diff options
Diffstat (limited to 'include')
38 files changed, 2979 insertions, 332 deletions
diff --git a/include/asm-alpha/io.h b/include/asm-alpha/io.h index f5ae98c25d1..5d15af24573 100644 --- a/include/asm-alpha/io.h +++ b/include/asm-alpha/io.h @@ -533,19 +533,6 @@ extern void outsl (unsigned long port, const void *src, unsigned long count); #define eth_io_copy_and_sum(skb,src,len,unused) \ memcpy_fromio((skb)->data,src,len) -static inline int -check_signature(const volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - do { - if (readb(io_addr) != *signature) - return 0; - io_addr++; - signature++; - } while (--length); - return 1; -} - /* * The Alpha Jensen hardware for some rather strange reason puts * the RTC clock at 0x170 instead of 0x70. Probably due to some diff --git a/include/asm-arm/arch-versatile/hardware.h b/include/asm-arm/arch-versatile/hardware.h index 41c1bee342a..edc06598d18 100644 --- a/include/asm-arm/arch-versatile/hardware.h +++ b/include/asm-arm/arch-versatile/hardware.h @@ -28,8 +28,8 @@ /* * PCI space virtual addresses */ -#define VERSATILE_PCI_VIRT_BASE 0xe8000000 -#define VERSATILE_PCI_CFG_VIRT_BASE 0xe9000000 +#define VERSATILE_PCI_VIRT_BASE (void __iomem *)0xe8000000ul +#define VERSATILE_PCI_CFG_VIRT_BASE (void __iomem *)0xe9000000ul #if 0 #define VERSATILE_PCI_VIRT_MEM_BASE0 0xf4000000 diff --git a/include/asm-arm/io.h b/include/asm-arm/io.h index 34aaaac4f61..ae999fd5dc6 100644 --- a/include/asm-arm/io.h +++ b/include/asm-arm/io.h @@ -193,23 +193,6 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define eth_io_copy_and_sum(s,c,l,b) \ eth_copy_and_sum((s),__mem_pci(c),(l),(b)) -static inline int -check_signature(void __iomem *io_addr, const unsigned char *signature, - int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - #elif !defined(readb) #define readb(c) (__readwrite_bug("readb"),0) diff --git a/include/asm-arm/uaccess.h b/include/asm-arm/uaccess.h index 87aba57a66c..09ad0cab901 100644 --- a/include/asm-arm/uaccess.h +++ b/include/asm-arm/uaccess.h @@ -110,7 +110,7 @@ extern int __get_user_4(void *); #define get_user(x,p) \ ({ \ const register typeof(*(p)) __user *__p asm("r0") = (p);\ - register unsigned int __r2 asm("r2"); \ + register unsigned long __r2 asm("r2"); \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ case 1: \ diff --git a/include/asm-avr32/irq_regs.h b/include/asm-avr32/irq_regs.h new file mode 100644 index 00000000000..3dd9c0b7027 --- /dev/null +++ b/include/asm-avr32/irq_regs.h @@ -0,0 +1 @@ +#include <asm-generic/irq_regs.h> diff --git a/include/asm-frv/io.h b/include/asm-frv/io.h index 7765f552889..20e44fe00ab 100644 --- a/include/asm-frv/io.h +++ b/include/asm-frv/io.h @@ -385,27 +385,6 @@ static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) */ #define xlate_dev_kmem_ptr(p) p -/* - * Check BIOS signature - */ -static inline int check_signature(volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - - retval = 1; -out: - return retval; -} - #endif /* __KERNEL__ */ #endif /* _ASM_IO_H */ diff --git a/include/asm-generic/bitops/sched.h b/include/asm-generic/bitops/sched.h index 5ef93a4d009..815bb014806 100644 --- a/include/asm-generic/bitops/sched.h +++ b/include/asm-generic/bitops/sched.h @@ -15,7 +15,7 @@ static inline int sched_find_first_bit(const unsigned long *b) #if BITS_PER_LONG == 64 if (unlikely(b[0])) return __ffs(b[0]); - if (unlikely(b[1])) + if (likely(b[1])) return __ffs(b[1]) + 64; return __ffs(b[2]) + 128; #elif BITS_PER_LONG == 32 diff --git a/include/asm-i386/io.h b/include/asm-i386/io.h index b3724fe93ff..68df0dc3ab8 100644 --- a/include/asm-i386/io.h +++ b/include/asm-i386/io.h @@ -224,33 +224,6 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int #define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(b),(c),(d)) -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * Cache management * diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h index 54d905ebc63..eef5133b9ce 100644 --- a/include/asm-i386/uaccess.h +++ b/include/asm-i386/uaccess.h @@ -404,20 +404,6 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero(void *to, * anything, so this is accurate. */ -/** - * __copy_to_user: - Copy a block of data into user space, with less checking. - * @to: Destination address, in user space. - * @from: Source address, in kernel space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep. - * - * Copy data from kernel space to user space. Caller must check - * the specified block with access_ok() before calling this function. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - */ static __always_inline unsigned long __must_check __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { @@ -439,35 +425,27 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) return __copy_to_user_ll(to, from, n); } -static __always_inline unsigned long __must_check -__copy_to_user(void __user *to, const void *from, unsigned long n) -{ - might_sleep(); - return __copy_to_user_inatomic(to, from, n); -} - /** - * __copy_from_user: - Copy a block of data from user space, with less checking. - * @to: Destination address, in kernel space. - * @from: Source address, in user space. + * __copy_to_user: - Copy a block of data into user space, with less checking. + * @to: Destination address, in user space. + * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. This function may sleep. * - * Copy data from user space to kernel space. Caller must check + * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * * Returns number of bytes that could not be copied. * On success, this will be zero. - * - * If some data could not be copied, this function will pad the copied - * data to the requested size using zero bytes. - * - * An alternate version - __copy_from_user_inatomic() - may be called from - * atomic context and will fail rather than sleep. In this case the - * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h - * for explanation of why this is needed. */ +static __always_inline unsigned long __must_check +__copy_to_user(void __user *to, const void *from, unsigned long n) +{ + might_sleep(); + return __copy_to_user_inatomic(to, from, n); +} + static __always_inline unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { @@ -493,6 +471,29 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) } return __copy_from_user_ll_nozero(to, from, n); } + +/** + * __copy_from_user: - Copy a block of data from user space, with less checking. + * @to: Destination address, in kernel space. + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * + * Context: User context only. This function may sleep. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. + * + * Returns number of bytes that could not be copied. + * On success, this will be zero. + * + * If some data could not be copied, this function will pad the copied + * data to the requested size using zero bytes. + * + * An alternate version - __copy_from_user_inatomic() - may be called from + * atomic context and will fail rather than sleep. In this case the + * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h + * for explanation of why this is needed. + */ static __always_inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h index 3ca7ab963d7..beeeaf6b054 100644 --- a/include/asm-i386/unistd.h +++ b/include/asm-i386/unistd.h @@ -324,10 +324,11 @@ #define __NR_vmsplice 316 #define __NR_move_pages 317 #define __NR_getcpu 318 +#define __NR_epoll_pwait 319 #ifdef __KERNEL__ -#define NR_syscalls 319 +#define NR_syscalls 320 #include <linux/err.h> /* diff --git a/include/asm-m32r/io.h b/include/asm-m32r/io.h index 70ad1c949c2..d06933bd631 100644 --- a/include/asm-m32r/io.h +++ b/include/asm-m32r/io.h @@ -166,38 +166,6 @@ static inline void _writel(unsigned long l, unsigned long addr) #define flush_write_buffers() do { } while (0) /* M32R_FIXME */ -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the ISA mmio address io_addr. - * Returns 1 on a match. - * - * This function is deprecated. New drivers should use ioremap and - * check_signature. - */ - -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; -#if 0 -printk("check_signature\n"); - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: -#endif - return retval; -} - static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) { diff --git a/include/asm-m68k/uaccess.h b/include/asm-m68k/uaccess.h index 88b1f47400e..e4c9f080ff2 100644 --- a/include/asm-m68k/uaccess.h +++ b/include/asm-m68k/uaccess.h @@ -76,7 +76,7 @@ asm volatile ("\n" \ break; \ case 8: \ { \ - const void *__pu_ptr = (ptr); \ + const void __user *__pu_ptr = (ptr); \ asm volatile ("\n" \ "1: moves.l %2,(%1)+\n" \ "2: moves.l %R2,(%1)\n" \ @@ -125,7 +125,7 @@ asm volatile ("\n" \ " .previous" \ : "+d" (res), "=&" #reg (__gu_val) \ : "m" (*(ptr)), "i" (err)); \ - (x) = (typeof(*(ptr)))(long)__gu_val; \ + (x) = (typeof(*(ptr)))(unsigned long)__gu_val; \ }) #define __get_user(x, ptr) \ @@ -221,16 +221,16 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: - __get_user_asm(res, *(u8 *)to, (u8 *)from, u8, b, d, 1); + __get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1); break; case 2: - __get_user_asm(res, *(u16 *)to, (u16 *)from, u16, w, d, 2); + __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, d, 2); break; case 3: __constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __get_user_asm(res, *(u32 *)to, (u32 *)from, u32, l, r, 4); + __get_user_asm(res, *(u32 *)to, (u32 __user *)from, u32, l, r, 4); break; case 5: __constant_copy_from_user_asm(res, to, from, tmp, 5, l, b,); @@ -302,16 +302,16 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) switch (n) { case 1: - __put_user_asm(res, *(u8 *)from, (u8 *)to, b, d, 1); + __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1); break; case 2: - __put_user_asm(res, *(u16 *)from, (u16 *)to, w, d, 2); + __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, d, 2); break; case 3: __constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __put_user_asm(res, *(u32 *)from, (u32 *)to, l, r, 4); + __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4); break; case 5: __constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,); diff --git a/include/asm-mips/io.h b/include/asm-mips/io.h index df624e1ee6e..c2d124badbe 100644 --- a/include/asm-mips/io.h +++ b/include/asm-mips/io.h @@ -562,32 +562,6 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *); #define eth_io_copy_and_sum(skb,src,len,unused) memcpy_fromio((skb)->data,(src),(len)) /* - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ -static inline int check_signature(char __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - -/* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that * can be applied to dma buffers. diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h index cbbd8c648df..3baff8b0fd5 100644 --- a/include/asm-powerpc/io.h +++ b/include/asm-powerpc/io.h @@ -404,32 +404,6 @@ static inline void __out_be64(volatile unsigned long __iomem *addr, unsigned lon #include <asm/eeh.h> -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ -static inline int check_signature(const volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* Nothing to do */ #define dma_cache_inv(_start,_size) do { } while (0) diff --git a/include/asm-ppc/io.h b/include/asm-ppc/io.h index 3d9a9e6f332..a4c411b753e 100644 --- a/include/asm-ppc/io.h +++ b/include/asm-ppc/io.h @@ -439,22 +439,6 @@ extern inline void * phys_to_virt(unsigned long address) #define iobarrier_r() eieio() #define iobarrier_w() eieio() -static inline int check_signature(volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * Here comes the ppc implementation of the IOMAP * interfaces. diff --git a/include/asm-sh/io.h b/include/asm-sh/io.h index ed12d38e8c0..a0e55b09e4f 100644 --- a/include/asm-sh/io.h +++ b/include/asm-sh/io.h @@ -304,22 +304,6 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags) #define iounmap(addr) \ __iounmap((addr)) -static inline int check_signature(char __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that diff --git a/include/asm-sh64/io.h b/include/asm-sh64/io.h index 252fedbb662..14d8e7b4bf4 100644 --- a/include/asm-sh64/io.h +++ b/include/asm-sh64/io.h @@ -178,22 +178,6 @@ extern void iounmap(void *addr); unsigned long onchip_remap(unsigned long addr, unsigned long size, const char* name); extern void onchip_unmap(unsigned