long arg) +{ + return _hypercall2(int, sched_op, cmd, arg); +} + +static inline long +HYPERVISOR_set_timer_op(u64 timeout) +{ + unsigned long timeout_hi = (unsigned long)(timeout>>32); + unsigned long timeout_lo = (unsigned long)timeout; + return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi); +} + +static inline int +HYPERVISOR_set_debugreg(int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static inline unsigned long +HYPERVISOR_get_debugreg(int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor(u64 ma, u64 desc) +{ + return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); +} + +static inline int +HYPERVISOR_memory_op(unsigned int cmd, void *arg) +{ + return _hypercall2(int, memory_op, cmd, arg); +} + +static inline int +HYPERVISOR_multicall(void *call_list, int nr_calls) +{ + return _hypercall2(int, multicall, call_list, nr_calls); +} + +static inline int +HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, + unsigned long flags) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall4(int, update_va_mapping, va, + new_val.pte_low, pte_hi, flags); +} + +static inline int +HYPERVISOR_event_channel_op(int cmd, void *arg) +{ + int rc = _hypercall2(int, event_channel_op, cmd, arg); + if (unlikely(rc == -ENOSYS)) { + struct evtchn_op op; + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, event_channel_op_compat, &op); + memcpy(arg, &op.u, sizeof(op.u)); + } + return rc; +} + +static inline int +HYPERVISOR_xen_version(int cmd, void *arg) +{ + return _hypercall2(int, xen_version, cmd, arg); +} + +static inline int +HYPERVISOR_console_io(int cmd, int count, char *str) +{ + return _hypercall3(int, console_io, cmd, count, str); +} + +static inline int +HYPERVISOR_physdev_op(int cmd, void *arg) +{ + int rc = _hypercall2(int, physdev_op, cmd, arg); + if (unlikely(rc == -ENOSYS)) { + struct physdev_op op; + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, physdev_op_compat, &op); + memcpy(arg, &op.u, sizeof(op.u)); + } + return rc; +} + +static inline int +HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count) +{ + return _hypercall3(int, grant_table_op, cmd, uop, count); +} + +static inline int +HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val, + unsigned long flags, domid_t domid) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall5(int, update_va_mapping_otherdomain, va, + new_val.pte_low, pte_hi, flags, domid); +} + +static inline int +HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type) +{ + return _hypercall2(int, vm_assist, cmd, type); +} + +static inline int +HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args) +{ + return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); +} + +static inline int +HYPERVISOR_suspend(unsigned long srec) +{ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, + SHUTDOWN_suspend, srec); +} + +static inline int +HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) +{ + return _hypercall2(int, nmi_op, op, arg); +} + +static inline void +MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags) +{ + mcl->op = __HYPERVISOR_update_va_mapping; + mcl->args[0] = va; +#ifdef CONFIG_X86_PAE + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; +#endif + mcl->args[3] = flags; +} + +static inline void +MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd, + void *uop, unsigned int count) +{ + mcl->op = __HYPERVISOR_grant_table_op; + mcl->args[0] = cmd; + mcl->args[1] = (unsigned long)uop; + mcl->args[2] = count; +} + +static inline void +MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags, + domid_t domid) +{ + mcl->op = __HYPERVISOR_update_va_mapping_otherdomain; + mcl->args[0] = va; +#ifdef CONFIG_X86_PAE + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; +#endif + mcl->args[3] = flags; + mcl->args[4] = domid; +} + +static inline void +MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, + struct desc_struct desc) +{ + mcl->op = __HYPERVISOR_update_descriptor; + mcl->args[0] = maddr; + mcl->args[1] = maddr >> 32; + mcl->args[2] = desc.a; + mcl->args[3] = desc.b; +} + +static inline void +MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg) +{ + mcl->op = __HYPERVISOR_memory_op; + mcl->args[0] = cmd; + mcl->args[1] = (unsigned long)arg; +} + +static inline void +MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, + int count, int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmu_update; + mcl->args[0] = (unsigned long)req; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; +} + +static inline void +MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmuext_op; + mcl->args[0] = (unsigned long)op; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; +} + +static inline void +MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries) +{ + mcl->op = __HYPERVISOR_set_gdt; + mcl->args[0] = (unsigned long)frames; + mcl->args[1] = entries; +} + +static inline void +MULTI_stack_switch(struct multicall_entry *mcl, + unsigned long ss, unsigned long esp) +{ + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = ss; + mcl->args[1] = esp; +} + +#endif /* __HYPERCALL_H__ */ diff --git a/include/asm-i386/xen/hypervisor.h b/include/asm-i386/xen/hypervisor.h new file mode 100644 index 00000000000..8e15dd28c91 --- /dev/null +++ b/include/asm-i386/xen/hypervisor.h @@ -0,0 +1,73 @@ +/****************************************************************************** + * hypervisor.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERVISOR_H__ +#define __HYPERVISOR_H__ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/version.h> + +#include <xen/interface/xen.h> +#include <xen/interface/version.h> + +#include <asm/ptrace.h> +#include <asm/page.h> +#include <asm/desc.h> +#if defined(__i386__) +# ifdef CONFIG_X86_PAE +# include <asm-generic/pgtable-nopud.h> +# else +# include <asm-generic/pgtable-nopmd.h> +# endif +#endif +#include <asm/xen/hypercall.h> + +/* arch/i386/kernel/setup.c */ +extern struct shared_info *HYPERVISOR_shared_info; +extern struct start_info *xen_start_info; +#define is_initial_xendomain() (xen_start_info->flags & SIF_INITDOMAIN) + +/* arch/i386/mach-xen/evtchn.c */ +/* Force a proper event-channel callback from Xen. */ +extern void force_evtchn_callback(void); + +/* Turn jiffies into Xen system time. */ +u64 jiffies_to_st(unsigned long jiffies); + + +#define MULTI_UVMFLAGS_INDEX 3 +#define MULTI_UVMDOMID_INDEX 4 + +#define is_running_on_xen() (xen_start_info ? 1 : 0) + +#endif /* __HYPERVISOR_H__ */ diff --git a/include/asm-i386/xen/interface.h b/include/asm-i386/xen/interface.h new file mode 100644 index 00000000000..165c3968e13 --- /dev/null +++ b/include/asm-i386/xen/interface.h @@ -0,0 +1,188 @@ +/****************************************************************************** + * arch-x86_32.h + * + * Guest OS interface to x86 32-bit Xen. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_32_H__ +#define __XEN_PUBLIC_ARCH_X86_32_H__ + +#ifdef __XEN__ +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } __guest_handle_ ## name +#else +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef type * __guest_handle_ ## name +#endif + +#define DEFINE_GUEST_HANDLE_STRUCT(name) \ + __DEFINE_GUEST_HANDLE(name, struct name) +#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) +#define GUEST_HANDLE(name) __guest_handle_ ## name + +#ifndef __ASSEMBLY__ +/* Guest handles for primitive C types. */ +__DEFINE_GUEST_HANDLE(uchar, unsigned char); +__DEFINE_GUEST_HANDLE(uint, unsigned int); +__DEFINE_GUEST_HANDLE(ulong, unsigned long); +DEFINE_GUEST_HANDLE(char); +DEFINE_GUEST_HANDLE(int); +DEFINE_GUEST_HANDLE(long); +DEFINE_GUEST_HANDLE(void); +#endif + +/* + * SEGMENT DESCRIPTOR TABLES + */ +/* + * A number of GDT entries are reserved by Xen. These are not situated at the + * start of the GDT because some stupid OSes export hard-coded selector values + * in their ABI. These hard-coded values are always near the start of the GDT, + * so Xen places itself out of the way, at the far end of the GDT. + */ +#define FIRST_RESERVED_GDT_PAGE 14 +#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) +#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) + +/* + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ +#define FLAT_RING1_CS 0xe019 /* GDT index 259 */ +#define FLAT_RING1_DS 0xe021 /* GDT index 260 */ +#define FLAT_RING1_SS 0xe021 /* GDT index 260 */ +#define FLAT_RING3_CS 0xe02b /* GDT index 261 */ +#define FLAT_RING3_DS 0xe033 /* GDT index 262 */ +#define FLAT_RING3_SS 0xe033 /* GDT index 262 */ + +#define FLAT_KERNEL_CS FLAT_RING1_CS +#define FLAT_KERNEL_DS FLAT_RING1_DS +#define FLAT_KERNEL_SS FLAT_RING1_SS +#define FLAT_USER_CS FLAT_RING3_CS +#define FLAT_USER_DS FLAT_RING3_DS +#define FLAT_USER_SS FLAT_RING3_SS + +/* And the trap vector is... */ +#define TRAP_INSTR "int $0x82" + +/* + * Virtual addresses beyond this are not modifiable by guest OSes. The + * machine->physical mapping table starts at this address, read-only. + */ +#ifdef CONFIG_X86_PAE +#define __HYPERVISOR_VIRT_START 0xF5800000 +#else +#define __HYPERVISOR_VIRT_START 0xFC000000 +#endif + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#endif + +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) +#endif + +/* Maximum number of virtual CPUs in multi-processor guests. */ +#define MAX_VIRT_CPUS 32 + +#ifndef __ASSEMBLY__ + +/* + * Send an array of these to HYPERVISOR_set_trap_table() + */ +#define TI_GET_DPL(_ti) ((_ti)->flags & 3) +#define TI_GET_IF(_ti) ((_ti)->flags & 4) +#define TI_SET_DPL(_ti, _dpl) ((_ti)->flags |= (_dpl)) +#define TI_SET_IF(_ti, _if) ((_ti)->flags |= ((!!(_if))<<2)) + +struct trap_info { + uint8_t vector; /* exception vector */ + uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */ + uint16_t cs; /* code selector */ + unsigned long address; /* code offset */ +}; +DEFINE_GUEST_HANDLE_STRUCT(trap_info); + +struct cpu_user_regs { + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint32_t esi; + uint32_t edi; + uint32_t ebp; + uint32_t eax; + uint16_t error_code; /* private */ + uint16_t entry_vector; /* private */ + uint32_t eip; + uint16_t cs; + uint8_t saved_upcall_mask; + uint8_t _pad0; + uint32_t eflags; /* eflags.IF == !saved_upcall_mask */ + uint32_t esp; + uint16_t ss, _pad1; + uint16_t es, _pad2; + uint16_t ds, _pad3; + uint16_t fs, _pad4; + uint16_t gs, _pad5; +}; +DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs); + +typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ + +/* + * The following is all CPU context. Note that the fpu_ctxt block is filled + * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + */ +struct vcpu_guest_context { + /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ + struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ +#define VGCF_I387_VALID (1<<0) +#define VGCF_HVM_GUEST (1<<1) +#define VGCF_IN_KERNEL (1<<2) + unsigned long flags; /* VGCF_* flags */ + struct cpu_user_regs user_regs; /* User-level CPU registers */ + struct trap_info trap_ctxt[256]; /* Virtual IDT */ + unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */ + unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ + unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ + unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */ + unsigned long event_callback_cs; /* CS:EIP of event callback */ + unsigned long event_callback_eip; + unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */ + unsigned long failsafe_callback_eip; + unsigned long vm_assist; /* VMASST_TYPE_* bitmap */ +}; +DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context); + +struct arch_shared_info { + unsigned long max_pfn; /* max pfn that appears in table */ + /* Frame containing list of mfns containing list of mfns containing p2m. */ + unsigned long pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; +}; + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */ +}; + +#endif /* !__ASSEMBLY__ */ + +/* + * Prefix forces emulation of some non-trapping instructions. + * Currently only CPUID. + */ +#ifdef __ASSEMBLY__ +#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ; +#define XEN_CPUID XEN_EMULATE_PREFIX cpuid +#else +#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; " +#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid" +#endif + +#endif diff --git a/include/asm-ia64/fb.h b/include/asm-ia64/fb.h new file mode 100644 index 00000000000..89a397cee90 --- /dev/null +++ b/include/asm-ia64/fb.h @@ -0,0 +1,23 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <linux/efi.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + if (efi_range_is_wc(vma->vm_start, vma->vm_end - vma->vm_start)) + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + else + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-ia64/ioctls.h b/include/asm-ia64/ioctls.h index 31ee521aeb7..f41b636a0bf 100644 --- a/include/asm-ia64/ioctls.h +++ b/include/asm-ia64/ioctls.h @@ -53,6 +53,10 @@ #define TIOCSBRK 0x5427 /* BSD compatibility */ #define TIOCCBRK 0x5428 /* BSD compatibility */ #define TIOCGSID 0x5429 /* Return the session ID of FD */ +#define TCGETS2 _IOR('T',0x2A, struct termios2) +#define TCSETS2 _IOW('T',0x2B, struct termios2) +#define TCSETSW2 _IOW('T',0x2C, struct termios2) +#define TCSETSF2 _IOW('T',0x2D, struct termios2) #define TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ #define TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */ diff --git a/include/asm-ia64/kprobes.h b/include/asm-ia64/kprobes.h index 6382e52ec22..067d9dea68f 100644 --- a/include/asm-ia64/kprobes.h +++ b/include/asm-ia64/kprobes.h @@ -82,8 +82,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe[ARCH_PREV_KPROBE_SZ]; }; -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)pentry - #define ARCH_SUPPORTS_KRETPROBES #define ARCH_INACTIVE_KPROBE_COUNT 1 diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h index 485759ba9e3..d6345464a2b 100644 --- a/include/asm-ia64/page.h +++ b/include/asm-ia64/page.h @@ -87,12 +87,13 @@ do { \ } while (0) -#define alloc_zeroed_user_highpage(vma, vaddr) \ -({ \ - struct page *page = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr); \ - if (page) \ - flush_dcache_page(page); \ - page; \ +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ +({ \ + struct page *page = alloc_page_vma( \ + GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr); \ + if (page) \ + flush_dcache_page(page); \ + page; \ }) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE diff --git a/include/asm-ia64/percpu.h b/include/asm-ia64/percpu.h index fbe5cf3ab8d..43a7aac414e 100644 --- a/include/asm-ia64/percpu.h +++ b/include/asm-ia64/percpu.h @@ -29,6 +29,16 @@ __attribute__((__section__(".data.percpu"))) \ __SMALL_ADDR_AREA __typeof__(type) per_cpu__##name +#ifdef CONFIG_SMP +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __SMALL_ADDR_AREA __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp +#else +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) +#endif + /* * Pretty much a literal copy of asm-generic/percpu.h, except that percpu_modcopy() is an * external routine, to avoid include-hell. diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h index f923d811c42..de6d01e24dd 100644 --- a/include/asm-ia64/pgtable.h +++ b/include/asm-ia64/pgtable.h @@ -395,22 +395,6 @@ ptep_test_and_clear_young (struct vm_area_struct *vma, unsigned long addr, pte_t #endif } -static inline int -ptep_test_and_clear_dirty (struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ -#ifdef CONFIG_SMP - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_D_BIT, ptep); -#else - pte_t pte = *ptep; - if (!pte_dirty(pte)) - return 0; - set_pte_at(vma->vm_mm, addr, ptep, pte_mkclean(pte)); - return 1; -#endif -} - static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -543,8 +527,10 @@ extern void lazy_mmu_prot_update (pte_t pte); # define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __safely_writable) \ ({ \ int __changed = !pte_same(*(__ptep), __entry); \ - if (__changed) \ - ptep_establish(__vma, __addr, __ptep, __entry); \ + if (__changed) { \ + set_pte_at((__vma)->vm_mm, (__addr), __ptep, __entry); \ + flush_tlb_page(__vma, __addr); \ + } \ __changed; \ }) #endif @@ -588,7 +574,6 @@ extern void lazy_mmu_prot_update (pte_t pte); #endif #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h index db81ba406ce..6251c76437d 100644 --- a/include/asm-ia64/processor.h +++ b/include/asm-ia64/processor.h @@ -295,9 +295,9 @@ struct thread_struct { regs->ar_bspstore = current->thread.rbs_bot; \ regs->ar_fpsr = FPSR_DEFAULT; \ regs->loadrs = 0; \ - regs->r8 = current->mm->dumpable; /* set "don't zap registers" flag */ \ + regs->r8 = get_dumpable(current->mm); /* set "don't zap registers" flag */ \ regs->r12 = new_sp - 16; /* allocate 16 byte scratch area */ \ - if (unlikely(!current->mm->dumpable)) { \ + if (unlikely(!get_dumpable(current->mm))) { \ /* \ * Zap scratch regs to avoid leaking bits between processes with different \ * uid/privileges. \ diff --git a/include/asm-ia64/termbits.h b/include/asm-ia64/termbits.h index 7fae3109ef4..9f162e0089a 100644 --- a/include/asm-ia64/termbits.h +++ b/include/asm-ia64/termbits.h @@ -149,6 +149,7 @@ struct ktermios { #define HUPCL 0002000 #define CLOCAL 0004000 #define CBAUDEX 0010000 +#define BOTHER 0010000 #define B57600 0010001 #define B115200 0010002 #define B230400 0010003 @@ -164,10 +165,12 @@ struct ktermios { #define B3000000 0010015 #define B3500000 0010016 #define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate (not used) */ +#define CIBAUD 002003600000 /* input baud rate */ #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ + /* c_lflag bits */ #define ISIG 0000001 #define ICANON 0000002 diff --git a/include/asm-ia64/termios.h b/include/asm-ia64/termios.h index 08750c2d360..689d218c0c2 100644 --- a/include/asm-ia64/termios.h +++ b/include/asm-ia64/termios.h @@ -87,8 +87,10 @@ struct termio { copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \ }) -#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios)) -#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios)) +#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2)) +#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2)) +#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios)) +#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios)) # endif /* __KERNEL__ */ diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h index 441c9e00177..315f8de950a 100644 --- a/include/asm-ia64/unistd.h +++ b/include/asm-ia64/unistd.h @@ -292,7 +292,7 @@ #define __NR_sync_file_range 1300 #define __NR_tee 1301 #define __NR_vmsplice 1302 -/* 1303 reserved for move_pages */ +#define __NR_fallocate 1303 #define __NR_getcpu 1304 #define __NR_epoll_pwait 1305 #define __NR_utimensat 1306 diff --git a/include/asm-ia64/ustack.h b/include/asm-ia64/ustack.h index a349467913e..504167c35b8 100644 --- a/include/asm-ia64/ustack.h +++ b/include/asm-ia64/ustack.h @@ -11,6 +11,7 @@ /* The absolute hard limit for stack size is 1/2 of the mappable space in the region */ #define MAX_USER_STACK_SIZE (RGN_MAP_LIMIT/2) #define STACK_TOP (0x6000000000000000UL + RGN_MAP_LIMIT) +#define STACK_TOP_MAX STACK_TOP #endif /* Make a default stack size of 2GiB */ diff --git a/include/asm-m32r/a.out.h b/include/asm-m32r/a.out.h index 9a4a5d20160..6a1b5d42f32 100644 --- a/include/asm-m32r/a.out.h +++ b/include/asm-m32r/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-m32r/fb.h b/include/asm-m32r/fb.h new file mode 100644 index 00000000000..d92e99cd8c8 --- /dev/null +++ b/include/asm-m32r/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-m32r/page.h b/include/asm-m32r/page.h index 6f6ecf7d14a..04fd183a2c5 100644 --- a/include/asm-m32r/page.h +++ b/include/asm-m32r/page.h @@ -15,7 +15,8 @@ extern void copy_page(void *to, void *from); #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-m32r/pgtable.h b/include/asm-m32r/pgtable.h index 35af58c6b81..92d7266783f 100644 --- a/include/asm-m32r/pgtable.h +++ b/include/asm-m32r/pgtable.h @@ -250,11 +250,6 @@ static inline pte_t pte_mkwrite(pte_t pte) return pte; } -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - return test_and_clear_bit(_PAGE_BIT_DIRTY, ptep); -} - static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep); @@ -348,7 +343,6 @@ static inline void pmd_set(pmd_t * pmdp, pte_t * ptep) remap_pfn_range(vma, vaddr, pfn, size, prot) #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/include/asm-m68k/a.out.h b/include/asm-m68k/a.out.h index eda1662773b..6fc86a221a9 100644 --- a/include/asm-m68k/a.out.h +++ b/include/asm-m68k/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-m68k/fb.h b/include/asm-m68k/fb.h new file mode 100644 index 00000000000..380b97ae815 --- /dev/null +++ b/include/asm-m68k/fb.h @@ -0,0 +1,34 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> +#include <asm/setup.h> + +#ifdef CONFIG_SUN3 +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + pgprot_val(vma->vm_page_prot) |= SUN3_PAGE_NOCACHE; +} +#else +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + if (CPU_IS_020_OR_030) + pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE030; + if (CPU_IS_040_OR_060) { + pgprot_val(vma->vm_page_prot) &= _CACHEMASK040; + /* Use no-cache mode, serialized */ + pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE_S; + } +} +#endif /* CONFIG_SUN3 */ + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-m68knommu/fb.h b/include/asm-m68knommu/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-m68knommu/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-m68knommu/irq.h b/include/asm-m68knommu/irq.h index 7b8f874f842..9373c31ac87 100644 --- a/include/asm-m68knommu/irq.h +++ b/include/asm-m68knommu/irq.h @@ -1,7 +1,5 @@ -#ifndef _M68K_IRQ_H_ -#define _M68K_IRQ_H_ - -#include <asm/ptrace.h> +#ifndef _M68KNOMMU_IRQ_H_ +#define _M68KNOMMU_IRQ_H_ #ifdef CONFIG_COLDFIRE /* @@ -17,75 +15,12 @@ /* * # of m68k interrupts */ -#define SYS_IRQS 8 -#define NR_IRQS (24+SYS_IRQS) +#define SYS_IRQS 8 +#define NR_IRQS (24 + SYS_IRQS) #endif /* CONFIG_COLDFIRE */ -/* - * Interrupt source definitions - * General interrupt sources are the level 1-7. - * Adding an interrupt service routine for one of these sources - * results in the addition of that routine to a chain of routines. - * Each one is called in succession. Each individual interrupt - * service routine should determine if the device associated with - * that routine requires service. - */ -#define IRQ1 (1) /* level 1 interrupt */ -#define IRQ2 (2) /* level 2 interrupt */ -#define IRQ3 (3) /* level 3 interrupt */ -#define IRQ4 (4) /* level 4 interrupt */ -#define IRQ5 (5) /* level 5 interrupt */ -#define IRQ6 (6) /* level 6 interrupt */ -#define IRQ7 (7) /* level 7 interrupt (non-maskable) */ - -/* - * Machine specific interrupt sources. - * - * Adding an interrupt service routine for a source with this bit - * set indicates a special machine specific interrupt source. - * The machine specific files define these sources. - * - * The IRQ_MACHSPEC bit is now gone - the only thing it did was to - * introduce unnecessary overhead. - * - * All interrupt handling is actually machine specific so it is better - * to use function pointers, as used by the Sparc port, and select the - * interrupt handling functions when initializing the kernel. This way - * we save some unnecessary overhead at run-time. - * 01/11/97 - Jes - */ - -extern void (*mach_enable_irq)(unsigned int); -extern void (*mach_disable_irq)(unsigned int); - -/* - * various flags for request_irq() - the Amiga now uses the standard - * mechanism like all other architectures - IRQF_DISABLED and - * IRQF_SHARED are your friends. - */ -#define IRQ_FLG_LOCK (0x0001) /* handler is not replaceable */ -#define IRQ_FLG_REPLACE (0x0002) /* replace existing handler */ -#define IRQ_FLG_FAST (0x0004) -#define IRQ_FLG_SLOW (0x0008) -#define IRQ_FLG_STD (0x8000) /* internally used */ - -#ifdef CONFIG_M68360 - -#define CPM_INTERRUPT IRQ4 - -/* see MC68360 User's Manual, p. 7-377 */ -#define CPM_VECTOR_BASE 0x04 /* 3 MSbits of CPM vector */ - -#endif /* CONFIG_M68360 */ - -/* - * Some drivers want these entry points - */ -#define enable_irq(x) do { } while (0) -#define disable_irq(x) do { } while (0) -#define disable_irq_nosync(x) disable_irq(x) #define irq_canonicalize(irq) (irq) -#endif /* _M68K_IRQ_H_ */ +#endif /* _M68KNOMMU_IRQ_H_ */ diff --git a/include/asm-m68knommu/irqnode.h b/include/asm-m68knommu/irqnode.h deleted file mode 100644 index 6132a9858b5..00000000000 --- a/include/asm-m68knommu/irqnode.h +++ /dev/null @@ -1,36 +0,0 @@ -#ifndef _M68K_IRQNODE_H_ -#define _M68K_IRQNODE_H_ - -#include <linux/interrupt.h> - -/* - * This structure is used to chain together the ISRs for a particular - * interrupt source (if it supports chaining). - */ -typedef struct irq_node { - irq_handler_t handler; - unsigned long flags; - void *dev_id; - const char *devname; - struct irq_node *next; -} irq_node_t; - -/* - * This structure has only 4 elements for speed reasons - */ -struct irq_entry { - irq_handler_t handler; - unsigned long flags; - void *dev_id; - const char *devname; -}; - -/* count of spurious interrupts */ -extern volatile unsigned int num_spurious; - -/* - * This function returns a new irq_node_t - */ -extern irq_node_t *new_irq_node(void); - -#endif /* _M68K_IRQNODE_H_ */ diff --git a/include/asm-m68knommu/m68360.h b/include/asm-m68knommu/m68360.h index dd11b070884..eb7d39ef285 100644 --- a/include/asm-m68knommu/m68360.h +++ b/include/asm-m68knommu/m68360.h @@ -3,3 +3,11 @@ #include "m68360_quicc.h" #include "m68360_enet.h" +#ifdef CONFIG_M68360 + +#define CPM_INTERRUPT 4 + +/* see MC68360 User's Manual, p. 7-377 */ +#define CPM_VECTOR_BASE 0x04 /* 3 MSbits of CPM vector */ + +#endif /* CONFIG_M68360 */ diff --git a/include/asm-m68knommu/page.h b/include/asm-m68knommu/page.h index 2a1b8bdcb29..9efa0a9851b 100644 --- a/include/asm-m68knommu/page.h +++ b/include/asm-m68knommu/page.h @@ -22,7 +22,8 @@ #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-m68knommu/pgtable.h b/include/asm-m68knommu/pgtable.h index 9dfbbc24aa7..e1e6a1d2333 100644 --- a/include/asm-m68knommu/pgtable.h +++ b/include/asm-m68knommu/pgtable.h @@ -49,7 +49,6 @@ static inline int pte_file(pte_t pte) { return 0; } * These would be in other places but having them here reduces the diffs. */ extern unsigned int kobjsize(const void *objp); -extern int is_in_rom(unsigned long); /* * No page table caches to initialise. diff --git a/include/asm-m68knommu/traps.h b/include/asm-m68knommu/traps.h index f2a81317cc1..d0671e5f8e2 100644 --- a/include/asm-m68knommu/traps.h +++ b/include/asm-m68knommu/traps.h @@ -16,6 +16,10 @@ typedef void (*e_vector)(void); extern e_vector vectors[]; +extern void init_vectors(void); +extern void enable_vector(unsigned int irq); +extern void disable_vector(unsigned int irq); +extern void ack_vector(unsigned int irq); #endif diff --git a/include/asm-m68knommu/uaccess.h b/include/asm-m68knommu/uaccess.h index 62b29b10bc6..9ed9169a884 100644 --- a/include/asm-m68knommu/uaccess.h +++ b/include/asm-m68knommu/uaccess.h @@ -15,12 +15,15 @@ #define access_ok(type,addr,size) _access_ok((unsigned long)(addr),(size)) +/* + * It is not enough to just have access_ok check for a real RAM address. + * This would disallow the case of code/ro-data running XIP in flash/rom. + * Ideally we would check the possible flash ranges too, but that is + * currently not so easy. + */ static inline int _access_ok(unsigned long addr, unsigned long size) { - extern unsigned long memory_start, memory_end; - - return (((addr >= memory_start) && (addr+size < memory_end)) || - (is_in_rom(addr) && is_in_rom(addr+size))); + return 1; } /* diff --git a/include/asm-mips/a.out.h b/include/asm-mips/a.out.h index ef33c3f1348..1ad60ba186d 100644 --- a/include/asm-mips/a.out.h +++ b/include/asm-mips/a.out.h @@ -40,6 +40,7 @@ struct exec #ifdef CONFIG_64BIT #define STACK_TOP (current->thread.mflags & MF_32BIT_ADDR ? TASK_SIZE32 : TASK_SIZE) #endif +#define STACK_TOP_MAX TASK_SIZE #endif diff --git a/include/asm-mips/dec/serial.h b/include/asm-mips/dec/serial.h deleted file mode 100644 index acad75890a0..00000000000 --- a/include/asm-mips/dec/serial.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * include/asm-mips/dec/serial.h - * - * Definitions common to all DECstation serial devices. - * - * Copyright (C) 2004 Maciej W. Rozycki - * - * Based on bits extracted from drivers/tc/zs.h for which - * the following copyrights apply: - * - * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996 Paul Mackerras (Paul.Mackerras@cs.anu.edu.au) - * Copyright (C) Harald Koerfgen - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#ifndef __ASM_MIPS_DEC_SERIAL_H -#define __ASM_MIPS_DEC_SERIAL_H - -struct dec_serial_hook { - int (*init_channel)(void *handle); - void (*init_info)(void *handle); - void (*rx_char)(unsigned char ch, unsigned char fl); - int (*poll_rx_char)(void *handle); - int (*poll_tx_char)(void *handle, unsigned char ch); - unsigned int cflags; -}; - -extern int register_dec_serial_hook(unsigned int channel, - struct dec_serial_hook *hook); -extern int unregister_dec_serial_hook(unsigned int channel); - -#endif /* __ASM_MIPS_DEC_SERIAL_H */ diff --git a/include/asm-mips/fb.h b/include/asm-mips/fb.h new file mode 100644 index 00000000000..bd3f68c9ddf --- /dev/null +++ b/include/asm-mips/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-mips/sibyte/bcm1480_regs.h b/include/asm-mips/sibyte/bcm1480_regs.h index bda391d3af8..2738c1366f6 100644 --- a/include/asm-mips/sibyte/bcm1480_regs.h +++ b/include/asm-mips/sibyte/bcm1480_regs.h @@ -220,17 +220,25 @@ #define A_BCM1480_DUART(chan) ((((chan)&2) == 0)? A_BCM1480_DUART0 : A_BCM1480_DUART1) #define BCM1480_DUART_CHANREG_SPACING 0x100 -#define A_BCM1480_DUART_CHANREG(chan,reg) (A_BCM1480_DUART(chan) \ - + BCM1480_DUART_CHANREG_SPACING*((chan)&1) \ - + (reg)) -#define R_BCM1480_DUART_CHANREG(chan,reg) (BCM1480_DUART_CHANREG_SPACING*((chan)&1) + (reg)) - -#define R_BCM1480_DUART_IMRREG(chan) (R_DUART_IMR_A + ((chan)&1)*DUART_IMRISR_SPACING) -#define R_BCM1480_DUART_ISRREG(chan) (R_DUART_ISR_A + ((chan)&1)*DUART_IMRISR_SPACING) - -#define A_BCM1480_DUART_IMRREG(chan) (A_BCM1480_DUART(chan) + R_BCM1480_DUART_IMRREG(chan)) -#define A_BCM1480_DUART_ISRREG(chan) (A_BCM1480_DUART(chan) + R_BCM1480_DUART_ISRREG(chan)) -#define A_BCM1480_DUART_IN_PORT(chan) (A_BCM1480_DUART(chan) + R_DUART_INP_ORT) +#define A_BCM1480_DUART_CHANREG(chan, reg) \ + (A_BCM1480_DUART(chan) + \ + BCM1480_DUART_CHANREG_SPACING * (((chan) & 1) + 1) + (reg)) +#define A_BCM1480_DUART_CTRLREG(chan, reg) \ + (A_BCM1480_DUART(chan) + \ + BCM1480_DUART_CHANREG_SPACING * 3 + (reg)) + +#define R_BCM1480_DUART_IMRREG(chan) \ + (R_DUART_IMR_A + ((chan) & 1) * DUART_IMRISR_SPACING) +#define R_BCM1480_DUART_ISRREG(chan) \ + (R_DUART_ISR_A + ((chan) & 1) * DUART_IMRISR_SPACING) + +#define A_BCM1480_DUART_IMRREG(chan) \ + (A_BCM1480_DUART_CTRLREG((chan), R_BCM1480_DUART_IMRREG(chan))) +#define A_BCM1480_DUART_ISRREG(chan) \ + (A_BCM1480_DUART_CTRLREG((chan), R_BCM1480_DUART_ISRREG(chan))) + +#define A_BCM1480_DUART_IN_PORT(chan) \ + (A_BCM1480_DUART_CTRLREG((chan), R_DUART_IN_PORT)) /* * These constants are the absolute addresses. diff --git a/include/asm-mips/sibyte/sb1250_regs.h b/include/asm-mips/sibyte/sb1250_regs.h index da7c188993c..220b7e94f1b 100644 --- a/include/asm-mips/sibyte/sb1250_regs.h +++ b/include/asm-mips/sibyte/sb1250_regs.h @@ -272,59 +272,69 @@ ********************************************************************* */ -#if SIBYTE_HDR_FEATURE_1250_112x /* This MC only on 1250 & 112x */ +#if SIBYTE_HDR_FEATURE_1250_112x /* This MC only on 1250 & 112x */ #define R_DUART_NUM_PORTS 2 #define A_DUART 0x0010060000 #define DUART_CHANREG_SPACING 0x100 -#define A_DUART_CHANREG(chan,reg) (A_DUART + DUART_CHANREG_SPACING*(chan) + (reg)) -#define R_DUART_CHANREG(chan,reg) (DUART_CHANREG_SPACING*(chan) + (reg)) + +#define A_DUART_CHANREG(chan, reg) \ + (A_DUART + DUART_CHANREG_SPACING * ((chan) + 1) + (reg)) #endif /* 1250 & 112x */ -#define R_DUART_MODE_REG_1 0x100 -#define R_DUART_MODE_REG_2 0x110 -#define R_DUART_STATUS 0x120 -#define R_DUART_CLK_SEL 0x130 -#define R_DUART_CMD 0x150 -#define R_DUART_RX_HOLD 0x160 -#define R_DUART_TX_HOLD 0x170 +#define R_DUART_MODE_REG_1 0x000 +#define R_DUART_MODE_REG_2 0x010 +#define R_DUART_STATUS 0x020 +#define R_DUART_CLK_SEL 0x030 +#define R_DUART_CMD 0x050 +#define R_DUART_RX_HOLD 0x060 +#define R_DUART_TX_HOLD 0x070 #if SIBYTE_HDR_FEATURE(1250, PASS2) || SIBYTE_HDR_FEATURE(112x, PASS1) || SIBYTE_HDR_FEATURE_CHIP(1480) -#define R_DUART_FULL_CTL 0x140 -#define R_DUART_OPCR_X 0x180 -#define R_DUART_AUXCTL_X 0x190 -#endif /* 1250 PASS2 || 112x PASS1 || 1480*/ +#define R_DUART_FULL_CTL 0x040 +#define R_DUART_OPCR_X 0x080 +#define R_DUART_AUXCTL_X 0x090 +#endif /* 1250 PASS2 || 112x PASS1 || 1480 */ /* * The IMR and ISR can't be addressed with A_DUART_CHANREG, - * so use this macro instead. + * so use these macros instead. */ -#define R_DUART_AUX_CTRL 0x310 -#define R_DUART_ISR_A 0x320 -#define R_DUART_IMR_A 0x330 -#define R_DUART_ISR_B 0x340 -#define R_DUART_IMR_B 0x350 -#define R_DUART_OUT_PORT 0x360 -#define R_DUART_OPCR 0x370 -#define R_DUART_IN_PORT 0x380 +#if SIBYTE_HDR_FEATURE_1250_112x /* This MC only on 1250 & 112x */ +#define DUART_IMRISR_SPACING 0x20 +#define DUART_INCHNG_SPACING 0x10 -#define R_DUART_SET_OPR 0x3B0 -#define R_DUART_CLEAR_OPR 0x3C0 +#define A_DUART_CTRLREG(reg) \ + (A_DUART + DUART_CHANREG_SPACING * 3 + (reg)) -#define DUART_IMRISR_SPACING 0x20 +#define R_DUART_IMRREG(chan) \ + (R_DUART_IMR_A + (chan) * DUART_IMRISR_SPACING) +#define R_DUART_ISRREG(chan) \ + (R_DUART_ISR_A + (chan) * DUART_IMRISR_SPACING) +#define R_DUART_INCHREG(chan) \ + (R_DUART_IN_CHNG_A + (chan) * DUART_INCHNG_SPACING) -#if SIBYTE_HDR_FEATURE_1250_112x /* This MC only on 1250 & 112x */ -#define R_DUART_IMRREG(chan) (R_DUART_IMR_A + (chan)*DUART_IMRISR_SPACING) -#define R_DUART_ISRREG(chan) (R_DUART_ISR_A + (chan)*DUART_IMRISR_SPACING) - -#define A_DUART_IMRREG(chan) (A_DUART + R_DUART_IMRREG(chan)) -#define A_DUART_ISRREG(chan) (A_DUART + R_DUART_ISRREG(chan)) +#define A_DUART_IMRREG(chan) A_DUART_CTRLREG(R_DUART_IMRREG(chan)) +#define A_DUART_ISRREG(chan) A_DUART_CTRLREG(R_DUART_ISRREG(chan)) +#define A_DUART_INCHREG(chan) A_DUART_CTRLREG(R_DUART_INCHREG(chan)) #endif /* 1250 & 112x */ - +#define R_DUART_AUX_CTRL 0x010 +#define R_DUART_ISR_A 0x020 +#define R_DUART_IMR_A 0x030 +#define R_DUART_ISR_B 0x040 +#define R_DUART_IMR_B 0x050 +#define R_DUART_OUT_PORT 0x060 +#define R_DUART_OPCR 0x070 +#define R_DUART_IN_PORT 0x080 + +#define R_DUART_SET_OPR 0x0B0 +#define R_DUART_CLEAR_OPR 0x0C0 +#define R_DUART_IN_CHNG_A 0x0D0 +#define R_DUART_IN_CHNG_B 0x0E0 /* diff --git a/include/asm-mips/sibyte/sb1250_uart.h b/include/asm-mips/sibyte/sb1250_uart.h index e87045e62bf..cf74fedcbef 100644 --- a/include/asm-mips/sibyte/sb1250_uart.h +++ b/include/asm-mips/sibyte/sb1250_uart.h @@ -75,7 +75,8 @@ #define V_DUART_PARITY_MODE_ADD_FIXED V_DUART_PARITY_MODE(K_DUART_PARITY_MODE_ADD_FIXED) #define V_DUART_PARITY_MODE_NONE V_DUART_PARITY_MODE(K_DUART_PARITY_MODE_NONE) -#define M_DUART_ERR_MODE _SB_MAKEMASK1(5) /* must be zero */ +#define M_DUART_TX_IRQ_SEL_TXRDY 0 +#define M_DUART_TX_IRQ_SEL_TXEMPT _SB_MAKEMASK1(5) #define M_DUART_RX_IRQ_SEL_RXRDY 0 #define M_DUART_RX_IRQ_SEL_RXFULL _SB_MAKEMASK1(6) @@ -246,10 +247,13 @@ #define M_DUART_ISR_BRK_A _SB_MAKEMASK1(2) #define M_DUART_ISR_IN_A _SB_MAKEMASK1(3) +#define M_DUART_ISR_ALL_A _SB_MAKEMASK(4,0) + #define M_DUART_ISR_TX_B _SB_MAKEMASK1(4) #define M_DUART_ISR_RX_B _SB_MAKEMASK1(5) #define M_DUART_ISR_BRK_B _SB_MAKEMASK1(6) #define M_DUART_ISR_IN_B _SB_MAKEMASK1(7) +#define M_DUART_ISR_ALL_B _SB_MAKEMASK(4,4) /* * DUART Channel A Interrupt Status Register (Table 10-17) @@ -262,6 +266,7 @@ #define M_DUART_ISR_RX _SB_MAKEMASK1(1) #define M_DUART_ISR_BRK _SB_MAKEMASK1(2) #define M_DUART_ISR_IN _SB_MAKEMASK1(3) +#define M_DUART_ISR_ALL _SB_MAKEMASK(4,0) #define M_DUART_ISR_RESERVED _SB_MAKEMASK(4,4) /* diff --git a/include/asm-parisc/a.out.h b/include/asm-parisc/a.out.h index 2a490cc9ec9..23e2c90943e 100644 --- a/include/asm-parisc/a.out.h +++ b/include/asm-parisc/a.out.h @@ -23,6 +23,7 @@ struct exec * prumpf */ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX DEFAULT_TASK_SIZE #endif diff --git a/include/asm-parisc/fb.h b/include/asm-parisc/fb.h new file mode 100644 index 00000000000..4d503a023ab --- /dev/null +++ b/include/asm-parisc/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE; +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-parisc/pgtable.h b/include/asm-parisc/pgtable.h index 7e222c8ba73..e88cacd6372 100644 --- a/include/asm-parisc/pgtable.h +++ b/include/asm-parisc/pgtable.h @@ -447,21 +447,6 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned #endif } -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ -#ifdef CONFIG_SMP - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(xlate_pabit(_PAGE_DIRTY_BIT), &pte_val(*ptep)); -#else - pte_t pte = *ptep; - if (!pte_dirty(pte)) - return 0; - set_pte_at(vma->vm_mm, addr, ptep, pte_mkclean(pte)); - return 1; -#endif -} - extern spinlock_t pa_dbit_lock; struct mm_struct; @@ -529,7 +514,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/include/asm-powerpc/a.out.h b/include/asm-powerpc/a.out.h index c7393a97736..5c5ea83f934 100644 --- a/include/asm-powerpc/a.out.h +++ b/include/asm-powerpc/a.out.h @@ -26,9 +26,12 @@ struct exec #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ STACK_TOP_USER32 : STACK_TOP_USER64) +#define STACK_TOP_MAX STACK_TOP_USER64 + #else /* __powerpc64__ */ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif /* __powerpc64__ */ #endif /* __KERNEL__ */ diff --git a/include/asm-powerpc/fb.h b/include/asm-powerpc/fb.h new file mode 100644 index 00000000000..411af8d17a6 --- /dev/null +++ b/include/asm-powerpc/fb.h @@ -0,0 +1,21 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = phys_mem_access_prot(file, off >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-powerpc/kprobes.h b/include/asm-powerpc/kprobes.h index b0e40ff32ee..8b08b447d6f 100644 --- a/include/asm-powerpc/kprobes.h +++ b/include/asm-powerpc/kprobes.h @@ -65,20 +65,18 @@ typedef unsigned int kprobe_opcode_t; } else if (name[0] != '.') \ addr = *(kprobe_opcode_t **)addr; \ } else { \ - char dot_name[KSYM_NAME_LEN+1]; \ + char dot_name[KSYM_NAME_LEN]; \ dot_name[0] = '.'; \ dot_name[1] = '\0'; \ - strncat(dot_name, name, KSYM_NAME_LEN); \ + strncat(dot_name, name, KSYM_NAME_LEN - 2); \ addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name); \ } \ } -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)((func_descr_t *)pentry) #define is_trap(instr) (IS_TW(instr) || IS_TD(instr) || \ IS_TWI(instr) || IS_TDI(instr)) #else /* Use stock kprobe_lookup_name since ppc32 doesn't use function descriptors */ -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)(pentry) #define is_trap(instr) (IS_TW(instr) || IS_TWI(instr)) #endif diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h index 2f2e3024fa6..73dc8ba4010 100644 --- a/include/asm-powerpc/percpu.h +++ b/include/asm-powerpc/percpu.h @@ -20,6 +20,11 @@ #define DEFINE_PER_CPU(type, name) \ __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp + /* var is in discarded region: offset to particular copy we want */ #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu))) #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset())) @@ -40,6 +45,8 @@ extern void setup_per_cpu_areas(void); #define DEFINE_PER_CPU(type, name) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) #define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var)) #define __get_cpu_var(var) per_cpu__##var diff --git a/include/asm-powerpc/pgtable-ppc32.h b/include/asm-powerpc/pgtable-ppc32.h index 6c236d4d626..86a54a4a8a2 100644 --- a/include/asm-powerpc/pgtable-ppc32.h +++ b/include/asm-powerpc/pgtable-ppc32.h @@ -621,13 +621,6 @@ static inline int __ptep_test_and_clear_young(unsigned int context, unsigned lon #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - return (pte_update(ptep, (_PAGE_DIRTY | _PAGE_HWWRITE), 0) & _PAGE_DIRTY) != 0; -} - #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/include/asm-powerpc/pgtable-ppc64.h b/include/asm-powerpc/pgtable-ppc64.h index 7ca8b5c1001..300f9a199bf 100644 --- a/include/asm-powerpc/pgtable-ppc64.h +++ b/include/asm-powerpc/pgtable-ppc64.h @@ -292,29 +292,6 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, __r; \ }) -/* - * On RW/DIRTY bit transitions we can avoid flushing the hpte. For the - * moment we always flush but we need to fix hpte_update and test if the - * optimisation is worth it. - */ -static inline int __ptep_test_and_clear_dirty(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old; - - if ((pte_val(*ptep) & _PAGE_DIRTY) == 0) - return 0; - old = pte_update(mm, addr, ptep, _PAGE_DIRTY, 0); - return (old & _PAGE_DIRTY) != 0; -} -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define ptep_test_and_clear_dirty(__vma, __addr, __ptep) \ -({ \ - int __r; \ - __r = __ptep_test_and_clear_dirty((__vma)->vm_mm, __addr, __ptep); \ - __r; \ -}) - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -342,14 +319,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, __young; \ }) -#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH -#define ptep_clear_flush_dirty(__vma, __address, __ptep) \ -({ \ - int __dirty = __ptep_test_and_clear_dirty((__vma)->vm_mm, __address, \ - __ptep); \ - __dirty; \ -}) - #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/include/asm-powerpc/systbl.h b/include/asm-powerpc/systbl.h index 1cc3f9cb6f4..cc6d8722825 100644 --- a/include/asm-powerpc/systbl.h +++ b/include/asm-powerpc/systbl.h @@ -308,6 +308,7 @@ COMPAT_SYS_SPU(move_pages) SYSCALL_SPU(getcpu) COMPAT_SYS(epoll_pwait) COMPAT_SYS_SPU(utimensat) +COMPAT_SYS(fallocate) COMPAT_SYS_SPU(signalfd) COMPAT_SYS_SPU(timerfd) SYSCALL_SPU(eventfd) diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h index f71c6061f1e..97d82b6a940 100644 --- a/include/asm-powerpc/unistd.h +++ b/include/asm-powerpc/unistd.h @@ -331,10 +331,11 @@ #define __NR_timerfd 306 #define __NR_eventfd 307 #define __NR_sync_file_range2 308 +#define __NR_fallocate 309 #ifdef __KERNEL__ -#define __NR_syscalls 309 +#define __NR_syscalls 310 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/include/asm-ppc/pgtable.h b/include/asm-ppc/pgtable.h index 18aa776313b..c159315d2c8 100644 --- a/include/asm-ppc/pgtable.h +++ b/include/asm-ppc/pgtable.h @@ -654,13 +654,6 @@ static inline int __ptep_test_and_clear_young(unsigned int context, unsigned lon #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - return (pte_update(ptep, (_PAGE_DIRTY | _PAGE_HWWRITE), 0) & _PAGE_DIRTY) != 0; -} - #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/include/asm-s390/a.out.h b/include/asm-s390/a.out.h index 72adee6ef33..46158dcaf51 100644 --- a/include/asm-s390/a.out.h +++ b/include/asm-s390/a.out.h @@ -32,6 +32,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX DEFAULT_TASK_SIZE #endif diff --git a/include/asm-s390/fb.h b/include/asm-s390/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-s390/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-s390/kprobes.h b/include/asm-s390/kprobes.h index 830fe4c4eea..340ba10446e 100644 --- a/include/asm-s390/kprobes.h +++ b/include/asm-s390/kprobes.h @@ -46,8 +46,6 @@ typedef u16 kprobe_opcode_t; ? (MAX_STACK_SIZE) \ : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)(pentry) - #define ARCH_SUPPORTS_KRETPROBES #define ARCH_INACTIVE_KPROBE_COUNT 0 diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h index 05ea6f17278..f326451ed6e 100644 --- a/include/asm-s390/page.h +++ b/include/asm-s390/page.h @@ -64,7 +64,8 @@ static inline void copy_page(void *to, void *from) #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* diff --git a/include/asm-s390/percpu.h b/include/asm-s390/percpu.h index 9ea7f1023e5..545857e6444 100644 --- a/include/asm-s390/percpu.h +++ b/include/asm-s390/percpu.h @@ -41,6 +41,11 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; __attribute__((__section__(".data.percpu"))) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp + #define __get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset) #define __raw_get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset) #define per_cpu(var,cpu) __reloc_hide(var,__per_cpu_offset[cpu]) @@ -59,6 +64,8 @@ do { \ #define DEFINE_PER_CPU(type, name) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) #define __get_cpu_var(var) __reloc_hide(var,0) #define __raw_get_cpu_var(var) __reloc_hide(var,0) diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h index 26215a97612..3208dc6c412 100644 --- a/include/asm-s390/pgtable.h +++ b/include/asm-s390/pgtable.h @@ -669,19 +669,6 @@ ptep_clear_flush_young(struct vm_area_struct *vma, return ptep_test_and_clear_young(vma, address, ptep); } -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - return 0; -} - -static inline int -ptep_clear_flush_dirty(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) -{ - /* No need to flush TLB; bits are in storage key */ - return ptep_test_and_clear_dirty(vma, address, ptep); -} - static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; @@ -707,16 +694,19 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep) pte_val(*ptep) = _PAGE_TYPE_EMPTY; } -static inline pte_t -ptep_clear_flush(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline void ptep_invalidate(unsigned long address, pte_t *ptep) { - pte_t pte = *ptep; - pte_t *shadow_pte = get_shadow_pte(ptep); - __ptep_ipte(address, ptep); - if (shadow_pte) - __ptep_ipte(address, shadow_pte); + ptep = get_shadow_pte(ptep); + if (ptep) + __ptep_ipte(address, ptep); +} + +static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + pte_t pte = *ptep; + ptep_invalidate(address, ptep); return pte; } @@ -726,21 +716,14 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); } -static inline void -ptep_establish(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, - pte_t entry) -{ - ptep_clear_flush(vma, address, ptep); - set_pte(ptep, entry); -} - -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ -({ \ - int __changed = !pte_same(*(__ptep), __entry); \ - if (__changed) \ - ptep_establish(__vma, __address, __ptep, __entry); \ - __changed; \ +#define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \ +({ \ + int __changed = !pte_same(*(__ptep), __entry); \ + if (__changed) { \ + ptep_invalidate(__addr, __ptep); \ + set_pte_at((__vma)->vm_mm, __addr, __ptep, __entry); \ + } \ + __changed; \ }) /* @@ -940,12 +923,9 @@ extern int remove_shared_memory(unsigned long start, unsigned long size); #define __HAVE_ARCH_MEMMAP_INIT extern void memmap_init(unsigned long, int, unsigned long, unsigned long); -#define __HAVE_ARCH_PTEP_ESTABLISH #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT diff --git a/include/asm-sh/a.out.h b/include/asm-sh/a.out.h index 6e9fca9ee33..685d0f6125f 100644 --- a/include/asm-sh/a.out.h +++ b/include/asm-sh/a.out.h @@ -20,6 +20,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-sh/fb.h b/include/asm-sh/fb.h new file mode 100644 index 00000000000..d92e99cd8c8 --- /dev/null +++ b/include/asm-sh/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-sh64/a.out.h b/include/asm-sh64/a.out.h index e1995e86b66..237ee4e5b72 100644 --- a/include/asm-sh64/a.out.h +++ b/include/asm-sh64/a.out.h @@ -31,6 +31,7 @@ struct exec #ifdef __KERNEL__ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP #endif diff --git a/include/asm-sh64/fb.h b/include/asm-sh64/fb.h new file mode 100644 index 00000000000..d92e99cd8c8 --- /dev/null +++ b/include/asm-sh64/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ + +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-sparc/a.out.h b/include/asm-sparc/a.out.h index 9090060a23e..917e0425069 100644 --- a/include/asm-sparc/a.out.h +++ b/include/asm-sparc/a.out.h @@ -92,6 +92,7 @@ struct relocation_info /* used when header.a_machtype == M_SPARC */ #include <asm/page.h> #define STACK_TOP (PAGE_OFFSET - PAGE_SIZE) +#define STACK_TOP_MAX STACK_TOP #endif /* __KERNEL__ */ diff --git a/include/asm-sparc/fb.h b/include/asm-sparc/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-sparc/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-sparc64/a.out.h b/include/asm-sparc64/a.out.h index eb3b8e90b27..902e07f89a4 100644 --- a/include/asm-sparc64/a.out.h +++ b/include/asm-sparc64/a.out.h @@ -101,6 +101,8 @@ struct relocation_info /* used when header.a_machtype == M_SPARC */ #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ STACK_TOP32 : STACK_TOP64) +#define STACK_TOP_MAX STACK_TOP64 + #endif #endif /* !(__ASSEMBLY__) */ diff --git a/include/asm-sparc64/fb.h b/include/asm-sparc64/fb.h new file mode 100644 index 00000000000..d6cd3a175fc --- /dev/null +++ b/include/asm-sparc64/fb.h @@ -0,0 +1,18 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-sparc64/io.h b/include/asm-sparc64/io.h index ad595b67984..9565a892801 100644 --- a/include/asm-sparc64/io.h +++ b/include/asm-sparc64/io.h @@ -14,11 +14,6 @@ #define __SLOW_DOWN_IO do { } while (0) #define SLOW_DOWN_IO do { } while (0) -extern unsigned long virt_to_bus_not_defined_use_pci_map(volatile void *addr); -#define virt_to_bus virt_to_bus_not_defined_use_pci_map -extern unsigned long bus_to_virt_not_defined_use_pci_map(volatile void *addr); -#define bus_to_virt bus_to_virt_not_defined_use_pci_map - /* BIO layer definitions. */ extern unsigned long kern_base, kern_size; #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) diff --git a/include/asm-sparc64/kprobes.h b/include/asm-sparc64/kprobes.h index a331b7b0dff..7f6774dca5f 100644 --- a/include/asm-sparc64/kprobes.h +++ b/include/asm-sparc64/kprobes.h @@ -10,7 +10,6 @@ typedef u32 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION_2 0x91d02071 /* ta 0x71 */ #define MAX_INSN_SIZE 2 -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)pentry #define arch_remove_kprobe(p) do {} while (0) #define ARCH_INACTIVE_KPROBE_COUNT 0 diff --git a/include/asm-sparc64/mdesc.h b/include/asm-sparc64/mdesc.h index e97c4313375..1acc7272e53 100644 --- a/include/asm-sparc64/mdesc.h +++ b/include/asm-sparc64/mdesc.h @@ -61,6 +61,16 @@ extern u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc); extern void mdesc_update(void); +struct mdesc_notifier_client { + void (*add)(struct mdesc_handle *handle, u64 node); + void (*remove)(struct mdesc_handle *handle, u64 node); + + const char *node_name; + struct mdesc_notifier_client *next; +}; + +extern void mdesc_register_notifier(struct mdesc_notifier_client *client); + extern void mdesc_fill_in_cpu_data(cpumask_t mask); extern void sun4v_mdesc_init(void); diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h index 88db872ce2f..caf8750792f 100644 --- a/include/asm-sparc64/percpu.h +++ b/include/asm-sparc64/percpu.h @@ -18,6 +18,11 @@ extern unsigned long __per_cpu_shift; #define DEFINE_PER_CPU(type, name) \ __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp + register unsigned long __local_per_cpu_offset asm("g5"); /* var is in discarded region: offset to particular copy we want */ @@ -38,6 +43,8 @@ do { \ #define real_setup_per_cpu_areas() do { } while (0) #define DEFINE_PER_CPU(type, name) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) #define per_cpu(var, cpu) (*((void)cpu, &per_cpu__##var)) #define __get_cpu_var(var) per_cpu__##var diff --git a/include/asm-sparc64/vio.h b/include/asm-sparc64/vio.h index 83c96422e9d..c0a8d4ed5bc 100644 --- a/include/asm-sparc64/vio.h +++ b/include/asm-sparc64/vio.h @@ -264,7 +264,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr, ((dr->prod - dr->cons) & (ring_size - 1))); } -#define VIO_MAX_TYPE_LEN 64 +#define VIO_MAX_TYPE_LEN 32 #define VIO_MAX_COMPAT_LEN 64 struct vio_dev { diff --git a/include/asm-um/a.out.h b/include/asm-um/a.out.h index 7016b893ac9..78bc9eed26b 100644 --- a/include/asm-um/a.out.h +++ b/include/asm-um/a.out.h @@ -17,4 +17,6 @@ extern int honeypot; #define STACK_TOP \ CHOOSE_MODE((honeypot ? host_task_size : task_size), task_size) +#define STACK_TOP_MAX STACK_TOP + #endif diff --git a/include/asm-v850/fb.h b/include/asm-v850/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-v850/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-x86_64/a.out.h b/include/asm-x86_64/a.out.h index 7255cde0653..e789300e41a 100644 --- a/include/asm-x86_64/a.out.h +++ b/include/asm-x86_64/a.out.h @@ -21,7 +21,8 @@ struct exec #ifdef __KERNEL__ #include <linux/thread_info.h> -#define STACK_TOP TASK_SIZE +#define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX TASK_SIZE64 #endif #endif /* __A_OUT_GNU_H__ */ diff --git a/include/asm-x86_64/fb.h b/include/asm-x86_64/fb.h new file mode 100644 index 00000000000..60548e651d1 --- /dev/null +++ b/include/asm-x86_64/fb.h @@ -0,0 +1,19 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> +#include <linux/fs.h> +#include <asm/page.h> + +static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, + unsigned long off) +{ + if (boot_cpu_data.x86 > 3) + pgprot_val(vma->vm_page_prot) |= _PAGE_PCD; +} + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-x86_64/kprobes.h b/include/asm-x86_64/kprobes.h index cf5317898fb..7db825403e0 100644 --- a/include/asm-x86_64/kprobes.h +++ b/include/asm-x86_64/kprobes.h @@ -41,7 +41,6 @@ typedef u8 kprobe_opcode_t; ? (MAX_STACK_SIZE) \ : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) -#define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)pentry #define ARCH_SUPPORTS_KRETPROBES #define ARCH_INACTIVE_KPROBE_COUNT 1 diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h index e327c830da0..88adf1afb0a 100644 --- a/include/asm-x86_64/page.h +++ b/include/asm-x86_64/page.h @@ -48,7 +48,8 @@ void copy_page(void *, void *); #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /* * These are used to make use of C type-checking.. diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h index c6fbb67eac9..5abd4827010 100644 --- a/include/asm-x86_64/percpu.h +++ b/include/asm-x86_64/percpu.h @@ -20,6 +20,11 @@ #define DEFINE_PER_CPU(type, name) \ __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + __typeof__(type) per_cpu__##name \ + ____cacheline_internodealigned_in_smp + /* var is in discarded region: offset to particular copy we want */ #define per_cpu(var, cpu) (*({ \ extern int simple_identifier_##var(void); \ @@ -46,6 +51,8 @@ extern void setup_per_cpu_areas(void); #define DEFINE_PER_CPU(type, name) \ __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) #define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var)) #define __get_cpu_var(var) per_cpu__##var diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h index 4f169ac6b10..3ba53099297 100644 --- a/include/asm-x86_64/pgtable.h +++ b/include/asm-x86_64/pgtable.h @@ -284,13 +284,6 @@ static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & struct vm_area_struct; -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte); -} - static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (!pte_young(*ptep)) @@ -427,7 +420,6 @@ extern int kern_addr_valid(unsigned long addr); (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o)) #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL #define __HAVE_ARCH_PTEP_SET_WRPROTECT diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h index 8696f8ad401..fc4e73f5f1f 100644 --- a/include/asm-x86_64/unistd.h +++ b/include/asm-x86_64/unistd.h @@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd) __SYSCALL(__NR_timerfd, sys_timerfd) #define __NR_eventfd 284 __SYSCALL(__NR_eventfd, sys_eventfd) +#define __NR_fallocate 285 +__SYSCALL(__NR_fallocate, sys_fallocate) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/include/asm-xtensa/a.out.h b/include/asm-xtensa/a.out.h index ffc4dcfd6ac..05a2f67c676 100644 --- a/include/asm-xtensa/a.out.h +++ b/include/asm-xtensa/a.out.h @@ -17,6 +17,7 @@ /* Note: the kernel needs the a.out definitions, even if only ELF is used. */ #define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP struct exec { diff --git a/include/asm-xtensa/fb.h b/include/asm-xtensa/fb.h new file mode 100644 index 00000000000..c7df3803099 --- /dev/null +++ b/include/asm-xtensa/fb.h @@ -0,0 +1,12 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/fb.h> + +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/include/asm-xtensa/pgtable.h b/include/asm-xtensa/pgtable.h index e9fc512cc24..06850f3b26a 100644 --- a/include/asm-xtensa/pgtable.h +++ b/include/asm-xtensa/pgtable.h @@ -267,17 +267,6 @@ ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, return 1; } -static inline int -ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep) -{ - pte_t pte = *ptep; - if (!pte_dirty(pte)) - return 0; - update_pte(ptep, pte_mkclean(pte)); - return 1; -} - static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -418,7 +407,6 @@ typedef pte_t *pte_addr_t; #endif /* !defined (__ASSEMBLY__) */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTEP_MKDIRTY diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fccd8b548d9..dc234c508a6 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -122,7 +122,7 @@ extern struct acpi_mcfg_allocation *pci_mmcfg_config; extern int pci_mmcfg_config_num; extern int sbf_port; -extern unsigned long acpi_video_flags; +extern unsigned long acpi_realmode_flags; #else /* !CONFIG_ACPI */ diff --git a/include/linux/aio.h b/include/linux/aio.h index b903fc02bdb..d10e608f232 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -86,7 +86,7 @@ struct kioctx; */ struct kiocb { struct list_head ki_run_list; - long ki_flags; + unsigned long ki_flags; int ki_users; unsigned ki_key; /* id of this request */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index e1a708337be..91c8c07fe8b 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -6,11 +6,13 @@ struct pt_regs; /* - * MAX_ARG_PAGES defines the number of pages allocated for arguments - * and envelope for the new program. 32 should suffice, this gives - * a maximum env+arg of 128kB w/4KB pages! + * These are the maximum length and maximum number of strings passed to the + * execve() system call. MAX_ARG_STRLEN is essentially random but serves to + * prevent the kernel from being unduly impacted by misaddressed pointers. + * MAX_ARG_STRINGS is chosen to fit in a signed 32-bit integer. */ -#define MAX_ARG_PAGES 32 +#define MAX_ARG_STRLEN (PAGE_SIZE * 32) +#define MAX_ARG_STRINGS 0x7FFFFFFF /* sizeof(linux_binprm->buf) */ #define BINPRM_BUF_SIZE 128 @@ -24,7 +26,12 @@ struct pt_regs; */ struct linux_binprm{ char buf[BINPRM_BUF_SIZE]; +#ifdef CONFIG_MMU + struct vm_area_struct *vma; +#else +# define MAX_ARG_PAGES 32 struct page *page[MAX_ARG_PAGES]; +#endif struct mm_struct *mm; unsigned long p; /* current top of mem */ int sh_bang; @@ -40,6 +47,7 @@ struct linux_binprm{ unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; + unsigned long argv_len; }; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 @@ -68,7 +76,7 @@ extern int register_binfmt(struct linux_binfmt *); extern int unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); -extern void remove_arg_zero(struct linux_binprm *); +extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *,struct pt_regs *); extern int flush_old_exec(struct linux_binprm * bprm); @@ -85,6 +93,7 @@ extern int suid_dumpable; extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); +extern int bprm_mm_init(struct linux_binprm *bprm); extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); extern void compute_creds(struct linux_binprm *binprm); extern int do_coredump(long signr, int exit_code, struct pt_regs * regs); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b32564a1e10..f78965fc642 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -624,7 +624,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) -#ifdef CONFIG_MMU +#ifdef CONFIG_BOUNCE extern int init_emergency_isa_pool(void); extern void blk_queue_bounce(request_queue_t *q, struct bio **bio); #else diff --git a/include/linux/bsg.h b/include/linux/bsg.h index bd998ca6cb2..8547b10c388 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -60,7 +60,6 @@ struct bsg_class_device { extern int bsg_register_queue(struct request_queue *, const char *); extern void bsg_unregister_queue(struct request_queue *); #else -struct bsg_class_device { }; #define bsg_register_queue(disk, name) (0) #define bsg_unregister_queue(disk) do { } while (0) #endif diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index e4ac016ad27..c4079b403e9 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -43,9 +43,6 @@ int coda_revalidate_inode(struct dentry *); int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *); int coda_setattr(struct dentry *, struct iattr *); -/* global variables */ -extern int coda_fake_statfs; - /* this file: heloers */ static __inline__ struct CodaFid *coda_i2f(struct inode *); static __inline__ char *coda_i2s(struct inode *); diff --git a/include/linux/coda_proc.h b/include/linux/coda_proc.h deleted file mode 100644 index 0dc1b0458e7..00000000000 --- a/include/linux/coda_proc.h +++ /dev/null @@ -1,76 +0,0 @@ -/* - * coda_statis.h - * - * CODA operation statistics - * - * (c) March, 1998 - * by Michihiro Kuramochi, Zhenyu Xia and Zhanyong Wan - * zhanyong.wan@yale.edu - * - */ - -#ifndef _CODA_PROC_H -#define _CODA_PROC_H - -void coda_sysctl_init(void); -void coda_sysctl_clean(void); - -#include <linux/sysctl.h> -#include <linux/coda_fs_i.h> -#include <linux/coda.h> - -/* these four files are presented to show the result of the statistics: - * - * /proc/fs/coda/vfs_stats - * cache_inv_stats - * - * these four files are presented to reset the statistics to 0: - * - * /proc/sys/coda/vfs_stats - * cache_inv_stats - */ - -/* VFS operation statistics */ -struct coda_vfs_stats -{ - /* file operations */ - int open; - int flush; - int release; - int fsync; - - /* dir operations */ - int readdir; - - /* inode operations */ - int create; - int lookup; - int link; - int unlink; - int symlink; - int mkdir; - int rmdir; - int rename; - int permission; - - /* symlink operatoins*/ - int follow_link; - int readlink; -}; - -/* cache invalidation statistics */ -struct coda_cache_inv_stats -{ - int flush; - int purge_user; - int zap_dir; - int zap_file; - int zap_vnode; - int purge_fid; - int replace; -}; - -/* these global variables hold the actual statistics data */ -extern struct coda_vfs_stats coda_vfs_stat; - -#endif /* _CODA_PROC_H */ diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index b541bb3d1f4..aa8f454b3b7 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -8,11 +8,6 @@ struct kstatfs; -struct coda_sb_info -{ - struct venus_comm *sbi_vcomm; -}; - /* communication pending/processing queues */ struct venus_comm { u_long vc_seq; @@ -24,9 +19,9 @@ struct venus_comm { }; -static inline struct coda_sb_info *coda_sbp(struct super_block *sb) +static inline struct venus_comm *coda_vcp(struct super_block *sb) { - return ((struct coda_sb_info *)((sb)->s_fs_info)); + return (struct venus_comm *)((sb)->s_fs_info); } @@ -74,8 +69,6 @@ int venus_statfs(struct dentry *dentry, struct kstatfs *sfs); /* messages between coda filesystem in kernel and Venus */ -extern int coda_hard; -extern unsigned long coda_timeout; struct upc_req { struct list_head uc_chain; caddr_t uc_data; @@ -85,7 +78,6 @@ struct upc_req { u_short uc_opcode; /* copied from data to save lookup */ int uc_unique; wait_queue_head_t uc_sleep; /* process' wait queue */ - unsigned long uc_posttime; }; #define REQ_ASYNC 0x1 diff --git a/include/linux/crc7.h b/include/linux/crc7.h new file mode 100644 index 00000000000..1786e772d5c --- /dev/null +++ b/include/linux/crc7.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_CRC7_H +#define _LINUX_CRC7_H +#include <linux/types.h> + +extern const u8 crc7_syndrome_table[256]; + +static inline u8 crc7_byte(u8 crc, u8 data) +{ + return crc7_syndrome_table[(crc << 1) ^ data]; +} + +extern u8 crc7(u8 crc, const u8 *buffer, size_t len); + +#endif diff --git a/include/linux/device.h b/include/linux/device.h index be2debed70d..d9f0a57f5a2 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -572,6 +572,16 @@ dev_dbg(struct device * dev, const char * fmt, ...) } #endif +#ifdef VERBOSE_DEBUG +#define dev_vdbg dev_dbg +#else +static inline int __attribute__ ((format (printf, 2, 3))) +dev_vdbg(struct device * dev, const char * fmt, ...) +{ + return 0; +} +#endif + #define dev_err(dev, format, arg...) \ dev_printk(KERN_ERR , dev , format , ## arg) #define dev_info(dev, format, arg...) \ diff --git a/include/linux/edac.h b/include/linux/edac.h new file mode 100644 index 00000000000..eab451e69a9 --- /dev/null +++ b/include/linux/edac.h @@ -0,0 +1,29 @@ +/* + * Generic EDAC defs + * + * Author: Dave Jiang <djiang@mvista.com> + * + * 2006-2007 (c) MontaVista Software, Inc. This file is licensed under + * the terms of the GNU General Public License version 2. This program + * is licensed "as is" without any warranty of any kind, whether express + * or implied. + * + */ +#ifndef _LINUX_EDAC_H_ +#define _LINUX_EDAC_H_ + +#include <asm/atomic.h> + +#define EDAC_OPSTATE_INVAL -1 +#define EDAC_OPSTATE_POLL 0 +#define EDAC_OPSTATE_NMI 1 +#define EDAC_OPSTATE_INT 2 + +extern int edac_op_state; +extern int edac_err_assert; +extern atomic_t edac_handlers; + +extern int edac_handler_set(void); +extern void edac_atomic_assert_error(void); + +#endif diff --git a/include/linux/efs_fs.h b/include/linux/efs_fs.h index dfed8009ebf..16cb25cbf7c 100644 --- a/include/linux/efs_fs.h +++ b/include/linux/efs_fs.h @@ -45,6 +45,7 @@ extern efs_block_t efs_map_block(struct inode *, efs_block_t); extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int); extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *efs_get_dentry(struct super_block *sb, void *vobjp); extern struct dentry *efs_get_parent(struct dentry *); extern int efs_bmap(struct inode *, int); diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 9a1e0674e56..e831759b2fb 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -38,17 +38,25 @@ * e.g. ELFNOTE(XYZCo, 42, .asciz, "forty-two") * ELFNOTE(XYZCo, 12, .long, 0xdeadbeef) */ -#define ELFNOTE(name, type, desctype, descdata) \ -.pushsection .note.name, "",@note ; \ - .align 4 ; \ +#define ELFNOTE_START(name, type, flags) \ +.pushsection .note.name, flags,@note ; \ + .balign 4 ; \ .long 2f - 1f /* namesz */ ; \ - .long 4f - 3f /* descsz */ ; \ + .long 4484f - 3f /* descsz */ ; \ .long type ; \ 1:.asciz #name ; \ -2:.align 4 ; \ -3:desctype descdata ; \ -4:.align 4 ; \ +2:.balign 4 ; \ +3: + +#define ELFNOTE_END \ +4484:.balign 4 ; \ .popsection ; + +#define ELFNOTE(name, type, desc) \ + ELFNOTE_START(name, type, "") \ + desc ; \ + ELFNOTE_END + #else /* !