long vaddr); -static __inline__ int check_signature(volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that diff --git a/include/asm-sparc64/io.h b/include/asm-sparc64/io.h index 0056770e83a..30b912d8e8b 100644 --- a/include/asm-sparc64/io.h +++ b/include/asm-sparc64/io.h @@ -440,21 +440,6 @@ _memcpy_toio(volatile void __iomem *dst, const void *src, __kernel_size_t n) #define memcpy_toio(d,s,sz) _memcpy_toio(d,s,sz) -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, - int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature++) - goto out; - io_addr++; - } while (--length); - retval = 1; -out: - return retval; -} - #define mmiowb() #ifdef __KERNEL__ diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h index 70e91fe7634..6ee9fadaaac 100644 --- a/include/asm-x86_64/io.h +++ b/include/asm-x86_64/io.h @@ -254,33 +254,6 @@ void memset_io(volatile void __iomem *a, int b, size_t c); #define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(b),(c),(d)) -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* Nothing to do */ #define dma_cache_inv(_start,_size) do { } while (0) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcc5de7cc48..64b4641904f 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -46,7 +46,8 @@ * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf - * bitmap_parse(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf + * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf + * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from list * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region @@ -106,7 +107,9 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits); extern int bitmap_scnprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); -extern int bitmap_parse(const char __user *ubuf, unsigned int ulen, +extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, + unsigned long *dst, int nbits); +extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_scnlistprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); @@ -270,6 +273,12 @@ static inline void bitmap_shift_left(unsigned long *dst, __bitmap_shift_left(dst, src, n, nbits); } +static inline int bitmap_parse(const char *buf, unsigned int buflen, + unsigned long *maskp, int nmaskbits) +{ + return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/carta_random32.h b/include/linux/carta_random32.h new file mode 100644 index 00000000000..f6f3bd9f20b --- /dev/null +++ b/include/linux/carta_random32.h @@ -0,0 +1,29 @@ +/* + * Fast, simple, yet decent quality random number generator based on + * a paper by David G. Carta ("Two Fast Implementations of the + * `Minimal Standard' Random Number Generator," Communications of the + * ACM, January, 1990). + * + * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P. + * Contributed by Stephane Eranian <eranian@hpl.hp.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License 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 + */ +#ifndef _LINUX_CARTA_RANDOM32_H_ +#define _LINUX_CARTA_RANDOM32_H_ + +u64 carta_random32(u64 seed); + +#endif /* _LINUX_CARTA_RANDOM32_H_ */ diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 4e1663d7691..cfdb4f6a89d 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -61,17 +61,23 @@ COMPATIBLE_IOCTL(FIGETBSZ) * Some need translations, these do not. */ COMPATIBLE_IOCTL(HDIO_GET_IDENTITY) -COMPATIBLE_IOCTL(HDIO_SET_DMA) -COMPATIBLE_IOCTL(HDIO_SET_UNMASKINTR) -COMPATIBLE_IOCTL(HDIO_SET_NOWERR) -COMPATIBLE_IOCTL(HDIO_SET_32BIT) -COMPATIBLE_IOCTL(HDIO_SET_MULTCOUNT) -COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) COMPATIBLE_IOCTL(HDIO_DRIVE_TASK) -COMPATIBLE_IOCTL(HDIO_SET_PIO_MODE) -COMPATIBLE_IOCTL(HDIO_SET_NICE) -COMPATIBLE_IOCTL(HDIO_SET_KEEPSETTINGS) +COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) +ULONG_IOCTL(HDIO_SET_MULTCOUNT) +ULONG_IOCTL(HDIO_SET_UNMASKINTR) +ULONG_IOCTL(HDIO_SET_KEEPSETTINGS) +ULONG_IOCTL(HDIO_SET_32BIT) +ULONG_IOCTL(HDIO_SET_NOWERR) +ULONG_IOCTL(HDIO_SET_DMA) +ULONG_IOCTL(HDIO_SET_PIO_MODE) +ULONG_IOCTL(HDIO_SET_NICE) +ULONG_IOCTL(HDIO_SET_WCACHE) +ULONG_IOCTL(HDIO_SET_ACOUSTIC) +ULONG_IOCTL(HDIO_SET_BUSSTATE) +ULONG_IOCTL(HDIO_SET_ADDRESS) COMPATIBLE_IOCTL(HDIO_SCAN_HWIF) +/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */ +COMPATIBLE_IOCTL(0x330) /* 0x02 -- Floppy ioctls */ COMPATIBLE_IOCTL(FDMSGON) COMPATIBLE_IOCTL(FDMSGOFF) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b268a3c0c37..d0e8c8b0e34 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these cpumasks are based. * - * For details of cpumask_scnprintf() and cpumask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of cpumask_scnprintf() and cpumask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of cpulist_scnprintf() and cpulist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c @@ -49,7 +49,7 @@ * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing - * int cpumask_parse(ubuf, ulen, mask) Parse ascii string as cpumask + * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing * int cpulist_parse(buf, map) Parse ascii string as cpulist * int cpu_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -273,12 +273,12 @@ static inline int __cpumask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define cpumask_parse(ubuf, ulen, dst) \ - __cpumask_parse((ubuf), (ulen), &(dst), NR_CPUS) -static inline int __cpumask_parse(const char __user *buf, int len, +#define cpumask_parse_user(ubuf, ulen, dst) \ + __cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS) +static inline int __cpumask_parse_user(const char __user *buf, int len, cpumask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define cpulist_scnprintf(buf, len, src) \ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 44605be5940..63f64a9a5bf 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -230,6 +230,7 @@ extern struct dentry * d_alloc_anon(struct inode *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); +extern void shrink_dcache_for_umount(struct super_block *); extern int d_invalidate(struct dentry *); /* only used at mount-time */ diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h new file mode 100644 index 00000000000..498503ee613 --- /dev/null +++ b/include/linux/ext4_fs.h @@ -0,0 +1,994 @@ +/* + * linux/include/linux/ext4_fs.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_H +#define _LINUX_EXT4_FS_H + +#include <linux/types.h> +#include <linux/blkdev.h> +#include <linux/magic.h> + +/* + * The second extended filesystem constants/structures + */ + +/* + * Define EXT4FS_DEBUG to produce debug messages + */ +#undef EXT4FS_DEBUG + +/* + * Define EXT4_RESERVATION to reserve data blocks for expanding files + */ +#define EXT4_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT4_MAX_RESERVE_BLOCKS 1027 +#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0 +/* + * Always enable hashed directories + */ +#define CONFIG_EXT4_INDEX + +/* + * Debug code + */ +#ifdef EXT4FS_DEBUG +#define ext4_debug(f, a...) \ + do { \ + printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (KERN_DEBUG f, ## a); \ + } while (0) +#else +#define ext4_debug(f, a...) do {} while (0) +#endif + +/* + * Special inodes numbers + */ +#define EXT4_BAD_INO 1 /* Bad blocks inode */ +#define EXT4_ROOT_INO 2 /* Root inode */ +#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */ +#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */ +#define EXT4_JOURNAL_INO 8 /* Journal inode */ + +/* First non-reserved inode for old ext4 filesystems */ +#define EXT4_GOOD_OLD_FIRST_INO 11 + +/* + * Maximal count of links to a file + */ +#define EXT4_LINK_MAX 32000 + +/* + * Macro-instructions used to manage several block sizes + */ +#define EXT4_MIN_BLOCK_SIZE 1024 +#define EXT4_MAX_BLOCK_SIZE 4096 +#define EXT4_MIN_BLOCK_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) +#else +# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) +#endif +#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (__u32)) +#ifdef __KERNEL__ +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +#else +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) +#endif +#ifdef __KERNEL__ +#define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits) +#define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size) +#define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino) +#else +#define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_INODE_SIZE : \ + (s)->s_inode_size) +#define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_FIRST_INO : \ + (s)->s_first_ino) +#endif + +/* + * Macro-instructions used to manage fragments + */ +#define EXT4_MIN_FRAG_SIZE 1024 +#define EXT4_MAX_FRAG_SIZE 4096 +#define EXT4_MIN_FRAG_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT4_FRAG_SIZE(s) (EXT4_SB(s)->s_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_SB(s)->s_frags_per_block) +#else +# define EXT4_FRAG_SIZE(s) (EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s)) +#endif + +/* + * Structure of a blocks group descriptor + */ +struct ext4_group_desc +{ + __le32 bg_block_bitmap; /* Blocks bitmap block */ + __le32 bg_inode_bitmap; /* Inodes bitmap block */ + __le32 bg_inode_table; /* Inodes table block */ + __le16 bg_free_blocks_count; /* Free blocks count */ + __le16 bg_free_inodes_count; /* Free inodes count */ + __le16 bg_used_dirs_count; /* Directories count */ + __u16 bg_flags; + __u32 bg_reserved[3]; + __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ + __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ + __le32 bg_inode_table_hi; /* Inodes table block MSB */ +}; + +#ifdef __KERNEL__ +#include <linux/ext4_fs_i.h> +#include <linux/ext4_fs_sb.h> +#endif +/* + * Macro-instructions used to manage group descriptors + */ +#define EXT4_MIN_DESC_SIZE 32 +#define EXT4_MIN_DESC_SIZE_64BIT 64 +#define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE +#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) +#ifdef __KERNEL__ +# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) +# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) +# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) +#else +# define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s)) +# define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) +#endif + +/* + * Constants relative to the data blocks + */ +#define EXT4_NDIR_BLOCKS 12 +#define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS +#define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1) +#define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1) +#define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1) + +/* + * Inode flags + */ +#define EXT4_SECRM_FL 0x00000001 /* Secure deletion */ +#define EXT4_UNRM_FL 0x00000002 /* Undelete */ +#define EXT4_COMPR_FL 0x00000004 /* Compress file */ +#define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */ +#define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */ +#define EXT4_NODUMP_FL 0x00000040 /* do not dump file */ +#define EXT4_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define EXT4_DIRTY_FL 0x00000100 +#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ +#define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ +#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ + +#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + +/* + * Inode dynamic state flags + */ +#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 */ + +/* Used to pass group descriptor data when online resize is done */ +struct ext4_new_group_input { + __u32 group; /* Group number for this data */ + __u64 block_bitmap; /* Absolute block number of block bitmap */ + __u64 inode_bitmap; /* Absolute block number of inode bitmap */ + __u64 inode_table; /* Absolute block number of inode table start */ + __u32 blocks_count; /* Total number of blocks in this group */ + __u16 reserved_blocks; /* Number of reserved blocks in this group */ + __u16 unused; +}; + +/* The struct ext4_new_group_input in kernel space, with free_blocks_count */ +struct ext4_new_group_data { + __u32 group; + __u64 block_bitmap; + __u64 inode_bitmap; + __u64 inode_table; + __u32 blocks_count; + __u16 reserved_blocks; + __u16 unused; + __u32 free_blocks_count; +}; + + +/* + * ioctl commands + */ +#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT4_IOC_GETVERSION _IOR('f', 3, long) +#define EXT4_IOC_SETVERSION _IOW('f', 4, long) +#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) +#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 +#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) +#endif +#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT4_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT4_IOC32_SETVERSION _IOW('f', 4, int) +#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 +#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif +#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION + + +/* + * Mount options + */ +struct ext4_mount_options { + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned long s_commit_interval; +#ifdef CONFIG_QUOTA + int s_jquota_fmt; + char *s_qf_names[MAXQUOTAS]; +#endif +}; + +/* + * Structure of an inode on the disk + */ +struct ext4_inode { + __le16 i_mode; /* File mode */ + __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_mtime; /* Modification time */ + __le32 i_dtime; /* Deletion Time */ + __le16 i_gid; /* Low 16 bits of Group Id */ + __le16 i_links_count; /* Links count */ + __le32 i_blocks; /* Blocks count */ + __le32 i_flags; /* File flags */ + union { + struct { + __u32 l_i_reserved1; + } linux1; + struct { + __u32 h_i_translator; + } hurd1; + struct { + __u32 m_i_reserved1; + } masix1; + } osd1; /* OS dependent 1 */ + __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ + __le32 i_generation; /* File version (for NFS) */ + __le32 i_file_acl; /* File ACL */ + __le32 i_dir_acl; /* Directory ACL */ + __le32 i_faddr; /* Fragment address */ + union { + struct { + __u8 l_i_frag; /* Fragment number */ + __u8 l_i_fsize; /* Fragment size */ + __le16 l_i_file_acl_high; + __le16 l_i_uid_high; /* these 2 fields */ + __le16 l_i_gid_high; /* were reserved2[0] */ + __u32 l_i_reserved2; + } linux2; + struct { + __u8 h_i_frag; /* Fragment number */ + __u8 h_i_fsize; /* Fragment size */ + __u16 h_i_mode_high; + __u16 h_i_uid_high; + __u16 h_i_gid_high; + __u32 h_i_author; + } hurd2; + struct { + __u8 m_i_frag; /* Fragment number */ + __u8 m_i_fsize; /* Fragment size */ + __le16 m_i_file_acl_high; + __u32 m_i_reserved2[2]; + } masix2; + } osd2; /* OS dependent 2 */ + __le16 i_extra_isize; + __le16 i_pad1; +}; + +#define i_size_high i_dir_acl + +#if defined(__KERNEL__) || defined(__linux__) +#define i_reserved1 osd1.linux1.l_i_reserved1 +#define i_frag osd2.linux2.l_i_frag +#define i_fsize osd2.linux2.l_i_fsize +#define i_file_acl_high osd2.linux2.l_i_file_acl_high +#define i_uid_low i_uid +#define i_gid_low i_gid +#define i_uid_high osd2.linux2.l_i_uid_high +#define i_gid_high osd2.linux2.l_i_gid_high +#define i_reserved2 osd2.linux2.l_i_reserved2 + +#elif defined(__GNU__) + +#define i_translator osd1.hurd1.h_i_translator +#define i_frag osd2.hurd2.h_i_frag; +#define i_fsize osd2.hurd2.h_i_fsize; +#define i_uid_high osd2.hurd2.h_i_uid_high +#define i_gid_high osd2.hurd2.h_i_gid_high +#define i_author osd2.hurd2.h_i_author + +#elif defined(__masix__) + +#define i_reserved1 osd1.masix1.m_i_reserved1 +#define i_frag osd2.masix2.m_i_frag +#define i_fsize osd2.masix2.m_i_fsize +#define i_file_acl_high osd2.masix2.m_i_file_acl_high +#define i_reserved2 osd2.masix2.m_i_reserved2 + +#endif /* defined(__KERNEL__) || defined(__linux__) */ + +/* + * File system states + */ +#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT4_ERROR_FS 0x0002 /* Errors detected */ +#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */ + +/* + * Mount flags + */ +#define EXT4_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ +#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT4_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ +#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */ +#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ + +/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ +#ifndef _LINUX_EXT2_FS_H +#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt +#define set_opt(o, opt) o |= EXT4_MOUNT_##opt +#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ + EXT4_MOUNT_##opt) +#else +#define EXT2_MOUNT_NOLOAD EXT4_MOUNT_NOLOAD +#define EXT2_MOUNT_ABORT EXT4_MOUNT_ABORT +#define EXT2_MOUNT_DATA_FLAGS EXT4_MOUNT_DATA_FLAGS +#endif + +#define ext4_set_bit ext2_set_bit +#define ext4_set_bit_atomic ext2_set_bit_atomic +#define ext4_clear_bit ext2_clear_bit +#define ext4_clear_bit_atomic ext2_clear_bit_atomic +#define ext4_test_bit ext2_test_bit +#define ext4_find_first_zero_bit ext2_find_first_zero_bit +#define ext4_find_next_zero_bit ext2_find_next_zero_bit + +/* + * Maximal mount counts between two filesystem checks + */ +#define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */ + +/* + * Behaviour when detecting errors + */ +#define EXT4_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT4_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT4_ERRORS_PANIC 3 /* Panic */ +#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE + +/* + * Structure of the super block + */ +struct ext4_super_block { +/*00*/ __le32 s_inodes_count; /* Inodes count */ + __le32 s_blocks_count; /* Blocks count */ + __le32 s_r_blocks_count; /* Reserved blocks count */ + __le32 s_free_blocks_count; /* Free blocks count */ +/*10*/ __le32 s_free_inodes_count; /* Free inodes count */ + __le32 s_first_data_block; /* First Data Block */ + __le32 s_log_block_size; /* Block size */ + __le32 s_log_frag_size; /* Fragment size */ +/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ + __le32 s_frags_per_group; /* # Fragments per group */ + __le32 s_inodes_per_group; /* # Inodes per group */ + __le32 s_mtime; /* Mount time */ +/*30*/ __le32 s_wtime; /* Write time */ + __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_magic; /* Magic signature */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le16 s_minor_rev_level; /* minor revision level */ +/*40*/ __le32 s_lastcheck; /* time of last check */ + __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le32 s_rev_level; /* Revision level */ +/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + /* + * These fields are for EXT4_DYNAMIC_REV superblocks only. + * + * Note: the difference between the compatible feature set and + * the incompatible feature set is that if there is a bit set + * in the incompatible feature set that the kernel doesn't + * know about, it should refuse to mount the filesystem. + * + * e2fsck's requirements are more strict; if it doesn't know + * about a feature in either the compatible or incompatible + * feature set, it must abort and not try to meddle with + * things it doesn't understand... + */ + __le32 s_first_ino; /* First non-reserved inode */ + __le16 s_inode_size; /* size of inode structure */ + __le16 s_block_group_nr; /* block group # of this superblock */ + __le32 s_feature_compat; /* compatible feature set */ +/*60*/ __le32 s_feature_incompat; /* incompatible feature set */ + __le32 s_feature_ro_compat; /* readonly-compatible feature set */ +/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*78*/ char s_volume_name[16]; /* volume name */ +/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ + /* + * Performance hints. Directory preallocation should only + * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. + */ + __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ + __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ + __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ + /* + * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set. + */ +/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ +/*E0*/ __le32 s_journal_inum; /* inode number of journal file */ + __le32 s_journal_dev; /* device number of journal file */ + __le32 s_last_orphan; /* start of list of inodes to delete */ + __le32 s_hash_seed[4]; /* HTREE hash seed */ + __u8 s_def_hash_version; /* Default hash version to use */ + __u8 s_reserved_char_pad; + __le16 s_desc_size; /* size of group descriptor */ +/*100*/ __le32 s_default_mount_opts; + __le32 s_first_meta_bg; /* First metablock block group */ + __le32 s_mkfs_time; /* When the filesystem was created */ + __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ + /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */ +/*150*/ __le32 s_blocks_count_hi; /* Blocks count */ + __le32 s_r_blocks_count_hi; /* Reserved blocks count */ + __le32 s_free_blocks_count_hi; /* Free blocks count */ + __u32 s_reserved[169]; /* Padding to the end of the block */ +}; + +#ifdef __KERNEL__ +static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} +static inline struct ext4_inode_info *EXT4_I(struct inode *inode) +{ + return container_of(inode, struct ext4_inode_info, vfs_inode); +} + +static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) +{ + return ino == EXT4_ROOT_INO || + ino == EXT4_JOURNAL_INO || + ino == EXT4_RESIZE_INO || + (ino >= EXT4_FIRST_INO(sb) && + ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); +} +#else +/* Assume that user mode programs are passing in an ext4fs superblock, not + * a kernel struct super_block. This will allow us to call the feature-test + * macros from user land. */ +#define EXT4_SB(sb) (sb) +#endif + +#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime + +/* + * Codes for operating systems + */ +#define EXT4_OS_LINUX 0 +#define EXT4_OS_HURD 1 +#define EXT4_OS_MASIX 2 +#define EXT4_OS_FREEBSD 3 +#define EXT4_OS_LITES 4 + +/* + * Revision levels + */ +#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ + +#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV +#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV + +#define EXT4_GOOD_OLD_INODE_SIZE 128 + +/* + * Feature set definitions + */ + +#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT4_SET_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 +#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 + +#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_INCOMPAT_COMPRESSION 0x0001 +#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ +#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ +#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 +#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ +#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 + +#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ + EXT4_FEATURE_INCOMPAT_RECOVER| \ + EXT4_FEATURE_INCOMPAT_META_BG| \ + EXT4_FEATURE_INCOMPAT_EXTENTS| \ + 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_BTREE_DIR) + +/* + * Default values for user and/or group using reserved blocks + */ +#define EXT4_DEF_RESUID 0 +#define EXT4_DEF_RESGID 0 + +/* + * Default mount options + */ +#define EXT4_DEFM_DEBUG 0x0001 +#define EXT4_DEFM_BSDGROUPS 0x0002 +#define EXT4_DEFM_XATTR_USER 0x0004 +#define EXT4_DEFM_ACL 0x0008 +#define EXT4_DEFM_UID16 0x0010 +#define EXT4_DEFM_JMODE 0x0060 +#define EXT4_DEFM_JMODE_DATA 0x0020 +#define EXT4_DEFM_JMODE_ORDERED 0x0040 +#define EXT4_DEFM_JMODE_WBACK 0x0060 + +/* + * Structure of a directory entry + */ +#define EXT4_NAME_LEN 255 + +struct ext4_dir_entry { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __le16 name_len; /* Name length */ + char name[EXT4_NAME_LEN]; /* File name */ +}; + +/* + * The new version of the directory entry. Since EXT4 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct ext4_dir_entry_2 { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[EXT4_NAME_LEN]; /* File name */ +}; + +/* + * Ext4 directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +#define EXT4_FT_UNKNOWN 0 +#define EXT4_FT_REG_FILE 1 +#define EXT4_FT_DIR 2 +#define EXT4_FT_CHRDEV 3 +#define EXT4_FT_BLKDEV 4 +#define EXT4_FT_FIFO 5 +#define EXT4_FT_SOCK 6 +#define EXT4_FT_SYMLINK 7 + +#define EXT4_FT_MAX 8 + +/* + * EXT4_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 4 + */ +#define EXT4_DIR_PAD 4 +#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) +#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ + ~EXT4_DIR_ROUND) +/* + * Hash Tree Directory indexing + * (c) Daniel Phillips, 2001 + */ + +#ifdef CONFIG_EXT4_INDEX + #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT4_FEATURE_COMPAT_DIR_INDEX) && \ + (EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) +#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) +#else + #define is_dx(dir) 0 +#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) +#endif + +/* Legal values for the dx_root hash_version field: */ + +#define DX_HASH_LEGACY 0 +#define DX_HASH_HALF_MD4 1 +#define DX_HASH_TEA 2 + +#ifdef __KERNEL__ + +/* hash info structure used by