__ASSEMBLER__ */ #include <linux/elf.h> /* diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h new file mode 100644 index 00000000000..8872fe8392d --- /dev/null +++ b/include/linux/exportfs.h @@ -0,0 +1,126 @@ +#ifndef LINUX_EXPORTFS_H +#define LINUX_EXPORTFS_H 1 + +#include <linux/types.h> + +struct dentry; +struct super_block; +struct vfsmount; + + +/** + * struct export_operations - for nfsd to communicate with file systems + * @decode_fh: decode a file handle fragment and return a &struct dentry + * @encode_fh: encode a file handle fragment from a dentry + * @get_name: find the name for a given inode in a given directory + * @get_parent: find the parent of a given directory + * @get_dentry: find a dentry for the inode given a file handle sub-fragment + * @find_exported_dentry: + * set by the exporting module to a standard helper function. + * + * Description: + * The export_operations structure provides a means for nfsd to communicate + * with a particular exported file system - particularly enabling nfsd and + * the filesystem to co-operate when dealing with file handles. + * + * export_operations contains two basic operation for dealing with file + * handles, decode_fh() and encode_fh(), and allows for some other + * operations to be defined which standard helper routines use to get + * specific information from the filesystem. + * + * nfsd encodes information use to determine which filesystem a filehandle + * applies to in the initial part of the file handle. The remainder, termed + * a file handle fragment, is controlled completely by the filesystem. The + * standard helper routines assume that this fragment will contain one or + * two sub-fragments, one which identifies the file, and one which may be + * used to identify the (a) directory containing the file. + * + * In some situations, nfsd needs to get a dentry which is connected into a + * specific part of the file tree. To allow for this, it passes the + * function acceptable() together with a @context which can be used to see + * if the dentry is acceptable. As there can be multiple dentrys for a + * given file, the filesystem should check each one for acceptability before + * looking for the next. As soon as an acceptable one is found, it should + * be returned. + * + * decode_fh: + * @decode_fh is given a &struct super_block (@sb), a file handle fragment + * (@fh, @fh_len) and an acceptability testing function (@acceptable, + * @context). It should return a &struct dentry which refers to the same + * file that the file handle fragment refers to, and which passes the + * acceptability test. If it cannot, it should return a %NULL pointer if + * the file was found but no acceptable &dentries were available, or a + * %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or + * %ENOMEM). + * + * encode_fh: + * @encode_fh should store in the file handle fragment @fh (using at most + * @max_len bytes) information that can be used by @decode_fh to recover the + * file refered to by the &struct dentry @de. If the @connectable flag is + * set, the encode_fh() should store sufficient information so that a good + * attempt can be made to find not only the file but also it's place in the + * filesystem. This typically means storing a reference to de->d_parent in + * the filehandle fragment. encode_fh() should return the number of bytes + * stored or a negative error code such as %-ENOSPC + * + * get_name: + * @get_name should find a name for the given @child in the given @parent + * directory. The name should be stored in the @name (with the + * understanding that it is already pointing to a a %NAME_MAX+1 sized + * buffer. get_name() should return %0 on success, a negative error code + * or error. @get_name will be called without @parent->i_mutex held. + * + * get_parent: + * @get_parent should find the parent directory for the given @child which + * is also a directory. In the event that it cannot be found, or storage + * space cannot be allocated, a %ERR_PTR should be returned. + * + * get_dentry: + * Given a &super_block (@sb) and a pointer to a file-system specific inode + * identifier, possibly an inode number, (@inump) get_dentry() should find + * the identified inode and return a dentry for that inode. Any suitable + * dentry can be returned including, if necessary, a new dentry created with + * d_alloc_root. The caller can then find any other extant dentrys by + * following the d_alias links. If a new dentry was created using + * d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry + * should be d_rehash()ed. + * + * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code + * can be returned. The @inump will be whatever was passed to + * nfsd_find_fh_dentry() in either the @obj or @parent parameters. + * + * Locking rules: + * get_parent is called with child->d_inode->i_mutex down + * get_name is not (which is possibly inconsistent) + */ + +struct export_operations { + struct dentry *(*decode_fh)(struct super_block *sb, __u32 *fh, + int fh_len, int fh_type, + int (*acceptable)(void *context, struct dentry *de), + void *context); + int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len, + int connectable); + int (*get_name)(struct dentry *parent, char *name, + struct dentry *child); + struct dentry * (*get_parent)(struct dentry *child); + struct dentry * (*get_dentry)(struct super_block *sb, void *inump); + + /* This is set by the exporting module to a standard helper */ + struct dentry * (*find_exported_dentry)( + struct super_block *sb, void *obj, void *parent, + int (*acceptable)(void *context, struct dentry *de), + void *context); +}; + +extern struct dentry *find_exported_dentry(struct super_block *sb, void *obj, + void *parent, int (*acceptable)(void *context, struct dentry *de), + void *context); + +extern int exportfs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len, + int connectable); +extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, __u32 *fh, + int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *), + void *context); + +#endif /* LINUX_EXPORTFS_H */ diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index de1f9f78625..cdee7aaa57a 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -71,7 +71,7 @@ /* * Maximal count of links to a file */ -#define EXT4_LINK_MAX 32000 +#define EXT4_LINK_MAX 65000 /* * Macro-instructions used to manage several block sizes @@ -102,6 +102,7 @@ EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif +#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) /* * Macro-instructions used to manage fragments @@ -201,6 +202,7 @@ struct ext4_group_desc #define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */ #define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ #define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ +#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { @@ -225,6 +227,11 @@ struct ext4_new_group_data { __u32 free_blocks_count; }; +/* + * Following is used by preallocation code to tell get_blocks() that we + * want uninitialzed extents. + */ +#define EXT4_CREATE_UNINITIALIZED_EXT 2 /* * ioctl commands @@ -237,7 +244,7 @@ struct ext4_new_group_data { #define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION #define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG #define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif #define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) @@ -253,7 +260,7 @@ struct ext4_new_group_data { #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) #define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) #define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG #define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) #endif #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION @@ -282,7 +289,7 @@ struct ext4_inode { __le16 i_uid; /* Low 16 bits of Owner Uid */ __le32 i_size; /* Size in bytes */ __le32 i_atime; /* Access time */ - __le32 i_ctime; /* Creation time */ + __le32 i_ctime; /* Inode Change time */ __le32 i_mtime; /* Modification time */ __le32 i_dtime; /* Deletion Time */ __le16 i_gid; /* Low 16 bits of Group Id */ @@ -331,10 +338,85 @@ struct ext4_inode { } osd2; /* OS dependent 2 */ __le16 i_extra_isize; __le16 i_pad1; + __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ + __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ + __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ + __le32 i_crtime; /* File Creation time */ + __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ }; #define i_size_high i_dir_acl +#define EXT4_EPOCH_BITS 2 +#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) +#define EXT4_NSEC_MASK (~0UL << EXT4_EPOCH_BITS) + +/* + * Extended fields will fit into an inode if the filesystem was formatted + * with large inodes (-I 256 or larger) and there are not currently any EAs + * consuming all of the available space. For new inodes we always reserve + * enough space for the kernel's known extended fields, but for inodes + * created with an old kernel this might not have been the case. None of + * the extended inode fields is critical for correct filesystem operation. + * This macro checks if a certain field fits in the inode. Note that + * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize + */ +#define EXT4_FITS_IN_INODE(ext4_inode, einode, field) \ + ((offsetof(typeof(*ext4_inode), field) + \ + sizeof((ext4_inode)->field)) \ + <= (EXT4_GOOD_OLD_INODE_SIZE + \ + (einode)->i_extra_isize)) \ + +static inline __le32 ext4_encode_extra_time(struct timespec *time) +{ + return cpu_to_le32((sizeof(time->tv_sec) > 4 ? + time->tv_sec >> 32 : 0) | + ((time->tv_nsec << 2) & EXT4_NSEC_MASK)); +} + +static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) +{ + if (sizeof(time->tv_sec) > 4) + time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) + << 32; + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> 2; +} + +#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ +do { \ + (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ + (raw_inode)->xtime ## _extra = \ + ext4_encode_extra_time(&(inode)->xtime); \ +} while (0) + +#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + (raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec); \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ + (raw_inode)->xtime ## _extra = \ + ext4_encode_extra_time(&(einode)->xtime); \ +} while (0) + +#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ +do { \ + (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ + ext4_decode_extra_time(&(inode)->xtime, \ + raw_inode->xtime ## _extra); \ +} while (0) + +#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + (einode)->xtime.tv_sec = \ + (signed)le32_to_cpu((raw_inode)->xtime); \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ + ext4_decode_extra_time(&(einode)->xtime, \ + raw_inode->xtime ## _extra); \ +} while (0) + #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_frag osd2.linux2.l_i_frag @@ -533,6 +615,13 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline struct timespec ext4_current_time(struct inode *inode) +{ + return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ? + current_fs_time(inode->i_sb) : CURRENT_TIME_SEC; +} + + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || @@ -603,6 +692,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 +#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 +#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 @@ -620,6 +711,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) EXT4_FEATURE_INCOMPAT_64BIT) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ + EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) /* @@ -862,6 +955,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern void ext4_truncate (struct inode *); extern void ext4_set_inode_flags(struct inode *); +extern void ext4_get_inode_flags(struct ext4_inode_info *); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_block_truncate_page(handle_t *handle, struct page *page, @@ -983,6 +1077,8 @@ extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, extern void ext4_ext_truncate(struct inode *, struct page *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); +extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, + loff_t len); static inline int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index acfe59740b0..81406f3655d 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -141,7 +141,25 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_MAX_BLOCK 0xffffffff -#define EXT_MAX_LEN ((1UL << 15) - 1) +/* + * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an + * initialized extent. This is 2^15 and not (2^16 - 1), since we use the + * MSB of ee_len field in the extent datastructure to signify if this + * particular extent is an initialized extent or an uninitialized (i.e. + * preallocated). + * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an + * uninitialized extent. + * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an + * uninitialized one. In other words, if MSB of ee_len is set, it is an + * uninitialized extent with only one special scenario when ee_len = 0x8000. + * In this case we can not have an uninitialized extent of zero length and + * thus we make it as a special case of initialized extent with 0x8000 length. + * This way we get better extent-to-group alignment for initialized extents. + * Hence, the maximum number of blocks we can have in an *initialized* + * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767). + */ +#define EXT_INIT_MAX_LEN (1UL << 15) +#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1) #define EXT_FIRST_EXTENT(__hdr__) \ @@ -188,8 +206,31 @@ ext4_ext_invalidate_cache(struct inode *inode) EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO; } +static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext) +{ + /* We can not have an uninitialized extent of zero length! */ + BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0); + ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN); +} + +static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext) +{ + /* Extent with ee_len of 0x8000 is treated as an initialized extent */ + return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN); +} + +static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) +{ + return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ? + le16_to_cpu(ext->ee_len) : + (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); +} + extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *); +extern int ext4_ext_try_to_merge(struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *); extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *); diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 9de49440699..1a511e9905a 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -153,6 +153,11 @@ struct ext4_inode_info { unsigned long i_ext_generation; struct ext4_ext_cache i_cached_extent; + /* + * File creation time. Its function is same as that of + * struct timespec i_{a,c,m}time in the generic inode. + */ + struct timespec i_crtime; }; #endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index 2347557a327..1b2ffee12be 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -73,7 +73,7 @@ struct ext4_sb_info { struct list_head s_orphan; unsigned long s_commit_interval; struct block_device *journal_bdev; -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ #endif @@ -81,6 +81,7 @@ struct ext4_sb_info { char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ int s_jquota_fmt; /* Format of quota to use */ #endif + unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ #ifdef EXTENTS_STATS /* ext4 extents stats */ diff --git a/include/linux/falloc.h b/include/linux/falloc.h new file mode 100644 index 00000000000..8e912ab6a07 --- /dev/null +++ b/include/linux/falloc.h @@ -0,0 +1,6 @@ +#ifndef _FALLOC_H_ +#define _FALLOC_H_ + +#define FALLOC_FL_KEEP_SIZE 0x01 /* default is extend size */ + +#endif /* _FALLOC_H_ */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 66226824ab6..cec54106aa8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -119,6 +119,7 @@ struct dentry; #define FB_ACCEL_NV_40 46 /* nVidia Arch 40 */ #define FB_ACCEL_XGI_VOLARI_V 47 /* XGI Volari V3XT, V5, V8 */ #define FB_ACCEL_XGI_VOLARI_Z 48 /* XGI Volari Z7 */ +#define FB_ACCEL_OMAP1610 49 /* TI OMAP16xx */ #define FB_ACCEL_NEOMAGIC_NM2070 90 /* NeoMagic NM2070 */ #define FB_ACCEL_NEOMAGIC_NM2090 91 /* NeoMagic NM2090 */ #define FB_ACCEL_NEOMAGIC_NM2093 92 /* NeoMagic NM2093 */ @@ -529,6 +530,8 @@ struct fb_cursor_user { #define FB_EVENT_CONBLANK 0x0C /* Get drawing requirements */ #define FB_EVENT_GET_REQ 0x0D +/* Unbind from the console if possible */ +#define FB_EVENT_FB_UNBIND 0x0E struct fb_event { struct fb_info *info; diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 4631086f506..c8e02de737f 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -1,5 +1,8 @@ /* Freezer declarations */ +#ifndef FREEZER_H_INCLUDED +#define FREEZER_H_INCLUDED + #include <linux/sched.h> #ifdef CONFIG_PM @@ -22,7 +25,7 @@ static inline int freezing(struct task_struct *p) /* * Request that a process be frozen */ -static inline void freeze(struct task_struct *p) +static inline void set_freeze_flag(struct task_struct *p) { set_tsk_thread_flag(p, TIF_FREEZE); } @@ -30,7 +33,7 @@ static inline void freeze(struct task_struct *p) /* * Sometimes we may need to cancel the previous 'freeze' request */ -static inline void do_not_freeze(struct task_struct *p) +static inline void clear_freeze_flag(struct task_struct *p) { clear_tsk_thread_flag(p, TIF_FREEZE); } @@ -53,7 +56,7 @@ static inline int thaw_process(struct task_struct *p) wake_up_process(p); return 1; } - clear_tsk_thread_flag(p, TIF_FREEZE); + clear_freeze_flag(p); task_unlock(p); return 0; } @@ -115,10 +118,19 @@ static inline int freezer_should_skip(struct task_struct *p) return !!(p->flags & PF_FREEZER_SKIP); } +/* + * Tell the freezer that the current task should be frozen by it + */ +static inline void set_freezable(void) +{ + current->flags &= ~PF_NOFREEZE; +} + #else static inline int frozen(struct task_struct *p) { return 0; } static inline int freezing(struct task_struct *p) { return 0; } -static inline void freeze(struct task_struct *p) { BUG(); } +static inline void set_freeze_flag(struct task_struct *p) {} +static inline void clear_freeze_flag(struct task_struct *p) {} static inline int thaw_process(struct task_struct *p) { return 1; } static inline void refrigerator(void) {} @@ -130,4 +142,7 @@ static inline int try_to_freeze(void) { return 0; } static inline void freezer_do_not_count(void) {} static inline void freezer_count(void) {} static inline int freezer_should_skip(struct task_struct *p) { return 0; } +static inline void set_freezable(void) {} #endif + +#endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/fs.h b/include/linux/fs.h index e6878081027..d33beadd9a4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -283,11 +283,14 @@ extern int dir_notify_enable; #include <linux/init.h> #include <linux/pid.h> #include <linux/mutex.h> +#include <linux/sysctl.h> +#include <linux/capability.h> #include <asm/atomic.h> #include <asm/semaphore.h> #include <asm/byteorder.h> +struct export_operations; struct hd_geometry; struct iovec; struct nameidata; @@ -694,20 +697,26 @@ struct fown_struct { * Track a single file's readahead state */ struct file_ra_state { - unsigned long start; /* Current window */ - unsigned long size; - unsigned long flags; /* ra flags RA_FLAG_xxx*/ - unsigned long cache_hit; /* cache hit count*/ - unsigned long prev_index; /* Cache last read() position */ - unsigned long ahead_start; /* Ahead window */ - unsigned long ahead_size; + pgoff_t start; /* where readahead started */ + unsigned long size; /* # of readahead pages */ + unsigned long async_size; /* do asynchronous readahead when + there are only # of pages ahead */ + unsigned long ra_pages; /* Maximum readahead window */ unsigned long mmap_hit; /* Cache hit stat for mmap accesses */ unsigned long mmap_miss; /* Cache miss stat for mmap accesses */ + unsigned long prev_index; /* Cache last read() position */ unsigned int prev_offset; /* Offset where last read() ended in a page */ }; -#define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */ -#define RA_FLAG_INCACHE 0x02 /* file is already in cache */ + +/* + * Check if @index falls in the readahead windows. + */ +static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) +{ + return (index >= ra->start && + index < ra->start + ra->size); +} struct file { /* @@ -859,7 +868,7 @@ extern void locks_init_lock(struct file_lock *); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_flock(struct file *); -extern int posix_test_lock(struct file *, struct file_lock *); +extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file *, struct file_lock *); @@ -870,6 +879,7 @@ extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int setlease(struct file *, long, struct file_lock **); +extern int vfs_setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); @@ -988,6 +998,9 @@ enum { #define put_fs_excl() atomic_dec(¤t->fs_excl) #define has_fs_excl() atomic_read(¤t->fs_excl) +#define is_owner_or_cap(inode) \ + ((current->fsuid == (inode)->i_uid) || capable(CAP_FOWNER)) + /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); extern void unlock_super(struct super_block *); @@ -1116,6 +1129,7 @@ struct file_operations { int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); + int (*setlease)(struct file *, long, struct file_lock **); }; struct inode_operations { @@ -1141,6 +1155,8 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); void (*truncate_range)(struct inode *, loff_t, loff_t); + long (*fallocate)(struct inode *inode, int mode, loff_t offset, + loff_t len); }; struct seq_file; @@ -1277,119 +1293,6 @@ static inline void file_accessed(struct file *file) int sync_inode(struct inode *inode, struct writeback_control *wbc); -/** - * struct export_operations - for nfsd to communicate with file systems - * @decode_fh: decode a file handle fragment and return a &struct dentry - * @encode_fh: encode a file handle fragment from a dentry - * @get_name: find the name for a given inode in a given directory - * @get_parent: find the parent of a given directory - * @get_dentry: find a dentry for the inode given a file handle sub-fragment - * @find_exported_dentry: - * set by the exporting module to a standard helper function. - * - * Description: - * The export_operations structure provides a means for nfsd to communicate - * with a particular exported file system - particularly enabling nfsd and - * the filesystem to co-operate when dealing with file handles. - * - * export_operations contains two basic operation for dealing with file - * handles, decode_fh() and encode_fh(), and allows for some other - * operations to be defined which standard helper routines use to get - * specific information from the filesystem. - * - * nfsd encodes information use to determine which filesystem a filehandle - * applies to in the initial part of the file handle. The remainder, termed - * a file handle fragment, is controlled completely by the filesystem. The - * standard helper routines assume that this fragment will contain one or - * two sub-fragments, one which identifies the file, and one which may be - * used to identify the (a) directory containing the file. - * - * In some situations, nfsd needs to get a dentry which is connected into a - * specific part of the file tree. To allow for this, it passes the - * function acceptable() together with a @context which can be used to see - * if the dentry is acceptable. As there can be multiple dentrys for a - * given file, the filesystem should check each one for acceptability before - * looking for the next. As soon as an acceptable one is found, it should - * be returned. - * - * decode_fh: - * @decode_fh is given a &struct super_block (@sb), a file handle fragment - * (@fh, @fh_len) and an acceptability testing function (@acceptable, - * @context). It should return a &struct dentry which refers to the same - * file that the file handle fragment refers to, and which passes the - * acceptability test. If it cannot, it should return a %NULL pointer if - * the file was found but no acceptable &dentries were available, or a - * %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or - * %ENOMEM). - * - * encode_fh: - * @encode_fh should store in the file handle fragment @fh (using at most - * @max_len bytes) information that can be used by @decode_fh to recover the - * file refered to by the &struct dentry @de. If the @connectable flag is - * set, the encode_fh() should store sufficient information so that a good - * attempt can be made to find not only the file but also it's place in the - * filesystem. This typically means storing a reference to de->d_parent in - * the filehandle fragment. encode_fh() should return the number of bytes - * stored or a negative error code such as %-ENOSPC - * - * get_name: - * @get_name should find a name for the given @child in the given @parent - * directory. The name should be stored in the @name (with the - * understanding that it is already pointing to a a %NAME_MAX+1 sized - * buffer. get_name() should return %0 on success, a negative error code - * or error. @get_name will be called without @parent->i_mutex held. - * - * get_parent: - * @get_parent should find the parent directory for the given @child which - * is also a directory. In the event that it cannot be found, or storage - * space cannot be allocated, a %ERR_PTR should be returned. - * - * get_dentry: - * Given a &super_block (@sb) and a pointer to a file-system specific inode - * identifier, possibly an inode number, (@inump) get_dentry() should find - * the identified inode and return a dentry for that inode. Any suitable - * dentry can be returned including, if necessary, a new dentry created with - * d_alloc_root. The caller can then find any other extant dentrys by - * following the d_alias links. If a new dentry was created using - * d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry - * should be d_rehash()ed. - * - * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code - * can be returned. The @inump will be whatever was passed to - * nfsd_find_fh_dentry() in either the @obj or @parent parameters. - * - * Locking rules: - * get_parent is called with child->d_inode->i_mutex down - * get_name is not (which is possibly inconsistent) - */ - -struct export_operations { - struct dentry *(*decode_fh)(struct super_block *sb, __u32 *fh, int fh_len, int fh_type, - int (*acceptable)(void *context, struct dentry *de), - void *context); - int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len, - int connectable); - - /* the following are only called from the filesystem itself */ - int (*get_name)(struct dentry *parent, char *name, - struct dentry *child); - struct dentry * (*get_parent)(struct dentry *child); - struct dentry * (*get_dentry)(struct super_block *sb, void *inump); - - /* This is set by the exporting module to a standard helper */ - struct dentry * (*find_exported_dentry)( - struct super_block *sb, void *obj, void *parent, - int (*acceptable)(void *context, struct dentry *de), - void *context); - - -}; - -extern struct dentry * -find_exported_dentry(struct super_block *sb, void *obj, void *parent, - int (*acceptable)(void *context, struct dentry *de), - void *context); - struct file_system_type { const char *name; int fs_flags; @@ -1526,7 +1429,7 @@ extern void putname(const char *name); #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); -extern int unregister_blkdev(unsigned int, const char *); +extern void unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); @@ -1566,7 +1469,7 @@ extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int register_chrdev(unsigned int, const char *, const struct file_operations *); -extern int unregister_chrdev(unsigned int, const char *); +extern void unregister_chrdev(unsigned int, const char *); extern void unregister_chrdev_region(dev_t, unsigned); extern int chrdev_open(struct inode *, struct file *); extern void chrdev_show(struct seq_file *,off_t); @@ -2050,5 +1953,9 @@ static inline void free_secdata(void *secdata) { } #endif /* CONFIG_SECURITY */ +int proc_nr_files(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + + #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 12e631f0fb7..1831b196c70 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -53,6 +53,7 @@ struct gianfar_platform_data { u32 bus_id; u32 phy_id; u8 mac_addr[6]; + phy_interface_t interface; }; struct gianfar_mdio_data { @@ -112,7 +113,7 @@ struct fsl_usb2_platform_data { struct fsl_spi_platform_data { u32 initial_spmode; /* initial SPMODE value */ u16 bus_num; - + bool qe_mode; /* board specific information */ u16 max_chipselect; void (*activate_cs)(u8 cs, u8 polarity); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0d2ef0b082a..bc68dd9a6d4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,6 +30,9 @@ struct vm_area_struct; * cannot handle allocation failures. * * __GFP_NORETRY: The VM implementation must not retry indefinitely. + * + * __GFP_MOVABLE: Flag that this page will be movable by the page migration + * mechanism or reclaimed */ #define __GFP_WAIT ((__force gfp_t)0x10u) /* Can wait and reschedule? */ #define __GFP_HIGH ((__force gfp_t)0x20u) /* Should access emergency pools? */ @@ -45,6 +48,7 @@ struct vm_area_struct; #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */ #define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */ +#define __GFP_MOVABLE ((__force gfp_t)0x80000u) /* Page is movable */ #define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) @@ -53,7 +57,8 @@ struct vm_area_struct; #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \ __GFP_NOFAIL|__GFP_NORETRY|__GFP_COMP| \ - __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE) + __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE| \ + __GFP_MOVABLE) /* This equals 0, but use constants in case they ever change */ #define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) @@ -65,6 +70,15 @@ struct vm_area_struct; #define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \ __GFP_HIGHMEM) +#define GFP_HIGHUSER_MOVABLE (__GFP_WAIT | __GFP_IO | __GFP_FS | \ + __GFP_HARDWALL | __GFP_HIGHMEM | \ + __GFP_MOVABLE) +#define GFP_NOFS_PAGECACHE (__GFP_WAIT | __GFP_IO | __GFP_MOVABLE) +#define GFP_USER_PAGECACHE (__GFP_WAIT | __GFP_IO | __GFP_FS | \ + __GFP_HARDWALL | __GFP_MOVABLE) +#define GFP_HIGHUSER_PAGECACHE (__GFP_WAIT | __GFP_IO | __GFP_FS | \ + __GFP_HARDWALL | __GFP_HIGHMEM | \ + __GFP_MOVABLE) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) @@ -92,6 +106,9 @@ static inline enum zone_type gfp_zone(gfp_t flags) if (flags & __GFP_DMA32) return ZONE_DMA32; #endif + if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) == + (__GFP_HIGHMEM | __GFP_MOVABLE)) + return ZONE_MOVABLE; #ifdef CONFIG_HIGHMEM if (flags & __GFP_HIGHMEM) return ZONE_HIGHMEM; diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 98e2cce996a..1fcb0033179 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -73,10 +73,27 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) } #ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +/** + * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags + * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE + * @vma: The VMA the page is to be allocated for + * @vaddr: The virtual address the page will be inserted into + * + * This function will allocate a page for a VMA but the caller is expected + * to specify via movableflags whether the page will be movable in the + * future or not + * + * An architecture may override this function by defining + * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own + * implementation. + */ static inline struct page * -alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr) +__alloc_zeroed_user_highpage(gfp_t movableflags, + struct vm_area_struct *vma, + unsigned long vaddr) { - struct page *page = alloc_page_vma(GFP_HIGHUSER, vma, vaddr); + struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags, + vma, vaddr); if (page) clear_user_highpage(page, vaddr); @@ -85,6 +102,21 @@ alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr) } #endif +/** + * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move + * @vma: The VMA the page is to be allocated for + * @vaddr: The virtual address the page will be inserted into + * + * This function will allocate a page for a VMA that the caller knows will + * be able to migrate in the future using move_pages() or reclaimed + */ +static inline struct page * +alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, + unsigned long vaddr) +{ + return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr); +} + static inline void clear_highpage(struct page *page) { void *kaddr = kmap_atomic(page, KM_USER0); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2c13715e9dd..49b7053043a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -15,6 +15,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) } int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); @@ -29,6 +30,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; +extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0e0fedd2039..260d6d76c5f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -50,14 +50,14 @@ */ #define JBD_DEFAULT_MAX_COMMIT_AGE 5 -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG /* * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless - * CONFIG_JBD_DEBUG is on. + * CONFIG_JBD2_DEBUG is on. */ #define JBD_EXPENSIVE_CHECKING -extern int jbd2_journal_enable_debug; +extern u8 jbd2_journal_enable_debug; #define jbd_debug(n, f, a...) \ do { \ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 5f06527dca2..f73de6fb5c6 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -7,9 +7,9 @@ #include <linux/errno.h> -#define KSYM_NAME_LEN 127 -#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + KSYM_NAME_LEN + \ - 2*(BITS_PER_LONG*3/10) + MODULE_NAME_LEN + 1) +#define KSYM_NAME_LEN 