the directory hash */ +struct dx_hash_info +{ + u32 hash; + u32 minor_hash; + int hash_version; + u32 *seed; +}; + +#define EXT4_HTREE_EOF 0x7fffffff + +/* + * Control parameters used by ext4_htree_next_block + */ +#define HASH_NB_ALWAYS 1 + + +/* + * Describe an inode's exact location on disk and in memory + */ +struct ext4_iloc +{ + struct buffer_head *bh; + unsigned long offset; + unsigned long block_group; +}; + +static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) +{ + return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); +} + +/* + * This structure is stuffed into the struct file's private_data field + * for directories. It is where we put information so that we can do + * readdir operations in hash tree order. + */ +struct dir_private_info { + struct rb_root root; + struct rb_node *curr_node; + struct fname *extra_fname; + loff_t last_pos; + __u32 curr_hash; + __u32 curr_minor_hash; + __u32 next_hash; +}; + +/* calculate the first block number of the group */ +static inline ext4_fsblk_t +ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); +} + +/* + * Special error return code only used by dx_probe() and its callers. + */ +#define ERR_BAD_DX_DIR -75000 + +void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, + unsigned long *blockgrpp, ext4_grpblk_t *offsetp); + +/* + * Function prototypes + */ + +/* + * Ok, these declarations are also in <linux/kernel.h> but none of the + * ext4 source programs needs to include it so they are duplicated here. + */ +# define NORET_TYPE /**/ +# define ATTRIB_NORET __attribute__((noreturn)) +# define NORET_AND noreturn, + +/* balloc.c */ +extern unsigned int ext4_block_group(struct super_block *sb, + ext4_fsblk_t blocknr); +extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, + ext4_fsblk_t blocknr); +extern int ext4_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group); +extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int *errp); +extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp); +extern void ext4_free_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count); +extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, + ext4_fsblk_t block, unsigned long count, + unsigned long *pdquot_freed_blocks); +extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *); +extern void ext4_check_blocks_bitmap (struct super_block *); +extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh); +extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext4_init_block_alloc_info(struct inode *); +extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv); + +/* dir.c */ +extern int ext4_check_dir_entry(const char *, struct inode *, + struct ext4_dir_entry_2 *, + struct buffer_head *, unsigned long); +extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, + __u32 minor_hash, + struct ext4_dir_entry_2 *dirent); +extern void ext4_htree_free_dir_info(struct dir_private_info *p); + +/* fsync.c */ +extern int ext4_sync_file (struct file *, struct dentry *, int); + +/* hash.c */ +extern int ext4fs_dirhash(const char *name, int len, struct + dx_hash_info *hinfo); + +/* ialloc.c */ +extern struct inode * ext4_new_inode (handle_t *, struct inode *, int); +extern void ext4_free_inode (handle_t *, struct inode *); +extern struct inode * ext4_orphan_get (struct super_block *, unsigned long); +extern unsigned long ext4_count_free_inodes (struct super_block *); +extern unsigned long ext4_count_dirs (struct super_block *); +extern void ext4_check_inodes_bitmap (struct super_block *); +extern unsigned long ext4_count_free (struct buffer_head *, unsigned); + + +/* inode.c */ +int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t blocknr); +struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *); +int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, + sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, + int create, int extend_disksize); + +extern void ext4_read_inode (struct inode *); +extern int ext4_write_inode (struct inode *, int); +extern int ext4_setattr (struct dentry *, struct iattr *); +extern void ext4_delete_inode (struct inode *); +extern int ext4_sync_inode (handle_t *, struct inode *); +extern void ext4_discard_reservation (struct inode *); +extern void ext4_dirty_inode(struct inode *); +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_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, + struct address_space *mapping, loff_t from); + +/* ioctl.c */ +extern int ext4_ioctl (struct inode *, struct file *, unsigned int, + unsigned long); +extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long); + +/* namei.c */ +extern int ext4_orphan_add(handle_t *, struct inode *); +extern int ext4_orphan_del(handle_t *, struct inode *); +extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, + __u32 start_minor_hash, __u32 *next_hash); + +/* resize.c */ +extern int ext4_group_add(struct super_block *sb, + struct ext4_new_group_data *input); +extern int ext4_group_extend(struct super_block *sb, + struct ext4_super_block *es, + ext4_fsblk_t n_blocks_count); + +/* super.c */ +extern void ext4_error (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void __ext4_std_error (struct super_block *, const char *, int); +extern void ext4_abort (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext4_warning (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext4_update_dynamic_rev (struct super_block *sb); +extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, + struct ext4_group_desc *bg); +extern void ext4_block_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_table_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); + +static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | + le32_to_cpu(es->s_blocks_count); +} + +static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) | + le32_to_cpu(es->s_r_blocks_count); +} + +static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) | + le32_to_cpu(es->s_free_blocks_count); +} + +static inline void ext4_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_blocks_count = cpu_to_le32((u32)blk); + es->s_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_free_blocks_count = cpu_to_le32((u32)blk); + es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_r_blocks_count = cpu_to_le32((u32)blk); + es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); +} + + + +#define ext4_std_error(sb, errno) \ +do { \ + if ((errno)) \ + __ext4_std_error((sb), __FUNCTION__, (errno)); \ +} while (0) + +/* + * Inodes and files operations + */ + +/* dir.c */ +extern const struct file_operations ext4_dir_operations; + +/* file.c */ +extern struct inode_operations ext4_file_inode_operations; +extern const struct file_operations ext4_file_operations; + +/* namei.c */ +extern struct inode_operations ext4_dir_inode_operations; +extern struct inode_operations ext4_special_inode_operations; + +/* symlink.c */ +extern struct inode_operations ext4_symlink_inode_operations; +extern struct inode_operations ext4_fast_symlink_inode_operations; + +/* extents.c */ +extern int ext4_ext_tree_init(handle_t *handle, struct inode *); +extern int ext4_ext_writepage_trans_blocks(struct inode *, int); +extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t iblock, + unsigned long max_blocks, struct buffer_head *bh_result, + int create, int extend_disksize); +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 *); +static inline int +ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, + unsigned long max_blocks, struct buffer_head *bh, + int create, int extend_disksize) +{ + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_get_blocks(handle, inode, block, max_blocks, + bh, create, extend_disksize); + return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh, + create, extend_disksize); +} + + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EXT4_FS_H */ diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h new file mode 100644 index 00000000000..a41cc24568c --- /dev/null +++ b/include/linux/ext4_fs_extents.h @@ -0,0 +1,198 @@ +/* + * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com + * Written by Alex Tomas <alex@clusterfs.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. + * + * 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 Licens + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- + */ + +#ifndef _LINUX_EXT4_EXTENTS +#define _LINUX_EXT4_EXTENTS + +#include <linux/ext4_fs.h> + +/* + * With AGRESSIVE_TEST defined, the capacity of index/leaf blocks + * becomes very small, so index split, in-depth growing and + * other hard changes happen much more often. + * This is for debug purposes only. + */ +#define AGRESSIVE_TEST_ + +/* + * With EXTENTS_STATS defined, the number of blocks and extents + * are collected in the truncate path. They'll be shown at + * umount time. + */ +#define EXTENTS_STATS__ + +/* + * If CHECK_BINSEARCH is defined, then the results of the binary search + * will also be checked by linear search. + */ +#define CHECK_BINSEARCH__ + +/* + * If EXT_DEBUG is defined you can use the 'extdebug' mount option + * to get lots of info about what's going on. + */ +#define EXT_DEBUG__ +#ifdef EXT_DEBUG +#define ext_debug(a...) printk(a) +#else +#define ext_debug(a...) +#endif + +/* + * If EXT_STATS is defined then stats numbers are collected. + * These number will be displayed at umount time. + */ +#define EXT_STATS_ + + +/* + * ext4_inode has i_block array (60 bytes total). + * The first 12 bytes store ext4_extent_header; + * the remainder stores an array of ext4_extent. + */ + +/* + * This is the extent on-disk structure. + * It's used at the bottom of the tree. + */ +struct ext4_extent { + __le32 ee_block; /* first logical block extent covers */ + __le16 ee_len; /* number of blocks covered by extent */ + __le16 ee_start_hi; /* high 16 bits of physical block */ + __le32 ee_start; /* low 32 bits of physical block */ +}; + +/* + * This is index on-disk structure. + * It's used at all the levels except the bottom. + */ +struct ext4_extent_idx { + __le32 ei_block; /* index covers logical blocks from 'block' */ + __le32 ei_leaf; /* pointer to the physical block of the next * + * level. leaf or next index could be there */ + __le16 ei_leaf_hi; /* high 16 bits of physical block */ + __u16 ei_unused; +}; + +/* + * Each block (leaves and indexes), even inode-stored has header. + */ +struct ext4_extent_header { + __le16 eh_magic; /* probably will support different formats */ + __le16 eh_entries; /* number of valid entries */ + __le16 eh_max; /* capacity of store in entries */ + __le16 eh_depth; /* has tree real underlying blocks? */ + __le32 eh_generation; /* generation of the tree */ +}; + +#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) + +/* + * Array of ext4_ext_path contains path to some extent. + * Creation/lookup routines use it for traversal/splitting/etc. + * Truncate uses it to simulate recursive walking. + */ +struct ext4_ext_path { + ext4_fsblk_t p_block; + __u16 p_depth; + struct ext4_extent *p_ext; + struct ext4_extent_idx *p_idx; + struct ext4_extent_header *p_hdr; + struct buffer_head *p_bh; +}; + +/* + * structure for external API + */ + +#define EXT4_EXT_CACHE_NO 0 +#define EXT4_EXT_CACHE_GAP 1 +#define EXT4_EXT_CACHE_EXTENT 2 + +/* + * to be called by ext4_ext_walk_space() + * negative retcode - error + * positive retcode - signal for ext4_ext_walk_space(), see below + * callback must return valid extent (passed or newly created) + */ +typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, + struct ext4_ext_cache *, + void *); + +#define EXT_CONTINUE 0 +#define EXT_BREAK 1 +#define EXT_REPEAT 2 + + +#define EXT_MAX_BLOCK 0xffffffff + +#define EXT_MAX_LEN ((1UL << 15) - 1) + + +#define EXT_FIRST_EXTENT(__hdr__) \ + ((struct ext4_extent *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_FIRST_INDEX(__hdr__) \ + ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_HAS_FREE_INDEX(__path__) \ + (le16_to_cpu((__path__)->p_hdr->eh_entries) \ + < le16_to_cpu((__path__)->p_hdr->eh_max)) +#define EXT_LAST_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_LAST_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_MAX_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) +#define EXT_MAX_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) + +static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) +{ + return (struct ext4_extent_header *) EXT4_I(inode)->i_data; +} + +static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh) +{ + return (struct ext4_extent_header *) bh->b_data; +} + +static inline unsigned short ext_depth(struct inode *inode) +{ + return le16_to_cpu(ext_inode_hdr(inode)->eh_depth); +} + +static inline void ext4_ext_tree_changed(struct inode *inode) +{ + EXT4_I(inode)->i_ext_generation++; +} + +static inline void +ext4_ext_invalidate_cache(struct inode *inode) +{ + EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO; +} + +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_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 *); +extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *); + +#endif /* _LINUX_EXT4_EXTENTS */ + diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h new file mode 100644 index 00000000000..bb42379cb7f --- /dev/null +++ b/include/linux/ext4_fs_i.h @@ -0,0 +1,158 @@ +/* + * linux/include/linux/ext4_fs_i.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_i.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_I +#define _LINUX_EXT4_FS_I + +#include <linux/rwsem.h> +#include <linux/rbtree.h> +#include <linux/seqlock.h> +#include <linux/mutex.h> + +/* data type for block offset of block group */ +typedef int ext4_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long long ext4_fsblk_t; + +struct ext4_reserve_window { + ext4_fsblk_t _rsv_start; /* First byte reserved */ + ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext4_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext4_reserve_window rsv_window; +}; + +struct ext4_block_alloc_info { + /* information about reservation window */ + struct ext4_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext4_inode_info + * is the logical (file-relative) number of the + * most-recently-allocated block in this file. + * We use this for detecting linearly ascending allocation requests. + */ + __u32 last_alloc_logical_block; + /* + * Was i_next_alloc_goal in ext4_inode_info + * is the *physical* companion to i_next_alloc_block. + * it the the physical block number of the block which was most-recentl + * allocated to this file. This give us the goal (target) for the next + * allocation when we detect linearly ascending requests. + */ + ext4_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end + +/* + * storage for cached extent + */ +struct ext4_ext_cache { + ext4_fsblk_t ec_start; + __u32 ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; +}; + +/* + * third extended file system inode data in memory + */ +struct ext4_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; +#ifdef EXT4_FRAGMENTS + __u32 i_faddr; + __u8 i_frag_no; + __u8 i_frag_size; +#endif + ext4_fsblk_t i_file_acl; + __u32 i_dir_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is ued for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + __u32 i_block_group; + __u32 i_state; /* Dynamic state flags for ext4 */ + + /* block reservation info */ + struct ext4_block_alloc_info *i_block_alloc_info; + + __u32 i_dir_start_lookup; +#ifdef CONFIG_EXT4DEV_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext4_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext4_get_block (growth) and ext4_truncate (shrinkth). + */ + loff_t i_disksize; + + /* on-disk additional length */ + __u16 i_extra_isize; + + /* + * truncate_mutex is for serialising ext4_truncate() against + * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext4 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have truncate_mutex. + */ + struct mutex truncate_mutex; + struct inode vfs_inode; + + unsigned long i_ext_generation; + struct ext4_ext_cache i_cached_extent; +}; + +#endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h new file mode 100644 index 00000000000..691a713139c --- /dev/null +++ b/include/linux/ext4_fs_sb.h @@ -0,0 +1,94 @@ +/* + * linux/include/linux/ext4_fs_sb.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_sb.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_SB +#define _LINUX_EXT4_FS_SB + +#ifdef __KERNEL__ +#include <linux/timer.h> +#include <linux/wait.h> +#include <linux/blockgroup_lock.h> +#include <linux/percpu_counter.h> +#endif +#include <linux/rbtree.h> + +/* + * third extended-fs super-block data in memory + */ +struct ext4_sb_info { + unsigned long s_frag_size; /* Size of a fragment in bytes */ + unsigned long s_desc_size; /* Size of a group descriptor in bytes */ + unsigned long s_frags_per_block;/* Number of fragments per block */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_frags_per_group;/* Number of fragments in a group */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + unsigned long s_gdb_count; /* Number of group descriptor blocks */ + unsigned long s_desc_per_block; /* Number of group descriptors per block */ + unsigned long s_groups_count; /* Number of groups in the fs */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */ + struct buffer_head ** s_group_desc; + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + u32 s_hash_seed[4]; + int s_def_hash_version; + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct blockgroup_lock s_blockgroup_lock; + + /* root of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct rb_root s_rsv_window_root; + struct ext4_reserve_window_node s_rsv_window_head; + + /* Journaling */ + struct inode * s_journal_inode; + struct journal_s * s_journal; + struct list_head s_orphan; + unsigned long s_commit_interval; + struct block_device *journal_bdev; +#ifdef CONFIG_JBD_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 +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif + +#ifdef EXTENTS_STATS + /* ext4 extents stats */ + unsigned long s_ext_min; + unsigned long s_ext_max; + unsigned long s_depth_max; + spinlock_t s_ext_stats_lock; + unsigned long s_ext_blocks; + unsigned long s_ext_extents; +#endif +}; + +#endif /* _LINUX_EXT4_FS_SB */ diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h new file mode 100644 index 00000000000..72dd631912e --- /dev/null +++ b/include/linux/ext4_jbd2.h @@ -0,0 +1,273 @@ +/* + * linux/include/linux/ext4_jbd2.h + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1998--1999 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Ext4-specific journaling extensions. + */ + +#ifndef _LINUX_EXT4_JBD_H +#define _LINUX_EXT4_JBD_H + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> + +#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) + +/* Define the number of blocks we need to account to a transaction to + * modify one block of data. + * + * We may have to touch one inode, one bitmap buffer, up to three + * indirection blocks, the group and superblock summaries, and the data + * block to complete the transaction. + * + * For extents-enabled fs we may have to allocate and modify up to + * 5 levels of tree + root which are stored in the inode. */ + +#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ + (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ + || test_opt(sb, EXTENTS) ? 27U : 8U) + +/* Extended attribute operations touch at most two data buffers, + * two bitmap buffers, and two group summaries, in addition to the inode + * and the superblock, which are already accounted for. */ + +#define EXT4_XATTR_TRANS_BLOCKS 6U + +/* Define the minimum size for a transaction which modifies data. This + * needs to take into account the fact that we may end up modifying two + * quota files too (one for the group, one for the user quota). The + * superblock only gets updated once, of course, so don't bother + * counting that again for the quota updates. */ + +#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ + EXT4_XATTR_TRANS_BLOCKS - 2 + \ + 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) + +/* Delete operations potentially hit one directory's namespace plus an + * entire inode, plus arbitrary amounts of bitmap/indirection data. Be + * generous. We can grow the delete transaction later if necessary. */ + +#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64) + +/* Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * write(2) and truncate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. */ + +#define EXT4_MAX_TRANS_DATA 64U + +/* We break up a large truncate or write transaction once the handle's + * buffer credits gets this low, we need either to extend the + * transaction or to start a new one. Reserve enough space here for + * inode, bitmap, superblock, group and indirection updates for at least + * one block, plus two quota updates. Quota allocations are not + * needed. */ + +#define EXT4_RESERVE_TRANS_BLOCKS 12U + +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 + +#ifdef CONFIG_QUOTA +/* Amount of blocks needed for quota update - we know that the structure was + * allocated so we need to update only inode+data */ +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +/* Amount of blocks needed for quota insert/delete - we do some block writes + * but inode, sb and group updates are done only once */ +#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) +#else +#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT4_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT4_QUOTA_DEL_BLOCKS(sb) 0 +#endif + +int +ext4_mark_iloc_dirty(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc); + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc); + +int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); + +/* + * Wrapper functions with which ext4 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext4 can control + * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't + * been done yet. + */ + +void ext4_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); + +static inline int +__ext4_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = jbd2_journal_get_undo_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = jbd2_journal_get_write_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline void +ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +{ + jbd2_journal_release_buffer(handle, bh); +} + +static inline int +__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_forget(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_revoke(const char *where, handle_t *handle, + ext4_fsblk_t blocknr, struct buffer_head *bh) +{ + int err = jbd2_journal_revoke(handle, blocknr, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_get_create_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_dirty_metadata(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + + +#define ext4_journal_get_undo_access(handle, bh) \ + __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_get_write_access(handle, bh) \ + __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_revoke(handle, blocknr, bh) \ + __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) +#define ext4_journal_get_create_access(handle, bh) \ + __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_dirty_metadata(handle, bh) \ + __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) +#define ext4_journal_forget(handle, bh) \ + __ext4_journal_forget(__FUNCTION__, (handle), (bh)) + +int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); + +handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); +int __ext4_journal_stop(const char *where, handle_t *handle); + +static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) +{ + return ext4_journal_start_sb(inode->i_sb, nblocks); +} + +#define ext4_journal_stop(handle) \ + __ext4_journal_stop(__FUNCTION__, (handle)) + +static inline handle_t *ext4_journal_current_handle(void) +{ + return journal_current_handle(); +} + +static inline int ext4_journal_extend(handle_t *handle, int nblocks) +{ + return jbd2_journal_extend(handle, nblocks); +} + +static inline int ext4_journal_restart(handle_t *handle, int nblocks) +{ + return jbd2_journal_restart(handle, nblocks); +} + +static inline int ext4_journal_blocks_per_page(struct inode *inode) +{ + return jbd2_journal_blocks_per_page(inode); +} + +static inline int ext4_journal_force_commit(journal_t *journal) +{ + return jbd2_journal_force_commit(journal); +} + +/* super.c */ +int ext4_force_commit(struct super_block *sb); + +static inline int ext4_should_journal_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 1; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + return 1; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 1; + return 0; +} + +static