128 +#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ + 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) #ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7a485250591..1eb9cde550c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -210,6 +210,7 @@ extern enum system_states { #define TAINT_MACHINE_CHECK (1<<4) #define TAINT_BAD_PAGE (1<<5) #define TAINT_USER (1<<6) +#define TAINT_DIE (1<<7) extern void dump_stack(void); diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h index aea34e74c49..8c4350a9ed8 100644 --- a/include/linux/kernelcapi.h +++ b/include/linux/kernelcapi.h @@ -64,7 +64,7 @@ struct capi20_appl { unsigned long nrecvdatapkt; unsigned long nsentctlpkt; unsigned long nsentdatapkt; - struct semaphore recv_sem; + struct mutex recv_mtx; struct sk_buff_head recv_queue; struct work_struct recv_work; int release_in_progress; diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 10f505c8431..5dc13848891 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -36,13 +36,57 @@ static inline int request_module(const char * name, ...) { return -ENOSYS; } #define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x))) struct key; -extern int call_usermodehelper_keys(char *path, char *argv[], char *envp[], - struct key *session_keyring, int wait); +struct file; +struct subprocess_info; + +/* Allocate a subprocess_info structure */ +struct subprocess_info *call_usermodehelper_setup(char *path, + char **argv, char **envp); + +/* Set various pieces of state into the subprocess_info structure */ +void call_usermodehelper_setkeys(struct subprocess_info *info, + struct key *session_keyring); +int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info, + struct file **filp); +void call_usermodehelper_setcleanup(struct subprocess_info *info, + void (*cleanup)(char **argv, char **envp)); + +enum umh_wait { + UMH_NO_WAIT = -1, /* don't wait at all */ + UMH_WAIT_EXEC = 0, /* wait for the exec, but not the process */ + UMH_WAIT_PROC = 1, /* wait for the process to complete */ +}; + +/* Actually execute the sub-process */ +int call_usermodehelper_exec(struct subprocess_info *info, enum umh_wait wait); + +/* Free the subprocess_info. This is only needed if you're not going + to call call_usermodehelper_exec */ +void call_usermodehelper_freeinfo(struct subprocess_info *info); static inline int -call_usermodehelper(char *path, char **argv, char **envp, int wait) +call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) { - return call_usermodehelper_keys(path, argv, envp, NULL, wait); + struct subprocess_info *info; + + info = call_usermodehelper_setup(path, argv, envp); + if (info == NULL) + return -ENOMEM; + return call_usermodehelper_exec(info, wait); +} + +static inline int +call_usermodehelper_keys(char *path, char **argv, char **envp, + struct key *session_keyring, enum umh_wait wait) +{ + struct subprocess_info *info; + + info = call_usermodehelper_setup(path, argv, envp); + if (info == NULL) + return -ENOMEM; + + call_usermodehelper_setkeys(info, session_keyring); + return call_usermodehelper_exec(info, wait); } extern void usermodehelper_init(void); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 06cbf41d32d..aa2fe22b1ba 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -36,15 +36,24 @@ extern char uevent_helper[]; /* counter to tag the uevent, read only except for the kobject core */ extern u64 uevent_seqnum; -/* the actions here must match the proper string in lib/kobject_uevent.c */ -typedef int __bitwise kobject_action_t; +/* + * The actions here must match the index to the string array + * in lib/kobject_uevent.c + * + * Do not add new actions here without checking with the driver-core + * maintainers. Action strings are not meant to express subsystem + * or device specific properties. In most cases you want to send a + * kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event + * specific variables added to the event environment. + */ enum kobject_action { - KOBJ_ADD = (__force kobject_action_t) 0x01, /* exclusive to core */ - KOBJ_REMOVE = (__force kobject_action_t) 0x02, /* exclusive to core */ - KOBJ_CHANGE = (__force kobject_action_t) 0x03, /* device state change */ - KOBJ_OFFLINE = (__force kobject_action_t) 0x04, /* device offline */ - KOBJ_ONLINE = (__force kobject_action_t) 0x05, /* device online */ - KOBJ_MOVE = (__force kobject_action_t) 0x06, /* device move */ + KOBJ_ADD, + KOBJ_REMOVE, + KOBJ_CHANGE, + KOBJ_MOVE, + KOBJ_ONLINE, + KOBJ_OFFLINE, + KOBJ_MAX }; struct kobject { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 23adf6075ae..51464d12a4e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -116,9 +116,12 @@ struct kprobe { */ struct jprobe { struct kprobe kp; - kprobe_opcode_t *entry; /* probe handling code to jump to */ + void *entry; /* probe handling code to jump to */ }; +/* For backward compatibility with old code using JPROBE_ENTRY() */ +#define JPROBE_ENTRY(handler) (handler) + DECLARE_PER_CPU(struct kprobe *, current_kprobe); DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -211,6 +214,7 @@ int longjmp_break_handler(struct kprobe *, struct pt_regs *); int register_jprobe(struct jprobe *p); void unregister_jprobe(struct jprobe *p); void jprobe_return(void); +unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); void unregister_kretprobe(struct kretprobe *rp); diff --git a/include/linux/lguest.h b/include/linux/lguest.h new file mode 100644 index 00000000000..500aace21ca --- /dev/null +++ b/include/linux/lguest.h @@ -0,0 +1,85 @@ +/* Things the lguest guest needs to know. Note: like all lguest interfaces, + * this is subject to wild and random change between versions. */ +#ifndef _ASM_LGUEST_H +#define _ASM_LGUEST_H + +#ifndef __ASSEMBLY__ +#include <asm/irq.h> + +#define LHCALL_FLUSH_ASYNC 0 +#define LHCALL_LGUEST_INIT 1 +#define LHCALL_CRASH 2 +#define LHCALL_LOAD_GDT 3 +#define LHCALL_NEW_PGTABLE 4 +#define LHCALL_FLUSH_TLB 5 +#define LHCALL_LOAD_IDT_ENTRY 6 +#define LHCALL_SET_STACK 7 +#define LHCALL_TS 8 +#define LHCALL_SET_CLOCKEVENT 9 +#define LHCALL_HALT 10 +#define LHCALL_GET_WALLCLOCK 11 +#define LHCALL_BIND_DMA 12 +#define LHCALL_SEND_DMA 13 +#define LHCALL_SET_PTE 14 +#define LHCALL_SET_PMD 15 +#define LHCALL_LOAD_TLS 16 + +#define LG_CLOCK_MIN_DELTA 100UL +#define LG_CLOCK_MAX_DELTA ULONG_MAX + +#define LGUEST_TRAP_ENTRY 0x1F + +static inline unsigned long +hcall(unsigned long call, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) + : "=a"(call) + : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3) + : "memory"); + return call; +} + +void async_hcall(unsigned long call, + unsigned long arg1, unsigned long arg2, unsigned long arg3); + +/* Can't use our min() macro here: needs to be a constant */ +#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) + +#define LHCALL_RING_SIZE 64 +struct hcall_ring +{ + u32 eax, edx, ebx, ecx; +}; + +/* All the good stuff happens here: guest registers it with LGUEST_INIT */ +struct lguest_data +{ +/* Fields which change during running: */ + /* 512 == enabled (same as eflags) */ + unsigned int irq_enabled; + /* Interrupts blocked by guest. */ + DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS); + + /* Virtual address of page fault. */ + unsigned long cr2; + + /* Async hypercall ring. 0xFF == done, 0 == pending. */ + u8 hcall_status[LHCALL_RING_SIZE]; + struct hcall_ring hcalls[LHCALL_RING_SIZE]; + +/* Fields initialized by the hypervisor at boot: */ + /* Memory not to try to access */ + unsigned long reserve_mem; + /* ID of this guest (used by network driver to set ethernet address) */ + u16 guestid; + /* KHz for the TSC clock. */ + u32 tsc_khz; + +/* Fields initialized by the guest at boot: */ + /* Instruction range to suppress interrupts even if enabled */ + unsigned long noirq_start, noirq_end; +}; +extern struct lguest_data lguest_data; +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_LGUEST_H */ diff --git a/include/linux/lguest_bus.h b/include/linux/lguest_bus.h new file mode 100644 index 00000000000..c9b4e05fee4 --- /dev/null +++ b/include/linux/lguest_bus.h @@ -0,0 +1,48 @@ +#ifndef _ASM_LGUEST_DEVICE_H +#define _ASM_LGUEST_DEVICE_H +/* Everything you need to know about lguest devices. */ +#include <linux/device.h> +#include <linux/lguest.h> +#include <linux/lguest_launcher.h> + +struct lguest_device { + /* Unique busid, and index into lguest_page->devices[] */ + unsigned int index; + + struct device dev; + + /* Driver can hang data off here. */ + void *private; +}; + +/* By convention, each device can use irq index+1 if it wants to. */ +static inline int lgdev_irq(const struct lguest_device *dev) +{ + return dev->index + 1; +} + +/* dma args must not be vmalloced! */ +void lguest_send_dma(unsigned long key, struct lguest_dma *dma); +int lguest_bind_dma(unsigned long key, struct lguest_dma *dmas, + unsigned int num, u8 irq); +void lguest_unbind_dma(unsigned long key, struct lguest_dma *dmas); + +/* Map the virtual device space */ +void *lguest_map(unsigned long phys_addr, unsigned long pages); +void lguest_unmap(void *); + +struct lguest_driver { + const char *name; + struct module *owner; + u16 device_type; + int (*probe)(struct lguest_device *dev); + void (*remove)(struct lguest_device *dev); + + struct device_driver drv; +}; + +extern int register_lguest_driver(struct lguest_driver *drv); +extern void unregister_lguest_driver(struct lguest_driver *drv); + +extern struct lguest_device_desc *lguest_devices; /* Just past max_pfn */ +#endif /* _ASM_LGUEST_DEVICE_H */ diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h new file mode 100644 index 00000000000..0ba414a40c8 --- /dev/null +++ b/include/linux/lguest_launcher.h @@ -0,0 +1,73 @@ +#ifndef _ASM_LGUEST_USER +#define _ASM_LGUEST_USER +/* Everything the "lguest" userspace program needs to know. */ +/* They can register up to 32 arrays of lguest_dma. */ +#define LGUEST_MAX_DMA 32 +/* At most we can dma 16 lguest_dma in one op. */ +#define LGUEST_MAX_DMA_SECTIONS 16 + +/* How many devices? Assume each one wants up to two dma arrays per device. */ +#define LGUEST_MAX_DEVICES (LGUEST_MAX_DMA/2) + +struct lguest_dma +{ + /* 0 if free to be used, filled by hypervisor. */ + u32 used_len; + unsigned long addr[LGUEST_MAX_DMA_SECTIONS]; + u16 len[LGUEST_MAX_DMA_SECTIONS]; +}; + +struct lguest_block_page +{ + /* 0 is a read, 1 is a write. */ + int type; + u32 sector; /* Offset in device = sector * 512. */ + u32 bytes; /* Length expected to be read/written in bytes */ + /* 0 = pending, 1 = done, 2 = done, error */ + int result; + u32 num_sectors; /* Disk length = num_sectors * 512 */ +}; + +/* There is a shared page of these. */ +struct lguest_net +{ + /* Simply the mac address (with multicast bit meaning promisc). */ + unsigned char mac[6]; +}; + +/* Where the Host expects the Guest to SEND_DMA console output to. */ +#define LGUEST_CONSOLE_DMA_KEY 0 + +/* We have a page of these descriptors in the lguest_device page. */ +struct lguest_device_desc { + u16 type; +#define LGUEST_DEVICE_T_CONSOLE 1 +#define LGUEST_DEVICE_T_NET 2 +#define LGUEST_DEVICE_T_BLOCK 3 + + u16 features; +#define LGUEST_NET_F_NOCSUM 0x4000 /* Don't bother checksumming */ +#define LGUEST_DEVICE_F_RANDOMNESS 0x8000 /* IRQ is fairly random */ + + u16 status; +/* 256 and above are device specific. */ +#define LGUEST_DEVICE_S_ACKNOWLEDGE 1 /* We have seen device. */ +#define LGUEST_DEVICE_S_DRIVER 2 /* We have found a driver */ +#define LGUEST_DEVICE_S_DRIVER_OK 4 /* Driver says OK! */ +#define LGUEST_DEVICE_S_REMOVED 8 /* Device has gone away. */ +#define LGUEST_DEVICE_S_REMOVED_ACK 16 /* Driver has been told. */ +#define LGUEST_DEVICE_S_FAILED 128 /* Something actually failed */ + + u16 num_pages; + u32 pfn; +}; + +/* Write command first word is a request. */ +enum lguest_req +{ + LHREQ_INITIALIZE, /* + pfnlimit, pgdir, start, pageoffset */ + LHREQ_GETDMA, /* + addr (returns &lguest_dma, irq in ->used_len) */ + LHREQ_IRQ, /* + irq */ + LHREQ_BREAK, /* + on/off flag (on blocks until someone does off) */ +}; +#endif /* _ASM_LGUEST_USER */ diff --git a/include/linux/limits.h b/include/linux/limits.h index eaf2e099f12..2d0f94162fb 100644 --- a/include/linux/limits.h +++ b/include/linux/limits.h @@ -5,8 +5,6 @@ #define NGROUPS_MAX 65536 /* supplemental group IDs are available */ #define ARG_MAX 131072 /* # bytes of args + environ for exec() */ -#define CHILD_MAX 999 /* no limit :-) */ -#define OPEN_MAX 256 /* # open files a process may have */ #define LINK_MAX 127 /* # links a file may have */ #define MAX_CANON 255 /* size of the canonical input queue */ #define MAX_INPUT 255 /* size of the type-ahead buffer */ diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index 9c01bde5bf1..08a92969c76 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -33,5 +33,13 @@ struct linux_logo { }; extern const struct linux_logo *fb_find_logo(int depth); +#ifdef CONFIG_FB_LOGO_EXTRA +extern void fb_append_extra_logo(const struct linux_logo *logo, + unsigned int n); +#else +static inline void fb_append_extra_logo(const struct linux_logo *logo, + unsigned int n) +{} +#endif #endif /* _LINUX_LINUX_LOGO_H */ diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 246de1d84a2..6f1637c61e1 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -27,6 +27,7 @@ struct nlmsvc_binding { struct nfs_fh *, struct file **); void (*fclose)(struct file *); + unsigned long (*get_grace_period)(void); }; extern struct nlmsvc_binding * nlmsvc_ops; @@ -38,4 +39,12 @@ extern int nlmclnt_proc(struct inode *, int, struct file_lock *); extern int lockd_up(int proto); extern void lockd_down(void); +unsigned long get_nfs_grace_period(void); + +#ifdef CONFIG_NFSD_V4 +unsigned long get_nfs4_grace_period(void); +#else +static inline unsigned long get_nfs4_grace_period(void) {return 0;} +#endif + #endif /* LINUX_LOCKD_BIND_H */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 14c937d345c..0e843bf6587 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -1,7 +1,8 @@ /* * Runtime locking correctness validator * - * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> * * see Documentation/lockdep-design.txt for more details. */ @@ -9,6 +10,7 @@ #define __LINUX_LOCKDEP_H struct task_struct; +struct lockdep_map; #ifdef CONFIG_LOCKDEP @@ -114,8 +116,44 @@ struct lock_class { const char *name; int name_version; + +#ifdef CONFIG_LOCK_STAT + unsigned long contention_point[4]; +#endif +}; + +#ifdef CONFIG_LOCK_STAT +struct lock_time { + s64 min; + s64 max; + s64 total; + unsigned long nr; +}; + +enum bounce_type { + bounce_acquired_write, + bounce_acquired_read, + bounce_contended_write, + bounce_contended_read, + nr_bounce_types, + + bounce_acquired = bounce_acquired_write, + bounce_contended = bounce_contended_write, }; +struct lock_class_stats { + unsigned long contention_point[4]; + struct lock_time read_waittime; + struct lock_time write_waittime; + struct lock_time read_holdtime; + struct lock_time write_holdtime; + unsigned long bounces[nr_bounce_types]; +}; + +struct lock_class_stats lock_stats(struct lock_class *class); +void clear_lock_stats(struct lock_class *class); +#endif + /* * Map the lock object (the lock instance) to the lock-class object. * This is embedded into specific lock instances: @@ -124,6 +162,9 @@ struct lockdep_map { struct lock_class_key *key; struct lock_class *class_cache; const char *name; +#ifdef CONFIG_LOCK_STAT + int cpu; +#endif }; /* @@ -165,6 +206,10 @@ struct held_lock { unsigned long acquire_ip; struct lockdep_map *instance; +#ifdef CONFIG_LOCK_STAT + u64 waittime_stamp; + u64 holdtime_stamp; +#endif /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' @@ -281,6 +326,30 @@ struct lock_class_key { }; #endif /* !LOCKDEP */ +#ifdef CONFIG_LOCK_STAT + +extern void lock_contended(struct lockdep_map *lock, unsigned long ip); +extern void lock_acquired(struct lockdep_map *lock); + +#define LOCK_CONTENDED(_lock, try, lock) \ +do { \ + if (!try(_lock)) { \ + lock_contended(&(_lock)->dep_map, _RET_IP_); \ + lock(_lock); \ + } \ + lock_acquired(&(_lock)->dep_map); \ +} while (0) + +#else /* CONFIG_LOCK_STAT */ + +#define lock_contended(lockdep_map, ip) do {} while (0) +#define lock_acquired(lockdep_map) do {} while (0) + +#define LOCK_CONTENDED(_lock, try, lock) \ + lock(_lock) + +#endif /* CONFIG_LOCK_STAT */ + #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_GENERIC_HARDIRQS) extern void early_init_irq_lock_class(void); #else diff --git a/include/linux/magic.h b/include/linux/magic.h index 9d713c03e3d..36cc20dfd14 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -13,7 +13,6 @@ #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 -#define KVMFS_SUPER_MAGIC 0x19700426 #define ANON_INODE_FS_MAGIC 0x09041934 #define MINIX_SUPER_MAGIC 0x137F /* original minix fs */ diff --git a/include/linux/major.h b/include/linux/major.h index 7e7c9093919..0cb98053537 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -158,6 +158,8 @@ #define VXSPEC_MAJOR 200 /* VERITAS volume config driver */ #define VXDMP_MAJOR 201 /* VERITAS volume multipath driver */ +#define XENVBD_MAJOR 202 /* Xen virtual block device */ + #define MSR_MAJOR 202 #define CPUID_MAJOR 203 diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index daabb3aa1ec..e147cf50529 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -159,7 +159,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p); extern struct mempolicy default_policy; extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr); + unsigned long addr, gfp_t gfp_flags); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -256,9 +256,9 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p) #define set_cpuset_being_rebound(x) do {} while (0) static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, gfp_t gfp_flags) { - return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER); + return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags); } static inline int do_migrate_pages(struct mm_struct *mm, diff --git a/include/linux/mm.h b/include/linux/mm.h index 97d0cddfd22..c456c3a1c28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -168,6 +168,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ +#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ + #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif @@ -190,6 +192,30 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; +#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ +#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ + + +/* + * vm_fault is filled by the the pagefault handler and passed to the vma's + * ->fault function. The vma's ->fault is responsible for returning a bitmask + * of VM_FAULT_xxx flags that give details about how the fault was handled. + * + * pgoff should be used in favour of virtual_address, if possible. If pgoff + * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear + * mapping support. + */ +struct vm_fault { + unsigned int flags; /* FAULT_FLAG_xxx flags */ + pgoff_t pgoff; /* Logical page offset based on vma */ + void __user *virtual_address; /* Faulting virtual address */ + + struct page *page; /* ->fault handlers should return a + * page here, unless VM_FAULT_NOPAGE + * is set (which is also implied by + * VM_FAULT_ERROR). + */ +}; /* * These are the virtual MM functions - opening of an area, closing and @@ -199,9 +225,11 @@ extern pgprot_t protection_map[16]; struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); - struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type); - unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address); - int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock); + int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); + struct page *(*nopage)(struct vm_area_struct *area, + unsigned long address, int *type); + unsigned long (*nopfn)(struct vm_area_struct *area, + unsigned long address); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -599,6 +627,7 @@ static inline struct address_space *page_mapping(struct page *page) { struct address_space *mapping = page->mapping; + VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; #ifdef CONFIG_SLUB @@ -654,7 +683,6 @@ static inline int page_mapped(struct page *page) */ #define NOPAGE_SIGBUS (NULL) #define NOPAGE_OOM ((struct page *) (-1)) -#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */ /* * Error return values for the *_nopfn functions @@ -668,16 +696,18 @@ static inline int page_mapped(struct page *page) * Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. */ -#define VM_FAULT_OOM 0x00 -#define VM_FAULT_SIGBUS 0x01 -#define VM_FAULT_MINOR 0x02 -#define VM_FAULT_MAJOR 0x03 - -/* - * Special case for get_user_pages. - * Must be in a distinct bit from the above VM_FAULT_ flags. - */ -#define VM_FAULT_WRITE 0x10 + +#define VM_FAULT_MINOR 0 /* For backwards compat. Remove me quickly. */ + +#define VM_FAULT_OOM 0x0001 +#define VM_FAULT_SIGBUS 0x0002 +#define VM_FAULT_MAJOR 0x0004 +#define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ + +#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ +#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ + +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS) #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) @@ -761,20 +791,10 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern int vmtruncate(struct inode * inode, loff_t offset); extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); -extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot); -extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot); #ifdef CONFIG_MMU -extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, +extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); - -static inline int handle_mm_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - int write_access) -{ - return __handle_mm_fault(mm, vma, address, write_access) & - (~VM_FAULT_WRITE); -} #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -788,7 +808,6 @@ static inline int handle_mm_fault(struct mm_struct *mm, extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); -void install_arg_page(struct vm_area_struct *, struct page *, unsigned long); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); @@ -805,32 +824,42 @@ int FASTCALL(set_page_dirty(struct page *page)); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); +extern unsigned long move_page_tables(struct vm_area_struct *vma, + unsigned long old_addr, struct vm_area_struct *new_vma, + unsigned long new_addr, unsigned long len); extern unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr); +extern int mprotect_fixup(struct vm_area_struct *vma, + struct vm_area_struct **pprev, unsigned long start, + unsigned long end, unsigned long newflags); /* - * Prototype to add a shrinker callback for ageable caches. - * - * These functions are passed a count `nr_to_scan' and a gfpmask. They should - * scan `nr_to_scan' objects, attempting to free them. + * A callback you can register to apply pressure to ageable caches. * - * The callback must return the number of objects which remain in the cache. + * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should + * look through the least-recently-used 'nr_to_scan' entries and + * attempt to free them up. It should return the number of objects + * which remain in the cache. If it returns -1, it means it cannot do + * any scanning at this time (eg. there is a risk of deadlock). * - * The callback will be passed nr_to_scan == 0 when the VM is querying the - * cache size, so a fastpath for that case is appropriate. - */ -typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask); - -/* - * Add an aging callback. The int is the number of 'seeks' it takes - * to recreate one of the objects that these functions age. + * The 'gfpmask' refers to the allocation we are currently trying to + * fulfil. + * + * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is + * querying the cache size, so a fastpath for that case is appropriate. */ +struct shrinker { + int (*shrink)(int nr_to_scan, gfp_t gfp_mask); + int seeks; /* seeks to recreate an obj */ -#define DEFAULT_SEEKS 2 -struct shrinker; -extern struct shrinker *set_shrinker(int, shrinker_t); -extern void remove_shrinker(struct shrinker *shrinker); + /* These are for internal use */ + struct list_head list; + long nr; /* objs pending delete */ +}; +#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ +extern void register_shrinker(struct shrinker *); +extern void unregister_shrinker(struct shrinker *); /* * Some shared mappigns will want the pages marked read-only @@ -1099,9 +1128,7 @@ extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); /* generic vm_area_ops exported for stackable file systems */ -extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *); -extern int filemap_populate(struct vm_area_struct *, unsigned long, - unsigned long, pgprot_t, unsigned long, int); +extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); /* mm/page-writeback.c */ int write_one_page(struct page *page, int wait); @@ -1116,13 +1143,20 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); -unsigned long page_cache_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); -void handle_ra_miss(struct address_space *mapping, - struct file_ra_state *ra, pgoff_t offset); + +void page_cache_sync_readahead(struct address_space *mapping, + struct file_ra_state *ra, + struct file *filp, + pgoff_t offset, + unsigned long size); + +void page_cache_async_readahead(struct address_space *mapping, + struct file_ra_state *ra, + struct file *filp, + struct page *pg, + pgoff_t offset, + unsigned long size); + unsigned long max_sane_readahead(unsigned long nr); /* Do stack extension */ @@ -1130,6 +1164,8 @@ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); #ifdef CONFIG_IA64 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #endif +extern int expand_stack_downwards(struct vm_area_struct *vma, + unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 04b1636a970..da8eb8ad9e9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -24,6 +24,14 @@ #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +/* + * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed + * costly to service. That is between allocation orders which should + * coelesce naturally under reasonable reclaim pressure and those which + * will not. + */ +#define PAGE_ALLOC_COSTLY_ORDER 3 + struct free_area { struct list_head free_list; unsigned long nr_free; @@ -146,6 +154,7 @@ enum zone_type { */ ZONE_HIGHMEM, #endif + ZONE_MOVABLE, MAX_NR_ZONES }; @@ -167,6 +176,7 @@ enum zone_type { + defined(CONFIG_ZONE_DMA32) \ + 1 \ + defined(CONFIG_HIGHMEM) \ + + 1 \ ) #if __ZONE_COUNT < 2 #define ZONES_SHIFT 0 @@ -499,10 +509,22 @@ static inline int populated_zone(struct zone *zone) return (!!zone->present_pages); } +extern int movable_zone; + +static inline int zone_movable_is_highmem(void) +{ +#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP) + return movable_zone == ZONE_HIGHMEM; +#else + return 0; +#endif +} + static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM - return (idx == ZONE_HIGHMEM); + return (idx == ZONE_HIGHMEM || + (idx == ZONE_MOVABLE && zone_movable_is_highmem())); #else return 0; #endif @@ -522,7 +544,9 @@ static inline int is_normal_idx(enum zone_type idx) static inline int is_highmem(struct zone *zone) { #ifdef CONFIG_HIGHMEM - return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM; + int zone_idx = zone - zone->zone_pgdat->node_zones; + return zone_idx == ZONE_HIGHMEM || + (zone_idx == ZONE_MOVABLE && zone_movable_is_highmem()); #else return 0; #endif diff --git a/include/linux/namei.h b/include/linux/namei.h index b7dd24917f0..6c38efbd810 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,8 +69,8 @@ extern int FASTCALL(__user_walk_fd(int dfd, const char __user *, unsigned, struc #define user_path_walk_link(name,nd) \ __user_walk_fd(AT_FDCWD, name, 0, nd) extern int FASTCALL(path_lookup(const char *, unsigned, struct nameidata *)); -extern int FASTCALL(path_walk(const char *, struct nameidata *)); -extern int FASTCALL(link_path_walk(const char *, struct nameidata *)); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct nameidata *); extern void path_release(struct nameidata *); extern void path_release_on_umount(struct nameidata *); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index da7a13c97eb..9820ca1e45e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1098,10 +1098,8 @@ extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern int dev_mc_sync(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); -extern void dev_mc_discard(struct net_device *dev); extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); -extern void __dev_addr_discard(struct dev_addr_list **list); extern void dev_set_promiscuity(struct net_device *dev, int inc); extern void dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); diff --git a/include/linux/netfilter_ipv4/ipt_iprange.h b/include/linux/netfilter_ipv4/ipt_iprange.h index 34ab0fb736e..a92fefc3c7e 100644 --- a/include/linux/netfilter_ipv4/ipt_iprange.h +++ b/include/linux/netfilter_ipv4/ipt_iprange.h @@ -1,6 +1,8 @@ #ifndef _IPT_IPRANGE_H #define _IPT_IPRANGE_H +#include <linux/types.h> + #define IPRANGE_SRC 0x01 /* Match source IP address */ #define IPRANGE_DST 0x02 /* Match destination IP address */ #define IPRANGE_SRC_INV 0x10 /* Negate the condition */ diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 9f62d6182d3..5cd19246909 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -42,6 +42,9 @@ #define NFSEXP_NOACL 0x8000 /* reserved for possible ACL related use */ #define NFSEXP_ALLFLAGS 0xFE3F +/* The flags that may vary depending on security flavor: */ +#define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ + | NFSEXP_ALLSQUASH) #ifdef __KERNEL__ @@ -64,6 +67,19 @@ struct nfsd4_fs_locations { int migrated; }; +/* + * We keep an array of pseudoflavors with the export, in order from most + * to least preferred. For the forseeable future, we don't expect more + * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3, + * spkm3i, and spkm3p (and using all 8 at once should be rare). + */ +#define MAX_SECINFO_LIST 8 + +struct exp_flavor_info { + u32 pseudoflavor; + u32 flags; +}; + struct svc_export { struct cache_head h; struct auth_domain * ex_client; @@ -76,6 +92,8 @@ struct svc_export { int ex_fsid; unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; + int ex_nflavors; + struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; }; /* an "export key" (expkey) maps a filehandlefragement to an @@ -95,10 +113,11 @@ struct svc_expkey { #define EX_SECURE(exp) (!((exp)->ex_flags & NFSEXP_INSECURE_PORT)) #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) -#define EX_RDONLY(exp) ((exp)->ex_flags & NFSEXP_READONLY) #define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE) #define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES) +int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp); +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp); /* * Function declarations @@ -112,13 +131,19 @@ struct svc_export * exp_get_by_name(struct auth_domain *clp, struct vfsmount *mnt, struct dentry *dentry, struct cache_req *reqp); +struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, + struct vfsmount *, + struct dentry *); struct svc_export * exp_parent(struct auth_domain *clp, struct vfsmount *mnt, struct dentry *dentry, struct cache_req *reqp); +struct svc_export * rqst_exp_parent(struct svc_rqst *, + struct vfsmount *mnt, + struct dentry *dentry); int exp_rootfh(struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); -__be32 exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); +__be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); __be32 nfserrno(int errno); extern struct cache_detail svc_export_cache; @@ -135,6 +160,7 @@ static inline void exp_get(struct svc_export *exp) extern struct svc_export * exp_find(struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp); +struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *); #endif /* __KERNEL__ */ diff --git a/include/linux/nfsd/interface.h b/include/linux/nfsd/interface.h deleted file mode 100644 index af0979704af..00000000000 --- a/include/linux/nfsd/interface.h +++ /dev/null @@ -1,13 +0,0 @@ -/* - * include/linux/nfsd/interface.h - * - * defines interface between nfsd and other bits of - * the kernel. Particularly filesystems (eventually). - * - * Copyright (C) 2000 Neil Brown <neilb@cse.unsw.edu.au> - */ - -#ifndef LINUX_NFSD_INTERFACE_H -#define LINUX_NFSD_INTERFACE_H - -#endif /* LINUX_NFSD_INTERFACE_H */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 72feac581aa..e452256d3f7 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -22,7 +22,6 @@ #include <linux/nfsd/export.h> #include <linux/nfsd/auth.h> #include <linux/nfsd/stats.h> -#include <linux/nfsd/interface.h> /* * nfsd version */ @@ -72,6 +71,9 @@ int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, const char *, int, struct svc_fh *); +__be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, + const char *, int, + struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, struct iattr *, int, time_t); #ifdef CONFIG_NFSD_V4 @@ -120,7 +122,8 @@ __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *); int nfsd_notify_change(struct inode *, struct iattr *); -__be32 nfsd_permission(struct svc_export *, struct dentry *, int); +__be32 nfsd_permission(struct svc_rqst *, struct svc_export *, + struct dentry *, int); int nfsd_sync_dir(struct dentry *dp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -149,6 +152,7 @@ extern int nfsd_max_blksize; * NFSv4 State */ #ifdef CONFIG_NFSD_V4 +extern unsigned int max_delegations; void nfs4_state_init(void); int nfs4_state_start(void); void nfs4_state_shutdown(void); @@ -236,6 +240,7 @@ void nfsd_lockd_shutdown(void); #define nfserr_badname __constant_htonl(NFSERR_BADNAME) #define nfserr_cb_path_down __constant_htonl(NFSERR_CB_PATH_DOWN) #define nfserr_locked __constant_htonl(NFSERR_LOCKED) +#define nfserr_wrongsec __constant_htonl(NFSERR_WRONGSEC) #define nfserr_replay_me __constant_htonl(NFSERR_REPLAY_ME) /* error codes for internal use */ diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index ab5c236bd9a..db348f74937 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -67,7 +67,7 @@ struct nfs4_cb_recall { int cbr_trunc; stateid_t cbr_stateid; u32 cbr_fhlen; - u32 cbr_fhval[NFS4_FHSIZE]; + char cbr_fhval[NFS4_FHSIZE]; struct nfs4_delegation *cbr_dp; }; @@ -224,6 +224,7 @@ struct nfs4_file { struct inode *fi_inode; u32 fi_id; /* used with stateowner->so_id * for stateid_hashtbl hash */ + bool fi_had_conflict; }; /* diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 09799bcee0a..1b653267133 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -293,6 +293,12 @@ struct nfsd4_rename { struct nfsd4_change_info rn_tinfo; /* response */ }; +struct nfsd4_secinfo { + u32 si_namelen; /* request */ + char *si_name; /* request */ + struct svc_export *si_exp; /* response */ +}; + struct nfsd4_setattr { stateid_t sa_stateid; /* request */ u32 sa_bmval[2]; /* request */ @@ -365,6 +371,7 @@ struct nfsd4_op { struct nfsd4_remove remove; struct nfsd4_rename rename; clientid_t renew; + struct nfsd4_secinfo secinfo; struct nfsd4_setattr setattr; struct nfsd4_setclientid setclientid; struct nfsd4_setclientid_confirm setclientid_confirm; diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 9431101bf87..be3f2bb6fcf 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -196,6 +196,8 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh, #define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ #define CPU_LOCK_ACQUIRE 0x0008 /* Acquire all hotcpu locks */ #define CPU_LOCK_RELEASE 0x0009 /* Release all hotcpu locks */ +#define CPU_DYING 0x000A /* CPU (unsigned)v not running any task, + * not handling interrupts, soon dead */ /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend * operation in progress @@ -208,6 +210,13 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh, #define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN) #define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN) #define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) +#define CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN) + +/* Hibernation and suspend events */ +#define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ +#define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ +#define PM_SUSPEND_PREPARE 0x0003 /* Going to suspend the system */ +#define PM_POST_SUSPEND 0x0004 /* Suspend finished */ #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ae2d79f2107..209d3a47f50 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -90,8 +90,12 @@ #define PG_reclaim 17 /* To be reclaimed asap */ #define PG_buddy 19 /* Page is free, on buddy lists */ +/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ +#define PG_readahead PG_reclaim /* Reminder to do async read-ahead */ + /* PG_owner_priv_1 users should have descriptive aliases */ #define PG_checked PG_owner_priv_1 /* Used by some filesystems */ +#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */ #if (BITS_PER_LONG > 32) /* @@ -170,6 +174,10 @@ static inline void SetPageUptodate(struct page *page) #define SetPageChecked(page) set_bit(PG_checked, &(page)->flags) #define ClearPageChecked(page) clear_bit(PG_checked, &(page)->flags) +#define PagePinned(page) test_bit(PG_pinned, &(page)->flags) +#define SetPagePinned(page) set_bit(PG_pinned, &(page)->flags) +#define ClearPagePinned(page) clear_bit(PG_pinned, &(page)->flags) + #define PageReserved(page) test_bit(PG_reserved, &(page)->flags) #define SetPageReserved(page) set_bit(PG_reserved, &(page)->flags) #define ClearPageReserved(page) clear_bit(PG_reserved, &(page)->flags) @@ -181,37 +189,15 @@ static inline void SetPageUptodate(struct page *page) #define __SetPagePrivate(page) __set_bit(PG_private, &(page)->flags) #define __ClearPagePrivate(page) __clear_bit(PG_private, &(page)->flags) +/* + * Only test-and-set exist for PG_writeback. The unconditional operators are + * risky: they bypass page accounting. + */ #define PageWriteback(page) test_bit(PG_writeback, &(page)->flags) -#define SetPageWriteback(page) \ - do { \ - if (!test_and_set_bit(PG_writeback, \ - &(page)->flags)) \ - inc_zone_page_state(page, NR_WRITEBACK); \ - } while (0) -#define TestSetPageWriteback(page) \ - ({ \ - int ret; \ - ret = test_and_set_bit(PG_writeback, \ - &(page)->flags); \ - if (!ret) \ - inc_zone_page_state(page, NR_WRITEBACK); \ - ret; \ - }) -#define ClearPageWriteback(page) \ - do { \ - if (test_and_clear_bit(PG_writeback, \ - &(page)->flags)) \ - dec_zone_page_state(page, NR_WRITEBACK); \ - } while (0) -#define TestClearPageWriteback(page) \ - ({ \ - int ret; \ - ret = test_and_clear_bit(PG_writeback, \ - &(page)->flags); \ - if (ret) \ - dec_zone_page_state(page, NR_WRITEBACK); \ - ret; \ - }) +#define TestSetPageWriteback(page) test_and_set_bit(PG_writeback, \ + &(page)->flags) +#define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback, \ + &(page)->flags) #define PageBuddy(page) test_bit(PG_buddy, &(page)->flags) #define __SetPageBuddy(page) __set_bit(PG_buddy, &(page)->flags) @@ -221,6 +207,10 @@ static inline void SetPageUptodate(struct page *page) #define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags) #define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags) +#define PageReadahead(page) test_bit(PG_readahead, &(page)->flags) +#define SetPageReadahead(page) set_bit(PG_readahead, &(page)->flags) +#define ClearPageReadahead(page) clear_bit(PG_readahead, &(page)->flags) + #define PageReclaim(page) test_bit(PG_reclaim, &(page)->flags) #define SetPageReclaim(page) set_bit(PG_reclaim, &(page)->flags) #define ClearPageReclaim(page) clear_bit(PG_reclaim, &(page)->flags) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2c7add16953..b15c6498fe6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -495,6 +495,8 @@ #define PCI_VENDOR_ID_AMD 0x1022 #define PCI_DEVICE_ID_AMD_K8_NB 0x1100 +#define PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP 0x1101 +#define PCI_DEVICE_ID_AMD_K8_NB_MEMCTL 0x1102 #define PCI_DEVICE_ID_AMD_K8_NB_MISC 0x1103 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 @@ -2209,6 +2211,7 @@ #define PCI_DEVICE_ID_INTEL_82915GM_IG 0x2592 #define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 #define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 +#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 #define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27A0 #define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27A2 #define PCI_DEVICE_ID_INTEL_ICH6_0 0x2640 diff --git a/include/linux/pm.h b/include/linux/pm.h index 273781c82e4..ad3cc2eb0d3 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -101,6 +101,7 @@ struct pm_dev */ extern void (*pm_idle)(void); extern void (*pm_power_off)(void); +extern void (*pm_power_off_prepare)(void); typedef int __bitwise suspend_state_t; @@ -284,8 +285,6 @@ extern int device_prepare_suspend(pm_message_t state); #define device_may_wakeup(dev) \ (device_can_wakeup(dev) && (dev)->power.should_wakeup) -extern int dpm_runtime_suspend(struct device *, pm_message_t); -extern void dpm_runtime_resume(struct device *); extern void __suspend_report_result(const char *function, void *fn, int ret); #define suspend_report_result(fn, ret) \ @@ -317,15 +316,6 @@ static inline int device_suspend(pm_message_t state) #define device_set_wakeup_enable(dev,val) do{}while(0) #define device_may_wakeup(dev) (0) -static inline int dpm_runtime_suspend(struct device * dev, pm_message_t state) -{ - return 0; -} - -static inline void dpm_runtime_resume(struct device * dev) -{ -} - #define suspend_report_result(fn, ret) do { } while (0) static inline int call_platform_enable_wakeup(struct device *dev, int is_on) diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eeb1976ef7b..ae8146abd74 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -110,6 +110,8 @@ static inline void ptrace_unlink(struct task_struct *child) __ptrace_unlink(child); } +int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data); +int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); #ifndef force_successful_syscall_return /* diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index dd5a05d03d4..75e17a05540 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -262,7 +262,7 @@ int bitmap_active(struct bitmap *bitmap); char *file_path(struct file *file, char *buf, int count); void bitmap_print_sb(struct bitmap *bitmap); -int bitmap_update_sb(struct bitmap *bitmap); +void bitmap_update_sb(struct bitmap *bitmap); int bitmap_setallbits(struct bitmap *bitmap); void bitmap_write_all(struct bitmap *bitmap); @@ -278,8 +278,8 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int d void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted); void bitmap_close_sync(struct bitmap *bitmap); -int bitmap_unplug(struct bitmap *bitmap); -int bitmap_daemon_work(struct bitmap *bitmap); +void bitmap_unplug(struct bitmap *bitmap); +void bitmap_daemon_work(struct bitmap *bitmap); #endif #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index de72c49747c..28ac632b42d 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -51,7 +51,7 @@ struct mdk_rdev_s sector_t size; /* Device size (in blocks) */ mddev_t *mddev; /* RAID array if running */ - unsigned long last_events; /* IO event timestamp */ + long last_events; /* IO event timestamp */ struct block_device *bdev; /* block device handle */ diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 1dd1c707311..85ea63f462a 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -67,6 +67,11 @@ extern void kernel_power_off(void); void ctrl_alt_del(void); +#define POWEROFF_CMD_PATH_LEN 256 +extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; + +extern int orderly_poweroff(bool force); + /* * Emergency restart, callable from an interrupt handler. */ diff --git a/include/linux/rtc/m48t59.h b/include/linux/rtc/m48t59.h new file mode 100644 index 00000000000..e8c7c21ceb1 --- /dev/null +++ b/include/linux/rtc/m48t59.h @@ -0,0 +1,57 @@ +/* + * include/linux/rtc/m48t59.h + * + * Definitions for the platform data of m48t59 RTC chip driver. + * + * Copyright (c) 2007 Wind River Systems, Inc. + * + * Mark Zhan <rongkai.zhan@windriver.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_RTC_M48T59_H_ +#define _LINUX_RTC_M48T59_H_ + +/* + * M48T59 Register Offset + */ +#define M48T59_YEAR 0x1fff +#define M48T59_MONTH 0x1ffe +#define M48T59_MDAY 0x1ffd /* Day of Month */ +#define M48T59_WDAY 0x1ffc /* Day of Week */ +#define M48T59_WDAY_CB 0x20 /* Century Bit */ +#define M48T59_WDAY_CEB 0x10 /* Century Enable Bit */ +#define M48T59_HOUR 0x1ffb +#define M48T59_MIN 0x1ffa +#define M48T59_SEC 0x1ff9 +#define M48T59_CNTL 0x1ff8 +#define M48T59_CNTL_READ 0x40 +#define M48T59_CNTL_WRITE 0x80 +#define M48T59_WATCHDOG 0x1ff7 +#define M48T59_INTR 0x1ff6 +#define M48T59_INTR_AFE 0x80 /* Alarm Interrupt Enable */ +#define M48T59_INTR_ABE 0x20 +#define M48T59_ALARM_DATE 0x1ff5 +#define M48T59_ALARM_HOUR 0x1ff4 +#define M48T59_ALARM_MIN 0x1ff3 +#define M48T59_ALARM_SEC 0x1ff2 +#define M48T59_UNUSED 0x1ff1 +#define M48T59_FLAGS 0x1ff0 +#define M48T59_FLAGS_WDT 0x80 /* watchdog timer expired */ +#define M48T59_FLAGS_AF 0x40 /* alarm */ +#define M48T59_FLAGS_BF 0x10 /* low battery */ + +#define M48T59_NVRAM_SIZE 0x1ff0 + +struct m48t59_plat_data { + /* The method to access M48T59 registers, + * NOTE: The 'ofs' should be 0x00~0x1fff + */ + void (*write_byte)(struct device *dev, u32 ofs, u8 val); + unsigned char (*read_byte)(struct device *dev, u32 ofs); +}; + +#endif /* _LINUX_RTC_M48T59_H_ */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 731edaca8ff..94f624aef01 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -345,6 +345,27 @@ typedef unsigned long mm_counter_t; (mm)->hiwater_vm = (mm)->total_vm; \ } while (0) +extern void set_dumpable(struct mm_struct *mm, int value); +extern int get_dumpable(struct mm_struct *mm); + +/* mm flags */ +/* dumpable bits */ +#define MMF_DUMPABLE 0 /* core dump is permitted */ +#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */ +#define MMF_DUMPABLE_BITS 2 + +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 4 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED)) + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -402,7 +423,7 @@ struct mm_struct { unsigned int token_priority; unsigned int last_interval; - unsigned char dumpable:2; + unsigned long flags; /* Must use atomic bitops to access the bits */ /* coredumping support */ int core_waiters; diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 706ee9a4c80..8518fa2a6f8 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -60,6 +60,8 @@ void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); +extern int early_serial_setup(struct uart_port *port); + extern int serial8250_find_port(struct uart_port *p); extern int serial8250_find_port_for_earlycon(void); extern int setup_early_serial8250_console(char *cmdline); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 7f2c99d66e9..773d8d8828a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -62,8 +62,9 @@ /* NEC v850. */ #define PORT_V850E_UART 40 -/* DZ */ -#define PORT_DZ 47 +/* DEC */ +#define PORT_DZ 46 +#define PORT_ZS 47 /* Parisc type numbers. */ #define PORT_MUX 48 @@ -142,6 +143,9 @@ /* Micrel KS8695 */ #define PORT_KS8695 76 +/* Broadcom SB1250, etc. SOC */ +#define PORT_SB1250_DUART 77 + #ifdef __KERNEL__ diff --git a/include/linux/slab.h b/include/linux/slab.h index 27402fea9b7..0e1d0daef6a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -31,6 +31,19 @@ #define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */ /* + * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. + * + * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. + * + * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. + * Both make kfree a no-op. + */ +#define ZERO_SIZE_PTR ((void *)16) + +#define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) < \ + (unsigned long)ZERO_SIZE_PTR) + +/* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); @@ -42,7 +55,6 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, void (*)(void *, struct kmem_cache *, unsigned long)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); -void *kmem_cache_zalloc(struct kmem_cache *, gfp_t); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); const char *kmem_cache_name(struct kmem_cache *); @@ -78,11 +90,37 @@ int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); /* * Common kmalloc functions provided by all allocators */ -void *__kzalloc(size_t, gfp_t); void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); size_t ksize(const void *); +/* + * Allocator specific definitions. These are mainly used to establish optimized + * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by + * selecting the appropriate general cache at compile time. + * + * Allocators must define at least: + * + * kmem_cache_alloc() + * __kmalloc() + * kmalloc() + * + * Those wishing to support NUMA must also define: + * + * kmem_cache_alloc_node() + * kmalloc_node() + * + * See each allocator definition file for additional comments and + * implementation notes. + */ +#ifdef CONFIG_SLUB +#include <linux/slub_def.h> +#elif defined(CONFIG_SLOB) +#include <linux/slob_def.h> +#else +#include <linux/slab_def.h> +#endif + /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. @@ -138,37 +176,9 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { if (n != 0 && size > ULONG_MAX / n) return NULL; - return __kzalloc(n * size, flags); + return __kmalloc(n * size, flags | __GFP_ZERO); } -/* - * Allocator specific definitions. These are mainly used to establish optimized - * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by - * selecting the appropriate general cache at compile time. - * - * Allocators must define at least: - * - * kmem_cache_alloc() - * __kmalloc() - * kmalloc() - * kzalloc() - * - * Those wishing to support NUMA must also define: - * - * kmem_cache_alloc_node() - * kmalloc_node() - * - * See each allocator definition file for additional comments and - * implementation notes. - */ -#ifdef CONFIG_SLUB -#include <linux/slub_def.h> -#elif defined(CONFIG_SLOB) -#include <linux/slob_def.h> -#else -#include <linux/slab_def.h> -#endif - #if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB) /** * kmalloc_node - allocate memory from a specific node @@ -242,5 +252,23 @@ extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *); #endif /* DEBUG_SLAB */ +/* + * Shortcuts + */ +static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) +{ + return kmem_cache_alloc(k, flags | __GFP_ZERO); +} + +/** + * kzalloc - allocate memory. The memory is set to zero. + * @size: how many bytes of memory are required. + * @flags: the type of memory to allocate (see kmalloc). + */ +static inline void *kzalloc(size_t size, gfp_t flags) +{ + return kmalloc(size, flags | __GFP_ZERO); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SLAB_H */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 365d036c454..32bdc2ffd71 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -32,6 +32,10 @@ static inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { int i = 0; + + if (!size) + return ZERO_SIZE_PTR; + #define CACHE(x) \ if (size <= x) \ goto found; \ @@ -54,32 +58,6 @@ found: return __kmalloc(size, flags); } -static inline void *kzalloc(size_t size, gfp_t flags) -{ - if (__builtin_constant_p(size)) { - int i = 0; -#define CACHE(x) \ - if (size <= x) \ - goto found; \ - else \ - i++; -#include "kmalloc_sizes.h" -#undef CACHE - { - extern void __you_cannot_kzalloc_that_much(void); - __you_cannot_kzalloc_that_much(); - } -found: -#ifdef CONFIG_ZONE_DMA - if (flags & GFP_DMA) - return kmem_cache_zalloc(malloc_sizes[i].cs_dmacachep, - flags); -#endif - return kmem_cache_zalloc(malloc_sizes[i].cs_cachep, flags); - } - return __kzalloc(size, flags); -} - #ifdef CONFIG_NUMA extern void *__kmalloc_node(size_t size, gfp_t flags, int node); extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); @@ -88,6 +66,10 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size)) { int i = 0; + + if (!size) + return ZERO_SIZE_PTR; + #define CACHE(x) \ if (size <= x) \ goto found; \ diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index a2daf2d418a..59a3fa476ab 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -33,14 +33,4 @@ static inline void *__kmalloc(size_t size, gfp_t flags) return kmalloc(size, flags); } -/** - * kzalloc - allocate memory. The memory is set to zero. - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kcalloc). - */ -static inline void *kzalloc(size_t size, gfp_t flags) -{ - return __kzalloc(size, flags); -} - #endif /* __LINUX_SLOB_DEF_H */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index a582f677152..07f7e4cbcee 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -16,7 +16,9 @@ struct kmem_cache_node { unsigned long nr_partial; atomic_long_t nr_slabs; struct list_head partial; +#ifdef CONFIG_SLUB_DEBUG struct list_head full; +#endif }; /* @@ -44,7 +46,9 @@ struct kmem_cache { int align; /* Alignment */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ +#ifdef CONFIG_SLUB_DEBUG struct kobject kobj; /* For sysfs */ +#endif #ifdef CONFIG_NUMA int defrag_ratio; @@ -159,18 +163,6 @@ static inline struct kmem_cache *kmalloc_slab(size_t size) #define SLUB_DMA 0 #endif - -/* - * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. - * - * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. - * - * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. - * Both make kfree a no-op. - */ -#define ZERO_SIZE_PTR ((void *)16) - - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); @@ -187,19 +179,6 @@ static inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -static inline void *kzalloc(size_t size, gfp_t flags) -{ - if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); - - if (!s) - return ZERO_SIZE_PTR; - - return kmem_cache_zalloc(s, flags); - } else - return __kzalloc(size, flags); -} - #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node); void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); diff --git a/include/linux/smp.h b/include/linux/smp.h index 96ac21f8dd7..259a13c3bd9 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -99,11 +99,14 @@ static inline int up_smp_call_function(void) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) -static inline int smp_call_function_single(int cpuid, void (*func) (void *info), - void *info, int retry, int wait) -{ - return -EBUSY; -} +#define smp_call_function_single(cpuid, func, info, retry, wait) \ +({ \ + WARN_ON(cpuid != 0); \ + local_irq_disable(); \ + (func)(info); \ + local_irq_enable(); \ + 0; \ +}) #endif /* !SMP */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 1be5ea05947..302b81d1d11 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -76,6 +76,7 @@ struct spi_device { #define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) #define SPI_CS_HIGH 0x04 /* chipselect active high? */ #define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ +#define SPI_3WIRE 0x10 /* SI/SO signals shared */ u8 bits_per_word; int irq; void *controller_state; diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 9dbca629dcf..b8db32cea1d 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -26,6 +26,7 @@ struct spi_bitbang { struct list_head queue; u8 busy; u8 use_dma; + u8 flags; /* extra spi->mode support */ struct spi_master *master; diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h new file mode 100644 index 00000000000..60b59187e59 --- /dev/null +++ b/include/linux/spi/tle62x0.h @@ -0,0 +1,24 @@ +/* + * tle62x0.h - platform glue to Infineon TLE62x0 driver chips + * + * Copyright 2007 Simtec Electronics + * Ben Dooks <ben@simtec.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ + +struct tle62x0_pdata { + unsigned int init_state; + unsigned int gpio_count; +}; diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 210549ba4ef..f6a3a951b79 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,14 +9,14 @@ * Released under the General Public License (GPL). */ -#include <linux/lockdep.h> - #if defined(CONFIG_SMP) # include <asm/spinlock_types.h> #else # include <linux/spinlock_types_up.h> #endif +#include <linux/lockdep.h> + typedef struct { raw_spinlock_t raw_lock; #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index 27644af20b7..04135b0e198 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -12,14 +12,10 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_DEBUG_SPINLOCK) || \ - defined(CONFIG_DEBUG_LOCK_ALLOC) +#ifdef CONFIG_DEBUG_SPINLOCK typedef struct { volatile unsigned int slock; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif } raw_spinlock_t; #define __RAW_SPIN_LOCK_UNLOCKED { 1 } @@ -34,9 +30,6 @@ typedef struct { } raw_spinlock_t; typedef struct { /* no debug version on UP */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif } raw_rwlock_t; #define __RAW_RW_LOCK_UNLOCKED { } diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 1d2b084c018..e7fa657d0c4 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -13,7 +13,7 @@ extern void save_stack_trace(struct stack_trace *trace); extern void print_stack_trace(struct stack_trace *trace, int spaces); #else # define save_stack_trace(trace) do { } while (0) -# define print_stack_trace(trace) do { } while (0) +# define print_stack_trace(trace, spaces) do { } while (0) #endif #endif diff --git a/include/linux/string.h b/include/linux/string.h index 7f2eb6a477f..836062b7582 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -105,8 +105,12 @@ extern void * memchr(const void *,int,__kernel_size_t); #endif extern char *kstrdup(const char *s, gfp_t gfp); +extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char **argv_split(gfp_t gfp, const char *str, int *argcp); +extern void argv_free(char **argv); + #ifdef __cplusplus } #endif diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index bbac101ac37..459c5fc11d5 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -58,6 +58,7 @@ u32 gss_unwrap( u32 gss_delete_sec_context( struct gss_ctx **ctx_id); +u32 gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 service); u32 gss_pseudoflavor_to_service(struct gss_api_mech *, u32 pseudoflavor); char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 129d50f2225..8531a70da73 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -212,6 +212,7 @@ struct svc_rqst { struct svc_pool * rq_pool; /* thread pool */ struct svc_procedure * rq_procinfo; /* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ + u32 rq_flavor; /* pseudoflavor */ struct svc_cred rq_cred; /* auth info */ struct sk_buff * rq_skbuff; /* fast recv inet buffer */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ @@ -248,6 +249,7 @@ struct svc_rqst { */ /* Catering to nfsd */ struct auth_domain * rq_client; /* RPC peer info */ + struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ struct svc_cacherep * rq_cacherep; /* cache info */ struct knfsd_fh * rq_reffh; /* Referrence filehandle, used to * determine what device number diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index de92619b082..22e1ef8e200 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -127,6 +127,7 @@ extern struct auth_domain *auth_unix_lookup(struct in_addr addr); extern int auth_unix_forget_old(struct auth_domain *dom); extern void svcauth_unix_purge(void); extern void svcauth_unix_info_release(void *); +extern int svcauth_unix_set_client(struct svc_rqst *rqstp); static inline unsigned long hash_str(char *name, int bits) { diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index 5a5db16ab66..417a1def56d 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -22,6 +22,7 @@ int gss_svc_init(void); void gss_svc_shutdown(void); int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name); +u32 svcauth_gss_flavor(struct auth_domain *dom); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_SVCAUTH_GSS_H */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 9c7cb643066..e8e6da394c9 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -43,14 +43,19 @@ static inline void pm_restore_console(void) {} * @prepare: prepare system for hibernation * @enter: shut down system after state has been saved to disk * @finish: finish/clean up after state has been reloaded + * @pre_restore: prepare system for the restoration from a hibernation image + * @restore_cleanup: clean up after a failing image restoration */ struct hibernation_ops { int (*prepare)(void); int (*enter)(void); void (*finish)(void); + int (*pre_restore)(void); + void (*restore_cleanup)(void); }; -#if defined(CONFIG_PM) && defined(CONFIG_SOFTWARE_SUSPEND) +#ifdef CONFIG_PM +#ifdef CONFIG_SOFTWARE_SUSPEND /* kernel/power/snapshot.c */ extern void __register_nosave_region(unsigned long b, unsigned long e, int km); static inline void register_nosave_region(unsigned long b, unsigned long e) @@ -68,16 +73,14 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern void hibernation_set_ops(struct hibernation_ops *ops); extern int hibernate(void); -#else -static inline void register_nosave_region(unsigned long b, unsigned long e) {} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} +#else /* CONFIG_SOFTWARE_SUSPEND */ static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} static inline void hibernation_set_ops(struct hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } -#endif /* defined(CONFIG_PM) && defined(CONFIG_SOFTWARE_SUSPEND) */ +#endif /* CONFIG_SOFTWARE_SUSPEND */ void save_processor_state(void); void restore_processor_state(void); @@ -85,4 +88,43 @@ struct saved_context; void __save_processor_state(struct saved_context *ctxt); void __restore_processor_state(struct saved_context *ctxt); +/* kernel/power/main.c */ +extern struct blocking_notifier_head pm_chain_head; + +static inline int register_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&pm_chain_head, nb); +} + +static inline int unregister_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&pm_chain_head, nb); +} + +#define pm_notifier(fn, pri) { \ + static struct notifier_block fn##_nb = \ + { .notifier_call = fn, .priority = pri }; \ + register_pm_notifier(&fn##_nb); \ +} +#else /* CONFIG_PM */ + +static inline int register_pm_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_pm_notifier(struct notifier_block *nb) +{ + return 0; +} + +#define pm_notifier(fn, pri) do { (void)(fn); } while (0) +#endif /* CONFIG_PM */ + +#if !defined CONFIG_SOFTWARE_SUSPEND || !defined(CONFIG_PM) +static inline void register_nosave_region(unsigned long b, unsigned long e) +{ +} +#endif + #endif /* _LINUX_SWSUSP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 00686888134..665f85f2a3a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -188,7 +188,8 @@ extern int rotate_reclaimable_page(struct page *page); extern void swap_setup(void); /* linux/mm/vmscan.c */ -extern unsigned long try_to_free_pages(struct zone **, gfp_t); +extern unsigned long try_to_free_pages(struct zone **zones, int order, + gfp_t gfp_mask); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 83d0ec11235..7a8b1e3322e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,6 +610,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas asmlinkage long sys_timerfd(int ufd, int clockid, int flags, const struct itimerspec __user *utmr); asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); diff --git a/include/linux/time.h b/include/linux/time.h index 4bb05a829be..ec3b0ced0af 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -36,7 +36,8 @@ struct timezone { #define NSEC_PER_SEC 1000000000L #define FSEC_PER_SEC 1000000000000000L -static inline int timespec_equal(struct timespec *a, struct timespec *b) +static inline int timespec_equal(const struct timespec *a, + const struct timespec *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h new file mode 100644 index 00000000000..44c28e94df5 --- /dev/null +++ b/include/linux/uio_driver.h @@ -0,0 +1,91 @@ +/* + * include/linux/uio_driver.h + * + * Copyright(C) 2005, Benedikt Spranger <b.spranger@linutronix.de> + * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2006, Hans J. Koch <hjk@linutronix.de> + * Copyright(C) 2006, Greg Kroah-Hartman <greg@kroah.com> + * + * Userspace IO driver. + * + * Licensed under the GPLv2 only. + */ + +#ifndef _UIO_DRIVER_H_ +#define _UIO_DRIVER_H_ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/interrupt.h> + +/** + * struct uio_mem - description of a UIO memory region + * @kobj: kobject for this mapping + * @addr: address of the device's memory + * @size: size of IO + * @memtype: type of memory addr points to + * @internal_addr: ioremap-ped version of addr, for driver internal use + */ +struct uio_mem { + struct kobject kobj; + unsigned long addr; + unsigned long size; + int memtype; + void __iomem *internal_addr; +}; + +#define MAX_UIO_MAPS 5 + +struct uio_device; + +/** + * struct uio_info - UIO device capabilities + * @uio_dev: the UIO device this info belongs to + * @name: device name + * @version: device driver version + * @mem: list of mappable memory regions, size==0 for end of list + * @irq: interrupt number or UIO_IRQ_CUSTOM + * @irq_flags: flags for request_irq() + * @priv: optional private data + * @handler: the device's irq handler + * @mmap: mmap operation for this uio device + * @open: open operation for this uio device + * @release: release operation for this uio device + */ +struct uio_info { + struct uio_device *uio_dev; + char *name; + char *version; + struct uio_mem mem[MAX_UIO_MAPS]; + long irq; + unsigned long irq_flags; + void *priv; + irqreturn_t (*handler)(int irq, struct uio_info *dev_info); + int (*mmap)(struct uio_info *info, struct vm_area_struct *vma); + int (*open)(struct uio_info *info, struct inode *inode); + int (*release)(struct uio_info *info, struct inode *inode); +}; + +extern int __must_check + __uio_register_device(struct module *owner, + struct device *parent, + struct uio_info *info); +static inline int __must_check + uio_register_device(struct device *parent, struct uio_info *info) +{ + return __uio_register_device(THIS_MODULE, parent, info); +} +extern void uio_unregister_device(struct uio_info *info); +extern void uio_event_notify(struct uio_info *info); + +/* defines for uio_device->irq */ +#define UIO_IRQ_CUSTOM -1 +#define UIO_IRQ_NONE -2 + +/* defines for uio_device->memtype */ +#define UIO_MEM_NONE 0 +#define UIO_MEM_PHYS 1 +#define UIO_MEM_LOGICAL 2 +#define UIO_MEM_VIRTUAL 3 + +#endif /* _LINUX_UIO_DRIVER_H_ */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 132b260aef1..c2b10cae5da 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -70,6 +70,10 @@ extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); extern void unmap_kernel_range(unsigned long addr, unsigned long size); +/* Allocate/destroy a 'vmalloc' VM area. */ +extern struct vm_struct *alloc_vm_area(size_t size); +extern void free_vm_area(struct vm_struct *area); + /* * Internals. Dont't use.. */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d9325cf8a13..75370ec0923 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -25,7 +25,7 @@ #define HIGHMEM_ZONE(xx) #endif -#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) +#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), @@ -170,7 +170,8 @@ static inline unsigned long node_page_state(int node, #ifdef CONFIG_HIGHMEM zone_page_state(&zones[ZONE_HIGHMEM], item) + #endif - zone_page_state(&zones[ZONE_NORMAL], item); + zone_page_state(&zones[ZONE_NORMAL], item) + + zone_page_state(&zones[ZONE_MOVABLE], item); } extern void zone_statistics(struct zonelist *, struct zone *); diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index d961635d0e6..699b7e9864f 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -75,6 +75,8 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); int vt_waitactive(int vt); void change_console(struct vc_data *new_vc); void reset_vc(struct vc_data *vc); +extern int unbind_con_driver(const struct consw *csw, int first, int last, + int deflt); /* * vc_screen.c shares this temporary buffer with the console write code so that diff --git a/include/media/saa7146.h b/include/media/saa7146.h index d3f4f5a3821..67703249b24 100644 --- a/include/media/saa7146.h +++ b/include/media/saa7146.h @@ -114,7 +114,7 @@ struct saa7146_dev struct mutex lock; unsigned char __iomem *mem; /* pointer to mapped IO memory */ - int revision; /* chip revision; needed for bug-workarounds*/ + u32 revision; /* chip revision; needed for bug-workarounds*/ /* pci-device & irq stuff*/ char name[32]; @@ -157,8 +157,8 @@ struct saa7146_format* format_by_fourcc(struct saa7146_dev *dev, int fourcc); int saa7146_pgtable_alloc(struct pci_dev *pci, struct saa7146_pgtable *pt); void saa7146_pgtable_free(struct pci_dev *pci, struct saa7146_pgtable *pt); int saa7146_pgtable_build_single(struct pci_dev *pci, struct saa7146_pgtable *pt, struct scatterlist *list, int length ); -char *saa7146_vmalloc_build_pgtable(struct pci_dev *pci, long length, struct saa7146_pgtable *pt); -void saa7146_vfree_destroy_pgtable(struct pci_dev *pci, char *mem, struct saa7146_pgtable *pt); +void *saa7146_vmalloc_build_pgtable(struct pci_dev *pci, long length, struct saa7146_pgtable *pt); +void saa7146_vfree_destroy_pgtable(struct pci_dev *pci, void *mem, struct saa7146_pgtable *pt); void saa7146_setgpio(struct saa7146_dev *dev, int port, u32 data); int saa7146_wait_for_debi_done(struct saa7146_dev *dev, int nobusyloop); diff --git a/include/media/tuner.h b/include/media/tuner.h index 6dcf3c45707..160381c72e4 100644 --- a/include/media/tuner.h +++ b/include/media/tuner.h @@ -23,8 +23,6 @@ #define _TUNER_H #include <linux/videodev2.h> -#include <linux/i2c.h> -#include <media/tuner-types.h> extern int tuner_debug; @@ -124,6 +122,7 @@ extern int tuner_debug; #define TUNER_THOMSON_FE6600 72 /* DViCO FusionHDTV DVB-T Hybrid */ #define TUNER_SAMSUNG_TCPG_6121P30A 73 /* Hauppauge PVR-500 PAL */ #define TUNER_TDA9887 74 /* This tuner should be used only internally */ +#define TUNER_TEA5761 75 /* Only FM Radio Tuner */ /* tv card specific */ #define TDA9887_PRESENT (1<<0) @@ -182,74 +181,6 @@ struct tuner_setup { int (*tuner_callback) (void *dev, int command,int arg); }; -struct tuner { - /* device */ - struct i2c_client i2c; - - unsigned int type; /* chip type */ - - unsigned int mode; - unsigned int mode_mask; /* Combination of allowable modes */ - - unsigned int tv_freq; /* keep track of the current settings */ - unsigned int radio_freq; - u16 last_div; - unsigned int audmode; - v4l2_std_id std; - - int using_v4l2; - - /* used by tda9887 */ - unsigned int tda9887_config; - unsigned char tda9887_data[4]; - - /* used by MT2032 */ - unsigned int xogc; - unsigned int radio_if2; - - /* used by tda8290 */ - unsigned char tda8290_easy_mode; - unsigned char tda827x_lpsel; - unsigned char tda827x_addr; - unsigned char tda827x_ver; - unsigned int sgIF; - - unsigned int config; - int (*tuner_callback) (void *dev, int command,int arg); - - /* function ptrs */ - void (*set_tv_freq)(struct i2c_client *c, unsigned int freq); - void (*set_radio_freq)(struct i2c_client *c, unsigned int freq); - int (*has_signal)(struct i2c_client *c); - int (*is_stereo)(struct i2c_client *c); - int (*get_afc)(struct i2c_client *c); - void (*tuner_status)(struct i2c_client *c); - void (*standby)(struct i2c_client *c); -}; - -extern unsigned const int tuner_count; - -extern int microtune_init(struct i2c_client *c); -extern int xc3028_init(struct i2c_client *c); -extern int tda8290_init(struct i2c_client *c); -extern int tda8290_probe(struct i2c_client *c); -extern int tea5767_tuner_init(struct i2c_client *c); -extern int default_tuner_init(struct i2c_client *c); -extern int tea5767_autodetection(struct i2c_client *c); -extern int tda9887_tuner_init(struct i2c_client *c); - -#define tuner_warn(fmt, arg...) do {\ - printk(KERN_WARNING "%s %d-%04x: " fmt, t->i2c.driver->driver.name, \ - i2c_adapter_id(t->i2c.adapter), t->i2c.addr , ##arg); } while (0) -#define tuner_info(fmt, arg...) do {\ - printk(KERN_INFO "%s %d-%04x: " fmt, t->i2c.driver->driver.name, \ - i2c_adapter_id(t->i2c.adapter), t->i2c.addr , ##arg); } while (0) -#define tuner_dbg(fmt, arg...) do {\ - extern int tuner_debug; \ - if (tuner_debug) \ - printk(KERN_DEBUG "%s %d-%04x: " fmt, t->i2c.driver->driver.name, \ - i2c_adapter_id(t->i2c.adapter), t->i2c.addr , ##arg); } while (0) - #endif /* __KERNEL__ */ #endif /* _TUNER_H */ diff --git a/include/mtd/ubi-header.h b/include/mtd/ubi-header.h index fa479c71aa3..74efa776347 100644 --- a/include/mtd/ubi-header.h +++ b/include/mtd/ubi-header.h @@ -74,42 +74,13 @@ enum { UBI_COMPAT_REJECT = 5 }; -/* - * ubi16_t/ubi32_t/ubi64_t - 16, 32, and 64-bit integers used in UBI on-flash - * data structures. - */ -typedef struct { - uint16_t int16; -} __attribute__ ((packed)) ubi16_t; - -typedef struct { - uint32_t int32; -} __attribute__ ((packed)) ubi32_t; - -typedef struct { - uint64_t int64; -} __attribute__ ((packed)) ubi64_t; - -/* - * In this implementation of UBI uses the big-endian format for on-flash - * integers. The below are the corresponding conversion macros. - */ -#define cpu_to_ubi16(x) ((ubi16_t){__cpu_to_be16(x)}) -#define ubi16_to_cpu(x) ((uint16_t)__be16_to_cpu((x).int16)) - -#define cpu_to_ubi32(x) ((ubi32_t){__cpu_to_be32(x)}) -#define ubi32_to_cpu(x) ((uint32_t)__be32_to_cpu((x).int32)) - -#define cpu_to_ubi64(x) ((ubi64_t){__cpu_to_be64(x)}) -#define ubi64_to_cpu(x) ((uint64_t)__be64_to_cpu((x).int64)) - /* Sizes of UBI headers */ #define UBI_EC_HDR_SIZE sizeof(struct ubi_ec_hdr) #define UBI_VID_HDR_SIZE sizeof(struct ubi_vid_hdr) /* Sizes of UBI headers without the ending CRC */ -#define UBI_EC_HDR_SIZE_CRC (UBI_EC_HDR_SIZE - sizeof(ubi32_t)) -#define UBI_VID_HDR_SIZE_CRC (UBI_VID_HDR_SIZE - sizeof(ubi32_t)) +#define UBI_EC_HDR_SIZE_CRC (UBI_EC_HDR_SIZE - sizeof(__be32)) +#define UBI_VID_HDR_SIZE_CRC (UBI_VID_HDR_SIZE - sizeof(__be32)) /** * struct ubi_ec_hdr - UBI erase counter header. @@ -137,14 +108,14 @@ typedef struct { * eraseblocks. */ struct ubi_ec_hdr { - ubi32_t magic; - uint8_t version; - uint8_t padding1[3]; - ubi64_t ec; /* Warning: the current limit is 31-bit anyway! */ - ubi32_t vid_hdr_offset; - ubi32_t data_offset; - uint8_t padding2[36]; - ubi32_t hdr_crc; + __be32 magic; + __u8 version; + __u8 padding1[3]; + __be64 ec; /* Warning: the current limit is 31-bit anyway! */ + __be32 vid_hdr_offset; + __be32 data_offset; + __u8 padding2[36]; + __be32 hdr_crc; } __attribute__ ((packed)); /** @@ -262,22 +233,22 @@ struct ubi_ec_hdr { * software (say, cramfs) on top of the UBI volume. */ struct ubi_vid_hdr { - ubi32_t magic; - uint8_t version; - uint8_t vol_type; - uint8_t copy_flag; - uint8_t compat; - ubi32_t vol_id; - ubi32_t lnum; - ubi32_t leb_ver; /* obsolete, to be removed, don't use */ - ubi32_t data_size; - ubi32_t used_ebs; - ubi32_t data_pad; - ubi32_t data_crc; - uint8_t padding1[4]; - ubi64_t sqnum; - uint8_t padding2[12]; - ubi32_t hdr_crc; + __be32 magic; + __u8 version; + __u8 vol_type; + __u8 copy_flag; + __u8 compat; + __be32 vol_id; + __be32 lnum; + __be32 leb_ver; /* obsolete, to be removed, don't use */ + __be32 data_size; + __be32 used_ebs; + __be32 data_pad; + __be32 data_crc; + __u8 padding1[4]; + __be64 sqnum; + __u8 padding2[12]; + __be32 hdr_crc; } __attribute__ ((packed)); /* Internal UBI volumes count */ @@ -306,7 +277,7 @@ struct ubi_vid_hdr { #define UBI_VTBL_RECORD_SIZE sizeof(struct ubi_vtbl_record) /* Size of the volume table record without the ending CRC */ -#define UBI_VTBL_RECORD_SIZE_CRC (UBI_VTBL_RECORD_SIZE - sizeof(ubi32_t)) +#define UBI_VTBL_RECORD_SIZE_CRC (UBI_VTBL_RECORD_SIZE - sizeof(__be32)) /** * struct ubi_vtbl_record - a record in the volume table. @@ -346,15 +317,15 @@ struct ubi_vid_hdr { * Empty records contain all zeroes and the CRC checksum of those zeroes. */ struct ubi_vtbl_record { - ubi32_t reserved_pebs; - ubi32_t alignment; - ubi32_t data_pad; - uint8_t vol_type; - uint8_t upd_marker; - ubi16_t name_len; - uint8_t name[UBI_VOL_NAME_MAX+1]; - uint8_t padding2[24]; - ubi32_t crc; + __be32 reserved_pebs; + __be32 alignment; + __be32 data_pad; + __u8 vol_type; + __u8 upd_marker; + __be16 name_len; + __u8 name[UBI_VOL_NAME_MAX+1]; + __u8 padding2[24]; + __be32 crc; } __attribute__ ((packed)); #endif /* !__UBI_HEADER_H__ */ diff --git a/include/net/scm.h b/include/net/scm.h index 5637d5e22d5..423cb1d5ac2 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -8,7 +8,7 @@ /* Well, we should have at least one descriptor open * to accept passed FDs 8) */ -#define SCM_MAX_FD (OPEN_MAX-1) +#define SCM_MAX_FD 255 struct scm_fp_list { diff --git a/include/net/tcp.h b/include/net/tcp.h index a8af9ae0017..8b404b1ef7c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -652,8 +652,7 @@ struct tcp_congestion_ops { /* lower bound for congestion window (optional) */ u32 (*min_cwnd)(const struct sock *sk); /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct sock *sk, u32 ack, - u32 rtt, u32 in_flight, int good_ack); + void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight, int good_ack); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ @@ -684,8 +683,7 @@ extern void tcp_slow_start(struct tcp_sock *tp); extern struct tcp_congestion_ops tcp_init_congestion_ops; extern u32 tcp_reno_ssthresh(struct sock *sk); -extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, - u32 rtt, u32 in_flight, int flag); +extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag); extern u32 tcp_reno_min_cwnd(const struct sock *sk); extern struct tcp_congestion_ops tcp_reno; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ae959e95017..a5f80bfbaaa 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -585,7 +585,6 @@ static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ct struct xfrm_dst { union { - struct xfrm_dst *next; struct dst_entry dst; struct rtable rt; struct rt6_info rt6; diff --git a/include/video/tgafb.h b/include/video/tgafb.h index 03d0dbe293a..7bc5e2c1482 100644 --- a/include/video/tgafb.h +++ b/include/video/tgafb.h @@ -216,6 +216,7 @@ struct tga_par { u32 pll_freq; /* pixclock in mhz */ u32 bits_per_pixel; /* bits per pixel */ u32 sync_on_green; /* set if sync is on green */ + u32 palette[16]; }; diff --git a/include/xen/events.h b/include/xen/events.h new file mode 100644 index 00000000000..2bde54d29be --- /dev/null +++ b/include/xen/events.h @@ -0,0 +1,48 @@ +#ifndef _XEN_EVENTS_H +#define _XEN_EVENTS_H + +#include <linux/interrupt.h> + +#include <xen/interface/event_channel.h> +#include <asm/xen/hypercall.h> + +enum ipi_vector { + XEN_RESCHEDULE_VECTOR, + XEN_CALL_FUNCTION_VECTOR, + + XEN_NR_IPIS, +}; + +int bind_evtchn_to_irq(unsigned int evtchn); +int bind_evtchn_to_irqhandler(unsigned int evtchn, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); +int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); +int bind_ipi_to_irqhandler(enum ipi_vector ipi, + unsigned int cpu, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); + +/* + * Common unbind function for all event sources. Takes IRQ to unbind from. + * Automatically closes the underlying event channel (even for bindings + * made with bind_evtchn_to_irqhandler()). + */ +void unbind_from_irqhandler(unsigned int irq, void *dev_id); + +void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector); + +static inline void notify_remote_via_evtchn(int port) +{ + struct evtchn_send send = { .port = port }; + (void)HYPERVISOR_event_channel_op(EVTCHNOP_send, &send); +} + +extern void notify_remote_via_irq(int irq); +#endif /* _XEN_EVENTS_H */ diff --git a/include/xen/features.h b/include/xen/features.h new file mode 100644 index 00000000000..27292d4d2a6 --- /dev/null +++ b/include/xen/features.h @@ -0,0 +1,23 @@ +/****************************************************************************** + * features.h + * + * Query the features reported by Xen. + * + * Copyright (c) 2006, Ian Campbell + */ + +#ifndef __XEN_FEATURES_H__ +#define __XEN_FEATURES_H__ + +#include <xen/interface/features.h> + +void xen_setup_features(void); + +extern u8 xen_features[XENFEAT_NR_SUBMAPS * 32]; + +static inline int xen_feature(int flag) +{ + return xen_features[flag]; +} + +#endif /* __ASM_XEN_FEATURES_H__ */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h new file mode 100644 index 00000000000..761c83498e0 --- /dev/null +++ b/include/xen/grant_table.h @@ -0,0 +1,107 @@ +/****************************************************************************** + * grant_table.h + * + * Two sets of functionality: + * 1. Granting foreign access to our memory reservation. + * 2. Accessing others' memory reservations via grant references. + * (i.e., mechanisms for both sender and recipient of grant references) + * + * Copyright (c) 2004-2005, K A Fraser + * Copyright (c) 2005, Christopher Clark + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __ASM_GNTTAB_H__ +#define __ASM_GNTTAB_H__ + +#include <asm/xen/hypervisor.h> +#include <xen/interface/grant_table.h> + +/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ +#define NR_GRANT_FRAMES 4 + +struct gnttab_free_callback { + struct gnttab_free_callback *next; + void (*fn)(void *); + void *arg; + u16 count; +}; + +int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, + int readonly); + +/* + * End access through the given grant reference, iff the grant entry is no + * longer in use. Return 1 if the grant entry was freed, 0 if it is still in + * use. + */ +int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); + +/* + * Eventually end access through the given grant reference, and once that + * access has been ended, free the given page too. Access will be ended + * immediately iff the grant entry is not in use, otherwise it will happen + * some time later. page may be 0, in which case no freeing will occur. + */ +void gnttab_end_foreign_access(grant_ref_t ref, int readonly, + unsigned long page); + +int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); + +unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); +unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); + +int gnttab_query_foreign_access(grant_ref_t ref); + +/* + * operations on reserved batches of grant references + */ +int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); + +void gnttab_free_grant_reference(grant_ref_t ref); + +void gnttab_free_grant_references(grant_ref_t head); + +int gnttab_empty_grant_references(const grant_ref_t *pprivate_head); + +int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); + +void gnttab_release_grant_reference(grant_ref_t *private_head, + grant_ref_t release); + +void gnttab_request_free_callback(struct gnttab_free_callback *callback, + void (*fn)(void *), void *arg, u16 count); +void gnttab_cancel_free_callback(struct gnttab_free_callback *callback); + +void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, + unsigned long frame, int readonly); + +void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, + unsigned long pfn); + +#define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) + +#endif /* __ASM_GNTTAB_H__ */ diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h new file mode 100644 index 00000000000..21c0ecfd786 --- /dev/null +++ b/include/xen/hvc-console.h @@ -0,0 +1,6 @@ +#ifndef XEN_HVC_CONSOLE_H +#define XEN_HVC_CONSOLE_H + +extern struct console xenboot_console; + +#endif /* XEN_HVC_CONSOLE_H */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h new file mode 100644 index 00000000000..a64d3df5bd9 --- /dev/null +++ b/include/xen/interface/elfnote.h @@ -0,0 +1,133 @@ +/****************************************************************************** + * elfnote.h + * + * Definitions used for the Xen ELF notes. + * + * Copyright (c) 2006, Ian Campbell, XenSource Ltd. + */ + +#ifndef __XEN_PUBLIC_ELFNOTE_H__ +#define __XEN_PUBLIC_ELFNOTE_H__ + +/* + * The notes should live in a SHT_NOTE segment and have "Xen" in the + * name field. + * + * Numeric types are either 4 or 8 bytes depending on the content of + * the desc field. + * + * LEGACY indicated the fields in the legacy __xen_guest string which + * this a note type replaces. + */ + +/* + * NAME=VALUE pair (string). + * + * LEGACY: FEATURES and PAE + */ +#define XEN_ELFNOTE_INFO 0 + +/* + * The virtual address of the entry point (numeric). + * + * LEGACY: VIRT_ENTRY + */ +#define XEN_ELFNOTE_ENTRY 1 + +/* The virtual address of the hypercall transfer page (numeric). + * + * LEGACY: HYPERCALL_PAGE. (n.b. legacy value is a physical page + * number not a virtual address) + */ +#define XEN_ELFNOTE_HYPERCALL_PAGE 2 + +/* The virtual address where the kernel image should be mapped (numeric). + * + * Defaults to 0. + * + * LEGACY: VIRT_BASE + */ +#define XEN_ELFNOTE_VIRT_BASE 3 + +/* + * The offset of the ELF paddr field from the acutal required + * psuedo-physical address (numeric). + * + * This is used to maintain backwards compatibility with older kernels + * which wrote __PAGE_OFFSET into that field. This field defaults to 0 + * if not present. + * + * LEGACY: ELF_PADDR_OFFSET. (n.b. legacy default is VIRT_BASE) + */ +#define XEN_ELFNOTE_PADDR_OFFSET 4 + +/* + * The version of Xen that we work with (string). + * + * LEGACY: XEN_VER + */ +#define XEN_ELFNOTE_XEN_VERSION 5 + +/* + * The name of the guest operating system (string). + * + * LEGACY: GUEST_OS + */ +#define XEN_ELFNOTE_GUEST_OS 6 + +/* + * The version of the guest operating system (string). + * + * LEGACY: GUEST_VER + */ +#define XEN_ELFNOTE_GUEST_VERSION 7 + +/* + * The loader type (string). + * + * LEGACY: LOADER + */ +#define XEN_ELFNOTE_LOADER 8 + +/* + * The kernel supports PAE (x86/32 only, string = "yes" or "no"). + * + * LEGACY: PAE (n.b. The legacy interface included a provision to + * indicate 'extended-cr3' support allowing L3 page tables to be + * placed above 4G. It is assumed that any kernel new enough to use + * these ELF notes will include this and therefore "yes" here is + * equivalent to "yes[entended-cr3]" in the __xen_guest interface. + */ +#define XEN_ELFNOTE_PAE_MODE 9 + +/* + * The features supported/required by this kernel (string). + * + * The string must consist of a list of feature names (as given in + * features.h, without the "XENFEAT_" prefix) separated by '|' + * characters. If a feature is required for the kernel to function + * then the feature name must be preceded by a '!' character. + * + * LEGACY: FEATURES + */ +#define XEN_ELFNOTE_FEATURES 10 + +/* + * The kernel requires the symbol table to be loaded (string = "yes" or "no") + * LEGACY: BSD_SYMTAB (n.b. The legacy treated the presence or absence + * of this string as a boolean flag rather than requiring "yes" or + * "no". + */ +#define XEN_ELFNOTE_BSD_SYMTAB 11 + +#endif /* __XEN_PUBLIC_ELFNOTE_H__ */ + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/interface/event_channel.h b/include/xen/interface/event_channel.h new file mode 100644 index 00000000000..919b5bdcb2b --- /dev/null +++ b/include/xen/interface/event_channel.h @@ -0,0 +1,195 @@ +/****************************************************************************** + * event_channel.h + * + * Event channels between domains. + * + * Copyright (c) 2003-2004, K A Fraser. + */ + +#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__ +#define __XEN_PUBLIC_EVENT_CHANNEL_H__ + +typedef uint32_t evtchn_port_t; +DEFINE_GUEST_HANDLE(evtchn_port_t); + +/* + * EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as + * accepting interdomain bindings from domain <remote_dom>. A fresh port + * is allocated in <dom> and returned as <port>. + * NOTES: + * 1. If the caller is unprivileged then <dom> must be DOMID_SELF. + * 2. <rdom> may be DOMID_SELF, allowing loopback connections. + */ +#define EVTCHNOP_alloc_unbound 6 +struct evtchn_alloc_unbound { + /* IN parameters */ + domid_t dom, remote_dom; + /* OUT parameters */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between + * the calling domain and <remote_dom>. <remote_dom,remote_port> must identify + * a port that is unbound and marked as accepting bindings from the calling + * domain. A fresh port is allocated in the calling domain and returned as + * <local_port>. + * NOTES: + * 2. <remote_dom> may be DOMID_SELF, allowing loopback connections. + */ +#define EVTCHNOP_bind_interdomain 0 +struct evtchn_bind_interdomain { + /* IN parameters. */ + domid_t remote_dom; + evtchn_port_t remote_port; + /* OUT parameters. */ + evtchn_port_t local_port; +}; + +/* + * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified + * vcpu. + * NOTES: + * 1. A virtual IRQ may be bound to at most one event channel per vcpu. + * 2. The allocated event channel is bound to the specified vcpu. The binding + * may not be changed. + */ +#define EVTCHNOP_bind_virq 1 +struct evtchn_bind_virq { + /* IN parameters. */ + uint32_t virq; + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_pirq: Bind a local event channel to PIRQ <irq>. + * NOTES: + * 1. A physical IRQ may be bound to at most one event channel per domain. + * 2. Only a sufficiently-privileged domain may bind to a physical IRQ. + */ +#define EVTCHNOP_bind_pirq 2 +struct evtchn_bind_pirq { + /* IN parameters. */ + uint32_t pirq; +#define BIND_PIRQ__WILL_SHARE 1 + uint32_t flags; /* BIND_PIRQ__* */ + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_ipi: Bind a local event channel to receive events. + * NOTES: + * 1. The allocated event channel is bound to the specified vcpu. The binding + * may not be changed. + */ +#define EVTCHNOP_bind_ipi 7 +struct evtchn_bind_ipi { + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_close: Close a local event channel <port>. If the channel is + * interdomain then the remote end is placed in the unbound state + * (EVTCHNSTAT_unbound), awaiting a new connection. + */ +#define EVTCHNOP_close 3 +struct evtchn_close { + /* IN parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_send: Send an event to the remote end of the channel whose local + * endpoint is <port>. + */ +#define EVTCHNOP_send 4 +struct evtchn_send { + /* IN parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_status: Get the current status of the communication channel which + * has an endpoint at <dom, port>. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may obtain the status of an event + * channel for which <dom> is not DOMID_SELF. + */ +#define EVTCHNOP_status 5 +struct evtchn_status { + /* IN parameters */ + domid_t dom; + evtchn_port_t port; + /* OUT parameters */ +#define EVTCHNSTAT_closed 0 /* Channel is not in use. */ +#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/ +#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */ +#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */ +#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */ +#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */ + uint32_t status; + uint32_t vcpu; /* VCPU to which this channel is bound. */ + union { + struct { + domid_t dom; + } unbound; /* EVTCHNSTAT_unbound */ + struct { + domid_t dom; + evtchn_port_t port; + } interdomain; /* EVTCHNSTAT_interdomain */ + uint32_t pirq; /* EVTCHNSTAT_pirq */ + uint32_t virq; /* EVTCHNSTAT_virq */ + } u; +}; + +/* + * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an + * event is pending. + * NOTES: + * 1. IPI- and VIRQ-bound channels always notify the vcpu that initialised + * the binding. This binding cannot be changed. + * 2. All other channels notify vcpu0 by default. This default is set when + * the channel is allocated (a port that is freed and subsequently reused + * has its binding reset to vcpu0). + */ +#define EVTCHNOP_bind_vcpu 8 +struct evtchn_bind_vcpu { + /* IN parameters. */ + evtchn_port_t port; + uint32_t vcpu; +}; + +/* + * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver + * a notification to the appropriate VCPU if an event is pending. + */ +#define EVTCHNOP_unmask 9 +struct evtchn_unmask { + /* IN parameters. */ + evtchn_port_t port; +}; + +struct evtchn_op { + uint32_t cmd; /* EVTCHNOP_* */ + union { + struct evtchn_alloc_unbound alloc_unbound; + struct evtchn_bind_interdomain bind_interdomain; + struct evtchn_bind_virq bind_virq; + struct evtchn_bind_pirq bind_pirq; + struct evtchn_bind_ipi bind_ipi; + struct evtchn_close close; + struct evtchn_send send; + struct evtchn_status status; + struct evtchn_bind_vcpu bind_vcpu; + struct evtchn_unmask unmask; + } u; +}; +DEFINE_GUEST_HANDLE_STRUCT(evtchn_op); + +#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h new file mode 100644 index 00000000000..d73228d1648 --- /dev/null +++ b/include/xen/interface/features.h @@ -0,0 +1,43 @@ +/****************************************************************************** + * features.h + * + * Feature flags, reported by XENVER_get_features. + * + * Copyright (c) 2006, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_FEATURES_H__ +#define __XEN_PUBLIC_FEATURES_H__ + +/* + * If set, the guest does not need to write-protect its pagetables, and can + * update them via direct writes. + */ +#define XENFEAT_writable_page_tables 0 + +/* + * If set, the guest does not need to write-protect its segment descriptor + * tables, and can update them via direct writes. + */ +#define XENFEAT_writable_descriptor_tables 1 + +/* + * If set, translation between the guest's 'pseudo-physical' address space + * and the host's machine address space are handled by the hypervisor. In this + * mode the guest does not need to perform phys-to/from-machine translations + * when performing page table operations. + */ +#define XENFEAT_auto_translated_physmap 2 + +/* If set, the guest is running in supervisor mode (e.g., x86 ring 0). */ +#define XENFEAT_supervisor_mode_kernel 3 + +/* + * If set, the guest does not need to allocate x86 PAE page directories + * below 4GB. This flag is usually implied by auto_translated_physmap. + */ +#define XENFEAT_pae_pgdir_above_4gb 4 + +#define XENFEAT_NR_SUBMAPS 1 + +#endif /* __XEN_PUBLIC_FEATURES_H__ */ diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h new file mode 100644 index 00000000000..219049802cf --- /dev/null +++ b/include/xen/interface/grant_table.h @@ -0,0 +1,375 @@ +/****************************************************************************** + * grant_table.h + * + * Interface for granting foreign access to page frames, and receiving + * page-ownership transfers. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_GRANT_TABLE_H__ +#define __XEN_PUBLIC_GRANT_TABLE_H__ + + +/*********************************** + * GRANT TABLE REPRESENTATION + */ + +/* Some rough guidelines on accessing and updating grant-table entries + * in a concurrency-safe manner. For more information, Linux contains a + * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * + * NB. WMB is a no-op on current-generation x86 processors. However, a + * compiler barrier will still be required. + * + * Introducing a valid entry into the grant table: + * 1. Write ent->domid. + * 2. Write ent->frame: + * GTF_permit_access: Frame to which access is permitted. + * GTF_accept_transfer: Pseudo-phys frame slot being filled by new + * frame, or zero if none. + * 3. Write memory barrier (WMB). + * 4. Write ent->flags, inc. valid type. + * + * Invalidating an unused GTF_permit_access entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & (GTF_reading|GTF_writing)). + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * + * Invalidating an in-use GTF_permit_access entry: + * This cannot be done directly. Request assistance from the domain controller + * which can set a timeout on the use of a grant entry and take necessary + * action. (NB. This is not yet implemented!). + * + * Invalidating an unused GTF_accept_transfer entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & GTF_transfer_committed). [*] + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * [*] If GTF_transfer_committed is set then the grant entry is 'committed'. + * The guest must /not/ modify the grant entry until the address of the + * transferred frame is written. It is safe for the guest to spin waiting + * for this to occur (detect by observing GTF_transfer_completed in + * ent->flags). + * + * Invalidating a committed GTF_accept_transfer entry: + * 1. Wait for (ent->flags & GTF_transfer_completed). + * + * Changing a GTF_permit_access from writable to read-only: + * Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing. + * + * Changing a GTF_permit_access from read-only to writable: + * Use SMP-safe bit-setting instruction. + */ + +/* + * A grant table comprises a packed array of grant entries in one or more + * page frames shared between Xen and a guest. + * [XEN]: This field is written by Xen and read by the sharing guest. + * [GST]: This field is written by the guest and read by Xen. + */ +struct grant_entry { + /* GTF_xxx: various type and flag information. [XEN,GST] */ + uint16_t flags; + /* The domain being granted foreign privileges. [GST] */ + domid_t domid; + /* + * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + */ + uint32_t frame; +}; + +/* + * Type of grant entry. + * GTF_invalid: This grant entry grants no privileges. + * GTF_permit_access: Allow @domid to map/access @frame. + * GTF_accept_transfer: Allow @domid to transfer ownership of one page frame + * to this guest. Xen writes the page number to @frame. + */ +#define GTF_invalid (0U<<0) +#define GTF_permit_access (1U<<0) +#define GTF_accept_transfer (2U<<0) +#define GTF_type_mask (3U<<0) + +/* + * Subflags for GTF_permit_access. + * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] + * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] + * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + */ +#define _GTF_readonly (2) +#define GTF_readonly (1U<<_GTF_readonly) +#define _GTF_reading (3) +#define GTF_reading (1U<<_GTF_reading) +#define _GTF_writing (4) +#define GTF_writing (1U<<_GTF_writing) + +/* + * Subflags for GTF_accept_transfer: + * GTF_transfer_committed: Xen sets this flag to indicate that it is committed + * to transferring ownership of a page frame. When a guest sees this flag + * it must /not/ modify the grant entry until GTF_transfer_completed is + * set by Xen. + * GTF_transfer_completed: It is safe for the guest to spin-wait on this flag + * after reading GTF_transfer_committed. Xen will always write the frame + * address, followed by ORing this flag, in a timely manner. + */ +#define _GTF_transfer_committed (2) +#define GTF_transfer_committed (1U<<_GTF_transfer_committed) +#define _GTF_transfer_completed (3) +#define GTF_transfer_completed (1U<<_GTF_transfer_completed) + + +/*********************************** + * GRANT TABLE QUERIES AND USES + */ + +/* + * Reference to a grant entry in a specified domain's grant table. + */ +typedef uint32_t grant_ref_t; + +/* + * Handle to track a mapping created via a grant reference. + */ +typedef uint32_t grant_handle_t; + +/* + * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access + * by devices and/or host CPUs. If successful, <handle> is a tracking number + * that must be presented later to destroy the mapping(s). On error, <handle> + * is a negative status code. + * NOTES: + * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address + * via which I/O devices may access the granted frame. + * 2. If GNTMAP_host_map is specified then a mapping will be added at + * either a host virtual address in the current address space, or at + * a PTE at the specified machine address. The type of mapping to + * perform is selected through the GNTMAP_contains_pte flag, and the + * address is specified in <host_addr>. + * 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a + * host mapping is destroyed by other means then it is *NOT* guaranteed + * to be accounted to the correct grant reference! + */ +#define GNTTABOP_map_grant_ref 0 +struct gnttab_map_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint32_t flags; /* GNTMAP_* */ + grant_ref_t ref; + domid_t dom; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ + grant_handle_t handle; + uint64_t dev_bus_addr; +}; + +/* + * GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings + * tracked by <handle>. If <host_addr> or <dev_bus_addr> is zero, that + * field is ignored. If non-zero, they must refer to a device/host mapping + * that is tracked by <handle> + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by <handle>. + * 3. After executing a batch of unmaps, it is guaranteed that no stale + * mappings will remain in the device or host TLBs. + */ +#define GNTTABOP_unmap_grant_ref 1 +struct gnttab_unmap_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint64_t dev_bus_addr; + grant_handle_t handle; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ +}; + +/* + * GNTTABOP_setup_table: Set up a grant table for <dom> comprising at least + * <nr_frames> pages. The frame addresses are written to the <frame_list>. + * Only <nr_frames> addresses are written, even if the table is larger. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. + * 3. Xen may not support more than a single grant-table page per domain. + */ +#define GNTTABOP_setup_table 2 +struct gnttab_setup_table { + /* IN parameters. */ + domid_t dom; + uint32_t nr_frames; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ + ulong *frame_list; +}; + +/* + * GNTTABOP_dump_table: Dump the contents of the grant table to the + * xen console. Debugging use only. + */ +#define GNTTABOP_dump_table 3 +struct gnttab_dump_table { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ +}; + +/* + * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The + * foreign domain has previously registered its interest in the transfer via + * <domid, ref>. + * + * Note that, even if the transfer fails, the specified page no longer belongs + * to the calling domain *unless* the error is GNTST_bad_page. + */ +#define GNTTABOP_transfer 4 +struct gnttab_transfer { + /* IN parameters. */ + unsigned long mfn; + domid_t domid; + grant_ref_t ref; + /* OUT parameters. */ + int16_t status; +}; + + +/* + * GNTTABOP_copy: Hypervisor based copy + * source and destinations can be eithers MFNs or, for foreign domains, + * grant references. the foreign domain has to grant read/write access + * in its grant table. + * + * The flags specify what type source and destinations are (either MFN + * or grant reference). + * + * Note that this can also be used to copy data between two domains + * via a third party if the source and destination domains had previously + * grant appropriate access to their pages to the third party. + * + * source_offset specifies an offset in the source frame, dest_offset + * the offset in the target frame and len specifies the number of + * bytes to be copied. + */ + +#define _GNTCOPY_source_gref (0) +#define GNTCOPY_source_gref (1<<_GNTCOPY_source_gref) +#define _GNTCOPY_dest_gref (1) +#define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) + +#define GNTTABOP_copy 5 +struct gnttab_copy { + /* IN parameters. */ + struct { + union { + grant_ref_t ref; + unsigned long gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; +}; + +/* + * GNTTABOP_query_size: Query the current and maximum sizes of the shared + * grant table. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. + */ +#define GNTTABOP_query_size 6 +struct gnttab_query_size { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + uint32_t nr_frames; + uint32_t max_nr_frames; + int16_t status; /* GNTST_* */ +}; + + +/* + * Bitfield values for update_pin_status.flags. + */ + /* Map the grant entry for access by I/O devices. */ +#define _GNTMAP_device_map (0) +#define GNTMAP_device_map (1<<_GNTMAP_device_map) + /* Map the grant entry for access by host CPUs. */ +#define _GNTMAP_host_map (1) +#define GNTMAP_host_map (1<<_GNTMAP_host_map) + /* Accesses to the granted frame will be restricted to read-only access. */ +#define _GNTMAP_readonly (2) +#define GNTMAP_readonly (1<<_GNTMAP_readonly) + /* + * GNTMAP_host_map subflag: + * 0 => The host mapping is usable only by the guest OS. + * 1 => The host mapping is usable by guest OS + current application. + */ +#define _GNTMAP_application_map (3) +#define GNTMAP_application_map (1<<_GNTMAP_application_map) + + /* + * GNTMAP_contains_pte subflag: + * 0 => This map request contains a host virtual address. + * 1 => This map request contains the machine addess of the PTE to update. + */ +#define _GNTMAP_contains_pte (4) +#define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte) + +/* + * Values for error status returns. All errors are -ve. + */ +#define GNTST_okay (0) /* Normal return. */ +#define GNTST_general_error (-1) /* General undefined error. */ +#define GNTST_bad_domain (-2) /* Unrecognsed domain id. */ +#define GNTST_bad_gntref (-3) /* Unrecognised or inappropriate gntref. */ +#define GNTST_bad_handle (-4) /* Unrecognised or inappropriate handle. */ +#define GNTST_bad_virt_addr (-5) /* Inappropriate virtual address to map. */ +#define GNTST_bad_dev_addr (-6) /* Inappropriate device address to unmap.*/ +#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */ +#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */ +#define GNTST_bad_page (-9) /* Specified page was invalid for op. */ +#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary */ + +#define GNTTABOP_error_msgs { \ + "okay", \ + "undefined error", \ + "unrecognised domain id", \ + "invalid grant reference", \ + "invalid mapping handle", \ + "invalid virtual address", \ + "invalid device address", \ + "no spare translation slot in the I/O MMU", \ + "permission denied", \ + "bad page", \ + "copy arguments cross page boundary" \ +} + +#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h new file mode 100644 index 00000000000..c2d1fa4dc1e --- /dev/null +++ b/include/xen/interface/io/blkif.h @@ -0,0 +1,94 @@ +/****************************************************************************** + * blkif.h + * + * Unified block-device I/O interface for Xen guest OSes. + * + * Copyright (c) 2003-2004, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_BLKIF_H__ +#define __XEN_PUBLIC_IO_BLKIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Front->back notifications: When enqueuing a new request, sending a + * notification can be made conditional on req_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Backends must set + * req_event appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()). + * + * Back->front notifications: When enqueuing a new response, sending a + * notification can be made conditional on rsp_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Frontends must set + * rsp_event appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()). + */ + +typedef uint16_t blkif_vdev_t; +typedef uint64_t blkif_sector_t; + +/* + * REQUEST CODES. + */ +#define BLKIF_OP_READ 0 +#define BLKIF_OP_WRITE 1 +/* + * Recognised only if "feature-barrier" is present in backend xenbus info. + * The "feature_barrier" node contains a boolean indicating whether barrier + * requests are likely to succeed or fail. Either way, a barrier request + * may fail at any time with BLKIF_RSP_EOPNOTSUPP if it is unsupported by + * the underlying block-device hardware. The boolean simply indicates whether + * or not it is worthwhile for the frontend to attempt barrier requests. + * If a backend does not recognise BLKIF_OP_WRITE_BARRIER, it should *not* + * create the "feature-barrier" node! + */ +#define BLKIF_OP_WRITE_BARRIER 2 + +/* + * Maximum scatter/gather segments per request. + * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE. + * NB. This could be 12 if the ring indexes weren't stored in the same page. + */ +#define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 + +struct blkif_request { + uint8_t operation; /* BLKIF_OP_??? */ + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; + } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +}; + +struct blkif_response { + uint64_t id; /* copied from request */ + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; + +/* + * STATUS RETURN CODES. + */ + /* Operation not supported (only happens on barrier writes). */ +#define BLKIF_RSP_EOPNOTSUPP -2 + /* Operation failed for some unspecified reason (-EIO). */ +#define BLKIF_RSP_ERROR -1 + /* Operation completed successfully. */ +#define BLKIF_RSP_OKAY 0 + +/* + * Generate blkif ring structures and types. + */ + +DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response); + +#define VDISK_CDROM 0x1 +#define VDISK_REMOVABLE 0x2 +#define VDISK_READONLY 0x4 + +#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */ diff --git a/include/xen/interface/io/console.h b/include/xen/interface/io/console.h new file mode 100644 index 00000000000..e563de70f78 --- /dev/null +++ b/include/xen/interface/io/console.h @@ -0,0 +1,23 @@ +/****************************************************************************** + * console.h + * + * Console I/O interface for Xen guest OSes. + * + * Copyright (c) 2005, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_CONSOLE_H__ +#define __XEN_PUBLIC_IO_CONSOLE_H__ + +typedef uint32_t XENCONS_RING_IDX; + +#define MASK_XENCONS_IDX(idx, ring) ((idx) & (sizeof(ring)-1)) + +struct xencons_interface { + char in[1024]; + char out[2048]; + XENCONS_RING_IDX in_cons, in_prod; + XENCONS_RING_IDX out_cons, out_prod; +}; + +#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */ diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h new file mode 100644 index 00000000000..518481c95f1 --- /dev/null +++ b/include/xen/interface/io/netif.h @@ -0,0 +1,158 @@ +/****************************************************************************** + * netif.h + * + * Unified network-device I/O interface for Xen guest OSes. + * + * Copyright (c) 2003-2004, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_NETIF_H__ +#define __XEN_PUBLIC_IO_NETIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Notifications after enqueuing any type of message should be conditional on + * the appropriate req_event or rsp_event field in the shared ring. + * If the client sends notification for rx requests then it should specify + * feature 'feature-rx-notify' via xenbus. Otherwise the backend will assume + * that it cannot safely queue packets (as it may not be kicked to send them). + */ + +/* + * This is the 'wire' format for packets: + * Request 1: netif_tx_request -- NETTXF_* (any flags) + * [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info) + * [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_MORE) + * Request 4: netif_tx_request -- NETTXF_more_data + * Request 5: netif_tx_request -- NETTXF_more_data + * ... + * Request N: netif_tx_request -- 0 + */ + +/* Protocol checksum field is blank in the packet (hardware offload)? */ +#define _NETTXF_csum_blank (0) +#define NETTXF_csum_blank (1U<<_NETTXF_csum_blank) + +/* Packet data has been validated against protocol checksum. */ +#define _NETTXF_data_validated (1) +#define NETTXF_data_validated (1U<<_NETTXF_data_validated) + +/* Packet continues in the next request descriptor. */ +#define _NETTXF_more_data (2) +#define NETTXF_more_data (1U<<_NETTXF_more_data) + +/* Packet to be followed by extra descriptor(s). */ +#define _NETTXF_extra_info (3) +#define NETTXF_extra_info (1U<<_NETTXF_extra_info) + +struct xen_netif_tx_request { + grant_ref_t gref; /* Reference to buffer page */ + uint16_t offset; /* Offset within buffer page */ + uint16_t flags; /* NETTXF_* */ + uint16_t id; /* Echoed in response message. */ + uint16_t size; /* Packet size in bytes. */ +}; + +/* Types of netif_extra_info descriptors. */ +#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ +#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ +#define XEN_NETIF_EXTRA_TYPE_MAX (2) + +/* netif_extra_info flags. */ +#define _XEN_NETIF_EXTRA_FLAG_MORE (0) +#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) + +/* GSO types - only TCPv4 currently supported. */ +#define XEN_NETIF_GSO_TYPE_TCPV4 (1) + +/* + * This structure needs to fit within both netif_tx_request and + * netif_rx_response for compatibility. + */ +struct xen_netif_extra_info { + uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */ + uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */ + + union { + struct { + /* + * Maximum payload size of each segment. For + * example, for TCP this is just the path MSS. + */ + uint16_t size; + + /* + * GSO type. This determines the protocol of + * the packet and any extra features required + * to segment the packet properly. + */ + uint8_t type; /* XEN_NETIF_GSO_TYPE_* */ + + /* Future expansion. */ + uint8_t pad; + + /* + * GSO features. This specifies any extra GSO + * features required to process this packet, + * such as ECN support for TCPv4. + */ + uint16_t features; /* XEN_NETIF_GSO_FEAT_* */ + } gso; + + uint16_t pad[3]; + } u; +}; + +struct xen_netif_tx_response { + uint16_t id; + int16_t status; /* NETIF_RSP_* */ +}; + +struct xen_netif_rx_request { + uint16_t id; /* Echoed in response message. */ + grant_ref_t gref; /* Reference to incoming granted frame */ +}; + +/* Packet data has been validated against protocol checksum. */ +#define _NETRXF_data_validated (0) +#define NETRXF_data_validated (1U<<_NETRXF_data_validated) + +/* Protocol checksum field is blank in the packet (hardware offload)? */ +#define _NETRXF_csum_blank (1) +#define NETRXF_csum_blank (1U<<_NETRXF_csum_blank) + +/* Packet continues in the next request descriptor. */ +#define _NETRXF_more_data (2) +#define NETRXF_more_data (1U<<_NETRXF_more_data) + +/* Packet to be followed by extra descriptor(s). */ +#define _NETRXF_extra_info (3) +#define NETRXF_extra_info (1U<<_NETRXF_extra_info) + +struct xen_netif_rx_response { + uint16_t id; + uint16_t offset; /* Offset in page of start of received packet */ + uint16_t flags; /* NETRXF_* */ + int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */ +}; + +/* + * Generate netif ring structures and types. + */ + +DEFINE_RING_TYPES(xen_netif_tx, + struct xen_netif_tx_request, + struct xen_netif_tx_response); +DEFINE_RING_TYPES(xen_netif_rx, + struct xen_netif_rx_request, + struct xen_netif_rx_response); + +#define NETIF_RSP_DROPPED -2 +#define NETIF_RSP_ERROR -1 +#define NETIF_RSP_OKAY 0 +/* No response: used for auxiliary requests (e.g., netif_tx_extra). */ +#define NETIF_RSP_NULL 1 + +#endif diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h new file mode 100644 index 00000000000..e8cbf431c8c --- /dev/null +++ b/include/xen/interface/io/ring.h @@ -0,0 +1,260 @@ +/****************************************************************************** + * ring.h + * + * Shared producer-consumer ring macros. + * + * Tim Deegan and Andrew Warfield November 2004. + */ + +#ifndef __XEN_PUBLIC_IO_RING_H__ +#define __XEN_PUBLIC_IO_RING_H__ + +typedef unsigned int RING_IDX; + +/* Round a 32-bit unsigned constant down to the nearest power of two. */ +#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) +#define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x)) +#define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x)) +#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x)) +#define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x)) + +/* + * Calculate size of a shared ring, given the total available space for the + * ring and indexes (_sz), and the name tag of the request/response structure. + * A ring contains as many entries as will fit, rounded down to the nearest + * power of two (so we can mask with (size-1) to loop around). + */ +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) + +/* + * Macros to make the correct C datatypes for a new kind of ring. + * + * To make a new ring datatype, you need to have two message structures, + * let's say struct request, and struct response already defined. + * + * In a header where you want the ring datatype declared, you then do: + * + * DEFINE_RING_TYPES(mytag, struct request, struct response); + * + * These expand out to give you a set of types, as you can see below. + * The most important of these are: + * + * struct mytag_sring - The shared ring. + * struct mytag_front_ring - The 'front' half of the ring. + * struct mytag_back_ring - The 'back' half of the ring. + * + * To initialize a ring in your code you need to know the location and size + * of the shared memory area (PAGE_SIZE, for instance). To initialise + * the front half: + * + * struct mytag_front_ring front_ring; + * SHARED_RING_INIT((struct mytag_sring *)shared_page); + * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page, + * PAGE_SIZE); + * + * Initializing the back follows similarly (note that only the front + * initializes the shared ring): + * + * struct mytag_back_ring back_ring; + * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page, + * PAGE_SIZE); + */ + +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + uint8_t pad[48]; \ + union __name##_sring_entry ring[1]; /* variable-length */ \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; + +/* + * Macros for manipulating rings. + * + * FRONT_RING_whatever works on the "front end" of a ring: here + * requests are pushed on to the ring and responses taken off it. + * + * BACK_RING_whatever works on the "back end" of a ring: here + * requests are taken off the ring and responses put on. + * + * N.B. these macros do NO INTERLOCKS OR FLOW CONTROL. + * This is OK in 1-for-1 request-response situations where the + * requestor (front end) never has more than RING_SIZE()-1 + * outstanding requests. + */ + +/* Initialising empty rings */ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + memset((_s)->pad, 0, sizeof((_s)->pad)); \ +} while(0) + +#define FRONT_RING_INIT(_r, _s, __size) do { \ + (_r)->req_prod_pvt = 0; \ + (_r)->rsp_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +#define BACK_RING_INIT(_r, _s, __size) do { \ + (_r)->rsp_prod_pvt = 0; \ + (_r)->req_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +/* Initialize to existing shared indexes -- for recovery */ +#define FRONT_RING_ATTACH(_r, _s, __size) do { \ + (_r)->sring = (_s); \ + (_r)->req_prod_pvt = (_s)->req_prod; \ + (_r)->rsp_cons = (_s)->rsp_prod; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ +} while (0) + +#define BACK_RING_ATTACH(_r, _s, __size) do { \ + (_r)->sring = (_s); \ + (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ + (_r)->req_cons = (_s)->req_prod; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ +} while (0) + +/* How big is this ring? */ +#define RING_SIZE(_r) \ + ((_r)->nr_ents) + +/* Number of free requests (for use on front side only). */ +#define RING_FREE_REQUESTS(_r) \ + (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) + +/* Test if there is an empty slot available on the front ring. + * (This is only meaningful from the front. ) + */ +#define RING_FULL(_r) \ + (RING_FREE_REQUESTS(_r) == 0) + +/* Test if there are outstanding messages to be processed on a ring. */ +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + ((_r)->sring->rsp_prod - (_r)->rsp_cons) + +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ + }) + +/* Direct access to individual ring elements, by index. */ +#define RING_GET_REQUEST(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) + +#define RING_GET_RESPONSE(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) + +/* Loop termination condition: Would the specified index overflow the ring? */ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ + (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) + +#define RING_PUSH_REQUESTS(_r) do { \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +} while (0) + +#define RING_PUSH_RESPONSES(_r) do { \ + wmb(); /* front sees responses /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +} while (0) + +/* + * Notification hold-off (req_event and rsp_event): + * + * When queueing requests or responses on a shared ring, it may not always be + * necessary to notify the remote end. For example, if requests are in flight + * in a backend, the front may be able to queue further requests without + * notifying the back (if the back checks for new requests when it queues + * responses). + * + * When enqueuing requests or responses: + * + * Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument + * is a boolean return value. True indicates that the receiver requires an + * asynchronous notification. + * + * After dequeuing requests or responses (before sleeping the connection): + * + * Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES(). + * The second argument is a boolean return value. True indicates that there + * are pending messages on the ring (i.e., the connection should not be put + * to sleep). + * + * These macros will set the req_event/rsp_event field to trigger a + * notification on the very next message that is enqueued. If you want to + * create batches of work (i.e., only receive a notification after several + * messages have been enqueued) then you will need to create a customised + * version of the FINAL_CHECK macro in your own code, which sets the event + * field appropriately. + */ + +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = __new; \ + mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + wmb(); /* front sees responses /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + mb(); /* front sees new responses /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +} while (0) + +#endif /* __XEN_PUBLIC_IO_RING_H__ */ diff --git a/include/xen/interface/io/xenbus.h b/include/xen/interface/io/xenbus.h new file mode 100644 index 00000000000..46508c7fa39 --- /dev/null +++ b/include/xen/interface/io/xenbus.h @@ -0,0 +1,44 @@ +/***************************************************************************** + * xenbus.h + * + * Xenbus protocol details. + * + * Copyright (C) 2005 XenSource Ltd. + */ + +#ifndef _XEN_PUBLIC_IO_XENBUS_H +#define _XEN_PUBLIC_IO_XENBUS_H + +/* The state of either end of the Xenbus, i.e. the current communication + status of initialisation across the bus. States here imply nothing about + the state of the connection between the driver and the kernel's device + layers. */ +enum xenbus_state +{ + XenbusStateUnknown = 0, + XenbusStateInitialising = 1, + XenbusStateInitWait = 2, /* Finished early + initialisation, but waiting + for information from the peer + or hotplug scripts. */ + XenbusStateInitialised = 3, /* Initialised and waiting for a + connection from the peer. */ + XenbusStateConnected = 4, + XenbusStateClosing = 5, /* The device is being closed + due to an error or an unplug + event. */ + XenbusStateClosed = 6 + +}; + +#endif /* _XEN_PUBLIC_IO_XENBUS_H */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h new file mode 100644 index 00000000000..99fcffb372d --- /dev/null +++ b/include/xen/interface/io/xs_wire.h @@ -0,0 +1,87 @@ +/* + * Details of the "wire" protocol between Xen Store Daemon and client + * library or guest kernel. + * Copyright (C) 2005 Rusty Russell IBM Corporation + */ + +#ifndef _XS_WIRE_H +#define _XS_WIRE_H + +enum xsd_sockmsg_type +{ + XS_DEBUG, + XS_DIRECTORY, + XS_READ, + XS_GET_PERMS, + XS_WATCH, + XS_UNWATCH, + XS_TRANSACTION_START, + XS_TRANSACTION_END, + XS_INTRODUCE, + XS_RELEASE, + XS_GET_DOMAIN_PATH, + XS_WRITE, + XS_MKDIR, + XS_RM, + XS_SET_PERMS, + XS_WATCH_EVENT, + XS_ERROR, + XS_IS_DOMAIN_INTRODUCED +}; + +#define XS_WRITE_NONE "NONE" +#define XS_WRITE_CREATE "CREATE" +#define XS_WRITE_CREATE_EXCL "CREATE|EXCL" + +/* We hand errors as strings, for portability. */ +struct xsd_errors +{ + int errnum; + const char *errstring; +}; +#define XSD_ERROR(x) { x, #x } +static struct xsd_errors xsd_errors[] __attribute__((unused)) = { + XSD_ERROR(EINVAL), + XSD_ERROR(EACCES), + XSD_ERROR(EEXIST), + XSD_ERROR(EISDIR), + XSD_ERROR(ENOENT), + XSD_ERROR(ENOMEM), + XSD_ERROR(ENOSPC), + XSD_ERROR(EIO), + XSD_ERROR(ENOTEMPTY), + XSD_ERROR(ENOSYS), + XSD_ERROR(EROFS), + XSD_ERROR(EBUSY), + XSD_ERROR(EAGAIN), + XSD_ERROR(EISCONN) +}; + +struct xsd_sockmsg +{ + uint32_t type; /* XS_??? */ + uint32_t req_id;/* Request identifier, echoed in daemon's response. */ + uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */ + uint32_t len; /* Length of data following this. */ + + /* Generally followed by nul-terminated string(s). */ +}; + +enum xs_watch_type +{ + XS_WATCH_PATH = 0, + XS_WATCH_TOKEN +}; + +/* Inter-domain shared memory communications. */ +#define XENSTORE_RING_SIZE 1024 +typedef uint32_t XENSTORE_RING_IDX; +#define MASK_XENSTORE_IDX(idx) ((idx) & (XENSTORE_RING_SIZE-1)) +struct xenstore_domain_interface { + char req[XENSTORE_RING_SIZE]; /* Requests to xenstore daemon. */ + char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ + XENSTORE_RING_IDX req_cons, req_prod; + XENSTORE_RING_IDX rsp_cons, rsp_prod; +}; + +#endif /* _XS_WIRE_H */ diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h new file mode 100644 index 00000000000..af36ead1681 --- /dev/null +++ b/include/xen/interface/memory.h @@ -0,0 +1,145 @@ +/****************************************************************************** + * memory.h + * + * Memory reservation and information. + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_MEMORY_H__ +#define __XEN_PUBLIC_MEMORY_H__ + +/* + * Increase or decrease the specified domain's memory reservation. Returns a + * -ve errcode on failure, or the # extents successfully allocated or freed. + * arg == addr of struct xen_memory_reservation. + */ +#define XENMEM_increase_reservation 0 +#define XENMEM_decrease_reservation 1 +#define XENMEM_populate_physmap 6 +struct xen_memory_reservation { + + /* + * XENMEM_increase_reservation: + * OUT: MFN (*not* GMFN) bases of extents that were allocated + * XENMEM_decrease_reservation: + * IN: GMFN bases of extents to free + * XENMEM_populate_physmap: + * IN: GPFN bases of extents to populate with memory + * OUT: GMFN bases of extents that were allocated + * (NB. This command also updates the mach_to_phys translation table) + */ + GUEST_HANDLE(ulong) extent_start; + + /* Number of extents, and size/alignment of each (2^extent_order pages). */ + unsigned long nr_extents; + unsigned int extent_order; + + /* + * Maximum # bits addressable by the user of the allocated region (e.g., + * I/O devices often have a 32-bit limitation even in 64-bit systems). If + * zero then the user has no addressing restriction. + * This field is not used by XENMEM_decrease_reservation. + */ + unsigned int address_bits; + + /* + * Domain whose reservation is being changed. + * Unprivileged domains can specify only DOMID_SELF. + */ + domid_t domid; + +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation); + +/* + * Returns the maximum machine frame number of mapped RAM in this system. + * This command always succeeds (it never returns an error code). + * arg == NULL. + */ +#define XENMEM_maximum_ram_page 2 + +/* + * Returns the current or maximum memory reservation, in pages, of the + * specified domain (may be DOMID_SELF). Returns -ve errcode on failure. + * arg == addr of domid_t. + */ +#define XENMEM_current_reservation 3 +#define XENMEM_maximum_reservation 4 + +/* + * Returns a list of MFN bases of 2MB extents comprising the machine_to_phys + * mapping table. Architectures which do not have a m2p table do not implement + * this command. + * arg == addr of xen_machphys_mfn_list_t. + */ +#define XENMEM_machphys_mfn_list 5 +struct xen_machphys_mfn_list { + /* + * Size of the 'extent_start' array. Fewer entries will be filled if the + * machphys table is smaller than max_extents * 2MB. + */ + unsigned int max_extents; + + /* + * Pointer to buffer to fill with list of extent starts. If there are + * any large discontiguities in the machine address space, 2MB gaps in + * the machphys table will be represented by an MFN base of zero. + */ + GUEST_HANDLE(ulong) extent_start; + + /* + * Number of extents written to the above array. This will be smaller + * than 'max_extents' if the machphys table is smaller than max_e * 2MB. + */ + unsigned int nr_extents; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mfn_list); + +/* + * Sets the GPFN at which a particular page appears in the specified guest's + * pseudophysical address space. + * arg == addr of xen_add_to_physmap_t. + */ +#define XENMEM_add_to_physmap 7 +struct xen_add_to_physmap { + /* Which domain to change the mapping for. */ + domid_t domid; + + /* Source mapping space. */ +#define XENMAPSPACE_shared_info 0 /* shared info page */ +#define XENMAPSPACE_grant_table 1 /* grant table page */ + unsigned int space; + + /* Index into source mapping space. */ + unsigned long idx; + + /* GPFN where the source mapping page should appear. */ + unsigned long gpfn; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap); + +/* + * Translates a list of domain-specific GPFNs into MFNs. Returns a -ve error + * code on failure. This call only works for auto-translated guests. + */ +#define XENMEM_translate_gpfn_list 8 +struct xen_translate_gpfn_list { + /* Which domain to translate for? */ + domid_t domid; + + /* Length of list. */ + unsigned long nr_gpfns; + + /* List of GPFNs to translate. */ + GUEST_HANDLE(ulong) gpfn_list; + + /* + * Output list to contain MFN translations. May be the same as the input + * list (in which case each input GPFN is overwritten with the output MFN). + */ + GUEST_HANDLE(ulong) mfn_list; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list); + +#endif /* __XEN_PUBLIC_MEMORY_H__ */ diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h new file mode 100644 index 00000000000..cd6939147cb --- /dev/null +++ b/include/xen/interface/physdev.h @@ -0,0 +1,145 @@ +/* + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PUBLIC_PHYSDEV_H__ +#define __XEN_PUBLIC_PHYSDEV_H__ + +/* + * Prototype for this hypercall is: + * int physdev_op(int cmd, void *args) + * @cmd == PHYSDEVOP_??? (physdev operation). + * @args == Operation-specific extra arguments (NULL if none). + */ + +/* + * Notify end-of-interrupt (EOI) for the specified IRQ. + * @arg == pointer to physdev_eoi structure. + */ +#define PHYSDEVOP_eoi 12 +struct physdev_eoi { + /* IN */ + uint32_t irq; +}; + +/* + * Query the status of an IRQ line. + * @arg == pointer to physdev_irq_status_query structure. + */ +#define PHYSDEVOP_irq_status_query 5 +struct physdev_irq_status_query { + /* IN */ + uint32_t irq; + /* OUT */ + uint32_t flags; /* XENIRQSTAT_* */ +}; + +/* Need to call PHYSDEVOP_eoi when the IRQ has been serviced? */ +#define _XENIRQSTAT_needs_eoi (0) +#define XENIRQSTAT_needs_eoi (1U<<_XENIRQSTAT_needs_eoi) + +/* IRQ shared by multiple guests? */ +#define _XENIRQSTAT_shared (1) +#define XENIRQSTAT_shared (1U<<_XENIRQSTAT_shared) + +/* + * Set the current VCPU's I/O privilege level. + * @arg == pointer to physdev_set_iopl structure. + */ +#define PHYSDEVOP_set_iopl 6 +struct physdev_set_iopl { + /* IN */ + uint32_t iopl; +}; + +/* + * Set the current VCPU's I/O-port permissions bitmap. + * @arg == pointer to physdev_set_iobitmap structure. + */ +#define PHYSDEVOP_set_iobitmap 7 +struct physdev_set_iobitmap { + /* IN */ + uint8_t * bitmap; + uint32_t nr_ports; +}; + +/* + * Read or write an IO-APIC register. + * @arg == pointer to physdev_apic structure. + */ +#define PHYSDEVOP_apic_read 8 +#define PHYSDEVOP_apic_write 9 +struct physdev_apic { + /* IN */ + unsigned long apic_physbase; + uint32_t reg; + /* IN or OUT */ + uint32_t value; +}; + +/* + * Allocate or free a physical upcall vector for the specified IRQ line. + * @arg == pointer to physdev_irq structure. + */ +#define PHYSDEVOP_alloc_irq_vector 10 +#define PHYSDEVOP_free_irq_vector 11 +struct physdev_irq { + /* IN */ + uint32_t irq; + /* IN or OUT */ + uint32_t vector; +}; + +/* + * Argument to physdev_op_compat() hypercall. Superceded by new physdev_op() + * hypercall since 0x00030202. + */ +struct physdev_op { + uint32_t cmd; + union { + struct physdev_irq_status_query irq_status_query; + struct physdev_set_iopl set_iopl; + struct physdev_set_iobitmap set_iobitmap; + struct physdev_apic apic_op; + struct physdev_irq irq_op; + } u; +}; + +/* + * Notify that some PIRQ-bound event channels have been unmasked. + * ** This command is obsolete since interface version 0x00030202 and is ** + * ** unsupported by newer versions of Xen. ** + */ +#define PHYSDEVOP_IRQ_UNMASK_NOTIFY 4 + +/* + * These all-capitals physdev operation names are superceded by the new names + * (defined above) since interface version 0x00030202. + */ +#define PHYSDEVOP_IRQ_STATUS_QUERY PHYSDEVOP_irq_status_query +#define PHYSDEVOP_SET_IOPL PHYSDEVOP_set_iopl +#define PHYSDEVOP_SET_IOBITMAP PHYSDEVOP_set_iobitmap +#define PHYSDEVOP_APIC_READ PHYSDEVOP_apic_read +#define PHYSDEVOP_APIC_WRITE PHYSDEVOP_apic_write +#define PHYSDEVOP_ASSIGN_VECTOR PHYSDEVOP_alloc_irq_vector +#define PHYSDEVOP_FREE_VECTOR PHYSDEVOP_free_irq_vector +#define PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY XENIRQSTAT_needs_eoi +#define PHYSDEVOP_IRQ_SHARED XENIRQSTAT_shared + +#endif /* __XEN_PUBLIC_PHYSDEV_H__ */ diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h new file mode 100644 index 00000000000..5fec575a800 --- /dev/null +++ b/include/xen/interface/sched.h @@ -0,0 +1,77 @@ +/****************************************************************************** + * sched.h + * + * Scheduler state interactions + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_SCHED_H__ +#define __XEN_PUBLIC_SCHED_H__ + +#include "event_channel.h" + +/* + * The prototype for this hypercall is: + * long sched_op_new(int cmd, void *arg) + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == Operation-specific extra argument(s), as described below. + * + * **NOTE**: + * Versions of Xen prior to 3.0.2 provide only the following legacy version + * of this hypercall, supporting only the commands yield, block and shutdown: + * long sched_op(int cmd, unsigned long arg) + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == 0 (SCHEDOP_yield and SCHEDOP_block) + * == SHUTDOWN_* code (SCHEDOP_shutdown) + */ + +/* + * Voluntarily yield the CPU. + * @arg == NULL. + */ +#define SCHEDOP_yield 0 + +/* + * Block execution of this VCPU until an event is received for processing. + * If called with event upcalls masked, this operation will atomically + * reenable event delivery and check for pending events before blocking the + * VCPU. This avoids a "wakeup waiting" race. + * @arg == NULL. + */ +#define SCHEDOP_block 1 + +/* + * Halt execution of this domain (all VCPUs) and notify the system controller. + * @arg == pointer to sched_shutdown structure. + */ +#define SCHEDOP_shutdown 2 +struct sched_shutdown { + unsigned int reason; /* SHUTDOWN_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown); + +/* + * Poll a set of event-channel ports. Return when one or more are pending. An + * optional timeout may be specified. + * @arg == pointer to sched_poll structure. + */ +#define SCHEDOP_poll 3 +struct sched_poll { + GUEST_HANDLE(evtchn_port_t) ports; + unsigned int nr_ports; + uint64_t timeout; +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_poll); + +/* + * Reason codes for SCHEDOP_shutdown. These may be interpreted by control + * software to determine the appropriate action. For the most part, Xen does + * not care about the shutdown code. + */ +#define SHUTDOWN_poweroff 0 /* Domain exited normally. Clean up and kill. */ +#define SHUTDOWN_reboot 1 /* Clean up, kill, and then restart. */ +#define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */ +#define SHUTDOWN_crash 3 /* Tell controller we've crashed. */ + +#endif /* __XEN_PUBLIC_SCHED_H__ */ diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h new file mode 100644 index 00000000000..ff61ea36599 --- /dev/null +++ b/include/xen/interface/vcpu.h @@ -0,0 +1,167 @@ +/****************************************************************************** + * vcpu.h + * + * VCPU initialisation, query, and hotplug. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_VCPU_H__ +#define __XEN_PUBLIC_VCPU_H__ + +/* + * Prototype for this hypercall is: + * int vcpu_op(int cmd, int vcpuid, void *extra_args) + * @cmd == VCPUOP_??? (VCPU operation). + * @vcpuid == VCPU to operate on. + * @extra_args == Operation-specific extra arguments (NULL if none). + */ + +/* + * Initialise a VCPU. Each VCPU can be initialised only once. A + * newly-initialised VCPU will not run until it is brought up by VCPUOP_up. + * + * @extra_arg == pointer to vcpu_guest_context structure containing initial + * state for the VCPU. + */ +#define VCPUOP_initialise 0 + +/* + * Bring up a VCPU. This makes the VCPU runnable. This operation will fail + * if the VCPU has not been initialised (VCPUOP_initialise). + */ +#define VCPUOP_up 1 + +/* + * Bring down a VCPU (i.e., make it non-runnable). + * There are a few caveats that callers should observe: + * 1. This operation may return, and VCPU_is_up may return false, before the + * VCPU stops running (i.e., the command is asynchronous). It is a good + * idea to ensure that the VCPU has entered a non-critical loop before + * bringing it down. Alternatively, this operation is guaranteed + * synchronous if invoked by the VCPU itself. + * 2. After a VCPU is initialised, there is currently no way to drop all its + * references to domain memory. Even a VCPU that is down still holds + * memory references via its pagetable base pointer and GDT. It is good + * practise to move a VCPU onto an 'idle' or default page table, LDT and + * GDT before bringing it down. + */ +#define VCPUOP_down 2 + +/* Returns 1 if the given VCPU is up. */ +#define VCPUOP_is_up 3 + +/* + * Return information about the state and running time of a VCPU. + * @extra_arg == pointer to vcpu_runstate_info structure. + */ +#define VCPUOP_get_runstate_info 4 +struct vcpu_runstate_info { + /* VCPU's current state (RUNSTATE_*). */ + int state; + /* When was current state entered (system time, ns)? */ + uint64_t state_entry_time; + /* + * Time spent in each RUNSTATE_* (ns). The sum of these times is + * guaranteed not to drift from system time. + */ + uint64_t time[4]; +}; + +/* VCPU is currently running on a physical CPU. */ +#define RUNSTATE_running 0 + +/* VCPU is runnable, but not currently scheduled on any physical CPU. */ +#define RUNSTATE_runnable 1 + +/* VCPU is blocked (a.k.a. idle). It is therefore not runnable. */ +#define RUNSTATE_blocked 2 + +/* + * VCPU is not runnable, but it is not blocked. + * This is a 'catch all' state for things like hotplug and pauses by the + * system administrator (or for critical sections in the hypervisor). + * RUNSTATE_blocked dominates this state (it is the preferred state). + */ +#define RUNSTATE_offline 3 + +/* + * Register a shared memory area from which the guest may obtain its own + * runstate information without needing to execute a hypercall. + * Notes: + * 1. The registered address may be virtual or physical, depending on the + * platform. The virtual address should be registered on x86 systems. + * 2. Only one shared area may be registered per VCPU. The shared area is + * updated by the hypervisor each time the VCPU is scheduled. Thus + * runstate.state will always be RUNSTATE_running and + * runstate.state_entry_time will indicate the system time at which the + * VCPU was last scheduled to run. + * @extra_arg == pointer to vcpu_register_runstate_memory_area structure. + */ +#define VCPUOP_register_runstate_memory_area 5 +struct vcpu_register_runstate_memory_area { + union { + struct vcpu_runstate_info *v; + uint64_t p; + } addr; +}; + +/* + * Set or stop a VCPU's periodic timer. Every VCPU has one periodic timer + * which can be set via these commands. Periods smaller than one millisecond + * may not be supported. + */ +#define VCPUOP_set_periodic_timer 6 /* arg == vcpu_set_periodic_timer_t */ +#define VCPUOP_stop_periodic_timer 7 /* arg == NULL */ +struct vcpu_set_periodic_timer { + uint64_t period_ns; +}; + +/* + * Set or stop a VCPU's single-shot timer. Every VCPU has one single-shot + * timer which can be set via these commands. + */ +#define VCPUOP_set_singleshot_timer 8 /* arg == vcpu_set_singleshot_timer_t */ +#define VCPUOP_stop_singleshot_timer 9 /* arg == NULL */ +struct vcpu_set_singleshot_timer { + uint64_t timeout_abs_ns; + uint32_t flags; /* VCPU_SSHOTTMR_??? */ +}; + +/* Flags to VCPUOP_set_singleshot_timer. */ + /* Require the timeout to be in the future (return -ETIME if it's passed). */ +#define _VCPU_SSHOTTMR_future (0) +#define VCPU_SSHOTTMR_future (1U << _VCPU_SSHOTTMR_future) + +/* + * Register a memory location in the guest address space for the + * vcpu_info structure. This allows the guest to place the vcpu_info + * structure in a convenient place, such as in a per-cpu data area. + * The pointer need not be page aligned, but the structure must not + * cross a page boundary. + */ +#define VCPUOP_register_vcpu_info 10 /* arg == struct vcpu_info */ +struct vcpu_register_vcpu_info { + uint32_t mfn; /* mfn of page to place vcpu_info */ + uint32_t offset; /* offset within page */ +}; + +#endif /* __XEN_PUBLIC_VCPU_H__ */ diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h new file mode 100644 index 00000000000..453235e923f --- /dev/null +++ b/include/xen/interface/version.h @@ -0,0 +1,60 @@ +/****************************************************************************** + * version.h + * + * Xen version, type, and compile information. + * + * Copyright (c) 2005, Nguyen Anh Quynh <aquynh@gmail.com> + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_VERSION_H__ +#define __XEN_PUBLIC_VERSION_H__ + +/* NB. All ops return zero on success, except XENVER_version. */ + +/* arg == NULL; returns major:minor (16:16). */ +#define XENVER_version 0 + +/* arg == xen_extraversion_t. */ +#define XENVER_extraversion 1 +struct xen_extraversion { + char extraversion[16]; +}; +#define XEN_EXTRAVERSION_LEN (sizeof(struct xen_extraversion)) + +/* arg == xen_compile_info_t. */ +#define XENVER_compile_info 2 +struct xen_compile_info { + char compiler[64]; + char compile_by[16]; + char compile_domain[32]; + char compile_date[32]; +}; + +#define XENVER_capabilities 3 +struct xen_capabilities_info { + char info[1024]; +}; +#define XEN_CAPABILITIES_INFO_LEN (sizeof(struct xen_capabilities_info)) + +#define XENVER_changeset 4 +struct xen_changeset_info { + char info[64]; +}; +#define XEN_CHANGESET_INFO_LEN (sizeof(struct xen_changeset_info)) + +#define XENVER_platform_parameters 5 +struct xen_platform_parameters { + unsigned long virt_start; +}; + +#define XENVER_get_features 6 +struct xen_feature_info { + unsigned int submap_idx; /* IN: which 32-bit submap to return */ + uint32_t submap; /* OUT: 32-bit submap */ +}; + +/* Declares the features reported by XENVER_get_features. */ +#include "features.h" + +#endif /* __XEN_PUBLIC_VERSION_H__ */ diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h new file mode 100644 index 00000000000..518a5bf79ed --- /dev/null +++ b/include/xen/interface/xen.h @@ -0,0 +1,447 @@ +/****************************************************************************** + * xen.h + * + * Guest OS interface to Xen. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_XEN_H__ +#define __XEN_PUBLIC_XEN_H__ + +#include <asm/xen/interface.h> + +/* + * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS). + */ + +/* + * x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5. + * EAX = return value + * (argument registers may be clobbered on return) + * x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6. + * RAX = return value + * (argument registers not clobbered on return; RCX, R11 are) + */ +#define __HYPERVISOR_set_trap_table 0 +#define __HYPERVISOR_mmu_update 1 +#define __HYPERVISOR_set_gdt 2 +#define __HYPERVISOR_stack_switch 3 +#define __HYPERVISOR_set_callbacks 4 +#define __HYPERVISOR_fpu_taskswitch 5 +#define __HYPERVISOR_sched_op 6 +#define __HYPERVISOR_dom0_op 7 +#define __HYPERVISOR_set_debugreg 8 +#define __HYPERVISOR_get_debugreg 9 +#define __HYPERVISOR_update_descriptor 10 +#define __HYPERVISOR_memory_op 12 +#define __HYPERVISOR_multicall 13 +#define __HYPERVISOR_update_va_mapping 14 +#define __HYPERVISOR_set_timer_op 15 +#define __HYPERVISOR_event_channel_op_compat 16 +#define __HYPERVISOR_xen_version 17 +#define __HYPERVISOR_console_io 18 +#define __HYPERVISOR_physdev_op_compat 19 +#define __HYPERVISOR_grant_table_op 20 +#define __HYPERVISOR_vm_assist 21 +#define __HYPERVISOR_update_va_mapping_otherdomain 22 +#define __HYPERVISOR_iret 23 /* x86 only */ +#define __HYPERVISOR_vcpu_op 24 +#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */ +#define __HYPERVISOR_mmuext_op 26 +#define __HYPERVISOR_acm_op 27 +#define __HYPERVISOR_nmi_op 28 +#define __HYPERVISOR_sched_op_new 29 +#define __HYPERVISOR_callback_op 30 +#define __HYPERVISOR_xenoprof_op 31 +#define __HYPERVISOR_event_channel_op 32 +#define __HYPERVISOR_physdev_op 33 +#define __HYPERVISOR_hvm_op 34 + +/* + * VIRTUAL INTERRUPTS + * + * Virtual interrupts that a guest OS may receive from Xen. + */ +#define VIRQ_TIMER 0 /* Timebase update, and/or requested timeout. */ +#define VIRQ_DEBUG 1 /* Request guest to dump debug info. */ +#define VIRQ_CONSOLE 2 /* (DOM0) Bytes received on emergency console. */ +#define VIRQ_DOM_EXC 3 /* (DOM0) Exceptional event for some domain. */ +#define VIRQ_DEBUGGER 6 /* (DOM0) A domain has paused for debugging. */ +#define NR_VIRQS 8 + +/* + * MMU-UPDATE REQUESTS + * + * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs. + * A foreigndom (FD) can be specified (or DOMID_SELF for none). + * Where the FD has some effect, it is described below. + * ptr[1:0] specifies the appropriate MMU_* command. + * + * ptr[1:0] == MMU_NORMAL_PT_UPDATE: + * Updates an entry in a page table. If updating an L1 table, and the new + * table entry is valid/present, the mapped frame must belong to the FD, if + * an FD has been specified. If attempting to map an I/O page then the + * caller assumes the privilege of the FD. + * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller. + * FD == DOMID_XEN: Map restricted areas of Xen's heap space. + * ptr[:2] -- Machine address of the page-table entry to modify. + * val -- Value to write. + * + * ptr[1:0] == MMU_MACHPHYS_UPDATE: + * Updates an entry in the machine->pseudo-physical mapping table. + * ptr[:2] -- Machine address within the frame whose mapping to modify. + * The frame must belong to the FD, if one is specified. + * val -- Value to write into the mapping entry. + */ +#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */ +#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */ + +/* + * MMU EXTENDED OPERATIONS + * + * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. + * A foreigndom (FD) can be specified (or DOMID_SELF for none). + * Where the FD has some effect, it is described below. + * + * cmd: MMUEXT_(UN)PIN_*_TABLE + * mfn: Machine frame number to be (un)pinned as a p.t. page. + * The frame must belong to the FD, if one is specified. + * + * cmd: MMUEXT_NEW_BASEPTR + * mfn: Machine frame number of new page-table base to install in MMU. + * + * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only] + * mfn: Machine frame number of new page-table base to install in MMU + * when in user space. + * + * cmd: MMUEXT_TLB_FLUSH_LOCAL + * No additional arguments. Flushes local TLB. + * + * cmd: MMUEXT_INVLPG_LOCAL + * linear_addr: Linear address to be flushed from the local TLB. + * + * cmd: MMUEXT_TLB_FLUSH_MULTI + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_INVLPG_MULTI + * linear_addr: Linear address to be flushed. + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_TLB_FLUSH_ALL + * No additional arguments. Flushes all VCPUs' TLBs. + * + * cmd: MMUEXT_INVLPG_ALL + * linear_addr: Linear address to be flushed from all VCPUs' TLBs. + * + * cmd: MMUEXT_FLUSH_CACHE + * No additional arguments. Writes back and flushes cache contents. + * + * cmd: MMUEXT_SET_LDT + * linear_addr: Linear address of LDT base (NB. must be page-aligned). + * nr_ents: Number of entries in LDT. + */ +#define MMUEXT_PIN_L1_TABLE 0 +#define MMUEXT_PIN_L2_TABLE 1 +#define MMUEXT_PIN_L3_TABLE 2 +#define MMUEXT_PIN_L4_TABLE 3 +#define MMUEXT_UNPIN_TABLE 4 +#define MMUEXT_NEW_BASEPTR 5 +#define MMUEXT_TLB_FLUSH_LOCAL 6 +#define MMUEXT_INVLPG_LOCAL 7 +#define MMUEXT_TLB_FLUSH_MULTI 8 +#define MMUEXT_INVLPG_MULTI 9 +#define MMUEXT_TLB_FLUSH_ALL 10 +#define MMUEXT_INVLPG_ALL 11 +#define MMUEXT_FLUSH_CACHE 12 +#define MMUEXT_SET_LDT 13 +#define MMUEXT_NEW_USER_BASEPTR 15 + +#ifndef __ASSEMBLY__ +struct mmuext_op { + unsigned int cmd; + union { + /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */ + unsigned long mfn; + /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */ + unsigned long linear_addr; + } arg1; + union { + /* SET_LDT */ + unsigned int nr_ents; + /* TLB_FLUSH_MULTI, INVLPG_MULTI */ + void *vcpumask; + } arg2; +}; +DEFINE_GUEST_HANDLE_STRUCT(mmuext_op); +#endif + +/* These are passed as 'flags' to update_va_mapping. They can be ORed. */ +/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */ +/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */ +#define UVMF_NONE (0UL<<0) /* No flushing at all. */ +#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */ +#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */ +#define UVMF_FLUSHTYPE_MASK (3UL<<0) +#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */ +#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */ +#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */ + +/* + * Commands to HYPERVISOR_console_io(). + */ +#define CONSOLEIO_write 0 +#define CONSOLEIO_read 1 + +/* + * Commands to HYPERVISOR_vm_assist(). + */ +#define VMASST_CMD_enable 0 +#define VMASST_CMD_disable 1 +#define VMASST_TYPE_4gb_segments 0 +#define VMASST_TYPE_4gb_segments_notify 1 +#define VMASST_TYPE_writable_pagetables 2 +#define VMASST_TYPE_pae_extended_cr3 3 +#define MAX_VMASST_TYPE 3 + +#ifndef __ASSEMBLY__ + +typedef uint16_t domid_t; + +/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */ +#define DOMID_FIRST_RESERVED (0x7FF0U) + +/* DOMID_SELF is used in certain contexts to refer to oneself. */ +#define DOMID_SELF (0x7FF0U) + +/* + * DOMID_IO is used to restrict page-table updates to mapping I/O memory. + * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO + * is useful to ensure that no mappings to the OS's own heap are accidentally + * installed. (e.g., in Linux this could cause havoc as reference counts + * aren't adjusted on the I/O-mapping code path). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can + * be specified by any calling domain. + */ +#define DOMID_IO (0x7FF1U) + +/* + * DOMID_XEN is used to allow privileged domains to map restricted parts of + * Xen's heap space (e.g., the machine_to_phys table). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if + * the caller is privileged. + */ +#define DOMID_XEN (0x7FF2U) + +/* + * Send an array of these to HYPERVISOR_mmu_update(). + * NB. The fields are natural pointer/address size for this architecture. + */ +struct mmu_update { + uint64_t ptr; /* Machine address of PTE. */ + uint64_t val; /* New contents of PTE. */ +}; +DEFINE_GUEST_HANDLE_STRUCT(mmu_update); + +/* + * Send an array of these to HYPERVISOR_multicall(). + * NB. The fields are natural register size for this architecture. + */ +struct multicall_entry { + unsigned long op; + long result; + unsigned long args[6]; +}; +DEFINE_GUEST_HANDLE_STRUCT(multicall_entry); + +/* + * Event channel endpoints per domain: + * 1024 if a long is 32 bits; 4096 if a long is 64 bits. + */ +#define NR_EVENT_CHANNELS (sizeof(unsigned long) * sizeof(unsigned long) * 64) + +struct vcpu_time_info { + /* + * Updates to the following values are preceded and followed + * by an increment of 'version'. The guest can therefore + * detect updates by looking for changes to 'version'. If the + * least-significant bit of the version number is set then an + * update is in progress and the guest must wait to read a + * consistent set of values. The correct way to interact with + * the version number is similar to Linux's seqlock: see the + * implementations of read_seqbegin/read_seqretry. + */ + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; /* TSC at last update of time vals. */ + uint64_t system_time; /* Time, in nanosecs, since boot. */ + /* + * Current system time: + * system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul + * CPU frequency (Hz): + * ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift + */ + uint32_t tsc_to_system_mul; + int8_t tsc_shift; + int8_t pad1[3]; +}; /* 32 bytes */ + +struct vcpu_info { + /* + * 'evtchn_upcall_pending' is written non-zero by Xen to indicate + * a pending notification for a particular VCPU. It is then cleared + * by the guest OS /before/ checking for pending work, thus avoiding + * a set-and-check race. Note that the mask is only accessed by Xen + * on the CPU that is currently hosting the VCPU. This means that the + * pending and mask flags can be updated by the guest without special + * synchronisation (i.e., no need for the x86 LOCK prefix). + * This may seem suboptimal because if the pending flag is set by + * a different CPU then an IPI may be scheduled even when the mask + * is set. However, note: + * 1. The task of 'interrupt holdoff' is covered by the per-event- + * channel mask bits. A 'noisy' event that is continually being + * triggered can be masked at source at this very precise + * granularity. + * 2. The main purpose of the per-VCPU mask is therefore to restrict + * reentrant execution: whether for concurrency control, or to + * prevent unbounded stack usage. Whatever the purpose, we expect + * that the mask will be asserted only for short periods at a time, + * and so the likelihood of a 'spurious' IPI is suitably small. + * The mask is read before making an event upcall to the guest: a + * non-zero mask therefore guarantees that the VCPU will not receive + * an upcall activation. The mask is cleared when the VCPU requests + * to block: this avoids wakeup-waiting races. + */ + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct vcpu_time_info time; +}; /* 64 bytes (x86) */ + +/* + * Xen/kernel shared data -- pointer provided in start_info. + * NB. We expect that this struct is smaller than a page. + */ +struct shared_info { + struct vcpu_info vcpu_info[MAX_VIRT_CPUS]; + + /* + * A domain can create "event channels" on which it can send and receive + * asynchronous event notifications. There are three classes of event that + * are delivered by this mechanism: + * 1. Bi-directional inter- and intra-domain connections. Domains must + * arrange out-of-band to set up a connection (usually by allocating + * an unbound 'listener' port and avertising that via a storage service + * such as xenstore). + * 2. Physical interrupts. A domain with suitable hardware-access + * privileges can bind an event-channel port to a physical interrupt + * source. + * 3. Virtual interrupts ('events'). A domain can bind an event-channel + * port to a virtual interrupt source, such as the virtual-timer + * device or the emergency console. + * + * Event channels are addressed by a "port index". Each channel is + * associated with two bits of information: + * 1. PENDING -- notifies the domain that there is a pending notification + * to be processed. This bit is cleared by the guest. + * 2. MASK -- if this bit is clear then a 0->1 transition of PENDING + * will cause an asynchronous upcall to be scheduled. This bit is only + * updated by the guest. It is read-only within Xen. If a channel + * becomes pending while the channel is masked then the 'edge' is lost + * (i.e., when the channel is unmasked, the guest must manually handle + * pending notifications as no upcall will be scheduled by Xen). + * + * To expedite scanning of pending notifications, any 0->1 pending + * transition on an unmasked channel causes a corresponding bit in a + * per-vcpu selector word to be set. Each bit in the selector covers a + * 'C long' in the PENDING bitfield array. + */ + unsigned long evtchn_pending[sizeof(unsigned long) * 8]; + unsigned long evtchn_mask[sizeof(unsigned long) * 8]; + + /* + * Wallclock time: updated only by control software. Guests should base + * their gettimeofday() syscall on this wallclock-base value. + */ + uint32_t wc_version; /* Version counter: see vcpu_time_info_t. */ + uint32_t wc_sec; /* Secs 00:00:00 UTC, Jan 1, 1970. */ + uint32_t wc_nsec; /* Nsecs 00:00:00 UTC, Jan 1, 1970. */ + + struct arch_shared_info arch; + +}; + +/* + * Start-of-day memory layout for the initial domain (DOM0): + * 1. The domain is started within contiguous virtual-memory region. + * 2. The contiguous region begins and ends on an aligned 4MB boundary. + * 3. The region start corresponds to the load address of the OS image. + * If the load address is not 4MB aligned then the address is rounded down. + * 4. This the order of bootstrap elements in the initial virtual region: + * a. relocated kernel image + * b. initial ram disk [mod_start, mod_len] + * c. list of allocated page frames [mfn_list, nr_pages] + * d. start_info_t structure [register ESI (x86)] + * e. bootstrap page tables [pt_base, CR3 (x86)] + * f. bootstrap stack [register ESP (x86)] + * 5. Bootstrap elements are packed together, but each is 4kB-aligned. + * 6. The initial ram disk may be omitted. + * 7. The list of page frames forms a contiguous 'pseudo-physical' memory + * layout for the domain. In particular, the bootstrap virtual-memory + * region is a 1:1 mapping to the first section of the pseudo-physical map. + * 8. All bootstrap elements are mapped read-writable for the guest OS. The + * only exception is the bootstrap page table, which is mapped read-only. + * 9. There is guaranteed to be at least 512kB padding after the final + * bootstrap element. If necessary, the bootstrap virtual region is + * extended by an extra 4MB to ensure this. + */ + +#define MAX_GUEST_CMDLINE 1024 +struct start_info { + /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */ + char magic[32]; /* "xen-<version>-<platform>". */ + unsigned long nr_pages; /* Total pages allocated to this domain. */ + unsigned long shared_info; /* MACHINE address of shared info struct. */ + uint32_t flags; /* SIF_xxx flags. */ + unsigned long store_mfn; /* MACHINE page number of shared page. */ + uint32_t store_evtchn; /* Event channel for store communication. */ + union { + struct { + unsigned long mfn; /* MACHINE page number of console page. */ + uint32_t evtchn; /* Event channel for console page. */ + } domU; + struct { + uint32_t info_off; /* Offset of console_info struct. */ + uint32_t info_size; /* Size of console_info struct from start.*/ + } dom0; + } console; + /* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */ + unsigned long pt_base; /* VIRTUAL address of page directory. */ + unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */ + unsigned long mfn_list; /* VIRTUAL address of page-frame list. */ + unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */ + unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ + int8_t cmd_line[MAX_GUEST_CMDLINE]; +}; + +/* These flags are passed in the 'flags' field of start_info_t. */ +#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */ +#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */ + +typedef uint64_t cpumap_t; + +typedef uint8_t xen_domain_handle_t[16]; + +/* Turn a plain number into a C unsigned long constant. */ +#define __mk_unsigned_long(x) x ## UL +#define mk_unsigned_long(x) __mk_unsigned_long(x) + +#else /* __ASSEMBLY__ */ + +/* In assembly code we cannot use C numeric constant suffixes. */ +#define mk_unsigned_long(x) x + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_XEN_H__ */ diff --git a/include/xen/page.h b/include/xen/page.h new file mode 100644 index 00000000000..1df6c193057 --- /dev/null +++ b/include/xen/page.h @@ -0,0 +1,179 @@ +#ifndef __XEN_PAGE_H +#define __XEN_PAGE_H + +#include <linux/pfn.h> + +#include <asm/uaccess.h> + +#include <xen/features.h> + +#ifdef CONFIG_X86_PAE +/* Xen machine address */ +typedef struct xmaddr { + unsigned long long maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + unsigned long long paddr; +} xpaddr_t; +#else +/* Xen machine address */ +typedef struct xmaddr { + unsigned long maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + unsigned long paddr; +} xpaddr_t; +#endif + +#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)) + +#ifdef CONFIG_X86_PAE +#define pte_mfn(_pte) (((_pte).pte_low >> PAGE_SHIFT) | \ + (((_pte).pte_high & 0xfff) << (32-PAGE_SHIFT))) + +static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + pte.pte_high = (page_nr >> (32 - PAGE_SHIFT)) | + (pgprot_val(pgprot) >> 32); + pte.pte_high &= (__supported_pte_mask >> 32); + pte.pte_low = ((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); + pte.pte_low &= __supported_pte_mask; + + return pte; +} + +static inline unsigned long long pte_val_ma(pte_t x) +{ + return ((unsigned long long)x.pte_high << 32) | x.pte_low; +} +#define pmd_val_ma(v) ((v).pmd) +#define pud_val_ma(v) ((v).pgd.pgd) +#define __pte_ma(x) ((pte_t) { .pte_low = (x), .pte_high = (x)>>32 } ) +#define __pmd_ma(x) ((pmd_t) { (x) } ) +#else /* !X86_PAE */ +#define pte_mfn(_pte) ((_pte).pte_low >> PAGE_SHIFT) +#define mfn_pte(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pte_val_ma(x) ((x).pte_low) +#define pmd_val_ma(v) ((v).pud.pgd.pgd) +#define __pte_ma(x) ((pte_t) { (x) } ) +#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 */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h new file mode 100644 index 00000000000..6f7c290651a --- /dev/null +++ b/include/xen/xenbus.h @@ -0,0 +1,234 @@ +/****************************************************************************** + * xenbus.h + * + * Talks to Xen Store to figure out what devices we have. + * + * Copyright (C) 2005 Rusty Russell, IBM Corporation + * Copyright (C) 2005 XenSource Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _XEN_XENBUS_H +#define _XEN_XENBUS_H + +#include <linux/device.h> +#include <linux/notifier.h> +#include <linux/mutex.h> +#include <linux/completion.h> +#include <linux/init.h> +#include <xen/interface/xen.h> +#include <xen/interface/grant_table.h> +#include <xen/interface/io/xenbus.h> +#include <xen/interface/io/xs_wire.h> + +/* Register callback to watch this node. */ +struct xenbus_watch +{ + struct list_head list; + + /* Path being watched. */ + const char *node; + + /* Callback (executed in a process context with no locks held). */ + void (*callback)(struct xenbus_watch *, + const char **vec, unsigned int len); +}; + + +/* A xenbus device. */ +struct xenbus_device { + const char *devicetype; + const char *nodename; + const char *otherend; + int otherend_id; + struct xenbus_watch otherend_watch; + struct device dev; + enum xenbus_state state; + struct completion down; +}; + +static inline struct xenbus_device *to_xenbus_device(struct device *dev) +{ + return container_of(dev, struct xenbus_device, dev); +} + +struct xenbus_device_id +{ + /* .../device/<device_type>/<identifier> */ + char devicetype[32]; /* General class of device. */ +}; + +/* A xenbus driver. */ +struct xenbus_driver { + char *name; + struct module *owner; + const struct xenbus_device_id *ids; + int (*probe)(struct xenbus_device *dev, + const struct xenbus_device_id *id); + void (*otherend_changed)(struct xenbus_device *dev, + enum xenbus_state backend_state); + int (*remove)(struct xenbus_device *dev); + int (*suspend)(struct xenbus_device *dev); + int (*suspend_cancel)(struct xenbus_device *dev); + int (*resume)(struct xenbus_device *dev); + int (*uevent)(struct xenbus_device *, char **, int, char *, int); + struct device_driver driver; + int (*read_otherend_details)(struct xenbus_device *dev); +}; + +static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv) +{ + return container_of(drv, struct xenbus_driver, driver); +} + +int __must_check __xenbus_register_frontend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); + +static inline int __must_check +xenbus_register_frontend(struct xenbus_driver *drv) +{ + WARN_ON(drv->owner != THIS_MODULE); + return __xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME); +} + +int __must_check __xenbus_register_backend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); +static inline int __must_check +xenbus_register_backend(struct xenbus_driver *drv) +{ + WARN_ON(drv->owner != THIS_MODULE); + return __xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME); +} + +void xenbus_unregister_driver(struct xenbus_driver *drv); + +struct xenbus_transaction +{ + u32 id; +}; + +/* Nil transaction ID. */ +#define XBT_NIL ((struct xenbus_transaction) { 0 }) + +int __init xenbus_dev_init(void); + +char **xenbus_directory(struct xenbus_transaction t, + const char *dir, const char *node, unsigned int *num); +void *xenbus_read(struct xenbus_transaction t, + const char *dir, const char *node, unsigned int *len); +int xenbus_write(struct xenbus_transaction t, + const char *dir, const char *node, const char *string); +int xenbus_mkdir(struct xenbus_transaction t, + const char *dir, const char *node); +int xenbus_exists(struct xenbus_transaction t, + const char *dir, const char *node); +int xenbus_rm(struct xenbus_transaction t, const char *dir, const char *node); +int xenbus_transaction_start(struct xenbus_transaction *t); +int xenbus_transaction_end(struct xenbus_transaction t, int abort); + +/* Single read and scanf: returns -errno or num scanned if > 0. */ +int xenbus_scanf(struct xenbus_transaction t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(scanf, 4, 5))); + +/* Single printf and write: returns -errno or 0. */ +int xenbus_printf(struct xenbus_transaction t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(printf, 4, 5))); + +/* Generic read function: NULL-terminated triples of name, + * sprintf-style type string, and pointer. Returns 0 or errno.*/ +int xenbus_gather(struct xenbus_transaction t, const char *dir, ...); + +/* notifer routines for when the xenstore comes up */ +extern int xenstored_ready; +int register_xenstore_notifier(struct notifier_block *nb); +void unregister_xenstore_notifier(struct notifier_block *nb); + +int register_xenbus_watch(struct xenbus_watch *watch); +void unregister_xenbus_watch(struct xenbus_watch *watch); +void xs_suspend(void); +void xs_resume(void); +void xs_suspend_cancel(void); + +/* Used by xenbus_dev to borrow kernel's store connection. */ +void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg); + +struct work_struct; + +/* Prepare for domain suspend: then resume or cancel the suspend. */ +void xenbus_suspend(void); +void xenbus_resume(void); +void xenbus_probe(struct work_struct *); +void xenbus_suspend_cancel(void); + +#define XENBUS_IS_ERR_READ(str) ({ \ + if (!IS_ERR(str) && strlen(str) == 0) { \ + kfree(str); \ + str = ERR_PTR(-ERANGE); \ + } \ + IS_ERR(str); \ +}) + +#define XENBUS_EXIST_ERR(err) ((err) == -ENOENT || (err) == -ERANGE) + +int xenbus_watch_path(struct xenbus_device *dev, const char *path, + struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int)); +int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int), + const char *pathfmt, ...) + __attribute__ ((format (printf, 4, 5))); + +int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); +int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); +int xenbus_map_ring_valloc(struct xenbus_device *dev, + int gnt_ref, void **vaddr); +int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref, + grant_handle_t *handle, void *vaddr); + +int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr); +int xenbus_unmap_ring(struct xenbus_device *dev, + grant_handle_t handle, void *vaddr); + +int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); +int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port); +int xenbus_free_evtchn(struct xenbus_device *dev, int port); + +enum xenbus_state xenbus_read_driver_state(const char *path); + +void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...); +void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...); + +const char *xenbus_strstate(enum xenbus_state state); +int xenbus_dev_is_online(struct xenbus_device *dev); +int xenbus_frontend_closed(struct xenbus_device *dev); + +#endif /* _XEN_XENBUS_H */ |