inline int ext4_should_order_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + return 1; + return 0; +} + +static inline int ext4_should_writeback_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + return 1; + return 0; +} + +#endif /* _LINUX_EXT4_JBD_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c25a38d8f60..5081d27bfa2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user * 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); +void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); diff --git a/include/linux/io.h b/include/linux/io.h index 2ad96c3f0e4..81877ea3930 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -28,4 +28,31 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); int ioremap_page_range(unsigned long addr, unsigned long end, unsigned long phys_addr, pgprot_t prot); +/** + * check_signature - find BIOS signatures + * @io_addr: mmio address to check + * @signature: signature block + * @length: length of signature + * + * Perform a signature comparison with the mmio address io_addr. This + * address should have been obtained by ioremap. + * Returns 1 on a match. + */ + +static inline int check_signature(const volatile void __iomem *io_addr, + const unsigned char *signature, int length) +{ + int retval = 0; + do { + if (readb(io_addr) != *signature) + goto out; + io_addr++; + signature++; + length--; + } while (length); + retval = 1; +out: + return retval; +} + #endif /* _LINUX_IO_H */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h new file mode 100644 index 00000000000..ddb12879578 --- /dev/null +++ b/include/linux/jbd2.h @@ -0,0 +1,1107 @@ +/* + * linux/include/linux/jbd2.h + * + * Written by Stephen C. Tweedie <sct@redhat.com> + * + * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Definitions for transaction data structures for the buffer cache + * filesystem journaling support. + */ + +#ifndef _LINUX_JBD_H +#define _LINUX_JBD_H + +/* Allow this file to be included directly into e2fsprogs */ +#ifndef __KERNEL__ +#include "jfs_compat.h" +#define JBD2_DEBUG +#define jfs_debug jbd_debug +#else + +#include <linux/types.h> +#include <linux/buffer_head.h> +#include <linux/journal-head.h> +#include <linux/stddef.h> +#include <linux/bit_spinlock.h> +#include <linux/mutex.h> +#include <linux/timer.h> + +#include <asm/semaphore.h> +#endif + +#define journal_oom_retry 1 + +/* + * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * certain classes of error which can occur due to failed IOs. Under + * normal use we want ext3 to continue after such errors, because + * hardware _can_ fail, but for debugging purposes when running tests on + * known-good hardware we may want to trap these errors. + */ +#undef JBD_PARANOID_IOFAIL + +/* + * The default maximum commit age, in seconds. + */ +#define JBD_DEFAULT_MAX_COMMIT_AGE 5 + +#ifdef CONFIG_JBD_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. + */ +#define JBD_EXPENSIVE_CHECKING +extern int jbd2_journal_enable_debug; + +#define jbd_debug(n, f, a...) \ + do { \ + if ((n) <= jbd2_journal_enable_debug) { \ + printk (KERN_DEBUG "(%s, %d): %s: ", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (f, ## a); \ + } \ + } while (0) +#else +#define jbd_debug(f, a...) /**/ +#endif + +extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry); +extern void * jbd2_slab_alloc(size_t size, gfp_t flags); +extern void jbd2_slab_free(void *ptr, size_t size); + +#define jbd_kmalloc(size, flags) \ + __jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) +#define jbd_rep_kmalloc(size, flags) \ + __jbd2_kmalloc(__FUNCTION__, (size), (flags), 1) + +#define JBD2_MIN_JOURNAL_BLOCKS 1024 + +#ifdef __KERNEL__ + +/** + * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. + * + * All filesystem modifications made by the process go + * through this handle. Recursive operations (such as quota operations) + * are gathered into a single update. + * + * The buffer credits field is used to account for journaled buffers + * being modified by the running process. To ensure that there is + * enough log space for all outstanding operations, we need to limit the + * number of outstanding buffers possible at any time. When the + * operation completes, any buffer credits not used are credited back to + * the transaction, so that at all times we know how many buffers the + * outstanding updates on a transaction might possibly touch. + * + * This is an opaque datatype. + **/ +typedef struct handle_s handle_t; /* Atomic operation type */ + + +/** + * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. + * + * journal_t is linked to from the fs superblock structure. + * + * We use the journal_t to keep track of all outstanding transaction + * activity on the filesystem, and to manage the state of the log + * writing process. + * + * This is an opaque datatype. + **/ +typedef struct journal_s journal_t; /* Journal control structure */ +#endif + +/* + * Internal structures used by the logging mechanism: + */ + +#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ + +/* + * On-disk structures + */ + +/* + * Descriptor block types: + */ + +#define JBD2_DESCRIPTOR_BLOCK 1 +#define JBD2_COMMIT_BLOCK 2 +#define JBD2_SUPERBLOCK_V1 3 +#define JBD2_SUPERBLOCK_V2 4 +#define JBD2_REVOKE_BLOCK 5 + +/* + * Standard header for all descriptor blocks: + */ +typedef struct journal_header_s +{ + __be32 h_magic; + __be32 h_blocktype; + __be32 h_sequence; +} journal_header_t; + + +/* + * The block tag: used to describe a single buffer in the journal. + * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this + * raw struct shouldn't be used for pointer math or sizeof() - use + * journal_tag_bytes(journal) instead to compute this. + */ +typedef struct journal_block_tag_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ +} journal_block_tag_t; + +#define JBD_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) +#define JBD_TAG_SIZE64 (sizeof(journal_block_tag_t)) + +/* + * The revoke descriptor: used on disk to describe a series of blocks to + * be revoked from the log + */ +typedef struct jbd2_journal_revoke_header_s +{ + journal_header_t r_header; + __be32 r_count; /* Count of bytes used in the block */ +} jbd2_journal_revoke_header_t; + + +/* Definitions for the journal tag flags word: */ +#define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ +#define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ +#define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ +#define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ + + +/* + * The journal superblock. All fields are in big-endian byte order. + */ +typedef struct journal_superblock_s +{ +/* 0x0000 */ + journal_header_t s_header; + +/* 0x000C */ + /* Static information describing the journal */ + __be32 s_blocksize; /* journal device blocksize */ + __be32 s_maxlen; /* total blocks in journal file */ + __be32 s_first; /* first block of log information */ + +/* 0x0018 */ + /* Dynamic information describing the current state of the log */ + __be32 s_sequence; /* first commit ID expected in log */ + __be32 s_start; /* blocknr of start of log */ + +/* 0x0020 */ + /* Error value, as set by jbd2_journal_abort(). */ + __be32 s_errno; + +/* 0x0024 */ + /* Remaining fields are only valid in a version-2 superblock */ + __be32 s_feature_compat; /* compatible feature set */ + __be32 s_feature_incompat; /* incompatible feature set */ + __be32 s_feature_ro_compat; /* readonly-compatible feature set */ +/* 0x0030 */ + __u8 s_uuid[16]; /* 128-bit uuid for journal */ + +/* 0x0040 */ + __be32 s_nr_users; /* Nr of filesystems sharing log */ + + __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ + +/* 0x0048 */ + __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ + __be32 s_max_trans_data; /* Limit of data blocks per trans. */ + +/* 0x0050 */ + __u32 s_padding[44]; + +/* 0x0100 */ + __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ +/* 0x0400 */ +} journal_superblock_t; + +#define JBD2_HAS_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) +#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) +#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) + +#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 +#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 + +/* Features known to this kernel version: */ +#define JBD2_KNOWN_COMPAT_FEATURES 0 +#define JBD2_KNOWN_ROCOMPAT_FEATURES 0 +#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ + JBD2_FEATURE_INCOMPAT_64BIT) + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/sched.h> + +#define JBD_ASSERTIONS +#ifdef JBD_ASSERTIONS +#define J_ASSERT(assert) \ +do { \ + if (!(assert)) { \ + printk (KERN_EMERG \ + "Assertion failure in %s() at %s:%d: \"%s\"\n", \ + __FUNCTION__, __FILE__, __LINE__, # assert); \ + BUG(); \ + } \ +} while (0) + +#if defined(CONFIG_BUFFER_DEBUG) +void buffer_assertion_failure(struct buffer_head *bh); +#define J_ASSERT_BH(bh, expr) \ + do { \ + if (!(expr)) \ + buffer_assertion_failure(bh); \ + J_ASSERT(expr); \ + } while (0) +#define J_ASSERT_JH(jh, expr) J_ASSERT_BH(jh2bh(jh), expr) +#else +#define J_ASSERT_BH(bh, expr) J_ASSERT(expr) +#define J_ASSERT_JH(jh, expr) J_ASSERT(expr) +#endif + +#else +#define J_ASSERT(assert) do { } while (0) +#endif /* JBD_ASSERTIONS */ + +#if defined(JBD_PARANOID_IOFAIL) +#define J_EXPECT(expr, why...) J_ASSERT(expr) +#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) +#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) +#else +#define __journal_expect(expr, why...) \ + ({ \ + int val = (expr); \ + if (!val) { \ + printk(KERN_ERR \ + "EXT3-fs unexpected failure: %s;\n",# expr); \ + printk(KERN_ERR why "\n"); \ + } \ + val; \ + }) +#define J_EXPECT(expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) +#endif + +enum jbd_state_bits { + BH_JBD /* Has an attached ext3 journal_head */ + = BH_PrivateStart, + BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ + BH_Freed, /* Has been freed (truncated) */ + BH_Revoked, /* Has been revoked from the log */ + BH_RevokeValid, /* Revoked flag is valid */ + BH_JBDDirty, /* Is dirty but journaled */ + BH_State, /* Pins most journal_head state */ + BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ +}; + +BUFFER_FNS(JBD, jbd) +BUFFER_FNS(JWrite, jwrite) +BUFFER_FNS(JBDDirty, jbddirty) +TAS_BUFFER_FNS(JBDDirty, jbddirty) +BUFFER_FNS(Revoked, revoked) +TAS_BUFFER_FNS(Revoked, revoked) +BUFFER_FNS(RevokeValid, revokevalid) +TAS_BUFFER_FNS(RevokeValid, revokevalid) +BUFFER_FNS(Freed, freed) + +static inline struct buffer_head *jh2bh(struct journal_head *jh) +{ + return jh->b_bh; +} + +static inline struct journal_head *bh2jh(struct buffer_head *bh) +{ + return bh->b_private; +} + +static inline void jbd_lock_bh_state(struct buffer_head *bh) +{ + bit_spin_lock(BH_State, &bh->b_state); +} + +static inline int jbd_trylock_bh_state(struct buffer_head *bh) +{ + return bit_spin_trylock(BH_State, &bh->b_state); +} + +static inline int jbd_is_locked_bh_state(struct buffer_head *bh) +{ + return bit_spin_is_locked(BH_State, &bh->b_state); +} + +static inline void jbd_unlock_bh_state(struct buffer_head *bh) +{ + bit_spin_unlock(BH_State, &bh->b_state); +} + +static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_lock(BH_JournalHead, &bh->b_state); +} + +static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_unlock(BH_JournalHead, &bh->b_state); +} + +struct jbd2_revoke_table_s; + +/** + * struct handle_s - The handle_s type is the concrete type associated with + * handle_t. + * @h_transaction: Which compound transaction is this update a part of? + * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. + * @h_ref: Reference count on this handle + * @h_err: Field for caller's use to track errors through large fs operations + * @h_sync: flag for sync-on-close + * @h_jdata: flag to force data journaling + * @h_aborted: flag indicating fatal error on handle + **/ + +/* Docbook can't yet cope with the bit fields, but will leave the documentation + * in so it can be fixed later. + */ + +struct handle_s +{ + /* Which compound transaction is this update a part of? */ + transaction_t *h_transaction; + + /* Number of remaining buffers we are allowed to dirty: */ + int h_buffer_credits; + + /* Reference count on this handle */ + int h_ref; + + /* Field for caller's use to track errors through large fs */ + /* operations */ + int h_err; + + /* Flags [no locking] */ + unsigned int h_sync: 1; /* sync-on-close */ + unsigned int h_jdata: 1; /* force data journaling */ + unsigned int h_aborted: 1; /* fatal error on handle */ +}; + + +/* The transaction_t type is the guts of the journaling mechanism. It + * tracks a compound transaction through its various states: + * + * RUNNING: accepting new updates + * LOCKED: Updates still running but we don't accept new ones + * RUNDOWN: Updates are tidying up but have finished requesting + * new buffers to modify (state not used for now) + * FLUSH: All updates complete, but we are still writing to disk + * COMMIT: All data on disk, writing commit record + * FINISHED: We still have to keep the transaction for checkpointing. + * + * The transaction keeps track of all of the buffers modified by a + * running transaction, and all of the buffers committed but not yet + * flushed to home for finished transactions. + */ + +/* + * Lock ranking: + * + * j_list_lock + * ->jbd_lock_bh_journal_head() (This is "innermost") + * + * j_state_lock + * ->jbd_lock_bh_state() + * + * jbd_lock_bh_state() + * ->j_list_lock + * + * j_state_lock + * ->t_handle_lock + * + * j_state_lock + * ->j_list_lock (journal_unmap_buffer) + * + */ + +struct transaction_s +{ + /* Pointer to the journal for this transaction. [no locking] */ + journal_t *t_journal; + + /* Sequence number for this transaction [no locking] */ + tid_t t_tid; + + /* + * Transaction's current state + * [no locking - only kjournald2 alters this] + * FIXME: needs barriers + * KLUDGE: [use j_state_lock] + */ + enum { + T_RUNNING, + T_LOCKED, + T_RUNDOWN, + T_FLUSH, + T_COMMIT, + T_FINISHED + } t_state; + + /* + * Where in the log does this transaction's commit start? [no locking] + */ + unsigned long t_log_start; + + /* Number of buffers on the t_buffers list [j_list_lock] */ + int t_nr_buffers; + + /* + * Doubly-linked circular list of all buffers reserved but not yet + * modified by this transaction [j_list_lock] + */ + struct journal_head *t_reserved_list; + + /* + * Doubly-linked circular list of all buffers under writeout during + * commit [j_list_lock] + */ + struct journal_head *t_locked_list; + + /* + * Doubly-linked circular list of all metadata buffers owned by this + * transaction [j_list_lock] + */ + struct journal_head *t_buffers; + + /* + * Doubly-linked circular list of all data buffers still to be + * flushed before this transaction can be committed [j_list_lock] + */ + struct journal_head *t_sync_datalist; + + /* + * Doubly-linked circular list of all forget buffers (superseded + * buffers which we can un-checkpoint once this transaction commits) + * [j_list_lock] + */ + struct journal_head *t_forget; + + /* + * Doubly-linked circular list of all buffers still to be flushed before + * this transaction can be checkpointed. [j_list_lock] + */ + struct journal_head *t_checkpoint_list; + + /* + * Doubly-linked circular list of all buffers submitted for IO while + * checkpointing. [j_list_lock] + */ + struct journal_head *t_checkpoint_io_list; + + /* + * Doubly-linked circular list of temporary buffers currently undergoing + * IO in the log [j_list_lock] + */ + struct journal_head *t_iobuf_list; + + /* + * Doubly-linked circular list of metadata buffers being shadowed by log + * IO. The IO buffers on the iobuf list and the shadow buffers on this + * list match each other one for one at all times. [j_list_lock] + */ + struct journal_head *t_shadow_list; + + /* + * Doubly-linked circular list of control buffers being written to the + * log. [j_list_lock] + */ + struct journal_head *t_log_list; + + /* + * Protects info related to handles + */ + spinlock_t t_handle_lock; + + /* + * Number of outstanding updates running on this transaction + * [t_handle_lock] + */ + int t_updates; + + /* + * Number of buffers reserved for use by all handles in this transaction + * handle but not yet modified. [t_handle_lock] + */ + int t_outstanding_credits; + + /* + * Forward and backward links for the circular list of all transactions + * awaiting checkpoint. [j_list_lock] + */ + transaction_t *t_cpnext, *t_cpprev; + + /* + * When will the transaction expire (become due for commit), in jiffies? + * [no locking] + */ + unsigned long t_expires; + + /* + * How many handles used this transaction? [t_handle_lock] + */ + int t_handle_count; + +}; + +/** + * struct journal_s - The journal_s type is the concrete type associated with + * journal_t. + * @j_flags: General journaling state flags + * @j_errno: Is there an outstanding uncleared error on the journal (from a + * prior abort)? + * @j_sb_buffer: First part of superblock buffer + * @j_superblock: Second part of superblock buffer + * @j_format_version: Version of the superblock format + * @j_state_lock: Protect the various scalars in the journal + * @j_barrier_count: Number of processes waiting to create a barrier lock + * @j_barrier: The barrier lock itself + * @j_running_transaction: The current running transaction.. + * @j_committing_transaction: the transaction we are pushing to disk + * @j_checkpoint_transactions: a linked circular list of all transactions + * waiting for checkpointing + * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction + * to start committing, or for a barrier lock to be released + * @j_wait_logspace: Wait queue for waiting for checkpointing to complete + * @j_wait_done_commit: Wait queue for waiting for commit to complete + * @j_wait_checkpoint: Wait queue to trigger checkpointing + * @j_wait_commit: Wait queue to trigger commit + * @j_wait_updates: Wait queue to wait for updates to complete + * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints + * @j_head: Journal head - identifies the first unused block in the journal + * @j_tail: Journal tail - identifies the oldest still-used block in the + * journal. + * @j_free: Journal free - how many free blocks are there in the journal? + * @j_first: The block number of the first usable block + * @j_last: The block number one beyond the last usable block + * @j_dev: Device where we store the journal + * @j_blocksize: blocksize for the location where we store the journal. + * @j_blk_offset: starting block offset for into the device where we store the + * journal + * @j_fs_dev: Device which holds the client fs. For internal journal this will + * be equal to j_dev + * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_list_lock: Protects the buffer lists and internal buffer state. + * @j_inode: Optional inode where we store the journal. If present, all journal + * block numbers are mapped into this inode via bmap(). + * @j_tail_sequence: Sequence number of the oldest transaction in the log + * @j_transaction_sequence: Sequence number of the next transaction to grant + * @j_commit_sequence: Sequence number of the most recently committed + * transaction + * @j_commit_request: Sequence number of the most recent transaction wanting + * commit + * @j_uuid: Uuid of client object. + * @j_task: Pointer to the current commit thread for this journal + * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a + * single compound commit transaction + * @j_commit_interval: What is the maximum transaction lifetime before we begin + * a commit? + * @j_commit_timer: The timer used to wakeup the commit thread + * @j_revoke_lock: Protect the revoke table + * @j_revoke: The revoke table - maintains the list of revoked blocks in the + * current transaction. + * @j_revoke_table: alternate revoke tables for j_revoke + * @j_wbuf: array of buffer_heads for jbd2_journal_commit_transaction + * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the + * number that will fit in j_blocksize + * @j_last_sync_writer: most recent pid which did a synchronous write + * @j_private: An opaque pointer to fs-private information. + */ + +struct journal_s +{ + /* General journaling state flags [j_state_lock] */ + unsigned long j_flags; + + /* + * Is there an outstanding uncleared error on the journal (from a prior + * abort)? [j_state_lock] + */ + int j_errno; + + /* The superblock buffer */ + struct buffer_head *j_sb_buffer; + journal_superblock_t *j_superblock; + + /* Version of the superblock format */ + int j_format_version; + + /* + * Protect the various scalars in the journal + */ + spinlock_t j_state_lock; + + /* + * Number of processes waiting to create a barrier lock [j_state_lock] + */ + int j_barrier_count; + + /* The barrier lock itself */ + struct mutex j_barrier; + + /* + * Transactions: The current running transaction... + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_running_transaction; + + /* + * the transaction we are pushing to disk + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_committing_transaction; + + /* + * ... and a linked circular list of all transactions waiting for + * checkpointing. [j_list_lock] + */ + transaction_t *j_checkpoint_transactions; + + /* + * Wait queue for waiting for a locked transaction to start committing, + * or for a barrier lock to be released + */ + wait_queue_head_t j_wait_transaction_locked; + + /* Wait queue for waiting for checkpointing to complete */ + wait_queue_head_t j_wait_logspace; + + /* Wait queue for waiting for commit to complete */ + wait_queue_head_t j_wait_done_commit; + + /* Wait queue to trigger checkpointing */ + wait_queue_head_t j_wait_checkpoint; + + /* Wait queue to trigger commit */ + wait_queue_head_t j_wait_commit; + + /* Wait queue to wait for updates to complete */ + wait_queue_head_t j_wait_updates; + + /* Semaphore for locking against concurrent checkpoints */ + struct mutex j_checkpoint_mutex; + + /* + * Journal head: identifies the first unused block in the journal. + * [j_state_lock] + */ + unsigned long j_head; + + /* + * Journal tail: identifies the oldest still-used block in the journal. + * [j_state_lock] + */ + unsigned long j_tail; + + /* + * Journal free: how many free blocks are there in the journal? + * [j_state_lock] + */ + unsigned long j_free; + + /* + * Journal start and end: the block numbers of the first usable block + * and one beyond the last usable block in the journal. [j_state_lock] + */ + unsigned long j_first; + unsigned long j_last; + + /* + * Device, blocksize and starting block offset for the location where we + * store the journal. + */ + struct block_device *j_dev; + int j_blocksize; + unsigned long long j_blk_offset; + + /* + * Device which holds the client fs. For internal journal this will be + * equal to j_dev. + */ + struct block_device *j_fs_dev; + + /* Total maximum capacity of the journal region on disk. */ + unsigned int j_maxlen; + + /* + * Protects the buffer lists and internal buffer state. + */ + spinlock_t j_list_lock; + + /* Optional inode where we store the journal. If present, all */ + /* journal block numbers are mapped into this inode via */ + /* bmap(). */ + struct inode *j_inode; + + /* + * Sequence number of the oldest transaction in the log [j_state_lock] + */ + tid_t j_tail_sequence; + + /* + * Sequence number of the next transaction to grant [j_state_lock] + */ + tid_t j_transaction_sequence; + + /* + * Sequence number of the most recently committed transaction + * [j_state_lock]. + */ + tid_t j_commit_sequence; + + /* + * Sequence number of the most recent transaction wanting commit + * [j_state_lock] + */ + tid_t j_commit_request; + + /* + * Journal uuid: identifies the object (filesystem, LVM volume etc) + * backed by this journal. This will eventually be replaced by an array + * of uuids, allowing us to index multiple devices within a single + * journal and to perform atomic updates across them. + */ + __u8 j_uuid[16]; + + /* Pointer to the current commit thread for this journal */ + struct task_struct *j_task; + + /* + * Maximum number of metadata buffers to allow in a single compound + * commit transaction + */ + int j_max_transaction_buffers; + + /* + * What is the maximum transaction lifetime before we begin a commit? + */ + unsigned long j_commit_interval; + + /* The timer used to wakeup the commit thread: */ + struct timer_list j_commit_timer; + + /* + * The revoke table: maintains the list of revoked blocks in the + * current transaction. [j_revoke_lock] + */ + spinlock_t j_revoke_lock; + struct jbd2_revoke_table_s *j_revoke; + struct jbd2_revoke_table_s *j_revoke_table[2]; + + /* + * array of bhs for jbd2_journal_commit_transaction + */ + struct buffer_head **j_wbuf; + int j_wbufsize; + + pid_t j_last_sync_writer; + + /* + * An opaque pointer to fs-private information. ext3 puts its + * superblock pointer here + */ + void *j_private; +}; + +/* + * Journal flag definitions + */ +#define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ +#define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ +#define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ +#define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ +#define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ +#define JBD2_BARRIER 0x020 /* Use IDE barriers */ + +/* + * Function declarations for the journaling transaction and buffer + * management + */ + +/* Filing buffers */ +extern void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_unfile_buffer(struct journal_head *); +extern void __jbd2_journal_refile_buffer(struct journal_head *); +extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_free_buffer(struct journal_head *bh); +extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_clean_data_list(transaction_t *transaction); + +/* Log buffer allocation */ +extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); +int jbd2_journal_next_log_block(journal_t *, unsigned long long *); + +/* Commit management */ +extern void jbd2_journal_commit_transaction(journal_t *); + +/* Checkpoint list management */ +int __jbd2_journal_clean_checkpoint_list(journal_t *journal); +int __jbd2_journal_remove_checkpoint(struct journal_head *); +void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); + +/* Buffer IO */ +extern int +jbd2_journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + struct journal_head **jh_out, + unsigned long long blocknr); + +/* Transaction locking */ +extern void __wait_on_journal (journal_t *); + +/* + * Journal locking. + * + * We need to lock the journal during transaction state changes so that nobody + * ever tries to take a handle on the running transaction while we are in the + * middle of moving it to the commit phase. j_state_lock does this. + * + * Note that the locking is completely interrupt unsafe. We never touch + * journal structures from interrupts. + */ + +static inline handle_t *journal_current_handle(void) +{ + return current->journal_info; +} + +/* The journaling code user interface: + * + * Create and destroy handles + * Register buffer modifications against the current transaction. + */ + +extern handle_t *jbd2_journal_start(journal_t *, int nblocks); +extern int jbd2_journal_restart (handle_t *, int nblocks); +extern int jbd2_journal_extend (handle_t *, int nblocks); +extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); +extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); +extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); +extern int jbd2_journal_forget (handle_t *, struct buffer_head *); +extern void journal_sync_buffer (struct buffer_head *); +extern void jbd2_journal_invalidatepage(journal_t *, + struct page *, unsigned long); +extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_stop(handle_t *); +extern int jbd2_journal_flush (journal_t *); +extern void jbd2_journal_lock_updates (journal_t *); +extern void jbd2_journal_unlock_updates (journal_t *); + +extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, + struct block_device *fs_dev, + unsigned long long start, int len, int bsize); +extern journal_t * jbd2_journal_init_inode (struct inode *); +extern int jbd2_journal_update_format (journal_t *); +extern int jbd2_journal_check_used_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_check_available_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_set_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_create (journal_t *); +extern int jbd2_journal_load (journal_t *journal); +extern void jbd2_journal_destroy (journal_t *); +extern int jbd2_journal_recover (journal_t *journal); +extern int jbd2_journal_wipe (journal_t *, int); +extern int jbd2_journal_skip_recovery (journal_t *); +extern void jbd2_journal_update_superblock (journal_t *, int); +extern void __jbd2_journal_abort_hard (journal_t *); +extern void jbd2_journal_abort (journal_t *, int); +extern int jbd2_journal_errno (journal_t *); +extern void jbd2_journal_ack_err (journal_t *); +extern int jbd2_journal_clear_err (journal_t *); +extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); +extern int jbd2_journal_force_commit(journal_t *); + +/* + * journal_head management + */ +struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); +struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); +void jbd2_journal_remove_journal_head(struct buffer_head *bh); +void jbd2_journal_put_journal_head(struct journal_head *jh); + +/* + * handle management + */ +extern kmem_cache_t *jbd2_handle_cache; + +static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) +{ + return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); +} + +static inline void jbd_free_handle(handle_t *handle) +{ + kmem_cache_free(jbd2_handle_cache, handle); +} + +/* Primary revoke support */ +#define JOURNAL_REVOKE_DEFAULT_HASH 256 +extern int jbd2_journal_init_revoke(journal_t *, int); +extern void jbd2_journal_destroy_revoke_caches(void); +extern int jbd2_journal_init_revoke_caches(void); + +extern void jbd2_journal_destroy_revoke(journal_t *); +extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); +extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); +extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *); + +/* Recovery revoke support */ +extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); +extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); +extern void jbd2_journal_clear_revoke(journal_t *); +extern void jbd2_journal_switch_revoke_table(journal_t *journal); + +/* + * The log thread user interface: + * + * Request space in the current transaction, and force transaction commit + * transitions on demand. + */ + +int __jbd2_log_space_left(journal_t *); /* Called with journal locked */ +int jbd2_log_start_commit(journal_t *journal, tid_t tid); +int __jbd2_log_start_commit(journal_t *journal, tid_t tid); +int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); +int jbd2_journal_force_commit_nested(journal_t *journal); +int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_log_do_checkpoint(journal_t *journal); + +void __jbd2_log_wait_for_space(journal_t *journal); +extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); +extern int jbd2_cleanup_journal_tail(journal_t *); + +/* Debugging code only: */ + +#define jbd_ENOSYS() \ +do { \ + printk (KERN_ERR "JBD unimplemented function %s\n", __FUNCTION__); \ + current->state = TASK_UNINTERRUPTIBLE; \ + schedule(); \ +} while (1) + +/* + * is_journal_abort + * + * Simple test wrapper function to test the JBD2_ABORT state flag. This + * bit, when set, indicates that we have had a fatal error somewhere, + * either inside the journaling layer or indicated to us by the client + * (eg. ext3), and that we and should not commit any further + * transactions. + */ + +static inline int is_journal_aborted(journal_t *journal) +{ + return journal->j_flags & JBD2_ABORT; +} + +static inline int is_handle_aborted(handle_t *handle) +{ + if (handle->h_aborted) + return 1; + return is_journal_aborted(handle->h_transaction->t_journal); +} + +static inline void jbd2_journal_abort_handle(handle_t *handle) +{ + handle->h_aborted = 1; +} + +#endif /* __KERNEL__ */ + +/* Comparison functions for transaction IDs: perform comparisons using + * modulo arithmetic so that they work over sequence number wraps. */ + +static inline int tid_gt(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference > 0); +} + +static inline int tid_geq(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference >= 0); +} + +extern int jbd2_journal_blocks_per_page(struct inode *inode); +extern size_t journal_tag_bytes(journal_t *journal); + +/* + * Return the minimum number of blocks which must be free in the journal + * before a new transaction may be started. Must be called under j_state_lock. + */ +static inline int jbd_space_needed(journal_t *journal) +{ + int nblocks = journal->j_max_transaction_buffers; + if (journal->j_committing_transaction) + nblocks += journal->j_committing_transaction-> + t_outstanding_credits; + return nblocks; +} + +/* + * Definitions which augment the buffer_head layer + */ + +/* journaling buffer types */ +#define BJ_None 0 /* Not journaled */ +#define BJ_SyncData 1 /* Normal data: flush before commit */ +#define BJ_Metadata 2 /* Normal journaled metadata */ +#define BJ_Forget 3 /* Buffer superseded by this transaction */ +#define BJ_IO 4 /* Buffer is for temporary IO use */ +#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 6 /* Buffer contains log descriptors */ +#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ +#define BJ_Locked 8 /* Locked for I/O during commit */ +#define BJ_Types 9 + +extern int jbd_blocks_per_page(struct inode *inode); + +#ifdef __KERNEL__ + +#define buffer_trace_init(bh) do {} while (0) +#define print_buffer_fields(bh) do {} while (0) +#define print_buffer_trace(bh) do {} while (0) +#define BUFFER_TRACE(bh, info) do {} while (0) +#define BUFFER_TRACE2(bh, bh2, info) do {} while (0) +#define JBUFFER_TRACE(jh, info) do {} while (0) + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_JBD_H */ diff --git a/include/linux/magic.h b/include/linux/magic.h index 22036dd2ba3..156c40fc664 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -8,6 +8,7 @@ #define EFS_SUPER_MAGIC 0x414A53 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 +#define EXT4_SUPER_MAGIC 0xEF53 #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 diff --git a/include/linux/mm.h b/include/linux/mm.h index 26146623be2..5a6068ff555 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1103,12 +1103,7 @@ static inline void vm_stat_account(struct mm_struct *mm, #ifndef CONFIG_DEBUG_PAGEALLOC static inline void -kernel_map_pages(struct page *page, int numpages, int enable) -{ - if (!PageHighMem(page) && !enable) - debug_check_no_locks_freed(page_address(page), - numpages * PAGE_SIZE); -} +kernel_map_pages(struct page *page, int numpages, int enable) {} #endif extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); diff --git a/include/linux/module.h b/include/linux/module.h index 4b2d8091a41..d1d00ce8f4e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -317,9 +317,6 @@ struct module /* Am I unsafe to unload? */ int unsafe; - /* Am I GPL-compatible */ - int license_gplok; - unsigned int taints; /* same bits as kernel:tainted */ #ifdef CONFIG_MODULE_UNLOAD diff --git a/include/linux/nbd.h b/include/linux/nbd.h index e712e7d47cc..d6b6dc09ad9 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -15,6 +15,8 @@ #ifndef LINUX_NBD_H #define LINUX_NBD_H +#include <linux/types.h> + #define NBD_SET_SOCK _IO( 0xab, 0 ) #define NBD_SET_BLKSIZE _IO( 0xab, 1 ) #define NBD_SET_SIZE _IO( 0xab, 2 ) diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 5dce5c21822..b1063e9cdb1 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * - * For details of nodemask_scnprintf() and nodemask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of nodemask_scnprintf() and nodemask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of nodelist_scnprintf() and nodelist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c. @@ -51,7 +51,7 @@ * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing - * int nodemask_parse(ubuf, ulen, mask) Parse ascii string as nodemask + * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -288,12 +288,12 @@ static inline int __nodemask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define nodemask_parse(ubuf, ulen, dst) \ - __nodemask_parse((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse(const char __user *buf, int len, +#define nodemask_parse_user(ubuf, ulen, dst) \ + __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) +static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_scnprintf(buf, len, src) \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b0ace3fd7eb..1912c6cbef5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,6 +431,10 @@ asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, int timeout); +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); asmlinkage long sys_gethostname(char __user *name, int len); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); |